AI in Structural Health Monitoring for Infrastructure Maintenance and Safety

Infrastructures, Год журнала: 2024, Номер 9(12), С. 225 - 225

Опубликована: Дек. 7, 2024

This study explores the growing influence of artificial intelligence (AI) on structural health monitoring (SHM), a critical aspect infrastructure maintenance and safety. begins with bibliometric analysis to identify current research trends, key contributing countries, emerging topics in AI-integrated SHM. We examine seven core areas where AI significantly advances SHM capabilities: (1) data acquisition sensor networks, highlighting improvements technology collection; (2) processing signal analysis, techniques enhance feature extraction noise reduction; (3) anomaly detection damage identification using machine learning (ML) deep (DL) for precise diagnostics; (4) predictive maintenance, optimize scheduling prevent failures; (5) reliability risk assessment, integrating diverse datasets real-time analysis; (6) visual inspection remote monitoring, showcasing role AI-powered drones imaging systems; (7) resilient adaptive infrastructure, enables systems respond dynamically changing conditions. review also addresses ethical considerations societal impacts SHM, such as privacy, equity, transparency. conclude by discussing future directions challenges, emphasizing potential efficiency, safety, sustainability systems.

Язык: Английский

---

Application of Machine Learning for Real-Time Structural Integrity Assessment of Bridges

CivilEng, Год журнала: 2025, Номер 6(1), С. 2 - 2

Опубликована: Янв. 7, 2025

The concept of digital twins (DT)s enhances traditional structural health monitoring (SHM) by integrating real-time data with models for predictive maintenance and decision-making whilst combined finite element modelling (FEM). However, the computational demand FE necessitates surrogate performance, alongside requirement inverse analysis to infer overall behaviour via measured response a structure. A FEM-based machine learning (ML) model is an ideal option in this context, as it can be trained perform those calculations instantly based on FE-based training data. performance depends ML architecture. In light, current study investigates three distinct DTs. It was identified that all demonstrated strong tree-based outperforming neural network (NN) model. highest accuracy random forest (RF) error 0.000350, lowest inference time observed XGBoost algorithm, which at approximately 1 millisecond. By leveraging capabilities ML, FEM, DTs, presents solution implementing DTs advance functionalities SHM systems.

Язык: Английский

---

Review of Condition Rating and Deterioration Modeling Approaches for Concrete Bridges

Buildings, Год журнала: 2025, Номер 15(2), С. 219 - 219

Опубликована: Янв. 13, 2025

Concrete bridges are the most prevalent bridge type worldwide, forming critical components of transportation infrastructure. These subjected to continuous deterioration due environmental exposure and operational stresses, necessitating ongoing condition monitoring. Despite extensive research on rating modeling concrete bridges, a comprehensive comparative understanding these processes remains underexplored. This paper addresses this gap by conducting scientometric systematic review approaches for highlight their strengths limitations. Accordingly, methods were found have heavy reliance qualitative visual inspections (VI) inherent subjective assumptions. Techniques such as fuzzy logic non-destructive evaluation (NDE) identified promising tools mitigate uncertainties enhance accuracy. Moreover, performance models was dependent quality historical data. The advancement hybrid models, integrating artificial intelligence (AI) with stochastic physics-based approaches, has proven be powerful strategy, combining each method deliver enhanced predictions. Finally, study offers key insights future directions assist researchers policymakers in advancing sustainable management practices.

Язык: Английский

---

Intelligent prediction and evaluation models for the seismic risk and vulnerability of reinforced concrete girder bridges in large-scale zones

Reliability Engineering & System Safety, Год журнала: 2024, Номер 256, С. 110743 - 110743

Опубликована: Дек. 10, 2024

Язык: Английский

---

Estimating the seismic vulnerability of buildings considering modified intensity measures

Structures, Год журнала: 2024, Номер 71, С. 107989 - 107989

Опубликована: Дек. 10, 2024

Язык: Английский

---

Bias-aware degradation models for reinforced concrete bridges based on XAI

Developments in the Built Environment, Год журнала: 2025, Номер unknown, С. 100617 - 100617

Опубликована: Фев. 1, 2025

Язык: Английский

---

Comparison of vulnerability models for masonry building portfolios considering different macroseismic intensity scales

Journal of Building Engineering, Год журнала: 2025, Номер unknown, С. 112066 - 112066

Опубликована: Фев. 1, 2025

Язык: Английский

---

Vibration sensing system integrating triboelectric nanogenerator and synaptic transistor for self-powered building vibration identification

Measurement, Год журнала: 2025, Номер unknown, С. 116966 - 116966

Опубликована: Фев. 1, 2025

Язык: Английский

---

Development of seismic risk models for low-rise masonry structures considering age and deterioration effects

Bulletin of Earthquake Engineering, Год журнала: 2024, Номер unknown

Опубликована: Ноя. 20, 2024

Язык: Английский

---

MACHINE LEARNING MODELS FOR SEISMIC ANALYSIS OF BUCKLING-RESTRAINED BRACED FRAMES

Journal of Building Engineering, Год журнала: 2024, Номер unknown, С. 111398 - 111398

Опубликована: Ноя. 1, 2024

Язык: Английский

---