Fault Diagnosis Research Of Diesel Engine Based On EEMD And PSO Optimization SVM Approach

Diesel engine as the power source of the engineering machinery is widely used in ships,vehicles,generators,and other fields.Due to the complexity of operation condition and poor working conditions,it is very easy to fall down.In the past,preventive maintenance was widely used on diesel engine valve fault handling maintenance and maintenance method,but this method is lack of accident foresee ability,high maintenance cost,low efficiency,so the practical intelligent fault diagnosis methods is necessary.In addition,due to the simple measuring of cylinder head vibration signal,it is always a hot topic to detect diesel engine fault by using diesel engine cylinder head vibration signal without disintegration.There are a lot of excitation sources in diesel engine cylinder head vibration signal,which belong to the non-stationary vibration signals.So,it is necessary to select a suitable method to process the vibration signal.The main research contents were as follows: Establish experimental platform for diesel engine cylinder head vibration signal.Acquire diesel engine cylinder head vibration signal under normal state and abnormal fuel injection advance angle,abnormal fuel quantity and abnormal fuel injection time states.By comparing the characteristic parameters of the vibration signals in different fault conditions,the status of the diesel engine is preliminarily determined.The application of ensemble empirical mode decomposition(EEMD)in data processing and feature extraction of the cylinder head vibration signal is studied.The normal state,and fault conditions were decomposed by EEMD,and the frequency-domain analysis was carried out on the decomposed IMFs.Finally,the first six IMF components with high correlation with the original vibration signal are selected to calculate the RMS,skewness,kurtosis and maximum singular value.The main parameters of Support Vector Machine(SVM)are optimized by Particle Swarm Optimization(PSO)algorithm.The maximum singular value,RMS value,kurtosis value and skewness of the first six IMF components are calculated and normalized it as the input vector of SVM model for fault pattern recognition,and compared with BP neural network results.The results show that the EEMD-PSO-SVM fusion technique can effectively identify three typical faults of diesel engines,and the diagnostic accuracy is higher than 90 %,which is higher than that using BP neural network.The result proves that the fusion technology The Feasibility and Engineering Application Value of Diesel Diagnostic Application.