• Journal of the Society of Disaster Information
• /
• v.17 no.3
• /
• pp.556-567
• /
• 2021

Purpose: In this study, various methods of deep learning-based automatic damage analysis technology were reviewed based on images taken through Unmanned Aerial Vehicle to more efficiently and reliably inspect the exterior inspection and inspection of railway bridges using Unmanned Aerial Vehicle. Method: A deep learning analysis model was created by defining damage items based on the acquired images and extracting deep learning data. In addition, the model that learned the damage images for cracks, concrete and paint scaling·spalling, leakage, and Reinforcement exposure among damage of railway bridges was applied and tested with the results of automatic damage analysis. Result: As a result of the analysis, a method with an average detection recall of 95% or more was confirmed. This analysis technology enables more objective and accurate damage detection compared to the existing visual inspection results. Conclusion: through the developed technology in this study, it is expected that it will be possible to analysis more accurate results, shorter time and reduce costs by using the automatic damage analysis technology using Unmanned Aerial Vehicle in railway maintenance.

• Journal of the Architectural Institute of Korea Structure & Construction
• /
• v.35 no.2
• /
• pp.3-11
• /
• 2019

The recent earthquake of Pohang (M5.4) and the Gyeongju earthquake (M5.8) suggested the possibility of a strong earthquake in Korea and reminded us that the Korea is no longer an earthquake-safe zone. In the disaster recovery stage in a disaster like an earthquake, the investigation of the damage situation and the safety assessment of the building serve to provide important information for the initial action such as establishment of the recovery strategy and rescue of the survivor. However, the research that depends on manpower can not cope with the difficulty of processing a large number of doses in a short time, and the expertise of the manpower must be taken into consideration, which may result in delayed initial action. In this study, we propose an rapid safety evaluation technique of building using unmanned aerial vehicle which evaluates the performance and safety of buildings by integrating conventional safety inspection method with unmanned aerial vehicle technology and developed evaluation method of each evaluation factor. In order to verify this, the buildings damaged by the earthquake in Pohang were checked and compared using this system. The results are consistent with the results of the existing emergency earthquake risk assessment. As a result, the possibility of checking the emergency safety using the unmanned aerial vehicle for the damaged structures in case of a large-scale disaster such as an earthquake was confirmed.

• Journal of the Korean Solar Energy Society
• /
• v.32 no.spc3
• /
• pp.262-268
• /
• 2012

In the recent research technical solutions have been studied to integrate renewable energy into unmanned aerial vehicles to use it as the main power source. As the weight of the aerial vehicle body is essential for its performance, we consider to use light-weight solar cell technology. Furthermore fuel cells are also integrated create a highly energy-efficient aerial robot. In this paper, construction concept and software design of the tilt-rotor aerial vehicle GAORI is introduced which uses solar cells and fuel cells as power source. The future work direction and prognosis are discussed.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.35 no.1
• /
• pp.39-46
• /
• 2012

An unmanned aerial vehicle (UAV) is a powered aerial vehicle that does not carry a human operator, uses aerodynamic forces to provide vehicle lift, can fly autonomously or be piloted remotely, can be expendable or recoverable, and can carry a lethal or non-lethal payload. An UAV is very important weapon system and is currently being employed in many military missions (surveillance, reconnaissance, communication relay, targeting, strike, etc.) in the war. To accomplish UAV's missions, guarantee of survivability should be preceded. The main objective of this study is a local path planning to maximize survivability for UAV on the battlefield of dynamic threats (obstacles, surface-to-air missiles, radar etc.). A local path planning is capable of producing a new path in response to environmental changes. This study suggests a $Smart$ $A^*$ (Smart A-star) algorithm for local path planning. The local path planned by $Smart$ $A^*$ algorithm is compared with the results of existing algorithms ($A^*$ $Replanner$, $D^*$) and evaluated performance of $Smart$ $A^*$ algorithm. The result of suggested algorithm gives the better solutions when compared with existing algorithms.

