Journal of Infrastructure Intelligence and Resilience最新文献_第3页

Strain signal denoising in bridge SHM: A comparative analysis of MODWT and other techniques 桥梁SHM应变信号去噪：MODWT与其它方法的比较分析

Journal of Infrastructure Intelligence and Resilience

Pub Date : 2025-09-01 Epub Date: 2025-04-29 DOI: 10.1016/j.iintel.2025.100155

Yun-Xia Xia , Ru-Kai Xu , Yi-Qing Ni , Zu-Quan Jin

Accurate denoising of strain signals is critical for early damage detection in bridge structural health monitoring (SHM). However, signals denoising methods often struggle with the non-stationary and broadband noise encountered in real-world environments. This study provides the first comprehensive comparison of various denoising techniques specifically tailored for bridge strain signals, emphasizing the maximal overlapping discrete wavelet transform (MODWT) for its capacity to handle complex noise profiles. We rigorously compare MODWT with time-domain (moving average filter, finite impulse response filter, empirical mode decomposition), frequency-domain (bandpass filter, Fourier mode decomposition), and other wavelet-based (discrete wavelet transform) approaches. Uniquely, this study employs three datasets from two distinct bridge types (masonry arch and steel bowstring) and evaluates performance using both expert assessments and quantitative metrics (signal-to-noise ratio, peak signal-to-noise ratio, root mean square error, and correlation coefficient). Our findings demonstrate that MODWT exhibits a distinct advantage in high-intensity white noise environments, a common scenario in real-world bridge monitoring, offering valuable guidance for engineers in selecting appropriate denoising strategies. The results not only validate MODWT as a promising preprocessing technique but also offer critical insights into the limitations of existing methods, paving the way for the development of more adaptive and robust denoising solutions in bridge SHM.

应变信号的准确去噪是桥梁结构健康监测中早期损伤检测的关键。然而，信号去噪方法经常与现实环境中遇到的非平稳和宽带噪声作斗争。本研究首次对各种专门针对桥梁应变信号的去噪技术进行了全面比较，强调了最大重叠离散小波变换（MODWT）处理复杂噪声剖面的能力。我们严格比较了MODWT与时域（移动平均滤波器、有限脉冲响应滤波器、经验模态分解）、频域（带通滤波器、傅立叶模态分解）和其他基于小波的（离散小波变换）方法。独特的是，本研究采用了来自两种不同桥梁类型（砌体拱桥和钢弓弦桥）的三个数据集，并使用专家评估和定量指标（信噪比、峰值信噪比、均方根误差和相关系数）来评估性能。我们的研究结果表明，MODWT在高强度白噪声环境中表现出明显的优势，这是现实世界桥梁监测中常见的场景，为工程师选择适当的去噪策略提供了有价值的指导。研究结果不仅验证了MODWT作为一种有前途的预处理技术，而且对现有方法的局限性提供了重要的见解，为开发更具适应性和鲁棒性的桥梁SHM去噪解决方案铺平了道路。

{"title":"Strain signal denoising in bridge SHM: A comparative analysis of MODWT and other techniques","authors":"Yun-Xia Xia , Ru-Kai Xu , Yi-Qing Ni , Zu-Quan Jin","doi":"10.1016/j.iintel.2025.100155","DOIUrl":"10.1016/j.iintel.2025.100155","url":null,"abstract":"<div><div>Accurate denoising of strain signals is critical for early damage detection in bridge structural health monitoring (SHM). However, signals denoising methods often struggle with the non-stationary and broadband noise encountered in real-world environments. This study provides the first comprehensive comparison of various denoising techniques specifically tailored for bridge strain signals, emphasizing the maximal overlapping discrete wavelet transform (MODWT) for its capacity to handle complex noise profiles. We rigorously compare MODWT with time-domain (moving average filter, finite impulse response filter, empirical mode decomposition), frequency-domain (bandpass filter, Fourier mode decomposition), and other wavelet-based (discrete wavelet transform) approaches. Uniquely, this study employs three datasets from two distinct bridge types (masonry arch and steel bowstring) and evaluates performance using both expert assessments and quantitative metrics (signal-to-noise ratio, peak signal-to-noise ratio, root mean square error, and correlation coefficient). Our findings demonstrate that MODWT exhibits a distinct advantage in high-intensity white noise environments, a common scenario in real-world bridge monitoring, offering valuable guidance for engineers in selecting appropriate denoising strategies. The results not only validate MODWT as a promising preprocessing technique but also offer critical insights into the limitations of existing methods, paving the way for the development of more adaptive and robust denoising solutions in bridge SHM.</div></div>","PeriodicalId":100791,"journal":{"name":"Journal of Infrastructure Intelligence and Resilience","volume":"4 3","pages":"Article 100155"},"PeriodicalIF":0.0,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144115297","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Deep learning in crack detection: A comprehensive scientometric review 裂纹检测中的深度学习：科学计量学综述

