Combining Artificial Intelligence and Advanced Techniques in Fault-Tolerant Control

We present the integration of artificial intelligence, robust, nonlinear and model reference adaptive control (MRAC) methods for fault-tolerant control (FTC). We combine MRAC schemes with classical PID controllers, artificial neural networks (ANNs), genetic algorithms (GAs), H∞ controls and sliding mode controls. Six different schemas are proposed: the first one is an MRAC with an artificial neural network and a PID controller whose parameters were tuned by a GA using Pattern Search Optimization. The second scheme is an MRAC controller with an H∞ control (H∞). The third scheme is an MRAC controller with a sliding mode controller (SMC). The fourth scheme is an MRAC controller with an ANN. The fifth scheme is an MRAC controller with a PID controller optimized by a GA. Finally, the last scheme is an MRAC classical control system. The objective of this research is to generate more powerful FTC methods and compare the performance of above schemes under different fault conditions in sensors and actuators. An industrial heat exchanger process was the test bed for these approaches. Simulation results showed that the use of Pattern Search Optimization and ANNs improved the performance of the FTC scheme because it makes the control system more robust against sensor and actuator faults.