Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations
Adaptive neural model-based fault tolerant control for multi-variable processes
Engineering Applications of Artificial Intelligence
| Hi-index | 0.00 |
This paper presents a fault tolerant control architecture using fault diagnosis and switching functions. The fault tolerant controller consists of a fault detection part to sense the faults, a fault isolation part to identify the types of faults that have occurred and a bank of compensators with switching for the control part. In the proposed method, the fault is detected when the errors between the nonlinear system and the neural network (NN) nominal system output cross a predetermined threshold. Once a fault in the system is detected, the fault classifier based on the NN isolates the fault. These results are fed into a controller block that selects an appropriate compensation scheme to handle the fault. Simulation results demonstrate the effectiveness of the proposed fault tolerant control method for nonlinear systems.