Application of UAVs for assessment of bridge infrastructure

The shortcomings of classical methods for inspection of transport infrastructure objects have led to the development of more efficient, more reliable, faster and cheaper procedures for condition assessment and load-bearing capacity and service life estimation of objects. In this context, different autonomous systems developed in the last decade have the most notable role and their development is continuously speeding up. This paper provides a state of the art review of the unmanned aerial vehicles application for structural inspection with a focus on bridges. The paper comprises the following: a review of the current regulations prescribing the types and frequency of inspections; a review of the current classical inspection methods with their advantages and disadvantages; analysis of advantages and disadvantages in application of unmanned aerial vehicles for bridge inspections and a review of the equipment commonly used in their development.

UAV-Based Bridge Inspection via Transfer Learning

As bridge inspection becomes more advanced and more ubiquitous, artificial intelligence (AI) techniques, such as machine and deep learning, could offer suitable solutions to the nation’s problems of overdue bridge inspections. AI coupling with various data that can be captured by unmanned aerial vehicles (UAVs) enables fully automated bridge inspections. The key to the success of automated bridge inspection is a model capable of detecting failures from UAV data like images and films. In this context, this paper investigates the performances of state-of-the-art convolutional neural networks (CNNs) through transfer learning for crack detection in UAV-based bridge inspection. The performance of different CNN models is evaluated via UAV-based inspection of Skodsberg Bridge, located in eastern Norway. The low-level features are extracted in the last layers of the CNN models and these layers are trained using 19,023 crack and non-crack images. There is always a trade-off between the number of trainable parameters that CNN models need to learn for each specific task and the number of non-trainable parameters that come from transfer learning. Therefore, selecting the optimized amount of transfer learning is a challenging task and, as there is not enough research in this area, it will be studied in this paper. Moreover, UAV-based bridge inception images require specific attention to establish a suitable dataset as the input of CNN models that are trained on homogenous images. However, in the real implementation of CNN models in UAV-based bridge inspection images, there are always heterogeneities and noises, such as natural and artificial effects like different luminosities, spatial positions, and colors of the elements in an image. In this study, the effects of such heterogeneities on the performance of CNN models via transfer learning are examined. The results demonstrate that with a simplified image cropping technique and with minimum effort to preprocess images, CNN models can identify crack elements from non-crack elements with 81% accuracy. Moreover, the results show that heterogeneities inherent in UAV-based bridge inspection data significantly affect the performance of CNN models with an average 32.6% decrease of accuracy of the CNN models. It is also found that deeper CNN models do not provide higher accuracy compared to the shallower CNN models when the number of images for adoption to a specific task, in this case crack detection, is not large enough; in this study, 19,023 images and shallower models outperform the deeper models.

Integrating Unmanned Aircraft Systems into State Department of Transportation Highway Bridge Inspection Procedures: Challenges, Implications, and Lessons Learned

Rapid proliferation of small, unmanned aircraft systems (UAS) promises to revolutionize traditional methods used to carry out civil engineering surveys and analyses and conduct physical infrastructure inspections. One of the most promising areas of implementation of innovative UAS technology includes the integration of UAS into current state Department of Transportation (DOT) bridge inspections. While regular bridge inspections are paramount for road user safety, many traditional inspection methods and procedures are cumbersome, expensive, and time consuming; present significant hazards to both the traveling public and the inspection personnel; and are disruptive to normal operations of the transportation facilities. The results of recent studies indicate that UAS can serve as a useful tool in many highway bridge inspection procedures, while significantly reducing costs and time and improving safety. The major factors that affect the success of integrating UAS into the bridge inspection process relate to selection of the proper types of UAS platforms and avionics, data collection sensors and processing software, as well as conduct of task-specific pilot training. The paper provides an examination of current standard bridge inspection procedures and protocols currently carried out by state DOTs; an evaluation of state DOT experiences with the integration of UAS technology into bridge inspections; and an assessment of the issues and challenges associated with this technology. It is expected that this paper will be of interest to a wide range of stakeholders representing state and federal governments, academia, and industry.

Towards Autonomous Bridge Inspection: Sensor Mounting Using Aerial Manipulators

Periodic bridge inspections are required every several years to determine the state of a bridge. Most commonly, the inspection is performed using specialized trucks allowing human inspectors to review the conditions underneath the bridge, which requires a road closure. The aim of this paper was to use aerial manipulators to mount sensors on the bridge to collect the necessary data, thus eliminating the need for the road closure. To do so, a two-step approach is proposed: an unmanned aerial vehicle (UAV) equipped with a pressurized canister sprays the first glue component onto the target area; afterward, the aerial manipulator detects the precise location of the sprayed area, and mounts the required sensor coated with the second glue component. The visual detection is based on an Red Green Blue - Depth (RGB-D) sensor and provides the target position and orientation. A trajectory is then planned based on the detected contact point, and it is executed through the adaptive impedance control capable of achieving and maintaining a desired force reference. Such an approach allows for the two glue components to form a solid bond. The described pipeline is validated in a simulation environment while the visual detection is tested in an experimental environment.

