In a significant leap for the carbon fiber composite industry, researchers have developed a groundbreaking method for predicting energy intensity during the manufacturing process. This innovative approach, centered around a Limit Jordan Deep Recurrent Neural Network (LJDRNN), promises not only to enhance operational efficiency but also to align with sustainability goals that are increasingly vital in today’s construction sector.
Carbon fibers, known for their strength and lightweight properties, are primarily produced from polyacrylonitrile precursors. However, the manufacturing process is notoriously energy-intensive and costly, often hindering the scalability and economic viability of carbon fiber applications. The new research, led by Rangaswamy Nikhil from the Department of Mechatronics Engineering at REVA University in Bengaluru, aims to address this issue head-on. “By accurately predicting energy intensity, we can help manufacturers optimize their processes, reduce costs, and ultimately make carbon fiber composites more accessible,” Nikhil stated.
The study introduces a sophisticated methodology that first identifies material values and processes relevant to energy consumption. Following this, it employs Linear Interpolated Honey Badger Optimization (LIHBO) to extract and select optimal components from the input data. The LJDRNN then predicts energy intensity with an impressive accuracy of 98.32%, significantly outperforming traditional methods such as the Jordan Recurrent Neural Network (JRNN) and Artificial Neural Networks (ANN).
The implications of this research extend far beyond theoretical advancements. For the construction industry, which increasingly relies on advanced materials for everything from structural components to lightweight designs, the ability to predict energy intensity could lead to substantial cost savings. “This tool offers a robust way to manage energy consumption effectively, which is crucial as we strive for greener construction practices,” Nikhil added.
By enabling precise energy intensity forecasting, the proposed method not only supports carbon fiber producers in optimizing their manufacturing processes but also enhances their competitiveness in a market that is increasingly driven by sustainability and efficiency. As construction projects seek to reduce their carbon footprints, innovations like this one could play a pivotal role in shaping the future of materials used in the industry.
The findings of this research have been published in ‘Materials Research Express’, a journal dedicated to advancing knowledge in the field of materials science. As the construction sector continues to evolve, the integration of such advanced predictive technologies could redefine how materials are manufactured and utilized, heralding a new era of efficiency and sustainability in construction.
For more information, you can visit the Department of Mechatronics Engineering, REVA University.
