Research of Sensor Fault Diagnosis Method Based on Immune Network and Fuzzy ART Neural Network

A new immune network model and its diagnosis algorithm were studied. With the deficiency of model algorithm in the identification of sensor correlation, a new algorithm used in the quantitative extraction and recognition of sensor correlation were proposed based on Fuzzy ART neural network, of which the diagnosis system was consisted and the immune network. By the simulation of temperature sensor fault in certain thermal control system, the method was validated. The simulation result shows that the system could recognize and diagnose the faults accurately, regardless of single or multiple sensor faults. The accuracy of recognition and diagnosis is above 90 percent when the sensor output is less than plusmn5 percent deviation.