Guansi Liu¹, Hui Jin^1,*, Keqin Ding², Hao Wang³, Violeta Mircevska⁴, Maosen Cao⁵

Structural Durability & Health Monitoring, Vol.20, No.3, 2026, DOI:10.32604/sdhm.2026.079074 - 18 May 2026

Abstract In response to the dynamic changes in fatigue damage location of crane welding structures under lifting loads and the difficulty in accurately obtaining the stress concentration factor of welds, which results in limited effetiveness of traditional health monitoring sensor placement. This paper proposes aa sensor placement optimization method that integrates damage prediction and risk assessment. Firstly, the influence of weld geometry on fatigue performance is analyzed, and a rapid estimation model for the stress concentration factor is established using a radial basis function support vector machine. Furthermore, a fatigue damage prediction model for the welded… More >

Ziliang Yang¹, Mykola Sysyn², Jin Li¹, Jizhe Zhang¹, Jian Liu¹, Lei Kou^1,3,*

Structural Durability & Health Monitoring, Vol.20, No.3, 2026, DOI:10.32604/sdhm.2026.078140 - 18 May 2026

Abstract Accurate assessment of the failure stage of rail rolling contact fatigue (RCF) is critical for guiding timely maintenance by track personnel, ensuring safe rail operations, and reducing maintenance costs. Although various methods have been developed to detect rail damage and classify surface defects, the rolling contact fatigue failure state of rails has not yet been comprehensively and objectively evaluated. This paper introduces the application of image processing and improved deep-learning network algorithms in rail failure evaluation and judgment. Based on Swin Transformer, a deep learning network is developed. By dividing the rail rolling contact fatigue More >

Minyan Zhan¹, Wei Yang^2,3, Minghao Wu^4,*, Hsin-Yi Wang⁵, Yu-Hsien Ho⁵

Structural Durability & Health Monitoring, Vol.20, No.3, 2026, DOI:10.32604/sdhm.2026.077926 - 18 May 2026

Abstract The inclination of wooden columns is a key indicator for evaluating the structural safety of traditional timber buildings in China. However, accurate measurement is challenging because these columns typically exhibit natural tapering, with diameters decreasing from the base to the top, and surface irregularities such as artificial cuts, cracks, and knots. Both the intrinsic geometric characteristics and surface defects reduce the precision of coordinate acquisition and the reliability of inclination estimation. To overcome these limitations, this study proposes a novel inclination measurement method for wooden columns in traditional timber buildings based on multi-section measurement and… More >

Shunpeng Yang¹, Yunpeng Wu¹, Wenwen Qin¹, Cheng Yang^2,*, Yu Qian³

Structural Durability & Health Monitoring, Vol.20, No.3, 2026, DOI:10.32604/sdhm.2026.077878 - 18 May 2026

Abstract To enhance traffic infrastructure health monitoring via computer vision (CV) in adverse weather conditions, image dehazing has emerged as a critical processing step. However, current supervised dehazing models, typically trained on synthetic hazy-clean image pairs, often demonstrate limited generalization ability when deployed in real-world haze scenarios. This study proposes a novel unsupervised dehazing framework named the unpaired dual-domain dehazing network (UD³Net). Initially, a novel dual-domain convolutional mixer (DCM) is developed, which can extract local features in the spatial domain and global features in the frequency domain to achieve thorough information fusion, aiming to facilitate accurate estimation… More >

Haoyu Li¹, Jiayi Wang¹, Zhaoyu Wu¹, Shuo Yan¹, Ziqi Zhang¹, Yang Gao^2,3, Genwang Peng^2,3, Zhiwei Cao^2,*

Structural Durability & Health Monitoring, Vol.20, No.3, 2026, DOI:10.32604/sdhm.2026.077736 - 18 May 2026

Abstract Key components of rail transit systems, such as tracks and vehicle bodies, are prone to developing various types and manifestations of defects during long-term operation. These defects not only accelerate component aging and failure but also pose serious threats to train operational safety. Among existing intelligent detection methods, they mostly rely solely on visible light images demonstrate limited robustness in complex scenarios. This limitation stems from their high dependence on ambient lighting conditions, rendering them insufficient to meet practical railway inspection requirements. While mainstream multimodal detection methods incorporate the complementary strengths of heterogeneous data sources,… More >

