Abstract
One problem with the application of neural networks to the multivariable control of mineral and extractive processes is determining whether and how to use them. The objective of this investigation was to compare neural network control to more conventional strategies and to determine if there are any advantages in using neural network control in terms of set-point tracking, rise time, settling time, disturbance rejection and other criteria.
The procedure involved developing neural network controllers using both historical plant data and simulation models. Various control patterns were tried, including both inverse and direct neural network plant models. These were compared to state space controllers that are, by nature, linear. For grinding and leaching circuits, a nonlinear neural network-based model predictive control strategy was superior to a state space-based linear quadratic gaussian controller.
The investigation pointed out the importance of incorporating state space into neural networks by making them recurrent, i.e., feeding certain output state variables into input nodes in the neural network. It was concluded that neural network controllers can have better disturbance rejection, set-point tracking, rise time, settling time and lower set-point overshoot, and it was also concluded that neural network controllers can be more reliable and easy to implement in complex, multivariable plants.
Similar content being viewed by others
References
Beale, M., Prisbrey, K., and Demuth, H., 1993, “Comminution control example using the fuzzy systems and neural network toolboxes for Matlab and Simulink,” SME Preprint 93–108.
Demuth, H., and Beale, M., 1994, “Neural network toolbox for use with Matlab,” The Math Works Inc., Natick, MA.
Flament, F., Thibault, J., and Hobouin, D., 1993, “Neural network based control of mineral grinding plants,” Minerals Engineering, Vol. 6, No. 3, pp. 235–249.
Herbst, J.A., Pate, W.T., and Oblad, A.E., 1989, “Model-based control of mineral processing operations,” Powder Technology, Vol. 69, No. 1, pp. 21–32.
Herbst, J.A., Hales, LB., and Gabardi, T.L., 1990, “Continuous measurement and control of charge volume in tumbling mills,” in Control 90, SME, pp. 163–171.
Herbst, J.A., and Lo, Y.C., 1992, “Optimization of grinding circuits,” Mines and Carrieres, Les Techniques, pp. 153–157.
Karr, C.L., and Gentry, E.J., 1993, “Application of fuzzy control techniques to a chaotic system,” in Emerging computer techniques for the minerals industry”, Scheiner, Stanley and Karr, eds., SME.
Nock, I.D., Parkin, R.M., and Bearman, R.A., 1994, “Knowledge-based system for condition monitoring of cone crushers,” Transactions of the Institution of Mining & Metallurgy, Section a: Mining Industry, Vol. 103, pp. A33–A39.
Rajamani, R.K., and Herbst, J.A., eds., 1988, “Recent advances in comminution, conference papers,” International Journal of Mineral Processing, Vol. 22, No. 1–4, 444 pp.
Rajamani, R.K., and Herbst, J.A., 1991, “Optimal control of a ball mill grinding circuit. I. Grinding circuit modeling and dynamic simulation,” Chemical Engineering Science, Vol. 46, No. 3, pp. 861–870.
Rajamani, R.K., and Herbst, J.A., 1991, “Optimal control of a ball mill grinding circuit. II. Feedback and optimal control,” Chemical Engineering Science, Vol. 46, No. 3, pp. 871–879.
Rajamani, R.K., and Herbst, J.A., 1990, “Application of expert systems in the minerals industry:,” in Control 90, SME, pp. 61–66.
Author information
Authors and Affiliations
Additional information
SME preprint 96–17, SME Annual Meeting, March 11–14, 1996, Phoenix, AZ
M&MP paper 96-618. Discussion of this peer-reviewed and approved paper is invited and must be submitted to SME prior to Aug. 31, 1997.
Rights and permissions
About this article
Cite this article
Cho, C., Vance, R., Mardi, N. et al. Neural network-based nonlinear model predictive control vs. linear quadratic gaussian control. Mining, Metallurgy & Exploration 14, 43–46 (1997). https://doi.org/10.1007/BF03402758
Received:
Revised:
Published:
Issue Date:
DOI: https://doi.org/10.1007/BF03402758