Battery Module Strain Estimation from Stress and Swelling Force

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current methods fail to accurately estimate strain in battery modules due to the lack of a direct correspondence between stress and strain, which can lead to deformation and potential damage from swelling pressures, especially in modular battery systems.

Innovation Solution

A module strain estimating apparatus and method that uses a learning module to derive a correspondence between stress and strain based on numerical information from the battery module, generating profiles to estimate strain under various forces and stresses, facilitating easier design and monitoring of battery modules.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If conventional methods are used to determine battery module deformation, then the measurement process becomes complex and time-consuming, but the accuracy of strain estimation remains insufficient

Engineering Contradiction:
Improvestrain estimation accuracyVSAvoidmeasurement process complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent replaces complex mechanical measurement systems with a machine learning-based computational approach. The processor uses trained neural network models to estimate strain directly from stress data and battery module parameters, eliminating the need for complex physical measurement apparatus while improving accuracy

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

Solution Approach 2:

The patent introduces a machine learning model as an intermediary between stress measurement and strain calculation. This intermediary processes the relationship between stress and strain through learned patterns from training data, providing accurate strain estimation without direct complex measurement

Inventive Principle:
Principle #24Intermediary (Mediator)

2Measurement precision

If direct stress-strain measurement methods are used, then measurement precision improves, but the device complexity and time consumption increase significantly

Engineering Contradiction:
Improvestrain measurement accuracyVSAvoidmeasurement time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent performs preliminary training of machine learning models offline using extensive datasets before actual strain estimation. This preliminary action creates pre-trained models that can quickly estimate strain in real-time applications, separating the time-consuming training phase from the rapid inference phase

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent substitutes time-consuming direct measurement methods with a computational model that provides rapid strain estimation once trained, significantly reducing measurement time while maintaining precision

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

3Reliability

If traditional deformation determination methods are applied, then the process becomes cumbersome and difficult to implement, but reliable strain data is needed for safety assessment

Engineering Contradiction:
Improvestrain data reliabilityVSAvoidimplementation ease
Core Design Contradiction:
ReliabilityVSEase of operation

Solution Approach 1:

The patent implements a self-service system where the machine learning model automatically learns the complex stress-strain relationships from training data and performs strain estimation without requiring complex manual measurement procedures. The system serves itself by using input parameters and stress data to generate reliable strain outputs

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent replaces cumbersome mechanical measurement and calculation methods with an automated computational approach using machine learning, significantly improving ease of implementation while maintaining data reliability

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

Data Source

PatentEP4063820B1Module strain estimating apparatus and method
Publication Date: 2024.02.28 LG ENERGY SOLUTION LTD
  • EP4063820B1 patent drawingFigure 1
  • EP4063820B1 patent drawingFigure 2
  • EP4063820B1 patent drawingFigure 3

AI summary

A module strain estimating apparatus according to an embodiment of the present disclosure includes: a module information obtaining unit configured to obtain a plurality of numerical information for a battery module; and a processor configured to receive the plurality of numerical information from the module information obtaining unit, generate a first profile representing a correspondence between a force applied from the inside of the battery module to the outside and a strain of the battery module and a second profile representing a correspondence between the force and a stress of the battery module based on a preset learning module and the plurality of numerical information, generate a third profile representing a correspondence between the strain and the stress of the battery module based on the first profile and the second profile, and estimate a strain of the battery module according to a stress of the battery module based on the third profile.