Work

Predicting anaerobic digestion stability in load-flexible operation using gas phase indicators and classification algorithms

Year: 2025

Type: article

Abstract: The increasing reliance on renewable energy sources requires improved management of energy production to match the energy demand. Biogas plants, due to their flexibility, can stabilize electricity grids when operated in load-flexible mode. This study investigates early warning indicators for process instabilities in anaerobic digestion caused by shock-loadings, focusing on parameters derived from the gas phase, avoiding costly laboratory analyses of the substrate. Six identical lab-scale anaerobic filters were operated with varying organic loading rates to simulate load-flexible operation. Process data, including CH₄, CO₂, H₂, and gas volume, were monitored in 40-minute intervals.Analysis showed that gas quality variability can act as an early warning indicator, with increased variability preceding observable process disturbances.Machine learning classifiers—Support Vector Machine, Random Forest, and Multi-Layer Perceptron—were used to distinguish stable and unstable states based on changes in the gas phase after shock loadings, achieving approximately 80% accuracy.These methods offer a cost-effective and rapid approach for process monitoring, suitable for real-scale biogas plants. However, the dependency on long-term datasets and OLR variability highlights the need for further validation.

Source: Bioresource Technology

DOI: 10.1016/j.biortech.2025.132508

Authors: Leoni Neubauer, Johannes Krümpel, Muhammad Tahir Khan, Andreas Lemmer

Institution: University of Hohenheim

Language: English

Topic: Anaerobic Digestion and Biogas Production

Subfield: Building and Construction

Field: Engineering

Domain: Physical Sciences

SDGs: Affordable and clean energy, Industry, innovation and infrastructure

Open Access status: hybrid

Estimated APC paid: $4,880