Journal of Infrastructure Intelligence and Resilience

Pub Date : 2025-09-01 Epub Date: 2025-02-23 DOI: 10.1016/j.iintel.2025.100144

Yingjie Wu , Shaoqi Li , Jingqiu Li , Yanping Yu , Jianchun Li , Yancheng Li

Cracks represent one of the common forms of damage in concrete structures and pavements, leading to safety issues and increased maintenance costs. Therefore, timely crack detection is crucial for preventing further damage and ensuring the safety of these structures. Traditional manual inspection methods are limited by factors such as time consumption, subjectivity, and labor intensity. To address these challenges, deep learning-based crack detection technologies have emerged as promising solutions, demonstrating satisfactory performance and accuracy. However, the field still lacks comprehensive scientometric analyses and critical surveys of existing works, which are vital for identifying research gaps and guiding future studies. This paper conducts a bibliometric and critical analysis of the collected literature, providing novel insights into current research trends and identifying potential areas for future investigation. Analytical tools, including VOSviewer and CiteSpace, were employed for in-depth analysis and visualization. This study identifies key research gaps and proposes future directions, focusing on advancements in model generalization, computational efficiency, dataset standardization, and the practical application of crack detection methods.

裂缝是混凝土结构和路面的常见损坏形式之一，会导致安全问题并增加维护成本。因此，及时检测裂缝对防止结构进一步破坏，保证结构安全至关重要。传统的人工检测方法受时间、主观性、劳动强度等因素的限制。为了应对这些挑战，基于深度学习的裂缝检测技术已经成为有前途的解决方案，表现出令人满意的性能和准确性。然而，该领域仍然缺乏对现有工作的全面科学计量分析和批判性调查，这对于确定研究差距和指导未来的研究至关重要。本文对收集到的文献进行了文献计量学和批判性分析，为当前的研究趋势提供了新的见解，并确定了未来研究的潜在领域。使用VOSviewer和CiteSpace等分析工具进行深入分析和可视化。本研究确定了关键的研究差距并提出了未来的研究方向，重点关注模型泛化、计算效率、数据集标准化和裂纹检测方法的实际应用方面的进展。

{"title":"Deep learning in crack detection: A comprehensive scientometric review","authors":"Yingjie Wu , Shaoqi Li , Jingqiu Li , Yanping Yu , Jianchun Li , Yancheng Li","doi":"10.1016/j.iintel.2025.100144","DOIUrl":"10.1016/j.iintel.2025.100144","url":null,"abstract":"<div><div>Cracks represent one of the common forms of damage in concrete structures and pavements, leading to safety issues and increased maintenance costs. Therefore, timely crack detection is crucial for preventing further damage and ensuring the safety of these structures. Traditional manual inspection methods are limited by factors such as time consumption, subjectivity, and labor intensity. To address these challenges, deep learning-based crack detection technologies have emerged as promising solutions, demonstrating satisfactory performance and accuracy. However, the field still lacks comprehensive scientometric analyses and critical surveys of existing works, which are vital for identifying research gaps and guiding future studies. This paper conducts a bibliometric and critical analysis of the collected literature, providing novel insights into current research trends and identifying potential areas for future investigation. Analytical tools, including VOSviewer and CiteSpace, were employed for in-depth analysis and visualization. This study identifies key research gaps and proposes future directions, focusing on advancements in model generalization, computational efficiency, dataset standardization, and the practical application of crack detection methods.</div></div>","PeriodicalId":100791,"journal":{"name":"Journal of Infrastructure Intelligence and Resilience","volume":"4 3","pages":"Article 100144"},"PeriodicalIF":0.0,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143739718","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Large multimodal model assisted underground tunnel damage inspection and human-machine interaction 大型多模态模型辅助地下隧道损伤检测和人机交互

