Abstract
To achieve the desired quality standards of certain manufactured materials, the involved parameters are still adjusted by knowledge-based procedures according to human expertise, which can be costly and time-consuming. To optimize operational efficiency and provide decision support for human experts, we develop a general continuous control framework that utilizes deep reinforcement learning (DRL) to automatically determine the main control parameters, in situations where simulation environments are unavailable and traditional PID controllers are not viable options. In our work, we aim to automatically learn the key control parameters to achieve the desired outlet thickness of the manufactured material. We first construct a surrogate environment based on real-world expert trajectories obtained from the true underlining manufacturing process to achieve this. Subsequently, we train a DRL agent within the surrogate environment. Our results suggest a Proximal Policy Optimization (PPO) algorithm combined with a Multi-Layer Perceptron (MLP) surrogate environment to successfully learn a policy that continuously changes parameter configurations optimally, achieving the desired target material thickness within an acceptable range.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Andrychowicz, M., et al.: What matters for on-policy deep actor-critic methods? A large-scale study. In: International Conference on Learning Representations (2021)
Araki, M.: PID control. In: Control Systems, Robotics and Automation: System Analysis and Control: Classical Approaches II, 58–79 (2009)
Bennett, S.: Development of the PID controller. IEEE Control Syst. Mag. 13(6), 58–62 (1993)
Brockman, G., et al.: OpenAI Gym (2016)
Deng, J., Sierla, S., Sun, J., Vyatkin, V.: Reinforcement learning for industrial process control: a case study in flatness control in steel industry. Comput. Ind. 143, 103748 (2022)
Dornheim, J., Link, N., Gumbsch, P.: Model-free adaptive optimal control of episodic fixed-horizon manufacturing processes using reinforcement learning. Int. J. Control Autom. Syst. 18, 1593–1604 (2020)
Gamal, O., Mohamed, M.I.P., Patel, C.G., Roth, H.: Data-driven model-free intelligent roll gap control of bar and wire hot rolling process using reinforcement learning. Int. J. Mech. Eng. Robot. Res. 10(7), 349–356 (2021)
Guo, F., Zhou, X., Liu, J., Zhang, Y., Li, D., Zhou, H.: A reinforcement learning decision model for online process parameters optimization from offline data in injection molding. Appl. Soft Comput. 85, 105828 (2019)
Hornik, K., Stinchcombe, M., White, H.: Multilayer feedforward networks are universal approximators. Neural Netw. 2(5), 359–366 (1989)
LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015)
Levine, S., Finn, C., Darrell, T., Abbeel, P.: End-to-end training of deep visuomotor policies. J. Mach. Learn. Res. 17(1), 1334–1373 (2016)
Levine, S., Pastor, P., Krizhevsky, A., Ibarz, J., Quillen, D.: Learning hand-eye coordination for robotic grasping with deep learning and large-scale data collection. Int. J. Robot. Res. 37(4–5), 421–436 (2018)
Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)
Lin, L.J.: Reinforcement Learning for Robots Using Neural Networks. Carnegie Mellon University (1992)
Martínez, M.A., Sanchis, J., Blasco, X.: Multiobjective controller design handling human preferences. Eng. Appl. Artif. Intell. 19(8), 927–938 (2006)
Mazgualdi, C.E., Masrour, T., Hassani, I.E., Khdoudi, A.: A deep reinforcement learning (DRL) decision model for heating process parameters identification in automotive glass manufacturing. In: Masrour, T., Cherrafi, A., El Hassani, I. (eds.) A2IA 2020. AISC, vol. 1193, pp. 77–87. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-51186-9_6
Mirhoseini, A., et al.: A graph placement methodology for fast chip design. Nature 594(7862), 207–212 (2021)
Mnih, V., et al.: Playing Atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)
Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529–533 (2015)
Ruelens, F., Claessens, B.J., Quaiyum, S., De Schutter, B., Babuška, R., Belmans, R.: Reinforcement learning applied to an electric water heater: from theory to practice. IEEE Trans. Smart Grid 9(4), 3792–3800 (2016)
Schulman, J., Levine, S., Abbeel, P., Jordan, M., Moritz, P.: Trust region policy optimization. In: International Conference on Machine Learning, pp. 1889–1897. PMLR (2015)
Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms (2017)
Silver, D., et al.: Mastering the game of go with deep neural networks and tree search. Nature 529(7587), 484–489 (2016)
Stewart, G., Samad, T.: Cross-application perspectives: application and market requirements. Impact Control Technol. 95–100 (2011)
Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (2018)
Wu, T., Zhao, H., Gao, B., Meng, F.: Energy-saving for a velocity control system of a pipe isolation tool based on a reinforcement learning method. Int. J. Precis. Eng. Manuf.-Green Technol. 9(1), 225–240 (2021). https://doi.org/10.1007/s40684-021-00309-8
Yu, J., Guo, P.: Run-to-run control of chemical mechanical polishing process based on deep reinforcement learning. IEEE Trans. Semicond. Manuf. 33(3), 454–465 (2020)
Zinn, J., Vogel-Heuser, B., Gruber, M.: Fault-tolerant control of programmable logic controller-based production systems with deep reinforcement learning. J. Mech. Des. 143(7), 072004 (2021)
Zirngibl, C., Dworschak, F., Schleich, B., Wartzack, S.: Application of reinforcement learning for the optimization of clinch joint characteristics. Prod. Eng. Res. Devel. 16(2–3), 315–325 (2022)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Dippel, O., Lisitsa, A., Peng, B. (2023). Deep Reinforcement Learning for Continuous Control of Material Thickness. In: Bramer, M., Stahl, F. (eds) Artificial Intelligence XL. SGAI 2023. Lecture Notes in Computer Science(), vol 14381. Springer, Cham. https://doi.org/10.1007/978-3-031-47994-6_30
Download citation
DOI: https://doi.org/10.1007/978-3-031-47994-6_30
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-47993-9
Online ISBN: 978-3-031-47994-6
eBook Packages: Computer ScienceComputer Science (R0)