论文部分内容阅读
Pneumatic control valve is the most typical actuator in industrial process and its property is closely connected to the performance of control loop,so pneumatic control valve fault diagnosis is of great importance.The Damadics Actuator Benchmark Library(DABLIB)was created to fulfill the requirements of model benchmark within the EC FP5 Research Training Network-Development and Application of Methods for Actuator Diagnosis in Industrial Control Systems(DAMADICS).This paper introduces the fault diagnosis method based on Sparse Bayesian Extreme Learning Machine(SBELM)of multiclass classification.The multi-fault diagnosis model of control valve with the data is trained through SBELM.The proposed method allows for estimating the marginal likelihood of network outputs and automatically pruning out unnecessary samples based on a certain performance criterion during learning phase,which results in an accurate and compact fault diagnosis model.