Probabilistic selection and design of concrete using machine learning
This work addresses the problem of reducing material inefficiencies and improving sustainability in concrete construction for engineers and builders, representing an incremental advance by applying a novel method to a known bottleneck in mix design.
The researchers tackled the challenge of designing sustainable concrete mixes by developing a machine learning algorithm that uses intermediate target variables and their noise to predict final properties, enabling the specification of mixes with high carbonation resistance and low environmental impact that meet strength, density, and cost targets, with experimental validation confirming the predictions.
Development of robust concrete mixes with a lower environmental impact is challenging due to natural variability in constituent materials and a multitude of possible combinations of mix proportions. Making reliable property predictions with machine learning can facilitate performance-based specification of concrete, reducing material inefficiencies and improving the sustainability of concrete construction. In this work, we develop a machine learning algorithm that can utilize intermediate target variables and their associated noise to predict the final target variable. We apply the methodology to specify a concrete mix that has high resistance to carbonation, and another concrete mix that has low environmental impact. Both mixes also fulfill targets on the strength, density, and cost. The specified mixes are experimentally validated against their predictions. Our generic methodology enables the exploitation of noise in machine learning, which has a broad range of applications in structural engineering and beyond.