Performance prediction and operating conditions optimization for aerobic fermentation heat recovery system based on machine learning

Wei He, Yongna Cao, Jiang Qin, Chao Guo, Zhanjiang Pei and Yanling Yu

Renewable Energy, 2025, vol. 239, issue C

Abstract: The low-grade, long-term production characteristics of aerobic fermentation heat (AFH) present challenges in heat recovery, leading to oversight. Clarifying the correlation between the operating conditions and performance of the aerobic fermentation heat recovery system (AFHRS) is crucial for achieving efficient AFH utilization. This study introduced machine learning tools to design and optimize an AFHRS that is suitable for two types of cold sources. A performance prediction model for the AFHRS was established with an average relative error of 3.66 %. The results demonstrate that, higher fermentation temperatures and flow rates exhibit advantageous effects on heat recovery performance. A moderate water flow is suitable for daily heating, providing a higher heat transfer rate (1573 W, 27.4 °C); a lower water flow is suitable for supplying hot water, providing a higher water temperature (898.7 W, 45.5 °C). High air flow shows unique potential in bio-drying, providing hot outdoor air (48.3 °C). In comparison to air (≤18.8 %), water demonstrates satisfactory heat recovery efficiency (49.5 %–82.1 %). However, maintaining optimum operating conditions for an extended duration is impractical. Intermittent heat recovery is a rational approach to align with the AFH production law. We deduced that cascaded heat exchangers can significantly increase AFH utilization efficiency.

Keywords: Aerobic fermentation heat; Heat recovery; Machine learning; Performance prediction model; Operating conditions optimization (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0960148124021876
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:renene:v:239:y:2025:i:c:s0960148124021876

DOI: 10.1016/j.renene.2024.122119

Access Statistics for this article

Renewable Energy is currently edited by Soteris A. Kalogirou and Paul Christodoulides

More articles in Renewable Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().