What question did this study set out to answer?

The aim is to develop predictive models for estimating crack repair percentages in self-healing concrete using machine learning.

December 9, 2025Scientific ReportsOpen Access

Prediction of crack repair percentage in self-healing concrete using machine learning

View Full Paper

Ask AI

Bookmark

Authors

HKHossein Khosravi PKPeyman Kiani MBMohammad Bahram

Discussion

Member takes

Overview

This study demonstrates improved prediction accuracy of crack repair in self-healing concrete using optimization algorithms in artificial neural networks.

Key Points

The aim is to develop predictive models for estimating crack repair percentages in self-healing concrete using machine learning.
Developed three hybrid predictive models: ANN optimized with GA, PSO, and LM algorithm.
Evaluated model performance using multiple statistical indices.
Compared performance against benchmarks from previous studies.
All three hybrid models outperformed the reference study by Zhuang et al.
The ANN-LM model achieved the highest prediction accuracy.
Findings suggest integrating optimization algorithms with ANN enhances prediction reliability.

Cite This Study

Khosravi et al. (2025) studied this question.

synapsesocial.com/papers/69401d5b2d562116f28f8bd7 https://doi.org/10.1038/s41598-025-30158-3

View Full Paper

Ask AI

Bookmark

December 9, 2025Scientific ReportsOpen Access

Prediction of crack repair percentage in self-healing concrete using machine learning

View Full Paper

Ask AI

Bookmark

Authors

HKHossein Khosravi PKPeyman Kiani MBMohammad Bahram

Discussion

Member takes

Overview

This study demonstrates improved prediction accuracy of crack repair in self-healing concrete using optimization algorithms in artificial neural networks.

Key Points

The aim is to develop predictive models for estimating crack repair percentages in self-healing concrete using machine learning.
Developed three hybrid predictive models: ANN optimized with GA, PSO, and LM algorithm.
Evaluated model performance using multiple statistical indices.
Compared performance against benchmarks from previous studies.
All three hybrid models outperformed the reference study by Zhuang et al.
The ANN-LM model achieved the highest prediction accuracy.
Findings suggest integrating optimization algorithms with ANN enhances prediction reliability.

Cite This Study

Khosravi et al. (2025) studied this question.

synapsesocial.com/papers/69401d5b2d562116f28f8bd7 https://doi.org/10.1038/s41598-025-30158-3

Also Consider

Synapse has enriched 2 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark