ML for Lithium-Ion Battery Thermal Runaway Prevention in EVs

Early warning system for fire prevention using visual and thermal sensing. The system combines visual and thermal images to detect temperature anomalies and identify the object causing the anomaly. This provides object-aware temperature monitoring to prevent false alarms and accurately predict fire risks. Computer vision is applied to visual images to classify objects, while thermal images detect temperature changes. By fusing the data, sudden temperature spikes in specific object features like batteries can be linked to their location and identified as fire hazards.

Source

Intelligent vehicle system that predicts and responds to thermal runaway events in vehicle batteries when parked in enclosed spaces. The system detects battery cell overheating and determines if the vehicle is parked in an enclosed area using sensors and vehicle data. If so, it alerts nearby people and first responders about the thermal event and provides instructions to evacuate the area. This mitigates risks from battery fires when parked indoors. The system also disconnects the battery to prevent spreading.

Source

Detecting anomalies in the behavior of electrical energy storage devices like vehicle batteries without relying on physical sensors inside the battery. The method involves monitoring operating variables of the battery, extracting features from the operating profiles, and using a variational autoencoder to compare the features against a distribution. A deviation from the distribution indicates an anomaly. This allows detecting battery issues without needing to directly measure internal battery aging.

Source

Determining abnormalities in time-series waveform data using machine learning. The method involves learning abnormality using an autoencoder and persistent homology conversion. The autoencoder learns normal waveforms. Persistent homology calculates changes in connected components based on threshold changes. A learner with inputs from the autoencoder and persistent homology determines abnormality. This improves accuracy compared to just using the autoencoder by capturing more waveform features.

Source

Thermal runaway in lithium-ion batteries generates toxic and flammable gases such as CO, C2H2, C2H4, presenting severe safety risks. Early detection of these is essential for battery monitoring. In this study, the gas sensing performances pristine Pt-doped indium selenide (InSe) monolayers toward C2H4 were investigated using first-principles density functional theory (DFT). The adsorption energies, charge transfer, electronic structure changes systematically analyzed to evaluate sensitivity. Results indicate that InSe exhibits weak interaction with all target gases. However, Pt doping significantly enhances increased energies substantial transfer. dopant also modulates InSe, which favorable signal transduction. These findings demonstrate possess excellent selectivity sensitivity critical warning from thermal runaway, offering theoretical guidance design high-performance 2D material-based sensors.

Source

Detecting abnormal temperatures in real-time with high accuracy, even when there is a change in ambient temperature. The method involves calculating temperature features, synthesizing them with past normal/abnormal indicators, training a model on the synthesized data, and using the model to determine if new temperature data is normal or abnormal. This allows accurate detection of abnormal temperatures even when ambient temperature changes, as the synthesis captures the difference between normal and abnormal temperature trends.

Source

Predicting thermal propagation between battery cells to prevent thermal runaway events. A thermal model is used to determine the likelihood of thermal propagation between cells based on their temperatures. The model is received by the battery management system and applied to the temperatures of specific cells to calculate the risk of thermal propagation between them. This helps prevent chain reactions that can lead to runaway conditions.

Source

Predicting thermal runaway events in battery packs to provide earlier warning and enable mitigation before catastrophic failure. The prediction is based on a thermal runaway model that takes attributes of the battery cells as input. The model simulates structural deformation, electrochemical behavior, and module-level interactions to predict if a cell will undergo thermal runaway. By feeding real-time cell data into the model, it can alert when conditions are trending towards runaway, giving time to intervene and potentially prevent the event.

Source

Abstract Thermal runaway in lithium-ion batteries is a critical safety concern for the battery industry due to its potential cause uncontrolled temperature rises and subsequent fires that can engulf pack surroundings. Modeling simulation offer cost-effective tools designing strategies mitigate thermal runaway. Accurately simulating chemical kinetics of runaway, commonly represented by systems Arrhenius-based Ordinary Differential Equations (ODEs), requires fitting kinetic parameters experimental calorimetry data, such as Accelerating Rate Calorimetry (ARC) measurements. Particle Swarm Optimization (PSO) offers promising approach directly data. Yet, created multiple Arrhenius ODEs, computational cost using brute-force searches entire parameter space simultaneously become prohibitive. This work introduces divide-and-conquer based on PSO fit N-equation ODE models ARC The proposed method achieves more accurate compared while maintaining low costs. analyzed two distinct datasets, resulting are further validated through simulations 3D oven tests, showing excellent agreement with data align... Read More

Source

Thermal runaway remains a critical safety challenge for lithium-ion batteries (LiBs) used in electric vehicles (EVs), with varying characteristics across different chemistries. This study presents comparative analysis of thermal predictions five widely LiB chemistries: Nickel Manganese Cobalt (NMC), Aluminum (NCA), Lithium Iron Phosphate (LFP), Oxide (LMO), and Titanate (LTO). A hybrid methodology combining controlled experimental abuse tests advanced physics-based machine learning models was employed to predict onset temperatures propagation behavior. Results reveal significant differences stability prediction accuracy among chemistries, LFP LTO exhibiting higher more reliable model predictions, whereas NMC NCA showed earlier rapid temperature escalation. These findings have direct implications battery management system (BMS) design protocols EVs, emphasizing chemistry-specific thresholds response strategies.

Source

Ensuring the safety of lithium-ion power batteries is primary prerequisite for developing electric vehicles and energy storage systems. The conventional method relies on temperature parameters only qualitatively assesses state (SOS), which reduces warning time battery management system (BMS). Here we present a thermal runaway based SOS. Specifically, analyze strain evolution trend under different abuse conditions propose trigger point runaway. Furthermore, multidimensional such as rise, median voltage, capacity, power, are used to quantify SOS parameter, with its value ranging from 0% 100%. Experimental results demonstrate that presented approach can warn around 5 h in advance.

Source

Automatically generating context-aware machine learning models for anomaly detection using feedback from model outputs. The technique involves generating multiple machine learning models using different field combinations from the input data. This provides context-awareness as the models analyze the data from multiple perspectives. Feedback from model outputs over time is analyzed to improve the models. This closed-loop process continuously enhances model quality and reduces false positives.

Source

Time-resolved scanning probe microscopy methods, like time-resolved electrostatic force (trEFM), enable imaging of dynamic processes ranging from ion motion in batteries to electronic dynamics microstructured thin film semiconductors for solar cells. Reconstructing the underlying physical these techniques can be challenging due interplay cantilever physics with actual transient kinetics interest resulting signal. Previously, quantitative trEFM used empirical calibration or feed-forward neural networks trained on simulated data extract interest. Both approaches are limited by interpreting signal as a single exponential function, which serves an approximation but does not adequately reflect many realistic systems. Here, we present multibranched, multioutput convolutional network (CNN) that uses addition parameters input. The CNN accurately extracts describing both single-exponential and biexponential functions more reconstructs real experimental presence noise. This work demonstrates application physics-informed machine learning complex processing tasks, enabling efficient accurate ana... Read More

Source

Early detection of abnormally deteriorated cells in battery modules to prevent safety issues like thermal runaway or ignition. The method involves monitoring capacity deviations of multiple cells over time. It calculates statistical values representing the capacity variations at two different time points. By comparing these values, it can detect cells that have significantly deteriorated compared to the others, indicating an abnormality.

Source

The thermal runaway of lithium-ion batteries is a critical factor influencing their safety. Investigating the characteristics essential for battery safety design. In this study, 18650 under different SOCs were systematically analyzed by experiment and simulation. It was found that at high SOC (100%), highly lithium state accelerated lattice oxygen release, promoted formation LiNiO intensified electrolytic liquid oxygenation combustion, while low (20%), reduction environment dominated, metal Ni residual graphite significantly enriched. Gas analysis shows CO2 H2 account more than 80%, proportion regulated SOC. Temperature pressure monitoring showed increase in increased peak temperature (100% up to 508.4 C) (0.531 MPa).The simulation results show when pack out control, ejection fire explosion wave are concentrated middle upper region (overpressure 0.8 MPa). This study reveals mechanism which affects path product gas generation regulating oxidation/reduction balance, lays theoretical foundation safe design quantitative evaluation runaway.

Source

Lithiumion batteries are the dominant battery type for emerging technologies in efforts to slow climate change. Accurate and quick estimations of state charge (SOC) internal cell temperature vital battery-management systems enable effective operation portable electronics electric vehicles. Therefore, a long short-term memory (LSTM) recurrent-neural network is proposed which completes estimation SOC average (Tavg) lithiumion under varying current loads. The trained evaluated using data compiled from newly developed extended single-particle model coupled with thermal dynamic model. Results promising, root mean square values typically 2% 1.2 K Tavg, while maintaining training testing times. In addition, we examined comparison single-feature versus multi-feature network, as well two different approaches partitioning.

Source

Abstract The widespread adoption of lithium batteries has raised concerns regarding safety due to the risk thermal runaway. mechanisms by which State Charge (SOC) and internal heat generation influence runaway in these remain unclear. In this study, we utilize a three-dimensional electrochemical-thermal coupled model investigate evolution with increasing temperature examining growth rate. Our findings indicate that: (1) both rate during initially increase before eventually decreasing; (2) an SOC leads reduction intercalation concentration at negative electrode, resulting decreased lower peak temperatures runaway; (3) significantly impacts critical time runaway, higher associated increased risk. These results provide theoretical support for optimizing battery preventing fires explosions.

Source

The paper presents the concept and modeling results of a multisensor system designed to prevent thermal runaway in lithium-ion batteries. This is especially true for LCO, NMC NCO integrates three types sensors: capacitive pressure sensor, gas sensor based on metal oxide semiconductor, platinum temperature sensor. Moreover, all sensors are located single chip, which ensures increased reliability safety, minimizing risks fire, explosion, or damage Three battery operating modes proposed: normal, hazardous, critical. In normal mode, concentration remain at safe levels, while hazardous they begin increase, indicating possible onset destructive reactions. critical reaches can lead damage, explosion. was modeled using COMSOL Multiphysics 6.1 package finite element method. approach helps improve safety batteries by solving problems monitoring their condition. scalability makes it suitable applications both portable electronics electric vehicles.

Source

<div class="section abstract"><div class="htmlview paragraph">Thermal runaway in battery cells presents a critical safety concern, emphasizing the need for thorough understanding of thermal behavior to enhance and performance. This study introduces newly developed AutoLion 3D model, which builds on earlier 1D framework offers significantly faster computational performance compared traditional CFD models. The model is validated through simulations heat-wait-search mode Accelerating Rate Calorimeter (ARC), accurately predicting by matching experimental temperature profiles from peer-reviewed studies. Once validated, employed investigate LFPO under controlled heating conditions, applying heat one or more surfaces at time while modeling transfer non-heated surfaces. primary objective understand how these localized patterns impact profiles, including average core temperatures surface each heated surface, examine evolution distributions over time. Additionally, explores effects varying rates using ARC assess different influence process. comprehensive approach aims provide valua... Read More

Source