Inspection Data Collection Research Articles

Multi-modal deep fusion for bridge condition assessment

Bridge condition rating is a challenging task as it largely depends on the experience-level of the manual inspection and therefore is prone to human errors. The inspection report often consists of a collection of images and sequences of sentences (text) explaining the condition of the considered bridge. In a routine manual bridge inspection, an inspector collects a set of images and textual descriptions of bridge components and assigns an overall condition rating (ranging between 0 and 9) based on the collected information. Unfortunately, this method of bridge inspection has been shown to yield inconsistent condition ratings that correlate with inspector experience. To improve the consistency among image-text inspection data and further predict the accordant condition ratings, this study first provides a collective image-text dataset, extracted from the collection of bridge inspection reports from the Virginia Department of Transportation. Using this dataset, we have developed novel deep learning-base methods for an automatic bridge condition rating prediction based on data fusion between the textual and visual data from the collected report sets.Our proposed multi modal deep fusion approach constructs visual and textual representations for images and sentences separately using appropriate encoding functions, and then fuses representations of images and text to enhance the multi-modal prediction performance of the assigned condition ratings. Moreover, we study interpretations of the deployed deep models using saliency maps to identify parts of the image-text inputs that are essential in condition rating predictions. The findings of this study point to potential improvements by leveraging consistent image-text inspection data collection as well as leveraging the proposed deep fusion model to improve the bridge condition prediction rating from both visual and textual reports.

Layout Optimization and Multi-scenes Intelligent Inspection Scheme Design Based on Substation Video Monitoring

In order to realize intelligent inspection of substation and improve inspection efficiency. This paper aims at the problems of irregular distribution, low reuse, low coverage of inspection points and waste of investment in the current substation video monitoring system. Propose a set of efficient distribution principles and methods. In view of the lack of scenario consideration in the preparation of substation inspection tasks, which leads to the lack of flexibility and poor practicability of inspection work. It is proposed to carry out multi scene inspection work according to the trigger conditions of different scenes. Through comprehensive collection of inspection data, combined with artificial intelligence algorithm, the overall perception of equipment operation status is realized. Taking a 220kV substation as an example, the scene based compilation and application based on the distribution of video monitoring system in the substation and in combination with inspection tasks. The intelligent inspection of the substation is realized to the greatest extent, which provides a certain idea for the subsequent large-scale promotion, construction and application of intelligent inspection of the substation.

Automated Unmanned Aerial Vehicle-Based Bridge Deck Delamination Detection and Quantification

Delamination is one of the most critical defects assessed during bridge deck inspections. Recently, infrared (IR) thermography has gained more attention for delamination detection since it provides fast and effective inspections with reasonable accuracy. However, point-by-point inspections with handheld IR cameras and manual data interpretation are still time consuming. In addition, manual data interpretation is highly dependent on the inspectors’ experiences. To tackle these concerns, this study conducted investigations from two perspectives to improve IR-based delamination detection: (1) data collection and (2) data interpretation. In this study, unmanned aerial vehicles (UAVs) equipped with IR sensors have been deployed to perform automated inspection data collection. Various factors have been considered to develop a preliminary UAV-based IR data collection plan. The developed data collection plan has been implemented on a full-scale bridge deck specimen at the Bridge Evaluation and Accelerated Structural Testing (BEAST) facility. Discussions and suggestions based on the results have been provided. A pixel-level deep learning method is developed for automatic delamination detection and quantification of the bridge deck. IR data collected from four real bridge decks are pixel-wise labeled and used for model calibration. The accuracy and mean intersection over union achieve 99.36%, 97.96%, 97.83% and 0.98, 0.96, 0.95 for training, validation, and testing datasets, respectively. Furthermore, an easy-to-use tool is developed based on the proposed method for practical implementation. The developed tool is validated using the BEAST specimen data. The fast and accurate implementation of the developed tool makes it a promising option for autonomous bridge deck inspection.

