Computer-Aided Civil and Infrastructure Engineering最新文献

英文中文

Cover Image, Volume 39, Issue 20 封面图片，第 39 卷第 20 期

IF 8.5 1区工程技术 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computer-Aided Civil and Infrastructure Engineering

Pub Date : 2024-10-01 DOI: 10.1111/mice.13351

The cover image is based on the Article Aggregation formulation for on-site multidepot vehicle scheduling scenario by Yi Gao et al., https://doi.org/10.1111/mice.13217.

封面图像基于高毅等人的文章《现场多网点车辆调度场景下的聚合公式》，https://doi.org/10.1111/mice.13217。

引用次数: 0

Weakly-supervised structural component segmentation via scribble annotations 通过涂鸦注释进行弱监督结构组件分割

IF 11.775 1区工程技术 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computer-Aided Civil and Infrastructure Engineering

Pub Date : 2024-09-30 DOI: 10.1111/mice.13350

Chenyu Zhang, Ke Li, Zhaozheng Yin, Ruwen Qin

Segmentation of structural components in infrastructure inspection images is crucial for automated and accurate condition assessment. While deep neural networks hold great potential for this task, existing methods typically require fully annotated ground truth masks, which are time-consuming and labor-intensive to create. This paper introduces Scribble-supervised Structural Component Segmentation Network (ScribCompNet), the first weakly-supervised method requiring only scribble annotations for multiclass structural component segmentation. ScribCompNet features a dual-branch architecture with higher-resolution refinement to enhance fine detail detection. It extends supervision from labeled to unlabeled pixels through a combined objective function, incorporating scribble annotation, dynamic pseudo label, semantic context enhancement, and scale-adaptive harmony losses. Experimental results show that ScribCompNet outperforms other scribble-supervised methods and most fully-supervised counterparts, achieving 90.19% mean intersection over union (mIoU) with an 80% reduction in labeling time. Further evaluations confirm the effectiveness of the novel designs and robust performance, even with lower-quality scribble annotations.

对基础设施检测图像中的结构部件进行分割，对于自动、准确地进行状态评估至关重要。虽然深度神经网络在这一任务中具有巨大潜力，但现有方法通常需要完全注释的地面实况掩模，而创建地面实况掩模耗时耗力。本文介绍了涂鸦监督结构组件分割网络（ScribCompNet），这是第一种只需要涂鸦注释就能进行多类结构组件分割的弱监督方法。ScribCompNet 采用双分支架构，具有更高分辨率的细化功能，可增强精细度检测。它通过一个综合目标函数，结合涂鸦注释、动态伪标签、语义上下文增强和规模自适应和谐损失，将监督范围从已标记像素扩展到未标记像素。实验结果表明，ScribCompNet 的性能优于其他涂鸦监督方法和大多数完全监督的同类方法，平均交集大于联合（mIoU）率达到 90.19%，标注时间减少了 80%。进一步的评估证实了新设计的有效性和强大的性能，即使是质量较低的涂鸦注释也不例外。

{"title":"Weakly-supervised structural component segmentation via scribble annotations","authors":"Chenyu Zhang, Ke Li, Zhaozheng Yin, Ruwen Qin","doi":"10.1111/mice.13350","DOIUrl":"https://doi.org/10.1111/mice.13350","url":null,"abstract":"Segmentation of structural components in infrastructure inspection images is crucial for automated and accurate condition assessment. While deep neural networks hold great potential for this task, existing methods typically require fully annotated ground truth masks, which are time-consuming and labor-intensive to create. This paper introduces Scribble-supervised Structural Component Segmentation Network (ScribCompNet), the first weakly-supervised method requiring only scribble annotations for multiclass structural component segmentation. ScribCompNet features a dual-branch architecture with higher-resolution refinement to enhance fine detail detection. It extends supervision from labeled to unlabeled pixels through a combined objective function, incorporating scribble annotation, dynamic pseudo label, semantic context enhancement, and scale-adaptive harmony losses. Experimental results show that ScribCompNet outperforms other scribble-supervised methods and most fully-supervised counterparts, achieving 90.19% mean intersection over union (mIoU) with an 80% reduction in labeling time. Further evaluations confirm the effectiveness of the novel designs and robust performance, even with lower-quality scribble annotations.","PeriodicalId":156,"journal":{"name":"Computer-Aided Civil and Infrastructure Engineering","volume":"9 1","pages":""},"PeriodicalIF":11.775,"publicationDate":"2024-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142329946","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}

