• Smart Structures and Systems
• /
• 제33권1호
• /
• pp.55-64
• /
• 2024

This paper proposes a fusion imaging-based coating-defect classification method for steel structures that uses zero-shot learning. In the proposed method, a halogen lamp generates heat energy on the coating surface of a steel structure, and the resulting heat responses are measured by an infrared (IR) camera, while photos of the coating surface are captured by a charge-coupled device (CCD) camera. The measured heat responses and visual images are then analyzed using zero-shot learning to classify the coating defects, and the estimated coating defects are visualized throughout the inspection surface of the steel structure. In contrast to older approaches to coating-defect classification that relied on visual inspection and were limited to surface defects, and older artificial neural network (ANN)-based methods that required large amounts of data for training and validation, the proposed method accurately classifies both internal and external defects and can classify coating defects for unobserved classes that are not included in the training. Additionally, the proposed model easily learns about additional classifying conditions, making it simple to add classes for problems of interest and field application. Based on the results of validation via field testing, the defect-type classification performance is improved 22.7% of accuracy by fusing visual and thermal imaging compared to using only a visual dataset. Furthermore, the classification accuracy of the proposed method on a test dataset with only trained classes is validated to be 100%. With word-embedding vectors for the labels of untrained classes, the classification accuracy of the proposed method is 86.4%.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2000년도 하계학술대회 논문집 C
• /
• pp.1951-1953
• /
• 2000

Partial Discharge is non-disruptive discharge, which can be discriminated to 3 kinds as firstly, internal discharge which is caused by internal voids inside of insulator, secondly, surface discharge which occurs from the surface of insulator and finally, corona discharge which is from the surface of an electrode. In this thesis, three kinds of defects are artificially made to the inside and the surface of the epoxy resine busing with internal voltage detection sensor, which is practically equipped into SF6 gas insulated switchgear for 22.9kV distribution line, so that discrimination of three kinds of PD signals by means of phi-q-n pattern analysis method was performed.

• 한국생산제조학회지
• /
• 제22권6호
• /
• pp.989-995
• /
• 2013

Unlike fossil-or nuclear fuel-based power generation, wind power generation using inexhaustible wind energy is a pollution-free, hazardless power generation method. In this study, ultrasound thermography is used for fabricating specimens of wind power generator bearings and wind power generator supplement flanges, and an optimally designed ultrasound horn and ultrasound excitation system are used for detecting damage to part materials of a wind power generation setup. In addition, thermal flow analysis and ultrasonic thermography imaging are comparatively analyzed for improving the detection reliability in terms of surface and internal defects of part materials and for verifying the developed system's field applicability and reliability.

• Transactions on Electrical and Electronic Materials
• /
• 제6권4호
• /
• pp.177-185
• /
• 2005

Fatigue characteristics of lead zirconate titanate (PZT) films deposited by electron cyclotron resonance plasma enhanced chemical vapor deposition (ECR-PECVD) were investigated. The fatigue characteristics were investigated with respect to PZT film thickness, domain structure, fatigue pulse height, temperature, electrode materials and electrode configurations. The used top and bottom electrode materials were Pt and $RuO_2$. In the fatigue characteristics with fatigue pulse height and PZT film thickness, the fatigue rates are independent of the applied fatigue pulse height at the electric field regions to saturate the P-E hysteresis and polarization $(P^*,\;P^A)$ characteristics. The unipolar and bipolar fatigue characteristics of PZT capacitors with four different electrode configurations $(Pt//Pt,\;Pt//RuO_2,\;RuO_2//Pt,\;and\;RuO_2//RuO_2)$ were also investigated. The polarization-shifts during the unipolar fatigue and the temperature dependence of fatigue rate suggest that the migration of charged defects should not be expected in our CVD-PZT films. It seems that the polarization degradations are attributed to the formation of charged defects only at the Pt/PZT interface during the domain switching. The charged defects pin the domain wall at the vicinity of Pt/PZT interface. When the top and bottom electrode configurations are of asymmetric $(Pt//RuO_2,\;RuO_2//Pt)$, the internal fields can be generated by the difference of charged defect densities between top and bottom interfaces.

• 한국소성가공학회:학술대회논문집
• /
• 한국소성가공학회 2006년도 춘계학술대회 논문집
• /
• pp.373-376
• /
• 2006

The ring rolling design for a large-scale Ti-6Al-4V alloy ring was performed with a calculation method and FEM simulation. The ring rolling design includes geometry design and optimization of process variables. The calculation method was to determine geometry design such as initial billet and blank size, and final rolled ring shape. A commercial FEM code, SHAPE was used to simulate the effect of process variables in ring rolling on the distribution of the internal state variables such as strain, strain rate and temperature. In order to predict the forming defects during ring rolling, the process-map approach based on Ziegler's instability criterion was used with FEM simulation. Finally, an optimum process design to obtain sound Ti-6Al-4V rings without forming defects was suggested through combined approach of Ziegler's instability map and FEM simulation results.

