LEARNING-BASED ADVANCED PROCESS CONTROL: A REVIEW
Tuyboyov O. . & Raxmonov S. .
Annotatsiya
Advanced Process Control (APC) is undergoing a fundamental transformation driven by the rapid integration of data-driven modeling and learning algorithms into industrial control architectures. While classical model-based approaches-most notably model predictive control (MPC)-have provided structured optimization, constraint handling, and stability guarantees, their effectiveness increasingly depends on accurate process models that are difficult to derive for highly nonlinear, large-scale, and time-varying systems. The proliferation of industrial data and advances in machine learning have enabled a new generation of learning-based APC strategies that enhance modeling flexibility, prediction accuracy, and adaptability. However, the deployment of such approaches in safety-critical chemical and industrial processes raises significant concerns regarding stability, robustness, interpretability, and constraint satisfaction. This review provides a systematic and critical synthesis of learning-based advanced process control methods published since 2020, with a particular focus on the progression from data-driven modeling to safe reinforcement learning. The literature is organized according to the functional role of learning within the control loop: (i) data-driven process modeling using neural networks and Gaussian processes, (ii) learning-based MPC frameworks that retain explicit constraint handling, (iii) safety-aware reinforcement learning approaches augmented with stability conditions or MPC supervision, and (iv) advanced soft sensors enabling reliable state estimation and monitoring. Across these categories, we analyze trade-offs among prediction accuracy, computational complexity, data efficiency, safety guarantees, and industrial maturity.
Adabiyotlar
- Huang, J., O'Connor, T., Ahmed, K., Chatterjee, S., Garvin, C., Ghosh, K., ... and Warman, M. (2021). AIChE PD2M Advanced Process Control workshop‐moving APC forward in the pharmaceutical industry. Journal of Advanced Manufacturing and Processing, 3(1), e10071.
- Rani, K. D., Kumar, S., Ranjan, V., Kumar, B., and Dhiman, T. (2025). An Analytical Study of Consumption and Saving Functions: Interlinkages of MPC, MPS, APC, and APS in Economic Theory and Practice. European Economics Letters, 15(4).
- Schwenzer, M., Ay, M., Bergs, T., and Abel, D. (2021). Review on model predictive control: An engineering perspective. The international journal of advanced manufacturing technology, 117(5), 1327-1349.
- Shrier, I., Redelmeier, A., Schnitzer, M. E., and Steele, R. J. (2021). Challenges in interpreting results from ‘multiple regression’when there is interaction between covariates. BMJ Evidence-Based Medicine, 26(2), 53-56.
- Valdés, L., and Caldentey, R. (2024). Financial hedging of operational risk constraints: A general framework. Production and Operations Management, 33(9), 1912-1930.
- Hanover, D., Foehn, P., Sun, S., Kaufmann, E., and Scaramuzza, D. (2021). Performance, precision, and payloads: Adaptive nonlinear mpc for quadrotors. IEEE Robotics and Automation Letters, 7(2), 690-697.
- Lewandowska-Ciszek, A. (2020). Complexity of a modern enterprise and its flexibility in the sector of industrial automation. Bulletin of the Polish Academy of Sciences: Technical Sciences.
- Ding, S., Gu, W., Lu, S., Chen, X., and Yu, R. (2023). Improving operational flexibility of integrated energy systems through operating conditions optimization of CHP units. CSEE Journal of Power and Energy Systems, 9(5), 1854-1865.
- Rhinehart, R. R. (2024). Nonlinear model-based control: using first-principles models in process control. John Wiley and Sons.
- Espina, E., Llanos, J., Burgos-Mellado, C., Cardenas-Dobson, R., Martinez-Gomez, M., and Saez, D. (2020). Distributed control strategies for microgrids: An overview. IEEe Access, 8, 193412-193448.
- O’Shea, E., Khan, R., Breathnach, C., and Margaria, T. (2020, December). Towards automatic data cleansing and classification of valid historical data an incremental approach based on mdd. In 2020 IEEE International Conference on Big Data (Big Data) (pp. 1914-1923). IEEE.
