Use of interpretable machine learning approaches for quantificationally understanding the performance of steel fiber-reinforced recycled aggregate concrete: From the perspective of compressive strength and splitting tensile strength

Engineering Applications of Artificial Intelligence, Год журнала: 2024, Номер 137, С. 109170 - 109170

Опубликована: Авг. 27, 2024

Язык: Английский

---

Evaluating enhanced predictive modeling of foam concrete compressive strength using artificial intelligence algorithms

Materials Today Communications, Год журнала: 2024, Номер 40, С. 110022 - 110022

Опубликована: Авг. 1, 2024

Язык: Английский

---

Grey wolf optimizer integrated within boosting algorithm: Application in mechanical properties prediction of ultra high-performance concrete including carbon nanotubes

Applied Materials Today, Год журнала: 2025, Номер 42, С. 102601 - 102601

Опубликована: Янв. 18, 2025

Язык: Английский

---

Prediction of non-uniform shrinkage of steel-concrete composite slabs based on explainable ensemble machine learning model

Journal of Building Engineering, Год журнала: 2024, Номер 88, С. 109002 - 109002

Опубликована: Март 12, 2024

Язык: Английский

---

A review on properties and multi-objective performance predictions of concrete based on machine learning models

Materials Today Communications, Год журнала: 2025, Номер unknown, С. 112017 - 112017

Опубликована: Фев. 1, 2025

Язык: Английский

---

Probabilistic machine leaning models for predicting the maximum displacements of concrete-filled steel tubular columns subjected to lateral impact loading

Engineering Applications of Artificial Intelligence, Год журнала: 2024, Номер 135, С. 108704 - 108704

Опубликована: Июнь 10, 2024

Язык: Английский

---

Integrating particle packing approach with ML techniques to optimise the compressive strength of RCA based concrete mixes

Journal of Building Engineering, Год журнала: 2024, Номер 94, С. 109994 - 109994

Опубликована: Июнь 21, 2024

Язык: Английский

---

Explainable artificial intelligence framework for FRP composites design

Composite Structures, Год журнала: 2024, Номер 341, С. 118190 - 118190

Опубликована: Май 7, 2024

Fiber-reinforced polymer (FRP) materials are integral to various industries, from automotive and aerospace infrastructure construction. While FRP composite design guidelines have been established, the process of obtaining desired strength an demands considerable time resources. Despite recent advancements in Machine Learning (ML) models which commonly used as predictive models, inherent 'black box' nature those poses challenges understanding relationship between input parameters output composite. Moreover, these do not provide tools facilitate designing The current study introduces explainable Artificial Intelligence (XAI) framework that will for input–output relationships model through SHapley Additive exPlanations (SHAP) Partial Dependence Plots (PDPs). In addition, provides first a approach adjusting important obtain by designer utilizing explainability technique called Counterfactual (CF). is evaluated 14-ply composite, successfully identifying critical parameters, specifying necessary adjustments meet requirements.

Язык: Английский

---

Failure node prediction study of in-service tunnel concrete for sulfate attack by PSO-LSTM based on Markov correction

Case Studies in Construction Materials, Год журнала: 2024, Номер 20, С. e03153 - e03153

Опубликована: Апрель 15, 2024

Sulfate attack seriously affects the durability of concrete structures, and many tunnels constructed in China early years did not adequately take it into account, resulting structural degradation currently operating within their service life. In this study, we integrated experimental machine learning (ML) approaches to assess tunnel concrete. Specifically, compared deteriorated by sulfate with freshly poured lining that was built using same mix ratio. By analyzing ultrasonic velocity data for different periods wet dry cyclic accelerated erosion experiments, evaluated effectiveness multiple time series statistical methods, ML techniques, optimization algorithms. Through analysis, derived best prediction model Particle Swarm Optimization - Long Short Term Memory (PSO-LSTM) its Markov-corrected results. Based on damage nodes compressive strength corrosion resistance coefficient (CCSCRC) actual test, target existing are predicted. The results show that: (1) PSO-LSTM is well adapted deterioration subjected attack, a correlation R2 0.9739. (2) corrected Markov chain can effectively capture trend predicted improve accuracy. (3) When CCSCRC decreased 82 %, loosening granulation occurred. addition, failure structure observed at 677.6 days after sampling, less than two years. outcomes research enhance precision predicting life linings providing valuable insights on-site maintenance construction, contributing as reference similar studies.

Язык: Английский

---

Proposal of a sequential machine learning modelling approach for optimal cementitious composites

Engineering Applications of Artificial Intelligence, Год журнала: 2025, Номер 143, С. 109837 - 109837

Опубликована: Янв. 18, 2025

Язык: Английский

---