Abstract
This study presents a comprehensive analysis of a 2 kW proton exchange membrane fuel cell-based combined heat and power (PEMFC-CHP) system operating under different electrical and thermal following modes across six representative energy demand profiles. The system’s operational and structural parameters are thoroughly examined, and a multi-objective optimization is conducted by integrating an artificial neural network (ANN) with the Non-dominated Sorting Genetic Algorithm II (NSGA-II). Results indicate that, in winter, the constant power-thermal following mode meets the thermal demand but shortens the PEMFC lifespan due to frequent start-stop cycles. The optimized leveled distributed power mode effectively mitigates shutdowns, achieving a system efficiency (EffCHP) of 0.9784 and a matching degree (φ) of 0.8763, while maintaining stable thermal performance in winter and mid-season. The EffCHP shows an overall improvement of 7% compared with previous studies. In summer, the system operates in electrical-following mode due to reducedthermal demand. According to EWM-TOPSIS analysis, the optimal Pareto solutions achieve φ of 0.9270 and EffCHP of 0.9796 in winter, and φ of 0.9883, EffCHP of 0.9574, with hydrogen consumption of 1.9 kg in summer, confirming superior efficiency and operational coordination.
| Original language | English |
|---|---|
| Journal | International Journal of Green Energy |
| DOIs | |
| State | Accepted/In press - 2026 |
UN SDGs
This output contributes to the following UN Sustainable Development Goals (SDGs)
-
SDG 7 Affordable and Clean Energy
Keywords
- artificial neural network
- combined heat and power
- multi-objective optimization
- Proton exchange membrane fuel cell
- thermal following mode
Fingerprint
Dive into the research topics of 'Analysis and optimization of a 2-kW PEMFC-CHP system under different operating modes'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver