International Journal of Damage Mechanics最新文献_第2页

Molecular insights into fatigue damage characteristics of monocrystalline and polycrystalline salt rock under cyclic compression 循环压缩下单晶和多晶盐岩疲劳损伤特征的分子分析

IF 4.2 2区工程技术

International Journal of Damage Mechanics Pub Date : 2026-10-08 DOI: 10.1177/10567895261495312

Jinyang Fan, Peiran Wen, Zongze Li, Marion Fourmeau, Jie Chen, Deyi Jiang, Daniel Nelias

{"title":"Molecular insights into fatigue damage characteristics of monocrystalline and polycrystalline salt rock under cyclic compression","authors":"Jinyang Fan, Peiran Wen, Zongze Li, Marion Fourmeau, Jie Chen, Deyi Jiang, Daniel Nelias","doi":"10.1177/10567895261495312","DOIUrl":"https://doi.org/10.1177/10567895261495312","url":null,"abstract":"This study presents a comparative investigation of the mechanical behavior of monocrystalline and polycrystalline salt rock under both constant-rate and variable-rate cyclic compression, revealing their fatigue damage characteristics at the micro-scale and elucidating the underlying dislocation motion mechanisms and fatigue damage evolution. Results demonstrate that under constant-rate cyclic loading, increasing the loading–unloading rate significantly reduces the hysteretic energy dissipation, softening rate, dislocation density in monocrystalline models, and atomic shear strain, thereby enhancing cyclic stress response and stabilizing the face-centered cubic lattice structure. Plastic yielding in monocrystalline salt rock can be delayed by either increasing the loading rate or employing variable-rate loading. In contrast, polycrystalline salt rock enters the plastic stage immediately upon the first cycle, with its lattice structure exhibiting recovery ordering after initial damage—a phenomenon most pronounced at lower loading rates. Regarding microscopic deformation mechanisms, dislocations and strain localization in monocrystalline salt rock are concentrated at the crystal top, forming continuous oblique patterns, while damage in polycrystalline salt rock is primarily confined to grain boundary regions. Under the same average loading rate, simulations reveal that the depressurization loading mode corresponding to the air extraction phase induces more severe structural softening, indicating that the accelerated loading path can more effectively inhibit the propagation of microcracks and the accumulation of intergranular damage. This research provides atomistic insight into cyclic deformation and defect evolution in salt rock, which may help inform future multiscale assessments of salt cavern stability.","PeriodicalId":13837,"journal":{"name":"International Journal of Damage Mechanics","volume":"4 1","pages":""},"PeriodicalIF":4.2,"publicationDate":"2026-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149130439","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Static–dynamic reloading degradation and brittle-to-ductile failure transition of cyclically pre-damaged sandstone: A multiscale experimental study 循环预损伤砂岩的静动再加载退化及脆性-延性破坏转变：多尺度试验研究

IF 4.2 2区工程技术

International Journal of Damage Mechanics Pub Date : 2026-10-08 DOI: 10.1177/10567895261494769

Jianjun Zeng, Guangliang Feng, Yang Yu, Yalong Jiang, Qi Ma, Yingjing Huang, Qincai Jiang, Chun Zhu

{"title":"Static–dynamic reloading degradation and brittle-to-ductile failure transition of cyclically pre-damaged sandstone: A multiscale experimental study","authors":"Jianjun Zeng, Guangliang Feng, Yang Yu, Yalong Jiang, Qi Ma, Yingjing Huang, Qincai Jiang, Chun Zhu","doi":"10.1177/10567895261494769","DOIUrl":"https://doi.org/10.1177/10567895261494769","url":null,"abstract":"Rock masses in underground engineering commonly experience cyclic disturbances induced by blasting, excavation, and seismic loading, which can generate persistent internal damage and strongly affect their subsequent reloading behavior. To clarify the unified mechanism governing the static and dynamic responses of cyclically pre-damaged rock, red sandstone specimens were first subjected to cyclic loading-unloading under different upper limit cyclic stresses and then tested under uniaxial compression and SHPB impact loading. Acoustic emission (AE), digital image correlation, fragment fractal analysis, and scanning electron microscopy were combined to characterize the multiscale evolution of deformation and failure. The results show that cyclic pre-damage progressively reconstructs the internal crack network and degrades the load-bearing skeleton of the rock, causing exponential reductions in static peak strength and elastic modulus and linear attenuation of dynamic mechanical parameters. AE activity is systematically enhanced, the pre-peak quiet period shortens, and burst signals occur earlier with increasing initial damage. Moreover, the sensitivity of dynamic parameters to pre-damage becomes stronger at higher strain rates, indicating a strain-rate amplification of damage weakening. Multiscale observations further demonstrate that cyclic pre-damage alters the energy dissipation pathway and drives the failure mode from brittle-dominated fracture to ductile-dominated instability. These findings provide a unified physical framework for evaluating the residual stability and dynamic disaster potential of disturbed rock masses.","PeriodicalId":13837,"journal":{"name":"International Journal of Damage Mechanics","volume":"15 1","pages":""},"PeriodicalIF":4.2,"publicationDate":"2026-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149130441","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Multi-scale damage evolution and fracture precursors of coral powder-modified UHPC under Brazilian splitting 巴西劈裂作用下珊瑚粉改性UHPC的多尺度损伤演化及断裂前兆

