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

With the 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 complexity growth of circuits,fault nodes,makes the rapid expansion of required information,and the diagnosis has become more and more difficult.Modern car fault diagnosis has not only included diagnosis,but also the warning during the driving.The accuracy of existing fault diagnosis apparatus needs to be improved.In addition,its failure on determining the fault trend,makes the existing fault diagnosis apparatus difficult to meet the security needs of modern cars.The article aims at the problems of domestic fault diagnosis,using Fuzzy Logic,Neural Network and Expert System,combines with the actual situation of engine fault diagnosis re-search on the construction and implementation of engine fault diagnosis system.The Fault Diagnostic System of Automobile Engine is a combination of Neural Networks and expert systems,which overcome the traditional shortcomings of expert system and neural network of their existence.So the expert system and neural network are put together and can be better applied to fault diagnosis field.The expert system contains the five components which include a knowledge base,database,consequence engine,knowledge acquisition and interpret part.The System is developed and accomplished based on Windows XP platform,using MATLAB for data-processing and Visual C++7.1 of object-oriented programming language for programming languages and Access for database language.This paper runs single fault and multiple fault simulation,using conventional fault diagnosis method to verify the results of single fault diagnosis with massive fault symptom samples data to verify the results of multiple fault diagnosis.This paper take exhaust gas(CO,CO2,NOx,HC,and O2)for the training samples in order to make the final sample pretreatment Based on gasoline engine under different load condition speed,then create the neural network on the base of reusable training samples.Finally,test the state of engine cylinder using the trained neural network so as to judge whether Cylinder is in normal condition,and get a specific fault.The design of man-machine interface systems and the users realize the numerical value of import and export based Visual Programming Language C++7.1,and the experimental results simulation on the base of MATLAB.