Bingchuan Bai, Bo Lu, Zhichao Wen, Han Yuan, Weijie Li, Xuefeng Zhao
Strain is one of the key indicators for structural health monitoring. In this study, we developed a low-cost microscopic vision-based real-time strain sensor using Raspberry Pi (called MISS-Dym). By strategies for image processing accelerated and the specific running logic, the strain can be outputted at a frequency of more than 30 Hz in real time. The MISS-Dym integrates multiple functions including real-time strain calculations, temperature compensation, data storage, and wireless transmission. Comparative experiments were performed with fiber Bragg grating to assess the accuracy of the sensor. In the static experiments, the maximum mean squared error was 1.77 µε, while the maximum relative error was 5.5% in the dynamic experiments. Additionally, a 10-day monitoring was conducted by MISS-Dym. The results show that the sensor can effectively capture both the vehicle-induced and the temperature-induced strain of the concrete bridge. The MISS-Dym provides an efficient and low-cost method for monitoring the dynamic strain responses of concrete structures.
{"title":"Development of a low-cost microscopic vision-based real-time strain sensor using Raspberry Pi","authors":"Bingchuan Bai, Bo Lu, Zhichao Wen, Han Yuan, Weijie Li, Xuefeng Zhao","doi":"10.1111/mice.13468","DOIUrl":"https://doi.org/10.1111/mice.13468","url":null,"abstract":"Strain is one of the key indicators for structural health monitoring. In this study, we developed a low-cost microscopic vision-based real-time strain sensor using Raspberry Pi (called MISS-Dym). By strategies for image processing accelerated and the specific running logic, the strain can be outputted at a frequency of more than 30 Hz in real time. The MISS-Dym integrates multiple functions including real-time strain calculations, temperature compensation, data storage, and wireless transmission. Comparative experiments were performed with fiber Bragg grating to assess the accuracy of the sensor. In the static experiments, the maximum mean squared error was 1.77 µε, while the maximum relative error was 5.5% in the dynamic experiments. Additionally, a 10-day monitoring was conducted by MISS-Dym. The results show that the sensor can effectively capture both the vehicle-induced and the temperature-induced strain of the concrete bridge. The MISS-Dym provides an efficient and low-cost method for monitoring the dynamic strain responses of concrete structures.","PeriodicalId":156,"journal":{"name":"Computer-Aided Civil and Infrastructure Engineering","volume":"28 1","pages":""},"PeriodicalIF":11.775,"publicationDate":"2025-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143678391","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
High-frequency detection of track defects is crucial for accurate track condition assessment and system safety. Onboard vibration data collection devices can significantly increase detection density without additional costs. However, defect assessment based on this is significantly challenging, including the spatial heterogeneity of track parameters, distribution mismatch between vibration data and defect labels, and variability in vibration responses across different defects. This study proposes a multilevel track defect assessment framework based on vehicle body vibration. The correlation intensity between vibrations and heterogeneity factors was analyzed, and a correlation-view spectral clustering algorithm was designed to achieve effective data set partitioning. A spectral-normalized neural Gaussian process-based adaptive-threshold self-training method (SNGP-ASM) was developed to generate high-quality pseudo-labels and generate a fully labeled data set. An attention-guided multitask cascaded convolutional neural network (CNN) was constructed to progressively assess track defects using channel-wise attentions and a cross-hierarchical attention guidance module. Validations on multiple Chinese metro lines demonstrated that the framework achieved a high performance in training and testing for most defect assessment tasks within lines, and the trained model can effectively adapt to new lines with only lightweight fine-tuning. Moreover, the framework maintained a high computational efficiency, enabling high-frequency track condition monitoring in practical deployment scenarios.