IF 4.2 2区工程技术

International Journal of Damage Mechanics Pub Date : 2026-10-08 DOI: 10.1177/10567895261492139

Gang Wang, Yuhao Zhuang, Leibo Song, Yi Luo, Tingting Liu, Jie Liu, Haolin Chen

{"title":"Multi-scale damage evolution and fracture precursors of coral powder-modified UHPC under Brazilian splitting","authors":"Gang Wang, Yuhao Zhuang, Leibo Song, Yi Luo, Tingting Liu, Jie Liu, Haolin Chen","doi":"10.1177/10567895261492139","DOIUrl":"https://doi.org/10.1177/10567895261492139","url":null,"abstract":"The sustainable utilisation of waste coral reefs has drawn significant attention in marine infrastructure development. Ultra-high-performance concrete was fabricated with 0%–25% cement replaced by coral powder (CP) at 5% intervals. Damage evolution during Brazilian splitting tests was tracked using acoustic emission (AE) and computed tomography (CT). Key precursors of progressive failure were identified, and the precursor response coefficient and precursor response stress ratio were introduced for comprehensive evaluation. Results showed that the mechanical performance strongly depended on CP content. A 5%–10% CP content shortened the compaction stage, steepened the linear-stage slope and delayed the pre-peak nonlinearity onset, whereas ≥15% CP produced opposite effects. Tensile strength peaked at 5% CP, with a 6.24% increase; the subsequent decline at higher CP contents may result from dilution and weakened cementation. Under the present CT conditions, 5% CP showed the lowest detectable defect level. With increasing CP content, defects increased, with limited meso-pore growth at 10%–15% and pronounced macropore expansion above 15%. CP content modulated the damage evolution pattern. During the unstable fracture stage, the CG5 group exhibited the smallest damage increment and the strongest crack-arrest capacity, whereas ≥15% of content intensified local deterioration. Multi-parameter AE analysis revealed that ρ and S provided relatively early warning signals yet exhibited substantial data dispersion, whereas tensile crack ratio and b value, although slightly delayed, demonstrated superior stability. A multi-indicator strategy was recommended to balance timeliness and robustness in the identification of failure precursors.","PeriodicalId":13837,"journal":{"name":"International Journal of Damage Mechanics","volume":"9 1","pages":""},"PeriodicalIF":4.2,"publicationDate":"2026-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149130442","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Intelligent prediction and explicit analysis of the compressive strength of UHPC: A comparison of ensemble algorithms and joint SHAP-SALib analysis UHPC抗压强度智能预测与显式分析：集成算法与联合SHAP-SALib分析的比较

IF 4.2 2区工程技术

International Journal of Damage Mechanics Pub Date : 2026-10-08 DOI: 10.1177/10567895261494798

