Fault Tolerant Control System Design based on Vitual Sensor for Determining of Surge Point in Industrial Compressors

In this paper، a novel technique is presented for determining of operating and surge point in compressor via sensor fault tolerant control. The analytical redundancy method and the dynamic neural network (DNN) based on robust identification scheme is presented to determine of compressor surge point accurately، even in the presence of uncertainty in the compressor and noise in the sensor. Generally، the main drawback of DNN method is the lack of systematic law for selecting of initial Hurwitz matrix. Therefore، in this paper the subspace identification method is proposed for selecting this matrix. The required data is obtained from compressor Moore-Greitzer simulated model. In the residual evaluation block، a specified algorithm is proposed for obtaining fault properties. Virtual sensor idea is utilized for fault tolerant control system. A number of simulation results are carried out to demonstrate and illustrate the advantages، capabilities، and performance of our proposed fault toleant control scheme.