Automatica (Journal of IFAC)
Metamodelling: for bond graphs and dynamic systems
Metamodelling: for bond graphs and dynamic systems
Hi-index | 0.00 |
This paper describes a fault tolerant control algarithm based on a simple integrater and a neural network model for a multiple-input multiple-output (MIMO) nonlinear system. Two situations are considered. First, the system is working under normal operation parameters and the control vector is computed only by the minimisation of the performance index using the gradient descent rule. Second, assuming that a fault in any actuator gain will degrade the controller performance, a threshold is expected to detect the fault and initiate a fault compensation procedure.