Canrong Xie, Yichan Hu, Weiwei Xie, Askar Zhussupbekov, Hao Chi, Jian Liang

{"title":"Intelligent prediction and explicit analysis of the compressive strength of UHPC: A comparison of ensemble algorithms and joint SHAP-SALib analysis","authors":"Canrong Xie, Yichan Hu, Weiwei Xie, Askar Zhussupbekov, Hao Chi, Jian Liang","doi":"10.1177/10567895261494798","DOIUrl":"https://doi.org/10.1177/10567895261494798","url":null,"abstract":"The prediction of compressive strength of ultra-high-performance concrete (UHPC) is essential for optimizing mix ratios and supporting engineering applications. Traditional testing methods are costly and time-consuming, while empirical formulas often lack generalizability, limiting their effectiveness for precise design requirements. This study aims to establish a high-precision and interpretable UHPC compressive strength prediction and interpretation framework. Utilizing 595 valid mix ratio-strength datasets (the data were split into training and test sets at an 8:2 ratio with five-fold cross-validation used for model evaluation), we compared the performance of six ensemble algorithms: XGBoost, CatBoost, random forest (RF), gradient boosting decision tree (GBDT), AdaBoost, and LightGBM (LGBM). Bayesian hyperparameter optimization was used to identify the optimal parameter combination, and combined SHAP-SALib analyses were employed to achieve explicit model interpretability. Results indicate that the Bayesian-optimized CatBoost model performs best (test set: R 2 = 0.951, RMSE = 6.56 MPa, MAPE = 3.10%), followed by XGBoost (test set: R 2 = 0.925, RMSE = 8.067 MPa, MAPE = 3.573%). Both models demonstrate significantly superior generalization stability compared to the others. SHAP analysis identifies the key influencing factors in descending order: age and steel fiber. SALib analysis confirms that the combined contribution of water-binder ratio, age and Silica fume is substantial, with significant multi-factor interaction effects. This study establishes a high-precision and interpretable UHPC compressive strength prediction model and provides data-driven guidance for mix proportion design.","PeriodicalId":13837,"journal":{"name":"International Journal of Damage Mechanics","volume":"146 1","pages":""},"PeriodicalIF":4.2,"publicationDate":"2026-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149130440","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

The resilience and damage of concrete 混凝土的回弹性和损伤

IF 4.2 2区工程技术

International Journal of Damage Mechanics Pub Date : 2026-10-08 DOI: 10.1177/10567895261488206

Dechun Lu, Shi Wei, Guosheng Wang, Xiuli Du

引用次数: 0

Wear mechanisms and damage evolution of superelastic NiTi orthodontic archwires under coupled bending-sliding loading in simulated oral conditions 模拟口腔弯曲-滑动耦合载荷下超弹性镍钛正畸弓丝磨损机理及损伤演化

IF 4.2 2区工程技术

International Journal of Damage Mechanics Pub Date : 2026-10-08 DOI: 10.1177/10567895261494760

Ines Ben Naceur, Khaled Elleuch

{"title":"Wear mechanisms and damage evolution of superelastic NiTi orthodontic archwires under coupled bending-sliding loading in simulated oral conditions","authors":"Ines Ben Naceur, Khaled Elleuch","doi":"10.1177/10567895261494760","DOIUrl":"https://doi.org/10.1177/10567895261494760","url":null,"abstract":"Nickel–titanium (NiTi) archwires are widely used in orthodontic applications due to their superelastic response and ability to deliver nearly constant forces. During clinical service, these components are subjected to repeated sliding, bending, and moderate temperature variations, which can promote progressive surface degradation. In this study, the influence of combined thermo-mechanical loading on the wear and damage behavior of commercial NiTi archwires was experimentally investigated under simulated oral conditions. Cyclic friction tests were performed in artificial saliva on circular and rectangular archwires at different temperatures, normal loads, and archwire deflection levels using a rotating tribometer. A bending device was employed to closely reproduce in-vivo conditions. After 12,000 sliding cycles, wear rates increased by ∼50% for the rectangular archwire in the active configuration and by about 60% when the normal load was raised to 13 N at 50 °C, compared with passive conditions at 2 N ( n = 3, p < 0.001). Increasing the test temperature above the austenite finish temperature ( A f ) led to a further decrease in wear resistance. Scanning electron microscopy analysis of the wear tracks revealed that abrasive and fatigue-assisted wear patterns were the dominant degradation mechanisms. Bending promoted localized deformation and surface cracking, contributing to reduced fatigue life. Cyclic friction in these regions further enhanced surface damage. These findings provide experimental insight into damage evolution in superelastic NiTi components under combined cyclic loading and moderate temperature variations, offering guidance for durability assessment of orthodontic archwires under service-like conditions.","PeriodicalId":13837,"journal":{"name":"International Journal of Damage Mechanics","volume":"12 1","pages":""},"PeriodicalIF":4.2,"publicationDate":"2026-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149130410","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Improving rolling contact fatigue behavior in wheel–rail systems using a slag powder–oil mixture friction modifier 用渣粉油混合摩擦改进剂改善轮轨系统滚动接触疲劳性能

