Machine learning approach for solving inconsistency problems of Li‐ion batteries during the manufacturing stage

Abstract

The inconsistency in the mass production of lithium-ion battery (LIB) packs stem from the inconsistency in the capacity, voltage and internal resistance of single batteries that compose packs. The inconsistency issue of these battery packs can greatly reduce the output performance of a large power pack. This paper proposed the machine learning approach based on self-organization mapping (SOM) neural networks for establishing the consistency of LIBs. This method comprehensively compares and analyzes the real-LIB parameters (internal resistance, capacity and voltage) data obtained during charging and discharging to form the clusters of similar performing LIBs. Experimental result validated the clustering analysis and it indicates that the performance of clustered battery pack typically precedes than that of original. The capacity of clustered battery pack increased 1.9% compared with brand-new pack. The temperature distribution of the battery pack assembled after screening is consistent. The peak temperature is 4°-5° lower than the ordinary battery, and the temperature fluctuation is reduced by 2.6°. In addition, the application of cluster analysis is expanded and some key research directions are pointed out.