Journal of Infrastructure Intelligence and Resilience

Pub Date : 2025-09-01 Epub Date: 2025-04-01 DOI: 10.1016/j.iintel.2025.100154

Yanzhi Qi , Zhi Ding , Yaozhi Luo

Artificial Intelligence is playing an increasingly important role in tunnel inspection as a core driver of the new generation of engineering. Traditional methods are difficult to directly generate human linguistic information and lack valid messages extracted from different modalities. This paper proposes Damage LMM, a multimodal damage detection model that can handle images or videos as well as text inputs, to realize fast damage identification and human-computer interaction. The visual instruction database is first created from real damage data collected using different visual sensors and captions extracted by a regional convolutional neural network. The basic language model is then fine-tuned into a specialised Damage LMM, which enhances user instructions by integrating virtual prompt injection and system messages. Finally, the enhanced prompts are processed through the tuned multimodal model to generate a detailed visual description of the damage. The performance of the method is evaluated using a real tunnel dataset, and the results show that it has better robustness and accuracy than other models in multimodal data, with an accuracy of 0.93 for the in-domain image data and a contextual correlation of 0.94. The proposed method can effectively identify tunnel defects and realize multimodal user interaction functions with a moderate number of markers and a short delay time, which will greatly help engineers to quickly obtain effective information and assess the degree of damage at the tunnel inspection site.

人工智能作为新一代工程的核心驱动力，在隧道检测中发挥着越来越重要的作用。传统方法难以直接生成人类语言信息，缺乏从不同模态中提取的有效信息。为了实现快速的损伤识别和人机交互，本文提出了一种可以处理图像或视频以及文本输入的多模态损伤检测模型——损伤LMM。视觉指令数据库首先由不同视觉传感器收集的真实损伤数据和由区域卷积神经网络提取的字幕创建。然后将基本语言模型微调为专门的损害LMM，该LMM通过集成虚拟提示注入和系统消息来增强用户指令。最后，通过调整后的多模态模型对增强的提示进行处理，以生成损坏的详细视觉描述。使用真实隧道数据集对该方法进行了性能评估，结果表明，该方法在多模态数据中具有更好的鲁棒性和精度，对域内图像数据的精度为0.93，上下文相关性为0.94。该方法可以有效识别隧道缺陷，实现多模态用户交互功能，标记数量适中，延迟时间短，将极大地帮助工程师在隧道检测现场快速获取有效信息和评估损伤程度。

{"title":"Large multimodal model assisted underground tunnel damage inspection and human-machine interaction","authors":"Yanzhi Qi , Zhi Ding , Yaozhi Luo","doi":"10.1016/j.iintel.2025.100154","DOIUrl":"10.1016/j.iintel.2025.100154","url":null,"abstract":"<div><div>Artificial Intelligence is playing an increasingly important role in tunnel inspection as a core driver of the new generation of engineering. Traditional methods are difficult to directly generate human linguistic information and lack valid messages extracted from different modalities. This paper proposes Damage LMM, a multimodal damage detection model that can handle images or videos as well as text inputs, to realize fast damage identification and human-computer interaction. The visual instruction database is first created from real damage data collected using different visual sensors and captions extracted by a regional convolutional neural network. The basic language model is then fine-tuned into a specialised Damage LMM, which enhances user instructions by integrating virtual prompt injection and system messages. Finally, the enhanced prompts are processed through the tuned multimodal model to generate a detailed visual description of the damage. The performance of the method is evaluated using a real tunnel dataset, and the results show that it has better robustness and accuracy than other models in multimodal data, with an accuracy of 0.93 for the in-domain image data and a contextual correlation of 0.94. The proposed method can effectively identify tunnel defects and realize multimodal user interaction functions with a moderate number of markers and a short delay time, which will greatly help engineers to quickly obtain effective information and assess the degree of damage at the tunnel inspection site.</div></div>","PeriodicalId":100791,"journal":{"name":"Journal of Infrastructure Intelligence and Resilience","volume":"4 3","pages":"Article 100154"},"PeriodicalIF":0.0,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143903728","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Few-shot learning with large foundation models for automated segmentation and accessibility analysis in architectural floor plans 在建筑平面图中进行自动分割和可访问性分析的大型基础模型的少量学习

Journal of Infrastructure Intelligence and Resilience

Pub Date : 2025-06-01 Epub Date: 2024-12-17 DOI: 10.1016/j.iintel.2024.100137

Haolan Zhang, Ruichuan Zhang

This paper presents a novel approach for extracting accessibility features from 2D raster floor plans by integrating few-shot learning techniques with the Segment Anything Model (SAM) and GPT-4. The proposed method addresses the limitations of existing deep learning-based floor plan analysis, which often require extensive annotated datasets and struggle with the variability of raster floor plans. Furthermore, there is a lack of research on extracting accessibility features from 2D raster floor plans, which remain one of the most common formats for storing architectural plans post-design and construction. Our approach, GPT-integrated Multi-object Few-shot SAM (GMFS), leverages similarity maps and cluster-based point sampling to generate accurate visual prompts for SAM, enabling the segmentation of rooms and doors using only five reference samples. The segmented masks are then classified using GPT-4, enhancing the semantic richness of the floor plan analysis. We validated GMFS using the CubiCasa and Rent3D datasets, demonstrating impressive performance in segmentation and classification. A detailed case study further showcased the practical application of our approach in calculating accessible means of egress and wheelchair clear space, which are critical features for accessibility compliance. The results highlight the effectiveness and adaptability of our approach in real-world scenarios, underscoring its potential to improve building accessibility and safety analysis in the architecture, engineering, and construction (AEC) industry.

