Lithium ion battery reliability evaluation method based on gray neural network model and self-service method

Abstract

According to the lithium ion battery reliability evaluation method based on the metabolism grey neural network model and the self-service method, the prediction precision is obviously improved compared with that of a common metabolism grey model and a BP neural network model; the combined model can make full use of the characteristics of strong learning ability, good non-linear mapping ability and simple gray model operation of a BP neural network model and the characteristic of low requirement of a self-service method for the number of samples, can better fit a battery performance degradation curve, has a better extrapolation prediction effect, and finally, the pseudo-life of the battery stored under different stresses is obtained, so that the reliability evaluation is completed more efficiently and at lower cost, and the final evaluation result has stronger objectivity and comprehensiveness.

Description

technical field [0001] The invention belongs to the technical field of lithium-ion battery reliability evaluation application research, in particular to a lithium-ion battery reliability evaluation method based on a gray neural network model of metabolism and a self-service method. Background technique [0002] Lithium-ion batteries are commonly used as a type of energy supply equipment for underwater weapons driven by electric power. They have the advantages of high specific energy, small size, long life, no memory, and environmental protection. They are widely used in the field of national defense. In peacetime, these equipment will be stored and overhauled for a long time after serving. Long-term environmental stress such as temperature and humidity may destroy its normal internal structure and working ability. The storage reliability of equipment will decrease with the prolongation of storage time, and the high reliability of its storage period is the basic guarantee fo...

AI Technical Summary

Problems solved by technology

[0005] The technical problem solved by the present invention is: in order to solve the problem of small sample size in the reliability evaluation of lithium-ion batteries serving underwater weapons, the present invention provides a method based on the metabolic gray neural network model and self-service method to process small sample stress acceleration Method of Reliability Evaluation of Life Test Results

Images