Comparative Assessment of Concrete Compressive Strength Prediction at Industry Scale Using Embedding-based Neural Networks, Transformers, and Traditional Machine Learning Approaches

2026-01-14

AI Summary

Concrete compressive strength is challenging to predict accurately due to material heterogeneity, mix proportions, and environmental factors, hindering the automation of construction quality control. This study leverages approximately 70,000 industrial-scale strength test records to systematically evaluate, for the first time in a large-scale engineering context, the predictive performance of linear regression, decision trees, random forests, Transformers, and embedded neural networks in estimating 28-day compressive strength using key variables such as water-to-binder ratio, binder content, and slump. The results demonstrate that the embedded neural network achieves the highest accuracy, with a mean prediction error of approximately 2.5%—comparable to the typical variability observed in laboratory testing—thereby confirming its superiority and practical utility for predicting engineering material performance.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Data Mining & Knowledge Management: Data Compression
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Concrete is the most widely used construction material worldwide; however, reliable prediction of compressive strength remains challenging due to material heterogeneity, variable mix proportions, and sensitivity to field and environmental conditions. Recent advances in artificial intelligence enable data-driven modeling frameworks capable of supporting automated decision-making in construction quality control. This study leverages an industry-scale dataset consisting of approximately 70,000 compressive strength test records to evaluate and compare multiple predictive approaches, including linear regression, decision trees, random forests, transformer-based neural networks, and embedding-based neural networks. The models incorporate key mixture design and placement variables such as water cement ratio, cementitious material content, slump, air content, temperature, and placement conditions. Results indicate that the embedding-based neural network consistently outperforms traditional machine learning and transformer-based models, achieving a mean 28-day prediction error of approximately 2.5%. This level of accuracy is comparable to routine laboratory testing variability, demonstrating the potential of embedding-based learning frameworks to enable automated, data-driven quality control and decision support in large-scale construction operations.

Problem

• concrete compressive strength
• prediction
• material heterogeneity
• mix proportions
• environmental conditions

Innovation

• embedding-based neural networks
• concrete compressive strength prediction
• industry-scale dataset
• automated quality control
• data-driven construction