Combining Adaptive with Artificial Intelligence and Nonlinear Methods for Fault Tolerant Control

Abstract

AbstractIn this article different schemes for Fault Tolerant Control (FTC) based on Adaptive Control, Artificial Intelligence (AI) and Robust Control are proposed. These schemes includes a Model Reference Adaptive Controller with a Neural Network and a PID controller optimized by a Genetic Algorithm (MRAC-PID-NN), a Model Reference Adaptive Controller with a Sliding Mode Control (MRAC-SMC) and a classical Model Reference Adaptive Controller (MRAC). In order to compare the performance of these schemes, an Industrial Heat Exchanger was used as test bed in which two different types of faults (abrupt and gradual) with different magnitudes (10% and 20%) were simulated. The simulation results showed that the use of AI methods improves the FTC schemes, developing a robust control system against sensor faults and a wider threshold to accommodate actuator faults in comparison with the two other schemes.KeywordsArtificial IntelligenceFault Tolerant ControlModel Reference Adaptive ControlNeural NetworkPIDSliding Mode Control