A new scheme combining neural feedforward control with model‐predictive control
Authors:
- 1 February 1992
- journal article
- research article
- Published by Wiley in AIChE Journal
- Vol. 38 (2) , 193-200
Abstract
A new control scheme is presented for feedforward control of unknown disturbances in the model‐predictive control (MPC) scheme. In this control scheme, a neural network is connected in parallel with the MPC controller and trained online by minimizing the MPC controller output corresponding to the unmodeled effect. It is applied to distillation column control and nonlinear reactor control to illustrate its effectiveness. The result shows that the neural feedforward controller can cope well with strong interactions, time delays, nonlinearities, and process/model mismatch. The controller also offers such advantages as fault tolerance, generalization capability by interpolation, and learning capability by randdom input patterns.Keywords
This publication has 14 references indexed in Scilit:
- Forecasting and control using adaptive connectionist networksComputers & Chemical Engineering, 1990
- Use of neural nets for dynamic modeling and control of chemical process systemsComputers & Chemical Engineering, 1990
- NONLINEAR MODEL PREDICTIVE CONTROLChemical Engineering Communications, 1990
- Multistep nonlinear predictive controllerIndustrial & Engineering Chemistry Research, 1989
- Hierarchical neural network model for voluntary movement with application to roboticsIEEE Control Systems Magazine, 1988
- A multilayered neural network controllerIEEE Control Systems Magazine, 1988
- Internal model control. 2. Design procedure for multivariable systemsIndustrial & Engineering Chemistry Process Design and Development, 1985
- Model algorithmic control (MAC); basic theoretical propertiesAutomatica, 1982
- Model predictive heuristic controlAutomatica, 1978
- Terminal composition control of a binary distillation columnChemical Engineering Science, 1973