Advancing Fire, Rescue & EV Safety Through Research and AI.

Super El Niño and Malaysia's Fire & Rescue Frontline

A STEMPCHEM™ Framework for Predictive Climate-Disaster Resilience

By Mohd Taufiq bin Abd Sattar

Malaysia Fire and Rescue Academy, Eastern Region, Marang, Terengganu

Abstract

Super El Niño events represent one of the most consequential climate-driven threats facing Malaysia's fire and rescue services in the twenty-first century. Prolonged drought, intensified wildfires, recurring peat fires, transboundary haze, water-supply stress, and elevated heat exposure for responders are no longer episodic disturbances-they are converging operational realities. This article examines the implications of Super El Niño from a Malaysian fire and rescue operational standpoint and proposes an integrated predictive-modelling approach built on the STEMPCHEM framework (Science, Technology, Engineering, Mathematics, Physics, Chemistry). By aligning climate science with artificial-intelligence forecasting, fire engineering, and field-level tactical doctrine, the framework offers a multidisciplinary pathway toward proactive, intelligence-led emergency management.

1. Introduction

Climate anomalies are reshaping the operational landscape of every fire and rescue service in the tropics, and Malaysia is no exception. As the planet warms and the El Niño-Southern Oscillation (ENSO) intensifies, the country is increasingly exposed to a category of climate event whose impact compounds rather than recedes: the Super El Niño.

During strong and Super El Niño phases, Malaysia routinely experiences prolonged drought, reduced rainfall, elevated ambient temperature, intensified wildfire and peat fire activity, recurring haze episodes, water-resource stress, and escalating demand on emergency response agencies. Each of these hazards alone tests operational capacity. Together, they threaten to overwhelm it.

This article advances a structured response to that challenge. It analyses the implications of Super El Niño through a Malaysian fire and rescue lens and proposes a predictive-modelling architecture grounded in the STEMPCHEM™ framework:

S — Science

T — Technology

E — Engineering

M — Mathematics

P — Physics

CHEM — Chemistry

Together, these six disciplines provide a coherent platform for integrating climate science, wildfire prediction, atmospheric monitoring, AI-assisted modelling, and operational decision-making an integration Malaysia will need if it is to stay ahead of the next extreme climate cycle.

2. Understanding Super El Niño

2.1 What Defines a Super El Niño

Super El Niño refers to an exceptionally strong warming phase of ENSO, marked by anomalous heating of sea-surface temperatures (SST) in the equatorial Pacific Ocean. This warming alters atmospheric circulation, weakens the trade winds, redistributes rainfall, and reorganises global heat transfer. Scientifically, events are commonly classified as "Super" when the Niño 3.4 SST anomaly exceeds approximately +2.0 °C.

The defining anomaly is calculated as:

2.2 ENSO Influence on Malaysia

Malaysia sits within one of the most ENSO-sensitive corridors on Earth. During El Niño phases, the country consistently experiences reduced rainfall, increased land-surface temperature, amplified urban heat-island effects, lower humidity, deteriorating air quality, and elevated hotspot formation. Domestic research has documented significant correlations between ENSO indices and temperature anomalies, an inverse relationship between ENSO intensity and rainfall, and measurable urban heat amplification during El Niño years.

The regions most exposed to these effects are peatland areas, forest reserves, agricultural zones, grasslands, and outdoor industrial storage sites-precisely the landscapes where the operational burden on fire and rescue agencies is greatest.

3. Fire & Rescue Implications in Malaysia

3.1 Increased Wildfire Frequency

Super El Niño substantially raises wildfire probability. Vegetation desiccates, fuel moisture drops, dry periods lengthen, and radiant heat exposure climbs. As ignition thresholds fall, even routine ignition sources like a discarded cigarette, an agricultural burn, a roadside spark-can trigger fast-moving fires.

For Malaysia's fire and rescue services, the operational consequences are direct and cumulative: more frequent deployments, longer suppression durations, faster resource exhaustion, earlier mutual-aid activation, and tighter inter-agency coordination demands. Fire crews increasingly fight not one incident at a time, but several across a region simultaneously.

3.2 Peat Fire Escalation

Peat fires are arguably the most hazardous fire signature of an El Niño year in Malaysia. Selangor, Pahang, Johor, Sarawak, and Sabah all carry substantial peat-fire risk. Unlike surface fires, peat fires burn underground, produce long-duration smoke, reignite repeatedly, demand vast quantities of water, and are a primary driver of regional haze events.

The physics of peat combustion is unforgiving. Heat moves by conduction through dense underground fuel layers, smouldering combustion sustains itself in oxygen-limited conditions, and thermal energy penetrates deep below the surface. The fundamental heat-transfer relationship is:

3.3 Water-Supply Crisis

During Super El Niño events, reservoir levels fall, rural water access tightens, hydrant pressures can weaken, and open water sources become scarce. Each of these has a direct operational footprint: structural firefighting, wildland suppression, relay pumping, and tanker shuttle operations all depend on reliable water. When supply contracts, tactics must adapt.

Fire and rescue agencies must therefore plan strategically: pre-positioning water tankers, identifying alternative drafting points, deploying mobile reservoir systems, and instituting water-conservation tactics on the fireground. Drought planning has become as central to readiness as equipment maintenance.

3.4 Heat Stress Among Firefighters

Rising ambient and wet-bulb temperatures during Super El Niño place firefighters under accelerating physiological load. Wearing PPE, SCBA, or wildland gear in extreme heat increases the risk of heat exhaustion, dehydration, cardiovascular strain, cognitive degradation, and decision-making fatigue. None of these are abstract concerns each one directly shapes scene safety, tactical efficiency, and command effectiveness.

Heat stress mitigation-structured, work-rest cycles, hydration protocols, rehabilitation sectors, and continuous physiological monitoring must be treated as a tactical priority on every protracted incident during dry-season operations.

3.5 Air Quality and Haze Operations

Peat fires and large-scale wildland combustion during El Niño produce significant atmospheric pollution, including PM2.5, carbon monoxide, volatile organic compounds, and a spectrum of other toxic combustion products. The downstream effects extend well beyond the fireground: public health deteriorates, visibility drops, aviation is disrupted, road traffic safety degrades, and outdoor rescue operations become more hazardous. The World Health Organization recognises ENSO as a major contributor to climate-related health emergencies, and Malaysia's haze experience consistently confirms it.

4. The STEMPCHEM™ Predictive Modelling Framework

The STEMPCHEM™ framework integrates six scientific disciplines into a single predictive architecture for climate-driven fire risk. It is designed to bridge what has traditionally been a gap between high-level climate forecasting and ground-level operational decision-making.

4.1 S — Science: Climate Integration

The scientific layer assembles the core variables that govern El Niño behaviour and its onshore consequences: SST anomaly, the Oceanic Niño Index (ONI), the Southern Oscillation Index (SOI), relative humidity, rainfall anomalies, and fuel-moisture content. Continuous monitoring of these variables enables early drought forecasting, seasonal hotspot prediction, and heatwave anticipation the upstream signals from which all downstream operational planning flows.

4.2 T — Technology: AI and Remote Sensing

Technology delivers the observational backbone. Satellite hotspot detection, UAV thermal surveillance, GIS mapping, IoT-based weather sensors, and AI-driven forecasting form an integrated sensing layer that can be coupled with national and international data sources-NASA FIRMS, MetMalaysia, Remote Automated Weather Stations (RAWS), and MODIS thermal imagery among them. Deep-learning systems trained on these data streams can identify fire-prone regions, drought intensification trends, and vegetation-stress signatures long before they manifest as ignitions.

4.3 E — Engineering: Fire Engineering Application

Engineering translates prediction into infrastructure. Hydrant reliability, water logistics, firebreak design, wildfire containment barriers, and pumping-system redundancy all sit within its scope. Simulation engineering computational fluid dynamics (CFD) for wildfire spread, heat-flux modelling, ember-transport prediction, and terrain-aware fire-dynamics analysis provides the testbed in which strategy is refined before crews ever leave the station.

4.4 M — Mathematics: Predictive Fire Spread

Mathematics quantifies what science observes. Predictive models estimate fire-spread velocity, heat-release rates, drought severity, and operational risk scores. A simplified rate-of-spread relationship captures the core dynamic:

4.5 P — Physics: Fire Behaviour

Physics governs the fire itself. Super El Niño directly modifies thermal radiation, convective heating, fuel-ignition thresholds, and atmospheric instability. Physics-based analysis brings rigour to the modelling of heat flux, flame propagation, wind-driven fire behaviour, and smoke-layer transport. Radiant heat flux is a primary driver of fire spread and firefighter exposure is described by the Stefan–Boltzmann relationship:

4.6 CHEM — Chemistry: Combustion and Atmosphere

Chemistry closes the loop. Super El Niño amplifies biomass combustion, carbon release, toxic gas production, and atmospheric particulate concentrations. The dominant combustion products CO₂, CO, NOₓ, VOCs, and PM2.5, each carry distinct toxicity profiles and atmospheric behaviours. Chemical analysis supports toxicity assessment, respiratory-risk evaluation, haze modelling, and environmental contamination studies, linking what burns on the ground to what populations breathe downwind.

5. AI-Based Predictive Modelling for Malaysia

A Malaysian implementation of the STEMPCHEM™ framework can be organised as a five-stage operational workflow:

Step 1 — Climate Monitoring

Collect ONI, SOI, SST anomaly, and rainfall-deficit indicators continuously from national and international sources.

Step 2 — Environmental Mapping

Analyse vegetation dryness, peat moisture content, and land-surface temperature across the country to produce a real-time exposure map.

Step 3 — Fire Risk Scoring

Generate district-level wildfire risk maps and dynamic hotspot probability layers that update as conditions evolve.

Step 4 — Operational Forecasting

Translate risk into requirements: anticipated resource demand, water-consumption projections, and personnel-deployment models.

Step 5 — Tactical AI Support

Integrate predictive intelligence with operational frameworks such as A.I.F.R.T.™ (Artificial Intelligence Fire & Rescue Tactics) and a Wildfire Predictive Intelligence platform, supported by UAV thermal reconnaissance for real-time field validation.

6. Integration with Malaysia Fire & Rescue Operations

The Malaysia Fire and Rescue Department (JBPM) stands to benefit directly from a system of this kind. Predictive intelligence can support seasonal preparedness, hazard zoning, pre-positioning of water tankers, air-quality emergency planning, and the activation of interstate mutual aid activities that today rely heavily on reactive judgement.

Operationally, the system can deliver a small set of high-value outputs: a daily wildfire danger index, a dynamic heat-risk map, peat-fire prediction zones, and an operational readiness dashboard. Each of these reduces uncertainty for incident commanders and gives strategic planners earlier, sharper situational awareness.

7. Future Direction

Looking ahead, Malaysia should consider developing a national AI wildfire prediction system, ENSO-integrated fire danger modelling, real-time environmental intelligence platforms, and multi-agency climate emergency coordination mechanisms. These align directly with the country's climate adaptation strategy, its national disaster resilience agenda, and the broader push toward smart emergency management. They also position the fire and rescue services not merely as responders, but as climate-resilient frontline institutions.

8. Conclusion

Super El Niño is one of the most significant climate-related operational threats facing Malaysia's fire and rescue ecosystem. Its compounding effects as drought, wildfire escalation, peat combustion, heat stress, water shortages, and haze emergencies, generate emergency-response challenges of a complexity earlier generations of firefighters did not face.

The STEMPCHEM™ framework offers a structured, multidisciplinary response. By integrating climate science, predictive modelling, fire engineering, AI intelligence, and operational strategy, Malaysia can move from a reactive posture toward a proactive disaster-management system the one which capable of anticipating Super El Niño impacts and mitigating them before they overwhelm the front line. The technology, the science, and the operational doctrine already exist. What remains is the integration and the institutional will to build it.

Flammability and Combustibility Limits: A Critical Framework for Fire Science and Modern Emergency Response

By : Mohd Taufiq Bin Abd Sattar

Abstract

The Lower Flammability Limit (LFL), Upper Flammability Limit (UFL), and stoichiometric mixture are foundational concepts in fire science, governing whether a fuel–air mixture will ignite, sustain combustion, or detonate. While these limits appear universally in fire safety references such as NFPA 325 and the International Fire Code (IFC), they are frequently treated as fixed constants,a misconception that has direct operational consequences. In reality, flammability and combustibility limits are conditional values, dependent upon ambient temperature, pressure, and oxygen concentration. This article re-examines these concepts through the STEMPCHEM™ lens integrating Science, Technology, Engineering, Mathematics, Physics, and Chemistry, and explores their operational implications for firefighting, hazardous materials (HazMat) response, electric vehicle (EV) fire incidents, hyperbaric environments, and confined space operations. The intent is to equip fire instructors, emergency responders, and researchers with a deeper, mechanism-based understanding rather than table-lookup familiarity.

Keywords: Flammability limit, combustibility limit, LFL, UFL, stoichiometric mixture, limiting oxygen concentration, ignition, vapour cloud explosion, fire science, STEMPCHEM™.

1. Introduction

Every flammable substance possesses a specific range of fuel–air concentrations within which combustion can occur. This range, bounded below by the Lower Flammability Limit (LFL) and above by the Upper Flammability Limit (UFL), is one of the most cited yet least critically examined parameters in fire science.

A common but misleading assumption is that LFL and UFL values listed in reference tables are absolute constants. They are not. The tabulated values are reported at standard reference conditions, typically 25 °C (or 20 °C), 1 atmosphere, and a normal atmospheric oxygen content of approximately 20.9 %. When any of these parameters deviate, the flammable envelope itself shifts.

This distinction is not academic. It governs the difference between a safe entry into a confined space and a fatal flash fire, between a controlled EV battery fire and a vapour cloud explosion (VCE), and between a stable hyperbaric chamber and a catastrophic enriched-oxygen ignition event.

2. Flammability versus Combustibility: A Terminological Clarification

The terms flammable and combustible are often used interchangeably, but they carry distinct technical meanings under most regulatory frameworks:

Both categories possess flammability limits when their vapours are produced and mixed with air. However:

A flammable substance can readily release ignitable vapours at ambient temperature.

A combustible substance must first be heated above its flash point before sufficient vapour is generated to fall within its flammability range.

This is why a pan of cooking oil at room temperature poses no ignition risk, but the same oil at 300 °C will ignite spontaneously, its vapour concentration finally enters the flammable envelope, and its temperature exceeds its auto-ignition point.

3. The Three Defining Concentrations

3.1 Lower Flammability Limit (LFL)

The Lower Flammability Limit is defined as the minimum concentration of vapour or gas of a flammable substance, mixed with air (containing approximately 21 % oxygen), within an open or confined space at a specified temperature and pressure, that can still sustain combustion when exposed to an ignition source.

Below the LFL, the mixture is described as “too lean to burn”, there are insufficient fuel molecules in proximity to one another to propagate a flame front, regardless of how energetic the ignition source may be.

3.2 Upper Flammability Limit (UFL)

The Upper Flammability Limit is the maximum concentration above which combustion cannot be sustained because the oxygen available is insufficient relative to the fuel present. Above the UFL, the mixture is “too rich to burn.” Critically, an above-UFL mixture is not safe, when diluted with fresh air (for example, when a fire crew opens a closed compartment containing accumulated fuel vapour), its concentration can fall back into the flammable range, producing a delayed flashback or backdraft.

3.3 Stoichiometric (Ideal) Mixture

The stoichiometric or ideal mixture represents the chemically perfect fuel-to-air ratio at which all fuel molecules react with all available oxygen molecules, with no excess of either reactant. At this point:

Flame temperature reaches its maximum

Flame propagation velocity is highest

Explosion overpressure is greatest, the most destructive condition in a vapour cloud explosion scenario

The internal combustion engine illustrates this concept clearly. The stoichiometric air–fuel ratio for petrol is 14.7 : 1 by mass, corresponding to lambda (λ) = 1.0. Modern engines deliberately operate close to this ratio under most conditions to balance power, efficiency, and emissions.

4. Representative Flammability Data

The following values are reported at standard conditions (NFPA 325):

The exceptionally wide flammability ranges of hydrogen and acetylene are why these gases are classified as extreme explosion hazards. This carries direct relevance to lithium-ion battery thermal runaway, where hydrogen is among the principal off-gassed species and placing EV fires squarely within an extreme explosion-risk profile.

5. The Conditional Nature of Flammability Limits

The most important and most often neglected principle is that LFL and UFL values are not invariant. They shift as a function of three environmental parameters.

5.1 Effect of Temperature

As ambient temperature rises:

LFL decreases (less fuel is needed to ignite, because the mixture is closer to its auto-ignition energy threshold)

UFL increases

The flammable range therefore widens

This is why a fuel that is safe at 20 °C may be hazardous at 60 °C, even without any additional vapour generation. Solar-heated storage tanks, engine compartments, and EV battery enclosures during thermal events all fall under this concern.