引用次数: 0

A cooperative methodology for multi-roller automation in pavement construction considering trajectory planning and collaborative operation 考虑轨迹规划和协同操作的路面施工中多碾压机自动化协同方法

IF 11.775 1区工程技术 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computer-Aided Civil and Infrastructure Engineering

Pub Date : 2024-09-29 DOI: 10.1111/mice.13347

Difei Wu, Sheng Zhong, Man Io Leong, Yishun Li, Boyuan Tian, Chenglong Liu, Yuchuan Du

Intelligent compaction, particularly fully autonomous compaction, has emerged as a widely accepted innovative technology for enhancing compaction quality and efficiency. When multiple rollers are concurrently engaged in compaction within the same region, the trajectory planning for each roller and cooperative control become pivotal factors in ensuring efficient and safe compaction. This paper presents a comprehensive methodology framework for achieving safe and efficient cooperative operations in multi-roller automation application. Initially, conventional rollers are retrofitted with autonomous functionality, allowing them to automatically follow preset trajectories through a tracking control algorithm. A trajectory planning method is then proposed, tailored for multi-roller operations. Subsequently, a series of cooperative control strategies are outlined to determine the optimal timing for executing compaction tasks. Additionally, a cooperative control strategy is proposed for multi-roller operations, known as “move forward and backward together” control, which ensures the rollers initiate and cease movement without colliding. Finally, the proposed trajectory planning method and cooperative control strategies are validated through field tests conducted on a 100-m-long, 12-m-wide compaction test site. These tests include single-roller trials, two-roller-in-a-row experiments, and multi-roller cooperation tests. The average trajectory tracking error is maintained below 15 cm, and the effectiveness of the control strategies is demonstrated.

智能压实技术，尤其是全自动压实技术，已成为提高压实质量和效率的一项广受认可的创新技术。当多个压路机在同一区域内同时进行压实作业时，每个压路机的轨迹规划和协同控制成为确保高效安全压实的关键因素。本文介绍了在多压路机自动化应用中实现安全高效协同操作的综合方法框架。首先，传统压路机加装了自主功能，可通过跟踪控制算法自动跟踪预设轨迹。然后，提出了一种针对多辊操作的轨迹规划方法。随后，概述了一系列合作控制策略，以确定执行压实任务的最佳时机。此外，还提出了一种适用于多压路机操作的合作控制策略，即 "一起向前和向后移动 "控制，可确保压路机在启动和停止运动时不会发生碰撞。最后，通过在 100 米长、12 米宽的压实试验场进行实地测试，验证了所提出的轨迹规划方法和协同控制策略。这些试验包括单个压路机试验、双压路机并排试验和多压路机合作试验。平均轨迹跟踪误差保持在 15 厘米以下，证明了控制策略的有效性。

{"title":"A cooperative methodology for multi-roller automation in pavement construction considering trajectory planning and collaborative operation","authors":"Difei Wu, Sheng Zhong, Man Io Leong, Yishun Li, Boyuan Tian, Chenglong Liu, Yuchuan Du","doi":"10.1111/mice.13347","DOIUrl":"https://doi.org/10.1111/mice.13347","url":null,"abstract":"Intelligent compaction, particularly fully autonomous compaction, has emerged as a widely accepted innovative technology for enhancing compaction quality and efficiency. When multiple rollers are concurrently engaged in compaction within the same region, the trajectory planning for each roller and cooperative control become pivotal factors in ensuring efficient and safe compaction. This paper presents a comprehensive methodology framework for achieving safe and efficient cooperative operations in multi-roller automation application. Initially, conventional rollers are retrofitted with autonomous functionality, allowing them to automatically follow preset trajectories through a tracking control algorithm. A trajectory planning method is then proposed, tailored for multi-roller operations. Subsequently, a series of cooperative control strategies are outlined to determine the optimal timing for executing compaction tasks. Additionally, a cooperative control strategy is proposed for multi-roller operations, known as “move forward and backward together” control, which ensures the rollers initiate and cease movement without colliding. Finally, the proposed trajectory planning method and cooperative control strategies are validated through field tests conducted on a 100-m-long, 12-m-wide compaction test site. These tests include single-roller trials, two-roller-in-a-row experiments, and multi-roller cooperation tests. The average trajectory tracking error is maintained below 15 cm, and the effectiveness of the control strategies is demonstrated.","PeriodicalId":156,"journal":{"name":"Computer-Aided Civil and Infrastructure Engineering","volume":"12 1","pages":""},"PeriodicalIF":11.775,"publicationDate":"2024-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142329284","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}

