Explore the vast range of titles available.

Automated pavement distress recognition is a key step in smart infrastructure assessment. Advances in deep learning and computer vision have improved the automated recognition of pavement distresses in road surface images. This task remains challenging due to the high variation of defects in shapes and sizes, demanding a better incorporation of contextual information into deep networks. In this paper, we show that an attention-based multi-scale convolutional neural network (A+MCNN) improves the automated classification of common distress and non-distress objects in pavement images by (i) encoding contextual information through multi-scale input tiles and (ii) employing a mid-fusion approach with an attention module for heterogeneous image contexts from different input scales. A+MCNN is trained and tested with four distress classes (crack, crack seal, patch, pothole), five non-distress classes (joint, marker, manhole cover, curbing, shoulder), and two pavement classes (asphalt, concrete). A+MCNN is compared with four deep classifiers that are widely used in transportation applications and a generic CNN classifier (as the control model). The results show that A+MCNN consistently outperforms the baselines by 1∼26% on average in terms of the F-score. A comprehensive discussion is also presented regarding how these classifiers perform differently on different road objects, which has been rarely addressed in the existing literature.

Automated recognition of road surface objects is vital for efficient and reliable road condition assessment. Despite recent advances in developing computer vision algorithms, it is still challenging to analyze road images due to the low contrast, background noises, object diversity, and variety of lighting conditions. Motivated by the need for an improved pavement objects classification, we present Dual Attention Convolutional Neural Network (DACNN) to improve the performance of multiclass classification using intensity and range images collected with 3D laser imaging devices. DACNN fuses heterogeneous information in intensity and range images to enhance distinguishing foreground from background, as well as to improve object classification in noisy images under various illumination conditions. DACNN also leverages multiscale input images by capturing contextual information for object classification with different sizes and shapes. DACNN contains an attention mechanism that (i) considers semantic interdependencies in spatial and channel dimensions and (ii) adaptively fuses scale-specific and mode-specific features so that each feature has its own level of contribution to the final decision. As a practical engineering project, dataset are collected from road surfaces using 3D laser imaging. DACNN is compared with four deep classifiers that are widely used in transportation applications. Experiments show that DACNN consistently outperforms the baselines by 22–35% on average in terms of the F-score. A comprehensive discussion is also presented regarding computational costs and how robustly the investigated classifiers perform on each road object.

Summary Data are used from three relatively large‐scale experimental soil‐foundation‐superstructure interaction (SFSI) systems to develop reduced‐order computational models for response prediction and change‐detection relevant to structural health monitoring and computational mechanics. The three systems under consideration consist of identical superstructures with: (i) fixed base; (ii) box foundation; and (iii) pile foundation. The three SFSI systems were developed and experimentally tested at Tongji University. In the first part of the study, a computational time‐marching prediction framework is proposed by incorporating trained neural network(s) within an ordinary differential equation solver and dynamically predicting the response (i.e., displacement and velocity) of the SFSI systems to various earthquake excitations. Two approaches are investigated: global approach and subsystem approach. Both approaches are tested and validated with linear and nonlinear systems, and their respective pros and cons are discussed. In the second part of the study, the trained neural networks from the global approach are further used for change‐detection in the SFSI systems. The detected changes in the systems are then quantified through a measure of a normalized error index. Challenges related to the physical interpretation of the quantified changes in the SFSI systems are addressed and discussed. It is shown that the general procedures adopted in this paper provide a robust nonlinear model that is reliable for computational studies, as well as furnishing a robust tool for detecting and quantifying inherent change in the system. Copyright © 2014 John Wiley & Sons, Ltd.

This paper presents the bridge cable inspection robot developed in Korea. Two types of the cable inspection robots were developed for cable-suspension bridges and cable-stayed bridge. The design of the robot system and performance of the NDT techniques associated with the cable inspection robot are discussed. A review on recent advances in emerging robot-based inspection technologies for bridge cables and current bridge cable inspection methods is also presented.

The distribution of fiber orientation is an important factor in determining the mechanical properties of fiber-reinforced concrete. This study proposes a new image analysis technique for improving the evaluation accuracy of fiber orientation distribution in the sectional image of fiber-reinforced concrete. A series of tests on the accuracy of fiber detection and the estimation performance of fiber orientation was performed on artificial fiber images to assess the validity of the proposed technique. The validation test results showed that the proposed technique estimates the distribution of fiber orientation more accurately than the direct measurement of fiber orientation by image analysis.

A nonparametric, data-driven methodology of monitoring for geotechnical structures subject to long-term environmental change is discussed. Avoiding physical assumptions or excessive simplification of the monitored structures, the nonparametric monitoring methodology presented in this paper provides reliable performance-related information particularly when the collection of sensor data is limited. For the validation of the nonparametric methodology, a field case study was performed using a full-scale retaining wall, which had been monitored for three years using three tilt gauges. Using the very limited sensor data, it is demonstrated that important performance-related information, such as drainage performance and sensor damage, could be disentangled from significant daily, seasonal and multiyear environmental variations. Extensive literature review on recent developments of parametric and nonparametric data processing techniques for geotechnical applications is also presented.

The development of effective structural health monitoring (SHM) methodologies is imperative for the efficient maintenance of important structures in aerospace, mechanical and civil engineering. Based on reliable condition assessment, the owners of monitored structures can expect two important benefits: to avoid catastrophic accidents by detecting various types of structural deterioration during operation, and to establish efficient maintenance means and time schedule to reduce maintenance costs. A vibration-based SHM methodology is evaluated for change detection in nonlinear systems that can be frequently seen in many engineering fields. The proposed methodology is advantageous over existing SHM methodologies regarding the following aspects: feasible to detect small changes in complex nonlinear systems, possible to make physical interpretation of detected changes, and possible to quantify the uncertainty associated with the change detection. A series of analytical and experimental studies was performed to investigate various important issues in modeling and monitoring of uncertain nonlinear systems. Different parametric and non-parametric identification methods were compared for monitoring purpose using full-scale nonlinear viscous dampers for seismic mitigation in civil structures. Then, the effects of uncertainty on change detection performance were investigated. Two types of uncertainty were studied: measurement uncertainty and system characteristic uncertainty. For measurement uncertainty, three different types of full-scale nonlinear viscous dampers were used to validate the proposed SHM methodology when the dampers' response was polluted with random noise. For system characteristic uncertainty, a semi-active magneto-rheological damper whose system characteristics were determined through user controllable input current was used. Statistical pattern recognition methods were studied to detect relatively small changes in nonlinear systems with different uncertainty types. The Bootstrap method, a statistical data resampling technique, was also studied to estimate the uncertainty bounds of change detection when the measurement data are insufficient for reliable statistical inference. A web-based real-time bridge monitoring system was developed and used for a forensic study involving a cargo ship collision with the Vincent Thomas Bridge, a critical suspension bridge in the metropolitan Los Angeles region.