5.2 Effect of Pressure

At elevated pressure:

UFL increases significantly

LFL is less affected but generally decreases slightly

The flammable range therefore widens

This carries particular importance for compressed natural gas (CNG) systems, liquefied petroleum gas (LPG) installations, and pressurized hydrogen storage. A leak from a high-pressure line creates not only a wider envelope of flammability but also a higher-energy ignition condition.

5.3 Effect of Oxygen Concentration

This is the parameter most directly relevant to operational fire and rescue practice. The standard definition of LFL and UFL assumes a normal air composition of approximately 21 % oxygen.

In oxygen-deficient atmospheres (such as nitrogen-inerted tanks), no fuel concentration can sustain combustion and the flammable envelope collapses entirely.

In oxygen-enriched atmospheres (such as hyperbaric chambers operating on oxygen-rich treatment tables, or pure-oxygen medical environments), LFL decreases significantly and the range widens dramatically. Materials normally considered non-flammable, such as cotton, paper, and certain metals can ignite from minor friction or electrical sparks.

This last point cannot be overstated. The single greatest fire risk in a hyperbaric facility is not the presence of fuel, but the elevated partial pressure of oxygen, which fundamentally rewrites the flammability behaviour of every material inside the chamber.

6. Limiting Oxygen Concentration (LOC)

The natural extension of the oxygen-dependency principle is the concept of Limiting Oxygen Concentration (LOC), also known as the Minimum Oxygen Concentration (MOC). The LOC is the lowest oxygen concentration at which combustion is possible, irrespective of fuel concentration. For most hydrocarbons, the LOC lies between 10 % and 12 % oxygen by volume.

Below the LOC:

Combustion cannot occur, even if the fuel concentration falls within its normal LFL–UFL range

Even an active ignition source cannot initiate sustained burning

The LOC underpins several major fire protection strategies:

Inerting of fuel tanks and process vessels with nitrogen or carbon dioxide

Total flooding systems using CO₂ in engine rooms, server halls, and machinery spaces

Confined space entry assessment, which is why a 4-gas detector measures O₂ as well as LEL

In operational practice, the LOC reinforces a fundamental truth: suppression of fire requires either removal of fuel, removal of heat, or most often in modern engineered systems, dilution of oxygen below the LOC.

7. Operational Applications

7.1 Hazardous Materials (HazMat) Response

Gas monitoring meters used in HazMat operations typically report concentration as a percentage of the LFL (“% LEL”). The standard action thresholds are:

10 % LEL - investigation threshold; ventilation initiated

20 % LEL - evacuation threshold; ignition sources eliminated

> 25 % LEL - withdrawal threshold; no entry without full protective measures

These thresholds incorporate a built-in safety factor. They acknowledge that meter accuracy varies, that mixtures may be heterogeneous, and that local concentrations near a leak may significantly exceed the average reading.

7.2 Electric Vehicle Battery Thermal Runaway

EV battery thermal runaway produces a complex off-gas mixture comprising hydrogen, carbon monoxide, methane, ethane, ethylene, and electrolyte vapours such as dimethyl carbonate. Inside a sealed battery enclosure, these gases can rapidly accumulate to concentrations exceeding the UFL, a “too rich” state.

The operational hazard arises when:

The vehicle's bodywork is breached during overhaul or extrication, or

Heat causes the enclosure to vent or rupture

In both cases, the gas mixture mixes with ambient air and its concentration falls back into the flammable range. The result is a delayed flashback or vapour cloud explosion, potentially several minutes after the initial event. This is one of the primary tactical concerns addressed by the P.L.A.C.E.™ Protocol and the L.A.C.E.™ procedure currently practised by the Malaysia Fire and Rescue Department for EV incident response.

7.3 Confined Space Operations

A confined space presents the worst-case scenario for flammability hazard accumulation. Unlike open environments, where dispersion limits the build-up of vapour, a confined space allows fuel concentration to:

Reach LFL quickly

Stratify by density (heavier-than-air vapours pool at the floor, lighter-than-air gases collect at the ceiling)

Remain ignitable for extended periods after the source is removed

Effective entry procedure therefore requires simultaneous monitoring of oxygen, LEL, carbon monoxide, and hydrogen sulphide, a four-gas standard that reflects the multifactorial nature of the hazard.

7.4 Hyperbaric and Diving Medical Environments

In a hyperbaric oxygen therapy (HBOT) chamber operating at elevated partial pressures of oxygen, the flammability landscape changes in ways that are easy to underestimate:

Standard fire safety rules trained for normal atmospheres no longer apply

Materials introduced into the chamber must be rigorously assessed for ignition risk

Electrical equipment must be intrinsically safe and certified for oxygen-rich environments

Patient clothing, bedding, and personal items are tightly regulated

A historical review of hyperbaric chamber fires reveals that virtually every incident has involved either an electrical ignition source or an introduced static-charge generator (synthetic textiles, certain plastics) combined with the oxygen-enriched atmosphere. The fuel was rarely the variable that changed the oxygen was.

8. Discussion: Why a Mechanism-Based Understanding Matters

Fire instructors and emergency responders are often taught flammability limits as a memorization exercise: methane is 5-15, hydrogen is 4-75, petrol is 1.4-7.6. While this familiarity has value, it is incomplete. A responder who understands only the numbers may be unprepared when:

A tank fire at elevated temperature ignites at a vapour concentration below the expected LFL

A pressurized gas leak produces a wider flammable cloud than tabulated values suggest

An EV battery vent stream proves more reactive than methane-based intuition implies

An oxygen-enriched environment makes ordinary materials behave unpredictably

A mechanism-based understanding need to be grounded in the chemistry of pre-mixed flames, the physics of vapour transport, and the engineering reality of operational environments, allows responders to anticipate hazard behaviour rather than merely recognize it after the fact. This is the philosophical foundation of the STEMPCHEM™ framework, and the rationale for treating LFL and UFL not as static numbers but as dynamic, conditional values.

9. Conclusion

The Lower Flammability Limit, Upper Flammability Limit, and stoichiometric mixture are far more than tabulated constants. They are conditional parameters that respond to temperature, pressure, and most critically to oxygen concentration.

Modern operational environments such as electric vehicles, pressurized energy systems, hyperbaric medical facilities, confined process spaces, routinely operate at conditions that depart from the standard reference state.

A fire science practitioner who understands the mechanism of flammability behaviour, rather than only its standard-condition values, is significantly better equipped to anticipate, prevent, and respond to ignition events.

Future fire safety education, particularly within Southeast Asia's expanding EV and renewable energy sectors, must therefore incorporate the conditional nature of flammability limits as a foundational principle, not a footnote.

References

National Fire Protection Association. NFPA 325: Guide to Fire Hazard Properties of Flammable Liquids, Gases, and Volatile Solids. NFPA, Quincy, MA.

National Fire Protection Association. NFPA 30: Flammable and Combustible Liquids Code. NFPA, Quincy, MA.

National Fire Protection Association. NFPA 99: Health Care Facilities Code (hyperbaric facility provisions). NFPA, Quincy, MA.

Drysdale, D. An Introduction to Fire Dynamics, 3rd ed., Wiley, 2011.

Crowl, D. A., and Louvar, J. F. Chemical Process Safety: Fundamentals with Applications, 4th ed., Pearson, 2019.

Zabetakis, M. G. Flammability Characteristics of Combustible Gases and Vapors. Bulletin 627, U.S. Bureau of Mines, 1965.

International Code Council. International Fire Code (IFC). ICC, current edition.

U.S. Navy. U.S. Navy Diving Manual, Rev. 7. Naval Sea Systems Command.

Undersea and Hyperbaric Medical Society (UHMS). Hyperbaric Oxygen Therapy Indications, current edition.

Human Performance Assessment in

Hyperbaric Chamber Dive Training

Integrating Task Execution (TE)™, the Cognitive Degradation Index (CDI)™, and the Narcosis Risk Score (NRS)™

By Mohd Taufiq Bin Abd Sattar

Hyperbaric Facility, Malaysia Fire and Rescue Academy (Eastern Region), Terengganu, Malaysia

Abstract

Hyperbaric chamber dive training has traditionally emphasised pressure adaptation, equalisation technique, and operational familiarisation. Modern public safety diving, however, demands a fuller understanding of how divers perform under pressure. Physical capability alone is insufficient: cognitive function, decision-making ability, communication effectiveness, and operational reliability must also be evaluated.

This article presents an integrated human-performance assessment framework built on three complementary models, the Task Execution (TE) model, the Cognitive Degradation Index (CDI), and the Narcosis Risk Score (NRS). Applied across chamber exposures of 10 m, 15 m, 18 m, and 20 m, the framework gives instructors measurable indicators of performance quality, cognitive stability, and narcosis risk. It supports objective assessment, strengthens safety management, and provides a structured foundation for future integration with the Artificial Intelligence Fire & Rescue Tactics (A.I.F.R.T.™) system.