IF 4.2 2区工程技术

International Journal of Damage Mechanics Pub Date : 2026-10-07 DOI: 10.1177/10567895261492142

Ömer Çölova, Khangardash Asgarov, Hayrettin Ahlatcı, Harun Çuğ

{"title":"Improving rolling contact fatigue behavior in wheel–rail systems using a slag powder–oil mixture friction modifier","authors":"Ömer Çölova, Khangardash Asgarov, Hayrettin Ahlatcı, Harun Çuğ","doi":"10.1177/10567895261492142","DOIUrl":"https://doi.org/10.1177/10567895261492142","url":null,"abstract":"This study investigates the effect of different top-of-rail friction modifier (FM) formulations on the rolling contact fatigue (RCF) behavior at the wheel–rail interface. Three different FMs were examined: flange oil, slag powder, and a hybrid oil + slag powder mixture. A twin-disc test was conducted over 700,000 cycles to evaluate crack initiation and propagation. Surface and subsurface damage characteristics were analyzed using scanning electron microscope (SEM) micrographs. The results show that under flange oil conditions, RCF cracks propagate deeper beneath the surface (127 µm), and the presence of liquid oil promotes crack opening and expansion due to hydraulic pressure within the microcracks. In contrast, slag powder (FMA) alone caused severe wear and surface delamination, demonstrating the lack of protective film formation. However, when combined with slag powder + oil (FMB), the cohesive third body layer formed by viscous oil and slag powder particles effectively restricted subsurface crack growth. The FMB formulation reduced the average subsurface crack length by approximately 42% compared to the flange oil condition and by approximately 35% compared to the slag powder-only condition. Similarly, it successfully reduced the average crack depth by up to 77% in rail discs. This improvement demonstrates the hybrid FM's ability to balance local stresses and suppress hydraulic crack propagation. In general, the findings indicate that hybrid FM, composed of oil and solid waste-based particles, can significantly increase RCF resistance by balancing lubrication and surface protection mechanisms. This highlights that it offers a promising approach for extending the service life of wheel/rail systems.","PeriodicalId":13837,"journal":{"name":"International Journal of Damage Mechanics","volume":"27 1","pages":""},"PeriodicalIF":4.2,"publicationDate":"2026-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149130445","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Anisotropic gradient damage modelling of cleavage crack propagation in metallic polycrystals 金属多晶解理裂纹扩展的各向异性梯度损伤模型

IF 4.2 2区工程技术

International Journal of Damage Mechanics Pub Date : 2026-10-01 DOI: 10.1177/10567895261492140

Augustin Perrier-Michon, Azdine Nait-Ali, Yann Charles, Mikael Gueguen, Damien Halm

{"title":"Anisotropic gradient damage modelling of cleavage crack propagation in metallic polycrystals","authors":"Augustin Perrier-Michon, Azdine Nait-Ali, Yann Charles, Mikael Gueguen, Damien Halm","doi":"10.1177/10567895261492140","DOIUrl":"https://doi.org/10.1177/10567895261492140","url":null,"abstract":"An anisotropic gradient damage model specifically built to capture cleavage-like crack propagation in metallic polycrystalline aggregates is developed. This study extends the classical scalar characteristic length of gradient damage models to a tensorial characteristic length field. This second-order tensor, varying from grain to grain with the local crystallographic orientation, contains information related to the anisotropy of single-crystal fracture resistance, and thus provides a physically motivated parameter governing crack path selection. By appropriately tuning this tensorial field, damage evolution can be hindered in certain directions while being promoted along others, naturally reproducing cleavage fracture behaviour where cracks propagate along preferred crystallographic planes. The present model is built within the framework of the thermodynamics of irreversible processes using the approach of Frémond and Nedjar. To account for the damage evolution under multi-axial stress states, an anisotropic volumetric-deviatoric stiffness decomposition is used. The model is assessed through several loading cases, including a crack propagation simulation in a polycrystalline aggregate where the effect of a tensorial characteristic length field is investigated.","PeriodicalId":13837,"journal":{"name":"International Journal of Damage Mechanics","volume":"53 1","pages":""},"PeriodicalIF":4.2,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149083853","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Quantification of hysteresis area and artificial intelligence-assisted prediction of cracking in biochar-amended soil under wet-dry cycles 干湿循环下生物炭改性土壤的滞后面积量化及开裂人工智能预测

