Battery Capacity Estimation Using Usage-History Trend Groups
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for estimating secondary battery capacity fail to consider the varying usage histories of batteries, leading to estimation errors due to different usage patterns among batteries, and it is impractical to prepare relational expressions for all possible combinations of these factors.
Innovation Solution
A secondary battery capacity estimation system that utilizes a classification model trained through machine learning to group batteries based on their usage history and internal resistance, allowing for efficient estimation of capacity by considering the specific usage patterns of each battery.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a single relational expression is used to estimate battery capacity from internal resistance, then the estimation process is simple, but estimation accuracy deteriorates due to varying usage histories
Solution Approach 1:
The patent segments the battery population into multiple groups based on usage history characteristics (charging frequency, discharge depth, temperature exposure, etc.). Each group has its own relational expression between internal resistance and capacity, allowing accurate estimation for diverse usage patterns without requiring a single complex universal model.
Solution Approach 2:
The patent changes the parameters of the estimation model by introducing usage history parameters as classification criteria. Instead of using a fixed relational expression, the system adjusts the relational expression parameters based on the detected usage history group, thereby adapting the estimation accuracy to different operational conditions.
2Measurement precision
If multiple relational expressions are prepared for different usage histories, then estimation accuracy improves, but the system complexity increases
Solution Approach 1:
The patent divides the complex problem of estimating capacity for all possible usage histories into multiple simpler sub-problems by segmenting batteries into distinct usage groups. Each segment uses a relatively simple relational expression, and the segmentation itself is achieved through straightforward classification based on usage history parameters.
Solution Approach 2:
The patent performs preliminary classification of batteries into usage history groups before applying the relational expressions. This preliminary action organizes the data structure in advance, allowing the system to efficiently select and apply the appropriate relational expression without real-time complex decision-making.
3Measurement precision
If usage history information is collected and analyzed, then estimation accuracy improves, but the time required for estimation increases
Solution Approach 1:
The patent collects and analyzes usage history information in advance to pre-classify batteries into usage groups. This preliminary classification allows the estimation process to quickly retrieve and apply the appropriate relational expression without performing complex real-time analysis of usage patterns during capacity estimation.
Solution Approach 2:
By segmenting usage histories into distinct categories, the patent reduces the complexity of real-time analysis. Instead of continuously analyzing detailed usage patterns, the system simply determines which segment the current battery belongs to and applies the corresponding pre-prepared relational expression, significantly reducing estimation time.
Data Source
Figure 1
Figure 2~3
Figure 4
AI summary
Provided is a secondary battery capacity estimation system that can efficiently estimate the capacity of a secondary battery from the state of an internal resistance of the secondary battery even when the usage history of the secondary battery is different from others. The secondary battery capacity estimation system is a system that estimates the capacity of a secondary battery, which includes: a target secondary battery information acquisition unit that acquires target secondary battery information; a group determination unit that inputs, to a classification model, the usage history of a target secondary battery and internal resistance value increase information included in the target secondary battery information to determine a trend group of the target secondary battery; and a capacity estimation unit that estimates a capacity index value of the target secondary battery based on correlation information corresponding to the target secondary battery information and the trend group. The classification model is a trained model obtained by machine learning using the sample secondary battery information as training data, and configured to output a trend group to which the target secondary battery is relevant when the target secondary battery information is input.