An Optimization-Based Correlation Vector Machine Fault Diagnosis Method for Armored Vehicle Power Compartment

Abstract

The present invention provides a method for diagnosing a fault in a power cabin of an armored vehicle based on an optimized correlation vector machine, comprising: step 1, collecting fault sample data of the power cabin by a sensor to obtain sample data, S={(x i ,y i )}, where, is the i-th n-dimensional attribute sample, i∈[1,N], N is the total number of samples; y i is the fault category corresponding to the i-th sample; step 2, the sample data S={(x i ,y i )} for normalized preprocessing to obtain the training set and test set; step 3, use the cuckoo search algorithm based on Gaussian perturbation to select the optimal RVM kernel parameter σ; step 4, input the training set data into the RVM model for training , to construct a correlation vector machine; step 5, use the constructed RVM classifier to classify the data of the test set, and obtain the corresponding power cabin fault status. The invention can improve the classification accuracy while shortening the training time, has strong generalization ability, can accurately detect different faults of the power cabin, and well solves the problem of the all-in-one fault diagnosis of the power cabin.

Description

technical field [0001] The invention relates to the technical field of armored vehicle power cabin measurement, in particular to an optimization-based correlation vector machine armored vehicle power cabin fault diagnosis method. Background technique [0002] The power cabin is an integrated machine including an engine and a gearbox. The engine converts chemical energy into mechanical energy, and the gearbox and the engine are coupled to achieve the purpose of changing speed and torque. They are one of the core components of armored vehicle power. The normal operation of the power cabin will seriously affect the performance of the armored vehicle. Therefore, it is necessary to diagnose the faults of the power cabin before the vehicle is assembled. These diagnostic and evaluation experiments are all completed on the test bench. [0003] In the prior art, the power cabin is disassembled, the engine and the gearbox are taken out, and fault diagnosis is carried out for each part...

AI Technical Summary

Problems solved by technology

However, the power cabin as a whole has relatively few measurable signals that can be used for diagnosis, and there are many types of faults that need to be diagnosed, and there are not many sample data, which brings difficulties to the fault diagnosis of the power cabin. Troubleshooting method

Images