Maqola

A novel cascade heat integration configuration for electricity/freshwater/hydrogen outputs using SOFC-GT, multi-effect desalination, and PEM electrolysis using machine learning optimization

Zhaoyang ZuoSchool of mechanical engineering, Xijing University, Xi’an, Shaanxi, 710123, ChinaJunhua WangSchool of Computer Science, South China Business College Guangdong University of Foreign Studies, Gangzhou, 510545, Guangdong, ChinaSarminah SamadDepartment of Management, College of Business Administration, Princess Nourah bint Abdulrahman University, Riyadh 11671, Saudi ArabiaNashwan Adnan OthmanDepartment of Computer Engineering, Al-Kitab University, Altun Kupri, IraqAhmad AlmadhorDepartment of Computer Engineering and Networks, College of Computer and Information Sciences, Jouf University, Saudi ArabiaRaymond GhandourCollege of Engineering and Technology, American University of the Middle East, Egaila, 54200, KuwaitIbrahim AlsayerDepartment of Chemical and Materials Engineering, Engineering College, Northern Border University, Arar, 91431, Saudi ArabiaDilsora AbduvalievaDepartment of Mathematics and Information Technologies, Tashkent State Pedagogical University, Bunyodkor avenue, 27, Tashkent, 100070, UzbekistanSalem AlkhalafDepartment of Computer Engineering, College of Computer, Qassim University, Buraydah, Saudi ArabiaSamah G. BabikerDepartment of Electronic Physics, Faculty of Applied Science, Red Sea University, Port Sudan, Sudan

2025en

ABI

Annotatsiya

The current study presents an innovative integrated multi-generation system tailored for residential communities based on a novel cascade heat integration configuration. The proposed system is designed for scalability, making it adaptable for various residential communities, from small housing complexes to larger urban developments. Its modular architecture allows flexible integration with existing infrastructure, enabling widespread deployment in diverse geographic and economic conditions. Utilizing a real-time machine learning framework, the system dynamically optimizes energy distribution and operational efficiency, making it feasible for large-scale implementation while maintaining economic viability and environmental benefits. Hence, a real-time machine learning framework is implemented to optimize key operational parameters dynamically, ensuring efficient fuel utilization, energy distribution, and load balancing across the system. The ML model continuously processes sensor data to adjust SOFC current density, GT pressure ratio, and ORC steam pressure, maximizing exergy efficiency while minimizing operational costs and CO 2 emissions. Additionally, it enhances system reliability through predictive maintenance and demand-based power allocation , enabling a more adaptive and cost-effective multi-generation process. Noteworthy outcomes highlight an exergy efficiency improvement from 48 % to 60 % and a power output increase from 6.1 MW to 11.6 MW. Additionally, the levelized cost of electricity is notably reduced from 8 to 3 cents/kWh. The system also provides extra benefits by generating freshwater and hydrogen, addressing various societal challenges.

Hali tarjima qilinmagan

Identifikatorlar

DOI: 10.1016/j.csite.2025.106275

Iqtiboslar va manbalar

0 ta iqtibos60 ta foydalanilgan manba