Bridge inspection using unmanned aerial vehicles (UAV) with high performance vision sensors has received considerable attention due to its safety and reliability. As bridges become obsolete, the number of bridges that need to be inspected increases, and they require much maintenance cost. Therefore, a bridge inspection method based on UAV with vision sensors is proposed as one of the promising strategies to maintain bridges. In this paper, a crack identification method by using a commercial UAV with a high resolution vision sensor is investigated in an aging concrete bridge. First, a point cloud-based background model is generated in the preliminary flight. Then, cracks on the structural surface are detected with the deep learning algorithm, and their thickness and length are calculated. In the deep learning method, region with convolutional neural networks (R-CNN)-based transfer learning is applied. As a result, a new network for the 384 collected crack images of 256 × 256 pixel resolution is generated from the pre-trained network. A field test is conducted to verify the proposed approach, and the experimental results proved that the UAV-based bridge inspection is effective at identifying and quantifying the cracks on the structures.

Displacement measurements are useful information for various engineering applications such as structural health monitoring (SHM), earthquake engineering and system identification. Most existing displacement measurement methods are costly, labor-intensive, and have difficulties particularly when applying to full-scale civil structures because the methods require stationary reference points. Indirect estimation methods converting acceleration to displacement can be a good alternative as acceleration transducers are generally cost-effective, easy to install, and have low noise. However, the application of acceleration-based methods to full-scale civil structures such as long span bridges is challenging due to the need to install cables to connect the sensors to a base station. This article proposes a low-cost wireless displacement measurement system using acceleration. Developed with smart sensors that are low-cost, wireless, and capable of on-board computation, the wireless displacement measurement system has significant potential to impact many applications that need displacement information at multiple locations of a structure. The system implements an FIR-filter type displacement estimation algorithm that can remove low frequency drifts typically caused by numerical integration of discrete acceleration signals. To verify the accuracy and feasibility of the proposed system, laboratory tests are carried out using a shaking table and on a three storey shear building model, experimentally confirming the effectiveness of the proposed system.

This paper proposes an innovative building-integrated wind turbine (BIWT) system by directly utilizing the building skin, which is an unused and unavailable area in all conventional BIWT systems. The proposed system has been developed by combining a guide vane that is able to effectively collect the incoming wind and increase its speed and a rotor with an appropriate shape for specific conditions. To this end, several important design issues for the guide vane as well as the rotor were thoroughly investigated and accordingly addressed in this paper. A series of computational fluid dynamics (CFD) analyses was performed to determine the optimal configuration of the proposed system. Finally, it is demonstrated from performance evaluation tests that the prototype with the specially designed guide vane and rotor for the proposed BIWT system accelerates the wind speed to a sufficient level and consequently increases the power coefficient significantly. Thus, it was confirmed that the proposed system is a promising environment-friendly energy production system for urban areas.

As cables are primary load carrying members in cable-stayed bridges, monitoring the tension forces of the cables provides valuable information regarding structural soundness. Incorporating wireless smart sensors with vibration-based tension estimation methods provides an efficient means of autonomous long-term monitoring of cable tensions. This study develops a wireless cable tension monitoring system using MEMSIC’s Imote2 smart sensors. The monitoring system features autonomous operation, sustainable energy harvesting and power consumption, and remote access using the internet. To obtain the tension force, an in-network data processing strategy associated with the vibration-based tension estimation method is implemented on the Imote2-based sensor network, significantly reducing the wireless data transmission and the power consumption. The proposed monitoring system has been deployed and validated on the Jindo Bridge, a cable-stayed bridge located in South Korea.

The structural condition of bridges is generally assessed using manual visual inspection. However, this approach consumes labor, time, and capital, and produces subjective results. Therefore, industries today are using automated visual inspection approaches, which quantify and localize damages such as cracks using robots and computer vision. This paper proposes an instant damage identification and localization approach that uses an image capturing and geo-tagging system and deep convolutional neural network for crack detection. The image capturing and geo-tagging allows the geo-tagging of three-dimensional coordinates and camera pose data with bridge inspection images; the deep convolutional neural network is trained for automated crack identification. The damages extracted by the convolutional neural network are instantly transformed into a global bridge damage map, with georeferencing data acquired using the image capturing and geo-tagging. This method is experimentally validated through a lab-scale test on a wall and a field test on a bridge to demonstrate the performance of the instant damage map.