A research on simultaneous fault diagnosis based on paired-RVM

Abstract

This paper studies the simultaneous fault diagnosis of the main reducer in the automobile transmission system assembly based on vibration signals. A simultaneous fault diagnosis model based on Paired Relevance Vector Machine (Paired-RVM) is proposed for the simultaneous fault of the main reducer, and each binary sub-classifier is trained with single fault samples and then fused by a pairing strategy. With F-measure as a measurement indicator of diagnosis precision, the threshold set DThreshold is used to train a threshold optimization algorithm so as to generate the optimal decision threshold, thus converting the probability output generated by the classification model into the final simultaneous fault mode. A contrast experiment is made between Paired-RVM and some commonly used supervised learning models of SVM, ELM and KELM, and the experimental results show that the performance of Paired-RVM proposed in this paper is superior to that of other models in simultaneous fault diagnosis and single fault diagnosis, verifying the effectiveness of the proposed method.