AI-Powered Thermal Control in EV Batteries

Battery management system (BMS) for lithium batteries that monitors battery temperature and environment temperature in real-time to proactively heat the battery if needed. The system has a battery monitoring unit and an auxiliary heating unit. If the battery temperature is low and charging is detected, or if the ambient temperature is low and vehicle usage time is reached, the auxiliary heating unit is activated to warm the battery. This prevents excessive internal resistance, voltage instability, and loss issues that occur at low temperatures.

Source

Predicting thermal failure of new energy vehicle batteries using a time-varying twin converter model. The method involves converting the multi-element battery signal into time-series features using downsampling and segmented sampling techniques. These features are extracted using a time attention mechanism to capture both global and local signal variations. The extracted features are then fed into a neural network for predicting battery thermal failure.

Source

A battery temperature control method and system that reduces power consumption while still maintaining optimal battery temperature for charging and discharging. The method involves predicting the battery temperature as the vehicle travels based on the planned route. If the predicted temperature exceeds a threshold, an excessive cooling amount is calculated. This excessive cooling amount is then subtracted from the predicted cooling need at the first point in the route. This shortens the time the cooling device operates. By accounting for the predicted future temperature, it prevents overcooling. Similar steps are taken for heating. This avoids overshooting the target temperature when heating is needed later.

Source

Thermal management system for electric vehicles that uses reinforcement learning to optimize cooling and heating of components like batteries and motors during driving. The system has separate thermal modules for components like batteries and motors that can be controlled by an "Agent" using reinforcement learning. A prediction module forecasts future conditions. By learning optimal strategies based on driving, environment, and historical data, the Agent decides when to actively cool or heat components to balance comfort, aging, and efficiency. The navigation system and vehicle electronics enable real-time implementation.

Source

Method for predicting battery temperature in vehicles to improve battery performance and longevity. The method involves using a pre-trained battery temperature prediction model to accurately predict battery temperature at a future time based on current battery attributes. This allows better temperature control compared to just predicting linear models at the next time point. The prediction involves extracting features from the current battery attributes, generating an attention weight matrix based on those features, and using it to calculate the future temperature. This allows accurate temperature prediction even with longer time intervals.

Source

Battery thermal management system for electric vehicles that accurately, efficiently, and energy-savingly controls the temperature of the battery pack by combining the temperature distribution inside the battery and external ambient temperature. The system has a battery management module, temperature measurement module, temperature decision module, and temperature regulation module. The decision module analyzes the internal battery temperature distribution and external ambient temperature to determine the optimal cooling or heating strategy. This allows differentiated temperature control based on the specific heat distribution within the battery pack rather than just the surface temperature.

Source

Efficient and energy-saving vehicle battery thermal management control method and device that uses machine learning to optimize cooling of electric vehicle batteries. The method involves collecting sensor data from a target vehicle's battery and other components like ambient temperature, speed, and fan speed under different operating conditions. This data is analyzed to develop a battery thermal management strategy that can be embedded in the vehicle's battery management system. The strategy optimizes cooling based on factors like ambient temperature, speed, and fan speed to improve battery performance and life while reducing energy consumption compared to conventional cooling methods.

Source

Method for predicting battery cell temperature using historical data from other cells. The method involves obtaining cell parameter information (like SOC, voltage, etc.) for a target cell at different steps in time. These parameters are then fed into separate models trained for current prediction and temperature prediction. By inputting the first cell's historical parameters into the current model and the second cell's historical parameters into the temperature model, the target cell's temperature after a set time can be predicted. This improves accuracy compared to just using a physical model as it avoids needing all the physical parameters and reduces modeling errors.

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

Pre-cooling the battery before driving under high load conditions to prevent output limitations and improve stability. The method involves predicting when the vehicle will encounter high load conditions based on navigation input. If the battery temperature is below a threshold before that time, components of the battery cooling system are controlled to further cool the battery until the target temperature is reached. This proactive cooling prevents the battery from overheating during high load driving and prevents output limitations.

Source

Predictive cooling control system for electric vehicles that improves cooling efficiency and reduces component damage by anticipating thermal demands and proactively cooling components before they overheat. The system uses advanced demand information like navigation, environmental, and thermal feedback to generate predictive cooling commands. This allows subcooling components before high loads to prevent overheating. By anticipating cooling needs, the system can avoid thermal runaway and component damage compared to reactive cooling approaches.

Source

Hard-pack lithium battery safety monitoring using deep learning to improve accuracy of detecting temperature abnormalities in individual cells. The method involves monitoring battery working state to extract temperature features at different steps: cell temperature difference, kernel PCA, homologous expansion, feature fusion, dynamic weighting, and vector conversion. This multi-step extraction improves understanding of cell states. A preset temperature analysis model processes the converted vectors to detect anomalies, then makes specific processing strategies for each cell based on the overall analysis.

Source

Optimizing battery temperature control in electric vehicles to improve performance and reduce waste. The method involves dynamically determining the optimal time to precondition the battery based on the vehicle's usage schedule rather than using a fixed advance time. This prevents over-early or over-late temperature adjustment that can waste energy or negatively impact battery life.

Source

Battery cooling control method for electric vehicles to reduce energy consumption and improve range. The method predicts vehicle arrival time, battery temperature rise rate, and predicted battery temperature. It dynamically adjusts the battery cooling output power based on the predicted temperature difference to match the desired temperature. This adaptive cooling reduces system energy consumption compared to fixed cooling. Multiple target temperature intervals with different cooling strategies are used to further optimize cooling.

Source

A vehicle battery cooling method that predicts the speed of a vehicle to determine the cooling needs of the battery. Historical big data of the vehicle's road conditions and speeds are used to predict the future speed. Based on this predicted speed and the battery's attributes, a temperature curve is determined. The vehicle then cools the battery using this curve to prevent overheating. This allows preemptive cooling based on the expected speed and road conditions to avoid battery damage from overheating.

Source

Predictive thermal management for electric vehicles that proactively regulates temperatures of the battery and motor based on current location and driving route. It determines optimal thermal strategies like cooling or heating based on attributes of the upcoming driving area. This allows targeted temperature control instead of reactive cooling/heating delays. It leverages electronic maps and vehicle location to anticipate conditions like high-speed entrances, charging areas, ramps, and parking spots.

Source

Estimating the surface temperature of a lithium ion battery using a deep neural network to improve battery monitoring and management. The method involves feeding inputs like voltage, current, charge state, and ambient temperature into a neural network trained on historical battery data. The network learns to predict the battery surface temperature. The neural network architecture uses long short-term memory (LSTM) gates to handle sequential inputs. The training involves finding an optimal filtering frequency for the input signals. The neural network is implemented on a battery management system.

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

Battery thermal management system for electric vehicles that improves performance and reduces energy waste. The system uses vehicle information and driver feedback to predict and optimize battery cooling. It adds man-machine interaction to the vehicle controller, generates auxiliary driving info, and acquires driver feedback. Using a simulation model, it predicts battery heating based on vehicle conditions. It also calculates a target heating value based on battery current. Then it adjusts the battery cooling system like pumps and fans to match the predicted or target heating. This improves response time and robustness compared to just controlling the cooling system.

Source

Battery thermal management system for heavy-duty electric trucks that efficiently controls battery temperature using a three-source heat pump architecture. The system utilizes waste heat from the air source and motor to heat and cool the battery instead of just using the compressor. The system intelligently determines the optimal thermal management mode based on vehicle status, ambient temperature, and battery conditions. It also partitions the battery into zones to enable more targeted temperature control. The goal is to save energy by maximizing use of available heat sources and avoiding excessive compressor activation.

Source