Researchers at the Indian Institute of Technology Madras (IIT-M) are using artificial intelligence (AI) tools to study the process involved in converting biomass into gaseous fuel. Computer simulations and modeling studies can provide faster insights for developing biomass conversion processes, since gaining such understanding through hands-on experiments would take time, IIT-M said.
With petroleum-derived fuels raising environmental concerns, researchers say biomass is a practical solution, not in the conventional sense of directly burning wood, but as a high-energy-density fuel source. Researchers around the world are looking for methods to extract fuel from biomass like wood, grass and even organic waste.
“This biomass-derived fuel is particularly relevant for India, as the current availability of biomass in India is estimated at around 750 million metric tons per year and the extraction of their fuel can immensely help the country to achieve the ‘fuel self-sufficiency’, the IIT-M mentioned.
Also Read: Global Fuel and Commodity Prices May Fall Ahead: NITI Aayog VP
The results of the research led by Dr. Himanshu Goyal, Assistant Professor, Department of Chemical Engineering, IIT-M and Dr. Niket S Kaisare, Professor, Department of Chemical Engineering, IIT-M, were recently published in the peer-reviewed journal Reading of the Royal Society of Chemistry Chemistry and Reaction Engineering.
“Understanding the complex mechanisms involved in converting raw biomass into fuel is important for designing the processes and optimizing reactors for this purpose,” said Dr Goyal, adding that there is an urgent need to train the next generation of engineers. on high performance. computer and machine learning skills.
These skills will help them tackle some of the biggest challenges facing the world, such as developing zero-emission technologies to combat climate change.
While models are being developed around the world to understand the conversion of biomass into fuels and chemicals, most models take a long time to become operational, IIT-M said, adding that tools for AI such as machine learning (ML) can speed up the modeling process.
The research team from IIT Madras used an ML method called Recurrent Neural Networks (RNN) to study the reactions that occur during the conversion of lignocellulosic biomass into high energy density syngas (biomass gasification ).
“The novelty of our ML approach is that it is able to predict the composition of the biofuel produced as a function of the time spent by the biomass in the reactor. We used a statistical reactor for the generation of accurate data, which allows the model to be applied over a wide range of operating conditions,” said Dr Kaisare.
The team believes that rapid advances in computational methods must be incorporated into basic engineering for faster development and growth of high-tech solutions. Such developments cannot be limited by specialties and departments.
Watch the latest DH videos here: