Artificial Neural Networks: A Tutorial
Computer - Special issue: neural computing: companion issue to Spring 1996 IEEE Computational Science & Engineering
Neural network fundamentals with graphs, algorithms, and applications
Neural network fundamentals with graphs, algorithms, and applications
Artificial Neural Networks
An optimal tracking neuro-controller for nonlinear dynamic systems
IEEE Transactions on Neural Networks
Diagonal recurrent neural networks for dynamic systems control
IEEE Transactions on Neural Networks
Hi-index | 0.00 |
Controllers based on artificial neural networks (ANNs) are demonstrating high potential in the nonconventional control of nonlinear dynamic systems. This work presents a comparative study of neurocontrollers based on different topologies of ANN, namely the feedforward neural network (FNN) using a generalized weight adaptation algorithm, and the diagonal recurrent neural network (DRNN) using a generalized dynamic back-propagation algorithm. Also, both on-line and off-line training methodologies of the adopted ANNs are investigated. The study is based on controlling the system using a coordination of feedforward controllers combined with inverse system dynamics identification. Simulation results are used to verify the effect of varying the topology of the ANNs and training methods on the control and system performance of nonlinear dynamic systems.