引用次数: 0

Mainshock–aftershock sequence simulation via latent space encoding of generative adversarial networks 通过生成式对抗网络的潜在空间编码进行主震-余震序列模拟

IF 11.775 1区工程技术 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computer-Aided Civil and Infrastructure Engineering

Pub Date : 2024-09-29 DOI: 10.1111/mice.13348

Zekun Xu, Jiaxu Shen, Huayong Wu, Jun Chen

Aftershocks (ASs) following strong mainshocks (MSs) can exacerbate structural damage or lead to collapse. However, the scarcity of recorded data necessitates reliance on artificial sequences, which have difficulty in characterizing the time-frequency correlation between MSs and ASs. This study innovatively converts the AS time history prediction into an image translation task, exploiting the invertible transformation between accelerograms and time-frequency representations. An encoder–decoder neural network is developed to encode the MS information into the latent space of a pre-trained generative adversarial network, enabling accurate AS predictions through the decoder. The integration of seismic parameters further improves the AS prediction performance. Comparative analyses demonstrate that the proposed method outperforms the traditional ones on accuracy and robustness and reproduces the non-stationarity of ASs.

强烈主震（MS）之后的余震（AS）会加剧结构破坏或导致坍塌。然而，由于记录数据稀缺，必须依赖人工序列，而人工序列难以表征 MS 和 AS 之间的时频相关性。本研究利用加速度图与时频表示之间的可逆变换，创新性地将自动变速器时间历史预测转换为图像转换任务。开发的编码器-解码器神经网络可将 MS 信息编码到预先训练好的生成式对抗网络的潜在空间中，从而通过解码器实现准确的 AS 预测。地震参数的整合进一步提高了 AS 预测性能。对比分析表明，所提出的方法在准确性和鲁棒性方面优于传统方法，并能再现 AS 的非平稳性。

引用次数: 0

Characterization of mechanical properties of shale constituent minerals using phase-identified nanoindentation 利用相位识别纳米压痕法表征页岩成分矿物的力学特性

IF 11.775 1区工程技术 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computer-Aided Civil and Infrastructure Engineering

Pub Date : 2024-09-21 DOI: 10.1111/mice.13346

Jianting Du, Ka-Veng Yuen, Andrew J. Whittle, Liming Hu, Thibaut Divoux, Jay N. Meegoda

Characterization of mechanical properties of shale constituent minerals (viz., the mechanical genes of shale) has been challenging but of great significance for engineering applications in shale formations. In this study, a phase-identified nanoindentation is proposed to decode the mechanical genes of shale using a large nanomechanical dataset. With the consideration of uniform prior probability density functions (PDFs) and Gaussian posterior PDFs, the evidence of the measured dataset generated by the candidate model classes was assessed by applying the expectation–maximization algorithm and solving the Hessian matrix of the likelihood function. In contrast with Bayesian information criterion analysis, which has been widely used in prior studies, the proposed phase-identified nanoindentation approach is insensitive to the size of the dataset. Here, the identified clusters are well matched with the constituent phases measured by coupling grid nanoindentation and surface physicochemical identification.