本文提出了一种结合分段任意模型（SAM）和GPT-4的少镜头学习技术，从二维栅格平面图中提取可达性特征的新方法。提出的方法解决了现有基于深度学习的平面图分析的局限性，这些分析通常需要大量带注释的数据集，并且与栅格平面图的可变性作抗争。此外，从二维栅格平面图中提取可达性特征的研究较少，而二维栅格平面图仍然是建筑平面图后期设计和施工中最常用的存储格式之一。我们的方法，gpt集成的多目标少镜头SAM (GMFS)，利用相似性地图和基于聚类的点采样为SAM生成准确的视觉提示，仅使用五个参考样本就可以分割房间和门。然后使用GPT-4对分割的掩模进行分类，增强了平面图分析的语义丰富性。我们使用CubiCasa和Rent3D数据集验证了GMFS，在分割和分类方面表现出令人印象深刻的性能。一个详细的案例研究进一步展示了我们的方法在计算无障碍出口和轮椅空间方面的实际应用，这些都是符合无障碍标准的关键特征。结果突出了我们的方法在现实场景中的有效性和适应性，强调了它在建筑、工程和施工（AEC）行业中改善建筑物可达性和安全分析的潜力。

{"title":"Few-shot learning with large foundation models for automated segmentation and accessibility analysis in architectural floor plans","authors":"Haolan Zhang, Ruichuan Zhang","doi":"10.1016/j.iintel.2024.100137","DOIUrl":"10.1016/j.iintel.2024.100137","url":null,"abstract":"<div><div>This paper presents a novel approach for extracting accessibility features from 2D raster floor plans by integrating few-shot learning techniques with the Segment Anything Model (SAM) and GPT-4. The proposed method addresses the limitations of existing deep learning-based floor plan analysis, which often require extensive annotated datasets and struggle with the variability of raster floor plans. Furthermore, there is a lack of research on extracting accessibility features from 2D raster floor plans, which remain one of the most common formats for storing architectural plans post-design and construction. Our approach, GPT-integrated Multi-object Few-shot SAM (GMFS), leverages similarity maps and cluster-based point sampling to generate accurate visual prompts for SAM, enabling the segmentation of rooms and doors using only five reference samples. The segmented masks are then classified using GPT-4, enhancing the semantic richness of the floor plan analysis. We validated GMFS using the CubiCasa and Rent3D datasets, demonstrating impressive performance in segmentation and classification. A detailed case study further showcased the practical application of our approach in calculating accessible means of egress and wheelchair clear space, which are critical features for accessibility compliance. The results highlight the effectiveness and adaptability of our approach in real-world scenarios, underscoring its potential to improve building accessibility and safety analysis in the architecture, engineering, and construction (AEC) industry.</div></div>","PeriodicalId":100791,"journal":{"name":"Journal of Infrastructure Intelligence and Resilience","volume":"4 2","pages":"Article 100137"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143642796","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Bayesian mixture of factor analyzers for structural damage detection under varying environmental conditions 基于贝叶斯混合因子的结构损伤检测

Journal of Infrastructure Intelligence and Resilience

Pub Date : 2025-06-01 Epub Date: 2025-01-06 DOI: 10.1016/j.iintel.2025.100140

Binbin Li , Yulong Zhang , Zihan Liao , Zhilin Xue

Variations of structural dynamic parameters (e.g., frequencies and damping ratios) can be caused by potential structural damages and environmental effects (e.g., temperature, humidity). It is of critical importance to distinguish them for a reliable vibration-based damage detection. A variational Bayesian mixture of factor analyzers (VB-MFA) is proposed in this paper for the probabilistic modeling of measured natural frequencies. It contains multiple factor analyzers to accommodate the nonlinear effect of environmental factors on the natural frequencies. The variational Bayes with automatic relevance determination prior empowers it to automatically determine the number of analyzers and the dimension of latent factors in each analyzer. In addition, the predictive marginal likelihood of natural frequencies is proposed as a damage index, which naturally considers the uncertainties in latent factors and estimated parameters. The method is verified in two case studies: a laboratory eight-story shear-type building model and the Z24-Bridge, both subjected to temperature variations. It shows that better performance has been achieved comparing to the conventional factor analysis and mixture of factor analyzers. The VB-MFA is capable to model the nonlinear effect of environmental effect on natural frequencies, and improves the accuracy of vibration-based structural damage detection.