• 한국정보통신학회논문지
• /
• 제17권11호
• /
• pp.2486-2491
• /
• 2013

세라믹 소재 영상은 사람의 육안으로 판단하기 힘든 내부 기공이나 균열, 이물질 등의 결함들이 존재한다. 본 논문에서는 사람의 육안으로 검출하기 힘든 세라믹 소재로 이루어진 파이프 용접부에 있는 결함을 확인하기 위해 ART2 알고리즘을 이용하여 세라믹 영상에서 결함을 검출하는 방법을 제안한다. 비파괴 검사는 본질에 손상이 전혀 가지 않는 검사 방법이기 때문에 소재의 결함 검출에 대해서는 적절한 방법이다. 따라서 본 논문에서는 Ends-In Search Stretching 기법을 적용하여 명암 대비를 강조하고, 명암 대비가 강조된 영상에서 삼각형 타입의 소속 함수를 이용한 퍼지 이진화 기법을 적용한 후, 임의의 패턴 입력에 대해서도 효과적으로 특징을 분류하는 개선된ART2 알고리즘을 적용하여 결함 영역을 검출한다. 제안된 방법을 세라믹 소재 영상을 대상으로 실험한 결과, 기존의 방법보다 효율적으로 결함이 검출되는 것을 확인하였다.

• 한국생산제조학회지
• /
• 제24권3호
• /
• pp.294-301
• /
• 2015

Oil filters for vehicular parts are used under high and low temperatures as the engine is cooled, and defects can be generated with repeated changes in the operating environment and with changes in the shape, such as very high internal losses for the bolts. Visually checking for defects inside a bolt is impossible. Nondestructive evaluation methods such as eddy current testing (ECT) are recommended as a more effective way to examine inside a bolt and detect surface defects in a short amount of time. In this study, the fit bobbin coil eddy current probe was applied to checking the bolts. The bolt parameters were calculated by using a COMSOL analysis program to obtain parameters for professional interior design and fault diagnosis.

• Journal of Electrical Engineering and Technology
• /
• 제9권1호
• /
• pp.293-300
• /
• 2014

This paper proposes a novel pattern recognition approach based on the radial basis function (RBF) neural network for identifying insulation defects of high-voltage electrical apparatus arising from partial discharge (PD). Pattern recognition of PD is used for identifying defects causing the PD, such as internal discharge, external discharge, corona, etc. This information is vital for estimating the harmfulness of the discharge in the insulation. Since an insulation defect, such as one resulting from PD, would have a corresponding particular pattern, pattern recognition of PD is significant means to discriminate insulation conditions of high-voltage electrical apparatus. To verify the proposed approach, experiments were conducted to demonstrate the field-test PD pattern recognition of cast resin current transformer (CRCT) models. These tests used artificial defects created in order to produce the common PD activities of CRCTs by using feature vectors of field-test PD patterns. The significant features are extracted by using nonlinear principal component analysis (NLPCA) method. The experimental data are found to be in close agreement with the recognized data. The test results show that the proposed approach is efficient and reliable.

• 소성∙가공
• /
• 제16권3호
• /
• pp.172-177
• /
• 2007

The process design for large-scale ring rolling of Ti-6Al-4V alloy was performed by calculation method, processing map approach and FEM simulation. The ring rolling design includes geometry design and optimization of process variables. The calculation method was used to make geometry design such as initial billet and blank sizes, and final rolled ring shape. A commercial FEM code, SHAPE-RR was used to simulate the effect of process variables in ring rolling on the distribution of the internal state variables such as strain, strain rate and temperature. In order to predict the forming defects during ring rolling and the formation of over-heating above $\beta$-transus temperature due to deformation heating, the process-map approach based on Ziegler's instability criterion was used with FEM simulation. Finally, an optimum process design to obtain sound Ti-6Al-4V rings without forming defects was suggested through combined approach of Ziegler's instability map and FEM simulation results.

• 비파괴검사학회지
• /
• 제34권1호
• /
• pp.10-17
• /
• 2014

A 3D model based on the finite element method (FEM) was built to simulate the infrared thermography (IRT) inspection process. Thermal contrast is an important parameter in IRT and was proven to be a function of defect parameters. Parametric studies were conducted on internal defects with different depths, thicknesses, and orientations. Thermal contrast evolution profiles with respect to the time of the defect and host material were obtained through numerical simulation. The thermal contrast decreased with defect depth and slightly increased with defect thickness. Different orientations of thin defects were detected with IRT, but doing so for thick defects was difficult. These thermal contrast variations with the defect depth, thickness, and orientation can help in optimizing the experimental process and interpretation of data from IRT.