IIT-Madras Researchers Use AI to Study Biomass Fuel Production

Researchers at the Indian Institute of Technology, Madras (IIT-M) announced that artificial intelligence tools were used to study the production of fuel from biomass. According to IIT Madras, computer simulations and modelling studies can provide faster insights that can be used to build the processes and plants for biomass processing.

"Gaining such understanding through hands-on experiments will be time-consuming and expensive, and as such, computer simulations and modelling studies can provide quick insights into developing biomass conversion processes," IIT-M said.

According to a press release, the study was led by assistant professor Dr. Himanshu Goyal and professor Dr. Niket S Kaisare. "With growing environmental concerns associated with petroleum-derived fuels, biomass is the practical solution not in the traditional sense of directly burning wood, cow dung, and coal, but as a source of energy-dense fuel," he said.

Fuel Extraction from Biomass:

Researchers from all over the world were working to develop methods for extracting fuel from biomass such as wood, grass, and waste organic matter.

"There is an urgent need to train the next generation of engineers in high-performance computing and machine-learning skills so that they can address some of the most difficult challenges that we face, such as developing zero-emission technologies to combat climate change," Goyal said.

While models were used all over the world to understand the conversion of biomass into fuels and chemicals, most of them take a long time to become operational. Artificial intelligence tools such as machine-earning can hasten the modelling processes.

According to the release, the IIT-M team used the machine-learning method known as recurrent neural networks to study the reactions that occur during the conversion of biomass into energy-dense syngas (gasification of biomass).

"The novelty of our machine-learning approach is that it can predict the composition of the bio-fuel produced based on the time the biomass spends in the reactor," Kaisare explained. "We used a statistical reactor to generate accurate data, allowing the model to be applied across a wide range of operating conditions," he added.