• Journal of the Korea institute for structural maintenance and inspection
• /
• v.23 no.7
• /
• pp.80-86
• /
• 2019

As computer performance improves, research using deep learning are being actively carried out in various fields. Recently, deep learning technology has been applying to the safety evaluation for structures. In particular, the internal blades of a turbine structure requires experienced experts and considerable time to detect surface damages because of the difficulty of separation of the blades from the structure and the dark environmental condition. This study proposes a Faster R-CNN deep learning model that can detect surface damages on the internal blades, which is one of the primary elements of the turbine structure. The deep learning model was trained using image data with dent and punch damages. The image data was also expanded using image filtering and image data generator techniques. As a result, the deep learning model showed 96.1% accuracy, 95.3% recall, and 96% precision. The value of the recall means that the proposed deep learning model could not detect the blade damages for 4.7%. The performance of the proposed damage detection system can be further improved by collecting and extending damage images in various environments, and finally it can be applicable for turbine engine maintenance.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2009.10a
• /
• pp.529-530
• /
• 2009

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2011.06a
• /
• pp.1077-1078
• /
• 2011

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.24 no.1 s.173
• /
• pp.190-195
• /
• 2000

It has been established that a crack has an important effect on the dynamic behavior of a structure. This effect depends mainly on the location and depth of the crack. To identify the location and depth of a crack in a structure. Nikolakopoulos et. al. used the intersection point of the superposed contours that correspond to the eigenfrequency caused by the crack presence. However the intersecting point of the superposed contours is not only difficult to find but also incorrect to calculate. A method is presented in this paper which uses optimization technique for the location and depth of the crack. The basic idea is to find parameters which use the structural eigenfrequencies on crack depth and location and optimization algorithm. With finite element model of the structure to calculate eigenfrequencies, it is possible to formulate the inverse problem in optimization format. Method of optimization is augmented lagrange multiplier method and search direction method is BFGS variable metric method and one dimensional search method is polynomial interpolation.

• Proceedings of the KIEE Conference
• /
• 2007.10a
• /
• pp.453-454
• /
• 2007

전력설비에 대한 부분방전 패턴인식은 결함의 차이에 따라 다양한 패턴의 차이를 보이고 있으며, 신경회로망을 비롯한 다양한 패턴인식 기법들이 적용되고 있다. 본 논문에서는 이의 일환으로 퍼지 집합 기반 퍼지뉴럴네트워크를 설계하여 초고압 XLPE 케이블 절연접속함의 모의 결합에 대해 부분방전 신호를 패턴인식하고자 한다. 부분방전 신호는 보이드 방전, 코로나 방전, 노이즈의 3개 클래스로 분류하게 되며, PRPDA 방법을 통해 556개의 입력 벡터와 3개의 출력 벡터를 가지며 총 120개의 패턴수를 가진다.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.18 no.4
• /
• pp.271-277
• /
• 1998

Nondestructive method can include both testing itself and analysis or evaluation of the testing results. Although vast amount of testing can be accomplished in a fairly short amount of time due to the advancement of electronic technology. it is really difficult matter to identify whether the indication found during testing corresponds to be a real defect. Thus, in ultrasonic testing, advanced digital signal processing techniques have been widely studied in order to identify the shape of the defect during testing, and one of the signal processing techniques, synthetic aperture focusing technique(SAFT) was tried for holes machined in carbon steel plate in this study. Result showed that signal to noise ratio has been improved considerably compared to the result from original RF signals.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.21 no.2
• /
• pp.146-153
• /
• 2011

Model based machine condition diagnosis methods are generally using a normal and many failure models which need sufficient data to train the models. However, data, especially for failure modes of interest, is very hard to get in real applications. So their industrial applications are either severely limited or impossible when the failure models cannot be trained. In this paper, continuous hidden Markov model(CHMM) with only a normal model has been suggested as a very promising machine condition diagnosis method which can be easily used for industrial applications. Generally hidden Markov model also uses many pattern models to recognize specific patterns and the recognition results of CHMM show the likelihood trend of models. By observing this likelihood trend of a normal model, it is possible to detect failures. This method has been successively applied to arc weld defect diagnosis. The result shows CHMM's big potential as a machine condition monitoring method.

• Proceedings of the KIEE Conference
• /
• 2003.07c
• /
• pp.1809-1811
• /
• 2003

Oil-TR에서의 이상을 진단하기 위해서, 유중가스 분석 및 AE센서를 사용한 부분방전측정을 중심으로 많은 연구가 진행/적용되어왔다. 근래 들어서는 거의 모든 진단항목이 환선상태에서 측정하는 것으로 전이되는 추세이며, 사용자가 설비의 현재의 상태를 계속 감시하여 수명을 연장시키는데 관심의 초점이 모아지고 있다. 이에 본 논문에서는 Spiral-Type의 광대역 UHF센서를 사용하여 TR에서 발생하는 부분방전을 측정하였다. 이 방식은 TR내부에 센서를 주입하는 방식으로서, 상대적으로 감도가 우수하며, 노이즈의 영향이 적게 받는다. 코로나방전, 표면방전 및 부유물 형태의 결함에 대하여 측정한 결과를 나타내었으며, 주파수 분포에 대한 변화를 주로 관측하였다. 결과적으로, 서로 다른 결함은 서로 다른 결과를 나타내었으며, 이를 바탕으로 Oil-TR에서 발생하는 결함을 인식할 수 있는 데이터로 활용할 수 있다.

• Journal of the Korean Society for Precision Engineering
• /
• v.15 no.7
• /
• pp.149-159
• /
• 1998

The importance of soundness and safety evaluation in weld zone using by the ultrasonic wave has been recently increased rapidly because of the collapses of huge structures and safety accidents. Especially, the ultrasonic method that has been often used for a major non-destructive testing(NDT) technique in many engineering fields plays an important role as a volume test method. Hence, the defecting any defects of weld Bone in austenitic stainless steel type 304 using by ultrasonic wave and neural network is explored in this paper. In order to detect defects, a distance amplitude curve on standard scan sensitivity and preliminary scan sensitivity represented of the relation between ultrasonic probe, instrument, and materials was drawn based on a quantitative standard. Also, a total of 93％ of defect types by testing 30 defect patterns after organizing neural network system, which is learned with an accuracy of 99％, based on ultrasonic evaluation is distinguished in order to classify defects such as holes or notches in experimental results. Thus, the proposed ultrasonic wave and neural network is useful for defect detection and Ultrasonic Non-Destructive Evaluation(UNDE) of weld zone in austenitic stainless steel 304.

• Smart Media Journal
• /
• v.11 no.9
• /
• pp.47-55
• /
• 2022

Quality control in the smart factory manufacturing process is an important factor. Currently, quality inspection of home appliance manufacturing parts produced by the mold process is mostly performed with the naked eye of the operator, resulting in a high error rate of inspection. In order to improve the quality competition, an automatic defect detection system was designed and implemented. The proposed system acquires an image by photographing an object with a high-performance scan camera at a specific location, and reads defective products due to scratches, dents, and foreign substances according to the vision inspection algorithm. In this study, the depth-based branch decision algorithm (DBD) was developed to increase the recognition rate of defects due to scratches, and the accuracy was improved.