Prevent Thermal Runaway in EV using Machine Learning

Detecting high impact scenarios using machine learning by iteratively generating test inputs with feature variations, simulating with the ML model to find output variations, and optimizing for maximized output variation with minimized input variation. This involves iteratively generating test inputs with feature variations, simulating with the ML model to find output variations, and using optimization to find the input feature that causes the most output variation with the least input variation. This allows identifying inputs that drastically change the ML output versus those with small changes.

Source

Determining failure of a vehicle component using trained artificial intelligence models to detect anomalies in measured signals. The method involves retrieving input signals correlated with the vehicle signal, predicting the signal using the AI model, determining a tolerance band, checking model validity, retrieving the actual signal, and determining if it's an anomaly based on the predicted, tolerance, and model validity. Counting and storing anomaly occurrences, and indicating component failure if a threshold of anomalies exceeds over time.

Source

Early warning system to detect thermal runaway in electric vehicle batteries using acoustic sensors. The system monitors sound waves emitted from battery cells to predict thermal runaway before it escalates. Acoustic sensors detect low frequency infrasound generated by gas bubbles forming during early stages of thermal runaway. An algorithm analyzes the acoustic data to predict thermal runaway. This allows earlier intervention to prevent escalation compared to temperature sensors.

Source

Estimating the internal temperature of a battery using impedance measurements at specific frequencies. The method involves applying a signal of a set frequency band to the battery, measuring the impedance, and using that impedance to estimate the internal temperature using a learning model. The set frequency band is determined based on a correlation between impedance and state of charge. By estimating internal temperature this way, it enables predicting battery fires before they occur.

Source

Multi-model fusion power battery thermal runaway early warning system that uses multiple warning models to accurately predict and warn of power battery thermal runaway failures. The system uses voltage, temperature, and heat transfer models to comprehensively monitor battery modules. It involves real-time acquisition of single cell voltages, historical voltage data, and internal temperature prediction using neural networks. The models consider voltage anomalies, physical heat generation, and cell-to-cell heat transfer. A decision model combines warnings for overall thermal runaway prediction. The multi-model fusion provides accurate early warnings and informed driver response to mitigate battery failure hazards.

Source

Lithium battery thermal runaway early warning method to improve accuracy and reduce calculation time compared to traditional methods. The method uses a deep learning model that integrates an offline electrothermal coupling model with an online model for surface temperature and voltage. A BiGRU neural network is trained using COA optimization to predict battery internal temperature. The method divides overcharge into three stages based on heat sources. This multi-stage prediction improves accuracy compared to single-stage direct prediction.

Source

Power battery temperature management method using a machine learning model to predict battery temperature and determine safe operating conditions. The method involves acquiring battery temperature and charge/discharge power data, extracting temperature correlation features, feeding them into a pre-trained LSTM model to predict future battery temperatures, and comparing the predictions to a threshold to determine temperature safety. This improves response speed and accuracy compared to conventional PID control.

Source

Battery thermal runaway early warning system using an electrochemical mechanism model to improve accuracy and reduce false alarms compared to traditional methods. The system predicts and warns of battery thermal runaway based on analyzing the battery's heat generation and iterating a model using real-time temperature, heating rate, and voltage data. It proposes a situation-based early warning scheme based on thermal trigger mechanisms rather than just monitoring temperature.

Source

An advanced warning system for battery thermal runaway using strain, temperature, and growth rate monitoring. The system uses a CNNLSTM neural network to detect when a battery is entering thermal runaway based on filtered strain, temperature, and growth rate data. It also defines a thermal runaway state using envelopes of the growth rates to quantify the severity of the runaway. The system provides early warning of thermal runaway by accurately predicting when it will occur and quantifying the runaway state in real-time.

Source

Early warning system for energy storage battery systems to prevent thermal runaway and improve safety. It uses real-time battery monitoring and simulation to detect and mitigate thermal runaway risks. The system obtains parameters like cell voltage, temperature, and gas concentration. It simulates cell behavior based on these inputs. By combining parameters like smoke concentration and module temperature, it determines thermal runaway risk levels. The system then takes appropriate actions based on the level to prevent escalation and protect the battery system.

