Significance Statement
The environmental problems, climate change and need to reduce greenhouse gases emission has compelled energy users to sort for alternative renewable and clean energy sources for a sustainable future. Researchers have identified hydrogen as a promising solution since it is a high-quality, clean and renewable energy source. Unfortunately, being a non-primary source, hydrogen can only be generated from other sources of energy such as fossil fuels, natural gas reforming, and coal gasification. However, such hydrogen production methods have failed to meet the requisite low carbon dioxide emission for sustainable development, therefore, researchers have been looking for alternative production techniques.
Presently, generating hydrogen from biomass has taken significant interest amongst researchers due to its renewability and zero carbon emission. To enhance hydrogen production process in large-scale experiments, the effects of a various operating condition like sorbent to biomass ratio, pressure, temperatures, and steam to biomass ratio have been investigated. Moreover, most of these methods have not been fully explored due to their expensive nature, time-consuming and less effective data mining techniques. The use of mathematical modeling techniques comprising computer-based models has henceforth been employed in the investigation of hydrogen production from biomass gasification. Despite the reported improvements, computer-based models are time-consuming, involve complicated algorithms and complex differential equations which may require assumption hence leading to inaccurate findings.
Recently, Dr. Jaroslaw Krzywanski at Jan Dlugosz University in Poland in collaboration with Chinese scientists at Zhejiang University proposed artificial intelligence (AI) methods that included artificial neural networks (ANN) and genetic algorithms (GA) as a simpler alternative method for data acquisition and analysis for hydrogen production via biomass steam gasification with CaO enhancement. They estimated hydrogen concentration in the syngas produced from biomass in circulating fluidized bed (CFB) and bubbling fluidized bed (FB). Also, they investigated the conditions and influencing parameters on hydrogen gas production. Eventually, they compared the experimental results and the simulation results. The work is published in the journal, Energy Conversion and Management.
The authors observed that desirably adjusting reaction temperature, CaO to carbon mole ratio and H2O to carbon mole ratio can result in a high hydrogen concentration in the syngas produced. Also, they noted that CFB produced high hydrogen concentration as compared to FB gasifiers. Furthermore, the similarity in the simulation and experimental results confirmed the efficiency of the proposed AI model. For instance, a maximum relative error less than ±8 was obtained between the calculated and measured data.
The developed non-iterative model enabled effective optimization of the hydrogen gas production process where the process parameters are generated from a given set of input data. In addition to the ability of the ANN to reproduce the whole process, the proposed AI approaches, therefore, overcomes the various limitation of the experimental procedures and programmed computing approaches. Consequently, owing to the simplicity of the model for handling data and experimental procedures, it can as well be used in hydrogen production for predicting its concentration in syngas from biomass via CaO sorption. This is possible for both CFB and FB gasifiers. The study will therefore advance hydrogen gas production for the realization of a sustainable development.
Journal Reference
Krzywanski, J., Fan, H., Feng, Y., Shaikh, A., Fang, M., & Wang, Q. (2018). Genetic algorithms and neural networks in optimization of sorbent enhanced H 2 production in FB and CFB gasifiers. Energy Conversion and Management, 171, 1651-1661.
Go To Energy Conversion and Management
The post Bio-Inspired Modeling for H2 Production appeared first on Renewable Energy Global Innovations.
Read more research excellence studies on: Renewable Energy Global Innovations (https://ift.tt/21cCPA4)