Tram Bui-Ngoc, Duy-Khuong Ly, Tam T. Truong, Chanachai Thongchom, T. Nguyen-Thoi
{"title":"基于深度神经网络的代用模型,用于识别具有不完整噪声测量值的全尺寸结构中的损伤","authors":"Tram Bui-Ngoc, Duy-Khuong Ly, Tam T. Truong, Chanachai Thongchom, T. Nguyen-Thoi","doi":"10.1007/s11709-024-1060-8","DOIUrl":null,"url":null,"abstract":"<p>The paper introduces a novel approach for detecting structural damage in full-scale structures using surrogate models generated from incomplete modal data and deep neural networks (DNNs). A significant challenge in this field is the limited availability of measurement data for full-scale structures, which is addressed in this paper by generating data sets using a reduced finite element (FE) model constructed by SAP2000 software and the MATLAB programming loop. The surrogate models are trained using response data obtained from the monitored structure through a limited number of measurement devices. The proposed approach involves training a single surrogate model that can quickly predict the location and severity of damage for all potential scenarios. To achieve the most generalized surrogate model, the study explores different types of layers and hyperparameters of the training algorithm and employs state-of-the-art techniques to avoid overfitting and to accelerate the training process. The approach’s effectiveness, efficiency, and applicability are demonstrated by two numerical examples. The study also verifies the robustness of the proposed approach on data sets with sparse and noisy measured data. Overall, the proposed approach is a promising alternative to traditional approaches that rely on FE model updating and optimization algorithms, which can be computationally intensive. This approach also shows potential for broader applications in structural damage detection.</p>","PeriodicalId":12476,"journal":{"name":"Frontiers of Structural and Civil Engineering","volume":"2016 1","pages":""},"PeriodicalIF":2.9000,"publicationDate":"2024-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A deep neural network based surrogate model for damage identification in full-scale structures with incomplete noisy measurements\",\"authors\":\"Tram Bui-Ngoc, Duy-Khuong Ly, Tam T. Truong, Chanachai Thongchom, T. Nguyen-Thoi\",\"doi\":\"10.1007/s11709-024-1060-8\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>The paper introduces a novel approach for detecting structural damage in full-scale structures using surrogate models generated from incomplete modal data and deep neural networks (DNNs). A significant challenge in this field is the limited availability of measurement data for full-scale structures, which is addressed in this paper by generating data sets using a reduced finite element (FE) model constructed by SAP2000 software and the MATLAB programming loop. The surrogate models are trained using response data obtained from the monitored structure through a limited number of measurement devices. The proposed approach involves training a single surrogate model that can quickly predict the location and severity of damage for all potential scenarios. To achieve the most generalized surrogate model, the study explores different types of layers and hyperparameters of the training algorithm and employs state-of-the-art techniques to avoid overfitting and to accelerate the training process. The approach’s effectiveness, efficiency, and applicability are demonstrated by two numerical examples. The study also verifies the robustness of the proposed approach on data sets with sparse and noisy measured data. Overall, the proposed approach is a promising alternative to traditional approaches that rely on FE model updating and optimization algorithms, which can be computationally intensive. This approach also shows potential for broader applications in structural damage detection.</p>\",\"PeriodicalId\":12476,\"journal\":{\"name\":\"Frontiers of Structural and Civil Engineering\",\"volume\":\"2016 1\",\"pages\":\"\"},\"PeriodicalIF\":2.9000,\"publicationDate\":\"2024-05-28\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Frontiers of Structural and Civil Engineering\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://doi.org/10.1007/s11709-024-1060-8\",\"RegionNum\":3,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"ENGINEERING, CIVIL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Frontiers of Structural and Civil Engineering","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1007/s11709-024-1060-8","RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, CIVIL","Score":null,"Total":0}
引用次数: 0
摘要
本文介绍了一种利用不完整模态数据生成的代用模型和深度神经网络(DNN)检测全尺寸结构中结构损伤的新方法。该领域面临的一个重大挑战是全尺寸结构的测量数据有限,本文通过使用 SAP2000 软件和 MATLAB 编程环构建的简化有限元 (FE) 模型生成数据集来解决这一问题。代用模型是通过数量有限的测量设备从被监测结构中获取的响应数据进行训练的。所提出的方法包括训练一个单一的代用模型,该模型可以快速预测所有潜在情况下的损坏位置和严重程度。为了获得最具通用性的代用模型,该研究探索了训练算法的不同层类型和超参数,并采用了最先进的技术来避免过度拟合和加速训练过程。该方法的有效性、效率和适用性通过两个数值示例得到了证明。这项研究还验证了所提方法在测量数据稀疏、噪声大的数据集上的鲁棒性。总之,与依赖 FE 模型更新和优化算法的传统方法相比,所提出的方法是一种很有前途的替代方法,因为传统方法的计算量很大。这种方法还显示出在结构损伤检测领域更广泛应用的潜力。
A deep neural network based surrogate model for damage identification in full-scale structures with incomplete noisy measurements
The paper introduces a novel approach for detecting structural damage in full-scale structures using surrogate models generated from incomplete modal data and deep neural networks (DNNs). A significant challenge in this field is the limited availability of measurement data for full-scale structures, which is addressed in this paper by generating data sets using a reduced finite element (FE) model constructed by SAP2000 software and the MATLAB programming loop. The surrogate models are trained using response data obtained from the monitored structure through a limited number of measurement devices. The proposed approach involves training a single surrogate model that can quickly predict the location and severity of damage for all potential scenarios. To achieve the most generalized surrogate model, the study explores different types of layers and hyperparameters of the training algorithm and employs state-of-the-art techniques to avoid overfitting and to accelerate the training process. The approach’s effectiveness, efficiency, and applicability are demonstrated by two numerical examples. The study also verifies the robustness of the proposed approach on data sets with sparse and noisy measured data. Overall, the proposed approach is a promising alternative to traditional approaches that rely on FE model updating and optimization algorithms, which can be computationally intensive. This approach also shows potential for broader applications in structural damage detection.
期刊介绍:
Frontiers of Structural and Civil Engineering is an international journal that publishes original research papers, review articles and case studies related to civil and structural engineering. Topics include but are not limited to the latest developments in building and bridge structures, geotechnical engineering, hydraulic engineering, coastal engineering, and transport engineering. Case studies that demonstrate the successful applications of cutting-edge research technologies are welcome. The journal also promotes and publishes interdisciplinary research and applications connecting civil engineering and other disciplines, such as bio-, info-, nano- and social sciences and technology. Manuscripts submitted for publication will be subject to a stringent peer review.