• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.32 no.4
• /
• pp.265-272
• /
• 2019

In this paper, a vision-based deep learning algorithm and image processing method are proposed to detect bolt-loosening in steel connections. To achieve this objective, the following approaches are implemented. First, a bolt-loosening detection method that includes regional convolutional neural network(RCNN)-based deep learning algorithm and Hough line transform(HLT)-based image processing algorithm are designed. The RCNN-based deep learning algorithm is developed to identify and crop bolts in a connection image. The HLT-based image processing algorithm is designed to estimate the bolt angles from the cropped bolt images. Then, the proposed vision-based method is evaluated for verifying bolt-loosening detection in a lab-scale girder connection. The accuracy of the RCNN-based bolt detector and HLT-based bolt angle estimator are examined with respect to various perspective distortions.

• Proceedings of the Korean Society of Propulsion Engineers Conference
• /
• 2010.11a
• /
• pp.523-526
• /
• 2010

In this study, we demonstrated a development of a non-releasing bolt which is fastened with a target by expanding a certain area of a bolt body. Being released a bolt causes many problems in a field where bolts are used. In order to figure out the problems, currently, many types of a non-releasing bolt have been developed and have been using. Unfortunately, however, they do not perfectly function not to be released. Therefore, the structures builded with bolts have many problems caused by external stress such as vibration and shock, and thus the bolts have to be regularly tightened for maintenance. With the important factors of internal geometry, the amount of explosive, and the firing pin, we developed a technology which could control the expansion degree of a certain area on a bolt body. Based on the results, it was founded that the performance of non-releasing was linearly proportional to the degree of body expansion.

• Journal of the Korean Society of Propulsion Engineers
• /
• v.16 no.3
• /
• pp.24-33
• /
• 2012

The present work has suggested the design methods of the bolt body for making the anti-releasing bolts and provided the changed properties of the bolt body after explosion. To prove this work, two models of the anti-releasing bolts, M10 and M20, are produced and the expansion properties of each model are experimentally obtained. This study verify that the expansion of the bolt body is reproducible and the expansion rate could be controlled by the combination of the design factors and the anti-releasing characteristics could be quantified. It also could provide the data that would be needed to make the bolts with the anti-releasing effect.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.46 no.12
• /
• pp.1004-1011
• /
• 2018

Recently, pyrotechnic separation nut has attracted a considerable attention because of its shock reduction effect among various pyrotechnic mechanical devices. However, its bolt loosening behavior under transverse vibration has not been studied sufficiently, since segmented nuts are utilized instead of conventional nut in pyrotechnic separation nut. With the background, bolt loosening analyses are carried out referring to Junker vibration test. The analysis procedure consists of two steps. The first step is the bolt fastening step, screwing the bolt by fastening torque. The second step is the bolt loosening step under transverse vibration. Through the procedure, bolt loosening behaviors are obtained, and the effect of clearance on loosening behavior is closely investigated for reliable design of pyrotechnic separation nut.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.41 no.4
• /
• pp.257-262
• /
• 2017

As the size of electric products such as mobile phones and smart watches decrease, the bolts used to assemble these products should also be miniaturized. A miniature-sized bolt has to provide sufficient joining torque and anti-releasing torque to keep the components together. We studied a serrated bolt as a candidate for a miniature-sized fastener to increase the anti-releasing torque. In a serrated bolt, a serrated shape is formed on the bottom surface of the bolt head to create an obstacle to releasing. In this study, finite element analyses for the joining and releasing of bolts were carried out, and the anti-releasing performance was predicted. Based on the results of analyses using various numbers of serrations and fastening depths, the effects of the number of serrations and fastening depth on the anti-releasing performance were investigated.

