Power battery fault diagnosis method and system

Abstract

The invention discloses a power battery fault diagnosis method and system. The method comprises the following steps: establishing a voltage matrix of a battery cell, extracting a sub-matrix interval of the voltage matrix, establishing a median matrix according to the median of the battery cell voltage in the sub-matrix interval, establishing a voltage deviation matrix according to the sub-matrix interval and the median matrix, calculating a voltage deviation increment according to a voltage deviation value in the voltage deviation matrix, establishing a voltage deviation increment matrix, accumulating the number of times that the voltage deviation value in the voltage deviation matrix exceeds a set interval, establishing a voltage deviation accumulation number matrix, establishing a jointmatrix, performing two-dimensional clustering on the established joint matrix by adopting a DBSCAN density clustering method, and judging whether the battery cell has a fault or not according to a clustering result. According to the power battery fault diagnosis method and system provided by the invention, the fault judgment efficiency of the battery cell can be improved, and the judgment accuracycan be improved.

Description

technical field [0001] The invention relates to the technical field of fault diagnosis, in particular to a power battery fault diagnosis method and system. Background technique [0002] Lithium-ion batteries are widely used in electric vehicles due to their high specific energy, high specific power and long service life. However, with the improvement of power battery specific energy and the wide application of ternary lithium-ion batteries, the safety problems of lithium-ion batteries have become increasingly prominent. , Battery thermal runaway has become the main cause of electric vehicle safety accidents. Battery thermal runaway accidents involve a large number of casualties and property losses, and are the core issues that need to be solved in the development of electric vehicles. [0003] The current research on battery thermal runaway is mainly to explore the internal reaction mechanism and external characteristics of the battery when thermal runaway occurs through ex...

AI Technical Summary

Problems solved by technology

Among them, Zhao Yang et al. proposed a fault diagnosis method for electric vehicle battery system based on big data statistical method, mainly based on machine learning algorithm and 3r multi-level screening strategy (3r-MSS), to detect and calculate the battery pack in the form of probability However, the performance of the battery is affected by many factors during the operation of the car, and the voltage of a single cell sometimes does not obey the normal distribution. At this time, if the normal distribution is used to test the fault forcibly, its accuracy will be reduced. Big discount

Hong Jichao, Sun Zhenyu and others proposed a Shannon entropy fault diagnosis method based on the battery cell voltage. This method only considers the latest data of the car, and the Z score is less than the threshold in most of the time, and the fault cannot be detected.

The Z score requires that the data obey the normal distribution, which is greatly affected by outliers and the number of outliers will not exceed 0.7%. However, in reality, the Shannon entropy of each monomer does not conform to the normal distribution, and the number of abnormal monomers also does not conform to the normal distribution. Not necessarily less than 0.7%, so this method is more subjective and the prediction accuracy is lower

Images