http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
구조물의 6자유도 변위 측정을 위한 비주얼 서보잉 기반 양립형 구조 광 로봇 시스템
전해민(Haemin Jeon),방유석(Yuseok Bang),김한근(Hangeun Kim),명현(Hyun Myung) 제어로봇시스템학회 2011 제어·로봇·시스템학회 논문지 Vol.17 No.10
This study aims to demonstrate the feasibility of a visual servoing-based paired structured light (SL) robot for estimating structural displacement under various external loads. The former paired SL robot, which was proposed in the previous study, was composed of two screens facing with each other, each with one or two lasers and a camera. It was found that the paired SL robot could estimate the translational and rotational displacement each in 3-DOF with high accuracy and low cost. However, the measurable range is fairly limited due to the limited screen size. In this paper, therefore, a visual servoing-based 2-DOF manipulator which controls the pose of lasers is introduced. By controlling the positions of the projected laser points to be on the screen, the proposed robot can estimate the displacement regardless of the screen size. We performed various simulations and experimental tests to verify the performance of the newly proposed robot. The results show that the proposed system overcomes the range limitation of the former system and it can be utilized to accurately estimate the structural displacement.
실시간 구조물 변위 모니터링을 위한 증분형 변위 측정 알고리즘
전해민(Haemin Jeon),신재욱(Jae-Uk Shin),명완철(Wancheol Myeong),명현(Hyun Myung) 제어로봇시스템학회 2012 제어·로봇·시스템학회 논문지 Vol.18 No.6
The purpose of this paper is to suggest IDE (Incremental Displacement Estimation) algorithm for the previously proposed visually servoed paired structured light system. The system is composed of two sides facing with each other, each with one or two lasers with a 2-DOF manipulator, a camera, and a screen. The 6-DOF displacement between two sides can be estimated by calculating the positions of the projected laser beams and rotation angles of the manipulators. In the previous study, Newton-Raphson or EKF (Extended Kalman Filter) has been used as an estimation algorithm. Although the various experimental tests have validated the performance of the system and estimation algorithms, the computation time is relatively long since aforementioned algorithms are iterative methods. Therefore, in this paper, a non-iterative incremental displacement estimation algorithm which updates the previously estimated displacement with a difference of the previous and the current observed data is introduced. To verify the performance of the algorithm, experimental tests have been performed. The results show that the proposed non-iterative algorithm estimates the displacement with the same level of accuracy compared to the EKF with multiple iterations with significantly less computation time.
k-근접 이웃 및 비전센서를 활용한 프리팹 강구조물 조립 성능 평가 기술
방현태,유병준,전해민,Bang, Hyuntae,Yu, Byeongjun,Jeon, Haemin 한국전산구조공학회 2022 한국전산구조공학회논문집 Vol.35 No.5
본 논문에서는 프리팹 구조물의 품질관리를 위한 딥러닝 및 비전센서 기반의 조립 성능 평가 모델을 개발하였다. 조립부 검출을 위해 인코더-디코더 형식의 네트워크와 수용 영역 블록 합성곱 모듈을 적용한 딥러닝 모델을 사용하였다. 검출된 조립부 영역 내의 볼트홀을 검출하고, 볼트홀의 위치 값을 산정하여 k-근접 이웃 기반 모델을 사용하여 조립 품질을 평가하였다. 제안된 기법의 성능을 검증하기 위해 조립부 모형을 3D 프린팅을 이용하여 제작하여 조립부 검출 및 조립 성능 예측 모델의 성능을 검증하였다. 성능 검증 결과 높은 정밀도로 조립부를 검출하였으며, 검출된 조립부내의 볼트홀의 위치를 바탕으로 프리팹 구조물의 조립 성능을 5% 이하의 판별 오차로 평가할 수 있음을 확인하였다. In this study, we developed a deep learning and vision sensor-based assembly performance evaluation method isfor prefabricated steel structures. The assembly parts were segmented using a modified version of the receptive field block convolution module inspired by the eccentric function of the human visual system. The quality of the assembly was evaluated by detecting the bolt holes in the segmented assembly part and calculating the bolt hole positions. To validate the performance of the evaluation, models of standard and defective assembly parts were produced using a 3D printer. The assembly part segmentation network was trained based on the 3D model images captured from a vision sensor. The sbolt hole positions in the segmented assembly image were calculated using image processing techniques, and the assembly performance evaluation using the k-nearest neighbor algorithm was verified. The experimental results show that the assembly parts were segmented with high precision, and the assembly performance based on the positions of the bolt holes in the detected assembly part was evaluated with a classification error of less than 5%.