Source

Early warning system to detect thermal runaway in energy storage systems like battery packs in electric vehicles or grid storage applications. The system uses a neural network model trained on historical temperature data to predict future temperatures. If the predicted temperature deviates significantly from actual readings or the reconstruction error is high, it indicates potential thermal runaway. This provides a more reliable and proactive warning compared to just monitoring individual sensor readings.

Source

Battery cabinet thermal runaway early warning method based on internal temperature estimation to accurately predict and prevent battery thermal runaway in energy storage systems. The method involves estimating the internal temperature distribution of the battery using a thermodynamic model considering charge/discharge current, voltage, resistance. This internal temperature is used to calculate the thermal runaway risk index. A multi-parameter early warning model combines this index, ambient temp, battery current to determine if early warning is needed. It provides real-time monitoring and warning of thermal runaway risk without requiring additional hardware.

Source

Early warning system for predicting battery thermal runaway to enable proactive intervention and mitigation. It uses a multi-factor scoring approach based on electrical and temperature characteristics to predict battery thermal runaway. The scoring involves factors like voltage overshoot, rate of voltage drop, temperature rise rate, and critical temperature. If scores consistently fall below thresholds, it indicates imminent thermal runaway.

Source

Temperature control for new energy batteries using a spatiotemporal recurrent neural network (STRNN) to accurately predict and mitigate thermal management risks. The STRNN model is trained using a customized loss function that prioritizes accurate prediction of high-risk thermal states. This allows the model to better anticipate and prevent potential thermal runaway events. The STRNN takes into account factors like battery environment, operating conditions, and history to provide proactive temperature control for new energy batteries in complex and variable environments.

Source

Early warning system for lithium-ion batteries in vehicles to detect and alert against thermal runaway caused by collision impacts. The system uses a combination of sensors, neural networks, and machine learning techniques to predict and mitigate battery failure and temperature spikes after collisions. It collects multiple battery characteristic physical quantities like voltage, temperature, and current to explore the connection between input features and failure. A combined neural network model with a deep CNN and LSTM predicts battery failure and temperature after collision. It uses weighted moving average filtering to smooth data, normalization to improve convergence, and multi-level warning strategies. This allows early warning before thermal runaway to take protective measures.

Source

Predicting and preventing thermal runaway in lithium-ion batteries used in electric vehicles to improve safety. The method involves predicting battery thermal runaway risk using a model based on battery status data, and then taking appropriate actions to prevent further runaway if risks are detected. The model analyzes factors like voltage, current, temperature, and charge level to predict battery state and identify triggers like overheating or internal shorts. If runaway indicators exceed thresholds, measures like cooling, ventilation, or disconnecting the battery are taken to prevent full runaway.

Source

Battery thermal runaway prediction method to determine if a vehicle's battery is at risk of overheating and thermal runaway. The method involves a two-step process: (1) assessing if the vehicle meets conditions indicating thermal runaway risk, and (2) if so, using a trained machine learning model to predict the battery's risk of thermal runaway. This allows targeted prediction for vehicles with elevated risk rather than using a single model for all vehicles. The risk assessment involves scoring factors like driving time, battery power, temperature, and weather.

Source

Lithium battery thermal runaway early warning method and system using unscented Kalman filters to accurately predict and provide early warning for battery thermal runaway in lithium batteries. The method involves estimating battery state of charge (SOC) and core temperature using unscented Kalman filters. This improves estimation accuracy compared to neural networks or electrochemical models. The early warning system uses this data to predict and diagnose battery thermal runaway.

Source

Early warning system for large-scale energy storage batteries to predict and mitigate thermal runaway events. The system uses real-time monitoring of voltage, temperature, and expansion force of the battery cells. It predicts cell state of charge (SOC) and state of health (SOH) using learned models. This allows accurate and timely detection of abnormal conditions that can lead to thermal runaway. The system proactively reports cell anomalies to prevent catastrophic failures.

Source

Battery thermal runaway early warning and protection system for lithium-ion batteries. The system uses deep learning to accurately predict battery thermal runaway events. It also provides adaptive protection strategies that dynamically adjust based on real-time monitoring data and battery status. This improves protection by tailoring measures to specific conditions rather than using one-size-fits-all strategies. The system also uses partitioned monitoring to provide independent monitoring of battery groups, regions, and fault locations. This allows more granular analysis and protection.

Source