Pengcheng Kang¹, Yuanyuan Tian¹, Ying Liu¹, Qian Xu¹, Yuting Chen¹, Lixin Jia², Shuge Guo², Heng Rong², Taolong Xu^2,*

Structural Durability & Health Monitoring, Vol.20, No.3, 2026, DOI:10.32604/sdhm.2026.077643 - 18 May 2026

Abstract Accurate assessment of gas explosion risks in urban underground culverts is often hindered by the decoupling of leakage diffusion and explosion mechanics. This study develops a high-fidelity numerical framework by implementing a one-way coupling strategy, where the steady-state methane concentration field simulated in FLUENT is mapped into ANSYS/LS-DYNA as the initial material status. Unlike traditional models assuming uniform gas distribution, this approach captures the realistic impact of complex culvert geometries on explosion precursors. A multi-material coupled model involving the confined space, road surface, and surrounding air was established to investigate shock-wave propagation and structural response. The More >

Zixuan Zong¹, Tingting Long¹, Huaqing Dong^1,*, Guoqiang Huang¹, Xiao Meng¹, Mohammadamin Azimi²

Structural Durability & Health Monitoring, Vol.20, No.3, 2026, DOI:10.32604/sdhm.2026.077489 - 18 May 2026

Abstract This paper proposes a novel approach for predicting the residual strength of corroded pipelines by combining the Kernel Extreme Learning Machine (KELM) with Sparrow Search Algorithm (SSA) optimization. The proposed SSA-KELM model addresses the limitations of traditional evaluation methods and single machine learning models in residual strength prediction. A dataset comprising 80 samples from burst tests and finite element simulations was used to validate the model. Results demonstrate that the SSA-KELM model achieves superior prediction accuracy with a maximum relative error of 13.54% and minimum relative error of 0.20%. The model’s mean absolute error (MAE), More >

Luis Sánchez Calderón^*, David Valverde Burneo, Walter Hurtares Orrala

Structural Durability & Health Monitoring, Vol.20, No.3, 2026, DOI:10.32604/sdhm.2026.077137 - 18 May 2026

Abstract Accurate characterization of live load histories remains critical for structural safety and efficient design; however, traditional codes often overestimate in-service loads. This study introduced an AI-driven framework integrating YOLOv8 object detection and DeepFace gender classification with continuous video surveillance to monitor live loads in academic buildings. Gender classification used local anthropometric data (77 kg males, 61 kg females) for precise load estimation, with privacy ensured via local processing and anonymized metadata only. Observed peaks were substantially below Eurocode and IBC provisions, confirming code conservatism. Uncertainty propagation from detector errors (recall 0.57, ±0.02 Kn/m²) minimally impacted projections. More >

Wenwen Hu¹, Xinzhan Li², Tao Luo^2,*, Li Li²

Structural Durability & Health Monitoring, Vol.20, No.3, 2026, DOI:10.32604/sdhm.2026.077120 - 18 May 2026

Abstract This study experimentally investigates the Hybrid Effect of Steel Fiber (SF) and Recycled Rubber Powder (RRP) on Freeze-Thaw (F-T) Resistance and Pore Structure of Concrete. With respect to the mechanical properties of Steel Reinforced Concrete (SRC) before and after F-T cycles, the mixture incorporating 1.5% SF and 10% RRP achieves the optimal performance, exhibiting a distinct positive hybrid effect with the γ of the tensile-to-compressive strength ratio of 1.427. The synergistic interaction between SF and RRP preserves the compressive strength and significantly enhances the tensile performance of SRC. Meanwhile, it alleviates the degradation of mechanical More >

Xiaodong Jia^1,*, Xiao Li², Yi Zhao³

Structural Durability & Health Monitoring, Vol.20, No.3, 2026, DOI:10.32604/sdhm.2026.077108 - 18 May 2026

Abstract With the increasing environmental pressure caused by waste plastic (WP), incorporating recycled plastics into asphalt concrete has become a promising strategy for sustainable pavement construction. In this study, waste polyethylene terephthalate (PET) was utilized to replace mineral aggregates through a dry process, and the effects of particle size and replacement level on the mechanical performance of asphalt concrete were systematically evaluated. High-temperature deformation resistance was assessed using wheel-tracking tests, followed by dynamic modulus measurements to examine the viscoelastic behavior and structural stiffness. Low-temperature cracking resistance was studied through fracture toughness and fracture energy tests, and… More >