{"title":"A multilevel track defects assessment framework based on vehicle body vibration","authors":"Xingqingrong Chen, Yuanjie Tang, Rengkui Liu","doi":"10.1111/mice.13466","DOIUrl":"https://doi.org/10.1111/mice.13466","url":null,"abstract":"High-frequency detection of track defects is crucial for accurate track condition assessment and system safety. Onboard vibration data collection devices can significantly increase detection density without additional costs. However, defect assessment based on this is significantly challenging, including the spatial heterogeneity of track parameters, distribution mismatch between vibration data and defect labels, and variability in vibration responses across different defects. This study proposes a multilevel track defect assessment framework based on vehicle body vibration. The correlation intensity between vibrations and heterogeneity factors was analyzed, and a correlation-view spectral clustering algorithm was designed to achieve effective data set partitioning. A spectral-normalized neural Gaussian process-based adaptive-threshold self-training method (SNGP-ASM) was developed to generate high-quality pseudo-labels and generate a fully labeled data set. An attention-guided multitask cascaded convolutional neural network (CNN) was constructed to progressively assess track defects using channel-wise attentions and a cross-hierarchical attention guidance module. Validations on multiple Chinese metro lines demonstrated that the framework achieved a high performance in training and testing for most defect assessment tasks within lines, and the trained model can effectively adapt to new lines with only lightweight fine-tuning. Moreover, the framework maintained a high computational efficiency, enabling high-frequency track condition monitoring in practical deployment scenarios.","PeriodicalId":156,"journal":{"name":"Computer-Aided Civil and Infrastructure Engineering","volume":"21 1","pages":""},"PeriodicalIF":11.775,"publicationDate":"2025-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143672664","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Qingqing Zhao, Jinjin Tang, Wen-Long Shang, Chao Li, Yifei Ren, Mohammed Quddus, Washington Ochieng
Passenger flow control and bus bridging are used widely in the operations and management of urban rail transit to relieve the pressure of urban rail transit passenger flow, especially in peak periods. This paper presents an optimization method based on time-varying running time in links. We first develop a mixed integer nonlinear programming model seeking to achieve the minimum total passenger travel time and operation cost. An optimization network and an algorithm are then designed to solve the model. We use the developed method to solve both a small-scale simulated case study and a real-world case study involving the Chengdu Metro. The results obtained by the designed algorithm are comparable with those obtained by the CPLEX solver but with a shorter calculation time. The results show that parallel bus bridging can effectively reduce the number of waiting passengers. A sensitivity analysis of weight suggests that the algorithm successfully balances passenger travel cost and operating cost while incorporating time-varying running times leads to more realistic and dynamic infrastructure planning. This work contributes to the development of intelligent urban rail and road infrastructure systems, promoting safer and more efficient public transport operations.
{"title":"Optimization of passenger flow control and parallel bus bridging in urban rail transit based on intelligent transport infrastructure","authors":"Qingqing Zhao, Jinjin Tang, Wen-Long Shang, Chao Li, Yifei Ren, Mohammed Quddus, Washington Ochieng","doi":"10.1111/mice.13460","DOIUrl":"https://doi.org/10.1111/mice.13460","url":null,"abstract":"Passenger flow control and bus bridging are used widely in the operations and management of urban rail transit to relieve the pressure of urban rail transit passenger flow, especially in peak periods. This paper presents an optimization method based on time-varying running time in links. We first develop a mixed integer nonlinear programming model seeking to achieve the minimum total passenger travel time and operation cost. An optimization network and an algorithm are then designed to solve the model. We use the developed method to solve both a small-scale simulated case study and a real-world case study involving the Chengdu Metro. The results obtained by the designed algorithm are comparable with those obtained by the CPLEX solver but with a shorter calculation time. The results show that parallel bus bridging can effectively reduce the number of waiting passengers. A sensitivity analysis of weight suggests that the algorithm successfully balances passenger travel cost and operating cost while incorporating time-varying running times leads to more realistic and dynamic infrastructure planning. This work contributes to the development of intelligent urban rail and road infrastructure systems, promoting safer and more efficient public transport operations.","PeriodicalId":156,"journal":{"name":"Computer-Aided Civil and Infrastructure Engineering","volume":"56 1","pages":""},"PeriodicalIF":11.775,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143661031","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The cover image is based on the article Modeling the chloride transport in concrete from microstructure generation to chloride diffusivity prediction by Liang-yu Tong et al., https://doi.org/10.1111/mice.13331.