Keywords: Hyperbaric chamber; public safety diving; Task Execution; Cognitive Degradation Index; Narcosis Risk Score; human performance assessment; A.I.F.R.T.™

1. Introduction

Pressure exposure affects more than the body's physiological systems. As ambient pressure rises, divers experience changes in breathing resistance, gas density, workload, and cognitive performance. Even within relatively shallow operational depths, subtle degradation of attention, reaction time, and decision-making can occur.

Historically, diver evaluation has focused on task completion, equalisation ability, gas management, and medical fitness. These indicators matter, but they do not explain why two divers performing the same task at the same depth can produce markedly different outcomes.

Human-performance research shows that operational effectiveness is shaped by several interacting factors - physiological adaptation, cognitive workload, stress response, fatigue, communication quality, and environmental conditions. To capture these dimensions, the Fire and Rescue Hyperbaric Facility developed three complementary assessment models:

Task Execution (TE) - operational performance under pressure;

Cognitive Degradation Index (CDI) - decline in mental performance;

Narcosis Risk Score (NRS) - likelihood and severity of inert-gas/cognitive impairment.

Together, these models let instructors evaluate not only whether a task was completed, but how effectively, safely, and reliably it was performed.

2. Task Execution (TE)™ Model

The Task Execution model measures the quality of operational performance under increased ambient pressure. Unlike pass-or-fail assessment, TE grades performance across several domains: accuracy, speed, procedural compliance, communication, teamwork, equipment handling, and situational awareness.

3. Cognitive Degradation Index (CDI)™

The Cognitive Degradation Index measures the decline in mental performance associated with pressure exposure and rising workload. It tracks attention, memory, decision-making, problem-solving, reaction time, and situational awareness.

CDI matters because many incidents occur not from a lack of technical skill, but because cognitive performance deteriorates before physical performance does. Early indicators include slower responses, forgetfulness, repeated questions, poor judgment, and a reduced attention span.

4. Narcosis Risk Score (NRS)™

The Narcosis Risk Score estimates the probability and severity of inert-gas narcosis and associated cognitive impairment during pressure exposure. Contributing factors include pressure, gas density, carbon-dioxide retention, breathing workload, fatigue, stress, and exposure duration.

Interpretation at training depths. Classical nitrogen narcosis is minimal at 10-20 m and becomes clinically noticeable only at greater depth (around 30 m / 4 ATA and beyond). At chamber training depths the NRS therefore functions chiefly as a recognition-training tool and as a combined index of carbon-dioxide retention, breathing workload, fatigue, and stress, rather than as a measure of significant nitrogen narcosis. This framing keeps the model honest while still developing the diver's ability to recognise impairment early.

5. Integrated Human-Performance Framework

The framework's real value emerges when TE, CDI, and NRS are read together, because each measures a different aspect of diver performance:

Integrated Interpretation Matrix

To convert three separate scales into a single decision, the framework applies a weakest-link rule: the diver's overall status is governed by the worst individual sub-score. This conservative approach reflects standard safety practice - a strong score in one dimension does not offset a critical weakness in another.

Example: a diver scoring TE 2, CDI 3, NRS 2 is rated AMBER overall — the task continues under enhanced supervision because the cognitive sub-score has reached the caution threshold, even though task execution and narcosis risk remain good.

6. Integration with A.I.F.R.T.™

The next stage of diver assessment is artificial-intelligence-assisted monitoring. Within the A.I.F.R.T.™ framework, live and recorded inputs - heart rate, SpO₂, task-completion times, error frequency, and the CDI and NRS scores - can be combined to deliver real-time performance assessment, early-warning alerts, predictive risk analysis, and data-driven training optimisation.

This integration transforms hyperbaric chamber training from a subjective grading exercise into a measurable, evidence-based performance system, with the Integrated Interpretation Matrix serving as the rule set that an automated monitor can apply consistently.

7. Benefits for Fire & Rescue Operations

Safety. Early detection of performance decline, fewer training incidents, and better-timed instructor intervention.

Operational. More reliable task execution, clearer communication, and sounder decision-making.

Research. Standardised performance data, AI-ready datasets, and long-term trend analysis.

Training. Objective assessment, consistent grading, and individualised development plans.

8. Conclusion

Modern hyperbaric chamber dive training extends well beyond simple pressure exposure. Effective preparation requires the simultaneous assessment of operational performance, cognitive capability, and narcosis risk. The Task Execution model, the Cognitive Degradation Index, and the Narcosis Risk Score - read together through the Integrated Interpretation Matrix - provide a comprehensive, defensible basis for judging diver readiness under pressure.

Together, these models establish a new generation of performance-based training capable of supporting advanced public safety diving operations, research initiatives, and future AI-assisted decision support. As the Academy continues to advance its capabilities, the integration of TE, CDI, NRS, and A.I.F.R.T.™ marks a significant step toward safer, smarter, and more effective public safety divers.

Train Safe • Dive Smart • Save Lives

Hyperbaric Facility - Malaysia Fire and Rescue Academy, Eastern Region - Terengganu, Malaysia

Powered by STEMPCHEM™

A.I.T.R.E.S.™: An Advanced Concept Mathematical Predictive Model for Real-Time Thermal Runaway Risk Prediction in Electric Vehicle Lithium-Ion Battery Systems

By Mohd Taufiq Bin Abd Sattar

Abstract

Electric vehicle adoption is rapidly transforming modern transportation, but it also introduces new challenges for fire safety, emergency response, battery diagnostics, and predictive risk management. One of the most critical hazards in electric vehicle lithium-ion battery systems is thermal runaway, a complex failure process involving heat generation, electrical instability, gas release, mechanical damage, and propagation between cells or modules.

The A.I.T.R.E.S.™ (Advanced Integrated Thermal Runaway Evaluation and Scoring System) model is proposed as a multi-parameter predictive framework designed to transform battery telemetry, environmental conditions, and sensor fusion data into three practical outputs:

• Thermal Runaway Risk Score (TRRS)

• Confidence-Adjusted Risk Output (CARO)

• Estimated Time-to-Failure (ETTF)

The framework integrates six primary risk domains:

1. Thermal Instability

2. Electrical Anomalies

3. Gas Release

4. Mechanical Damage

5. Contextual Operating Conditions

6. Propagation Likelihood

Drawing upon lithium-ion battery thermal runaway research, heat transfer theory, electrochemical degradation mechanisms, and probabilistic risk modelling, A.I.T.R.E.S.™ provides a structured pathway for early detection and prediction of battery failure. The framework is intended for future application in EV battery management systems, charging infrastructure safety, battery testing laboratories, fire and rescue operations, and AI-assisted emergency response platforms.

This article introduces the conceptual and mathematical foundation of A.I.T.R.E.S.™, its operational value for electric vehicle safety, and its potential contribution to fire and rescue decision-making, battery monitoring systems, research validation, and future AI-assisted emergency response platforms.

1. Introduction

Lithium-ion batteries have become the dominant energy storage technology for electric vehicles due to their high energy density, long cycle life, and favourable power characteristics. Modern EV battery packs commonly operate between 300 V and 800 V and may contain hundreds or even thousands of individual cells storing energy levels exceeding 50 - 150 kWh.

Despite these advantages, lithium-ion batteries remain vulnerable to thermal runaway, a self-accelerating exothermic process that can result in:

• Rapid temperature escalation, sometimes exceeding 800°C in localized regions

• Toxic and flammable gas release

• Jet flames and fireballs

• Cell-to-cell thermal propagation

• Reignition after suppression

• Structural battery pack failure

Research by Feng et al. (2018), Finegan et al. (2017), Larsson et al. (2017), and various NREL battery safety studies demonstrates that thermal runaway is rarely triggered by a single parameter. Instead, it develops through the interaction of thermal, electrical, chemical, and mechanical degradation processes.

In practical terms, a battery may appear stable externally while internal decomposition has already begun. Temperature increases may only become obvious after significant internal damage has occurred. In other cases, gas generation, voltage abnormalities, or mechanical damage may provide earlier warning signs than temperature alone.

For this reason, predictive safety systems must move beyond simple threshold alarms and adopt a multi-dimensional risk assessment methodology. A.I.T.R.E.S.™ was developed to address this requirement.

2. Scientific Basis of Thermal Runaway

Thermal runaway generally progresses through several distinct operational and chemical stages:

Experimental studies indicate the following extreme environmental conditions during a failure event:

• Internal temperatures may exceed 800 – 1000°C.

• Cell pressure may exceed 1 – 2 MPa before venting.

