Lithium battery fault data screening method constrained by normalized mutual information criterion

Abstract

The invention relates to a lithium battery fault data screening method constrained by a normalized mutual information criterion, and belongs to the field of lithium battery fault diagnosis. The methodcomprises the following steps that S1, data is collected, wherein the real lithium battery fault data is collected through a sensor, and the candidate lithium battery fault data is generated by meansof a perceptual generation network; S2, fractional Fourier transform is adopted for extracting characteristics of the lithium battery fault data; S3, normalized mutual information between a real lithium battery fault characteristic matrix A and a candidate lithium battery fault characteristic matrix B is calculated and adopted as a screening measure for the lithium battery fault data; S4, a screening threshold value is selected through a fault diagnosis experiment. According to the method, the screened lithium battery fault data can be real and effective, the screening speed can be increasedat the same time, and a high-quality data guarantee is provided for a deep learning method of fault diagnosis.

Description

technical field [0001] The invention belongs to the field of lithium battery fault diagnosis, and relates to deep learning, in particular to screening lithium battery fault data generated by perception by adopting fractional Fourier transform and normalized fault mutual information methods. Background technique [0002] At present, the fault diagnosis of lithium batteries through the combination of data-driven and deep learning is an effective method for lithium battery safety status monitoring. However, the deep learning method relies on a large amount of data, and it is difficult to collect lithium battery failure data. The laboratory data cannot fully reflect the actual complex and uncertain working conditions of the lithium battery, and the operating data of the real traffic environment is incomplete and missing. In this regard, perceptual generation can be used to increase the fault data of model training, but due to the uncertainty brought by random variables introduce...

AI Technical Summary

Problems solved by technology

However, the deep learning method relies on a large amount of data, and it is difficult to collect lithium battery failure data. The laboratory data cannot fully reflect the actual complex and uncertain working conditions of lithium batteries, and the operating data of the real traffic environment is incomplete and missing.

In this regard, perceptual generation can be used to increase the fault data of model training, but due to the uncertainty brought by random variables introduced in the generation process, the lithium battery fault data generated by perceptual generation may not be true and effective, lacking physical meaning, thus affecting the performance of the fault diagnosis model , causing unnecessary economic losses

In practice, low-efficiency manual methods are often used to screen out high-value data. To solve this problem, there is an urgent need for a method that can quickly and efficiently screen lithium battery failure data

Images