Research On Diesel Engine Fault Diagnosis System Based On Multisensory Data Fusion

Diesel engine is the main drive equipment of vessel; the faults of it would badly affect the daily use of the vessel and even result in unpredictable graveness accidents. The problem of seeking after a suit of condition monitoring techniques and fault diagnosis methods for diesel engine has drawn more and more attention.This thesis has constructed a condition monitoring and fault diagnosis system for diesel engine, and developed the technique of fault diagnosis. The main content of this article is as follows:1) This article has designed the hardware of the condition monitoring and fault diagnosis of diesel engine on the distributing frame, design the software of the condition monitoring and fault diagnosis system with virtual instrumentation software Labview, analysis the key technique of the designing of hardware and software based on the characteristics and the requirements of the condition monitoring and fault diagnosis of diesel;2) After the implemented the design of a condition monitoring and fault diagnosis system, it develops the theoretical research of fault diagnosis of diesel engine based on information fusion, analyzes the relation of fault diagnosis and information fusion, which shows great importance on the appliance requirement of the information fusion in fault diagnosis process of diesel. The basic methods of information fusion include Fuzzy pattern recognition, Rough Sets Theory, D-S Evidence Theory.3) It has testified the needing and the validity of Information Fusion in condition monitoring and fault diagnosis of diesel engine through the application of Fuzzy pattern recognition, Rough Sets Theory, D-S evidence theory based on the real data and the faults analysis of diesel system. The introduction of Information Fusion theory solves the problems in fault diagnosis such as information faintness、 information redundancy and information complementarity, and improve the precision of fault diagnosis.