结构动态参数（如频率和阻尼比）的变化可能由潜在的结构损坏和环境影响（如温度、湿度）引起。区分它们对于可靠的基于振动的损伤检测至关重要。本文提出了一种变分贝叶斯混合因子分析法（VB-MFA），用于测量固有频率的概率建模。它包含多因素分析仪，以适应环境因素对固有频率的非线性影响。具有自动关联确定先验的变分贝叶斯能够自动确定分析器的数量和每个分析器中潜在因素的维度。此外，提出了固有频率的预测边际似然作为损伤指标，自然地考虑了潜在因素和估计参数的不确定性。该方法在两个案例研究中得到验证：一个实验室八层剪切式建筑模型和z24桥，两者都受到温度变化的影响。结果表明，与传统因子分析和混合因子分析相比，该方法取得了更好的性能。VB-MFA能够模拟环境对固有频率的非线性影响，提高基于振动的结构损伤检测的精度。

{"title":"Bayesian mixture of factor analyzers for structural damage detection under varying environmental conditions","authors":"Binbin Li , Yulong Zhang , Zihan Liao , Zhilin Xue","doi":"10.1016/j.iintel.2025.100140","DOIUrl":"10.1016/j.iintel.2025.100140","url":null,"abstract":"<div><div>Variations of structural dynamic parameters (e.g., frequencies and damping ratios) can be caused by potential structural damages and environmental effects (e.g., temperature, humidity). It is of critical importance to distinguish them for a reliable vibration-based damage detection. A variational Bayesian mixture of factor analyzers (VB-MFA) is proposed in this paper for the probabilistic modeling of measured natural frequencies. It contains multiple factor analyzers to accommodate the nonlinear effect of environmental factors on the natural frequencies. The variational Bayes with automatic relevance determination prior empowers it to automatically determine the number of analyzers and the dimension of latent factors in each analyzer. In addition, the predictive marginal likelihood of natural frequencies is proposed as a damage index, which naturally considers the uncertainties in latent factors and estimated parameters. The method is verified in two case studies: a laboratory eight-story shear-type building model and the Z24-Bridge, both subjected to temperature variations. It shows that better performance has been achieved comparing to the conventional factor analysis and mixture of factor analyzers. The VB-MFA is capable to model the nonlinear effect of environmental effect on natural frequencies, and improves the accuracy of vibration-based structural damage detection.</div></div>","PeriodicalId":100791,"journal":{"name":"Journal of Infrastructure Intelligence and Resilience","volume":"4 2","pages":"Article 100140"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143552763","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Modular approach to model order reduction for offshore wind turbines supported by multi-bucket jacket foundation 多筒导管基础支撑海上风力机模型降阶的模块化方法

Journal of Infrastructure Intelligence and Resilience

Pub Date : 2025-06-01 Epub Date: 2025-02-20 DOI: 10.1016/j.iintel.2025.100143

Zhaofeng Shen , Yue Chen , Pengfei Li , Jun Liang , Ying Wang , Jinping Ou

Offshore wind turbines (OWTs) supported by multi-bucket jacket foundations (MBJF) provide a cost-effective solution for offshore wind energy production when water depth exceeds 50 m. However, numerical simulation of their dynamic behaviors towards high accuracy and efficiency becomes challenging due to the intricate structural configuration. To tackle it, this paper introduces a model order reduction framework for OWTs with MBJF. The framework strategically decomposes the structure into five substructures, whose reduced-order models (ROMs) are individually constructed and then assembled into a ROM for the entire OWT structure with fixed boundary conditions. The parameters of the assembled ROM on soil are subsequently calibrated through a model updating process, to ensure the alignment of modal parameters and structural displacements between ROM and full-order model (FOM). The results show that Young's moduli of both tower and jacket dominate the frequencies of global bending modes while Young's modulus of the blade dominates the frequencies of blade bending modes. Among the support parameters, the combined T-Z soil spring stiffness plays a critical role, affecting the frequencies of global motion and bending modes. The proposed model order reduction framework provides a robust methodology towards accurate and efficient simulation of structural dynamics for OWTs supported by MBJF.

