Battery Test System Predicting Results Using Partial Data

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Standardized battery tests for automotive batteries can take weeks or months to complete, leading to delayed feedback for design and manufacturing processes, which can hinder timely adjustments and compliance with regulatory standards.

Innovation Solution

A battery testing system that uses a predictive model based on partial test data to forecast test outcomes, allowing for early prediction of battery performance and reducing the duration of testing, utilizing a computer-readable medium and processor-executable instructions to analyze historical data and provide predictions on battery characteristics like discharge capacity.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If standardized battery tests are conducted for extended periods to ensure accurate lifetime performance measurement, then measurement precision is improved, but loss of time increases

Engineering Contradiction:
Improveaccuracy of battery lifetime performance measurementVSAvoidduration of battery testing
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system performs preliminary analysis of battery test data at intermediate stages to predict final outcomes. By analyzing discharge capacity, charge capacity, and efficiency metrics during the test process, the system can forecast whether the battery will meet lifetime performance requirements before the complete test duration elapses, thus reducing the effective testing time required while maintaining measurement accuracy.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system continuously monitors battery test parameters and provides feedback through predictive analytics. By comparing real-time test data against historical patterns and performance thresholds, the system can determine with high confidence whether a battery will pass or fail lifetime performance requirements, enabling early termination of tests for clearly failing units and reducing overall testing time while preserving measurement precision.

Inventive Principle:
Principle #23Feedback

2Reliability

If full-duration standardized tests are completed to obtain reliable battery performance data, then reliability of test results is improved, but productivity decreases

Engineering Contradiction:
Improvereliability of battery test resultsVSAvoidspeed of battery design and manufacturing feedback
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The system applies partial action by analyzing only the most critical test parameters (discharge capacity, charge capacity, efficiency) at strategically selected intermediate time points rather than requiring complete test duration. This partial analysis provides sufficient reliability for design decisions while dramatically improving productivity by enabling earlier feedback in the development cycle.

Inventive Principle:
Principle #16Partial or excessive action

Solution Approach 2:

The system replaces the mechanical time-based testing process with a computational prediction model. Instead of waiting for physical test completion, the system uses machine learning algorithms and historical data patterns to predict final outcomes from intermediate measurements, substituting computational analysis for extended physical testing and thereby improving productivity while maintaining result reliability.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentEP3362809B1Battery test system for predicting battery test results
Publication Date: 2022.04.20 CPS TECHNOLOGY HOLDINGS LLC
  • EP3362809B1 patent drawingFigure 1
  • EP3362809B1 patent drawingFigure 2
  • EP3362809B1 patent drawingFigure 3

AI summary

A method of predicting battery test results includes using a battery test computer to predict a battery test result for a battery undergoing testing. The battery test computer comprises a tangible, non-transitory computer-readable medium storing a battery test management system implemented as one or more sets of instructions. The battery test management system includes a predictive module configured to predict the battery test result using less than all data required for the battery test to be complete, a validation module configured to validate the prediction, and a training module configured to re-train the predictive module based on results generated by the validation module. The battery test computer also includes processing circuitry configured to execute the one or more sets of instructions, and outputting, via a user interface, the prediction of the result and a confidence level associated with the prediction.