Battery Pack Charging Profiles for AI Lithium Plating Prediction
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 transformations 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 machine learning models are trained in advance using historical sensor data and voltage profiles to recognize patterns indicative of lithium plating. This preliminary training enables the system to make accurate predictions during operation without requiring complex real-time analysis infrastructure.
Solution Approach 2:
The patent introduces machine learning models as an intermediary layer between raw sensor measurements and lithium plating detection. These models process and interpret the sensor data, transforming complex measurement patterns into actionable predictions while maintaining system modularity.
2Measurement precision
If voltage profile transformations and mean-comparison features are used, then measurement precision is improved, but calculation time increases
Solution Approach 1:
The voltage profile transformations and mean-comparison feature extractions are performed on historical data during the model training phase. This preliminary processing creates optimized feature representations that can be quickly evaluated during real-time operation without repeating computationally intensive transformations.
Solution Approach 2:
The patent applies selective transformations and feature extractions only to the extent necessary for accurate prediction. By identifying and processing only the most relevant voltage profile characteristics, the system achieves high detection accuracy while minimizing unnecessary computational overhead.
Data Source
AI summary
In one aspect, computer-implemented method may include, while a battery pack is charging, receiving, from sensors, measurements associated with the battery pack. The battery pack includes cells. The method may include separating the measurements into separate profiles for the cells, wherein the separate profiles include data pertaining to current, voltage, temperature, or some combination thereof. The method may include identifying, using the separate profiles, features, generating a training dataset by reducing the features based on a mean-comparison technique, a minority scaling technique, or both, and generating a trained machine learning model using the training dataset including the reduced features as labeled input and true lithium plating occurrence statuses as labeled output. The method may include predicting, using the trained machine learning model, an occurrence of lithium plating by inputting subsequently received data into the trained machine learning model.