Partial Inverse Design of High-Performance Concrete Using Cooperative Neural Networks for Constraint-Aware Mix Generation

TL;DR

This paper introduces a cooperative neural network framework for partial inverse design of high-performance concrete, enabling efficient and accurate generation of mix designs under practical constraints, surpassing baseline models in performance.

Contribution

The study presents a novel cooperative neural network approach that integrates imputation and surrogate modeling for constraint-aware inverse concrete mix design, improving accuracy and efficiency.

Findings

Achieves R-squared of 0.87 to 0.92 in predictions.

Reduces mean squared error by 50-70%.

Generates valid mix designs in a single forward pass.

Abstract

High-performance concrete requires complex mix design decisions involving interdependent variables and practical constraints. While data-driven methods have improved predictive modeling for forward design in concrete engineering, inverse design remains limited, especially when some variables are fixed and only the remaining ones must be inferred. This study proposes a cooperative neural network framework for the partial inverse design of high-performance concrete. The framework integrates an imputation model with a surrogate strength predictor and learns through cooperative training. Once trained, it generates valid and performance-consistent mix designs in a single forward pass without retraining for different constraint scenarios. Compared with baseline models, including autoencoder models and Bayesian inference with Gaussian process surrogates, the proposed method achieves R-squared values of 0.87 to 0.92 and substantially reduces mean squared error by approximately 50% and 70%, respectively. The results show that the framework provides an accurate and computationally efficient foundation for constraint-aware, data-driven mix proportioning.