{"title":"Cover Image, Volume 40, Issue 9","authors":"","doi":"10.1111/mice.13465","DOIUrl":"10.1111/mice.13465","url":null,"abstract":"<p><b>The cover image</b> is based on the article <i>Modeling the chloride transport in concrete from microstructure generation to chloride diffusivity prediction</i> by Liang-yu Tong et al., https://doi.org/10.1111/mice.13331.\u0000\u0000 <figure>\u0000 <div><picture>\u0000 <source></source></picture><p></p>\u0000 </div>\u0000 </figure>\u0000 </p>","PeriodicalId":156,"journal":{"name":"Computer-Aided Civil and Infrastructure Engineering","volume":"40 9","pages":""},"PeriodicalIF":8.5,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/mice.13465","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143666461","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Coordinating a platoon of connected and automated vehicles significantly improves traffic efficiency and safety. Current platoon control methods prioritize consistency and convergence performance but overlook the inherent interdependence between the platoon and the the non-connected leading vehicle. This oversight constrains the platoon's adaptability in car-following scenarios, resulting in suboptimal optimization performance. To address this issue, this paper proposed a platoon control framework based on multi-agent reinforcement learning, aiming to integrate cooperative optimization with platoon tracking behavior and internal coordination strategies. This strategy employs a bidirectional cooperative optimization mechanism to effectively decouple the platoon's tracking behavior from its internal coordination control, and then recouple it in a multi-objective optimized manner. Additionally, it leverages long short-term memory networks to accurately capture and manage the platoon's dynamic nature over time, aiming to achieve enhanced optimization outcomes. The simulation results demonstrate that the proposed method effectively improves the platoon's cooperative effect and car-following adaptability. Compared to the consensus control strategy, it reduces the average spacing error by 8.3%. Furthermore, the average length of the platoon decreases by 19.1%.
{"title":"Enhanced consensus control architecture for autonomous platoon utilizing multi-agent reinforcement learning","authors":"Xin Guo, Jiankun Peng, Dawei Pi, Hailong Zhang, Changcheng Wu, Chunye Ma","doi":"10.1111/mice.13463","DOIUrl":"https://doi.org/10.1111/mice.13463","url":null,"abstract":"Coordinating a platoon of connected and automated vehicles significantly improves traffic efficiency and safety. Current platoon control methods prioritize consistency and convergence performance but overlook the inherent interdependence between the platoon and the the non-connected leading vehicle. This oversight constrains the platoon's adaptability in car-following scenarios, resulting in suboptimal optimization performance. To address this issue, this paper proposed a platoon control framework based on multi-agent reinforcement learning, aiming to integrate cooperative optimization with platoon tracking behavior and internal coordination strategies. This strategy employs a bidirectional cooperative optimization mechanism to effectively decouple the platoon's tracking behavior from its internal coordination control, and then recouple it in a multi-objective optimized manner. Additionally, it leverages long short-term memory networks to accurately capture and manage the platoon's dynamic nature over time, aiming to achieve enhanced optimization outcomes. The simulation results demonstrate that the proposed method effectively improves the platoon's cooperative effect and car-following adaptability. Compared to the consensus control strategy, it reduces the average spacing error by 8.3%. Furthermore, the average length of the platoon decreases by 19.1%.","PeriodicalId":156,"journal":{"name":"Computer-Aided Civil and Infrastructure Engineering","volume":"14 1","pages":""},"PeriodicalIF":11.775,"publicationDate":"2025-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143660435","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In structural health monitoring, only the deflection of key sections of the bridge can be monitored; the spatial continuous deflection of the main girder cannot be identified. To solve this problem, a method for expanding sparse point deflection measurements to spatially continuous data via optical fiber sensors in long-span suspension bridges is proposed. First, the distributed fiber-optic sensors are arranged longitudinally along the bridge to obtain the strain data of high-density measurement points on the main girder. Second, the influences of ambient temperature and cable system on the main girder strain of the suspension bridge are eliminated by using multiple types of sensors, and a transformation model from strain to deflection of the main girder based on an inverse finite element method is established. Then, by using thin-walled bar torsion analysis and deflection data obtained from point sensors, a method for expanding the deflection data of high-density measurement points on long-span suspension bridges that combines data interpolation and particle swarm optimization is proposed. The proposed method can extend the deflection monitoring data at key sections to the spatial continuous position of the main girder, thus effectively identifying the deflection of high-density measurement points on the main girder. Finally, a numerical simulation and monitoring data of a real bridge are used to evaluate the effectiveness of the proposed method, and the results show that the deflection identification results of the proposed method are more accurate than the conjugate beam method and the inverse finite element method without considering the main girder torsion.
