• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.18 no.2
• /
• pp.185-195
• /
• 2018

As machines have been automated in the field of industries in recent years, it is a paramount importance to manage and maintain the automation machines. When a fault occurs in sensors attached to the machine, the machine may malfunction and further, a huge damage will be caused in the process line. To prevent the situation, the fault of sensors should be monitored, diagnosed and classified in a proper way. In the paper, we propose a sensor fault detection scheme based on SVM and CNN to detect and classify typical sensor errors such as erratic, drift, hard-over, spike, and stuck faults. Time-domain statistical features are utilized for the learning and testing in the proposed scheme, and the genetic algorithm is utilized to select the subset of optimal features. To classify multiple sensor faults, a multi-layer SVM is utilized, and ensemble technique is used for CNN. As a result, the SVM that utilizes a subset of features selected by the genetic algorithm provides better performance than the SVM that utilizes all the features. However, the performance of CNN is superior to that of the SVM.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.36 no.6
• /
• pp.691-698
• /
• 2012

The joining of aluminum and HSS (high-strength steel) by the conventional clinching process is limited by the low formability of HSS. Defects in the clinching joint, such as necking of the upper sheet, cracks, and lack of interlocking, are produced by the different ductility properties of HSS and aluminum. In this study, we propose the hole clinching process for joining Al6061 and SPFC440, in which deformation of SPFC440 is avoided by drilling a hole in the SPFC440. The dimensions of the interlocking in the hole-clinched joint necessary to provide the required joint strength were determined. Based on the volume constant of the hole clinching process, the shapes of the tools were designed by finite element (FE)-analysis. A hole clinching experiment was performed to verify the proposed process. A cross-section of the joint showed good agreement with the results of the FE-analysis. The lap shear strength was found to be 2.56 kN, which is higher than required joint strength.

• Proceedings of the KIPE Conference
• /
• 2010.07a
• /
• pp.512-513
• /
• 2010

최근 일정전압의 신뢰성 있는 전원공급 장치의 개발에 대한 필요성이 날로 증가하고 있다. 기존의 AVR(Automatic Voltage Regulator)은 디지털식이므로 고장시 수리하는데 많은 어려움이 있지만 기계식AVR은 고장시 즉각 대처 할 수 있기 때문에 신뢰성 있는 전원공급 장치로 볼 수 있다. 본 논문에서는 PM(Permanent Magnet)동기발전기에 부하가 걸렸을 때 전원이 리액턴스로 인한 전압강하가 생기므로 기계식AVR을 이용하여 보상하고자한다. SVR(Slidac Voltage Regulator)형 자동전압장치와 절연변압기를 이용하여 기계식AVR을 설정하는 방법을 제시하고 PM동기발전기와 연결하여 전압강하를 보상하는 시뮬레이션을 통하여 검증하였다.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.40 no.8
• /
• pp.721-724
• /
• 2016

Because of the inherent uncertainties caused by the manufacturing process variations, future loading conditions, and incomplete damage models, the lifetimes of mechanical structures under field conditions are significantly different from the results obtained in the laboratories. In this study, a dual sensor was developed to prognosticate the fatigue failure of structures under these uncertain conditions, and its effectiveness was demonstrated on a rectangular columnar structure under repeated uni-axial loading. The dual sensor is a slightly weaker structure embedded in the target structure, so that failure occurs in the sensor earlier than in the target structure. From the signal differences in the strain gauges in the embedded dual sensor, it is possible to differentiate between the normal status and warning status, even under variable loads.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.27 no.7
• /
• pp.1088-1097
• /
• 2021

Vibration data of mechanical equipment inevitably have noise. This noise adversely af ects the maintenance of mechanical equipment. Accordingly, the performance of a learning model depends on how effectively the noise of the data is removed. In this study, the noise of the data was removed using the Denoising Auto Encoder (DAE) technique which does not include the characteristic extraction process in preprocessing time series data. In addition, the performance was compared with that of the Wavelet Transform, which is widely used for machine signal processing. The performance comparison was conducted by calculating the failure detection rate. For a more accurate comparison, a classification performance evaluation criterion, the F-1 Score, was calculated. Failure data were detected using the One-Class SVM technique. The performance comparison, revealed that the DAE technique performed better than the Wavelet Transform technique in terms of failure diagnosis and error rate.

