• Journal of Korean Society for Quality Management
• /
• v.47 no.1
• /
• pp.75-86
• /
• 2019

Purpose: It is essential for the steel industry to produce steel products without unexpected downtime to reduce costs and produce high quality products. A hot strip rolling mill consists of many mechanical and electrical units. In condition monitoring and diagnosis, various units could fail for unknown reasons. Methods: In this study, we propose an effective method to detect units with abnormal status early to minimize system downtime. The early warning problem with various units was first defined. An autoencoder was modeled to detect abnormal states. An application of the proposed method was also implemented in a simulated field-data analysis. Results: We can compare images of original data and reconstructed images, as well as visually identify differences between original and reconstruction images. We confirmed that normal and abnormal states can be distinguished by reconstruction error of autoencoder. Experimental results show the possibility of prediction due to the increase of reconstruction error from just before equipment failure. Conclusion: In this paper, hot strip roughing mill monitoring method using autoencoder is proposed and experiments are performed to study the benefit of the autoencoder.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.11
• /
• pp.5123-5127
• /
• 2011

Research and development for the technology, that is about maintenance and accidents prevention of underground power distribution line, are demanding. The precise detection of leakage point of underground power line is very important, because it is difficult to detect the exact location of a fault in underground power line and to repair faults. When earth electric potential is measured to detect underground electric leakage point after transmitting AC electric pulse wave to underground power line, it must be measured in a specific half period of AC pulse wave because the distribution of the electric earth potential varies with the polarity of the transmitted wave. In this paper we proposed the measurement of half period modulated earth potential as a method to detect a underground leakage point. And We compared the proposed method with other methods. Through experiments we verified that the proposed method can be implemented and operated properly.

• Proceedings of the KIEE Conference
• /
• 2004.07c
• /
• pp.1845-1847
• /
• 2004

In oil-filled equipment such as transformers, partial discharge or local overheating will precede a final shutdown. Accompanied with such problems is a decomposition of insulating material into gases, which are dissolved into the transformer oil. The gases dissolved in oil can be separated with some membranes based on the differences in permeability of membranes to different gases. This paper discuss the permeability characteristics of several membranes for separation hydrogen gas in oil. With result of this paper, it may become possible to detect fault-related gases from transformer oil and predict incipient failures in the future.

• Journal of Power Electronics
• /
• v.13 no.2
• /
• pp.264-274
• /
• 2013

A new sensorless position estimation method for switched reluctance motor (SRM) drives is presented in this paper. This method uses the change of the slope of the phase inductance to detect the aligned position. Since the aligned positions for successive electrical cycle of each phase are apart by a fixed mechanical angle $45^{\circ}$ in the case of 12/8 SRM, the speed of the machine can be calculated to estimate the rotor position. Since no prior knowledge of motor parameters is required, the method is easy for implementation without adding any additional hardware or memory. In order to verify the validity of this technique, effects such as changes in the advanced angle and phase lacking faults are examined. In addition, an inductance threshold based sensorless starting scheme is also proposed. Experimental results demonstrate the validity of the proposed method.

• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.1364-1366
• /
• 1997

To operate electric power systems economically and stably, and to supply the electric power of good quality, it is necessary that the measured information (current, voltage, and so on) be detected and transmutted with high reliability and high effieincy. For the reason, the optical magnetic field sensor is possible to rapidly detect to over current and recover when electric power line have fault. In addition, the optical sensor have no electro magnetic distortion and no electric insulation. In this study, we designed OCR(Over Current Relay) using optical sensor. The designed OCR using optical sensor was measured characteristic and compared contentional OCR. This system have highest optical advantages and reliability.

• Transactions of the Korean Society of Pressure Vessels and Piping
• /
• v.6 no.1
• /
• pp.9-15
• /
• 2010

This paper describes the Visual Tool for automatic ultrasonic examination that is under developing as a part of the project for development of automatic ultrasonic wave acquisition and analysis program. This tool that is supported by various image processing techniques will be adopted to detect the flaws in the component and piping welds in NPP. Visual Tool will enhance the integrity of nuclear power plant. The object of this paper is to address the Visual Tool which is developing for automatic ultrasonic inspection of welds in NPP.

• Proceedings of the IEEK Conference
• /
• 1998.10a
• /
• pp.1069-1072
• /
• 1998

Recently the development of design and automation technology and manufacturing method, has reduced the cost of chip, but it becomes more difficult to test IC chip because test technique doesn't keep up with these techniques. In case of IC testing, obtaining test vectors to be able to detect good chip or bad one is very important, but according to increasing complexity, it is very complex and difficult. Another problem is that during testing, there could be capability of physical and electrical damage on chip. Also there is difficulty in synchronization between CUT (circuit under test) and Test equipment〔1〕. Because of these difficulties, built in self test has been proposed. Not only obtaining test vectors but also reducing test time becomes hot issues nowadays. This paper presents a new test BIST(built in self test) method. Proposed BIST implementation reduces test time and obtains high fault coverage. By searching internal nodes in which are inserted test_point_cells〔2〕and allocating TPG(test pattern generation) stages, test length becomes much shorter.

• Proceedings of the IEEK Conference
• /
• 1998.10a
• /
• pp.507-510
• /
• 1998

In this paper, a novel test method is proposed to detect hard and soft fault in CMOS operational amplifiers. Proposed test method mark use of the offset character, which is one of the op-amps characteristics. During the test mode, CUT is implemented to unit gain op-amps with feedback loop. When the input is grounded, a good circuit has a small offset voltage, but a faulty circuit has a large offset voltage exceeding predefined range of tolerance. Using the proposed method, no test vector is required to be applied. Therefore the test vector generation problem is eliminated and the test time is reduced. The accuracy and effectiveness of the method is verified through HSPICE simulation.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.6 no.1
• /
• pp.1-12
• /
• 2010

Recently, large amount of information in IDS(Intrusion Detection System) can be un manageable and also be mixed with false prediction error. In this paper, we propose a data mining methodology for IDS, which contains uncertainty based on training process and post-processing analysis additionally. Our system is trained to classify the existing attack for misuse detection, to detect the new attack pattern for anomaly detection, and to define border patter between attack and normal pattern. In experimental results show that our approach improve the performance against existing attacks and new attacks,from 0.62 to 0.84 about 35%.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.41 no.5
• /
• pp.81-90
• /
• 2004

This paper presents new testability measure based on learning, which can be useful in the deterministic process of test pattern generation algorithms. This testability measure uses the structural information that are obtained by teaming. The proposed testability measure searches for test pattern that can early detect the conflict in case of the hardest decision problems. On the other hand in case of the easiest decision problem, it searches for test pattern that likely results in the least conflict. The proposed testability measure reduces CPU time to generate test pattern that accomplishes the same fault coverage as that of the distance-based measure.