A Multitask Deep Learning Model for Parsing Bridge Elements and Segmenting Defect in Bridge Inspection Images

The vast network of bridges in the United States has a high requirement for maintenance and rehabilitation. The massive cost of manual visual inspection to assess bridge conditions is a burden to some extent. Advanced robots have been used to automate inspection data collection. Automating the segmentations of multiclass elements and surface defects on the elements in the large volume of inspection image data would facilitate an efficient and effective assessment of bridge conditions. Training separate single-task networks for element parsing (i.e., semantic segmentation of multiclass elements) and defect segmentation fails to incorporate the close connection between these two tasks. Both recognizable structural elements and apparent surface defects are present in the inspection images. This paper is motivated to develop a multitask deep learning model that fully uses such interdependence between bridge elements and defects to boost the model’s task performance and generalization. Furthermore, the study investigated the effectiveness of the proposed model designs for improving task performance, including feature decomposition, cross-talk sharing, and multi-objective loss function. A data set with pixel-level labels of bridge elements and corrosion was developed for model training and testing. Quantitative and qualitative results from evaluating the developed multitask deep model demonstrate its advantages over the single-task-based model not only in performance (2.59% higher mIoU on bridge parsing and 1.65% on corrosion segmentation) but also in computational time and implementation capability.

Quality estimation method for gear hobbing based on attention and adversarial transfer learning

Because the gear inspection process is time-consuming and the equipment wears easily, gear machining and inspection data collection are costly; therefore, it is difficult to collect sufficient gear machining data for deep learning training. To solve this problem, this study proposes an attention and adversarial transfer learning method based on ResNet with adaptive Coral loss (A2ResNet-aCoral) for training small-sample datasets. The method integrates sample-spatial attention and dynamic-channel attention to enhance the feature extraction ability. To realize the transfer ability, an adversarial domain structure is constructed to induce the network to extract the homogeneous features of the source and target domains. Moreover, an adaptive correlation alignment loss is proposed to shorten the distance between the source and target domains. The results of a case study indicate that A2ResNet-aCoral has good transfer ability on small sample gear hobbing signals, and the accuracy can reach 92.71%.

Automatic inspection data collection of building surface based on BIM and UAV

Conventional high-rise building surface inspection is usually inefficient and requires the inspectors to work at heights with high risk. Unmanned aerial vehicles (UAVs) carrying optical or thermal cameras are currently widely utilized as an effective tool for inspection. The UAV-based data collection, especially for unreachable inspection areas, is the basis of unmanned inspection of building surface. In addition, building information modeling (BIM) with rich geometric and semantic information can also be instrumental in building surface inspection. Therefore, this paper presented an automatic inspection method of building surface, especially for the inspection data collection, by integrating UAV and BIM. To minimize the length of UAV flight while collecting complete and high-quality image data considering the limited endurance capability, the coverage path planning problem is solved using genetic algorithm (GA). The required inspection areas are obtained from the BIM model of the target building to be inspected. To further enhance the automation of building surface inspection, the optimized UAV flight mission parameters are rapidly calculated based on the BIM model and proposed algorithm. A real office building in Shenzhen University campus is used to validate the presented automatic method. The quality of the collected inspection images using the UAV with optimized flight mission are evaluated. The results show that this method leads to time-efficient, accurate, and high-quality inspection data collection for building surface.

Inspection Data Collection Tool for Field Testing of Photovoltaic Modules in the Atacama Desert

The Atacama Desert receives the highest levels of solar irradiance in the world with an annual average of 2500 kWh/m2 for the global horizontal irradiance and 3500 kWh/m2 for the direct normal irradiance. One of the challenges is the large portion of ultraviolet light. This part of the spectrum be detrimental for the encapsulant materials, reducing their lifetime. To develop a module adapted to the Atacama Desert conditions, it is imperative to have standardized information from first-hand about the typical faults experienced by photovoltaic modules operating in the desert. This work reports on the design and implementation of the Inspection Data Collection Tool to evaluate crystalline silicon-based moules operating in desert climates. The tool brings together novel features of compatibility with current standards, efficient mobile-type instrumentation (equipment and tools), clear procedures/protocols for non-expert users and low development costs. A total of 95 modules were inspected to characterize failure/degradation issues. Three components of the solar modules were assessed: front cover glass, ethylene-vinyl acetate encapsulant and solar cells. Seven abnormalities were analyzed: Soiling, front cover glass discoloration, encapsulant delamination, hotspots, partial shading, cell fracture and faulty soldering. Soiling was the most common issue, showing correlation between dust deposition and location.

