Machine learning-based prediction and optimization of green hydrogen production technologies from water industries for a circular economy

被引:43
作者
Kabir, Mohammad Mahbub [1 ,2 ,3 ]
Roy, Sujit Kumar [4 ]
Alam, Faisal [3 ]
Nam, Sang Yong [5 ]
Im, Kwang Seop [5 ]
Tijing, Leonard [1 ,2 ]
Shon, Ho Kyong [1 ,2 ]
机构
[1] Univ Technol Sydney, Fac Engn & IT, Sch Civil & Environm Engn, ARC Res Hub Nutrients Circular Econ, PO Box 123, Broadway, NSW 2007, Australia
[2] Univ Technol Sydney, Ctr Technol Water & Wastewater, Sch Civil & Environm Engn, Fac Engn & IT, PO Box 123, Broadway, NSW 2007, Australia
[3] Noakhali Sci & Technol Univ, Dept Environm Sci & Disaster Management, Noakhali 3814, Bangladesh
[4] Bangladesh Univ Engn & Technol BUET, Inst Water & Flood Management IWFM, Dhaka, Bangladesh
[5] Gyeongsang Natl Univ, Res Inst Green Energy Convergence Technol, Dept Mat Engn & Convergence Technol, Jinju 52828, South Korea
基金
澳大利亚研究理事会;
关键词
Machine learning; Green hydrogen; Partial dependency analysis; Dark fermentation; Proton exchange membrane; Artificial intelligence (AI); BIOHYDROGEN PRODUCTION; PHOTO-FERMENTATION; REGRESSION; DARK; GENERATION; MODEL; SLUDGE; WASTE;
D O I
10.1016/j.desal.2023.116992
中图分类号
TQ [化学工业];
学科分类号
0817 ;
摘要
Currently, there exists a significant number of green hydrogen production (GHP) technologies based on scaling -up issues (SCUI). Optimal prediction and process optimization could be one of the most substantial SCUI of GHP. Machine learning (ML)-based prediction and optimization of GHP technologies from water industries for a cir-cular economy (CRE) could be a plausible solution for these SCUI. We studied a detailed techno-economic and environmental feasibility study, which recommended proton exchange membrane (PEM) and dark fermentation (DF) as the most promising and environment-friendly technologies for GHP. Thus, the present investigation aims to apply different ML models to predict and optimize the GHP of DF and PEM technologies to solve the SCUI. The results revealed K-nearest neighbor and random forest are the best-fitted models to predict GHP for DF and PEM, correspondingly based on the regression co-efficient (R2), root mean squared error (RMSE) and mean absolute error (MEA). The permutation variable index (PVI) recommended that chemical oxygen demand (COD), buty-rate, temperature, pH and acetate/butyrate ratio are the most influential process parameters in decreasing order for DF, while temperature, cell areas, cell pressure, cell voltage and catalysts loadings are the most effective process parameters for PEM in reducing order. The partial dependency analysis (PDA) demonstrated GHP in-creases with increasing COD values up to 10 mg/L, and the optimal temperature range in the DF process is between 25 and 30 degrees C. On the other hand, cell temperature up to 35 degrees C should be considered optimum for PEM, and 40-70 cm2 cell areas could produce a significant GHP. In summary, the present study underscores the po-tential of machine learning (ML) and artificial intelligence (AI) as promising techniques for optimizing GHP, ultimately addressing scaling-up challenges in large-scale industrial GHP production and ensuring a sustainable hydrogen economy (HE).
引用
收藏
页数:17
相关论文
共 108 条
[1]   Towards the development of new generation of ion exchange membranes for reverse electrodialysis: A review [J].
Abidin, Muhammad Nidzhom Zainol ;
Nasef, Mohamed Mahmoud ;
Veerman, Joost .
DESALINATION, 2022, 537
[2]   A critical review of comparative global historical energy consumption and future demand: The story told so far [J].
Ahmad, Tanveer ;
Zhang, Dongdong .
ENERGY REPORTS, 2020, 6 :1973-1991
[3]   Evolutionary Prediction of Biohydrogen Production by Dark Fermentation [J].
Akhbari, Azam ;
Ibrahim, Shaliza ;
Zinatizadeh, Ali A. ;
Bonakdari, Hossein ;
Ebtehaj, Isa ;
Khozani, Zohre S. ;
Vafaeifard, Mohsen ;
Gharabaghi, Bahram .
CLEAN-SOIL AIR WATER, 2019, 47 (01)
[4]   Desalination and acid-base recovery in a novel design of microbial desalination and chemical recovery cell [J].
Al Hinai, Azhar ;
Jafary, Tahereh ;
Alhimali, Halima ;
Rahman, Sadik ;
Al-Mamun, Abdullah .
DESALINATION, 2022, 525
[5]   Modeling of continuous dark fermentative hydrogen production in an anaerobic up-flow column bioreactor [J].
Alexandropoulou, Maria ;
Antonopoulou, Georgia ;
Lyberatos, Gerasimos .
CHEMOSPHERE, 2022, 293
[6]   Bibliometric studies and impediments to valorization of dry reforming of methane for hydrogen production [J].
Alhassan, M. ;
Jalil, A. A. ;
Nabgan, W. ;
Hamid, M. Y. S. ;
Bahari, M. B. ;
Ikram, M. .
FUEL, 2022, 328
[7]   Overview of hydrogen production technologies from biogas and the applications in fuel cells [J].
Alves, Helton Jose ;
Bley Junior, Cicero ;
Niklevicz, Rafael Rick ;
Frigo, Elisandro Pires ;
Frigo, Michelle Sato ;
Coimbra-Araujo, Carlos Henrique .
INTERNATIONAL JOURNAL OF HYDROGEN ENERGY, 2013, 38 (13) :5215-5225
[8]   Multiphysical Models for Hydrogen Production Using NaOH and Stainless Steel Electrodes in Alkaline Electrolysis Cell [J].
Aquigeh, Ivan Newen ;
Ayissi, Merlin Zacharie ;
Bitondo, Dieudonne .
JOURNAL OF COMBUSTION, 2021, 2021
[9]   Mapping the desalination journal: A systematic bibliometric study over 54 years [J].
Ashraf, Hafsa M. ;
Al-Sobhi, Saad A. ;
El-Naas, Muftah H. .
DESALINATION, 2022, 526
[10]   Modelling aerobic granular sludge reactors through apparent half-saturation coefficients [J].
Baeten, Janis E. ;
van Loosdrecht, Mark C. M. ;
Volcke, Eveline I. P. .
WATER RESEARCH, 2018, 146 :134-145