دانشگاه آزاد اسلامی واحد تهران جنوب

صفحه اصلی / نخستین همایش هوش مصنوعی و پژوهش های نوظهور: همگرایی انسان و سیستم های هوشمند

AI-Based Lifespan Estimation and Energy Efficiency Optimization of Port Ship Unloader Motors Under Harsh Environmental Conditions

نویسندگان :

Mohammadali Zarghami¹ Sadigh Raissi² Hamid Tohidi³ Shahrooz Bamdad⁴

1- دانشگاه آزاد اسلامی واحد تهران جنوب 2- دانشگاه آزاد اسلامی واحد تهران جنوب 3- دانشگاه آزاد اسلامی واحد تهران جنوب 4- دانشگاه آزاد اسلامی واحد تهران جنوب

کلمات کلیدی :

Environmental Stress،Deep Reinforcement Learning،Remaining Useful Life (RUL،Energy Saving

چکیده :

Heavy-duty cargo handling equipment at industrial ports like Bandar Imam Khomeini faces extreme environmental challenges—including high temperatures, humidity, and airborne dust—that accelerate equipment wear and increase the risk of unexpected motor failures. These conditions often result in unplanned downtime and significant energy waste. To address this, our study proposes a predictive maintenance strategy aimed at improving energy efficiency by reducing equipment failure through smarter repair scheduling. At the core of this approach is a robust dynamic state estimation (DSE) method, built on an enhanced Sage-Husa adaptive algorithm integrated with the Extended Kalman Filter (EKF). Unlike traditional techniques that assume fixed noise parameters, our method continuously adjusts to real-time changes in measurement noise, providing more accurate and reliable state tracking—even under highly uncertain and fluctuating conditions. Simulation results using the IEEE 39-bus test system, including real-world Phasor Measurement Unit (PMU) data and variable noise scenarios, demonstrate the algorithm’s superior accuracy, adaptability, and convergence. This adaptive DSE framework offers a practical, scalable solution for energy-conscious maintenance planning in harsh operational environments and holds strong potential for deployment in wide-area monitoring systems at ports and industrial sites.