页岩成分矿物的力学特性（即页岩的力学基因）的表征具有挑战性，但对页岩层的工程应用具有重要意义。本研究提出了一种相位识别纳米压痕法，利用大型纳米力学数据集解码页岩的力学基因。考虑到均匀先验概率密度函数（PDF）和高斯后验概率密度函数（PDF），通过应用期望最大化算法和求解似然函数的 Hessian 矩阵，评估了候选模型类产生的测量数据集的证据。与之前研究中广泛使用的贝叶斯信息准则分析相比，所提出的相位识别纳米压痕方法对数据集的大小不敏感。在这里，通过耦合网格纳米压痕法和表面物理化学识别法测得的相位与识别出的簇非常匹配。

引用次数: 0

Automated quantification of crack length and width in asphalt pavements 自动量化沥青路面的裂缝长度和宽度

IF 8.5 1区工程技术 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computer-Aided Civil and Infrastructure Engineering

Pub Date : 2024-09-18 DOI: 10.1111/mice.13344

Zhe Li, Tuo Zhang, Yi Miao, Jiupeng Zhang, Mehran Eskandari Torbaghan, Yinzhang He, Jiasheng Dai

Rapid, accurate, and fully automated estimation of both length and width of asphalt pavement cracks, essential for achieving a proactive asset management, presents a significant challenge, primarily due to limitations in the effectiveness of automatic image segmentation and the accuracy of crack width and length estimation algorithms. To address this challenge, this paper introduces the Branch Growing (BG) algorithm, specifically designed for crack length estimation in asphalt pavements, along with an optimized OrthoBoundary algorithm tailored for crack width estimation. Leveraging four widely adopted deep learning models for asphalt pavement crack segmentation, four distinct sets of image segmentation results have been produced. Subsequently, a comprehensive evaluation has been conducted to assess the effectiveness of both crack dimensions estimation algorithms. The findings demonstrate that the integration of the BG algorithm, the optimized OrthoBoundary algorithm, and the fully convolutional network with the HRNet backbone achieve a prediction accuracy of 80.21% for crack length estimation and 84.32% for average width estimation. Moreover, the image processing speed, at a resolution of 3024 × 3024, can be maintained at approximately 5 s, with average width estimation observed to be up to 9.1-fold faster than the unoptimized OrthoBoundary algorithm. These results signify advancements in automated crack quantification methodologies, with implications for enhancing civil infrastructure maintenance practices.

沥青路面裂缝长度和宽度的快速、准确和全自动估算对于实现积极的资产管理至关重要，但主要由于自动图像分割的有效性以及裂缝宽度和长度估算算法的准确性受到限制，这给估算工作带来了巨大挑战。为应对这一挑战，本文介绍了专为沥青路面裂缝长度估算设计的分支生长（BG）算法，以及为裂缝宽度估算量身定制的优化 OrthoBoundary 算法。利用四种广泛采用的沥青路面裂缝分割深度学习模型，产生了四组不同的图像分割结果。随后，对两种裂缝尺寸估算算法的有效性进行了综合评估。研究结果表明，将 BG 算法、优化的 OrthoBoundary 算法和全卷积网络与 HRNet 骨干进行整合后，裂缝长度估算的预测准确率达到 80.21%，平均宽度估算的预测准确率达到 84.32%。此外，在分辨率为 3024 × 3024 的情况下，图像处理速度可保持在 5 秒左右，平均宽度估计速度比未经优化的 OrthoBoundary 算法快达 9.1 倍。这些结果标志着自动裂缝量化方法的进步，对加强民用基础设施维护实践具有重要意义。

