ENGINE SENSOR FAULT DIAGNOSIS USING MAIN AND DECENTRALIZED NEURAL NET WORKS

ＡｎａｌｙｔｉｃａｌｒｅｄｕｎｄａｎｃｙｔｅｃｈｎｉｑｕｅｓｓｕｃｈａｓｅｘｔｅｎｄｅｄＫａｌｍａｎｆｉｌｔｅｒ，ｃｏｍｐｏｎｅｎｔｓｔｒａｃｋｉｎｇｆｉｌｔｅｒａｎｄｓｏｏｎｃａｎｄｅｔｅｃｔ，ｉｓｏｌａｔｅａｎｄａｃｏｍｍｏｄａｔｅｆａｉｌｕｒ...

ENGINE SENSOR FAULT DIAGNOSIS USING MAIN AND DECENTRALIZED NEURAL NET WORKS

This Paper presents a methodology for solving the sensor failure detection, isolation and accommodation of aeroengine control systems using on-line learning neural networks(NN), which has one main NN and a set of decentralized NNs. Changes in the system dynamics are monitored by the on-line learning NN. When a failure occurs in some sensor, the sensor failure detection can be accomplished with high precision, and the sensor failure accommodation can be achieved by replacing the value from the failed sensor with its estimate from the decentralized NN. By integrating the optimal estimation and failure logic, this method can detect soft failures. Simulation of one kind of turboshaft engine control system with this multiple neural network architecture shows that the ANN developed can detect and isolate hard and soft sensor failures timely and provide accurate accommodation.