New energy vehicle maintenance and fault monitoring and diagnosis method based on machine learning

Abstract

The invention provides a new energy vehicle maintenance and fault monitoring and diagnosis method based on machine learning, and relates to the field of new energy vehicle device monitoring and fault diagnosis application. According to the new energy vehicle maintenance and fault monitoring and diagnosis method based on machine learning, firstly, a vehicle state data set of a new energy vehicle is obtained, feature extraction is conducted on the vehicle state data set, a preliminary feature data set is formed, then the preliminary feature data set is pre-trained, and an embedded feature vector set is generated. And the embedded feature vector set is used as the input of a recurrent neural network for training to obtain a vehicle fault monitoring and diagnosis algorithm model, and finally monitoring and fault analysis are carried out on the vehicle state through the received vehicle state data based on the vehicle fault monitoring and diagnosis algorithm model. Therefore, the running condition of the vehicle can be effectively monitored in time, potential safety hazards and economic losses caused by vehicle faults can be avoided, and the running safety of the vehicle is improved.

Description

technical field [0001] The invention relates to the application field of device monitoring and fault diagnosis of new energy vehicles, in particular to a method for maintenance and fault monitoring and diagnosis of new energy vehicles based on machine learning. Background technique [0002] In recent years, the penetration rate of new energy vehicles in the public transportation industry has increased significantly, making great contributions to urban environmental protection. At present, two types of new energy vehicles, pure electric and plug-in hybrid, are prevalent in the Chinese market. The existing maintenance technology solutions for new energy vehicles are mainly based on the conventional maintenance experience of the traditional automobile industry, and the maintenance, maintenance, fault detection and diagnosis are carried out on the vehicle at regular intervals or when the vehicle reaches a fixed mileage. However, due to the driver's driving habits and actual veh...

AI Technical Summary

Problems solved by technology

However, due to the driver's driving habits and actual vehicle conditions, the vehicle may fail when the maintenance period or mileage of the maintenance plan is not reached, especially some failures that will not be directly detected

For example, if the battery management system fails, the battery will not be fully charged, and if the temperature of the ignition device is too high, there may be problems such as leakage and short circuit.

[0003] In addition, the development history of new energy vehicles in my country is relatively short, and the vehicle maintenance and repair technology at the

Images