Enhancing Control Efficiency in Waste-to-Energy Thermal Power Plants: Radial Basis Function Autoregressive with Exogenous-Based Model Predictive Controller for Steam Boiler Optimization

Abstract:

The availability of electrical energy is essential for human progress and economic development. Renewable energy solutions, including waste-to-energy (WtE) systems, present sustainable alternatives but require advanced control strategies for optimal performance. This research aims to enhance the control of drum level, temperature, and pressure in WtE steam boilers at Ethiopia's Reppie power plant. The existing Programmable Logic Controller (PLC) system is limited in its ability to predict future states and handle nonlinear system behaviors. To overcome these challenges, a Radial Basis Function Autoregressive with Exogenous input (RBF-ARX) model was developed and integrated with a Model Predictive Controller (MPC). The results demonstrate that the MPC approach significantly surpasses the performance of the Linear Quadratic Regulator (LQR) in terms of control efficiency. For temperature control, the MPC achieves a settling time of 0.3955 seconds and a rise time of 0.0195 seconds, compared to LQR's 5.99 seconds. Similarly, for pressure control, the MPC achieves a settling time of 0.6678 seconds, outperforming the LQR's 12.507 seconds. Drum level regulation further showcases the superiority of MPC, with a settling time of 0.5223 seconds versus the LQR's 8.302 seconds. This proposed RBF-ARX-based MPC framework not only optimizes control efficiency at Reppie but also demonstrates scalability and applicability to other WtE plants, enhancing operational performance under varying conditions. MATLAB/Simulink was used for the modeling and simulation, confirming the robustness of this approach for global adoption in WtE systems.

• Periodical: International Journal of Engineering Research in Africa (Volume 74)
• Pages: 115-138
• DOI: https://doi.org/10.4028/p-q8eIyU
• Online since: June 2025
• Authors: Tefera Terefe, Mehret G. Agonafer, Gashaye L. Hailu*
• Keywords: MATLAB, Model Predictive Control, Proportional Integral Derivative Control, Radial Basis Function, Radial Basis Function Autoregressive with Exogenous Inputs, System Identification, Thermal Power Plant

References

[1] Rebellon, Harold E., et al, Thermoelectric modules: applications and opportunities in building environments for sustainable energy generation: from biomass, municipal waste, and other sources, Engineered Science 29 (2024): 1164.

[2] Akroot, Abdulrazzak, Mohamed Almaktar, and Feras Alasali, The Integration of Renewable Energy into a Fossil Fuel Power Generation System in Oil-Producing Countries: A Case Study of an Integrated Solar Combined Cycle at the Sarir Power Plant, Sustainability 16.11 (2024): 4820.

DOI: 10.3390/su16114820

[3] Rezania, Shahabaldin, et al, Review on waste-to-energy approaches toward a circular economy in developed and developing countries, Processes 11.9 (2023): 2566.

DOI: 10.3390/pr11092566

[4] Kachalla, Ibrahim Ali, and Christian Ghiaus, Electric Water Boiler Energy Prediction: State-of-the-Art Review of Influencing Factors, Techniques, and Future Directions,  Energies 17.2 (2024): 443.

DOI: 10.3390/en17020443

[5] Bjelić, Draženko, et al, Waste to energy" as a driver towards a sustainable and circular energy future for the Balkan countries, Energy, Sustainability and Society 14.1 (2024): 3.

DOI: 10.1186/s13705-023-00435-y

[6] Kasiński, Sławomir, and Marcin Dębowski, Municipal Solid Waste as a Renewable Energy Source: Advances in Thermochemical Conversion Technologies and Environmental Impacts, Energies 17.18 (2024): 4704.

DOI: 10.3390/en17184704

[7] Hu, Zongyang, et al, Efficient model predictive control of boiler coal combustion based on NARX neutral network, Journal of Process Control 134 (2024): 103158.