{"title":"Automated quantification of crack length and width in asphalt pavements","authors":"Zhe Li, Tuo Zhang, Yi Miao, Jiupeng Zhang, Mehran Eskandari Torbaghan, Yinzhang He, Jiasheng Dai","doi":"10.1111/mice.13344","DOIUrl":"10.1111/mice.13344","url":null,"abstract":"Rapid, accurate, and fully automated estimation of both length and width of asphalt pavement cracks, essential for achieving a proactive asset management, presents a significant challenge, primarily due to limitations in the effectiveness of automatic image segmentation and the accuracy of crack width and length estimation algorithms. To address this challenge, this paper introduces the Branch Growing (BG) algorithm, specifically designed for crack length estimation in asphalt pavements, along with an optimized OrthoBoundary algorithm tailored for crack width estimation. Leveraging four widely adopted deep learning models for asphalt pavement crack segmentation, four distinct sets of image segmentation results have been produced. Subsequently, a comprehensive evaluation has been conducted to assess the effectiveness of both crack dimensions estimation algorithms. The findings demonstrate that the integration of the BG algorithm, the optimized OrthoBoundary algorithm, and the fully convolutional network with the HRNet backbone achieve a prediction accuracy of 80.21% for crack length estimation and 84.32% for average width estimation. Moreover, the image processing speed, at a resolution of 3024 × 3024, can be maintained at approximately 5 s, with average width estimation observed to be up to 9.1-fold faster than the unoptimized OrthoBoundary algorithm. These results signify advancements in automated crack quantification methodologies, with implications for enhancing civil infrastructure maintenance practices.","PeriodicalId":156,"journal":{"name":"Computer-Aided Civil and Infrastructure Engineering","volume":"39 21","pages":"3317-3336"},"PeriodicalIF":8.5,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/mice.13344","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142237072","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}

引用次数: 0

A hybrid non-parametric ground motion model of power spectral density based on machine learning 基于机器学习的功率谱密度混合非参数地动模型

IF 11.775 1区工程技术 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computer-Aided Civil and Infrastructure Engineering

Pub Date : 2024-09-18 DOI: 10.1111/mice.13340

Jiawei Ding, Dagang Lu, Zhenggang Cao

In the fields of engineering seismology and earthquake engineering, researchers have predominantly focused on ground motion models (GMMs) for intensity measures. However, there has been limited research on power spectral density GMMs (PSD-GMMs) that characterize spectral characteristics. PSD, being structure-independent, offers unique advantages. This study aims to construct PSD-GMMs using non-parametric machine learning (ML) techniques. By considering 241 different frequencies from 0.1 to 25.12 Hz and evaluating eight performance indicators, seven highly accurate and stable ML techniques are selected from 12 different ML techniques as foundational models for the PSD-GMM. Through mixed effects regression analysis, inter-event, intra-event, and inter-site standard deviations are derived. To address inherent modeling uncertainty, this study uses the ratio of the reciprocal of the standard deviation of the total residuals of the foundational models to the sum of the reciprocals of the total residuals of the seven ML GMMs as weight coefficients for constructing a hybrid non-parametric PSD-GMM. Utilizing this model, ground motion records can be simulated, and seismic hazard curves and uniform hazard PSD can be obtained. In summary, the hybrid non-parametric PSD-GMM demonstrates remarkable efficacy in simulating and predicting ground motion records and holds significant potential for guiding seismic hazard and risk analysis.

在工程地震学和地震工程学领域，研究人员主要关注烈度测量的地动模型 (GMM)。然而，对描述频谱特征的功率谱密度 GMM（PSD-GMM）的研究还很有限。PSD 与结构无关，具有独特的优势。本研究旨在利用非参数机器学习（ML）技术构建 PSD-GMM。通过考虑从 0.1 到 25.12 Hz 的 241 个不同频率，并评估 8 个性能指标，从 12 种不同的 ML 技术中筛选出 7 种高度准确和稳定的 ML 技术作为 PSD-GMM 的基础模型。通过混合效应回归分析，得出了事件间、事件内和站点间的标准偏差。为了解决建模固有的不确定性，本研究使用基础模型总残差标准偏差的倒数与七个 ML GMM 总残差倒数之和的比值作为权重系数，构建混合非参数 PSD-GMM。利用该模型可以模拟地动记录，并获得地震危险性曲线和均匀危险性 PSD。总之，混合非参数 PSD-GMM 在模拟和预测地动记录方面表现出卓越的功效，在指导地震灾害和风险分析方面具有巨大的潜力。