트랜스포머 알고리즘을 활용한 탄소나노튜브와 플라이애시 혼입 시멘트 복합재료의 압저항 특성 분석
김종혁,방진호,전해민,Jonghyeok Kim,Jinho Bang,Haemin Jeon 한국전산구조공학회 2023 한국전산구조공학회논문집 Vol.36 No.6
본 논문에서는 시멘트에 탄소나노튜브를 혼입하여 전기 전도성을 향상시킨 복합재료의 압저항 특성을 딥러닝 기반 트랜스포머 알고리즘을 적용하여 분석하였다. 훈련 데이터 확보를 위한 실험수행을 병행하였으며, 기존 연구문헌을 참조하여 배합설정, 시편제작, 화학조성 분석, 압저항 성능측정 실험을 수행하였다. 특히 본 연구에서는 탄소나노튜브 혼입 시편뿐 아니라 플라이애시를 바인더 대비 50% 대체한 시편에 대한 제작 및 성능평가를 함께 수행하여, 전도성 시멘트 복합재료의 압저항 특성 향상 가능성을 탐구하였다. 실험결과, 플라이애시 대체 바인더의 경우 보다 안정적인 압저항 특성결과가 관찰되었으며, 측정된 데이터의 80%를 이용하여 트랜스포머 모델을 훈련시키고 나머지 20%를 통해 검증하였다. 해석 결과는 실험적 측정과 대체로 부합하였으며, 평균 절대 오차 및 평균 제곱근 오차는 각각 0.069~0.074와 0.124~0.132을 나타내었다. In this study, the piezoresistive properties of cementitious composites enhanced with carbon nanotubes for improved electrical conductivity were analyzed using a deep learning-based transformer algorithm. Experimental execution was performed in parallel for acquisition of training data. Previous studies on mixture design, specimen fabrication, chemical composition analysis, and piezoresistive performance testing are also reviewed in this paper. Notably, specimens in which fly ash substituted 50% of the binder material were fabricated and evaluated in this study, in addition to carbon nanotube-infused specimens, thereby exploring the potential enhancement of piezoresistive characteristics in conductive cementitious materials. The experimental results showed more stable piezoresistive responses in specimens with fly-ash substituted binder. The transformer model was trained using 80% of the gathered data, with the remaining 20% employed for validation. The analytical outcomes were generally consistent with empirical measurements, yielding an average absolute error and root mean square error between 0.069 to 0.074 and 0.124 to 0.132, respectively.
김인호 ( Kim In-ho ),전해민 ( Jeon Haemin ),정형조 ( Jung Hyung-jo ) 한국구조물진단유지관리공학회 2018 한국구조물진단유지관리공학회 학술발표대회 논문집 Vol.22 No.1
Bridge inspection based unmanned aerial vehicle (UAV) has received considerable attention due to its several advantages such as reliability and safety as well as saving time and cost. An unmanned inspection equipment for bridge inspection is composed of UAV and imaging devices such as RGB cameras and infrared cameras. However, many challenging issues should be solved in order to apply this technology to the field. In this paper, an UAV based crack detection method is investigated. To detect the cracks, the image processing techniques with deep learning algorithm are used. To build the spatial information of aging bridge, 3D point cloud based background model is generated.