{"title":"Expanding sparse point deflection measurements to spatially continuous data via optical fiber sensors in long-span suspension bridges","authors":"Qianen Xu, Xinteng Ma, Yang Liu","doi":"10.1111/mice.13459","DOIUrl":"https://doi.org/10.1111/mice.13459","url":null,"abstract":"In structural health monitoring, only the deflection of key sections of the bridge can be monitored; the spatial continuous deflection of the main girder cannot be identified. To solve this problem, a method for expanding sparse point deflection measurements to spatially continuous data via optical fiber sensors in long-span suspension bridges is proposed. First, the distributed fiber-optic sensors are arranged longitudinally along the bridge to obtain the strain data of high-density measurement points on the main girder. Second, the influences of ambient temperature and cable system on the main girder strain of the suspension bridge are eliminated by using multiple types of sensors, and a transformation model from strain to deflection of the main girder based on an inverse finite element method is established. Then, by using thin-walled bar torsion analysis and deflection data obtained from point sensors, a method for expanding the deflection data of high-density measurement points on long-span suspension bridges that combines data interpolation and particle swarm optimization is proposed. The proposed method can extend the deflection monitoring data at key sections to the spatial continuous position of the main girder, thus effectively identifying the deflection of high-density measurement points on the main girder. Finally, a numerical simulation and monitoring data of a real bridge are used to evaluate the effectiveness of the proposed method, and the results show that the deflection identification results of the proposed method are more accurate than the conjugate beam method and the inverse finite element method without considering the main girder torsion.","PeriodicalId":156,"journal":{"name":"Computer-Aided Civil and Infrastructure Engineering","volume":"27 1","pages":""},"PeriodicalIF":11.775,"publicationDate":"2025-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143640561","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper proposes a novel origin–destination (OD) prediction (ODP) model, namely, knowledge-enhanced hybrid spatial–temporal graph neural networks (KE-H-GNN). KE-H-GNN integrates a deep learning predictive model with traffic engineering domain knowledge and a multi-linear regression (MLR) module for incorporating external factors. Leveraging insights from the gravity model, we propose two meaningful region partitioning strategies for reducing data dimension: election districts and K-means clustering. The aggregated OD matrices and graph inputs are processed using an long short-term memory network to capture temporal correlations and a multi-graph input graph convolutional network module to capture spatial correlations. The model also employs a global–local attention module, inspired by traffic flow theory, to capture nonlinear spatial features. Finally, an MLR module was designed to quantify the relationship between OD matrices and external factors. Experiments on real-world datasets from New York and Tokyo demonstrate that KE-H-GNN outperforms all the baseline models while maintaining interpretability. Additionally, the MLR module outperformed the concatenation method for integrating external factors, regarding both performance and transparency. Moreover, the election district-based partitioning approach proved more effective and simpler for practical applications. The proposed KE-H-GNN offers an effective and interpretable solution for ODP that can be practically applied in real-world scenarios.
{"title":"Origin–destination prediction via knowledge-enhanced hybrid learning","authors":"Zeren Xing, Edward Chung, Yiyang Wang, Azusa Toriumi, Takashi Oguchi, Yuehui Wu","doi":"10.1111/mice.13458","DOIUrl":"https://doi.org/10.1111/mice.13458","url":null,"abstract":"This paper proposes a novel origin–destination (OD) prediction (ODP) model, namely, knowledge-enhanced hybrid spatial–temporal graph neural networks (KE-H-GNN). KE-H-GNN integrates a deep learning predictive model with traffic engineering domain knowledge and a multi-linear regression (MLR) module for incorporating external factors. Leveraging insights from the gravity model, we propose two meaningful region partitioning strategies for reducing data dimension: election districts and K-means clustering. The aggregated OD matrices and graph inputs are processed using an long short-term memory network to capture temporal correlations and a multi-graph input graph convolutional network module to capture spatial correlations. The model also employs a global–local attention module, inspired by traffic flow theory, to capture nonlinear spatial features. Finally, an MLR module was designed to quantify the relationship between OD matrices and external factors. Experiments on real-world datasets from New York and Tokyo demonstrate that KE-H-GNN outperforms all the baseline models while maintaining interpretability. Additionally, the MLR module outperformed the concatenation method for integrating external factors, regarding both performance and transparency. Moreover, the election district-based partitioning approach proved more effective and simpler for practical applications. The proposed KE-H-GNN offers an effective and interpretable solution for ODP that can be practically applied in real-world scenarios.","PeriodicalId":156,"journal":{"name":"Computer-Aided Civil and Infrastructure Engineering","volume":"125 1","pages":""},"PeriodicalIF":11.775,"publicationDate":"2025-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143640791","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Phat Tai Lam, Jaehyuk Lee, Yunwoo Lee, Xuan Tinh Nguyen, Van Vy, Kevin Han, Hyungchul Yoon
