Abstract
Cold rolling is an important part of the iron and steel industry, and the unsteady rolling process of cold rolling usually brings significant influences on the stability of product quality. In the unsteady rolling process, various disturbances and uncertainties such as variable lubrication state, variable equipment working conditions lead to difficulties in the establishment of state space model of thickness and tension, which has become a thorny problem in thickness and tension control. In this paper, we present a model-free controller based on Deep Deterministic Policy Gradient (DDPG), which can continuously control the thickness tension of the unsteady rolling process without the mathematical model. We first formulate the thickness and tension control problem to Markov Decision Process (MDP). We apply strategies such as dividing state space variables with the mechanism model, defining reward function and state normalization, the random disturbance and complex uncertainties of the unsteady cold rolling process are coped with by utilizing the DDPG controller. In addition, these strategies also ensure the learning performance and stability of DDPG controller under random disturbance. Simulations and experiments show that the proposed the DDPG controller does not require any prior knowledge of uncertain parameters and can operate without knowing unsteady rolling mathematical models, which has better accuracy, stability, and rapidity for thickness and tension in the unsteady rolling process than proportional integral (PI) controller. The artificial intelligence–based controller brings both product quality improvement and intelligence to cold rolling.
Similar content being viewed by others
Data availability
The data are available on reasonable demand.
Code availability
The code is available on reasonable demand.
References
Zhang X, Zhang Q, Sun C (2009) Gauge and tension control in unsteady state of cold rolling using mixed H2/H∞ control. In IEEE International Conference on Control and Automation Christchurch, New Zealand, pp 9–11
Seung-Ho S, Seung-Ki S (2000) A new tension controller for continuous strip processing line. IEEE Trans Ind Appl 36:2. https://doi.org/10.1109/28.833782
Wang Y, Xia J, Wang Z, Shen H (2020) Design of a fault-tolerant output-feedback controller for thickness control in cold rolling mills. Appl Math Comput. https://doi.org/10.1016/j.amc.2019.124841
Friebel T, Zabet K, Haber R, Jelali M (2015) Predictive functional control of tandem cold metal rolling. IEEE Conf Control Appl 324–329
Li B, Fan X, Jiang C, Jiang G (2014) Decoupling control of thickness and tension based on DRNN-PID in cold-rolling. In Proceeding of the 11th World Congress on Intelligent Control and Automation, pp 1180–1184
Tan S, Wang L, Liu J (2014) Research on decoupling method of thickness and tension control in rolling process. In Proceeding of the 11th World Congress on Intelligent Control and Automation Shenyang, pp. 4715–4717
An S (2016) The decoupling control of tandem cold rolling tension and gauge. In 2016 3rd International Conference on Information Science and Control Engineering (ICISCE), pp. 1154–1158
Hu Y-J, Sun J, Wang Q-L, Yin F-C, Zhang D-H (2018) Characteristic analysis and optimal control of the thickness and tension system on tandem cold rolling. Int J Adv Manuf Technol. https://doi.org/10.1007/s00170-018-3088-1
Hu Y, Sun J, Chen SZ, Zhang X, Peng W, Zhang D (2019) Optimal control of tension and thickness for tandem cold rolling process based on receding horizon control. Ironmak Steelmak 1–11. https://doi.org/10.1080/03019233.2019.1615813
Koofigar HR, Sheikholeslam F, Hosseinnia S (2011) Unified gauge-tension control in cold rolling mills: a robust regulation technique. Int J Precis Eng Manuf 12(3):393–403. https://doi.org/10.1007/s12541-011-0051-6
Ogasahara T, Hovd M, Asano K (2016) Explicit model predictive controller design for thickness and tension control in a cold rolling mill. IFAC-PapersOnLine 49(20):126–131
Hu Y, Sun J, Peng W, Zhang D (2021) Nash equilibrium-based distributed predictive control strategy for thickness and tension control on tandem cold rolling system. J Process Control 97:92–102. https://doi.org/10.1016/j.jprocont.2020.11.014
Ozaki K, Ohtsuka T, Fujimoto K, Kitamura A, Nakayama M (2010) Nonlinear receding horizon control of thickness and tension in a tandem cold mill with a variable rolling speed. Tetsu-to-Hagane 96(7):459–467. https://doi.org/10.2355/tetsutohagane.96.459
Cao L, Li X, Wang Q, Zhang D (2021) Vibration analysis and numerical simulation of rolling interface during cold rolling with unsteady lubrication. Tribol Int. https://doi.org/10.1016/j.triboint.2020.106604
Sun B, He M, Wang Y, Gui W, Yang C, Zhu Q (2018) A data-driven optimal control approach for solution purification process. J Process Control 68:171–185. https://doi.org/10.1016/j.jprocont.2018.06.005
Frikha MS, Gammar SM, Lahmadi A, Andrey L (2021) Reinforcement and deep reinforcement learning for wireless Internet of Things: a survey. Comput Commun 178:98–113. https://doi.org/10.1016/j.comcom.2021.07.014
Viharos ZJ, Jakab R (2021) Reinforcement learning for statistical process control in manufacturing. Measurement. https://doi.org/10.1016/j.measurement.2021.109616
