Abstract
This paper presents a controller design method for multi-input multi-output (MIMO) nonlinear timevarying systems using Radial Basis Funtion (RBF) neural network. The developed neuro-controller generates optimal control signals abiding by constraints, if any, on the control signal or on the system output. The proposed controller does not require an explicit knowledge of the states of the system or any apriori knowledge of the structure of nonlinearity of the system. Time based variations in system parameters as well as system nonlinearities are successfully compensated by the neural network. Simulation results for nonlinear time-varying systems are included at the end and controller performance is analyzed.
| Original language | English |
|---|---|
| Pages (from-to) | 711-720 |
| Number of pages | 10 |
| Journal | WSEAS Transactions on Systems and Control |
| Volume | 5 |
| Issue number | 9 |
| State | Published - Sep 2010 |
Keywords
- Constraints
- Multivariable
- Neural network
- Optimization
- Radial basis functions
ASJC Scopus subject areas
- Control and Systems Engineering
- Control and Optimization