• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.14 no.1
• /
• pp.84-92
• /
• 2001

In this papers, we proposed the new method in order to diagnosis aging state of transformers. For wavelet transform, Daubechies filter is used, we can obtain wavelet coefficients which is used to extract feature of statistical parameters (maximum value, average value, dispersion skewness, kurtosis) about each acoustic emission signal. Also, these coefficients are used to identify normal and fault signal of internal partial discharge in transformer. As improved method for classification use neural network. Extracted statistical parameters are input into an back-propagation neural network. The number of neurons of hidden layer are obtained through Result of Cross-Validation. The network, after training, can decide whether the test signal is early aging state, alst aging state or normal state. In quantity analysis, capability of proposed method is superior to compared that of classical method.

• 한국초전도학회:학술대회논문집
• /
• v.10
• /
• pp.252-256
• /
• 2000

We investigated resistance development in Au/YBCO thin film meander lines during quench. The meander lines were fabricated by coating YBCO films insitu with a gold layer and patterning them by photolithography. The center stripe quenched fastest even though the flux flow resistance that appeared upon the current passing the critical current was uniform. Quench started at an area of the center stripe and propagate both through the gold layer and the sapphire substrate. Quench propagation speed was uniform and 60 cm/s at 30 V$_{rms}$.

• Proceedings of the KIEE Conference
• /
• 1999.11b
• /
• pp.309-311
• /
• 1999

대용량의 전원단지를 포함한 전력계통에서 기간 송전선로(Route) 고장발생시 해당 계통내 동기 탈조의 불안정 현상을 보이는 발전기들의 동기탈조를 방지하기 위한 사고파급방지장치(FPPC:Fault Propagation Preventive Controller)의 기본 구성, 알고리즘 현장시험 및 적용시 설치효과에 대해 검토하였다. 전원용량이 클수록 발전기 차단 제어 완료까지 요구되는 시간은 짧아지며, 제어 요구량 또한 증가한다. 따라서 제어완료까지의 시간을 최대한 짧게 하기 위한 시스템설계 및 오동작 발생을 방지하기 위한 Fail-safe 기능을 S/W와 H/W적으로 구성하였다.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.3 no.6
• /
• pp.262-273
• /
• 1995

For rotating machinery with high speed and high efficiency, large labor and high expenses are required to conduct machine health monitoring. Therefore, it becomes necessary to develop new diagnosis technique which can detect abnormalities of the rotating machinery effectively. In this paper, it is identified that bispectrum analysis technique can be successfully applied to dectect the abnormalities of the roating machinery through computer simulation, and results of the bispectrum analysis are patterned in griding form. Further, pattern recognition technique using back propagation algorithm, which is one of neural network algorithm, being consisted of patterned input layer and output layer for abnormal status, is applied to detect the abnormalities of simulator which is able to make up various kinds of abnorml conditions(misalignment, unbalance, rubbing etc.) of the rotating machinery.

• Proceedings of the KIEE Conference
• /
• 1995.07b
• /
• pp.606-609
• /
• 1995

This paper presents discriminate between magnetizing inrush and internal faults of power transformer by artificial neural networks trained with preprocessing of fault discriminant. The proposed neural networks contain multi-layer perceptron using back-propagation learning algorithm with logistic sigmoid activation function. For this training and test, we used the relaying signals obtained from the EMTP simulation of model power system. It is shown that the proposed transformer protection system by neural networks never misoperated.

• 유체기계공업학회:학술대회논문집
• /
• 1999.12a
• /
• pp.317-323
• /
• 1999

The necessity of diagnosis of the rotating machinery which is widely used in the industry is increasing. Many research has been conducted to manipulate field vibration signal data for diagnosing the fault of designated machinery. As the pattern recognition tool of that signal, neural network which use usually back-propagation algorithm was used in the diagnosis of rotating machinery. In this paper, self-organizing feature map(SOFM) which is unsupervised learning algorithm is used in the abnormal vibration diagnosis of rotating machinery and then learning vector quantization(LVQ) which is supervised teaming algorithm is used to improve the quality of the classifier decision regions.

