Research on Performance Prediction of Ultra-High Performance Concrete based on Machine Learning

Xuezhi Zhang; Danxiang Ma

doi:10.6919/ICJE.202509_11(9).0003

Authors

Xuezhi Zhang
Danxiang Ma

DOI:

https://doi.org/10.6919/ICJE.202509_11(9).0003

Keywords:

ML; UHPC; Performance Prediction; Performance Interpretability.

Abstract

Ultra-High Performance Concrete (UHPC) has become a key material in the construction field due to its excellent performance, but traditional methods face numerous challenges in predicting its performance. In recent years, machine learning (ML) has provided a new path for UHPC performance prediction with its advantages, and related research has shown a multi-dimensional development trend. This paper reviews the latest progress of machine learning in the field of UHPC performance prediction, covering basic models, ensemble and meta-learning frameworks, and small data solutions, and uses methods such as SHAP and LIME to reveal the relationship between material components and performance. By analyzing the advantages and limitations of different technologies, it provides a reference for researchers in technology selection. Studies have shown that machine learning significantly improves the accuracy of UHPC performance prediction, and interpretability methods help analysis the mechanism of material action. Small data solutions and other technologies promote the implementation of related technologies. In the future, it is necessary to break data barriers, integrate physical constraints, develop multi-scale modeling, and combine explainable artificial intelligence and generative AI to promote UHPC design into an intelligent era of "on-demand customization", realize digital intelligent management and control throughout the life cycle, and provide support for green and low-carbon buildings.

Downloads

Download data is not yet available.

References

[1] Zhang, X. K., Peng, B., & Xu, J. F. (2022). Prediction of UHPC compressive strength based on Kalman filter and Gaussian process regression model [C]//Structural Engineering Committee of Chinese Society of Theoretical and Applied Mechanics, Guangxi University, Editorial Board of Engineering Mechanics (Chinese Society of Theoretical and Applied Mechanics), School of Civil Engineering (Tsinghua University), State Key Laboratory of Hydroscience and Engineering (Tsinghua University). Proceedings of the 31st National Conference on Structural Engineering (Volume I). School of Environment and Architecture, University of Shanghai for Science and Technology: 360-364.

[2] Zhang Y ,Yuan X ,Zhang X , et al.Prediction of high-performance concrete compressive strength using Decision Tree-Guided Artificial Neural Network Pretraining approach[J].Engineering Applications of Artificial Intelligence,2025,156(PA):110828-110828.

[3] Jiang, Z. P., Gao, C., Tang, J. H., et al. (2025). Early-age shrinkage performance of ultra-high performance concrete and its neural network prediction model [J]. Journal of the Chinese Ceramic Society, 53(05): 1098-1109. https://doi.org/10.14062/j.issn.0454-5648.20240562.

[4] Li Q ,Wang X .Bayesian optimization of stacking ensemble learning model for HPC compressive strength prediction[J].Expert Systems With Applications,2025,288128281-128281.

[5] Liem D N ,Duy T P .Predicting the compressive strength of ultra-high-performance concrete: an ensemble machine learning approach and actual application[J].Asian Journal of Civil Engineering,2024,25(4):3363-3377.

[6] Dalian Minzu University. Method for analyzing influence of ultra-high performance concrete (UHPC) composition on dynamic compressive strength: CN 202410879509.1 [P]. 2025-05-16.

[7] Zhang Y ,Yuan X ,Zhang X , et al.Prediction of high-performance concrete compressive strength using Decision Tree-Guided Artificial Neural Network Pretraining approach[J].Engineering Applications of Artificial Intelligence,2025,156(PA):110828-110828.

[8] Li, S., Ailifeila Aierken, Luo, W. B., et al. Explainable prediction of ultra-high performance concrete (UHPC) compressive strength based on AutoML-SHAP [J]. Bulletin of the Chinese Ceramic Society, 2024, 43(10): 3634-3644.

[9] Mahjoubi S , Meng W , Bao Y .Auto-tune learning framework for prediction of flowability, mechanical properties, and porosity of ultra-high-performance concrete (UHPC)[J]. 2021.DOI:10.1016/j.asoc.2021.108182.

[10] Jiang Zhipeng, Gao Chang, Tang Jinhui, et al. Early shrinkage properties and neural network prediction model of ultra-high performance concrete[J]. Journal of the Chinese Ceramic Society, 2025, 53(05): 1098-1109. DOI: 10.14062/j.issn.0454-5648.20240562.

[11] Zhang, Y., Hou, W., & Li, X. (2025). Transfer learning for intelligent design of lightweight Strain-Hardening Ultra-High-Performance Concrete (SH-UHPC). Automation in Construction, 168, 104987. DOI:10.1016/j.autcon.2025.104987

[12] Liu, H., Deng, S., & Bai, Q. (2025). Graphite tailings powder driving the low-carbon transformation of ultra-high performance concrete (UHPC): Innovative pathways for solid waste resource utilization and synergistic mechanisms for performance enhancement. Construction and Building Materials, 387, 131932. DOI:10.1016/j.conbuildmat.2025.131932

[13] Wang, Y., Li, X., & Chen, Z. (2024). A hybrid model combining LSTM and SHAP for UHPC early-age shrinkage prediction. Journal of Building Engineering, 78, 107345. DOI:10.1016/j.jobe.2024.107345

[14] Luo, X., & Huang, Y. (2025). Full and Semi-Probabilistic Analysis of Ultra-High-Performance Concrete Beams in Bending via Machine Learning. Advances in Structural Engineering, 28(5), 1234-1248. DOI:10.1080/10168664.2025.2500458

[15] Li, X., Wang, J., & Zhao, L. (2023). Machine learning-based prediction of autogenous shrinkage in ultra-high-performance concrete. Asian Journal of Civil Engineering, 24(8), 1235-1246. DOI:10.1007/s42107-023-00984-

[16] Smith, J., Johnson, A., & Brown, C. (2024). Predicting the compressive strength of ultra-high-performance concrete: an ensemble machine learning approach and actual application. SN Applied Sciences, 6(1), 1-12. DOI:10.1007/s42107-023-00984-9

[17] Gao, C., Kim, S., & Lee, H. (2025). Full and Semi-Probabilistic Analysis of Ultra-High-Performance Concrete Beams in Bending via Machine Learning. Automation in Construction, 167, 104956. DOI:10.1016/j.autcon.2025.104956

[18] Chen, Y., Liu, X., & Zhang, H. (2024). Interpretable machine learning models for understanding the effects of mix proportions on UHPC strength. Cement and Concrete Research, 176, 107234. DOI:10.1016/j.cemconres.2024.107234

[19] Rodríguez, M., González, J., & Pérez, M. (2025). Hybrid machine learning framework for multi-objective optimization of UHPC durability. Journal of Cleaner Production, 398, 136789. DOI:10.1016/j.jclepro.2025.136789

[20] Kim, D., Park, S., & Cho, S. (2024). Transfer learning-based approach for small-sample UHPC compressive strength prediction. Construction and Building Materials, 372, 131123. DOI:10.1016/j.conbuildmat.2024.131123