多桶套基础（MBJF）支撑的海上风力涡轮机（owt）为水深超过50米的海上风力发电提供了一种经济有效的解决方案。然而，由于其复杂的结构结构，对其动态特性进行高精度和高效率的数值模拟具有挑战性。为了解决这一问题，本文引入了基于MBJF的owt模型降阶框架。该框架将结构战略性地分解为五个子结构，每个子结构的降阶模型（ROM）被单独构建，然后组装成具有固定边界条件的整个OWT结构的ROM。随后，通过模型更新过程对土壤上组装的ROM参数进行校准，以确保ROM与全阶模型（FOM）之间的模态参数和结构位移对齐。结果表明，塔架和导管套的杨氏模量主导了整体弯曲模态的频率，而叶片的杨氏模量主导了叶片弯曲模态的频率。在支护参数中，T-Z组合土弹簧刚度对整体运动模态和弯曲模态的频率起着关键作用。所提出的模型降阶框架为MBJF支持的owt结构动力学的准确和有效模拟提供了一种强大的方法。

{"title":"Modular approach to model order reduction for offshore wind turbines supported by multi-bucket jacket foundation","authors":"Zhaofeng Shen , Yue Chen , Pengfei Li , Jun Liang , Ying Wang , Jinping Ou","doi":"10.1016/j.iintel.2025.100143","DOIUrl":"10.1016/j.iintel.2025.100143","url":null,"abstract":"<div><div>Offshore wind turbines (OWTs) supported by multi-bucket jacket foundations (MBJF) provide a cost-effective solution for offshore wind energy production when water depth exceeds 50 m. However, numerical simulation of their dynamic behaviors towards high accuracy and efficiency becomes challenging due to the intricate structural configuration. To tackle it, this paper introduces a model order reduction framework for OWTs with MBJF. The framework strategically decomposes the structure into five substructures, whose reduced-order models (ROMs) are individually constructed and then assembled into a ROM for the entire OWT structure with fixed boundary conditions. The parameters of the assembled ROM on soil are subsequently calibrated through a model updating process, to ensure the alignment of modal parameters and structural displacements between ROM and full-order model (FOM). The results show that Young's moduli of both tower and jacket dominate the frequencies of global bending modes while Young's modulus of the blade dominates the frequencies of blade bending modes. Among the support parameters, the combined T-Z soil spring stiffness plays a critical role, affecting the frequencies of global motion and bending modes. The proposed model order reduction framework provides a robust methodology towards accurate and efficient simulation of structural dynamics for OWTs supported by MBJF.</div></div>","PeriodicalId":100791,"journal":{"name":"Journal of Infrastructure Intelligence and Resilience","volume":"4 2","pages":"Article 100143"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143681861","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Fractal-based numerical simulation of multivariate typhoon wind speeds utilizing weierstrass mandelbrot function 基于weierstrass mandelbrot函数的多变量台风风速分形数值模拟

Journal of Infrastructure Intelligence and Resilience

Pub Date : 2025-06-01 Epub Date: 2024-11-22 DOI: 10.1016/j.iintel.2024.100135

Kang Cai , Mingfeng Huang , Qiang Li , Qing Wang , Yi-Qing Ni

This paper proposes a fractal-based technique for simulating multivariate nonstationary wind fields by the stochastic Weierstrass Mandelbrot function. Upon conducting a systematic fractal analysis, it was found that the structure function method is more suitable and reliable than the box counting method, variation method, and R/S analysis method for estimating the fractal dimension of the stochastic wind speed series. Wind field measurement at the meteorological gradient tower with a height of 356 m in Shenzhen was conducted during Typhoon Mandelbrot (1983). Significant non-stationary properties and fractal dimensions of typhoon wind speed data at various heights were analyzed and used to demonstrate the effectiveness of the proposed multivariate typhoon wind speed simulation method. The multivariate wind speed components simulated by the proposed fractal-based method are in good agreement with the measured records in terms of the fractal dimension, standard deviation, probability density function, wind spectrum and cross-correlation coefficient.

本文提出了一种基于分形的随机Weierstrass Mandelbrot函数模拟多变量非平稳风场的方法。通过系统的分形分析，发现结构函数法比箱计数法、变分法和R/S分析法更适合和可靠地估计随机风速序列的分形维数。在1983年台风“曼德布洛特”期间，在深圳海拔356 m的气象梯度塔上进行了风场测量。分析了不同高度台风风速数据的显著非平稳特性和分形维数，验证了多元台风风速模拟方法的有效性。基于分形方法模拟的多变量风速分量在分形维数、标准差、概率密度函数、风谱和相互关系系数等方面与实测记录吻合较好。

