Method for training fault prediction model, method and device for vehicle fault prediction

Abstract

The embodiment of the present application provides a fault prediction model training method and a vehicle fault prediction method, which are used to obtain a fault code probability and a component fault probability according to vehicle information and a target fault prediction model. The method in the embodiment of the present application includes: acquiring a plurality of sample data from the database, each sample data in the plurality of sample data includes at least the vehicle type, mileage and fault code, and the fault code is corresponding to the vehicle type A fault code that occurs when the vehicle travels to the mileage, the fault code corresponds to at least one component; an initial fault prediction model is trained using the plurality of sample data and the failure probability coefficient of the at least one component to obtain a target fault A prediction model, the target failure prediction model is used to determine the DTC probability of the DTC and the failure probability of the at least one component corresponding to the DTC. Therefore, the embodiments of the present application improve the accuracy of vehicle failure prediction.

Description

technical field [0001] The embodiments of the present application relate to the technical field of automobiles, and in particular to a fault prediction model training method, a vehicle fault prediction method, a fault prediction model training device, and a vehicle fault prediction device. Background technique [0002] With the rapid development of the automobile industry, the number of automobiles in our country continues to increase. Automobiles have been ubiquitous in the daily life of users and have become more and more important means of transportation. Predicting the occurrence of faults is an important method to ensure the normal driving of the car. [0003] In the prior art, for future possible faults of the automobile, it is mainly based on the maintenance experience and maintenance level of the maintenance technician to judge the possible faults of the current automobile, and then maintain or replace a certain component that may be faulty. [0004] However, with t...

AI Technical Summary

Problems solved by technology

[0004] However, with the continuous increase of the number of cars and vehicle types in our country, when the maintenance technicians have insufficient experience or do not know enough about the current vehicle model, the method of predicting the possible faults of the car relying on the maintenance level and experience of the maintenance technicians Can not accurately predict the failure of the car, resulting in driving hazards

Images