Quality Evaluation of Digital Twins Generated Based on UAV Photogrammetry and TLS: Bridge Case Study

In the current modern era of information and technology, emerging remote advancements have been widely established for detailed virtual inspections and assessments of infrastructure assets, especially bridges. These technologies are capable of creating an accurate digital representation of the existing assets, commonly known as the digital twins. Digital twins are suitable alternatives to in-person and on-site based assessments that can provide safer, cheaper, more reliable, and less distributive bridge inspections. In the case of bridge monitoring, Unmanned Aerial Vehicle (UAV) photogrammetry and Terrestrial Laser Scanning (TLS) are among the most common advanced technologies that hold the potential to provide qualitative digital models; however, the research is still lacking a reliable methodology to evaluate the generated point clouds in terms of quality and geometric accuracy for a bridge size case study. Therefore, this paper aims to provide a comprehensive methodology along with a thorough bridge case study to evaluate two digital point clouds developed from an existing Australian heritage bridge via both UAV-based photogrammetry and TLS. In this regard, a range of proposed approaches were employed to compare point clouds in terms of points’ distribution, level of outlier noise, data completeness, surface deviation, and geometric accuracy. The comparative results of this case study not only proved the capability and applicability of the proposed methodology and approaches in evaluating these two voluminous point clouds, but they also exhibited a higher level of point density and more acceptable agreements with as-is measurements in TLS-based point clouds subjected to the implementation of a precise data capture and a 3D reconstruction model.

Application of Unmanned Aerial Systems for Bridge Inspection

Unmanned aerial systems (UAS) are experiencing tremendous growth in both the technological advancement of the systems themselves and the expansion of practical uses for the systems. One application for this system includes the use of UAS as a tool in support of bridge inspections. The ability to fly UAS into positions difficult to reach by an inspector has the potential to save time, reduce costs, and improve safety. An increasing number of bridge owners are exploring the use of UAS for bridge inspections through pilot studies and early adoption as an integral part of their inspection processes. This study aims to enhance the industry awareness and knowledge base of stakeholders in bridge inspection processes. This paper presents the aircraft and sensors used to assist or augment inspections, the data needs of the bridge owners that can be provided through the use of UAS, and the means and methods by which the bridge owner, or the organization supporting the bridge owner, can manage the tremendous amount of data that can be collected by sensors deployed on UAS during an inspection.

QUALITY ASSURANCE DAN QUALITY CONTROL PEMERIKSAAN JEMBATAN DENGAN APLIKASI INVI-J

Bridge inspection aims to determine the condition of the bridge, so that the bridge manager can determine the appropriate action. Bridge inspection using the INVI-J application makes it easy to implement and store data, but requires a quality assurance and quality control. In this study, data from questionnaires and interviews were used to complete the quality assurance and quality control of bridge inspections with the INVI-J application in the regions of Central Java and the Special Region of Yogyakarta. The results of the evaluation of the audit report data showed 95% for completeness of the data, 33% for the suitability of the documentation, and 78% for the suitability of the examination results. Evaluation of the field inspection gives a conformity value of 47% at level 1 and 40% at level 2. Evaluation of the inspection report data provides a higher level of conformity than the evaluation of independent inspection data. Keywords: bridge inspection; INVI-J application; quality assurance; quality control. Abstrak Pemeriksaan jembatan bertujuan untuk mengetahui kondisi jembatan, sehingga pengelola jembatan dapat menentukan tindakan yang tepat. Pemeriksaan jembatan menggunakan aplikasi INVI-J memudahkan pelaksanaan dan penyimpanan data, tetapi memerlukan suatu Quality assurance dan quality control. Pada studi ini, data hasil kuesioner dan wawancara digunakan untuk melengkapi quality assurance dan quality control pemeriksaan jembatan dengan aplikasi INVI-J di wilayah-wilayah Jawa Tengah dan Daerah Istimewa Yogyakarta. Hasil evaluasi terhadap data laporan pemeriksaan menunjukkan capaian 95% untuk kelengkapan data, 33% untuk kesesuaian dokumentasi, dan 78% untuk kesesuaian hasil pemeriksaan. Evaluasi terhadap pemeriksaan lapangan memberikan nilai kesesuaian 47 % pada level 1 dan 40% pada level 2. Evaluasi terhadap data inspection report memberikan tingkat kesesuaian yang lebih tinggi dibandingkan dengan evaluasi terhadap data independent inspection. Kata-kata kunci: pemeriksaan jembatan; aplikasi INVI-J; quality assurance; quality control.

Benchmarking Unmanned Aerial Systems-Assisted Inspection of Steel Bridges for Fatigue Cracks

Inspection agencies have been increasingly implementing unmanned aerial systems (UAS) for bridge inspections. Currently, UAS are typically used for long-range monitoring and surveillance tasks, but bridge managers are hopeful that they may be utilized for detailed inspection, such as condition assessments and the inspection of fracture critical members (FCMs) in the near future. As an assistive tool for visual inspections, the accuracy of UAS-assisted inspections is unknown. This study investigates the relationship between the characteristics of the individual inspectors and a set of performance metrics associated with UAS-assisted FCM inspections. Four bridge inspectors used a UAS to inspect a series of full-sized bridge specimens with known fatigue cracks. The inspection videos were later shared with 19 bridge inspectors for a desk review. The performance of each inspector was evaluated and compared with the results from 30 hands-on inspections of the same specimens. The results showed that an inspector’s past experience with UAS, licensure, and academic degree could have a significant influence on one or more of the three defined performance metrics. The comparison between the results of the UAS-assisted inspections and the hands-on inspections revealed that crack detection was comparable. However, the hands-on inspections were more accurate.