- Au, H., Alptekin, H., Jensen, A. C., Olsson, E., O’Keefe, C. A., Smith, T., ... and Titirici, M. M. (2020). A revised mechanistic model for sodium insertion in hard carbons. Energy and environmental science, 13(10), 3469-3479.
- Mohsen, O., Mohamed, Y., and Al-Hussein, M. (2022). A machine learning approach to predict production time using real-time RFID data in industrialized building construction. Advanced Engineering Informatics, 52, 101631.
- Sha, X., Ma, Z., Sethuvenkatraman, S., and Li, W. (2025). Online learning-enhanced data-driven model predictive control for optimizing HVAC energy consumption, indoor air quality and thermal comfort. Applied Energy, 383, 125341.
- Shakya, A. K., Pillai, G., and Chakrabarty, S. (2023). Reinforcement learning algorithms: A brief survey. Expert Systems with Applications, 231, 120495.
- Li, Z., Liu, F., Yang, W., Peng, S., and Zhou, J. (2021). A survey of convolutional neural networks: analysis, applications, and prospects. IEEE transactions on neural networks and learning systems, 33(12), 6999-7019.
- Yang, G. R., and Wang, X. J. (2020). Artificial neural networks for neuroscientists: a primer. Neuron, 107(6), 1048-1070.
- Li, H., Lin, L., and Zeng, H. (2024). Machine learning methods (pp. 1-532). Singapore: Springer.
- Hewing, L., Wabersich, K. P., Menner, M., and Zeilinger, M. N. (2020). Learning-based model predictive control: Toward safe learning in control. Annual Review of Control, Robotics, and Autonomous Systems, 3(1), 269-296.
- Han, C., Jeong, Y., Ahn, J., Kim, T., Choi, J., Ha, J. H., ... and Park, I. (2023). Recent advances in sensor–actuator hybrid soft systems: Core advantages, intelligent applications, and future perspectives. Advanced Science, 10(35), 2302775.
- Lin, Y. S., Chien, C. F., and Chou, D. (2022). UNISON decision framework for hybrid optimization of wastewater treatment and recycle for Industry 3.5 and cleaner semiconductor manufacturing. Resources, Conservation and Recycling, 182, 106282.
- Arabzadeh, V., and Frank, R. (2024). Creating a renewable energy-powered energy system: Extreme scenarios and novel solutions for large-scale renewable power integration. Applied Energy, 374, 124088.
- Barto, L., Bulín, J., Krokhin, A., and Opršal, J. (2021). Algebraic approach to promise constraint satisfaction. Journal of the ACM (JACM), 68(4), 1-66.
- Daryanavard, S. (2024). Real-time predictive artificial intelligence: deep reinforcement learning for closed-loop control systems and open-loop signal processing (Doctoral dissertation, University of Glasgow).
- Ramos, I. F., Gianini, G., Leva, M. C., and Damiani, E. (2024). Collaborative intelligence for safety-critical industries: A literature review. Information, 15(11), 728.
- Shakya, A. K., Pillai, G., and Chakrabarty, S. (2023). Reinforcement learning algorithms: A brief survey. Expert Systems with Applications, 231, 120495.
- Lee, M., Yu, Y., Cheon, Y., Baek, S., Kim, Y., Kim, K., ... and Jeong, J. (2023). Machine learning-based prediction of controlled variables of APC systems using time-series data in the petrochemical industry. Processes, 11(7), 2091.
- Ahmadi, H., and Kazemi, A. (2020). The Lyapunov-based stability analysis of reduced order micro-grid via uncertain LMI condition. International Journal of Electrical Power and Energy Systems, 117, 105585.
- Zhang, T., Chen, J., Li, F., Zhang, K., Lv, H., He, S., and Xu, E. (2022). Intelligent fault diagnosis of machines with small and imbalanced data: A state-of-the-art review and possible extensions. ISA transactions, 119, 152-171.