{"title":"Fractal-based numerical simulation of multivariate typhoon wind speeds utilizing weierstrass mandelbrot function","authors":"Kang Cai , Mingfeng Huang , Qiang Li , Qing Wang , Yi-Qing Ni","doi":"10.1016/j.iintel.2024.100135","DOIUrl":"10.1016/j.iintel.2024.100135","url":null,"abstract":"<div><div>This paper proposes a fractal-based technique for simulating multivariate nonstationary wind fields by the stochastic Weierstrass Mandelbrot function. Upon conducting a systematic fractal analysis, it was found that the structure function method is more suitable and reliable than the box counting method, variation method, and R/S analysis method for estimating the fractal dimension of the stochastic wind speed series. Wind field measurement at the meteorological gradient tower with a height of 356 m in Shenzhen was conducted during Typhoon Mandelbrot (1983). Significant non-stationary properties and fractal dimensions of typhoon wind speed data at various heights were analyzed and used to demonstrate the effectiveness of the proposed multivariate typhoon wind speed simulation method. The multivariate wind speed components simulated by the proposed fractal-based method are in good agreement with the measured records in terms of the fractal dimension, standard deviation, probability density function, wind spectrum and cross-correlation coefficient.</div></div>","PeriodicalId":100791,"journal":{"name":"Journal of Infrastructure Intelligence and Resilience","volume":"4 2","pages":"Article 100135"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143146658","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Corrigendum to “Fractal-based numerical simulation of multivariate typhoon wind speeds utilizing weierstrass mandelbrot function” [J. Infrastruct. Intell. Resilience, 2 (2025) 100135] “利用weierstrass mandelbrot函数的多变量台风风速分形数值模拟”的勘误[J]。Infrastruct。智能。弹性，2 (2025)100135]

Journal of Infrastructure Intelligence and Resilience

Pub Date : 2025-06-01 Epub Date: 2025-06-21 DOI: 10.1016/j.iintel.2025.100156

Kang Cai , Mingfeng Huang , Qiang Li , Qing Wang , Yi-Qing Ni

引用次数: 0

Positional inaccuracy investigation and innovative connection solution for robotic construction of load carrying structures 承载结构机器人施工位置误差研究及创新连接解决方案

Journal of Infrastructure Intelligence and Resilience

Pub Date : 2025-06-01 Epub Date: 2025-01-16 DOI: 10.1016/j.iintel.2025.100141

Cheav Por Chea, Yu Bai, Yihai Fang

Robotic construction of load carrying structures in civil engineering becomes promising with the supports from robotics, computer-vision, and design for manufacturing and assembly. A multi-robot system was developed to demonstrate an automated construction of reciprocal frame structures where mobile robots were used to facilitate the access of robotic arms and a series of programming packages were developed to automate the construction. Furthermore, the AprilTag fiducial marker system was applied as a positioning system to align the mobile robots during construction tasks and to target the structural components. In this context, the key challenges are centred on the understanding of the accuracy and tolerance of the robotic system in positioning and navigation. To this end, experimental methods were developed in this study to understand the observed distances and the accuracy of the positioning system. The optimal observation distance for the positioning system in the robotic system was then determined considering the positional and orientational accuracies of the AprilTag fiducial marker system using a red, green, blue-depth (RGB-D) camera. Moreover, experiments were conducted to study the impact of the barycentre of robotic arms on the precision of the mobile robots and to determine the offset of the mobile robot during the manoeuvre. In consideration of the positional inaccuracies, the magnetic connection approach was creatively implemented using their inherent self-aligning property. The corresponding effective range was also firstly determined, within which the structural components could be installed successfully.

在机器人技术、计算机视觉以及制造和装配设计的支持下，土木工程中承载结构的机器人施工前景广阔。开发了一个多机器人系统来演示互惠框架结构的自动化构建，其中移动机器人用于方便机械臂的访问，并开发了一系列编程包来实现自动化构建。此外，应用AprilTag基准标记系统作为定位系统，在施工任务中对移动机器人进行对齐，并对结构部件进行定位。在这种情况下，关键的挑战集中在机器人系统的定位和导航的精度和公差的理解。为此，本研究开发了实验方法来了解定位系统的观测距离和精度。考虑到AprilTag基准标记系统采用红绿蓝深（RGB-D）相机的定位精度和方位精度，确定了机器人系统中定位系统的最佳观测距离。此外，通过实验研究了机械臂重心对移动机器人精度的影响，确定了移动机器人在机动过程中的偏移量。考虑到定位误差，创造性地利用磁连接的自对准特性实现磁连接。首先确定了相应的有效范围，在该有效范围内结构构件可以顺利安装。

