Control de un sistema multivariable no lineal y en fase no mínima empleando un controlador predictivo neuronal

Elmer  Calle Chojeda; José Oliden Semino; William Ipanaqué Alama

doi:10.4995/riai.2022.17375

Autores/as

Elmer Calle Chojeda Universidad de Piura https://orcid.org/0000-0001-7011-4933
José Oliden Semino Universidad de Piura https://orcid.org/0000-0002-0423-546X
William Ipanaqué Alama Universidad de Piura https://orcid.org/0000-0003-4039-4422

DOI:

https://doi.org/10.4995/riai.2022.17375

Palabras clave:

control predictivo basado en modelo, redes neuronales artificiales, sistema MIMO, sistema de tanque cuádruple

Resumen

En este artículo se propone un Controlador Predictivo Neuronal (ANN-MPC) para controlar un sistema no lineal de tanque cuádruple, el cual es complejo de controlar debido a la no linealidad de sus válvulas y a la interacción entre sus variables controladas. Además, el problema se agrava ya que el proceso presenta una respuesta transitoria con dinámica inversa por estar en fase no mínima. El ANN-MPC emplea una estructura modular de red neuronal artificial y el algoritmo de entrenamiento Levenberg-Marquardt para estimar con mayor precisión y rapidez las salidas del proceso no lineal y evitar el sobreajuste del modelo. Se generaron datos operativos a partir de la planta para entrenar la red neuronal empleando Matlab. Se probó el rendimiento del ANN-MPC ante cambios de referencia y se comparó con un MPC lineal y un MPC no lineal. Los resultados de simulación mostraron que el ANN-MPC produjo un menor tiempo de establecimiento que el MPC lineal y generó valores RMSE de las salidas similares a los del NMPC. Además, se redujo el tiempo de cómputo requerido para calcular la variable de control óptima comparado con el NMPC.

Descargas

Los datos de descargas todavía no están disponibles.

Biografía del autor/a

Elmer Calle Chojeda, Universidad de Piura

Laboratorio de Sistemas Automáticos de Control, Departamento de Ingeniería Mecánico-Eléctrica

José Oliden Semino, Universidad de Piura

Laboratorio de Sistemas Automáticos de Control, Departamento de Ingeniería Mecánico-Eléctrica

William Ipanaqué Alama, Universidad de Piura

Laboratorio de Sistemas Automáticos de Control, Departamento de Ingeniería Mecánico-Eléctrica

Citas

Alvarado, I., Limon, D., Muñoz de la Peña, D., Maestre, J., Ridao, M., Scheu, H., Marquardt, W., Negenborn, R., De Schutter, B., Valencia, F., Espinosa, J., 2011. A comparative analysis of distributed mpc techniques applied to the hd-mpc four-tank benchmark. Journal of Process Control, 21(5), 800-815. Special Issue on Hierarchical and Distributed Model Predictive Control. https://doi.org/10.1016/j.jprocont.2011.03.003

Amari, S.-i., 1993. Backpropagation and stochastic gradient descent method. Neurocomputing 5 (4), 185-196. https://doi.org/10.1016/0925-2312(93)90006-O

Bahar, A., Özgen, C., Leblebicioˇglu, K., Halıcı, U., 2004. Artificial neural network estimator design for the inferential model predictive control of an industrial distillation column. Industrial & Engineering Chemistry Research, 43(19), 6102-6111. https://doi.org/10.1021/ie030585g

Brigham, K., Gupta, S., Brigham, J. C., 2018. Predicting responses to mechanical ventilation for preterm infants with acute respiratory illness using artificial neural networks. International Journal for Numerical Methods in Biomedical Engineering, 34(8), e3094. https://doi.org/10.1002/cnm.3094

Calle, E., Oliden, J., 2021a. Iterative dual-gradient descent method for model predictive control with constraints. In 2021 IEEE XXVIII International Conference on Electronics, Electrical Engineering and Computing (INTERCON), 1-4. https://doi.org/10.1109/INTERCON52678.2021.9532891

Calle, E., Oliden, J., 2021b. Recurrent neural network based predictive control applied to 4 coupled-tank system. In 2021 IEEE International Conference on Automation/XXIV Congress of the Chilean Association of Automatic Control (ICA-ACCA), 1-6. https://doi.org/10.1109/ICAACCA51523.2021.9465192

Carvalho, C. B., Carvalho, E. P., Ravagnani, M. A. S. S., 2020. Implementation of a neural network mpc for heat exchanger network temperature control. Brazilian Journal of Chemical Engineering, 3, 729-744. https://doi.org/10.1007/s43153-020-00058-2

Colosi, T., Abrudean, M.-I., 2013. Numerical Simulation of Distributed Parameter Processes. Springer International Publishing.

https://doi.org/10.1007/978-3-319-00014-5

Csekö, L. H., Kvasnica, M., Lantos, B., 2015. Explicit mpc-based rbf neural network controller design with discrete-time actual kalman filter for semiactive suspension. IEEE Transactions on Control Systems Technology, 23(5), 1736-1753. https://doi.org/10.1109/TCST.2014.2382571