• Heat release rates may exceed 5 – 20 kW per cell depending on chemistry.

• Thermal propagation between adjacent cells may occur within seconds to minutes.

These findings form the scientific foundation of the A.I.T.R.E.S.™ framework and reinforce the need for predictive monitoring rather than reactive detection.

3. Project Overview

A.I.T.R.E.S.™ stands as an advanced predictive model for electric vehicle lithium-ion battery safety. Its purpose is to support real-time thermal runaway risk prediction through mathematical modelling, sensor fusion, confidence adjustment, and dynamic escalation analysis.

The project is designed to support several future applications:

• Electric vehicle battery safety research

• Fire and rescue operational decision support

• Battery management system enhancement

• EV charging station safety monitoring

• AI-assisted emergency response systems

• PhD and journal-level research development

• Thermal runaway experimental validation

• Prototype algorithm and simulation development

The main objective of A.I.T.R.E.S.™ is to convert raw battery and environmental data into three practical outputs: Thermal Runaway Risk Score, Confidence-Adjusted Risk Output, and Estimated Time-to-Failure. These outputs allow responders, engineers, researchers, and system designers to understand not only whether a battery is at risk, but also how reliable the prediction is and how quickly the situation may escalate.

4. Problem Statement

Thermal runaway prediction remains difficult because lithium-ion battery failure is multi-dimensional. A battery may appear stable externally while internal degradation is already occurring. In some cases, temperature increase becomes obvious only after internal decomposition has already advanced. In other cases, electrical anomalies, gas release, or mechanical damage may occur before a visible fire or smoke condition is detected.

This creates several operational problems:

• Firefighters may arrive after the battery has already entered an unstable phase.

• EV users may receive insufficient early warning before a serious battery event.

• Charging station operators may lack a proper risk score to determine whether to isolate power or evacuate the area.

• Battery monitoring systems may generate alerts without explaining confidence level or escalation speed.

• Researchers may have sensor data but lack a structured method to convert it into a predictive risk output.

A.I.T.R.E.S.™ attempts to solve this gap by creating a structured mathematical pathway from multi-sensor data to real-time risk interpretation.

5. Modelling Philosophy of A.I.T.R.E.S.™

The A.I.T.R.E.S.™ model is based on five core principles:

5.1 Multi-Parameter Fusion

Thermal runaway is not determined by one variable alone. Temperature, voltage, gas emission, impact history, state of charge, cooling performance, and propagation potential must be evaluated together.

5.2 Normalized Scoring

Different sensor values use different units. Temperature may be measured in degrees Celsius, voltage in volts, current in amperes, gas concentration in ppm, and deformation in millimetres. A.I.T.R.E.S.™ converts these raw values into normalized scores so they can be compared and combined seamlessly.

5.3 Weighted Contribution

Not all indicators contribute equally. Thermal instability may carry higher predictive importance than some contextual indicators, but contextual stress may still influence the final risk score. The model therefore allows different indicators to be weighted according to experimental evidence and calibration.

5.4 Confidence-Aware Prediction

A prediction is only useful if the system understands how reliable the data is. A.I.T.R.E.S.™ includes a confidence factor based on sensor reliability, data completeness, model agreement, and similarity to known training cases.

5.5 Dynamic Forecasting

Battery risk is not static. A battery may move from normal to advisory, warning, high risk, and critical condition within a short period. The model therefore includes an escalation momentum factor to reflect how fast the hazard is developing.

6. The Six Main Risk Indicator Groups

A.I.T.R.E.S.™ uses six major indicator groups to evaluate the risk of thermal runaway.

6.1 Thermal Instability Index (TII)

The Thermal Instability Index evaluates heat-related battery behaviour. It includes temperature rise rate, temperature acceleration, hotspot intensity, cell-to-cell temperature deviation, and module-to-module thermal deviation.

This index is one of the strongest predictors because abnormal heat generation is closely linked to internal failure, separator breakdown, electrolyte decomposition, and propagation risk.

\[TII\ = \ 0.35T\_ r\ + \ 0.25T\_ a\ + \ 0.20H\_ s\ + \ 0.10\backslash Delta\ T\_ c\ + \ 0.10\backslash Delta\ T\_ m\]

Where:

• \(T\_ r\) = temperature rise rate

• \(T\_ a\) = temperature acceleration

• \(H\_ s\) = hotspot severity

• \(\backslash Delta\ T\_ c\) = cell temperature deviation

• \(\backslash Delta\ T\_ m\) = module temperature deviation

Typical Interpretation:

• Normal rise rate: \(< 1{^\circ}C/min\}\)

• Elevated concern: \(> 3{^\circ}C/min\}\)

• Critical escalation: \(> 10{^\circ}C/min\}\)

Example Case: If temperature increases from 45°C to 75°C within 5 minutes:

\[\frac{75\, - \, 45}{5}\, = \, 6\text{°C}\text{/}\text{min}\]

This significantly exceeds normal operating behavior and indicates severe abnormal internal heat generation.

6.2 Electrical Anomaly Index (EAI)

The Electrical Anomaly Index evaluates abnormal electrical behaviour inside the battery system. It includes voltage imbalance, voltage decay rate, current oscillation, internal resistance growth, and overcharge stress. Electrical anomalies are important because internal short circuits, overcharging, and resistance growth may occur before obvious external signs of fire break out.

\[EAI = 0.30V_{i} + 0.25V_{d} + 0.20I_{o} + 0.15R_{g} + 0.10OC_{s}\]

Where:

• \(V_{i}\) = voltage imbalance

• \(V_{d}\) = voltage decay

• \(I_{o}\) = current oscillation

• \(R_{g}\) = resistance growth

• \(OC_{s}\) = overcharge stress

Typical Warning Indicators:

• Cell imbalance \(> 50mV\)

• Resistance increase >20\%

• Unexpected sudden voltage collapse

• Abnormal high-voltage charging behavior

### 6.3 Gas Release Index (GRI)

The Gas Release Index evaluates the presence and trend of gas emissions associated with battery degradation and decomposition. This includes hydrogen, carbon monoxide, volatile organic compounds, and gas release rate. Gas release is a critical early-warning indicator because it signals that internal chemical reactions are occurring before visible flaming begins.

\[GRI = 0.40CO + 0.25H_{2} + 0.20VOC + 0.15G_{r}\]

Where:

• \(G_{r}\) = gas release rate

Strategic Value: Diagnostic studies suggest detectable off-gas venting events may occur between 5 and 30 minutes prior to full thermal runaway propagation, making gas sensing an invaluable early-warning layer.

6.4 Mechanical Damage Index (MDI)

The Mechanical Damage Index evaluates physical degradation conditions that increase the structural probability of battery failure. These include impact severity, vibration anomaly, enclosure deformation, and delayed post-impact anomaly behaviour.

\[MDI = 0.35I_{s} + 0.25D_{f} + 0.20V_{a} + 0.20P_{a}\]

Where:

• \(I_{s}\) = impact severity

• \(D_{f}\) = deformation factor

• \(V_{a}\) = vibration anomaly

• \(P_{a}\) = post-impact anomaly

This metric is highly relevant for emergency responders attending automobile accidents, severe underbody strikes, battery enclosure intrusions, and post-crash structural battery assessments.

6.5 Contextual Operating Index (COI)

The Contextual Operating Index evaluates environmental and macro-operational factors that elevate baseline risk profiles. A battery operating at high state of charge, under rapid fast-charging parameters, exposed to extreme ambient temperatures, or running with compromised cooling lines exhibits a significantly increased vulnerability to terminal runaway.

\[COI = 0.35\text{SOC} + 0.25A_{T} + 0.20C_{R} + 0.20C_{D}\]

Where:

• \(\text{SOC}\) = State of Charge

• \(A_{T}\) = Ambient Temperature

• \(C_{R}\) = Charging Rate

• \(C_{D}\) = Cooling Degradation

Empirical Vulnerability Constraints:

• \(\text{SOC} > 90\backslash\%\) exponentially increases structural runaway thermal severity.

• Fast charging parameters \(\left( > 2\text{C} \right)\) elevate continuous local thermal stress.

• Ambient temperatures \(> 40\text{°C}\) accelerate internal chemical degradation pathways.

6.6 Propagation Likelihood Index (PLI)

The Propagation Likelihood Index evaluates whether a localized single-cell failure will spread cascade-style to adjacent target cells or modules.

\[PLI = 0.40N_{H} + 0.30M_{G} + 0.30S_{R}\]

Where:

• \(N_{H}\) = neighbouring cell heating

• \(M_{G}\) = module thermal gradient

• \(S_{R}\) = spread rate

Experimental studies demonstrate cascade propagation velocities ranging widely from \(0.5\text{ to }10\text{ cm}\text{/}\text{min}\) depending heavily on specific pack chemistry, interstitial cell spacing configurations, cooling architecture, and structural pack materials.

