Abstract
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.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
