Application of Optimized DHKELM to Fault Diagnosis of Diesel Engine
To accurately and efficiently diagnose faults in the diesel engine,an optimized deep hybrid kernel extreme learning machine(DHKELM)is proposed for diesel engine fault diagnosis.The method uses the spectral amplitude of each sample as the fault feature,which is normalized and used as input to the DHKELM model,thus enabling the identification of each fault status of the diesel engine.Compared with the extreme learning machine,the model has a deeper structure and introduces hybrid kernel func-tions and automatic encoders to accurately distinguish confusing fault types and improve diagnosis accura-cy.To address the problem that each hyperparameter in the DHKELM model is difficult to be determined,an improved sparrow search algorithm(ISSA)is proposed to optimize the hyperparameters in the model and give full play to the fault diagnosis performance of the model.The experimental results show that the proposed method has better fault diagnosis accuracy compared with the traditional methods in the laborato-ry measured data,which provides a new idea for diesel engine fault diagnosis.
NETL
NSTL
万方数据
维普
