Vibration Signal Fusion Technique And Its Study In Valve Clearance Fault Diagnosis Of Engine

As power source of automobile, the running condition of engine can directly affect the whole working condition of automobile. Engine faults constitute most proportion of automobile faults, and it takes high cost and long time to maintain it. The reliability and security of automobile will be enhanced if we can exactly judge the engine current condition in time, distinguish the positions of the faults and point out the reason and solving method with the engine being not disassembly.Engine vibration reflects the running condition of its parts.The paper studys DA462-1A/D G.D.I gasoline engine and diagnoses the valve clearance fault through analyzing and comparing the collected vibration signals from Cylinder Block. Also the paper extracts the faults characters based on wavelet multiresolution analysis technology.The BP neural network of forward type has the very strong mode identification and classific ability. From appliance aspect this paper analyzes network layer number, nerve cell number of inside layer, original weigh, train speed, expecting error and so on when designing BP network and puts forward the improvement methods.This paper introduces wavelet multiresolution analysis theory and neural network to diagnose the faults of engine, puts forward a model of BP neural network for engine fault diagnosis.We design an experiment system that can diagnose the engine faults based on the established BP neural network, and validate the system through simulating the faults of valve clearance, which are one of most common faults of engine.The experimental results show that the established diagnostic system based on neural network using wavelet analysis can efectively diagnose the valve clearance fault and its results are accurate.