Nian R, Liu J, Huang B (2020) A review on reinforcement learning: introduction and applications in industrial process control. Comput Chem Eng. https://doi.org/10.1016/j.compchemeng.2020.106886
Du Y, Zandi H, Kotevska O, Kurte K, Munk J, Amasyali K, Makee E, Li F (2021) Intelligent multi-zone residential HVAC control strategy based on deep reinforcement learning. Appl Energy. https://doi.org/10.1016/j.apenergy.2020.11611
Gu S, Ethan H, Timothy L, Sergey L (2017) Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates. In Proceedings of the 2017 IEEE International Conference on Robotics and Automation (ICRA), pp 3389–3396
Liu L, Chen E, Gao Z, Wang Y (2019) Research on motion planning of seven degree of freedom manipulator based on DDPG. In Wang K., Wang Y., Strandhagen J., Yu T. (eds) Advanced Manufacturing and Automation VIII. IWAMA 2018. Lecture Notes in Electrical Engineering, vol 484. Springer, Singapore. https://doi.org/10.1007/978-981-13-2375-1_44
Qiu C, Hu Y, Chen Y, Zeng B (2019) Deep deterministic policy gradient (DDPG)-based energy harvesting wireless communications. IEEE Internet Things J 6(5):8577–8588. https://doi.org/10.1109/jiot.2019.2921159
Wang Y, Shen H, Duan D (2017) On stabilization of quantized sampled-data neural-network-based control systems. IEEE Transactions on Cybernetics 47(10):3124–3135. https://doi.org/10.1109/tcyb.2016.2581220
Qi Z, Peng S, Honghai L, Shengyuan X (2012) Neural-network-based decentralized adaptive output-feedback control for large-scale stochastic nonlinear systems. IEEE Trans Syst Man Cybern Part B (Cybern) 42(6):1608–1619. https://doi.org/10.1109/tsmcb.2012.2196432
Buşoniu L, de Bruin T, Tolić D, Kober J, Palunko I (2018) Reinforcement learning for control: performance, stability, and deep approximators. Annu Rev Control 46:8–28. https://doi.org/10.1016/j.arcontrol.2018.09.005
Gao G, Li J, Wen Y (2020) DeepComfort: energy-efficient thermal comfort control in buildings via reinforcement learning. IEEE Internet Things J 7(9):8472–8484. https://doi.org/10.1109/jiot.2020.2992117
Ma Y, Zhu W, Benton MG, Romagnoli J (2019) Continuous control of a polymerization system with deep reinforcement learning. J Process Control 75:40–47. https://doi.org/10.1016/j.jprocont.2018.11.004
Siraskar R (2021) Reinforcement learning for control of valves. Mach Learn Appl. https://doi.org/10.1016/j.mlwa.2021.100030
Spielberg S, Gopaluni RB, Loewen PD (2017) Deep reinforcement learning approaches for process control. In 2017 6th International Symposium on Advanced Control of Industrial Processes (AdCONIP), pp: 28–31
Mnih V, Kavukcuoglu K, Silver D, Graves A, Antonoglou L, Wierstra D, Riedmiller M (2013) Playing atari with deep reinforcement learning. arXiv:1312.5602
Lillicrap TP, Hunt JJ, Pritzel A, Heess N, Erez T, Tassa Y, Silver D, Wierstra D (2015) Continuous control with deep reinforcement learning. arXiv:1509.02971
Sutton RS, McAllester D, Singh S, Mansour Y (2000) Policy gradient methods for reinforcement learning with function approximation. Adv Neural Inf Process Syst 1057–1063
Mnih V, Kavukcuoglu K, Silver D, Rusu AA, Veness J, Bellemare MG, Graves A, Riedmiler M, Fidjeland AK, Ostrovski G, Petersen S, Beattie C, Sadik A, Antonoglou I, King H, Kumaran D, Wierstra D, Legg S, Hassabis D (2015) Human-level control through deep reinforcement learning. Nature 518(7540):529–533. https://doi.org/10.1038/nature14236
Fang X, Han Y, Wang J, Zhao Q (2019) A cognitive control approach for microgrid performance optimization in unstable wireless communication. Neurocomputing 355:168–182. https://doi.org/10.1016/j.neucom.2019.04.048
Abadi M, Barham P, Chen J, Chen Z, Davis A, Dean J, Devin M, Ghemawat S, Irving G, Isard M, Levenberg J, Monga R, Morre S, GMurray, D, G., Steiner, B., Tucker, P., (2016) Tensorflow: a system for large-scale machine learning. OSDI 16:265–283
Funding
This work was supported by the National Natural Science Foundation of China (U21A20475,U1908213), Colleges and Universities in Hebei Province Science Research Program (QN2020504), The Fundamental Research Funds for the Central Universities (N2223001).
Author information
Authors and Affiliations
Contributions
Wenying Zeng: conceptualization, methodology, investigation, data curation, software, formal analysis, experiment, and writing of the manuscript. Jinkuan Wang: conceptualization, resources, funding acquisition, supervision, project administration, and review. Yan Zhang: data collection and curation, writing review and editing. Yinghua Han: methodology, supervision, and writing including review and editing. Qiang Zhao: methodology, supervision, and writing including review and editing.
Corresponding author
Ethics declarations
Ethics approval and consent to participate
All authors understand and approve the ethical responsibilities of the authors. The authors consent to participate.
Consent for publication
The authors consent to transfer the copyright of the article to publish.
Conflict of interest
All authors declare no competing interests.
Additional information
Publisher's note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Zeng, W., Wang, J., Zhang, Y. et al. DDPG-based continuous thickness and tension coupling control for the unsteady cold rolling process. Int J Adv Manuf Technol 120, 7277–7292 (2022). https://doi.org/10.1007/s00170-022-09239-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00170-022-09239-4