Fault diagnosis of diesel engine lubrication system based on PSO-SVM and centroid location algorithm

Abstract

Fault of diesel engine lubrication system will affect engine performance, and diesel engine operation parameters reflect the working state of the engine. In this paper, a data-driven fault diagnosis is proposed using engine real working data. Considering the randomness and instability of the oil pressure in the lubrication system, a fault diagnosis method based on PSO-SVM model and centroid location algorithm is presented. Firstly, fault features are extracted analyzing the data in normal condition. Secondly, particle swarm optimization (PSO) algorithm is used to search the best parameters of support vector machine (SVM) to establish the model of fault diagnosis. Then, support vector machine classification interface is fitted to a curve, and the boundary conditions of fault diagnosis are obtained. Finally, the typical faults of diesel engine lubrication system are diagnosed by the proposed fault diagnosis algorithm. The results show that he proposed PSO-SVM model achieved above 95% classification accuracy; and two typical lubrication system faults of diesel engine can be diagnosed based on the proposed diagnosis method.