{"title":"A hybrid non-parametric ground motion model of power spectral density based on machine learning","authors":"Jiawei Ding, Dagang Lu, Zhenggang Cao","doi":"10.1111/mice.13340","DOIUrl":"https://doi.org/10.1111/mice.13340","url":null,"abstract":"In the fields of engineering seismology and earthquake engineering, researchers have predominantly focused on ground motion models (GMMs) for intensity measures. However, there has been limited research on power spectral density GMMs (PSD-GMMs) that characterize spectral characteristics. PSD, being structure-independent, offers unique advantages. This study aims to construct PSD-GMMs using non-parametric machine learning (ML) techniques. By considering 241 different frequencies from 0.1 to 25.12 Hz and evaluating eight performance indicators, seven highly accurate and stable ML techniques are selected from 12 different ML techniques as foundational models for the PSD-GMM. Through mixed effects regression analysis, inter-event, intra-event, and inter-site standard deviations are derived. To address inherent modeling uncertainty, this study uses the ratio of the reciprocal of the standard deviation of the total residuals of the foundational models to the sum of the reciprocals of the total residuals of the seven ML GMMs as weight coefficients for constructing a hybrid non-parametric PSD-GMM. Utilizing this model, ground motion records can be simulated, and seismic hazard curves and uniform hazard PSD can be obtained. In summary, the hybrid non-parametric PSD-GMM demonstrates remarkable efficacy in simulating and predicting ground motion records and holds significant potential for guiding seismic hazard and risk analysis.","PeriodicalId":156,"journal":{"name":"Computer-Aided Civil and Infrastructure Engineering","volume":"44 1","pages":""},"PeriodicalIF":11.775,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142237073","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}

引用次数: 0

Diagnosis of high-speed railway ballastless track arching based on unsupervised learning framework 基于无监督学习框架的高速铁路无砟轨道起拱诊断

IF 11.775 1区工程技术 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computer-Aided Civil and Infrastructure Engineering

Pub Date : 2024-09-18 DOI: 10.1111/mice.13342

Xueyang Tang, Yi Wang, Xiaopei Cai, Fei Yang, Yue Hou

Vehicle-mounted detection methods have been widely applied in the maintenance of high-speed railways (HSRs), providing feasibility for diagnosing ballastless track arching. However, applying detection data faces several key limitations: (1) The threshold mostly requires manual setting, making recognition accuracy highly subjective; (2) the extensive workload of manual inspections makes it challenging to label detection data, hindering the application of supervised learning approaches. To address these problems, this paper utilizes the longitudinal level irregularity data obtained from vehicle-mounted detection, employing the concept of unsupervised learning for dimensionality reduction, combined with clustering algorithms and minimal label fine-tuning, to design two frameworks: the fully unsupervised framework (FUF) and the few-shot fine-tuned framework (FFF). Experiments on dynamic detection data from a Chinese HSR line were conducted, comparing the performance of data dimensionality reduction, clustering, and classification under different strategy combinations. The results show that the improved variational autoencoder significantly enhances the performance of the encoder in dimensionality reduction, facilitating better feature extraction; the FUF achieves effective clustering outcomes without any labeled samples and its adjusted rand index score exceeded 0.8, showcasing its robustness and applicability in scenarios with no prior annotations; the FFF requires only a small number of labeled samples (labeling ratio of 5%) and achieves excellent performance, with metrics such as accuracy exceeding 0.85, thus greatly reducing the reliance on labeled data. This study offers a novel method for solving engineering issues with limited labeled data, providing an efficient solution for identifying track arching defects and advancing railway infrastructure monitoring.

车载检测方法已广泛应用于高速铁路（HSR）的维护中，为诊断无砟轨道拱起提供了可行性。然而，检测数据的应用面临着几个主要的局限性：（1）阈值大多需要人工设置，使得识别精度具有很大的主观性；（2）人工检测的工作量大，使得对检测数据进行标注具有挑战性，阻碍了监督学习方法的应用。为解决这些问题，本文利用车载检测获得的纵向水平不规则数据，采用无监督学习的降维概念，结合聚类算法和最小标签微调，设计了两个框架：完全无监督框架（FUF）和少量标签微调框架（FFF）。对中国高铁线路的动态检测数据进行了实验，比较了不同策略组合下数据降维、聚类和分类的性能。结果表明，改进的变分自动编码器显著提高了编码器的降维性能，有利于更好地提取特征；FUF在没有任何标注样本的情况下实现了有效的聚类结果，其调整后的兰德指数得分超过了0.8，显示了其在无先验标注场景下的鲁棒性和适用性；FFF只需要少量的标注样本（标注率为5%）就能实现出色的性能，准确率等指标超过了0.85，从而大大降低了对标注数据的依赖。这项研究为利用有限的标注数据解决工程问题提供了一种新方法，为识别轨道拱起缺陷和推进铁路基础设施监测提供了一种高效的解决方案。