With the rapid increase in the number of vehicles, accurately identifying vehicle loads is crucial for maintaining and operating transportation infrastructure systems. Existing load identification methods typically rely on collecting vehicle load data from weigh-in-motion (WIM) systems when vehicles pass over them. However, cumbersome installation, high costs, and regular maintenance are the main obstacles that prevent WIM from being widely used in practice. This study introduces the visual WIM (V-WIM) framework, a vision-based approach for tracking and identifying moving loads. The V-WIM framework consists of two main components, the vehicle weight estimation and the vehicle tracking and location estimation. Vehicle weight is estimated using tire deformation parameters extracted from tire images through object detection and optical character recognition techniques. A deep learning-based YOLOv8 algorithm is employed as a vehicle detector, combined with the ByteTrack algorithm for tracking vehicle location. The vehicle weight and its corresponding location are then integrated to enable simultaneous vehicle weight estimation and tracking. The performance of the proposed framework was evaluated through two component validation tests and one on-site validation test, demonstrating its capability to overcome the limitations of existing methods.
{"title":"A vision-based weigh-in-motion approach for vehicle load tracking and identification","authors":"Phat Tai Lam, Jaehyuk Lee, Yunwoo Lee, Xuan Tinh Nguyen, Van Vy, Kevin Han, Hyungchul Yoon","doi":"10.1111/mice.13461","DOIUrl":"https://doi.org/10.1111/mice.13461","url":null,"abstract":"With the rapid increase in the number of vehicles, accurately identifying vehicle loads is crucial for maintaining and operating transportation infrastructure systems. Existing load identification methods typically rely on collecting vehicle load data from weigh-in-motion (WIM) systems when vehicles pass over them. However, cumbersome installation, high costs, and regular maintenance are the main obstacles that prevent WIM from being widely used in practice. This study introduces the visual WIM (V-WIM) framework, a vision-based approach for tracking and identifying moving loads. The V-WIM framework consists of two main components, the vehicle weight estimation and the vehicle tracking and location estimation. Vehicle weight is estimated using tire deformation parameters extracted from tire images through object detection and optical character recognition techniques. A deep learning-based YOLOv8 algorithm is employed as a vehicle detector, combined with the ByteTrack algorithm for tracking vehicle location. The vehicle weight and its corresponding location are then integrated to enable simultaneous vehicle weight estimation and tracking. The performance of the proposed framework was evaluated through two component validation tests and one on-site validation test, demonstrating its capability to overcome the limitations of existing methods.","PeriodicalId":156,"journal":{"name":"Computer-Aided Civil and Infrastructure Engineering","volume":"89 1","pages":""},"PeriodicalIF":11.775,"publicationDate":"2025-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143631374","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Drop brackets (DB) and swivel clevises (SC) are critical components of railway catenary systems, playing a key role in maintaining cantilever stability. The condition of these components significantly impacts the safe operation of the catenary, necessitating periodic inspections to detect defects. This task is typically performed by onboard cameras using computer vision. However, traditional image processing methods often focus on shallow features, making it difficult to handle the interference from complex structures of components. While deep learning methods have strong capabilities in capturing semantic features, the lack of crack samples makes reliable crack identification challenging. Therefore, a joint approach for crack detection based on structural perception is proposed. The approach integrates three main components: object structure perception, stick structure perception, and crack defect detection. A multistream catenary components segmentation network (MCSnet) is employed to extract structural features of the DB and SC. Subsequently, an adaptive stick perception method (ASPM) is applied to identify potential crack candidates based on stick structure. The combined structural features enable effective detection of crack defects. Experimental results validate the effectiveness of the proposed approach.
