• Nuclear Engineering and Technology
• /
• v.55 no.2
• /
• pp.493-505
• /
• 2023

Comprehensive condition monitoring of large industry systems such as nuclear power plants (NPPs) is essential for safety and maintenance. In this study, we developed novel system-scale diagnostic technology based on deep-learning and IR thermography that can efficiently and cost-effectively classify system conditions using compact Raspberry Pi and IR sensors. This diagnostic technology can identify the presence of an abnormality or accident in whole system, and when an accident occurs, the type of accident and the location of the abnormality can be identified in real-time. For technology development, the experiment for the thermal image measurement and performance validation of major components at each accident condition of NPPs was conducted using a thermal-hydraulic integral effect test facility with compact infrared sensor modules. These thermal images were used for training of deep-learning model, convolutional neural networks (CNN), which is effective for image processing. As a result, a proposed novel diagnostic was developed that can perform diagnosis of components, whole system and accident classification using thermal images. The optimal model was derived based on the modern CNN model and performed prompt and accurate condition monitoring of component and whole system diagnosis, and accident classification. This diagnostic technology is expected to be applied to comprehensive condition monitoring of nuclear power plants for safety.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.30 no.11
• /
• pp.693-698
• /
• 2017

In this study, the thermal degradation properties of polyethylene terephthalate film has been examined by the capacitance, Tan ${\delta}$, thermography, FTIR, and SEM results at temperatures of $90{\sim}170^{\circ}C$ and frequencies of 0.3~3,000 kHz. It was found that the capacitance decreased with increasing thermal imaging temperature, probably caused by weakening of chemical bond with increasing temperature. Tan ${\delta}$ decreased upon increasing temperature from $90^{\circ}C$ to $170^{\circ}C$, probably due to the molecular motion of COOH radical or OH radical. The FT-IR measurement reveals that no structural change of the material occurs upon thermal radiation. The SEM measurement shows that the material is stabilized by thermal decomposition with increasing temperature; however, excessive thermal degradation obstructs the stabilization of the material.

• Proceedings of the KIEE Conference
• /
• 2015.07a
• /
• pp.1501-1502
• /
• 2015

배전기자재는 오래 사용하다 보면 열적, 전기적, 기계적, 환경적, 복합적 스트레스에 의해 절연성능이 떨어진다. 이때 발생하는 열화현상으로는 발열도 되고, 전자파, 빛, 균열, 침식, 진동음도 발생한다. 따라서 열화된 기자재를 검출하기 위해여 광학장비 또는 과학화 진단장비를 활용하여 고장예방을 하고 있다. 하지만 기자재가 열화되면서 발생하는 증상을 모르고 진단을 하면 투입된 인력과 예산에 비해 초라한 적출실적도 발생할 수 있다. 따라서 한해 동안 배전설비 진단에 가장 많이 활용하고 있는 열화상진단과 초음파 진단의 실적과 적출결과를 분석하여 기자재별 효과적인 진단방식을 제공하고자 한다.

• Journal of Animal Science and Technology
• /
• v.59 no.10
• /
• pp.21.1-21.6
• /
• 2017

Background: The aim of the study is to evaluate the effectiveness of thermographic monitoring, using the temperature changes of perianal and perivulvar areas for the determination of estrus in Anatolian Shepherd bitches. Fifteen bitches were used in the study. Blood and vaginal smear samples were collected and thermographic monitoring of perianal and perivulvar areas were carried out starting from proestrus to early diestrus. Also, external signs of estrus were investigated. Smear samples were evaluated by light microscopy after Diff-Quik staining method and superficial and keratinized superficial cells were determined as percentage (S + KS%). Progesterone and luteinizing hormone measurements were done by radioimmunoassay. The difference in temperature between perianal and perivulvar areas was evaluated through thermographic images by FLIR ResearchIR Software. Results: According to the results obtained from the study, differences between progesterone and S + KS% were statistically significant (P < 0,05). Although temperature showed increase and decrease with progesterone and S + KS%, the differences were not important statistically (P > 0,05). Serum luteinizing hormone levels did not sign any difference (P > 0,05). Conclusions: As a result, thermographic monitoring alone is not enough for estrus detection in Anatolian Shepherd bitches. However, it can be used to assist the actual estrus detection technique in terms of providing some foreknowledge by evaluating the differences in temperature.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.3
• /
• pp.570-590
• /
• 2024

