• 한국지반공학회:학술대회논문집
• /
• 한국지반공학회 2001년도 봄 학술발표회 논문집
• /
• pp.245-248
• /
• 2001

During the core drilling for the design of a railway bridge crossing over the inferred fault system along the river, fracture zone, extends vertically more than the bottom of borehole, filled with fault gouge was found. The safety of bridge could be threatened by the excessive subsidence or the reduced bearing capacity of bedrock, if a fault would be developed under or around the pier foundation. Thus, a close examination of the fault was required to rearrange pier locations away from the fault or to select a reinforcement method if necessary. Geophysical methods, seismic reflection method and electrical resistivity survey over the water covered area, were applied to delineate the weak zone associated with the fault system. The results of geophysical survey clearly showed a number of faults extending vertically more than 50m. Reinforcement was not desirable because of the high cost and the water contamination, etc. The pier locations were thus rearranged based on the results of geophysical surveys to avoid the undesirable situations, and additional core drillings on the rearranged pier locations were carried out. The bedrock conditions at the additional drilling sites turned out to be acceptable for the construction of piers.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권5호
• /
• pp.1610-1629
• /
• 2021

Failures frequently occurred in manufacturing machines due to complex and changeable manufacturing environments, increasing the downtime and maintenance costs. This manuscript develops a novel deep learning-based method named Multi-Domain Convolutional Neural Network (MDCNN) to deal with this challenging task with vibration signals. The proposed MDCNN consists of time-domain, frequency-domain, and statistical-domain feature channels. The Time-domain channel is to model the hidden patterns of signals in the time domain. The frequency-domain channel uses Discrete Wavelet Transformation (DWT) to obtain the rich feature representations of signals in the frequency domain. The statistic-domain channel contains six statistical variables, which is to reflect the signals' macro statistical-domain features, respectively. Firstly, in the proposed MDCNN, time-domain and frequency-domain channels are processed by CNN individually with various filters. Secondly, the CNN extracted features from time, and frequency domains are merged as time-frequency features. Lastly, time-frequency domain features are fused with six statistical variables as the comprehensive features for identifying the fault. Thereby, the proposed method could make full use of those three domain-features for fault diagnosis while keeping high distinguishability due to CNN's utilization. The authors designed massive experiments with 10-folder cross-validation technology to validate the proposed method's effectiveness on the CWRU bearing data set. The experimental results are calculated by ten-time averaged accuracy. They have confirmed that the proposed MDCNN could intelligently, accurately, and timely detect the fault under the complex manufacturing environments, whose accuracy is nearly 100%.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2010년도 추계학술대회 논문집
• /
• pp.513-514
• /
• 2010

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2010년도 춘계학술대회 논문집
• /
• pp.239-240
• /
• 2010

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2013년도 추계학술대회 논문집
• /
• pp.314-315
• /
• 2013

• 광물과 암석
• /
• 제35권3호
• /
• pp.377-386
• /
• 2022

불소는 인위적 기원 외에 마그마 분화작용, 열수변질작용, 광화작용, 단층 활동과 같은 지질학적 기원에 의해 자연적으로 암석 내 부화될 수 있다. 일반적으로 화성암 및 변성암이 분포하는 지역에서 고농도의 불소가 산출되는 것으로 알려져 있으며, 연구지역은 흑운모화강암이 주로 분포하는 지역이다. 그러나 선행연구에서 자연기원 불소의 부화기작에 대한 규명이 부족했고 이를 보다 명확히 규명하기 위해 단층대에 대한 연구를 수행하였다. 을왕산 흑운모화강암과 단층대 암석의 구성 광물은 동일하지만 정량적인 차이가 나타난다. 석영과 불소함유광물(형석, 견운모 등)은 높은 함량으로 존재하며, 사장석과 알칼리장석은 낮은 함량으로 존재한다. 이러한 차이는 열수에 의한 광물의 변질작용 때문인 것으로 판단된다. 현미경 관찰 결과 또한 열수에 의한 불소함유광물의 생성이 대부분의 시료에서 관찰된다. 따라서 용유도 등지에 넓게 분포하는 동일한 연령의 흑운모화강암의 암석·광물학적인 차이는 소규모 지질학적 사건에 의한 열수변질작용에 의한 것으로 해석할 수 있다.

• 전기전자학회논문지
• /
• 제26권2호
• /
• pp.319-328
• /
• 2022

베어링은 기계가 작동할때 중요한 역할을 한다. 때문에, 베어링에 결함이 발생하면 기계전체의 치명적인 결함을 발생시킨다. 그러므로 베어링 결함은 조기에 발견되어야한다. 본 논문에서는 연속 웨이블릿 변환과 Switchable 정규화를 기반으로 한 합성곱 신경망(SN-CNN)을 이용한 방법을 베어링 결함 감지 모델에 대해 설명한다. 모델의 정확도는 Case Western Reserve University(CWRU) 베어링 데이터 집합을 사용하여 측정되었다. 또한 배치 정규화(BN, Batch Normalization)[1] 방법과 스펙트로그램 이미지가 모델 성능의 비교를 위해 사용되었다.

• 한국소음진동공학회논문집
• /
• 제14권12호
• /
• pp.1287-1294
• /
• 2004

Hub bearings not only sustain the body of a cat, but permit wheels to rotate freely. Excessive radial or axial load and many other reasons can cause defects to be created and grown in each component. Therefore, nitration and noise from unwanted defects in outer-race, inner-race or ball elements of a Hub bearing are what we want to detect as early as possible. How early we can detect the faults has to do with how the detection algorithm finds the fault information from measured signal. Fortunately, the bearing signal has Periodic impulse train. This information allows us to find the faults regardless how much noise contaminates the signal. This paper shows the basic signal processing idea and experimental results that demonstrate how good the method is.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2004년도 춘계학술대회논문집
• /
• pp.593-596
• /
• 2004

Hub bearings not only sustain the body of a car, but permit wheels to rotate freely. Excessive radial or axial load and many other reasons can cause defects to be created and grown in each component. Therefore, vibration and noise from unwanted defects in outer-race, inner-race or ball elements of a Hub bearing are what we want to detect as early as possible. How early we can detect the faults has to do with how the detection algorithm finds the fault information from measured signal. Fortunately, the bearing signal has periodic impulse train. This information allows us to find the faults regardless how much noise contaminates the signal. This paper shows the basic signal processing idea and experimental results that demonstrate how good the method is.

• 한국산업융합학회 논문집
• /
• 제23권5호
• /
• pp.825-833
• /
• 2020

Currently, the K-Water uses various valves that can be remotely controlled for optimal water management. Valve system fault can be classified into rotor defects, stator defects, bearing defects, and gear defects of induction motors. If the valve cannot be operated due to a gear fault, the water management operation can be greatly affected. For effective water management, there is an urgent need for preemptive repairs to determine whether gear is damaged through failure prediction diagnosis.. Recently, deep learning algorithms are being applied for valve failure diagnosis. However, the method currently applied has a disadvantage of attaching a vibration sensor to the valve. In this paper, propose a new algorithm to determine whether a fault exists using a convolutional neural network (CNN) based on the voltage and current information of the valve without additional sensor mounting. In particular, a normalized Lisasjous diagram was used to maximize the fault classification performance in the CNN-based diagnostic system.