Dong, L., Yan, J., Yuan, X., He, H., Sun, C., 2019. Functional nonlinear model predictive control based on adaptive dynamic programming. IEEE Transactions on Cybernetics, 49(12), 4206-4218. https://doi.org/10.1109/TCYB.2018.2859801

Gao, Y., Xu, X., Yang, Y., 2011. A new neural network for solving nonlinear programming problems. Advances in Neural Networks - ISNN 2011, 565-571. https://doi.org/10.1007/978-3-642-21105-8_65

Hornik, K., Stinchcombe, M., White, H., 1989. Multilayer feedforward networks are universal approximators. Neural Networks, 2(5), 359-366. https://doi.org/10.1016/0893-6080(89)90020-8

Johansson, K. H., 2000. The quadruple-tank process: a multivariable laboratory process with an adjustable zero. IEEE Transactions on Control Systems Technology, 8(3), 456-465. https://doi.org/10.1109/87.845876

Kouvaritakis, B., Cannon, M., 2016. Model Predictive Control: Classical, Robust and Stochastic. Springer, Cham, 1st ed. https://doi.org/10.1007/978-3-319-24853-0

Lucia, S., Karg, B., 2018. A deep learning-based approach to robust nonlinear model predictive control. IFAC-PapersOnLine, vol. 51, no. 20, 511-516. 6th IFAC Conference on Nonlinear Model Predictive Control NMPC 2018. https://doi.org/10.1016/j.ifacol.2018.11.038

Manonmani, A., Thyagarajan, T., Elango, M., Sutha, S., 2018. Modelling and control of greenhouse system using neural networks. Transactions of the Institute of Measurement and Control 40, 918e929. https://doi.org/10.1177/0142331216670235

Nguyen, N.-S., 2020. Level control of quadruple tank system based on adaptive inverse evolutionary neural controller. International Journal of Control, Automation and Systems 18. https://doi.org/10.1007/s12555-019-0504-8

Pan, Y., Wang, J., 2010. A neurodynamic optimization approach to nonlinear model predictive control. In 2010 IEEE International Conference on Systems, Man and Cybernetics, 1597-1602. https://doi.org/10.1109/ICSMC.2010.5642367

Pan, Y., Wang, J., 2012. Model predictive control of unknown nonlinear dynamical systems based on recurrent neural networks. IEEE Transactions on Industrial Electronics, 59(8), 3089-3101. https://doi.org/10.1109/TIE.2011.2169636

Piga, D., Forgione, M., Formentin, S., Bemporad, A., 2019. Performance oriented model learning for data-driven mpc design. IEEE Control Systems Letters, 3(3), 577-582. https://doi.org/10.1109/LCSYS.2019.2913347

Popoola, S. I., Jefia, A., Atayero, A. A., Kingsley, O., Faruk, N., Oseni, O. F., Abolade, R. O., 2019. Determination of neural network parameters for path loss prediction in very high frequency wireless channel. IEEE Access 7, 150462-150483. https://doi.org/10.1109/ACCESS.2019.2947009

Rawlings, J. B., Mayne, D. Q., Moritz, M. D. (Eds.), 2017. Model predictive control: theory, computation, and design, 2nd Edition. Nob Hill Publishing.

Saadon, A., Abdullah, J., Muhammad, N. S., Ariffin, J., Sep 2020. Development of riverbank erosion rate predictor for natural channels using narx-qr factorization model: a case study of sg. bernam, selangor, malaysia. Neural Computing and Applications 32 (18), 14839-14849. https://doi.org/10.1007/s00521-020-04835-5

Sarali, D. S., Agnes Idhaya Selvi, V., Pandiyan, K., 2019. An improved design for neural-network-based model predictive control of three-phase inverters. In 2019 IEEE International Conference on Clean Energy and Energy Efficient Electronics Circuit for Sustainable Development (INCCES), 1-5. https://doi.org/10.1109/INCCES47820.2019.9167697

Shin, Y., Smith, R., Hwang, S., 2020. Development of model predictive control system using an artificial neural network: A case study with a distillation column. Journal of Cleaner Production, 277(2020) 124124. https://doi.org/10.1016/j.jclepro.2020.124124

Tang, W., Daoutidis, P., 2019. Distributed control and optimization of process system networks: A review and perspective. Chinese Journal of Chemical Engineering, 27(7), 1461-1473. https://doi.org/10.1016/j.cjche.2018.08.027

Viera, B. G., Santos, V., Carvalho, F. R., Pereira, J., Frattini Fileti, A. M., 2005. Identification and predictive control of a fcc unit using a mimo neural model. Chemical Engineering and Processing, 44(8), 855-868. https://doi.org/10.1016/j.cep.2004.08.008

Xu, J., Li, C., He, X., Huang, T., 2016. Recurrent neural network for solving model predictive control problem in application of four-tank benchmark. Neurocomputing 190, 172-178. https://doi.org/10.1016/j.neucom.2016.01.020

Yan, Y., Xu, Q., 2019. Neural networks-based model predictive control for precision motion control of a micropositioning system. In 2019 IEEE International Conference on Real-time Computing and Robotics (RCAR), 252-257. https://doi.org/10.1109/RCAR47638.2019