Battery Capacity Estimation Using Converted Sensor Data Models
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current battery capacity estimation methods rely on full discharge, which is inefficient and requires significant computational resources, and lack accuracy and reliability.
Innovation Solution
A system and method utilizing sensors, a controller, and a data-driven model to estimate battery capacity without full discharge, employing data conversion and a data-driven BCE model trained with reduced data sets to improve efficiency and accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If Coulomb counting with full discharge is used for battery capacity estimation, then measurement precision is improved, but loss of time and use of energy increase significantly
Solution Approach 1:
The system performs preliminary actions by collecting and storing battery operational data (voltage, current, temperature) during normal use before the actual estimation is needed. This pre-collected data is then used to train the neural network model, eliminating the need for time-consuming full discharge cycles while maintaining estimation accuracy.
Solution Approach 2:
The patent creates a digital copy of the battery's operational characteristics through the neural network model trained on historical data. Instead of physically measuring capacity through full discharge, the system uses the trained model to predict capacity based on patterns from copied operational data, significantly reducing time requirements.
2Measurement precision
If Coulomb counting with full discharge is used for battery capacity estimation, then measurement precision is improved, but use of energy increases significantly
Solution Approach 1:
The system performs preliminary actions by collecting and storing battery operational data (voltage, current, temperature) during normal use before the actual estimation is needed. This pre-collected data is then used to train the neural network model, eliminating the need for time-consuming full discharge cycles while maintaining estimation accuracy.
Solution Approach 2:
The patent creates a digital copy of the battery's operational characteristics through the neural network model trained on historical data. Instead of physically measuring capacity through full discharge, the system uses the trained model to predict capacity based on patterns from copied operational data, significantly reducing time requirements.
3Device complexity
If traditional battery capacity estimation methods are used, then device complexity is kept simple, but measurement precision and reliability deteriorate
Solution Approach 1:
The patent replaces the mechanical/physical measurement system (requiring actual battery discharge through hardware circuits) with an information-processing system using neural networks. This substitution maintains hardware simplicity while dramatically improving measurement precision through computational analysis of operational patterns.
Solution Approach 2:
The patent creates a digital copy of the battery's operational characteristics through the neural network model trained on historical data. Instead of physically measuring capacity through full discharge, the system uses the trained model to predict capacity based on patterns from copied operational data, significantly reducing time requirements.
4Measurement precision
If comprehensive sensor data collection is performed continuously, then measurement precision is improved, but device complexity and computational resources increase
Solution Approach 1:
The system extracts only the essential features from comprehensive sensor data by feeding processed voltage, current, and temperature measurements into the neural network. The model automatically identifies and extracts the most relevant patterns from the data, filtering out unnecessary information while maintaining estimation accuracy without requiring complex processing of all raw sensor data.
Data Source
AI summary
A system for efficient battery capacity estimation includes vehicle with a battery, sensors, and a human-machine-interface (HMI). The vehicle has a controller that executes a battery capacity estimation (BCE) application. The BCE application performs local data collection from the sensors, transmits the data collected by the sensors to the remote servers where data conversion occurs and a data-driven BCE model is trained. Data conversion substantially reduces a size of and removes a time-dependency of the sensor data. The local vehicle portion of the BCE application receives, from the server, the data-driven model and estimates a capacity of a battery of the battery-operated device. Upon determining a battery capacity estimate, the system notifies vehicle users, via the HMI, of the current battery capacity estimate, and shares the current battery capacity estimate with additional vehicle sub-systems.