آمار

تعداد نشریات8
تعداد شماره‌ها414
تعداد مقالات5,480
تعداد مشاهده مقاله6,018,491
تعداد دریافت فایل اصل مقاله5,301,787
Barekatain, Maryam, Sayyaf, Negin. (1404). Enhancing the Reliability of Control Systems Using an Improved Deep Reinforcement Learning Framework. نشریه مهندسی عمران امیرکبیر, (), -. doi: 10.22060/ajme.2025.24021.6172
Maryam Barekatain; Negin Sayyaf. "Enhancing the Reliability of Control Systems Using an Improved Deep Reinforcement Learning Framework". نشریه مهندسی عمران امیرکبیر, , , 1404, -. doi: 10.22060/ajme.2025.24021.6172
Barekatain, Maryam, Sayyaf, Negin. (1404). 'Enhancing the Reliability of Control Systems Using an Improved Deep Reinforcement Learning Framework', نشریه مهندسی عمران امیرکبیر, (), pp. -. doi: 10.22060/ajme.2025.24021.6172
Barekatain, Maryam, Sayyaf, Negin. Enhancing the Reliability of Control Systems Using an Improved Deep Reinforcement Learning Framework. نشریه مهندسی عمران امیرکبیر, 1404; (): -. doi: 10.22060/ajme.2025.24021.6172

Enhancing the Reliability of Control Systems Using an Improved Deep Reinforcement Learning Framework

AUT Journal of Mechanical Engineering
مقالات آماده انتشار، پذیرفته شده، انتشار آنلاین از تاریخ 09 خرداد 1404
نوع مقاله: Research Article
شناسه دیجیتال (DOI): 10.22060/ajme.2025.24021.6172
نویسندگان
Maryam Barekatain؛ Negin Sayyaf*
Department of Electrical Engineering, Faculty of Engineering, University of Isfahan, Isfahan, Iran.
چکیده
This paper presents an improved framework for deep reinforcement learning algorithms integrating online system identification, based on the Dyna-Q architecture. The proposed framework is designed to tackle the challenges of both Multi Input Multi Output (MIMO) and Multi Input Single Output (MISO) systems in complex, industry relevant environments, thereby significantly enhancing adaptability and reliability in industrial control systems. It should be noted that in the suggested novel framework, the system identification and model control processes run in parallel with the control process, ensuring a reliable backup in case of faults or disruptions. To verify the efficiency of the aforementioned approach, comparative evaluations in the presence of three of the most common deep reinforcement learning algorithms, i.e. Deep Q Network (DQN), Deep Deterministic Policy Gradient (DDPG), and Twin Delayed Deep Deterministic Policy Gradient (TD3), are conducted on industry-relevant environments simulations available in OpenAI Gym, including the Cart Pole, Pendulum, and Bipedal Walker, each chosen to reflect specific aspects of the novel framework. Results demonstrate that the proposed method for leveraging both real and simulated experiences in this framework improves sample efficiency, stability, and robustness.
کلیدواژه‌ها
Deep Reinforcement Learning؛ Industrial Control Systems؛ System Stability؛ Model-Based Control؛ Intelligent Control Systems
آمار
تعداد مشاهده مقاله: 5


سامانه مدیریت نشریات علمی. طراحی و پیاده سازی از سیناوب