Abstract:
Renewable energy technologies can be beneficial for the economic development of any
country on the planet. Also, with the present situation in the energy sector, the high cost
of fuel, the use of renewable energy resources has seemed to have gained importance.
The energy resources that pertain to solar, biomass, and wind energies are clean energy
friendly to the environment. In the modern world, fossil fuels meet the requirements of
the transportation sector in large volume and bring several negative impacts viz., air
pollution, noise, and global warming. Besides, the fast decline of below-ground
petroleum resources that arise with the rapid consumption of fossil fuels is accompanied
by another grave problem for the transportation sector. Usually, the gasifier's
temperature is greater than 1000°C. Before coal is put into the gasifier, it must go
through a process called pyrolysis, a sequence of intricate physical and chemical
reactions that occur without oxygen or air and gradually increase in temperature from
150 to 700 degrees Celsius. High molecular weight charcoal and volatile substances,
such as CO, H2, H2O, CO2, and CH4, are the process byproducts. In this research work,
machine learning algorithms such as Artificial Neural Network (ANN), Random Forest
(RF), GBR, and XGB will be used to increase the efficiency of biomass gasification
using AI-based machine learning algorithms. A dataset of biomass converting into
syngas and other useful products is obtained to estimate the output of syngas, H2, CH4,
and composition of different gases based on input parameters, namely carbon,
temperature, sulfur, oxygen, nitrogen and ash, etc. The algorithms have an advantage
in their capacity to train a model using a dataset consisting of numerical values and
achieve an optimal fit point by incorporating efficiency parameters. Root Mean Square
Error (RMSE) is a frequently used metric to estimate the precision of predictions. The
RMSE values will be computed for each scenario. The approach will be experimented
with under temperature variations, and other relevant constraints.
