A neural network based nonlinear PID controller using PID gradient training
1999
A nonlinear PID controller is proposed to handle some nonlinear process control problems. In this scheme, the controller uses the system error, the integral of the system error, and the derivative of the system error as its inputs but the mapping from the inputs to the output is nonlinear. The corresponding nonlinear mapping may be specified based on the control requirement. The NPIDC strategy is realized using neural networks. For online training of the neural network based NPIDC, a PID gradient descent optimizing algorithm with momentum term is proposed. Then, the convergent characteristic of the algorithm is presented. Finally, a simulation study of applying the neural NPIDC strategy to a continuous-stirred-tank-reactor and a van de Vusse reactor is illustrated.
Keywords:
- Correction
- Source
- Cite
- Save
- Machine Reading By IdeaReader
5
References
5
Citations
NaN
KQI