• Smart Structures and Systems
• /
• 제30권6호
• /
• pp.673-686
• /
• 2022

Deep learning algorithms for Structural Health Monitoring (SHM) have been extracting the interest of researchers and engineers. These algorithms commonly used loss functions and evaluation indices like the mean square error (MSE) which were not originally designed for SHM problems. An updated loss function which was specifically constructed for deep-learning-based structural damage detection problems has been proposed in this study. By tuning the coefficients of the loss function, the weights for damage localization and quantification can be adapted to the real situation and the deep learning network can avoid unnecessary iterations on damage localization and focus on the damage severity identification. To prove efficiency of the proposed method, structural damage detection using convolutional neural networks (CNNs) was conducted on a truss bridge model. Results showed that the validation curve with the updated loss function converged faster than the traditional MSE. Data augmentation was conducted to improve the anti-noise ability of the proposed method. For reducing the training time, the normalized modal strain energy change (NMSEC) was extracted, and the principal component analysis (PCA) was adopted for dimension reduction. The results showed that the training time was reduced by 90% and the damage identification accuracy could also have a slight increase. Furthermore, the effect of different modes and elements on the training dataset was also analyzed. The proposed method could greatly improve the performance for structural damage detection on both the training time and detection accuracy.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• 제35권4호
• /
• pp.779-789
• /
• 2015

Because cable-supported bridges have long spans and large members, their movements and geometrical changes by temperatures tend to be bigger than those of small or medium-sized bridges. Therefore, it is important for maintenance engineers to monitor and assess the effect of temperature on the cable-supported bridges. To evaluate how much the superstructure expands or contracts when subjected to changes in temperature is the first step for the maintenance. Thermal movements of a cable-stayed bridge in service are evaluated by using long-term temperatures and displacements data. Displacements data are obtained from extensometers and newly installed GNSS (Global Navigation Satellite System) receivers on the bridge. Based on the statistical data such as air temperatures, each sensor's temperatures, average temperatures and effective temperatures, correlation analysis between temperatures and displacements has been performed. Average temperatures or effective temperatures are most suitable for the evaluation of thermal movements. From linear regression analysis between effective temperatures and displacements, the variation rate's of displacement to temperature have been calculated. From additional regression analysis between expansion length's and variation rate's of displacement to temperature, the thermal expansion coefficient and neutral point have been estimated. Comparing these parameters with theoretical and analytical results, a practical procedure for evaluating the real thermal behaviors of the cable-supported bridges is proposed.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• 제30권6호
• /
• pp.541-547
• /
• 2017

Climate change has become the main cause of the exacerbation in natural disasters. Social Overhead Capital(SOC) structure needs to be checked for displacement and crack periodically to prevent damage and the collapse caused by natural disaster and ensure the safety. For efficient structure maintenance, the optical image technology is applied to the Structure Health Monitoring(SHM). However, optical image is sensitive to environmental factors. So it is necessary to verify its validity. In this paper, the accuracy of estimating the vertical displacement was verified with respect to environmental condition such as natural light, measurement distance, and the number of image sheets. The result of experiments showed that the effect of natural light on accuracy of estimating vertical displacement was the greatest of all. The measurement angle which was affected by the change in measurement distance was also important to check the vertical displacement. These findings will be taken into account by applying appropriate environmental condition to minimize errors when the bridge was measured by camera. It will also enable the application of optical images to the SHM.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 한국전산구조공학회 2009년도 정기 학술대회
• /
• pp.106-109
• /
• 2009

본 논문에서는 교량의 상태감시 테스트베드 구축을 위한 한-미 국제공동연구의 현황 및 활동 내용들을 논하였다. 이 국제공동연구는 최첨단 센서와 구조건전도 모니터링 방법의 유용성 및 통합화하는데 그 목적을 두고 있다. 테스트베드 구축을 위해 가속도계과 동적 FBG 센서, 압전 센서 등과 같은 스마트 센서를 사용하였으며, 무선 데이터수집 시스템이 도입되었다. 교량 모니터링 기법으로는 압전 센서 및 EM센서로부터 취합된 데이터를 이용하여 국부손상검색을 수행하였으며, 가속도계, 동적 FBG센서 및 이미지 프로세싱을 이용하여 진동기반 전역손상검색을 수행하였다. 테스트베드 교량으로는 PC박스 거더교, 강상자형교, 강판형교, 사장교의 4가지 형식의 교량이 사용되었다. 테스트베드 교량에 최신 이동통신 인터넷 연결기술을 이용하여 교량에 설치된 센서로부터 취합된 데이터와 모니터링 시스템으로부터 교량의 상태를 실시간 감시할 수 있는 네트워크 시스템을 구축하였다. 이러한 원거리 이동통신시스템을 통하여 구조물의 건전성 평가결과를 실시간으로 전송 및 분석할 수 있도록 하였다.

• Structural Engineering and Mechanics
• /
• 제31권3호
• /
• pp.333-347
• /
• 2009

Due to structural complicacy, structural health monitoring for civil engineering needs more accurate and effectual methods of damage identification. This study aims to import multi-source information fusion (MSIF) into structural damage diagnosis to improve the validity of damage detection. Firstly, the essential theory and applied mathematic methods of MSIF are introduced. And then, the structural damage identification method based on multi-mode information fusion is put forward. Later, on the basis of a numerical simulation of a concrete continuous box beam bridge, it is obviously indicated that the improved modal strain energy method based on multi-mode information fusion has nicer sensitivity to structural initial damage and favorable robusticity to noise. Compared with the classical modal strain energy method, this damage identification method needs much less modal information to detect structural initial damage. When the noise intensity is less than or equal to 10%, this method can identify structural initial damage well and truly. In a word, this structural damage identification method based on multi-mode information fusion has better effects of structural damage identification and good practicability to actual structures.

