Vehicle fault intelligent reasoning method and system based on Bayesian network

Abstract

The invention discloses a vehicle fault intelligent reasoning method based on Bayesian network, which includes constructing a fault tree model based on Bayesian network, obtaining the prior probability of fault tree nodes and a detection method for associated fault tree nodes; Input the model, prior probability and detection method to the inference engine to generate the optimal detection method; receive the detection result of the manual execution of the optimal detection method and input it to the inference engine to obtain the posterior probability of the fault tree node; determine whether there is a The posterior probability of the fault tree node reaches the preset locking probability; if so, check the fault cause corresponding to the current fault tree node, push the maintenance procedure, and update the prior probability of the fault tree node according to the current maintenance data; if not, then Carry out a new round of detection methods. The method provided by the invention reduces the requirement of the fault tree on the accuracy of manual experience, improves the accuracy of the reasoning system, shortens the troubleshooting steps of the fault cause, and improves the troubleshooting efficiency.

Description

technical field [0001] The invention relates to the technical field of vehicle intelligent diagnosis, in particular to a Bayesian network-based intelligent vehicle fault reasoning method and system. Background technique [0002] As the application of electronic control technology in automobiles becomes more and more mature, there are more and more electronic control units, electronic control devices, sensors, wiring harnesses and other components on commercial vehicles, and the electronic control system is becoming more and more complex. The maintenance of the control system also brings new challenges to the service station. In order to reduce the maintenance threshold of the electronic control system and improve the maintenance efficiency, the existing technology usually combines artificial intelligence algorithms. For example, the Bayesian network algorithm is introduced into the commercial vehicle fault maintenance process. Diagnostic instruments, TBOX and other equipmen...

AI Technical Summary

Problems solved by technology

However, this method often has the following disadvantages: first, the order of screening in the decision tree is fixed, and the order of screening cannot be automatically adjusted according to each reasoning result. Logical judgment can only troubleshoot the cause of the fault in the node, and cannot deal with uncertain situations, which will affect the accuracy of the troubleshooting results; third, because the decision tree has strong logic, self-learning is difficult and time-consuming. Not strong implementation

Images