7. Composite Thermal Runaway Risk Score

The six individual indices are combined into a standardized composite base thermal runaway risk score (TRRS), mapped to a robust scalar range from 0 to 100. Each distinct index contributes according to an engineered calibration weight, prioritizing thermal and electrical telemetry over environmental operational inputs.

8. Confidence-Adjusted Risk Output (CARO)

A.I.T.R.E.S.™ evaluates structural data confidence alongside raw risk parameters to prevent sensor drops, noise, or incomplete datasets from skewing system predictions.

The Confidence Factor (CF) is mathematically formulated as:

\[CF\ = \ 0.35SR\ + \ 0.25DC\ + \ 0.20MA\ + \ 0.20TS\]

Where:

• \(SR\) = Sensor Reliability

• \(DC\) = Data Completeness

• \(MA\) = Model Agreement

• \(TS\) = Training Similarity

The final Confidence-Adjusted Risk Output (CARO) is evaluated as:

\[CARO\ = \ TRRS\ \times CF\]

Operational Safety Guardrail: A raw risk score of 82 paired with a degraded confidence factor of 0.60 yields a CARO value of 49.2. This adjustment indicates high data uncertainty rather than a safe battery condition. In safety-critical automation, an alert must be triggered if either TRRS or CARO crosses their respective safety thresholds, ensuring that compromised data confidence never dangerously masks an imminent thermal crisis.

9. Escalation Momentum Factor (EMF)

Battery hazard progression is dynamic. A cell displaying a moderate risk score paired with an aggressive rate of temperature and gas escalation presents a more critical hazard than a high-score cell that has stabilized. The Escalation Momentum Factor (EMF) addresses this by quantifying the rate of failure acceleration.

\[EMF = 0.40\frac{dT}{dt} + 0.25\frac{d^{2}T}{dt^{2}} + 0.20\frac{dV}{dt} + 0.15\frac{dG}{dt}\]

Where:

• \(\frac{dT}{dt}\) = temperature rise rate

• \(\frac{d^{2}T}{dt^{2}}\) = thermal acceleration

• \(\frac{dV}{dt}\) = voltage decay rate

• \(\frac{dG}{dt}\) = gas generation rate

Mathematical Scaling Note: Because raw telemetry derivatives utilize radically different physical units (e.g., °C/min versus V/min or ppm/min), all raw input gradients are passed through a localized, non-linear min-max scaling function prior to index calculation. This normalizes each derivative into a dimensionless scalar range \((0 \leq x \leq 100)\), ensuring that no single parameter disproportionately dominates the EMF weight matrix.

10. Estimated Time-to-Failure (ETTF)

A primary contribution of the A.I.T.R.E.S.™ architecture is computing a clear remaining time window before terminal structural failure occurs, providing vital operational data to emergency crews.

A simplified hazard-based model for ETTF estimation is expressed as:

\[ETTF = \frac{K}{TRRS \times EMF}\]

Where:

• \(K\) = calibration constant

System Gating and Boundary Constraints: To prevent division-by-zero errors or infinite temporal outputs \((\infty)\) during nominal baseline vehicle operation, the ETTF computation engine features an automated logical gate. The algorithm remains dormant while the battery is within standard parameters \((TRRS \leq 20)\), and dynamically activates only when an active, non-zero escalation trend \((EMF > 0)\) is verified.

Operational Output Example \(\left( \mathbf{K = 10000,TRRS = 80,EMF = 6} \right)\):

\[ETTF = \frac{10000}{80 \times 6} = 20.8\text{ minutes}\]

11. Probability Mapping

A.I.T.R.E.S.™ converts the combined multi-parameter framework into an explicit, highly readable probability metric using a logistic sigmoidal mapping equation. This delivers an actionable, easy-to-interpret percentage value (e.g., Probability of Runaway: 72% / Confidence: 0.81) that can be immediately utilized by non-technical dispatchers, commanders, and emergency personnel.

12. STEMPCHEM™ Interpretation of A.I.T.R.E.S.™

The interdisciplinary nature of the A.I.T.R.E.S.™ platform is cleanly evaluated through the holistic STEMPCHEM™ framework:

• Science: Grounded in understanding battery failure chemistry, heat propagation pathways, and gas generation kinematics.

• Technology: Encompasses multi-sensor physical integration, telemetry data links, dashboard interfaces, and edge computing algorithms.

• Engineering: Addresses physical cell geometries, structural cooling lines, structural containment, and field charging interfaces.

• Mathematics: Built upon normalization arrays, linear scoring weight matrix scaling, confidence vectors, and logistic sigmoidal curves.

• Physics: Tracks core thermodynamic heat transfer laws, thermal gradients, mechanical forces, and electrical circuit dynamics.

• Chemistry: Evaluates SEI layer decomposition pathways, toxic off-gassing reactions, and exothermic structural cell degradation.

13. Application in Fire and Rescue Operations

For fire and rescue services, A.I.T.R.E.S.™ supports crucial tactical decision-making across all operational phases of an EV incident:

• A.I.F.R.T.™ (Artificial Intelligence Fire Rescue Tactics): Integrates directly with advanced incident management models to feed real-time risk scores into tactical command modules.

• P.L.A.C.E.™ (Push Isolation, Layout Blanket, Approach Safely, Cover Vehicle, Evaluate & Coordinate): Provides critical timing data for rapid deployment and positioning of specialized equipment.

• L.A.C.E.™ (Locate Fire Blanket, Approach Safely, Cover Vehicle, Evaluate & Coordinate): Delivers a definitive safety window (ETTF) before teams approach a vehicle to deploy specialized containment blankets.

• Post-Incident Overhaul: Guides tactical isolation decisions, perimeter distances, and monitors long-term cell cooling to mitigate thermal reignition risks.

14. Application in EV Charging Station Safety

EV charging stations represent high-stress environments due to rapid electrical and thermal energy transfer. Integrating A.I.T.R.E.S.™ into charging nodes enables early localized isolation actions before a vehicle enters an uncontrollable failure state. Warning triggers such as charging current anomalies or local gas concentration changes interface directly with facility safety loops to trigger power disconnects, deploy on-site containment assets, or automatically alert dispatch channels.

15. Research and Validation Strategy

Empirical validation requires running the predictive engine against controlled physical abuse test profiles:

• Overcharging and deep external electrical short circuits.

• Mechanical drop, crush, and direct nail-penetration abuse profiles.

• Localized heater-induced thermal runaway and cooling loss simulations.

System optimization criteria must prioritize maximizing valid early-warning lead times while driving down false-alarm rates (FAR) and keeping missed detection rates (MDR) close to zero, ensuring absolute operational dependability for emergency crews.

16. Limitations and Future Development

Several developmental gates remain before wide-scale commercial field application:

1. Calibration: Fixed weight profiles must be validated across varied modern battery chemistries (e.g., LFP, NMC, Solid-State).

2. Hardware Durability: Physical sensor arrays must retain operational accuracy under high heat, blast forces, submersion, and impact.

3. Cross-Validation: The software must be tested against non-runaway stress cases to prevent system over-sensitisation.

Future targets include cross-linking predictive models with automated mitigation loops, like localized emergency cooling activation or active cell venting containment.

17. Conclusion

A.I.T.R.E.S.™ represents a structured advancement in electric vehicle battery safety, fire science, and emergency response technology. By combining thermal, electrical, gas, mechanical, contextual, and propagation indicators into a single predictive model, A.I.T.R.E.S.™ moves beyond simple threshold-based warning systems.

Its strength lies in its ability to generate a real-time Thermal Runaway Risk Score, adjust that score according to confidence, evaluate escalation momentum, estimate time-to-failure, and support operational decision-making. As electric vehicle adoption continues to grow, predictive safety systems must evolve beyond passive monitoring. A.I.T.R.E.S.™ provides a clear pathway toward proactive, intelligent, and scientifically structured thermal runaway risk prediction.

Technical Signature Statement

The A.I.T.R.E.S.™ Advanced Mathematical Predictive Model provides a structured quantitative pathway for translating battery telemetry, thermal behaviour, gas generation, electrical anomalies, mechanical damage, operating context, and propagation likelihood into real-time prediction of electric vehicle thermal runaway risk, confidence, and expected escalation time.

Author / Project Credit

Developed under the research and innovation direction of Mohd Taufiq Bin Abd Sattar, with application toward electric vehicle safety, fire and rescue emergency response, thermal runaway research, and AI-assisted predictive fire science.

