Many controlled processes, such as biochemical ones, are repetitive, similar to batch-organized processes. They generate Optimal Control Problems (OCPs) solved by optimal controllers, which often predict the best control values over a prediction horizon using a process model (PM). The latter can encompass imprecise, incomplete, and uncertain knowledge, nonlinearities, or may represent a distributed-parameter system, among other features. Using metaheuristics like the Evolutionary Algorithm (EA) within control structures is a practical approach for specific OCPs. The main drawback of this solution is its high computational demands, which can exceed the sampling period. Previously, the authors explored a new topic: whether a machine learning (ML) algorithm could “learn” the optimal behavior of the couple (EA and PM). Multilinear regression functions were trained and utilized within the ML controller, leading to a significant reduction in its execution time. This article extends the research and proposes using Regressive Neural Networks (RNNs) instead of regression functions, because they have limited capacity to capture nonlinearities. RNNs are more complex regression models, with a greater capacity to model EA-PM couples. The article meticulously describes how the training data is obtained. Algorithms for constructing the RNNs, developing the RNN predictor, and simulating the closed-loop are also proposed. The results are convincing: a) the control-loop dynamic was practically identical with that using the EA predictor; b) the performance indices were practically the same; c) the controller’s execution time decreased remarkably. Using MATLAB for the Park Ramirez Problem, this time was 38 seconds, with the multilinear regression functions, it was 0. 08 seconds, and now with the RNN predictor, it is 0.0549 seconds. This outstanding reduction in prediction time opens the possibility to apply Receding Horizon Control (RHC) not only to slow processes but also to fast ones, which have small time constants.
References
[1]
Siarry, P. (2016) Metaheuristics. Springer.
[2]
Talbi, E. (2009) Metaheuristics. Wiley. https://doi.org/10.1002/9780470496916
[3]
Kruse, R., Borgelt, C., Braune, C., Mostaghim, S. and Steinbrecher, M. (2016) Computational Intelligence—A Methodological Introduction. 2nd Edition, Springer.
[4]
Faber, R., Jockenhövel, T. and Tsatsaronis, G. (2005) Dynamic Optimization with Simulated Annealing. Computers&ChemicalEngineering, 29, 273-290. https://doi.org/10.1016/j.compchemeng.2004.08.020
[5]
Onwubolu, G. and Babu, B.V. (2004) New Optimization Techniques in Engineering. Springer.
[6]
Valadi, J. and Siarry, P. (2014) Applications of Metaheuristics in Process Engineering, Springer International Publishing, 1-39. https://doi.org/10.1007/978-3-319-06508-3
[7]
Minzu, V., Riahi, S. and Rusu, E. (2021) Optimal Control of an Ultraviolet Water Disinfection System. AppliedSciences, 11, Article 2638. https://doi.org/10.3390/app11062638
[8]
Abraham, A., Jain, L. and Goldberg, R. (2005) Evolutionary Multiobjective Optimization—Theoretical Advances and Applications. Springer.
[9]
Mînzu, V., Rusu, E. and Arama, I. (2023) Execution Time Decrease for Controllers Based on Adaptive Particle Swarm Optimization. Inventions, 8, Article 9. https://doi.org/10.3390/inventions8010009
[10]
Minzu, V. and Serbencu, A. (2020) Systematic Procedure for Optimal Controller Implementation Using Metaheuristic Algorithms. IntelligentAutomation&SoftComputing, 26, 663-677. https://doi.org/10.32604/iasc.2020.010101
[11]
Minzu, V. (2020) Optimal Control Implementation with Terminal Penalty Using Metaheuristic Algorithms. Automation, 1, 48-65. https://doi.org/10.3390/automation1010004
[12]
Minzu, V., Ifrim, G. and Arama, I. (2021) Control of Microalgae Growth in Artificially Lighted Photobioreactors Using Metaheuristic-Based Predictions. Sensors, 21, 8065. https://doi.org/10.3390/s21238065
[13]
Minzu, V., Riahi, S. and Rusu, E. (2021) Implementation Aspects Regarding Closed-Loop Control Systems Using Evolutionary Algorithms. Inventions, 6, Article 53. https://doi.org/10.3390/inventions6030053
[14]
Mînzu, V. and Arama, I. (2022) Optimal Control Systems Using Evolutionary Algorithm-Control Input Range Estimation. Automation, 3, 95-115. https://doi.org/10.3390/automation3010005
[15]
Mînzu, V., Georgescu, L. and Rusu, E. (2022) Predictions Based on Evolutionary Algorithms Using Predefined Control Profiles. Electronics, 11, Article 1682. https://doi.org/10.3390/electronics11111682
[16]
Goodfellow, I., Bengio, Y. and Courville, A. (2016) Machine Learning Basics. In: Dietterich, T., Bishop, C., Heckerman, D., Jordan, M., and Kearns, M., Eds., Deep Learning, The MIT Press, 95-161.