• Journal of Korean Society of Steel Construction
• /
• v.23 no.5
• /
• pp.629-636
• /
• 2011

This paper describes the smart structural system that uses smart materials for real-time monitoring and active control of bolted joints in steel structures. The impedance-based structural health monitoring (SHM) techniques, which utilize the electro-mechanical coupling property of piezoelectric materials, was used to detect loose bolts in bolted joints. By monitoring the measured electrical impedance and comparing it with the measured baseline, a bolt loosening damage was detected. The damage was evaluated quantitatively using the damage metrics in conductance signature with respect to the healthy states. When loosening damage was detected in the bolted joint, the external heater actuated the shape memory alloy (SMA) washer. Then the heated SMA washer expanded axially and adjusted the bolt tension to restore the lost torque. An experiment was conducted by integrating the piezoelectric-material-based SHM function and the SMA-based active control function on a bolted joint, after which the performance of thesmart self-healing joint system was investigated.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.3
• /
• pp.1117-1121
• /
• 2011

The movable bracket structure, which is an apparatus for supplying electric power to a running electric locomotive, is applied by a repeated load during the passage of the electric locomotive. Such a repeated load becomes an excitation source that causes screws constituting the movable bracket structure to be loosened. This study was conducted on the causes and countermeasures of the bolt loosening caused by the repeated vibration using a computer simulation. As the result, a simulation model was constructed to enable the dynamic analysis of the movable bracket structure. It could be found that the principal excitation frequency range for the bolt loosening of the movable bracket structure was less than 200 Hz. In addition, the bolts are prevented from being loosened by increasing stiffness of H beams. The vibration mode of a lower band bracket is found to be triggered in a frequency range between 300 and 600 Hz. And the increase in stiffness of the lower band bracket exhibits the effect to avoid the bolt loosening at a frequency range of 200 Hz or more.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.36 no.4
• /
• pp.221-232
• /
• 2023

This paper presents a novel convolutional neural network (CNN)-based approach for predicting bolt clamping force in the early bolt loosening state of bolted structures. The approach entails tightening eight bolts with different clamping forces and generating frequency responses, which are then used to create a similarity map. This map quantifies the magnitude and shape similarity between the frequency responses and the initial model in a fully fastened state. Krylov subspace-based model order reduction is employed to efficiently handle the large amount of frequency response data. The CNN model incorporates a regression output layer to predict the clamping forces of the bolts. Its performance is evaluated by training the network by using various amounts of training data and convolutional layers. The input data for the model are derived from the magnitude and shape similarity map obtained from the frequency responses. The results demonstrate the diagnostic potential and effectiveness of the proposed approach in detecting early bolt loosening. Accurate bolt clamping force predictions in the early loosening state can thus be achieved by utilizing the frequency response data and CNN model. The findings afford valuable insights into the application of CNNs for assessing the integrity of bolted structures.

• 열병합발전
• /
• s.72
• /
• pp.4-16
• /
• 2009

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 2010.04a
• /
• pp.666-669
• /
• 2010

여러 가지 지하시설물 중 국가 주요 자원의 수송망을 책임지는 주요구조물인 수도관, 가스관등의 배관구조물은 접근이 쉽지 않은 지하공간에 복잡하게 연결되어 있어 그 중요성에 비해 유지, 관리, 보수가 쉽지 않았다. 이러한 배관구조물을 균열, 조인트 풀림 등의 손상으로부터 보다 안전하고 효율적으로 관리하기 위하여 상시적 배관구조물 손상진단기법을 연구하였다. 이를 위해 배관 구조물 시험체에 볼트풀림, notch 등과 같은 손상에 대하여 대표적인 압전센서인 PZT와 MFC를 부착하고 임피던스기법 및 유도 초음파기법을 적용하여 볼트풀림개수, notch 손상개수 증가에 따른 출력신호를 반복 계측하였다. 객관적인 평가를 위해 계측된 신호를 신호처리기법인 웨이블렛 변환을 수행하고, RMSD 및 1-CC의 손상지수를 사용하여 구조물손상을 정량화 시켰으며 이를 토대로 구조물의 건전성의 기준이 되는 임계값을 설정함으로서 임피던스와 유도초음파 두 검색기법을 이용한 상시적 배관구조물 건전성 모니터링의 가능성을 살펴보았다.