Real-time geometry identification of moving ships by computer vision techniques in bridge area

Shunlong Li,Yapeng Guo,Yang Xu,Zhonglong Li 국제구조공학회 2019 Smart Structures and Systems, An International Jou Vol.23 No.4

As part of a structural health monitoring system, the relative geometric relationship between a ship and bridge has been recognized as important for bridge authorities and ship owners to avoid ship–bridge collision. This study proposes a novel computer vision method for the real-time geometric parameter identification of moving ships based on a single shot multibox detector (SSD) by using transfer learning techniques and monocular vision. The identification framework consists of ship detection (coarse scale) and geometric parameter calculation (fine scale) modules. For the ship detection, the SSD, which is a deep learning algorithm, was employed and fine-tuned by ship image samples downloaded from the Internet to obtain the rectangle regions of interest in the coarse scale. Subsequently, for the geometric parameter calculation, an accurate ship contour is created using morphological operations within the saturation channel in hue, saturation, and value color space. Furthermore, a local coordinate system was constructed using projective geometry transformation to calculate the geometric parameters of ships, such as width, length, height, localization, and velocity. The application of the proposed method to in situ video images, obtained from cameras set on the girder of the Wuhan Yangtze River Bridge above the shipping channel, confirmed the efficiency, accuracy, and effectiveness of the proposed method.

Dynamic deflection monitoring of high-speed railway bridges with the optimal inclinometer sensor placement

Shunlong Li,Xin Wang,Hongzhan Liu,Yi Zhuo,Wei Su,Hao Di 국제구조공학회 2020 Smart Structures and Systems, An International Jou Vol.26 No.5

Dynamic deflection monitoring is an essential and critical part of structural health monitoring for high-speed railway bridges. Two critical problems need to be addressed when using inclinometer sensors for such applications. These include constructing a general representation model of inclination-deflection and addressing the ill-posed inverse problem to obtain the accurate dynamic deflection. This paper provides a dynamic deflection monitoring method with the placement of optimal inclinometer sensors for high-speed railway bridges. The deflection shapes are reconstructed using the inclination-deflection transformation model based on the differential relationship between the inclination and displacement mode shape matrix. The proposed optimal sensor configuration can be used to select inclination-deflection transformation models that meet the required accuracy and stability from all possible sensor locations. In this study, the condition number and information entropy are employed to measure the ill-condition of the selected mode shape matrix and evaluate the prediction performance of different sensor configurations. The particle swarm optimization algorithm, genetic algorithm, and artificial fish swarm algorithm are used to optimize the sensor position placement. Numerical simulation and experimental validation results of a 5-span high-speed railway bridge show that the reconstructed deflection shapes agree well with those of the real bridge.

Optimal sensor placement for cable force monitoring using spatial correlation analysis and bond energy algorithm

Shunlong Li,Jialin Dong,Wei Lu,Hui Li,Wencheng Xu,Yao Jin 국제구조공학회 2017 Smart Structures and Systems, An International Jou Vol.20 No.6

Cable force monitoring is an essential and critical part of the safety evaluation of cable-supported bridges. A reasonable cable force monitoring scheme, particularly, sensor placement related to accurate safety assessment and budget costsaving becomes a major concern of bridge administrative authorities. This paper presents optimal sensor placement for cable force monitoring by selecting representative sensor positions, which consider the spatial correlativeness existing in the cable group. The limited sensors would be utilized for maximizing useful information from the monitored bridges. The maximum information coefficient (MIC), mutual information (MI) based kernel density estimation, as well as Pearson coefficients, were all employed to detect potential spatial correlation in the cable group. Compared with the Pearson coefficient and MIC, the mutual information is more suitable for identifying the association existing in cable group and thus, is selected to describe the spatial relevance in this study. Then, the bond energy algorithm, which collects clusters based on the relationship of surrounding elements, is used for the optimal placement of cable sensors. Several optimal placement strategies are discussed with different correlation thresholds for the cable group of Nanjing No.3 Yangtze River Bridge, verifying the effectiveness of the proposed method.

Dominant failure modes identification and structural system reliability analysis for a long-span arch bridge

Xin Gao,Shunlong Li 국제구조공학회 2017 Structural Engineering and Mechanics, An Int'l Jou Vol.63 No.6

Failure of a redundant long-span bridge is often described by innumerable failure modes, which make the structural system reliability analysis become a computationally intractable work. In this paper, an innovative procedure is proposed to efficiently identify the dominant failure modes and quantify the structural reliability for a long-span bridge system. The procedure is programmed by ANSYS and MATLAB. Considering the correlation between failure paths, a new branch and bound operation criteria is applied to the traditional stage critical strength branch and bound algorithm. Computational effort can be saved by ignoring the redundant failure paths as early as possible. The reliability of dominant failure mode is computed by FORM, since the limit state function of failure mode can be expressed by the final stage critical strength. PNET method and FORM for system are suggested to be the suitable calculation method for the bridge system reliability. By applying the procedure to a CFST arch bridge, the proposed method is demonstrated suitable to the system reliability analysis for long-span bridge structure.

