Online battery fault detection and analysis method and device for new energy vehicle

Abstract

The invention discloses an online battery fault detection and analysis method and device for a new energy vehicle. The method comprises: establishing a long-short-term memory (LSTM) neural network model, a support vector machine (SVM) model and two softmax multi-classification models for a sensor fault and a vehicle battery fault; during detection, sensor data being subjected to fault diagnosis through an LSTM model; distinguishing the sensor fault and the vehicle battery fault through the SVM model, and then performing sensor or vehicle battery fault type classification and positioning through the two softmax multi-classification models so that online and accurate fault detection can be realized. Through distinguishing and judging a sensor fault and a vehicle battery fault, the requirement for a fault type classification model can be well lowered, the classification precision can be further improved, the fault type can be judged more accurately, the distinction degree of the fault severity level can be higher, and therefore a vehicle can be better overhauled and maintained in time, the driving safety and comfort are improved, and the accident occurrence rate is reduced.

Description

technical field [0001] The invention relates to the field of automobile fault detection, in particular to a new energy vehicle online battery fault detection and analysis method and device. Background technique [0002] New energy vehicles include pure electric vehicles, fuel cell vehicles, hybrid vehicles, etc. With the development and progress of new energy vehicle manufacturing technologies and processes, more and more people choose and use new energy vehicles. Neglect, and fault detection is an important and indispensable part of this. In the past, the fault detection was often after the vehicle failed to be used normally, and the owner drove it to the repair shop for subsequent repairs and maintenance. However, such recognized faults have often missed the best time for repairs, and there are great safety hazards. Since the high-frequency faults of electric vehicles mainly occur in the battery system, the faults of the battery system often cause major accidents such as ...

AI Technical Summary

Problems solved by technology

In the past, the fault detection was often after the vehicle failed to be used normally, and the owner drove it to the repair shop for subsequent repairs and maintenance. However, such recognized faults have often missed the best time for repairs, and there are great potential safety hazards.

Since the high-frequency faults of electric vehicles mainly occur in the battery system, the faults of the battery system often cause major accidents such as car fires.

Images