• The Journal of Korean Association of Computer Education
• /
• v.6 no.2
• /
• pp.33-40
• /
• 2003

Criticality prediction models that determine whether a design entity is fault-prone or non fault-prone play an important role in reducing system development costs because the problems in early phases largely affect the quality of the late products. Real-time systems such as telecommunication systems are so large that criticality prediction is mere important in real-time system design. The current models are based on the technique such as discriminant analysis, neural net and classification trees. These models have some problems with analyzing causes of the prediction results and low extendability. This paper builds a new prediction model, GAM, based on Genetic Algorithm. GAM is different from other models because it produces a criticality function. So GAM can be used for comparison between entities by criticality. GAM is implemented and compared with a well-known prediction model, BackPropagation neural network Model(BPM), considering Internal characteristics and accuracy of prediction.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.35C no.12
• /
• pp.13-22
• /
• 1998

In this paper, we propose a high-performance BICS(built-in current sensor) which is fabricated in 0.8${\mu}{\textrm}{m}$ single-poly two-metal process for IDDQ testing of CMOS VLSI circuit. The CUT(circuit under test) is 4-bit full adder with a bridging fault. Using two nMOSs that have different size, two bridging faults that have different resistance values are injected in the CUT. And controlling a gate node, we experimented various fault effects. The proposed BICS detects the faulty current at the end of the clock period, therefore it can test a CUT that has a much longer critical propagation delay time and larger area than conventional BICSs. As expected in the HSPICE simulation, experimental results of fabricated chip demonstrated that the proposed BICS can exactly detect bridging faults in the circuit.

• Journal of Korean Society on Water Environment
• /
• v.24 no.1
• /
• pp.91-98
• /
• 2008

This work was performed to develop a model possible to predict the influent flow and influent components, which are one of main disturbances causing process problems at the operation of municipal wastewater treatment plant. In this study, artificial neural network (ANN) was used in order to develop a model that was able to predict the influent flow, $COD_{Mn}$, SS, TN 1 day-ahead, 2day-ahead and 3 day ahead. Multi-layer feed-forward back-propagation network was chosen as neural network type, and tanh-sigmoid function was used as activation function to transport signal at the neural network. And Levenberg-Marquart (LM) algorithm was used as learning algorithm to train neural network. Among 420 data sets except missing data, which were collected between 2005 and 2006 at field plant, 210 data sets were used for training, and other 210 data sets were used for validation. As result of it, ANN model for predicting the influent flow and components 1-3day ahead could be developed successfully. It is expected that this developed model can be practically used as follows: Detecting the fault related to effluent concentration that can be happened in the future by combining with other models to predict process performance in advance, and minimization of the process fault through the establishment of various control strategies based on the detection result.

• Korean Journal of Materials Research
• /
• v.12 no.7
• /
• pp.550-554
• /
• 2002

The effect of Mn on cavitation erosion resistance and the sliding wear resistance of Fe-base hardfacing NewAlloy was investigated. Mn is known to decrease stacking fault energy and enhance the formation of $\varepsilon$-martensite. Cavitation erosion resistance for 50 hours and sliding wear resistance for 100 cycles were evaluated by weight loss. Fe-base hardfacing NewAlloy showed more excellent cavitation erosion resistance than Mn-added NewAlloys. $\Upsilon-\alpha$' phase transformation that can enhance erosion resistance by matrix hardening occurred in every specimens. But, only in Mn free Fe-base hardfacing NewAlloy, the hardened matrix could repress the propagation of cracks that was initialed at the matrix-carbides interfaces more effectively than Mn-added NewAlloy The Mn free Fe-base hardfacing NewAlloy showed better sliding wear resistance than Mn-added alloys. Mn-addition up to 5wt.% couldn't increase the sliding wear and cavitation erosion resistance of Fe-base hardfacing alloy because it didn't make $\Upsilon\to\varepsilon$ martensite phase transformation. Therefore, it is considered that the cavitation erosion and the sliding wear resistance can be improved due to $\Upsilon\to\varepsilon$ martensite phase transformation when Mn is added more than 5wt.% in Fe-base hardfacing alloys.