Machine learning-based early accelerated aging diagnosis method for ternary lithium ion battery

Abstract

The invention discloses a machine learning-based early accelerated aging diagnosis method for a ternary lithium ion battery. The method comprises the steps that 17 aging feature parameters representing the health state of the ternary lithium ion battery are extracted from a discharge capacity-voltage curve, a discharge IC curve and a discharge DV curve of the ternary lithium ion battery; then, a new combinatorial algorithm is utilized to accurately diagnose accelerated aging of the ternary lithium ion battery in an early stage, firstly, important features are selected through a random forest, then, linear correlation of the important features is reduced through linear correlation analysis, and finally, accelerated aging is judged through a logistic regression model. Accurate early diagnosis of accelerated aging of the ternary lithium ion battery is realized, so that whether accelerated aging of the ternary lithium ion battery occurs or not is judged in the early stage, and important information is provided for health state management and health state evaluation of the lithium ion battery.

Description

Technical field [0001] The present invention relates to a technical field three yuan battery health management, particularly the Three lithium-ion battery early machine learning diagnostic method of accelerated aging. Background technique [0002] Lithium-ion batteries during operation may undergo accelerated aging. Accelerated aging of lithium-ion batteries can reduce battery performance and lead to security problems. Therefore a lithium ion battery for the early diagnosis of accelerated aging of lithium-ion battery health management is very important. Accelerate the decline of the capacity of the lithium ion battery capacity is accompanied by rapid decay, and a substantial loss of lithium ions inside the positive and negative electrode material. Lithium-ion batteries are currently associated with accelerated degradation diagnosis method is based on logistic regression. States researchers are now increasingly concerned about the accelerated aging of lithium-ion batteries, and co...

AI Technical Summary

Problems solved by technology

Researchers from various countries are now paying more and more attention to the accelerated aging phenomenon of lithium-ion batteries, and have carried out research on the accelerated aging mechanism and inflection point identification of lithium-ion batteries, but the early diagnosis methods for accelerated aging are still lacking.

Traditional machine learning models can diagnose various faults, but the degradation mechanism of ternary lithium-ion batteries is complex and changeable, so the application of machine learning models to the accelerated aging diagnosis of ternary lithium-ion batteries requires the combination of battery-related knowledge

Images