Modeling and optimization of photo-fermentation biohydrogen production from co-substrates basing on response surface methodology and artificial neural network integrated genetic algorithm. (April 2023)

• Record Type: Journal Article
• Authors: Zhang, Xueting; Zhang, Quanguo; Li, Yameng; Zhang, Huan
• Is Part Of: Bioresource technology. Volume 374(2023)
• Publication Date: 2023-04
• Subjects: Photo-fermentation biohydrogen production -- Modeling -- Artificial Neural Network -- Optimization -- Co-substrates; Biomass -- Periodicals; Biomass energy -- Periodicals; Bioremediation -- Periodicals; Agricultural wastes -- Periodicals; Factory and trade waste -- Periodicals; Organic wastes -- Periodicals; Bioénergie -- Périodiques; Déchets agricoles -- Périodiques; Déchets industriels -- Périodiques; Déchets organiques -- Périodiques; Déchets (Combustible) -- Périodiques; 662.88
• DOI: 10.1016/j.biortech.2023.128789
• Languages: English
• ISSNs: 0960-8524

Abstract

Graphical abstract: Highlights: Duckweed was first attempted to adjust C/N ratio in photo fermentation system. Co-digestion of duckweed and corn straw to improve hydrogen production efficiency. Optimization of biohydrogen process using CCD-RSM and ANN- GA models. Abstract: The main aim of the present study was to establish a relationship model between bio-hydrogen yield and the key operating parameters affecting photo-fermentation hydrogen production (PFHP) from co-substrates. Central composite design-response surface methodology (CCD-RSM) and artificial neural network-genetic algorithm (ANN-GA) models were used to optimize the hydrogen production performance from co-substrates. Compared to CCD-RSM, the ANN-GA had higher determination coefficient ( R 2 = 0.9785) and lower mean square error ( MSE = 9.87), average percentage deviation ( APD = 2.72) and error (4.3%), indicating the ANN-GA was more suitable, reliable and accurate in predicting biohydrogen yield from co-substrates by PFHP. The highest biohydrogen yield (99.09 mL/g) predicted by the ANN-GA model at substrate concentration 35.62 g/L, temperature 30.94 °C, initial pH 7.49 and inoculation ratio 32.98 %(v/v), which was 4.20 % higher than the CCD-RSM model (95.10 mL/g).