Battery Life Estimation Using Time Information Accumulation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for accurately estimating the state and life of electric vehicle batteries are inadequate, affecting user confidence and safety, as they fail to provide precise monitoring and prediction of battery degradation due to environmental and usage-related factors.
Innovation Solution
A battery life estimation apparatus that accumulates and analyzes time information from voltage, current, and temperature signals, using machine learning algorithms to predict the end-of-life (EOL) of the battery based on usage history and learning information, transforming input vectors to reduce dimensionality and enhance estimation accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If current battery state estimation methods are used, then device complexity is reduced, but measurement precision and reliability of battery life estimation deteriorate
Solution Approach 1:
The battery estimation apparatus is divided into distinct functional modules: a time information accumulator that collects usage data, a dimension transformer that processes the accumulated information, and a life estimator that predicts battery end-of-life. This segmentation allows each module to perform a specific function, improving overall estimation accuracy while keeping individual module complexity manageable
Solution Approach 2:
The patent introduces a time dimension by accumulating battery usage information over multiple cycles and transforming this temporal data into predictive insights. The dimension transformer converts accumulated time-series data into features that reveal degradation patterns, enabling more accurate life estimation without requiring complex hardware
2Reliability
If comprehensive battery monitoring is implemented, then reliability and safety are improved, but loss of time for state assessment increases
Solution Approach 1:
The time information accumulator continuously collects and preprocesses battery usage data in the background during normal operation, accumulating voltage, current, and temperature information across multiple charge-discharge cycles. This preliminary data preparation enables the life estimator to generate rapid predictions without requiring time-consuming assessments when battery state queries are made
Solution Approach 2:
The patent replaces traditional complex electrochemical modeling methods with a data-driven dimension transformation approach. By using mathematical transformations on accumulated usage data rather than computationally intensive physical models, the system achieves reliable battery life prediction with reduced calculation time
Data Source
AI summary
A method and apparatus for estimating a state of a battery are provided. A battery life estimation apparatus includes a time information accumulator configured to partition sensing data of a battery into sections, and to accumulate time information corresponding to the sections. The battery life estimation apparatus also includes a time information extractor configured to extract time information corresponding to a period from the accumulated time information. The battery life estimation apparatus further includes a life estimator configured to extract expected time information based on the accumulated time information, the time information corresponding to the period, and learning information, and configured to estimate an end of life (EOL) of the battery based on the expected time information.