{"title":"Diagnosis of high-speed railway ballastless track arching based on unsupervised learning framework","authors":"Xueyang Tang, Yi Wang, Xiaopei Cai, Fei Yang, Yue Hou","doi":"10.1111/mice.13342","DOIUrl":"https://doi.org/10.1111/mice.13342","url":null,"abstract":"Vehicle-mounted detection methods have been widely applied in the maintenance of high-speed railways (HSRs), providing feasibility for diagnosing ballastless track arching. However, applying detection data faces several key limitations: (1) The threshold mostly requires manual setting, making recognition accuracy highly subjective; (2) the extensive workload of manual inspections makes it challenging to label detection data, hindering the application of supervised learning approaches. To address these problems, this paper utilizes the longitudinal level irregularity data obtained from vehicle-mounted detection, employing the concept of unsupervised learning for dimensionality reduction, combined with clustering algorithms and minimal label fine-tuning, to design two frameworks: the fully unsupervised framework (FUF) and the few-shot fine-tuned framework (FFF). Experiments on dynamic detection data from a Chinese HSR line were conducted, comparing the performance of data dimensionality reduction, clustering, and classification under different strategy combinations. The results show that the improved variational autoencoder significantly enhances the performance of the encoder in dimensionality reduction, facilitating better feature extraction; the FUF achieves effective clustering outcomes without any labeled samples and its adjusted rand index score exceeded 0.8, showcasing its robustness and applicability in scenarios with no prior annotations; the FFF requires only a small number of labeled samples (labeling ratio of 5%) and achieves excellent performance, with metrics such as accuracy exceeding 0.85, thus greatly reducing the reliance on labeled data. This study offers a novel method for solving engineering issues with limited labeled data, providing an efficient solution for identifying track arching defects and advancing railway infrastructure monitoring.","PeriodicalId":156,"journal":{"name":"Computer-Aided Civil and Infrastructure Engineering","volume":"196 1","pages":""},"PeriodicalIF":11.775,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142246256","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}

引用次数: 0

Corrigendum to “Cooperative control of a platoon of connected autonomous vehicles and unconnected human-driven vehicles” "一排联网自动驾驶车辆与非联网人类驾驶车辆的合作控制 "更正

IF 8.5 1区工程技术 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computer-Aided Civil and Infrastructure Engineering

Pub Date : 2024-09-17 DOI: 10.1111/mice.13345

Zhou A, Peeta S, Wang J. Cooperative control of a platoon of connected autonomous vehicles and unconnected human-driven vehicles. Computer-Aided Civil and Infrastructure Engineering. 2023;38(18): 2513–2536.

In the “Funding Information” section, the text “National Key Research and Development Program of China, Grant/Award Number: 2018YFE0102700.” was incorrect. This should have read: “National Key Research and Development Program of China, Grant/Award Number: 2021YFB1600100.”

The authors apologize for this error.

Zhou A, Peeta S, Wang J. 互联自动驾驶车辆和非互联人类驾驶车辆排的合作控制。计算机辅助土木与基础设施工程》。2023;38(18): 2513-2536.在 "资助信息 "部分，"中国国家重点研发计划，资助/奖励编号：2018YFE0102700 "有误。应为"中国国家重点研发计划，资助/奖励编号：2021YFB1600100。"作者对此错误深表歉意。

引用次数: 0

A relaxation-based Voronoi diagram approach for equitable resource distribution 基于松弛的 Voronoi 图公平分配资源法

IF 11.775 1区工程技术 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computer-Aided Civil and Infrastructure Engineering