• Smart Structures and Systems
• /
• 제14권2호
• /
• pp.105-128
• /
• 2014

The stochastic damage locating vector (SDLV) method has been studied extensively in recent years because of its potential to determine the location of damage in structures without the need for measuring the input excitation. The SDLV method has been shown to be a particularly useful tool for damage localization in steel truss bridges through numerical simulation and experimental validation. However, several issues still need clarification. For example, two methods have been suggested for determining the observation matrix C identified for the structural system; yet little guidance has been provided regarding the conditions under which the respective formulations should be used. Additionally, the specific layout of the sensors to achieve effective performance with the SDLV method and the associated relationship to the specific type of truss structure have yet to be explored. Moreover, how the location of truss members influences the damage localization results should be studied. In this paper, these three issues are first investigated through numerical simulation and subsequently the main results are validated experimentally. The results of this paper provide guidance on the effective use of the SDLV method.

• Smart Structures and Systems
• /
• 제29권1호
• /
• pp.141-151
• /
• 2022

In recent years, the industry and research communities have focused on developing autonomous crack inspection approaches, which mainly include image acquisition and crack detection. In these approaches, mobile devices such as cameras, drones or smartphones are utilized as sensing platforms to acquire structural images, and the deep learning (DL)-based methods are being developed as important crack detection approaches. However, the process of image acquisition and collection is time-consuming, which delays the inspection. Also, the present mobile devices such as smartphones can be not only a sensing platform but also a computing platform that can be embedded with deep neural networks (DNNs) to conduct on-site crack detection. Due to the limited computing resources of mobile devices, the size of the DNNs should be reduced to improve the computational efficiency. In this study, an architecture called pruned crack recognition network (PCR-Net) was developed for the detection of structural cracks. A dataset containing 11000 images was established based on the raw images from bridge inspections. A pruning method was introduced to reduce the size of the base architecture for the optimization of the model size. Comparative studies were conducted with image processing techniques (IPTs) and other DNNs for the evaluation of the performance of the proposed PCR-Net. Furthermore, a modularly designed framework that integrated the PCR-Net was developed to realize a DL-based crack detection application for smartphones. Finally, on-site crack detection experiments were carried out to validate the performance of the developed system of smartphone-based detection of structural cracks.

• Smart Structures and Systems
• /
• 제29권1호
• /
• pp.153-166
• /
• 2022

Identifying fine cracks in steel bridge facilities is a challenging task of structural health monitoring (SHM). This study proposed an end-to-end crack image segmentation framework based on a one-step Convolutional Neural Network (CNN) for pixel-level object recognition with high accuracy. To particularly address the challenges arising from small object detection in complex background, efforts were made in loss function selection aiming at sample imbalance and module modification in order to improve the generalization ability on complicated images. Specifically, loss functions were compared among alternatives including the Binary Cross Entropy (BCE), Focal, Tversky and Dice loss, with the last three specialized for biased sample distribution. Structural modifications with dilated convolution, Spatial Pyramid Pooling (SPP) and Feature Pyramid Network (FPN) were also performed to form a new backbone termed CrackDet. Models of various loss functions and feature extraction modules were trained on crack images and tested on full-scale images collected on steel box girders. The CNN model incorporated the classic U-Net as its backbone, and Dice loss as its loss function achieved the highest mean Intersection-over-Union (mIoU) of 0.7571 on full-scale pictures. In contrast, the best performance on cropped crack images was achieved by integrating CrackDet with Dice loss at a mIoU of 0.7670.

• Smart Structures and Systems
• /
• 제29권1호
• /
• pp.63-75
• /
• 2022

The raw data collected by structural health monitoring (SHM) systems may suffer multiple patterns of anomalies, which pose a significant barrier for an automatic and accurate structural condition assessment. Therefore, the detection and classification of these anomalies is an essential pre-processing step for SHM systems. However, the heterogeneous data patterns, scarce anomalous samples and severe class imbalance make data anomaly detection difficult. In this regard, this study proposes a convolutional neural network-based data anomaly detection method. The time and frequency domains data are transferred as images and used as the input of the neural network for training. ResNet18 is adopted as the feature extractor to avoid training with massive labelled data. In addition, the focal loss function is adopted to soften the class imbalance-induced classification bias. The effectiveness of the proposed method is validated using acceleration data collected in a long-span cable-stayed bridge. The proposed approach detects and classifies data anomalies with high accuracy.

• Smart Structures and Systems
• /
• 제18권5호
• /
• pp.885-909
• /
• 2016

Advances in low-cost wireless sensing have made instrumentation of large civil infrastructure systems with dense arrays of wireless sensors possible. A critical issue with regard to effective use of the information harvested from these sensors is synchronized sensing. Although a number of synchronization methods have been developed, most provide only clock synchronization. Synchronized sensing requires not only clock synchronization among wireless nodes, but also synchronization of the data. Existing synchronization protocols are generally limited to networks of modest size in which all sensor nodes are within a limited distance from a central base station. The scale of civil infrastructure is often too large to be covered by a single wireless sensor network. Multiple independent networks have been installed, and post-facto synchronization schemes have been developed and applied with some success. In this paper, we present a new approach to achieving synchronized sensing among multiple networks using the Pulse-Per-Second signals from low-cost GPS receivers. The method is implemented and verified on the Imote2 sensor platform using TinyOS to achieve $50{\mu}s$ synchronization accuracy of the measured data for multiple networks. These results demonstrate that the proposed approach is highly-scalable, realizing precise synchronized sensing that is necessary for effective structural health monitoring.