A Nonlinear Model Predictive Control Strategy Using Multiple Neural Network Models
Combining multiple neural networks appears to be a very promising approach for improving neural network generalization since it is very difficult, if not impossible, to develop a perfect single neural network. Therefore in this paper, a nonlinear model predictive control (NMPC) strategy using multiple neural networks is proposed. Instead of using a single neural network as a model, multiple neural networks are developed and combined to model the nonlinear process and then used in NMPC. The proposed technique is applied to water level control in a conic water tank. Application results demonstrate that the proposed technique can significantly improve both setpoint tracking and disturbance rejection performance.
KeywordsManipulate Variable Nonlinear Model Predictive Control Tank Level Single Neural Network Multiple Neural Network
Unable to display preview. Download preview PDF.
- 1.Chen, J., Yea, Y.: Neural Network-Based Predictive Control for Multivariable Processes. Chemical Engineering and Communication 189, 866–894 (2002)Google Scholar
- 3.Zhang, J.: Sequential Training of Bootstrap Aggregated Neural Networks for Nonlinear Systems Modeling. In: American Control Conference, vol. 1, pp. 531–536 (2002)Google Scholar