AI-guided auto-discovery of low-carbon cost-effective ultra-high performance concrete (UHPC)

This paper presents an AI-guided approach to automatically discover low-carbon cost-effective ultra-high per-formance concrete (UHPC). The presented approach automates data augmentation, machine learning model generation, and mixture selection by integrating advanced techniques of generative modeling, automated ma-chine learning, and many-objective optimization. New data are synthesized by generative modeling and semi -supervised learning to enlarge datasets for training machine learning models that are automatically generated to predict the compressive strength, flexural strength, mini-slump spread, and porosity of UHPC. The proposed approach was used to explore new UHPC mixtures in two design scenarios with different objectives. The first scenario maximizes the compressive and flexural strengths and minimizes porosity while retaining self -consolidation. The second scenario minimizes the life-cycle carbon footprint, embodied energy, and material cost, besides the objectives of the first scenario. The life-cycle carbon footprint, embodied energy, and material cost of the UHPC in the second scenario are respectively reduced by 73%, 71%, and 80%, compared with the UHPC in the first scenario. This research advances the capability of developing cementitious composites using AI -guided approaches.

Automated summary

This paper presents an AI-guided approach to automatically discover low-carbon cost-effective ultra-high performance concrete (UHPC). The approach integrates advanced techniques of generative modeling, automated machine learning, and many-objective optimization to automate data augmentation, machine learning model generation, and mixture selection. The proposed approach synthesizes new data for training machine learning models using generative modeling and semi-supervised learning, and predicts the properties of UHPC such as compressive strength, flexural strength, mini-slump spread, and porosity. The approach was applied in two design scenarios, resulting in significant reductions in life-cycle carbon footprint, embodied energy, and material cost compared to traditional UHPC mixtures.