Battery Pack Cell Arrangement Using Machine Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current battery pack construction in vehicles does not optimize cell arrangement for maximum performance, life, and efficiency, leading to suboptimal operation, heat-related issues, and wastage of low-quality cells.
Innovation Solution
A method using machine learning to analyze data from fleet vehicles and battery testing devices to generate predictive models for estimating electrical characteristics of cells, determining optimal arrangements within battery packs, and directing the arrangement of cells based on these characteristics.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If cells are arranged without optimization in battery packs, then manufacturing process is simple, but battery pack performance and life are suboptimal
Solution Approach 1:
The system performs preliminary analysis of cell characteristics data before battery pack assembly, using machine learning models to predict electrical characteristics and determine optimal arrangement configurations in advance, thereby optimizing performance before the cells are physically assembled into packs
Solution Approach 2:
The patent replaces traditional manual or rule-based cell arrangement methods with machine learning-based predictive modeling and automated arrangement determination, substituting mechanical/physical optimization processes with computational intelligence to achieve superior battery pack performance
2Reliability
If low quality cells are excluded from battery packs, then battery reliability improves, but cell wastage increases
Solution Approach 1:
The system applies local quality assessment by evaluating individual cell characteristics and assigning specific cells to particular positions within battery packs based on their unique electrical properties, rather than applying a blanket exclusion criterion to all cells below a certain quality threshold
Solution Approach 2:
The patent changes the quality assessment parameter from a binary pass/fail inspection to a continuous electrical characteristic profile, using machine learning to predict performance based on multiple parameters including voltage, impedance, and capacity, thereby enabling nuanced utilization of cells that would traditionally be rejected
3Productivity
If machine learning predictive models are used to estimate electrical characteristics, then cell arrangement optimization improves, but system complexity and computational requirements increase
Solution Approach 1:
The system performs preliminary training of machine learning models using historical cell data before deployment, establishing predictive capabilities in advance that enable rapid optimization during battery pack assembly without requiring complex real-time computations
Solution Approach 2:
The patent uses machine learning models to create virtual representations or copies of cell electrical characteristics based on limited measured data, allowing the system to predict full performance profiles without requiring exhaustive testing of each cell, thereby reducing computational complexity while maintaining optimization effectiveness
Data Source
AI summary
Systems, methods, and storage media for arranging a plurality of cells in a vehicle battery pack are disclosed. A method includes receiving, by a processing device, data pertaining to cells within a battery pack installed in each vehicle of a fleet of vehicles, the data received from at least one of each vehicle in the fleet and one or more battery testing devices, providing, by the processing device, the data to a machine learning server, directing, by the processing device, the machine learning server to generate a predictive model, the predictive model based on machine learning of the data, estimating, by the processing device, one or more electrical characteristics of each cell to be included in the vehicle battery pack based on the predictive model, and directing, by the processing device, an arrangement of the cells within the battery pack based on the electrical characteristics.