Prediction and prevention of concrete chloride penetration: machine learning and MICP techniques

Lianqiang Li, Le Su, Bingchuan Guo, Rongjiang Cai, Xi Wang, Tao Zhang

Research output: Contribution to journalArticlepeer-review

Abstract

The chloride migration coefficient (CMC) of concrete is crucial for evaluating its durability. This study develops ensemble models to predict the CMC of concrete, addressing the limitations of traditional, labor-intensive laboratory tests. We developed three ensemble models: an inverse variance-based model, an Artificial Neural Network (ANN)-based model, and a tree-based model using the random forest regression algorithm. These models were trained on a dataset comprising 843 concrete mix proportions from existing literature. Results indicate that ensemble models outperform single models such as ANN and Support Vector Regression (SVR) in predicting CMC, with the combined random forest and ANN model showing the highest accuracy. Sensitivity analysis using Shapley Additive Explanations (SHAP) reveals that the CMC is most influenced by the water-to-cement ratio and curing age. Additionally, we designed a graphical user interface (GUI) to facilitate the practical application of our models. This research offers a robust methodology for evaluating concrete durability and potential for extending the prediction to other concrete properties.

Original languageEnglish
Article number1445547
JournalFrontiers in Materials
Volume11
DOIs
Publication statusPublished - 2024

Keywords

  • GUI
  • chloride migration coefficient
  • concrete
  • durability
  • machine learning

Fingerprint

Dive into the research topics of 'Prediction and prevention of concrete chloride penetration: machine learning and MICP techniques'. Together they form a unique fingerprint.

Cite this