Statistik Terkini Kenderaan HEV, PHEV, BEV dan FCEV di Malaysia September 2026

Peralihan Mobiliti Elektrifikasi Semakin Jelas & Ketara-Malaysia Sedang Memasuki Fasa Baharu Mobiliti Elektrifikasi

Tarikh Data: 31 Julai 2026
Status Semakan: 2 September 2026

Disediakan oleh : Mohd Taufiq bin Abd Sattar

Landskap automotif Malaysia sedang berubah dengan semakin pantas. Kenderaan yang menggunakan teknologi elektrifikasi daripada Hybrid Electric Vehicle (HEV) dan Plug-in Hybrid Electric Vehicle (PHEV) hingga kepada Battery Electric Vehicle (BEV/EV), kini semakin ketara di jalan raya Malaysia.

Berdasarkan data pendaftaran kenderaan Jabatan Pengangkutan Jalan (JPJ) yang tersedia melalui portal data terbuka kerajaan, data lengkap terkini adalah sehingga 31 Julai 2026. Angka tersebut memberikan gambaran yang semakin jelas bahawa penggunaan kenderaan elektrik bukan lagi sekadar perkembangan kecil dalam pasaran automotif negara, tetapi sedang berkembang menjadi salah satu komponen penting dalam mobiliti Malaysia.

BEV/EV Mencatat Pertumbuhan Kukuh

Sebanyak 6,937 BEV/EV telah didaftarkan pada Julai 2026, berbanding 6,215 unit pada Jun 2026. Ini merupakan peningkatan sebanyak 722 unit, atau kira-kira 11.6% dalam tempoh sebulan.

Secara kumulatif, jumlah pendaftaran BEV/EV telah mencapai kira-kira 122,286 unit sehingga akhir Julai 2026.

Lebih menarik, sebanyak 38,675 EV telah didaftarkan sepanjang Januari hingga Julai 2026. Angka ini menunjukkan peningkatan kira-kira 94% berbanding tempoh yang sama tahun sebelumnya.

Dengan kata lain, kadar penerimaan EV di Malaysia bukan sahaja meningkat, malah momentum pertumbuhannya semakin kuat.

Antara model yang menonjol dalam pendaftaran Julai ialah Proton e.MAS 5, yang mencatat sekitar 2,402 unit. Ia diikuti beberapa model popular seperti BYD Atto 3, Proton e.MAS 7, Tesla Model Y dan Zeekr 7X.

Prestasi Proton e.MAS 5 amat signifikan kerana model tersebut bukan sahaja mendahului kategori EV, malah dilaporkan berada dalam kelompok teratas pendaftaran keseluruhan kereta penumpang di Malaysia bagi bulan Julai.

Perkembangan ini memberikan satu petunjuk penting: EV kini mula bersaing secara langsung dengan kenderaan konvensional dalam pasaran arus perdana Malaysia.

HEV dan PHEV Kekal Sebagai Komponen Penting

Bagi kategori hybrid, sebanyak 5,622 kenderaan direkodkan pada Julai 2026 berbanding kira-kira 5,646 unit pada Jun.

Ini merupakan penurunan kecil sebanyak 24 unit, atau sekitar 0.4%. Walaupun berlaku sedikit penurunan secara bulanan, jumlah pendaftaran hybrid kekal tinggi.

Secara kumulatif, rekod kategori hybrid telah mencapai sekitar 203,682 unit sehingga akhir Julai 2026.

Antara model hybrid dan plug-in hybrid yang menonjol ialah Proton e.MAS 7 PHEV, Toyota Yaris Cross, Toyota Corolla Cross, Toyota Vios, GWM Haval H6 dan GWM Wey G9.

Proton e.MAS 7 PHEV khususnya mencatat sekitar 872 pendaftaran pada Julai, menjadikannya antara model elektrifikasi yang paling ketara dalam pasaran ketika ini.

Kehadiran model baharu juga terus berkembang. Antaranya ialah Volkswagen Tayron yang mula muncul dalam rekod pendaftaran hybrid pada Julai.

BEV Kini Mengatasi Hybrid dalam Pendaftaran Bulanan

Salah satu perkembangan yang menarik pada Julai ialah jumlah pendaftaran BEV/EV telah mengatasi kategori hybrid.

Dengan 6,937 EV berbanding 5,622 hybrid, EV mempunyai kelebihan sebanyak 1,315 unit bagi bulan tersebut.

Gabungan pendaftaran EV dan hybrid pula mewakili sekitar 15.7% daripada keseluruhan pendaftaran kenderaan pada Julai 2026.

Secara mudah, angka ini menghampiri nisbah satu daripada setiap enam kenderaan baharu yang didaftarkan pada bulan tersebut menggunakan suatu bentuk sistem pemacuan elektrifikasi.

Perubahan ini penting kerana ia menunjukkan teknologi elektrifikasi sedang bergerak daripada pasaran khusus kepada penggunaan yang semakin meluas.

Bagaimana Pula dengan FCEV dan Kenderaan Hidrogen?

Perkembangan Fuel Cell Electric Vehicle (FCEV) di Malaysia masih berada pada tahap yang sangat kecil berbanding HEV, PHEV dan BEV.

Toyota Mirai merupakan antara model FCEV yang dapat dikenal pasti dengan jelas dalam rekod yang tersedia. Setakat data yang boleh dikenal pasti, terdapat sekitar sembilan unit Toyota Mirai dalam rekod pendaftaran, tanpa pertambahan baharu pada Julai 2026. Namun angka ini perlu ditafsir dengan berhati-hati.

Dalam data awam JPJ, Toyota Mirai boleh dan sepatutnya direkodkan di bawah kategori EV, bukannya kategori khusus "Hydrogen" atau "FCEV". Oleh itu, jumlah sebenar FCEV tidak semestinya dapat diperoleh hanya dengan melihat kategori bahan api dalam dataset awam.

Malaysia pada masa yang sama telah menjalankan beberapa projek demonstrasi teknologi hidrogen, termasuk penggunaan Toyota Mirai bersama infrastruktur pengisian hidrogen.

Ini menunjukkan bahawa FCEV di Malaysia ketika ini lebih tepat dianggap berada dalam fasa demonstrasi, penyelidikan dan pembangunan ekosistem, berbanding perkembangan penggunaan di pasaran.

Perkara Penting dalam Membaca Statistik JPJ

Walaupun data JPJ merupakan antara sumber rasmi terbaik untuk melihat perkembangan kenderaan di Malaysia, terdapat beberapa batasan yang perlu difahami sebelum angka ini digunakan untuk analisis teknikal atau penyelidikan.

Pertama, angka tersebut merupakan rekod pendaftaran kenderaan, bukannya angka jualan sebenar oleh pengeluar atau jumlah kenderaan yang masih aktif di jalan raya.

Kedua, kategori Hybrid dalam data awam JPJ tidak semestinya membezakan secara jelas antara HEV, PHEV dan sesetengah konfigurasi hybrid lain.

Ini bermakna tidak tepat untuk menganggap semua 203,682 rekod hybrid sebagai HEV sahaja atau PHEV sahaja.

Untuk mendapatkan jumlah HEV dan PHEV yang benar-benar berasingan, analisis perlu dilakukan pada peringkat model dan varian, kemudian setiap kenderaan perlu diklasifikasikan semula berdasarkan teknologi powertrain sebenar.

Ketiga, isu yang sama berlaku kepada FCEV. Jika sebuah Toyota Mirai direkodkan sebagai EV, analisis berdasarkan kategori bahan api sahaja boleh menyebabkan kenderaan tersebut dikira sebagai BEV sedangkan teknologi sebenarnya ialah hydrogen fuel-cell electric vehicle.

Oleh itu, statistik elektrifikasi Malaysia sebaik-baiknya dibaca sebagai gabungan antara data rasmi JPJ dengan semakan teknikal berdasarkan model kenderaan.

Gambaran Keseluruhan

*Jumlah kumulatif hendaklah dibaca mengikut klasifikasi dataset JPJ dan bukan sebagai jumlah kenderaan aktif di jalan raya.

Kesimpulan

Data sehingga akhir Julai 2026 menunjukkan bahawa peralihan Malaysia ke arah mobiliti elektrifikasi sedang berlaku dengan lebih pantas.

BEV mencatat pertumbuhan bulanan yang kukuh, hybrid terus mengekalkan jumlah pendaftaran yang besar, manakala PHEV semakin mendapat tempat sebagai teknologi peralihan antara enjin pembakaran dalaman dan mobiliti elektrik sepenuhnya.

