AI Battery Cell Detection for Lithium Plating Risk
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Lithium-ion batteries face premature degradation and reduced lifespan due to lithium plating, which can lead to short circuits and increased recycling demands, with existing detection methods being invasive and inefficient.
Innovation Solution
A computer-implemented method using machine learning models trained with sensor data from battery packs to predict lithium plating occurrences, allowing for early detection and preventative actions, such as replacing faulty cells, through voltage profile analysis and mean-comparison features.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If machine learning models are used to predict lithium plating, then detection accuracy is improved, but device complexity increases
Solution Approach 1:
The patent introduces voltage profile analysis as an intermediary step between raw sensor data and lithium plating detection. The system transforms sensor measurements into voltage profiles, then applies machine learning models to these processed profiles rather than raw data directly. This intermediary transformation layer improves detection accuracy while managing complexity by structuring the data flow in manageable stages.
Solution Approach 2:
The patent segments the detection process into distinct modules: sensor data acquisition, voltage profile generation, transformation operations, feature extraction, and machine learning prediction. Each module handles a specific aspect of the detection task, improving overall accuracy while allowing independent optimization and maintenance of each segment, thereby managing device complexity.
2Duration of action of stationary object
If early detection of lithium plating is implemented, then battery lifespan is extended, but loss of time for data processing increases
Solution Approach 1:
The system performs preliminary transformations on voltage profiles during normal operation, preparing feature data in advance for the machine learning model. By pre-processing the voltage data and extracting features continuously as data becomes available, the system enables early detection of lithium plating without requiring lengthy batch processing, thus extending battery lifespan while minimizing processing time delays.
3Measurement precision
If fleet data is used for training machine learning models, then prediction accuracy is improved, but loss of information during data transmission increases
Solution Approach 1:
The patent extracts only the essential features from raw fleet data before transmission and storage. Instead of transmitting and storing complete raw sensor datasets, the system processes data locally to extract meaningful features (such as voltage profile characteristics) and transmits only these extracted features for model training. This reduces data transmission volume and minimizes information loss while maintaining prediction accuracy.
Data Source
AI summary
In one aspect, computer-implemented method may include receiving, from a cloud-based computing system, one or more machine learning model parameters that are configured to enable predicting a remaining useful life of each cell of a battery pack of a vehicle. The method may include loading, into memory of a processing device at the vehicle, the one or more machine learning model parameters, receiving data comprising one or more measurements and one or more user battery usage profiles, and based on the data, executing a trained machine learning model with the one or more parameters to input the data and to output the remaining useful life of each cell of the battery pack.