{"title":"A crack detection method based on structure perception for drop brackets and swivel clevises in catenary system","authors":"Dongkai Zhang, Lifan Sun, Ferrante Neri, Zhumu Fu, Long Yu, Jian Wang, Yajie Yu","doi":"10.1111/mice.13464","DOIUrl":"https://doi.org/10.1111/mice.13464","url":null,"abstract":"Drop brackets (DB) and swivel clevises (SC) are critical components of railway catenary systems, playing a key role in maintaining cantilever stability. The condition of these components significantly impacts the safe operation of the catenary, necessitating periodic inspections to detect defects. This task is typically performed by onboard cameras using computer vision. However, traditional image processing methods often focus on shallow features, making it difficult to handle the interference from complex structures of components. While deep learning methods have strong capabilities in capturing semantic features, the lack of crack samples makes reliable crack identification challenging. Therefore, a joint approach for crack detection based on structural perception is proposed. The approach integrates three main components: object structure perception, stick structure perception, and crack defect detection. A multistream catenary components segmentation network (MCSnet) is employed to extract structural features of the DB and SC. Subsequently, an adaptive stick perception method (ASPM) is applied to identify potential crack candidates based on stick structure. The combined structural features enable effective detection of crack defects. Experimental results validate the effectiveness of the proposed approach.","PeriodicalId":156,"journal":{"name":"Computer-Aided Civil and Infrastructure Engineering","volume":"69 1","pages":""},"PeriodicalIF":11.775,"publicationDate":"2025-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143618923","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Structural performance prediction for structures and their components is a critical issue for ensuring the safety of civil engineering structures. Thus, enhancing the reliability of the prediction models with better generalization capability and quantifying the uncertainties of their predictions is significant. However, existing mechanism-driven and data-driven prediction models for reliable engineering applications incorporate complicated modifications on models and are sensitive to the precision of relevant prior knowledge. Focusing on these issues, a novel and concise data-driven approach, named “R2CU” (stands for transforming regression to classification with uncertainty-aware), is proposed to introduce the relative fuzzy prior knowledge into the data-driven prediction models. To enhance generalization capacity, the conventional regression task is transformed into a classification task based on the fuzzy prior knowledge and the experimental data. Then the aleatoric and epistemic uncertainty of the prediction is estimated to provide the confidence interval, which reflects the prediction's trustworthiness. A validation case study based on shear capacity prediction of reinforced concrete (RC) deep beams is carried out. The result proved that the model's generalization capability for extrapolating has been effectively enhanced with the proposed approach (the prediction precision was raised 80%). Meanwhile, the uncertainties within the model's prediction are rationally estimated, which made the proposed approach a practical alternative for structural performance prediction.
{"title":"Uncertainty-aware fuzzy knowledge embedding method for generalized structural performance prediction","authors":"Xiang-Yu Wang, Xin-Rui Ma, Shi-Zhi Chen","doi":"10.1111/mice.13457","DOIUrl":"https://doi.org/10.1111/mice.13457","url":null,"abstract":"Structural performance prediction for structures and their components is a critical issue for ensuring the safety of civil engineering structures. Thus, enhancing the reliability of the prediction models with better generalization capability and quantifying the uncertainties of their predictions is significant. However, existing mechanism-driven and data-driven prediction models for reliable engineering applications incorporate complicated modifications on models and are sensitive to the precision of relevant prior knowledge. Focusing on these issues, a novel and concise data-driven approach, named “R2CU” (stands for transforming regression to classification with uncertainty-aware), is proposed to introduce the relative <i>fuzzy prior knowledge</i> into the data-driven prediction models. To enhance generalization capacity, the conventional regression task is transformed into a classification task based on the fuzzy prior knowledge and the experimental data. Then the aleatoric and epistemic uncertainty of the prediction is estimated to provide the confidence interval, which reflects the prediction's trustworthiness. A validation case study based on shear capacity prediction of reinforced concrete (RC) deep beams is carried out. The result proved that the model's generalization capability for extrapolating has been effectively enhanced with the proposed approach (the prediction precision was raised 80%). Meanwhile, the uncertainties within the model's prediction are rationally estimated, which made the proposed approach a practical alternative for structural performance prediction.","PeriodicalId":156,"journal":{"name":"Computer-Aided Civil and Infrastructure Engineering","volume":"23 1","pages":""},"PeriodicalIF":11.775,"publicationDate":"2025-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143618918","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：