Condition assessment for high-speed railway bridges based on train-induced strain response

Zhonglong Li,Shunlong Li,Jia Lv,Hui Li 국제구조공학회 2015 Structural Engineering and Mechanics, An Int'l Jou Vol.54 No.2

This paper presents the non-destructive evaluation of a high-speed railway bridge usingtrain-induced strain responses. Based on the train-track-bridge interaction analysis, the strain responses of ahigh-speed railway bridge under moving trains with different operation status could be calculated. The traininduced strain responses could be divided into two parts: the force vibration stage and the free vibrationstage. The strain-displacement relationship is analysed and used for deriving critical displacements fromtheoretical stain measurements at a forced vibration stage. The derived displacements would be suitable forthe condition assessment of the bridge through design specifications defined indexes and would show certainlimits to the practical application. Thus, the damage identification of high-speed railways, such as thestiffness degradation location, needs to be done by comparing the measured strain response under movingtrains in different states because the vehicle types of high-speed railway are relatively clear and definite. Themonitored strain responses at the free vibration stage, after trains pass through the bridge, would be used foridentifying the strain modes. The relationship between and the degradation degree and the strain modeshapes shows certain rules for the widely used simply supported beam bridges. The numerical simulationproves simple and effective for the proposed method to locate and quantify the stiffness degradation.

Condition assessment for high-speed railway bridges based on train-induced strain response

Li, Zhonglong,Li, Shunlong,Lv, Jia,Li, Hui Techno-Press 2015 Structural Engineering and Mechanics, An Int'l Jou Vol.54 No.2

This paper presents the non-destructive evaluation of a high-speed railway bridge using train-induced strain responses. Based on the train-track-bridge interaction analysis, the strain responses of a high-speed railway bridge under moving trains with different operation status could be calculated. The train induced strain responses could be divided into two parts: the force vibration stage and the free vibration stage. The strain-displacement relationship is analysed and used for deriving critical displacements from theoretical stain measurements at a forced vibration stage. The derived displacements would be suitable for the condition assessment of the bridge through design specifications defined indexes and would show certain limits to the practical application. Thus, the damage identification of high-speed railways, such as the stiffness degradation location, needs to be done by comparing the measured strain response under moving trains in different states because the vehicle types of high-speed railway are relatively clear and definite. The monitored strain responses at the free vibration stage, after trains pass through the bridge, would be used for identifying the strain modes. The relationship between and the degradation degree and the strain mode shapes shows certain rules for the widely used simply supported beam bridges. The numerical simulation proves simple and effective for the proposed method to locate and quantify the stiffness degradation.

Indirect displacement monitoring of high-speed railway box girders consider bending and torsion coupling effects

Xin Wang,Zhonglong Li,Yi Zhuo,Hao Di,Jianfeng Wei,Yuchen Li,Shunlong Li 국제구조공학회 2021 Smart Structures and Systems, An International Jou Vol.28 No.6

The dynamic displacement is considered to be an important indicator of structural safety, and becomes an indispensable part of Structural Health Monitoring (SHM) system for high-speed railway bridges. This paper proposes an indirect strain based dynamic displacement reconstruction methodology for high-speed railway box girders. For the typical box girders under eccentric train load, the plane section assumption and elementary beam theory is no longer applicable due to the bend-torsion coupling effects. The monitored strain was decoupled into bend and torsion induced strain, pre-trained multi-output support vector regression (M-SVR) model was employed for such decoupling process considering the sensor layout cost and reconstruction accuracy. The decoupled strained based displacement could be reconstructed respectively using box girder plate element analysis and mode superposition principle. For the transformation modal matrix has a significant impact on the reconstructed displacement accuracy, the modal order would be optimized using particle swarm algorithm (PSO), aiming to minimize the ill conditioned degree of transformation modal matrix and the displacement reconstruction error. Numerical simulation and dynamic load testing results show that the reconstructed displacement was in good agreement with the simulated or measured results, which verifies the validity and accuracy of the algorithm proposed in this paper.

Vision-based full-field panorama generation by UAV using GPS data and feature points filtering

Yapeng Guo,Yang Xu,Haowei Niu,Zhonglong Li,Yuhui E.,Xinghua Jiao,Shunlong Li 국제구조공학회 2020 Smart Structures and Systems, An International Jou Vol.25 No.5

To meet the urgent requirements of safety surveillance from civil engineering management authorities, this study proposes a refined and efficient approach to generate full-field high-resolution panorama of construction sites using cameraamounted UAV (Unmanned Aerial Vehicle). GPS (Global Position System) information extraction for pre-registration, feature points filtering for efficient registration and optimal seaming line seeking for fusion are performed in sequence to form the full-field panorama generation framework. Advantages of the proposed method are as follows. First, GPS information can sort images for pre-registration, avoiding inefficient repeated pairwise calculations and matching. Second, the feature points are filtered according to the characteristics of the construction site images to reduce the amount of calculation. The proposed framework is validated on a road construction site and results demonstrate that it can generate an accurate and high-quality full-site panorama for the safety supervision in a much efficient manner.