In a significant stride towards sustainable construction practices, researchers have developed a novel approach to predict the strength of marine coral sand–clay mixtures (MCCM), offering promising opportunities for the maritime and civil engineering sectors. This innovative method, detailed in a recent study published in the journal ‘Buildings’ (translated to English), leverages machine learning to enhance the predictive accuracy of MCCM’s mechanical properties, crucial for ensuring the safety and stability of structures built with these eco-friendly materials.
At the helm of this research is Bowen Yang, affiliated with Shanxi Ning Guli New Materials Joint Stock Company Limited in Jinzhong, China. Yang and his team conducted a series of triaxial shear tests under varied conditions, including asperity spacing, asperity height, reinforcement layers, confining pressure, and axial strain. These tests generated a comprehensive dataset that served as the foundation for developing several predictive models.
Among the models created, the hybrid Logical Development Algorithm-Support Vector Machine (LDA-SVM) model stood out, achieving a remarkable test RMSE of 1.67245 and a correlation coefficient (R) of 0.996. This model’s superior performance highlights its potential for practical applications in the maritime industry.
“The LDA-SVM model exhibited the best performance, demonstrating superior prediction accuracy and strong generalization ability,” said Yang. This model’s success is a testament to the power of machine learning in enhancing our understanding of complex materials like MCCM.
The study also identified the most influential factors affecting MCCM strength, including asperity spacing, asperity height, and confining pressure. This insight is invaluable for practitioners aiming to optimize the design and safety evaluation of structures using MCCM.
One of the most practical outcomes of this research is the derivation of an explicit empirical equation from the LDA-SVM model. This equation allows engineers to estimate the strength of MCCM without relying on complex machine learning tools, making the technology more accessible and user-friendly.
For the maritime sector, the implications are substantial. MCCM offers a sustainable alternative to traditional fill materials, reducing the environmental impact of construction projects. The ability to accurately predict the strength of these mixtures ensures structural integrity, making them a viable option for various applications, from coastal defenses to offshore structures.
Moreover, the commercial opportunities are vast. As the demand for green construction materials grows, companies that adopt and refine these predictive models can gain a competitive edge. The technology developed by Yang and his team not only supports sustainable practices but also opens new avenues for innovation and growth in the maritime industry.
In summary, this research represents a significant advancement in the field of sustainable construction. By harnessing the power of machine learning, Bowen Yang and his team have provided a robust tool for predicting the strength of MCCM, paving the way for safer, more sustainable, and cost-effective construction practices in the maritime sector.