• IE interfaces
• /
• v.24 no.4
• /
• pp.304-313
• /
• 2011

An Unmanned Aerial Vehicle(UAV) is a powered pilotless aircraft, which is controlled remotely or autonomously. UAVs are currently employed in many military missions(surveillance, reconnaissance, communication relay, targeting, strike etc.) and a number of civilian applications(communication service, broadcast service, traffic control support, monitoring, measurement etc.). For accomplishing the UAV's missions, guarantee of survivability should be preceded. The main objective of this study is the path planning to maximize survivability for UAV based on 3-dimensional environment. A mathematical programming model is suggested by using MRPP(Most Reliable Path Problem) and solved by transforming MRPP into SPP(Shortest Path Problem). This study also suggests a $A^*PS$ algorithm based on 3-dimensional environment to UAV's path planning. According to comparison result of the suggested algorithm and SPP algorithms (Dijkstra, $A^*$ algorithm), the suggested algorithm gives better solution than SPP algorithms.

• International Journal of Aeronautical and Space Sciences
• /
• v.11 no.4
• /
• pp.313-318
• /
• 2010

The power plant system of a tilt rotor unmanned aerial vehicle (UAV) was verified by the Ironbird ground test, which considerably reduces cost and risk during the developmental stages. The function and performance of the engine, drive line, nacelle conversion, and rotor systems were evaluated using a building block test approach. The Ironbird test concept facilitates the discovery of potential faults in earlier stages of the testing period. As a result, the developmental testing period could effectively be shortened. The measured test data acquired through a ground control and data acquisition system exhibited satisfactory results which meet the developmental specifications of a tilt rotor UAV.

• Journal of the Korean Society for Aviation and Aeronautics
• /
• v.21 no.1
• /
• pp.23-29
• /
• 2013

This paper presents a tracking filter of radar beacon system (RBS) for automatic takeoff and landing of an unmanned aerial vehicle. The proposed tracking filter is designed as the decoupled tracking filter to reduce the computational burden. Also, an adaptive estimation method of the measurement error covariance is proposed to provide an improved tracking performance compared to the conventional decoupled tracking filter whenever the accuracy of RBS observations is degraded. 100 times Monte Carlo runs performed to analyze the performance of the proposed tracking filter in case of normal operation and degraded operations, respectively. The simulation results show that the proposed tracking filter provides the improved tracking accuracy in comparison with the conventional decoupled tracking filter.

• Journal of the Korean Society for Aviation and Aeronautics
• /
• v.15 no.3
• /
• pp.33-45
• /
• 2007

The collision avoidance maneuver flight simulation for tilt rotor unmanned aerial vehicle was performed by time-accurate numerical integration method based on wind tunnel test data. Five representative collision avoidance maneuvers were simulated under constraints of aerodynamic stall, propulsion power, structural load, and control actuator capability. The collision avoidance performances of the maneuvers were compared by the computed collision avoidance times. The sensitivities of initial flight speed and collision zone shape on the collision avoidance time were investigated. From these results, it was found that the moderate pull-up turn maneuver defined using moderate pitch and maximum roll controls within simulation constraints is the most robust and efficient collision avoidance maneuver under the various flight speeds and collision object shapes in the tilt rotor UAV applications.

• Journal of the Korea Safety Management & Science
• /
• v.13 no.2
• /
• pp.103-113
• /
• 2011

This research is to select a path planning algorithm to maximize survivability for Unmanned Aerial Vehicle(UAV). An UAV is a powered pilotless aircraft, which is controlled remotely or autonomously. UAVs are currently employed in many military missions(surveillance, reconnaissance, communication relay, targeting, strike etc.) and a number of civilian applications(communication service, broadcast service, traffic control support, monitoring, measurement etc.). In this research, a mathematical programming model is suggested by using MRPP(Most Reliable Path Problem) and verified by using ILOG CPLEX. A path planning algorithm for UAV is selected by comparing of SPP(Shortest Path Problem) algorithms which transfer MRPP into SPP.

• Proceedings of the Korean Society of Propulsion Engineers Conference
• /
• 2010.05a
• /
• pp.226-230
• /
• 2010

In this paper, the performance of an electric powered small Unmanned Aerial Vehicle which has a battery and electric motor is analysed. Aerodynamic data is obtained through flight test and flight performance is predicted. As a result, we present the optimum flight speed for the maximum endurance and predict endurance and range according to the variation of flight speed.