Research on Fault Diagnosis of Marine Diesel Engine Based on Grey Relational Analysis and Kernel Fuzzy C-means Clustering

Abstract

According to the problem of small samples and nonlinear feature in fault diagnosis of marine diesel engine, comprehensively using the methods of grey relational analysis and kernel fuzzy c-means clustering, a method solving fault diagnosis of marine diesel engine is proposed. Firstly, kernel fuzzy c-means clustering was made on historical fault dataset. Secondly, the preliminary fault diagnosis was made on testing samples by using grey relational analysis and kernel fuzzy cmeans clustering separately. Finally, the final fault diagnosis results were got by the linear weighting matrix of fuzzy membership matrix and grey relational matrix. The fault diagnosis results of MAN B&W 10L90MC marine diesel engine show that this method can improve the accuracy of marine diesel engine.