In the quest for sustainable construction materials, a team of researchers led by Athira M. Santhosh from the Department of Civil Engineering at Amrita School of Engineering, Coimbatore, has made significant strides in understanding and predicting the behavior of self-compacting geopolymer paste. Their work, published in the journal *Results in Materials* (which translates to *Materials Research Results*), offers promising insights for the energy sector and beyond.
Geopolymers, inorganic aluminosilicate polymers that gain strength through polymerization, are emerging as a viable alternative to traditional cement. “Cement is neither sustainable nor economical,” Santhosh explains. “The cement manufacturing industry contributes significantly to anthropogenic carbon dioxide emissions, increasing the carbon footprint. Geopolymers offer a more sustainable and cost-effective solution.”
The study delves into the influence of various ingredients and experimental parameters on the rheological and mechanical properties of self-compacting geopolymer paste. One of the key findings is that testing temperature plays a crucial role in the rheology of geopolymer paste. “As the duration after mixing increases, the mix loses its plasticity and starts to set, becoming more viscous,” Santhosh notes.
The research also highlights the adverse effects of superplasticizer (SP) on mechanical properties. To model and predict these properties, the team employed an autoencoder-based deep learning algorithm. This innovative approach involved training, validating, and testing the algorithm with a dataset of 330 geopolymer mixes with different SP dosages. The results showed a good correlation between predicted and measured data, demonstrating the potential of deep learning techniques in construction materials research.
The implications of this research are far-reaching, particularly for the energy sector. As the world shifts towards sustainable energy solutions, the demand for eco-friendly construction materials is on the rise. Geopolymers, with their lower carbon footprint and cost-effectiveness, could revolutionize the way we build infrastructure.
Moreover, the use of deep learning algorithms to predict material properties opens up new avenues for research and development. “This study paves the way for more sophisticated models that can accurately predict the behavior of construction materials under various conditions,” Santhosh says.
As the construction industry continues to evolve, the integration of sustainable materials and advanced technologies will be crucial. This research not only advances our understanding of geopolymers but also sets the stage for future developments in the field. With the growing emphasis on sustainability and innovation, the findings of this study could shape the future of construction, offering a glimpse into a more eco-friendly and efficient industry.