Retracted] Design and Analysis of Bridge Inspection System Based on Wireless Communication and Internet of Things Technology

The continuous development of information technology and various electronic devices has accelerated the process of informatization and digitization, enabling the development and application of the emerging technology of wireless communication and the Internet of Things. Since the continuous occurrence of vicious bridge collapse accidents in China in recent years, the problem of bridge inspection has become a hot topic among the people. At the same time, how to apply wireless communication and the Internet of Things technology to bridge inspection systems has also become a new research topic. This article mainly studies the design and analysis of bridge detection systems based on wireless communication and Internet of Things technology. In order to expand the field of bridge detection and standard management and improve the credibility and reliability of safety problem prediction and evaluation, the bridge detection system will integrate IoT sensing, internet, remote communication, digital signal analysis and processing, big data knowledge mining, big data prediction and other technologies, design and analysis of the main structure of roads and bridges, and other multifaceted knowledge fields and build a professional intelligent digital network based on bridge inspection data collection, monitoring, analysis, evaluation, and early warning. From design to use and maintenance of the bridge, a digital neural network spanning time and space throughout the life cycle is constructed to construct a digital brain with bridge sensing points as neurons. This paper uses high‐power infrared sensor equipment, satellite positioning systems, sensor equipment, and other technical equipment to achieve the purpose of data communication and exchange and realize intelligent positioning, identification, supervision, tracking, and other functions, making the wireless communication and Internet of Things reliable transmission, comprehensive perception, intelligent processing, and other capabilities very effective in the field of bridge inspection. Through the research and analysis of this article, there are more and more bridge inspection systems developed by the Internet of Things and wireless communication technology in China, and the percentage of related equipment used can reach more than 90%. The functions of the bridge inspection system are becoming more and more complete, and the results of the inspection data are also increasing.

Reliability Evaluation of Public Building: Case Study Atrium Premiere Hotel Yogyakarta, Indonesia

Accordance with Regional Regulation of Sleman Regency No 5/2011, it is important to check the reliability of existing public buildings, to know the capacity of buildings and services to consumers. The study aims to evaluate the reliability of Atrium Premiere Hotel, as one of hotels in Yogyakarta which is located on the main street of Yogyakarta. The methodology used with building inspection data collection and comparison of existing data with PUSLITBANG standard reference Housing and Settlement in 2016 on the inspection process. Building reliability check results based on architectural components, structures, utilities, accessibility, building codes and environments with percentages were 9,9%, 30%, 50%, 4,75% and 5%, respectively. The conclusion of the examination results shows that total value of Atrium Premiere Hotel reliability of 99,65%, so declared reliably.

Bridge Health Index: Study of Element Condition States and Importance Weights

The AASHTO Pontis bridge management system has been used to support network-level and project-level decision making on the condition and functional obsolescence of bridges. State departments of transportation often develop bridge inspection data collection methods, deterioration models, cost models, and other preservation analysis capabilities to comply with the requirements of the federal Government Accounting Standards Board. The bridge health index (BHI) in the Pontis bridge management system has been used in the evaluation of the condition of bridges and elements at the project and network levels. This paper investigates three issues in the computation of the BHI: the effects of using linear and nonlinear scales for the condition state weights when computing the element health index (EHI); the application of amplification weights to EHI values to emphasize bridge elements in bad condition; and the development of element weights based on element replacement costs, element long-term costs, element vulnerability to hazard risks, and a combination of these measures. Historical condition data from element-based inspection were used to evaluate these effects at the network level.

Practicing Management and Leadership

Practicing Management and Leadership

Experimentally Derived Cost-Effective Planning of Bridge Deck Rehabilitation by Steel Plate Bonding

Rehabilitation cycle is being studied in relation to life-cycle costing based on the realization that making rehabilitation cost-effective would require minimizing the necessary investment. However, the progress of an actual structure’s deterioration cannot be predicted precisely without a collection of inspection data, and therefore, at present the rehabilitation cycle is merely calculated on the idealized progressive deterioration hypothesis. In this study, the optimal life cycle of reinforced concrete deck slabs is derived from the residual life determined through a series of fatigue experiments on deck slabs cut out from existing bridges and rehabilitated afterwards. As a result, precise and cost-effective rehabilitation planning was made possible.

Multipurpose inspection task simulator

Experimentation using a computer simulation of a system has many advantages over more traditional techniques. In this project, computer graphics are used to create an inspection task simulator. The simulator allows for easy manipulation of variables known to affect inspection performance, quick construction of visual stimuli, a choice of randomly generated or intentionally input faults on the stimuli, controlled % defective, feedback options and automatic collection of inspection data. The inspection task simulator has possible applications in experimentation, training and selection of inspectors.