DOI: 10.1016/j.jprocont.2023.103158

[8] Tavoosi, J., and A. Mohammadzadeh, A new recurrent radial basis function network-based model predictive control for a power plant boiler temperature control, International Journal of Engineering 34.3 (2021): 667-675.

DOI: 10.5829/ije.2021.34.03c.11

[9] Wang, Jun, Baocang Ding, and Ping Wang, Modeling and Finite-Horizon MPC for a Boiler-Turbine System Using Minimal Realization State-Space Model, Energies 15.21 (2022): 7935.

DOI: 10.3390/en15217935

[10] Tian, Hao, Jian Tang, and Tianzheng Wang, Furnace temperature model predictive control based on particle swarm rolling optimization for municipal solid waste incineration, Sustainability 16.17 (2024): 7670.

DOI: 10.3390/su16177670

[11] Lan, Jianglin, Efficient model predictive control for nonlinear systems modelled by deep neural networks, arXiv preprint arXiv:2405.10372 (2024).

[12] Kůdela, Jakub, et al, Optimal control of combined heat and power station operation, Optimization and Engineering 25.1 (2024): 121-145.

DOI: 10.1007/s11081-023-09848-2

[13] Zhang, Liang, et al, Challenges and opportunities of machine learning control in building operations, Building Simulation. Vol. 16. No. 6. Beijing: Tsinghua University Press, 2023.

[14] Saloux, Etienne, Jason Runge, and Kun Zhang, Operation optimization of multi-boiler district heating systems using artificial intelligence-based model predictive control: Field demonstrations, Energy 285 (2023): 129524.

DOI: 10.1016/j.energy.2023.129524

[15] Stanger, Lukas, et al, Model predictive control of a dual fluidized bed gasification plant, Applied Energy 361 (2024): 122917.

DOI: 10.1016/j.apenergy.2024.122917

[16] Tang, Jian, et al, An Overview of Artificial Intelligence Application for Optimal Control of Municipal Solid Waste Incineration Process, Sustainability 16.5 (2024): 2042.

DOI: 10.3390/su16052042

[17] Liu, Minghao, et al, A Chattering-Suppression Sliding Mode Controller for an Underwater Manipulator Using Time Delay Estimation, Journal of Marine Science and Engineering 11.9 (2023): 1742.

DOI: 10.3390/jmse11091742

[18] Gayvoronskiy, Sergey, Tatiana Ezangina, and Ivan Khozhaev, Parametric Synthesis of a Water Level Controller for a Boiler Unit on a Base of D-Partition in Vertices of aParametric Polytope, 2020 International Conference on Industrial Engineering, Applications and Manufacturing (ICIEAM). IEEE, 2020.

DOI: 10.1109/icieam48468.2020.9111944

[19] Jha, R. S., and Mandar M. Lele, Dynamic modeling of a water tube boiler,  Heat Transfer 51.7 (2022): 6087-6121.

DOI: 10.1002/htj.22581

[20] Gowthaman, E., et al, Performance analysis of hybrid fuzzy-PID controller action on boiler drum level control, 2016 Online International Conference on Green Engineering and Technologies (IC-GET). IEEE, 2016.

DOI: 10.1109/get.2016.7916709

[21] Yonezawa, Heisei, Ansei Yonezawa, and Itsuro Kajiwara, Experimental verification of model-free active damping system based on virtual controlled object and fuzzy sliding mode control, Mechanical Systems and Signal Processing 224 (2025): 111961.

DOI: 10.1016/j.ymssp.2024.111961

[22] Jan, Ahmed Zubair, Krzysztof Kedzia, and Muhammad Jamshed Abbass, Fractional-order PID controller (FOPID)-based iterative learning control for a nonlinear boiler system, Energies 16.3 (2023): 1045.

DOI: 10.3390/en16031045

[23] Perez, Anthony, and Yu Yang. Offset-free ARX-based adaptive model predictive control applied to a nonlinear process, ISA transactions 123 (2022): 251-262.

