Battery Cell Abnormality Detection Using Standardized Pack Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Detecting abnormality in a battery cell within a battery pack composed of multiple cells is challenging due to the difficulty in identifying individual cell states among a plurality of interconnected cells.
Innovation Solution
An electronic device with a battery module, detection circuit, and processor that processes input data as an M×N matrix to standardize and analyze column vectors, using a learning-based model and other schemes to determine first and second state abnormalities in battery cells, employing techniques like offset removal, smoothing, and window averaging to identify cell anomalies.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Power
If multiple battery cells are connected in series and/or parallel to form a battery pack, then the output voltage and charge/discharge capacity are improved, but the difficulty of detecting abnormality in individual battery cells increases
Solution Approach 1:
The patent applies segmentation by dividing the battery pack into individual battery cell units for separate monitoring. Each battery cell's state values are obtained independently through the detection circuit, allowing individual abnormality detection despite being connected in series/parallel configurations. The processor analyzes each cell's data separately to identify abnormalities in specific cells within the pack.
Solution Approach 2:
The patent introduces an intermediary detection circuit and processing system between the battery cells and the monitoring system. This intermediary layer standardizes the state values from multiple cells and applies learning-based models to detect abnormalities, effectively bridging the gap between the complex multi-cell configuration and the abnormality detection requirement.
2Reliability
If state values of multiple battery cells are obtained simultaneously, then the comprehensiveness of battery monitoring is improved, but the complexity of data processing increases
Solution Approach 1:
The patent transforms the raw state values from multiple battery cells into standardized data through parameter changes. The standardization process converts diverse state values into a unified format suitable for learning-based model analysis. This parameter transformation simplifies the subsequent abnormality detection process while maintaining comprehensive monitoring of all battery cells.
Data Source
AI summary
An electronic device obtains input data through a detection circuit, standardizes each of column vectors of the input data to obtain standardized data for the input data, obtains determination reference data based on the standardized data, and determines first state abnormality and/or second state abnormality of each of the M battery cells based on values indicated by the entries of respective row vectors of the determination reference data. The first state abnormality is determined based on a learning-based model, and the second state abnormality is determined based on a scheme other than the learning-based model.