Multilayer feedforward networks are universal approximators
Neural Networks
Controlling nonlinear time-varying systems via Euler approximations
Automatica (Journal of IFAC)
Process Control Systems: Application, Design and Tuning
Process Control Systems: Application, Design and Tuning
Nonlinear and Adaptive Control Design
Nonlinear and Adaptive Control Design
Fast learning in networks of locally-tuned processing units
Neural Computation
Dynamic structure neural networks for stable adaptive control of nonlinear systems
IEEE Transactions on Neural Networks
Design of an adaptive neural sliding-mode controller for seesaw systems
International Journal of Computer Applications in Technology
Hi-index | 22.14 |
This paper presents a robust control method for a class of nonlinear systems, based on a mixed PID/adaptive algorithm. The nonlinear system is considered as a second-order linear dominant model with an unmodeled dynamics that is possibly nonlinear and time-varying. The PID part of the controller is applied to stabilize the dominant model. The adaptive part of the controller is used to compensate for the deviation of the system characteristics from the dominant linear model for performance enhancement. The advantage of our controller is that it can cope with strong nonlinearities in the system without abandoning the PID controller which is well-known to many engineers. The proposed control scheme guarantees the boundedness of the system states and parameter estimation. An example is given to illustrate the effectiveness of the proposed controller.