Open AccessResearch on Marine Diesel Engine Fault Diagnosis Based on the Manifold Learning and ELM
Author(s) -
Mingqi Shao,
Jin Wang,
Sibo Wang
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1549/4/042113
Subject(s) - diesel engine , fault (geology) , feature extraction , diesel fuel , nonlinear dimensionality reduction , computer science , automotive engineering , manifold (fluid mechanics) , feature (linguistics) , artificial intelligence , engineering , pattern recognition (psychology) , dimensionality reduction , mechanical engineering , geology , linguistics , philosophy , seismology
As the core equipment of marine power system, the operation state of marine diesel engine has a direct impact on the safe navigation of the whole ship. In order to extract fault features from vibration signals of diesel engine more comprehensively, a new fault diagnosis method is proposed based on the advantages of feature fusion and manifold learning algorithm in dealing with nonlinear data. The manifold learning method is used for feature extraction. Through this method, the vibration signal of diesel engine is extracted, and the feasibility and superiority of this method are verified from the perspective of three-dimensional visualization. The extracted features are input into the elm model to identify the working condition of marine diesel engine. Experimental results show that the proposed method can achieve real-time fault diagnosis with high classification accuracy.