Mixture optimization for environmental, economical and mechanical objectives in silica fume concrete: A novel frame-work based on machine learning and a new meta-heuristic algorithm

Abstract

Abstract Partial replacement of cement by silica fume in concrete provides advantages such as mitigation of the impact on the environment of carbon dioxide emitted during cement production, recycling of industrial by-products and improvement of concrete strength and durability. The optimization of the mixture of silica fume concrete (SFC) requires trade-off among multiple objectives (strength, cost and embodied CO2) and consideration of a large number of variables under highly nonlinear constraints. Obtaining the Pareto front of this multi-objective optimization (MOO) problem is computationally expensive. To address this issue, the present study develops a MOO model using machine learning (ML) techniques and a new meta-heuristic algorithm. Firstly, the relationships between components and SFC properties are modelled on a dataset using a back propagation neural network (BPNN) model. Then an individual-intelligence-based multi-objective beetle antennae search algorithm (MOBAS) is developed to search for optimal SFC mixtures that maximize UCS, and minimize cost and embodied CO2 under defined constraints. Results indicate that the proposed MOBAS is more computationally efficient with satisfactory accuracy in comparison with algorithms based on swarm intelligence. The MOO model achieves reliable predictions for UCS with a very high correlation coefficient (0.9663) on the test set. The Pareto front of optimal SFC mixture proportions of the MOO problem is successfully obtained using the proposed model. The proposed frame-work improves the efficiency in SFC mixture optimization and can facilitate appropriate decision making before construction.