The use of genetic algorithms for advanced instrument fault detection and isolation schemes

An advanced scheme for Instrument Fault Detection and Isolation is proposed. It is mainly based on Artificial Neural Networks (ANNs), organized in layers and handled by knowledge-based analytical redundancy relationships. ANN design and training is performed by genetic algorithms which allow ANN architecture and parameters to be easily optimized. The diagnostic performance of the proposed scheme is evaluated with reference to a measurement station for automatic testing of induction motors.