{"title":"Positional inaccuracy investigation and innovative connection solution for robotic construction of load carrying structures","authors":"Cheav Por Chea, Yu Bai, Yihai Fang","doi":"10.1016/j.iintel.2025.100141","DOIUrl":"10.1016/j.iintel.2025.100141","url":null,"abstract":"<div><div>Robotic construction of load carrying structures in civil engineering becomes promising with the supports from robotics, computer-vision, and design for manufacturing and assembly. A multi-robot system was developed to demonstrate an automated construction of reciprocal frame structures where mobile robots were used to facilitate the access of robotic arms and a series of programming packages were developed to automate the construction. Furthermore, the AprilTag fiducial marker system was applied as a positioning system to align the mobile robots during construction tasks and to target the structural components. In this context, the key challenges are centred on the understanding of the accuracy and tolerance of the robotic system in positioning and navigation. To this end, experimental methods were developed in this study to understand the observed distances and the accuracy of the positioning system. The optimal observation distance for the positioning system in the robotic system was then determined considering the positional and orientational accuracies of the AprilTag fiducial marker system using a red, green, blue-depth (RGB-D) camera. Moreover, experiments were conducted to study the impact of the barycentre of robotic arms on the precision of the mobile robots and to determine the offset of the mobile robot during the manoeuvre. In consideration of the positional inaccuracies, the magnetic connection approach was creatively implemented using their inherent self-aligning property. The corresponding effective range was also firstly determined, within which the structural components could be installed successfully.</div></div>","PeriodicalId":100791,"journal":{"name":"Journal of Infrastructure Intelligence and Resilience","volume":"4 2","pages":"Article 100141"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143146657","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Intelligent control of structural vibrations based on deep reinforcement learning 基于深度强化学习的结构振动智能控制

Journal of Infrastructure Intelligence and Resilience

Pub Date : 2025-06-01 Epub Date: 2024-12-15 DOI: 10.1016/j.iintel.2024.100136

Xuekai Guo, Pengfei Lin, Qiulei Wang, Gang Hu

This paper explores the application of Deep Reinforcement Learning (DRL) in structural vibration control, aiming to achieve effective control of the dynamic response of building structures during natural disasters such as earthquakes. A DRL-based control strategy is proposed, and dynamic interaction between the OpenSees environment and the deep reinforcement learning environment is realized. By adjusting the parameters in the reward function, the control preference of the DRL algorithm for different metrics can be effectively modified. Additionally, an intelligent structural vibration control platform based on DRL has been developed to simplify the design process of DRL algorithms. Case studies conducted on the platform demonstrate that DRL can effectively suppress structural responses in both single-layer and multi-layer complex structures. Meanwhile, comparisons with PID and LQR algorithms that are based on linear analysis design, reveal the stability advantages of DRL in handling structural dynamic responses characterized by high nonlinearity, time delay, and large actuator output intervals.

本文探讨了深度强化学习（Deep Reinforcement Learning， DRL）在结构振动控制中的应用，旨在有效控制建筑结构在地震等自然灾害下的动力响应。提出了一种基于drl的控制策略，实现了OpenSees环境与深度强化学习环境的动态交互。通过调整奖励函数中的参数，可以有效地修改DRL算法对不同指标的控制偏好。此外，开发了基于DRL的智能结构振动控制平台，简化了DRL算法的设计过程。在平台上进行的实例研究表明，DRL可以有效地抑制单层和多层复杂结构的结构响应。同时，通过与基于线性分析设计的PID和LQR算法的比较，揭示了DRL在处理高非线性、时滞和大执行器输出区间的结构动态响应方面的稳定性优势。

{"title":"Intelligent control of structural vibrations based on deep reinforcement learning","authors":"Xuekai Guo, Pengfei Lin, Qiulei Wang, Gang Hu","doi":"10.1016/j.iintel.2024.100136","DOIUrl":"10.1016/j.iintel.2024.100136","url":null,"abstract":"<div><div>This paper explores the application of Deep Reinforcement Learning (DRL) in structural vibration control, aiming to achieve effective control of the dynamic response of building structures during natural disasters such as earthquakes. A DRL-based control strategy is proposed, and dynamic interaction between the OpenSees environment and the deep reinforcement learning environment is realized. By adjusting the parameters in the reward function, the control preference of the DRL algorithm for different metrics can be effectively modified. Additionally, an intelligent structural vibration control platform based on DRL has been developed to simplify the design process of DRL algorithms. Case studies conducted on the platform demonstrate that DRL can effectively suppress structural responses in both single-layer and multi-layer complex structures. Meanwhile, comparisons with PID and LQR algorithms that are based on linear analysis design, reveal the stability advantages of DRL in handling structural dynamic responses characterized by high nonlinearity, time delay, and large actuator output intervals.</div></div>","PeriodicalId":100791,"journal":{"name":"Journal of Infrastructure Intelligence and Resilience","volume":"4 2","pages":"Article 100136"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143146656","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0