Breast cancer ranks among the most prevalent forms of malignancy and foremost cause of death by cancer worldwide. It is not preventable. Early and precise detection is the only remedy for lowering the rate of mortality and improving the probability of survival for victims. In contrast to present procedures, thermography aids in the early diagnosis of cancer and thereby saves lives. But the accuracy experiences detrimental impact by low sensitivity for small and deep tumours and the subjectivity by physicians in interpreting the images. Employing deep learning approaches for cancer detection can enhance the efficacy. This study explored the utilization of thermography in early identification of breast cancer with the use of a publicly released dataset known as the DMR-IR dataset. For this purpose, we employed a novel approach that entails the utilization of a pre-trained MobileNetV2 model and fine tuning it through transfer learning techniques. We created three models using MobileNetV2: one was a baseline transfer learning model with weights trained from ImageNet dataset, the second was a fine-tuned model with an adaptive learning rate, and the third utilized early stopping with callbacks during fine-tuning. The results showed that the proposed methods achieved average accuracy rates of 85.15%, 95.19%, and 98.69%, respectively, with various performance indicators such as precision, sensitivity and specificity also being investigated.

• Smart Structures and Systems
• /
• v.33 no.1
• /
• 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%.

• Journal of the Korean institute of surface engineering
• /
• v.36 no.5
• /
• pp.406-412
• /
• 2003

FT-IR and thermography were used to investigate the infrared radiation characteristic of SiO$_2$ film and SiO$_2$/Fe$_2$O$_3$film coated on aluminum. Through FT-TR spectrum, SiO$_2$film showed high infrared absorption in accordance with the stretching vibration of Si-O-Si, and as$ Fe_2$$O_3$was mixed additional absorption band appeared resulting from the stretching vibration of Fe-O at $590cm^{-1}$ and the bond of Si-O-Fe at $900 cm^{-1}$ The two kinds of film measured by the integration method and the reflective method coincided with each other in the wavelength area of infrared absorption and radiation, and corresponded well with Kirchhoff's law as the infrared emissivity is high in wavelength where infrared absorption rate is high. The emissivity of $SiO_2$ film was 0.65 and that of $SiO_2$/Fe$_2$$O_3$film was 0.77, so the addition of$ Fe_2$$O_3$ raised the infrared emissivity by approximately 13%.$ SiO_2$$Fe_2$$O_3$ film is efficient as an infrared radiator at below $100^{\circ}C$. The temperature of heat radiation after 7 minutes was 117$^{\circ}C$ in aluminum plate and $155^{\circ}C$ in $SiO_2$$Fe_2$$O_3$ film, $38^{\circ}C$ higher than the former.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.61 no.11
• /
• pp.1656-1661
• /
• 2012

UV inspection technology is being used for predictive maintenance of power facility together with IR-thermography and ultrasonic devices. In this paper, the UV corona camera design, fabrication, and perform a simple test to be take advantage of the diagnostic equipment. The UV corona camera developed a $6.4^{\circ}{\times}4.8^{\circ}$ of the field of view as a conventional camera to diagnose a wide range of slightly enlarged, and power equipment to measure the distance between the camera and the distance meter has been attached. The transmission between 250 to 280nm was 11% ($12.5%{\times}88%{\times}98%$) by combing the transmission on absorption film, window and other filter(UG 5, nickel sulphate and so on). In a distance of 5m with the UV corona camera it is possible to detect partial discharge with a PD level of 2.5pC and a RIV level of $3.6dB{\mu}V$.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.26 no.4
• /
• pp.211-219
• /
• 2006