DOI: 10.1016/j.isatra.2021.05.030

[24] Tian, Xiaoying, and Pengfei Gao, RBF-ARX model-based fast robust predictive control strategy, Proceedings of the 2024 4th International Conference on Artificial Intelligence, Big Data and Algorithms. 2024.

DOI: 10.1145/3690407.3690508

[25] Peng, H., et al, The RBF-ARX Model Based Modeling And Predictive Control for a Class Of Nonlinear Processes, IFAC Proceedings Volumes 35.1 (2002): 443-448.

DOI: 10.3182/20020721-6-es-1901.00323

[26] Vasičkaninová, Anna, et al, Model predictive control of a tubular chemical reactor,  2019 22nd International Conference on Process Control (PC19). IEEE, 2019.

DOI: 10.1109/pc.2019.8815033

[27] Yang, Yang, et al, Modeling and control approach for dual clutch transmission vehicles starting process based on state-dependent autoregressive with exogenous model, IEEE Access 8 (2020): 158712-158726.

DOI: 10.1109/access.2020.3014162

[28] Tian, Binbin, and Hui Peng, RBF-ARX model-based MPC approach to inverted pendulum: An event-triggered mechanism, Chaos, Solitons & Fractals 176 (2023): 114081.

DOI: 10.1016/j.chaos.2023.114081

[29] De Giorgi, Maria Grazia, Luciano Strafella, and Antonio Ficarella, Neural nonlinear autoregressive model with exogenous input (NARX) for turboshaft aeroengine fuel control unit model, Aerospace 8.8 (2021): 206.

DOI: 10.3390/aerospace8080206

[30] Tian, Binbin, and Hui Peng, RBF-ARX model-based MPC approach to inverted pendulum: An event-triggered mechanism, Chaos, Solitons & Fractals 176 (2023): 114081.

DOI: 10.1016/j.chaos.2023.114081

[31] Nikentari, Nerfita, and H-L. Wei, Multi-task learning using non-linear autoregressive models and recurrent neural networks for tide level forecasting, International Journal of Electrical and Computer Engineering (IJECE) 14.1 (2024): 960-970.

DOI: 10.11591/ijece.v14i1.pp960-970

[32] Li, Lianhui, Adham Manyara, and Jie Liu, Structural parameter optimization of radial basis function neural network based on improved genetic algorithm and cost function model, Advances in Mechanical Engineering 16.11 (2024): 16878132241298190.

DOI: 10.1177/16878132241298190

[33] Kang, Tiao, et al, Deep Learning-Based State-Dependent ARX Modeling and Predictive Control of Nonlinear Systems, IEEE Access 11 (2023): 32579-32594.

DOI: 10.1109/access.2023.3263180

[34] Chacko, Sanjay Joseph, P. C. Neeraj, and Rajesh Joseph Abraham, Optimizing LQR controllers: A comparative study, Results in Control and Optimization 14 (2024): 100387.

DOI: 10.1016/j.rico.2024.100387

[35] Kumari, Soni, Madan Mohan Rayguru, and Shreyansh Upadhyaya, Analysis of Model Predictive Controller versus Linear Quadratic Regulator for DC-DC Buck Converter Systems, 2023 7th International Conference on Intelligent Computing and Control Systems (ICICCS). IEEE, 2023.

DOI: 10.1109/iciccs56967.2023.10142519

[36] Byrski, Witold, et al, Comparison of LQR with MPC in the adaptive stabilization of a glass conditioning process using soft-sensors for parameter identification and state observation, Control Engineering Practice 146 (2024): 105884.

DOI: 10.1016/j.conengprac.2024.105884

[37] Wu, Fangyu, et al, Composing MPC with LQR and neural network for amortized efficiency and stable control, IEEE Transactions on Automation Science and Engineering 21.2 (2023): 2088-2101.

DOI: 10.1109/tase.2023.3259428

[38] Tang, Jian, Hao Tian, and Tianzheng Wang, A Review of Model Predictive Control for the Municipal Solid Waste Incineration Process, Sustainability 16.17 (2024): 7650.

DOI: 10.3390/su16177650