http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
정대진,허헌,Daejin Jeong,Heon Huh 한국인터넷방송통신학회 2024 한국인터넷방송통신학회 논문지 Vol.24 No.2
X-rays are extensively employed for non-destructive inspection, applied to packaged food, human anatomy, and industrial products. Recently, this technology has extended to inspecting batteries in electric vehicles. Given the challenge of manual inspection for a substantial volume of batteries, deep learning is leveraged to detect battery defects. However, the effectiveness of deep learning heavily depends upon data size, and acquiring authentic defective images is a difficult and time-consuming task. In this study, we use data augmentation and investigate the impact of data size on battery inspection performance. The results provide valuable insights for enhancing the capabilities of the inspection process.
이선우,허헌,SunWoo Lee,Heon Huh 한국인터넷방송통신학회 2024 한국인터넷방송통신학회 논문지 Vol.24 No.2
Since the outbreak of COVID-19, there has been a surge in sports conducted through online platforms due to the increase in remote and non-contact activities. Billiards, being suitable for online platforms, has received much attention, leading to research on detecting the position and trajectory of balls. In this paper, we propose a new method utilizing machine vision to detect the position of the balls accurately. The proposed method detects the outline of the ball using the Canny edge detection and then employs simple correlation to determine its position. This correlation-based approach offers satisfactory system performance and is easily applicable in practical systems due to its low implementation complexity and robustness to noise.
Automatic Error Correction of Position Sensors for Servo Motors via Iterative Learning
한석희,하태균,허헌,하인중,고명삼,Han, Seok-Hee,Ha, Tae-Kyoon,Huh, Heon,Ha, In-Joong,Ko, Myoung-Sam The Institute of Electronics and Information Engin 1994 전자공학회논문지-B Vol.b31 No.9
In this paper, we present an iterative learning method of compensating for position sensor error. The previously known compensation algorithms need a special perfect position sensor or a priori information about error sources, while ours does not. to our best knowledge, any iterative learning approach has not been taken for sensor error compensation. Furthermore, our iterativelearning algorithm does not have the drawbacks of the existing interativelearning control theories. To be more specivic, our algorithm learns an uncertain function itself rather than its special time-trajectory and does not reuquest the derivatives of measurement signals. Moreover, it does not require the learning system to start with the same initial condition for all iterations. To illuminate the generality and practical use of our algorithm, we give the rigorous proof for its convergence and some experimental results.
Robot Application of Electroadhesion Pads with Dual Insulation
정용진(Yongjin Jeong),김기현(Kihyun Kim),허헌(Heon Huh) Korean Society for Precision Engineering 2020 한국정밀공학회지 Vol.37 No.10
Electroadhesion has many advantages over other adhesion methods such as pneumatic, hydraulic, magnet, etc. The applications include electrostatic chucks and grippers. Recently, electroadhesion has been adopted for robots working in limited environments. The electro-adhesive climbing robots can be used for inspection and exploration in a variety of conditions. The electroadhesion robots often have a limited adhesion force. In this paper, we propose a novel pad structure improving the adhesion force. An additional insulating layer prevents the discharge from the high voltage application and increases the adhesion force per unit area. The electroadhesion forces were compared for the different pad materials and electrode structures and were partly confirmed as the theoretical model. The proposed pad was used for a climbing robot wheel. The climbing robot weighs approximately 3 kg and can manage to 3 kg of extra weight on metal walls. Experiments showed a 90-degree gradability for the climbing robot.