TY - JOUR
T1 - Machine Learning Assisted Prediction of Solar to Liquid Fuel Production
T2 - A Case Study
AU - Shahzad, Muhammad Wakil
AU - Nguyen, Viet Hung
AU - Xu, Ben Bin
AU - Tariq, Rasikh
AU - Imran, Muhammad
AU - Muhammad Ashraf, Waqar
AU - Ng, Kim Choon
AU - Ahmad Jamil, Muhammad
AU - Ijaz, Amna
AU - Sheikh, Nadeem Ahmed
N1 - Funding information: The authors would like to thank Northumbria University and the British Council grant for the SAFECONOMY - Solar to Alternative Fuel Economy Research Consortia and Capacity Building Platform project. The authors also would like to thank RAEng / Leverhulme Trust Research Fellowships Tranche 19 for the FAM project (LTRF2223-19-103) awarded to Dr. Shahzad Northumbria University UK.
PY - 2024/4/1
Y1 - 2024/4/1
N2 - In this era of heightened environmental awareness, the global community faces the critical challenge of climate change. Renewable energy (RE) emerges as a vital contender to mitigate global warming and meet increasing energy needs. Nonetheless, the fluctuating nature of renewable energy sources underscores the necessity for efficient conversion and storage strategies. This pioneering research focuses on the transformation of solar energy (SE) into liquid fuels, with a specific emphasis on formic acid (FA) as a case study, done in Binh Thuan, Vietnam. The paper unveils a technology designed to convert solar energy into formic acid, ensuring its stability and storage at ambient conditions. It involves detailed simulations to quantify the daily and monthly electricity output from photovoltaic (PV) systems and the corresponding mass of formic acid producible through solar energy. The simulation of a dual-axis solar tracking system for the PV panels, intended to maximize solar energy capture, is one of the project's illustrations. The elevation and azimuth angles, which are two essential tracking system parameters, are extensively studied in the present research. The project makes use of machine learning algorithms in the field of predictive modeling, specifically Artificial Neural Networks (ANN) and Support Vector Machines (SVM). These tools play a crucial role in modeling PV power output and formic acid production while accounting for a variety of influencing factors. A comparative study shows that SVM outperforms ANN in accurately predicting the production of FA and PV power generation, both of which are the major goals. This model is a predictive tool that can be used to forecast these goals based on certain causal variables. Overall, it is observed that the maximum power produced with 2-axis solar tracker was achieved in February as 2355 kW resulting in the highest formic acid production of 2.25 x 106 grams. The study's broad ramifications demonstrate solar liquid fuel technology's potential as a long-term fix in the field of renewable energy. In addition to advancing the field of renewable energy storage, the study represents a major step toward tackling the global challenge of climate change.
AB - In this era of heightened environmental awareness, the global community faces the critical challenge of climate change. Renewable energy (RE) emerges as a vital contender to mitigate global warming and meet increasing energy needs. Nonetheless, the fluctuating nature of renewable energy sources underscores the necessity for efficient conversion and storage strategies. This pioneering research focuses on the transformation of solar energy (SE) into liquid fuels, with a specific emphasis on formic acid (FA) as a case study, done in Binh Thuan, Vietnam. The paper unveils a technology designed to convert solar energy into formic acid, ensuring its stability and storage at ambient conditions. It involves detailed simulations to quantify the daily and monthly electricity output from photovoltaic (PV) systems and the corresponding mass of formic acid producible through solar energy. The simulation of a dual-axis solar tracking system for the PV panels, intended to maximize solar energy capture, is one of the project's illustrations. The elevation and azimuth angles, which are two essential tracking system parameters, are extensively studied in the present research. The project makes use of machine learning algorithms in the field of predictive modeling, specifically Artificial Neural Networks (ANN) and Support Vector Machines (SVM). These tools play a crucial role in modeling PV power output and formic acid production while accounting for a variety of influencing factors. A comparative study shows that SVM outperforms ANN in accurately predicting the production of FA and PV power generation, both of which are the major goals. This model is a predictive tool that can be used to forecast these goals based on certain causal variables. Overall, it is observed that the maximum power produced with 2-axis solar tracker was achieved in February as 2355 kW resulting in the highest formic acid production of 2.25 x 106 grams. The study's broad ramifications demonstrate solar liquid fuel technology's potential as a long-term fix in the field of renewable energy. In addition to advancing the field of renewable energy storage, the study represents a major step toward tackling the global challenge of climate change.
KW - Formic acid
KW - Liquid fuel
KW - Solar energy
KW - Two-axis solar tracking system
UR - http://www.scopus.com/inward/record.url?scp=85186382188&partnerID=8YFLogxK
U2 - 10.1016/j.psep.2024.02.060
DO - 10.1016/j.psep.2024.02.060
M3 - Article
SN - 0957-5820
VL - 184
SP - 1119
EP - 1130
JO - Process Safety and Environmental Protection
JF - Process Safety and Environmental Protection
ER -