The UET(ultrasound excited thermography) for the ,eat-time diagnostics of the object employs an infrared camera to image defects of the surface and subsurface which are locally heated using high-frequency putted ultrasonic excitation. The dissipation of high-power ultrasonic energy around the feces of the defects causes an increase In temperature. The defect's image appears as a hot spot (bright IR source) within a dark background field. The UET for nondestructive diagnostic and evaluation is based on the image analysis of the hot spot as a local response to ultrasonic excited heat deposition. In this paper the applicability of VET for fast imaging of defect is described. The ultrasonic energy is injected into the sample through a transducer in the vertical and horizontal directions respectively. The voltage applied to the transducer is measured by digital oscilloscope, and the waveform are compared. Measurements were performed on four kinds of materials: SUS fatigue crack specimen(thickness 14mm), PCB plate(1.8 mm), CFRP plate(3 mm) and Inconel 600 plate (1 mm). A high power ultrasonic energy with pulse durations of 250ms Is injected into the samples in the horizontal and vertical directions respectively The obtained experimental result reveals that the dissipation loss of the ultrasonic energy In the vertical injection is less than that in the horizontal direction. In the cafe or PCB, CFRP, the size of hot spot in the vortical injection if larger than that in horizontal direction. Duration time of the hot spot in the vertical direction is three times as long as that in the horizontal direction. In the case of Inconel 600 plate and SUS sample, the hot spot in the horizontal injection was detected faster than that in the vertical direction

• Restorative Dentistry and Endodontics
• /
• v.27 no.4
• /
• pp.370-381
• /
• 2002

This study was performed to evaluate the temperature rise on various position of the Buchanan plugger, the peak temperature of plugger's type and the temperature change by its touching time of heat control spling. The heat carrier system 'System B' (Model 1005, Analytic Technologies, USA) and the Buchanan's plug-gers of F, FM, M and ML sizes are used for this study. The temperature was set to 20$0^{\circ}C$ which Dr. Buchanan's "continuous wave of condensation" technique recommended on digital display and the power level on it was set to 10. In order to apply heat on the Buchanan's pluggers, the heat control spring was touched for 1, 2, 3, 4 and 5 seconds respectively. The temperature rise on the surface of the pluggers were measured at 0.5 mm intervals from tip to 20 mm length of shank using the infrared thermography (Radiation Thermometer-IR Temper, NEC San-ei Instruments, Ltd, Japan) and TH31-702 Data capture software program (NEC San-ei Instruments, Ltd, Japan). Data were analyzed using a one way ANOVA followed by Duncan's multiple range test and linear regression test. The results as follows. 1. The position at which temperature peaked was approximately at 0.5 mm to 1.5 mm far from the tip of Buchanan's pluggers (p<0.001). The temperature was constantly decreased toward the shank from the tip of it (p<0.001). 2. When the pluggerss were heated over 5 seconds, the peak temperature by time of measurement revealed from 253.3$\pm$10.5$^{\circ}C$ to 192.1$\pm$3.3$^{\circ}C$ in a touch for 1 sec, from 218.6$\pm$5.$0^{\circ}C$ to 179.5$\pm$4.2$^{\circ}C$ in a touch for 2 sec, from 197.5$\pm$3.$0^{\circ}C$ to 167.5$\pm$3.7$^{\circ}C$ in a touch for 3 sec, from 183.7$\pm$2.5$^{\circ}C$ to 159.8$\pm$3.6$^{\circ}C$ in a touch for 4 sec and from 164.9$\pm$2.$0^{\circ}C$ to 158.4$\pm$1.8$^{\circ}C$ in a touch for 5 sec. A touch for 1 sec showed the highest peak temperature, followed by, in descending order, 2 sec, 3 sec, 4 sec. A touch for 5 sec showed the lowest peak temperature (p<0.001). 3. A each type of pluggers showed different peak temperatures. The peak temperature was the highest in F type and followed by, in descending order, M type, ML type. FM type revealed the lowest peak temperature (p<0.001). The results of this study indicated that pluggers are designed to concentrate heat at around its tip, its actual temperature does not correlate well with the temperature which Buchanan's "continuous wave of condensation" technique recommend, and finally a quick touch of heat control spring for 1sec reveals the highest temperature rise.