https://doi.org/10.17113/ftb.63.02.25.8792

Article in press

Predictive Modelling of H₂S Removal from Biogas Generated from Palm Oil Mill Effluent (POME) Using Biological Scrubber in an Industrial Biogas Plant: Integration of Artificial Neural Network (ANN) and Process Simulation

Joanna Lisa Clifford¹, Yi Jing Chan^1*, Mohd Amran Bin Mohd Yusof¹, Timm Joyce Tiong¹, Siew Shee Lim¹, Chai Siah Lee² and Woei-Yenn Tong³

¹Department of Chemical and Environmental Engineering, University of Nottingham Malaysia, Broga Road, 43500, Semenyih, Selangor Darul Ehsan, Malaysia

²Advanced Materials Research Group, Faculty of Engineering, University of Nottingham, NG7 2RD, UK

³Universiti Kuala Lumpur, Institute of Medical Science Technology, A1-1, Jalan TKS 1, Taman Kajang Sentral, 43000 Kajang, Selangor, Malaysia

Copyright © 2024 This is a Diamond Open Access article published under CC-BY licence. Copyright remains with the authors, who grant third parties the unrestricted right to use, copy, distribute and reproduce the article as long as the original author(s) and source are acknowledged.

Article history:

Received: 24 July 2024

Accepted: 31 March 2025

Keywords:

palm oil mill effluent; biogas; simulation; Artificial Neural Network; bioscrubber

Summary:

Research background. Biogas production from Palm Oil Mill Effluent (POME) is inherently unstable due to variations in feedstock composition and operating conditions. These fluctuations can result in inconsistent biogas quality, variable methane content, and fluctuating levels of hydrogen sulphide (H₂S), posing significant challenges for bioscrubbers in removing H₂S to meet the quality standards for gas engines used in electricity generation. This research aims to address these challenges by integrating simulation models using a computer programme and Artificial Neural Network (ANN) to predict the performance of a bioscrubber at a POME treatment plant in Johor, Malaysia.

Experimental approach. Initially, the process flowsheet model was simulated using a computer programme. The prediction of H₂S removal was then conducted using a machine learning algorithm, specifically ANN, based on two years of historical data obtained from the biogas plant. Furthermore, a detailed techno-economic analysis was conducted to determine the economic feasibility of the process.

Results and conclusions. Simulation results revealed a biogas yield of 26.12 Nm³ of biogas per m³ of POME, aligning with industry data with less than 1 % deviation. The ANN model achieved a high coefficient of determination (R²) of 0.9 and a low mean squared error (MSE), with the bioscrubber reaching approximately 96 % H2S removal efficiency. The techno-economic analysis indicated that the process is feasible, with a net present value of $131,000 and a payback period of 7 years.

Novelty and scientific contribution. The integration of ANN and the computer programme provides a robust framework for predicting bioscrubber performance and ensuring stable bioscrubber operation due to their complementary strengths. ANN accurately predicts H2S removal using daily recorded data, while the computer programme estimates parameters not monitored daily, such as chemical oxygen demand (COD), biological oxygen demand (BOD), and total suspended solids (TSS). This research provides valuable insights into sustainable biogas production practices, offering opportunities to improve energy efficiency and environmental sustainability in the palm oil industry.