FCEV pula masih berada pada tahap awal, dengan pembangunan teknologi hidrogen lebih tertumpu kepada demonstrasi, pembangunan infrastruktur dan pembentukan ekosistem.

Namun terdapat satu perkara yang semakin jelas: profil risiko kenderaan di Malaysia sedang berubah seiring dengan perubahan teknologi automotif.

Pertumbuhan HEV, PHEV, BEV dan pada masa hadapan FCEV bermakna pengetahuan mengenai bateri voltan tinggi, lithium-ion battery thermal runaway, stranded electrical energy, sistem pengecasan, bahan api hidrogen, pengasingan tenaga, pemadaman kebakaran dan teknik penyelamatan akan menjadi semakin penting.

Perubahan ini bukan sahaja melibatkan industri automotif dan pengguna. Ia turut memberi kesan langsung kepada perkhidmatan kecemasan, pasukan bomba dan penyelamat, pengendali lebuh raya, industri insurans, bengkel, pusat pengecasan, pengurusan bangunan serta agensi keselamatan dan penguatkuasaan.

Malaysia bukan sekadar sedang menerima lebih banyak kenderaan elektrik. Negara sedang melalui perubahan dalam keseluruhan ekosistem keselamatan mobiliti

Sumber Utama

Data utama hendaklah dirujuk kepada Jabatan Pengangkutan Jalan Malaysia (JPJ) dan data.gov.my, dengan sumber industri automotif berwibawa digunakan untuk rujukan silang model, teknologi powertrain dan perkembangan pasaran.

Nota / Note: Data terkini lengkap yang digunakan dalam artikel ini berakhir pada 31 Julai 2026. Statistik Ogos 2026 belum dimasukkan sehingga dataset rasmi JPJ diterbitkan dan boleh disahkan.

Latest HEV, PHEV, BEV and FCEV Statistics in Malaysia: The Shift Towards Electrified Mobility Becomes Clearer - Malaysia Is Entering a New Phase of Electrified Mobility

Data Cut-off: 31 July 2026
Review Status: 2 September 2026

By : Mohd Taufiq bin Abd Sattar

Malaysia's automotive landscape is changing rapidly. Electrified vehicles—from Hybrid Electric Vehicles (HEVs) and Plug-in Hybrid Electric Vehicles (PHEVs) to Battery Electric Vehicles (BEVs/EVs)—are becoming increasingly visible on Malaysian roads.

Based on vehicle registration data from Malaysia's Road Transport Department (JPJ) made available through the government's open-data platform, the latest complete dataset currently extends to 31 July 2026.

The figures provide an increasingly clear indication that vehicle electrification is no longer a small niche within Malaysia's automotive market. It is becoming an important part of the country's mobility landscape.

Strong Growth in BEV Registrations

Malaysia recorded 6,937 BEV/EV registrations in July 2026, compared with 6,215 in June.

This represents an increase of 722 vehicles, equivalent to approximately 11.6% month-on-month growth.

Cumulative BEV/EV registrations reached approximately 122,286 vehicles by the end of July 2026.

More significantly, approximately 38,675 EVs were registered between January and July 2026, representing growth of around 94% compared with the corresponding period a year earlier.

The figures suggest that EV adoption is not simply continuing—it is gaining momentum.

Among the prominent EV models registered during July was the Proton e.MAS 5, with approximately 2,402 registrations, followed by models including the BYD Atto 3, Proton e.MAS 7, Tesla Model Y and Zeekr 7X.

The performance of the e.MAS 5 is particularly significant because it was not merely competitive within the EV segment. It reportedly entered the upper ranks of Malaysia's overall passenger-car registration chart for the month.

This is an important development because it suggests that EVs are beginning to compete directly with conventional vehicles in Malaysia's mainstream automotive market.

HEVs and PHEVs Remain an Important Part of the Market

Approximately 5,622 hybrid vehicles were registered in July 2026, compared with around 5,646 in June.

This represents a modest reduction of only 24 vehicles, or approximately 0.4% month-on-month.

Despite the slight monthly decline, hybrid registrations remain substantial, with cumulative registrations reaching approximately 203,682 vehicles by the end of July.

Prominent hybrid and plug-in hybrid models included the Proton e.MAS 7 PHEV, Toyota Yaris Cross, Toyota Corolla Cross, Toyota Vios, GWM Haval H6 and GWM Wey G9.

The Proton e.MAS 7 PHEV was particularly notable, recording approximately 872 registrations during July.

Newer models are also beginning to appear in the registration data, including the Volkswagen Tayron.

BEVs Overtake Hybrids in Monthly Registrations

One of the most interesting developments in July was that BEV registrations exceeded hybrid registrations.

With 6,937 EVs compared with 5,622 hybrids, BEVs led by 1,315 registrations during the month.

Combined EV and hybrid registrations represented approximately 15.7% of total vehicle registrations in July 2026.

In practical terms, this approaches one out of every six newly registered vehicles during the month using some form of electrified powertrain.

This is significant because it indicates that electrification is gradually moving beyond a specialist market and towards broader mainstream adoption.

What About FCEVs and Hydrogen Vehicles?

Malaysia's Fuel Cell Electric Vehicle (FCEV) segment remains extremely small compared with HEVs, PHEVs and BEVs.

The Toyota Mirai is one of the few FCEVs that can be clearly identified in the available registration records. Approximately nine Toyota Mirai vehicles can currently be identified, with no additional registrations recorded in July 2026.

This figure, however, requires careful interpretation.

Within publicly available JPJ data, the Toyota Mirai may be classified under EV rather than under a dedicated "Hydrogen" or "FCEV" category.

Consequently, determining Malaysia's exact FCEV population solely from the public fuel-type classification is difficult.

Malaysia has nevertheless undertaken hydrogen mobility demonstration activities involving Toyota Mirai vehicles and hydrogen refuelling infrastructure.

At present, therefore, FCEV deployment in Malaysia is more appropriately regarded as being within a demonstration, research and ecosystem-development phase rather than a mass-market adoption phase.

An Important Limitation of JPJ Statistics

JPJ registration data remains one of the most authoritative sources for monitoring Malaysia's vehicle population, but several limitations should be recognised.

First, these figures represent vehicle registration records. They should not automatically be interpreted as manufacturer sales figures or as the number of vehicles currently active on Malaysian roads.

Second, the public JPJ Hybrid classification does not necessarily provide a clean separation between HEVs, PHEVs and other hybrid configurations.

It would therefore be incorrect to interpret all 203,682 hybrid records as HEVs or, conversely, as PHEVs.

Producing an accurate HEV-versus-PHEV breakdown would require analysis at the individual model and variant level, followed by technical reclassification according to the actual powertrain technology.

The same issue applies to FCEVs. If a Toyota Mirai is classified as an EV, a simple fuel-category analysis could incorrectly include it within the BEV population even though its actual propulsion technology is a hydrogen fuel-cell electric powertrain.

For this reason, Malaysia's electrified-vehicle statistics are best interpreted through a combination of official JPJ registration data and model-specific technical classification.

Statistical Snapshot

*Cumulative figures should be interpreted according to JPJ dataset classifications and should not be treated as the number of vehicles currently active on the road.

Conclusion

The figures through the end of July 2026 indicate that Malaysia's transition towards electrified mobility is accelerating.

BEVs are recording strong monthly growth, hybrids continue to account for a substantial number of registrations, and PHEVs are increasingly establishing themselves as a transition technology between conventional internal-combustion vehicles and fully electric mobility.

FCEVs remain at an early stage, with Malaysia's hydrogen-mobility activities currently centred more on technology demonstration, infrastructure development and ecosystem building.

One wider implication is becoming increasingly important: Malaysia's vehicle risk profile is changing alongside its automotive technology.

The growing population of HEVs, PHEVs and BEVs—and potentially FCEVs in the future—means that knowledge of high-voltage batteries, lithium-ion battery thermal runaway, stranded electrical energy, charging systems, hydrogen fuel, energy isolation, firefighting and rescue techniques will become increasingly important.

This transition therefore affects far more than vehicle manufacturers and owners. It has direct implications for emergency services, fire and rescue agencies, highway operators, insurers, workshops, charging-station operators, building managers, regulators and enforcement agencies.

Malaysia is not simply putting more electric vehicles on its roads. It is gradually transforming its entire mobility safety ecosystem.

Primary Sources

The primary data should be referenced from the Road Transport Department Malaysia (JPJ) and data.gov.my, with reputable automotive industry sources used for cross-referencing vehicle models, powertrain technologies, and market developments.

Note: The latest complete data used in this article covers the period up to 31 July 2026. Statistics for August 2026 have not yet been included, pending the publication and verification of the official JPJ dataset.