• Journal of Electrical Engineering and Technology
• /
• v.2 no.1
• /
• pp.118-122
• /
• 2007

In this work, experimental investigation is carried out in order to design and fabricate the UHF sensor that is able to detect the partial discharges produced from 10 artificial defects introduced into the real scale 70kV GIS mock-up under high voltage within a well shielded room. As well, in order to verify the on-site applicability of our method, the newly proposed CAPD (chaos analysis of partial discharge) is combined with spectral analysis for identifying the nature of 10 artificial defects under investigation. The PD pattern recognition of each defect has been fulfilled by applying our ANN software. The result indicates that the recognition rate reaches up to 80% by the newly proposed method while the traditional PRPD analysis method allows us to obtain 41%. In consequence, it can be pointed out that the proposed method seems likely to be applicable to the real GIS at the site.

• Proceedings of the KIEE Conference
• /
• 2005.07c
• /
• pp.2223-2225
• /
• 2005

In this work, experimental investigation has been mainly done. For this purpose, UHF sensor has been designed and fabricated to detect the partial discharges produced from the 10 artificial defects introduced into the real scale 70kV GIS mock-up under the high voltage at the well shielded room. And also, in order to verify the applicability of the proposed method at the site, the proposed CAPD (chaos analysis of partial discharge) is combined with spectral analysis method in order to identify the nature of the above 10 defects. The PD pattern recognition of each defect has been fulfilled by applying self developed artificial neural network soft ware. The result shows that the recognition rate is reached to be 80% by newly proposed method while the traditional PRPD analysis method leads us to obtain 41%. In consequence, it can be pointed out that the proposed method seems likely to be applicable to the real GIS at the site.

• Journal of Welding and Joining
• /
• v.16 no.3
• /
• pp.64-73
• /
• 1998

This paper is concerned with defects detection and evaluation of heat affected zone (HAZ) in austenitic stainless steel type 304 by ultrasonic wave and neural network. In experiment, the reflected ultrasonic defect signals from artificial defects (side hole, vertical hole, notch) of HAZ appears as beam distance of prove-defect, distance of probe-surface, depth of defect-surface on CRT. For defect classification simulation, neural network system was organized using total results of ultrasonic experiment. The organized neural network system was learned with the accuracy of 99%. Also it could be classified with the accuracy of 80% in side hole, and 100% in vertical hole, 90% in notch about ultrasonic pattern recognition. Simulation results of neural network agree fairly well with results of ultrasonic experiment. Thus were think that the constructed system (ultrasonic wave - neural network) in this work is useful for defects dection and classification such as holes and notches in HAZ of austenitic stainless steel 304.

• Journal of Arbitration Studies
• /
• v.31 no.4
• /
• pp.119-136
• /
• 2021

Due to the restriction of movement caused by the Corona epidemic and the expansion of the "big face" through human distance, the "unmanned system" based on artificial intelligence and the Internet of Things has been widely used in modern life. "Self-driving," one of the transportation systems based on artificial technology, has taken the initiative in the transportation system as the spread of Corona has begun. Self-driving technology eliminates unnecessary contact and saves time and manpower, which can significantly impact current and future transportation. Accidents may occur, however, due to the performance of self-driving technology during transportation albeit the U.S. allows ordinary people to drive automatically through experimental operations, and the product liability law will resolve the dispute. Self-driving has become popular in the U.S. after the experimental stage, and in the event of a self-driving accident, product liability should be applied to protect drivers from complicated self-driving disputes. The purpose of this paper is to investigate whether disputes caused by defects in ordinary cars can be resolved through arbitration through U.S. precedents and to investigate whether disputes caused by defects in autonomous cars can be arbitrated.

• Journal of Korean Dental Science
• /
• v.16 no.2
• /
• pp.156-163
• /
• 2023

Purpose: The aim of this study was to evaluate the feasibility of deep learning techniques to classify the morphology and severity of peri-implantitis bone defects based on periapical radiographs. Materials and Methods: Based on a pre-trained and fine-tuned ResNet-50 deep learning algorithm, the morphology and severity of peri-implantitis bone defects on periapical radiographs were classified into six groups (class I/II and slight/moderate/severe). Accuracy, precision, recall, and F1 scores were calculated to measure accuracy. Result: A total of 971 dental images were included in this study. Deep-learning-based classification achieved an accuracy of 86.0% with precision, recall, and F1 score values of 84.45%, 81.22%, and 82.80%, respectively. Class II and moderate groups had the highest F1 scores (92.23%), whereas class I and severe groups had the lowest F1 scores (69.33%). Conclusion: The artificial intelligence-based deep learning technique is promising for classifying the morphology and severity of peri-implantitis. However, further studies are required to validate their feasibility in clinical practice.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.5 no.2
• /
• pp.22-33
• /
• 1986

The application and development of on-line monitoring technology of AE to surveillance of crack propagation will contribute to the structural integrity of reactor pressure vessel and piping system. This research has been performed in order to obtain the evaluation technology for source location of AE and the analysis for the AE signal of the welded specimen. AE is detected by 4-channels AE system during pressurization in small pressure vessels. The cracking of artificial defects can be accurately located and categorized in real time. The welded specimens have more events rate and higher amplitude than the weldless less specimens, and the events rate have a peak around the yield point and just before the failure under tensile test.

• Journal of the Korean Society for Precision Engineering
• /
• v.12 no.5
• /
• pp.33-39
• /
• 1995

This paper presents a method of detecting localized defects on tapered roller bearing in main spindle of machine tool system. The statistical parameters in time-domain processing technique have been calculated to extract useful features from bearing vibration signals. These features are used by the input feature of an artificial neural network to detect and diagnose bearing defects. As a results, the detection of bearing defect conditions could be successfully performed by using an artificial neural network with statistical parameters of acceleration signals.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.58 no.2
• /
• pp.356-362
• /
• 2009

The ELectromagnetic Core Imperfection Detector (EL-CID) test was performed on a small generator in the laboratory and a gas turbine generator in the field to assess the fault condition of generator stator core. Artificial defects with six different sizes were introduced in the small generator. The scan results on six defects show a very large increase in the magnitude of fault current compared to that obtained with a healthy core. After the stator core heats up, a thermal imaging camera was used to detect hot spot on the inner surface of the core for comparison. Several faults were found during inspection of the gas turbine generator with the EL-CID. It has been shown that the existence of a fault can be determined by monitoring the magnitude of fault current.

• The Transactions of the Korean Institute of Electrical Engineers C
• /
• v.51 no.5
• /
• pp.199-204
• /
• 2002

In order to recognize the deterioration of insulation system by partial discharge (PD), the characteristics of PD patterns which are occurring at the interface between epoxy and rubber materials in extra high voltage cable joints, have been investigated. The artificial defects such as voids, metal particles, insulation fiber and water impregnated insulation fiber are planted between the interfaces. A high frequency partial discharge detection system was used for measuring PD signals. An analysis of the PD patterns is focused on the shape of PD pattern, phase, width and time-dependence for each artificial defect. The PD Patterns in each defect show the different behaviors and it is suggested that the precise discrimination of PD patterns could be used for the diagnosis of deterioration in the insulation systems.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.38 no.6
• /
• pp.18-25
• /
• 2001

KBANN (knowledge-based artificial neural network) combining the analytical learning and the inductive learning has been shown to be more effective than other machine learning models. However KBANN doesn't have the theory refinement ability because the topology of network can't be altered dynamically. Although TopGen was proposed to extend the ability of KABNN in this respect, it also had some defects. The algorithms which could solve this TopGen's defects, enabling the refinement of theory, by extending KBANN, are designed.