• The Transactions of the Korea Information Processing Society
• /
• v.13 no.3
• /
• pp.130-139
• /
• 2024

Artificial intelligence models are being used to detect facility anomalies using physics data such as vibration, current, and temperature for predictive maintenance in the manufacturing industry. Since the types of facility anomalies, such as facility defects and failures, anomaly detection methods using autoencoder-based unsupervised learning models have been mainly applied. Normal or abnormal facility conditions can be effectively classified using the reconstruction error of the autoencoder, but there is a limit to identifying facility anomalies specifically. When facility anomalies such as unbalance, misalignment, and looseness occur, the facility vibration frequency shows a pattern different from the normal state in a specific frequency range. This paper presents an N-segmentation anomaly detection method that performs anomaly detection by dividing the entire vibration frequency range into N regions. Experiments on nine kinds of anomaly data with different frequencies and amplitudes using vibration data from a compressor showed better performance when N-segmentation was applied. The proposed method helps materialize them after detecting facility anomalies.

• Journal of the KSME
• /
• v.54 no.7
• /
• pp.28-33
• /
• 2014

최근 풍력에너지 발전기술이 해상 풍력 및 대형 풍력으로 천이되어 감에 따라 더 향상된 신뢰성 기술을 요구하고 있고, 풍력 블레이드는 풍력발전시스템에서 고장 빈도가 비교적 낮지 않고, 고장 발생 시 심각도가 상대적으로 높아 신뢰성을 고려해야 하는 부품이다. 블레이드 제작 생산 과정과 사용 중에 발생하는 손상 및 결함은 신뢰성의 심각성에 큰 영향을 미치고 있어 본 기술에서는 블레이드에서 발생할 수 있는 결함 유형, 결함을 탐지하는 기술 그리고 신뢰성을 평가하는 시험/평가 기술에 대하여 소개하고자 한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.10c
• /
• pp.391-393
• /
• 2003

본 논문은 다양한 환경변화에 적응하는 무선 통신 기술인 SDR시스템에서 소프트웨어 다운로드 과정을 마친 후 소프트웨어 모듈들을 사용자의 요구 또는 환경에 맞게 유연한 재구성을 할 수 있도록 설계하고 재구성 과정에서 발생할 수 있는 다양한 고장이나 결함을 탐지하여 그에 대한 안전한 복구 과정을 통해 전체 시스템의 신뢰성과 가용성을 향상시키는 결함허용 방식의 모듈재구성 메커니즘을 제안한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2002.11b
• /
• pp.921-924
• /
• 2002

기존의 보안 관점에서의 정보보호는 암호화, 인증과 접근제어를 이용하여 권한없는 접근을 방지하는 부분과 침입탐지와 같은 수동적인 관점에서 많이 연구되었다. 그러나 프로그램의 계속적인 취약성이 발견됨에 따라 보다 적극적인 방어 개념인 정보 생존성에 대한 연구도 활발히 이루어지고 있다. 본 논문에서는 정보 생존성에서 네트워크 관점에서 고장 또한 침입에 의한 결함에도 지속적인 네트워크 서비스를 제공할 수 있는 결함허용 네트워크에 대한 아키텍처를 제시한다.

• Proceedings of the Korean Nuclear Society Conference
• /
• 2004.10a
• /
• pp.633-634
• /
• 2004

• Journal of the Korean Society for Nondestructive Testing
• /
• v.34 no.5
• /
• pp.356-361
• /
• 2014

The eddy current testing performance directly affects the results of a steam generator tube integrity assessment because the integrity assessment of defected tubes is conducted based on eddy current testing results. This means that it may not be possible to accurately discriminate between adjacent flaws. This paper presents an investigation on the resolution of rotating pancake coils with multiple cracks and the effects on the structural integrity assessment of steam generator tubes.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.2
• /
• pp.561-568
• /
• 2023

Various defects occur in concrete structures due to internal and external environments. If there is a defect, it is important to efficiently identify and maintain it because there is a problem with the structural safety of concrete. However, recent deep learning research has focused on cracks in concrete, and studies on exfoliation and contamination are lacking. In this study, focusing on exfoliation and contamination, which are difficult to label, four models were developed and their performance evaluated through unlabelling method, filtering method, the convergence of transfer learning based k-means clustering. As a result of the analysis, the convergence model classified the defects in the most detail and could increase the efficiency compared to direct labeling. It is hoped that the results of this study will contribute to the development of deep learning models for various types of defects that are difficult to label in the future.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.586-588
• /
• 2022

산업용 설비의 결함을 예측하기 위해 기기에 탑재된 다양한 센서의 시계열 데이터를 이용한 결함 진단 연구가 확대되고 있다. 센서의 시계열 데이터는 값의 특성이 명확하지 않을 경우, 특징 추출이 제한적이지만, 주파수 영역으로 변환하면 진폭, 피크 주파수 등 데이터의 정보를 다각도로 담고 있어 특성을 추출하는 데에 이점이 있다. 따라서, 본 논문은 FFT(Fast Fourier Transform) 기법을 이용해 분해된 데이터를 조합하여 학습에 적용하는 선택적 FFT 기법을 제안한다. 제안 기법은 협동 로봇의 진동 신호를 이용한 결함 진단에 적용하였으며, 기존 결함 진단 정확도 대비 최대 41.81% 향상된 성능을 보였다.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.41 no.5
• /
• pp.401-407
• /
• 2017

This paper describes wavenumber filtering for damage detection using single-frequency standing wave excitation and laser scanning sensing. An embedded piezoelectric sensor generates ultrasonic standing waves, and the responses are measured using a laser Doppler vibrometer and mirror tilting device. After scanning, newly developed damage detection techniques based on wavenumber filtering are applied to the full standing wave field. To demonstrate the performance of the proposed techniques, several experiments were performed on composite plates with delamination and aluminum plates with corrosion damage. The results demonstrated that the developed techniques could be applied to various structures to localize the damage, with the potential to improve the damage detection capability at a high interrogation speed.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.41 no.8
• /
• pp.729-736
• /
• 2017

In this study, the physics-based model and machine learning technique were used to conduct model-assisted probability of detection (MAPOD) experiments. The possibility of using in-service cracked parts was also investigated. Bolt hole shaped specimens with fatigue crack on the hole surface were inspected using eddy current inspection. Owing to MAPOD, the number of experimental factors decreased significantly. The uncertainty in the crack length measurement for in-service cracked parts was considered by the application of Monte Carlo simulation.