[17]
Zou, S., Chu, C., Shen, N. and Ren, J. (2023) Healthcare Cost Prediction Based on Hybrid Machine Learning Algorithms. Mathematics, 11, Article 4778. https://doi.org/10.3390/math11234778
[18]
Cuadrado, D., Valls, A. and Riaño, D. (2023) Predicting Intensive Care Unit Patients’ Discharge Date with a Hybrid Machine Learning Model That Combines Length of Stay and Days to Discharge. Mathematics, 11, Article 4773. https://doi.org/10.3390/math11234773
[19]
Albahli, S., Irtaza, A., Nazir, T., Mehmood, A., Alkhalifah, A. and Albattah, W. (2022) A Machine Learning Method for Prediction of Stock Market Using Real-Time Twitter Data. Electronics, 11, Article 3414. https://doi.org/10.3390/electronics11203414
[20]
Mînzu, V. and Arama, I. (2024) A Machine Learning Algorithm That Experiences the Evolutionary Algorithm’s Predictions—An Application to Optimal Control. Mathematics, 12, Article 187. https://doi.org/10.3390/math12020187
[21]
Newbold, P., Carlson, W.L. and Thorne, B. (2007) Multiple Regression. In: Pfaltzgraff, M. and Bradley, A., Eds., StatisticsforBusinessandEconomics, 6th Edition, Pearson Education, Inc., 454-537.
[22]
Shi, H., Zhang, X., Gao, Y., Wang, S. and Ning, Y. (2023) Robust Total Least Squares Estimation Method for Uncertain Linear Regression Model. Mathematics, 11, Article 4354. https://doi.org/10.3390/math11204354
[23]
Goodfellow, I., Bengio, Y. and Courville, A. (2016) Example: Linear Regression. In: Dietterich, T., Bishop, C., Heckerman, D., Jordan, M., and Kearns, M., Eds., DeepLearning, The MIT Press, 104-113.
[24]
Hu, X. and Chen, W. (2005) Genetic Algorithm Based on Receding Horizon Control for Arrival Sequencing and Scheduling. EngineeringApplicationsofArtificialIntelligence, 18, 633-642. https://doi.org/10.1016/j.engappai.2004.11.012
[25]
Hu, X.B. and Chen, W.H. (2005) Genetic Algorithm Based on Receding Horizon Control for Real-Time Implementations in Dynamic Environments. Proceedingsofthe 16thTriennialWorldCongress, Prague, 4-8 July 2005, 156-161.
[26]
Mayne, D.Q. and Michalska, H. (1990) Receding Horizon Control of Nonlinear Systems. IEEETransactionsonAutomaticControl, 35, 814-824. https://doi.org/10.1109/9.57020
[27]
Goggos, V. and King, R.E. (1996) Evolutionary Predictive Control (EPC) Computers&ChemicalEngineering, 20, S817-S822. https://doi.org/10.1016/0098-1354(96)00144-5
[28]
Chiang, P. and Willems, P. (2015) Combine Evolutionary Optimization with Model Predictive Control in Real-Time Flood Control of a River System. WaterResourcesManagement, 29, 2527-2542. https://doi.org/10.1007/s11269-015-0955-5
[29]
Banga, J.R., Balsa-Canto, E., Moles, C.G. and Alonso, A.A. (2005) Dynamic Optimization of Bioprocesses: Efficient and Robust Numerical Strategies. JournalofBiotechnology, 117, 407-419. https://doi.org/10.1016/j.jbiotec.2005.02.013
[30]
Balsa-Canto, E., Banga, J.R., Alonso, A.A. and Vassiliadis, V.S. (2001) Dynamic Optimization of Chemical and Biochemical Processes Using Restricted Second-Order Information. Computers&ChemicalEngineering, 25, 539-546. https://doi.org/10.1016/s0098-1354(01)00633-0