Pub Date : 2024-09-17 DOI: 10.1111/mice.13339

Kuangying Li, Asya Atik, Dayang Zheng, Leila Hajibabai, Ali Hajbabaie

This paper introduces a methodology designed to reduce cost, improve demand coverage, and ensure equitable vaccine distribution during the initial stages of the vaccination campaign when demand significantly exceeds supply. We formulate an enhanced maximum covering problem as a mixed integer linear program, aiming to minimize the total vaccine distribution cost while maximizing the allocation of vaccines to population blocks under equity constraints. Block-level census data are employed to define demand locations, identifying gender, age, and racial groups within each block using population data. A Lagrangian relaxation technique integrated with a modified Voronoi diagram is proposed to solve the location–allocation problem efficiently. Empirical case studies in Pennsylvania, using real-world data from the Centers for Disease Control and Prevention and health department websites, were conducted for the first 4 months of the COVID-19 vaccination campaign. Preliminary results show that the proposed solution algorithm effectively solves the problem, achieving a 5.92% reduction in total transportation cost and a 28.15% increase in demand coverage. Moreover, our model can reduce the deviation from equity to 0.07 (∼50% improvement).

本文介绍了一种旨在降低成本、提高需求覆盖率并确保疫苗公平分配的方法，该方法适用于需求明显超过供应的疫苗接种活动初始阶段。我们将一个增强的最大覆盖问题表述为一个混合整数线性程序，旨在使疫苗分配总成本最小化，同时在公平约束条件下最大化疫苗在人口区块的分配。利用区块级人口普查数据确定需求地点，并利用人口数据识别每个区块内的性别、年龄和种族群体。为了有效解决位置分配问题，提出了一种与改进的沃罗诺图相整合的拉格朗日松弛技术。在 COVID-19 疫苗接种活动的前 4 个月，利用疾病控制与预防中心和卫生部门网站提供的真实世界数据，在宾夕法尼亚州进行了经验案例研究。初步结果显示，所提出的解决算法有效地解决了问题，实现了总运输成本降低 5.92%，需求覆盖率提高 28.15%。此外，我们的模型还能将公平偏差降低到 0.07（提高了 50%）。

{"title":"A relaxation-based Voronoi diagram approach for equitable resource distribution","authors":"Kuangying Li, Asya Atik, Dayang Zheng, Leila Hajibabai, Ali Hajbabaie","doi":"10.1111/mice.13339","DOIUrl":"https://doi.org/10.1111/mice.13339","url":null,"abstract":"This paper introduces a methodology designed to reduce cost, improve demand coverage, and ensure equitable vaccine distribution during the initial stages of the vaccination campaign when demand significantly exceeds supply. We formulate an enhanced maximum covering problem as a mixed integer linear program, aiming to minimize the total vaccine distribution cost while maximizing the allocation of vaccines to population blocks under equity constraints. Block-level census data are employed to define demand locations, identifying gender, age, and racial groups within each block using population data. A Lagrangian relaxation technique integrated with a modified Voronoi diagram is proposed to solve the location–allocation problem efficiently. Empirical case studies in Pennsylvania, using real-world data from the Centers for Disease Control and Prevention and health department websites, were conducted for the first 4 months of the COVID-19 vaccination campaign. Preliminary results show that the proposed solution algorithm effectively solves the problem, achieving a 5.92% reduction in total transportation cost and a 28.15% increase in demand coverage. Moreover, our model can reduce the deviation from equity to 0.07 (∼50% improvement).","PeriodicalId":156,"journal":{"name":"Computer-Aided Civil and Infrastructure Engineering","volume":"7 1","pages":""},"PeriodicalIF":11.775,"publicationDate":"2024-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142235506","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}

引用次数: 0

首页上一页

下一页尾页

类型

全部化学•材料生命科学医学物理工程技术环境•农林材料科学地球科学法学管理学化学环境科学与生态学计算机科学教育学经济学农林科学人文科学生物学数学物理与天体物理心理学综合性期刊其他工业工程理学历史学农学文学信息工程

数据库

全部 ACS Publications Elsevier ieeexplore Springer The Royal Society of Chemistry Wiley

期刊

Computer-Aided Civil and Infrastructure Engineering

全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.

﹀