IF 4.2 2区工程技术

International Journal of Damage Mechanics Pub Date : 2026-09-30 DOI: 10.1177/10567895261491004

Mingjie Jiang, Jun Zhong, Muyang Li, Dayu Wan, Guoxiong Mei

{"title":"Quantification of hysteresis area and artificial intelligence-assisted prediction of cracking in biochar-amended soil under wet-dry cycles","authors":"Mingjie Jiang, Jun Zhong, Muyang Li, Dayu Wan, Guoxiong Mei","doi":"10.1177/10567895261491004","DOIUrl":"https://doi.org/10.1177/10567895261491004","url":null,"abstract":"This study investigates the coupled hysteresis-cracking interaction in expansive soil under wet-dry cycles, integrating artificial intelligence predictive modeling. Based on the Van Genuchten ( VG ) model, an analytical formula for hysteresis area and a one-dimensional crack depth equation considering hysteresis were developed. Laboratory experiments on expansive soil with varying biochar contents revealed hysteresis and crack patterns. Biochar optimizes soil structure via a bimodal pore system, reducing hysteresis and cracking. After 10 cycles, hysteresis area decreased by 37% in bare soil and 70% in 15% biochar-amended soil; the crack intensity factor after five cycles was 9.11 versus 15.17 for the control, confirming crack suppression. The analytical formula matched experimental data well ( R 2 > 0.98). Parameter sensitivity shows hysteresis area depends primarily on VG parameters α , n, and cycle number; higher α and n reduce hysteresis, and area stabilizes with increasing cycles. Hysteresis area strongly correlates with crack depth, serving as a cracking predictor. A mechanism-constrained random forest surrogate model ( R 2 = 0.93, RMSE = 0.82) was developed for rapid crack depth assessment under various material compositions and cycling conditions. These findings offer a theoretical foundation and data-driven techniques for screening protective materials and evaluating damage evolution in unsaturated soils under wet-dry cycling.","PeriodicalId":13837,"journal":{"name":"International Journal of Damage Mechanics","volume":"96 1","pages":""},"PeriodicalIF":4.2,"publicationDate":"2026-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149078089","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Computer vision-based assessment method of repairing failures for stop-hole in steel box girders 基于计算机视觉的箱梁止孔故障修复评估方法

IF 4.2 2区工程技术

International Journal of Damage Mechanics Pub Date : 2026-09-30 DOI: 10.1177/10567895261490381

Yuhang Liu, Zhiyuan Yuanzhou, Bohai Ji, Hongbin Sun

{"title":"Computer vision-based assessment method of repairing failures for stop-hole in steel box girders","authors":"Yuhang Liu, Zhiyuan Yuanzhou, Bohai Ji, Hongbin Sun","doi":"10.1177/10567895261490381","DOIUrl":"https://doi.org/10.1177/10567895261490381","url":null,"abstract":"Fatigue cracks and their corresponding repair status are crucial indicators of the health of steel bridges. Moreover, detailed crack identification is essential for intelligent bridge management and maintenance. Hence, this study proposes a method based on visual geometric characteristics to assess the status of stop-holes and quantify crack features. A multi-task deep learning network, Crack-Weld-Network (CWNet), is designed to simultaneously identify fatigue cracks and weld joints. CWNet consists of two branches: a boundary-guided segmentation branch and a weld joint detection branch, both of which embed feature pyramid networks to fuse features. During the training process, task-specific evaluation metrics were designed for different tasks, and the training results were compared with the baseline models to assess performance improvements. The proposed assessment and quantification method was validated through laboratory tests on specimens representing local details of a steel box girder. Experimental results demonstrated that, compared to the baseline models, CWNet improved the mean intersection over union and structural similarity by more than 7% and 9%. Additionally, the line similarity metric for weld joint detection achieved 84.7%. On images of structural specimens, CWNet achieved a segmentation performance exceeding 75% and a weld detection score exceeding 90%. In addition, the proposed crack length quantification method yielded an average relative error of approximately 3.4%, while the accuracy of the stop-hole repair status assessment exceeded 95%.","PeriodicalId":13837,"journal":{"name":"International Journal of Damage Mechanics","volume":"11 1","pages":""},"PeriodicalIF":4.2,"publicationDate":"2026-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149078086","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0