Lithium-ion battery fault diagnosis method

Abstract

The invention discloses a lithium-ion battery fault diagnosis method. The method comprises the following steps: S1, acquiring battery data when a lithium-ion battery does not fail and various types offaults occur; S2, performing noise reduction processing on the data obtained in the step S1 by using a signal noise reduction model; S3, calculating through a feature extraction model to obtain feature parameters representing chemical reactions of different frequencies in the lithium-ion battery; S4, calculating a safety threshold of the lithium-ion battery; S5, determining a corresponding faulttype during alarming according to the safety threshold, and establishing a lithium-ion battery fault diagnosis model; S6, acquiring charging and discharging cycle battery data of a to-be-diagnosed lithium-ion battery in a use process, reducing noise of the data, calculating a characteristic parameter curve, and performing similarity comparison on the characteristic parameter curve and the reference parameter curve to obtain a similarity degree; and S7, inputting the similarity degree into the lithium-ion battery fault diagnosis model in the step S5, and if the similarity degree reaches a threshold value, sending a corresponding fault type alarm signal.

Description

technical field [0001] The invention belongs to the field of battery fault diagnosis, and in particular relates to a lithium ion battery fault diagnosis method. Background technique [0002] In recent years, secondary lithium-ion batteries have been widely used in C products, electric vehicles, and energy storage due to their high energy density, long service life, low self-discharge rate, and no memory effect. Especially with the increasingly prominent environmental protection issues, the use of lithium-ion batteries in the field of electric vehicles shows an almost linear growth trend. However, due to the instability and abuse of lithium-ion batteries and the more stringent technical requirements for thinner batteries and higher energy density due to technological development, frequent safety accidents have attracted more and more attention. Therefore, it is imminent to invent a method that can detect power battery faults in real time and predict the results accurately. ...

AI Technical Summary

Problems solved by technology

[0003] Lithium-ion battery is a complex nonlinear system that changes in real time. The internal chemical reaction mechanism is complex, and the external performance is affected by changes in various parameters. It is very complicated to establish an electrochemical mechanism model for prediction, and it is difficult to achieve real-time prediction.

In recent years, neural networks have been widely used in power battery fault diagnosis, but there are defects such as complex structure, huge amount of calculation, poor interpretability, and this method is purely based on data-driven, without considering the internal microscopic chemical reaction and external macroscopic performance when a fault occurs The relationship between the prediction results is poor

Images