Battery Capacity Estimation from Charging Intervals and GPR Features

Solution Overview

Problem

Existing methods for battery capacity estimation in lithium-ion batteries require large amounts of data and time, leading to inaccurate predictions and potential shutdowns due to capacity jumps, especially as batteries age.

Innovation Solution

A method using a Gaussian process regression model for battery capacity estimation based on charging current, voltage, and time intervals, reducing data requirements by utilizing electrochemical and time domain features, and employing principal component analysis to optimize model training.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If complete experimental cycling data is used for battery capacity estimation, then estimation accuracy is improved, but data amount and estimation time increase significantly

Engineering Contradiction:

Improvebattery capacity estimation accuracyVSAvoidestimation time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent extracts only the essential charging voltage and charging current data segments from complete experimental cycling data, eliminating unnecessary data while preserving the key information needed for accurate capacity estimation through the constructed neural network model

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

Instead of using complete cycling data, the patent applies partial action by utilizing only the charging process data segments that contain the most relevant information for capacity estimation, reducing data processing requirements while maintaining estimation accuracy

Inventive Principle:

Principle #16Partial or excessive action

2Measurement precision

If complete experimental cycling data is used for battery capacity estimation, then estimation accuracy is improved, but data amount increases

Engineering Contradiction:

Improvebattery capacity estimation accuracyVSAvoiddata amount

Core Design Contradiction:

Measurement precisionVSQuantity of substance

Solution Approach 1:

The patent extracts only the essential charging voltage and charging current data segments from complete experimental cycling data, eliminating unnecessary data while preserving the key information needed for accurate capacity estimation through the constructed neural network model

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

Instead of using complete cycling data, the patent applies partial action by utilizing only the charging process data segments that contain the most relevant information for capacity estimation, reducing data processing requirements while maintaining estimation accuracy

Inventive Principle:

Principle #16Partial or excessive action

3Device complexity

If traditional capacity estimation methods are used for aged batteries, then computational simplicity is maintained, but accuracy decreases leading to capacity jumps and shutdowns

Engineering Contradiction:

Improveestimation method complexityVSAvoidbattery capacity estimation accuracy

Core Design Contradiction:

Device complexityVSMeasurement precision

Solution Approach 1:

The patent performs preliminary action by constructing and training a neural network model in advance using charging voltage and current data, so that when the battery is in use, the model can quickly and accurately estimate capacity without complex real-time calculations, preventing capacity jumps and shutdowns

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent changes the estimation approach from traditional methods to a neural network-based method that processes charging voltage and current parameters, improving accuracy for aged batteries while maintaining computational efficiency through the pre-trained model

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentEP4253974B1Battery capacity estimation method, electronic apparatus and storage medium

Publication Date: 2026.03.18 DONGGUAN NVT TECH

Figure 1
Figure 2
Figure 3

AI summary

This application discloses a method of battery capacity estimation including: obtaining a charging current, charging voltage, and charging time of a battery being estimated and a charging voltage interval; determining a charging current interval and a charging time interval based on the charging current, the charging voltage, and the charging time, where the charging current interval and the charging time interval correspond to the charging voltage interval; obtaining training features for model training, where the training features include training electrochemical features and training time domain features; determining actual features of the battery being estimated based on the charging voltage interval, the charging current interval, the charging time interval, and the training features, where the actual features include actual electrochemical features and actual time domain features; and estimating, based on the model and the test features, an actual capacity of the battery being estimated. This application also provides an electronic apparatus and a storage medium that can reduce the amount of data required and shorten the estimation time.