Partial Inverse Design of High-Performance Concrete Using Cooperative Neural Networks for Constraint-Aware Mix Generation
Preprint
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.Keywords
All Related Versions
This publication has 29 references indexed in Scilit:
- Transfer learning for intelligent design of lightweight Strain-Hardening Ultra-High-Performance Concrete (SH-UHPC)Automation in Construction, 2025
- Generative AI for performance-based design of engineered cementitious compositeComposites Part B: Engineering, 2023
- Implications of data-driven product design: From information age towards intelligence ageAdvanced Engineering Informatics, 2022
- Data-driven generative design for mass customization: A case studyAdvanced Engineering Informatics, 2022
- Parametric sensitivity analysis and modelling of mechanical properties of normal- and high-strength recycled aggregate concrete using grey theory, multiple nonlinear regression and artificial neural networksConstruction and Building Materials, 2019
- Multiple mechanical properties prediction of hydraulic concrete in the form of combined damming by experimental data miningConstruction and Building Materials, 2019
- Comparative LCA of concrete with natural and recycled coarse aggregate in the New York City areaThe International Journal of Life Cycle Assessment, 2017
- High-performance Concrete Compressive Strength Prediction using Time-Weighted Evolutionary Fuzzy Support Vector Machines Inference ModelAutomation in Construction, 2012
- Concrete compressive strength analysis using a combined classification and regression techniqueAutomation in Construction, 2012
- Fuzzy polynomial neural networks for approximation of the compressive strength of concreteApplied Soft Computing, 2008