Research Of Vehicle Engine Fault Diagnosis Method Based On Fuzzy Neural Network

With the fast development of automobile technology, automobile structure became more complex, more electronic, and the security issues about automobiles became more prominent. Fault diagnosis of vehicle engine is the key problem to that issue. The growing complexity of circuits, fault nodes, makes the rapid expansion of required information, and the diagnosis has become increasingly difficult. Modern car fault diagnosis has not only included diagnosis, but also the warning during the driving. The accuracy of existing fault diagnosis apparatus and method needs to be improved. In addition, its failure on determining the trend of the fault, makes the existing fault diagnosis apparatus and method difficult to meet the security needs of modern cars.This paper based on the analysis of engine electronic control system, proposed a fuzzy neural network to establish a fault diagnosis system, and used the 465Q engine electronic control system for example, applied MATLAB software for the simulation experiments.This paper firstly tells background and significance of vehicle engine fault diagnosis, and then discusses vehicle engine fault diagnosis based on fuzzy neural networks is an effective way to solve these problems. Introduced the structure,function and common faults of four subsystems of engine electronic control system (electronic ignition control system, electronic fuel injection control system, idle speed control system and exhaust gas recirculation control system). Completed the design of diagnosis system based on fuzzy BP neural network, including: fault symptom information collection and fuzzy processing, BP network structure and parameter setting, fault diagnosis fuzzy rule base design. The system will collect fault symptom information, through the fuzzy processing as the input of BP network, use fuzzy rules as the standard of BP network simulation to obtain the final possible fault reason.This paper run single fault and multiple fault simulation, use conventional fault diagnosis method to verify the results of single fault diagnosis, use massive fault symptom samples datas to verify the results of multiple fault diagnosis. The results show obvious superiority of engine fault diagnosis based on fuzzy neural network in multiple fault diagnosis and trend judgment. It provides a feasible idea in vehicle engine intelligent fault diagnosis.