• Journal of Biosystems Engineering
• /
• v.6 no.1
• /
• pp.28-38
• /
• 1981

A survey has been conducted to investigate the presents of breaks down and repair of power tiller for efficient use. Eight provinces were covered for this study. The results are summarized as follows. A. Frequency of breaks down. 1) Power tiller was breaken down 9.05 times a year and it represents a break down every 39.1 hours of use. High frequency of breaks down was found from the fuel and ignition system. For only these system, the number of breaks down were 2.02 and it represents 23.3% among total breaks down. It was followed by attachments, cylinder system, and traction device. 2) For the power tiller which was more than six years old, breaks down accured 37.7 hours of use and every 38.6 hours for the power tiller which was purchased in less than 2 years. 3) For the kerosene engine power tiller, breaks down occured every 36.8 hours of use, which is a higher value compared with diesel engine power tiller which break down every 42.8 hours of use. The 8HP kerosene engine power tiller showed higher frequency of break down compared with any other horse power tiller. 4) In October, the lowest frequency of break down was found with the value of once for every 51.5 hours of use, and it was followed by the frequency of break down in June. The more hours of use, the less breaks down was found. E. Repair place 1) 45.3% among total breaks down of power tiller was repaired by the owner, and 54.7% was repaired at repair shop. More power tiller were repaired at repair shop than by owner of power tiller. 2) The older the power tiller is, the higher percentage of repairing at the repair shop was found compared with the repairing by the owner. 3) Higher percentage of repairing by the owner was found for the diesel engine power tiller compared with the kerosene engine power tiller. It was 10 HP power tiller for the kerosene power tiller and 8 HP for the diesel engine power tiller. 4) 66.7% among total breaks down of steering device was repaired by the owner. It was the highest value compared with the percentage of repairing of any other parts of power tiller. The lowest percentage of repairing by owner was found for the attachments to the power tiller with the value of 26.5%. C. Cause of break down 1) Among the total breaks down of power tiller, 57.2% is caused by the old parts of power tiller with the value of 5.18 times break down a year and 34.7% was caused by the poor maintenance and over loading. 2) For the power tiller which was purchased in less than two years, more breaks down were caused by poor maintenance in comparison to the old parts of power tiller. 3) For the both 8-10 HP kerosene and diesel engine power tiller, the aspects of breaks down was almost the same. But for the 5 HP power tiller, more breaks down was caused by over loading in comparison to the old parts of power tiller. 4) For the cylinder system and traction device, most of the breaks down was caused by the old parts and for the fuel and ignition system, breaks down was caused mainly by the poor maintenance. D. Repair Cost 1) For each power tiller, repair cost was 34,509 won a year and it was 97 won for one hoar operation. 2) Repair cost of kerosene engine power tiller was 40,697 won a year, and it use 28,320 won for a diesel engine power tiller. 3) Average repair cost for one hour operation of kerosene engine power tiller was 103 won, and 86 won for a diesel engine power tiller. No differences were found between the horse power of engines. 4) Annual repair cost of cylinder system was 13,036 won which is the highest one compared with the repair cost of any other parts 362 won a year was required to repair the steering device, and it was the least among repair cost of parts. 5) Average cost for repairing the power tiller one time was 3,183 won. It was 10,598 won for a cylinder system and 1,006 won for a steering device of power tiller. E. Time requirement for repairing by owner. 1) Average time requirements for repairing the break down of a power tiller by owner himself was 8.36 hours, power tiller could not be used for operation for 93.58 hours a year due to the break down. 2) 21.3 hours were required for repairing by owner himself the break down of a power tiller which was more than 6 years old. This value is the highest one compared with the repairing time of power tiller which were purchased in different years. Due to the break down of the power tiller, it could not be used for operation annually 127.13 hours. 3) 10.66 hours were required for repairing by the owner himself a break down of a diesel engine power tiller and 6.48 hours for kerosene engine power tiller could not be used annually 99.14 hours for operation due to the break down and it was 88.67 hour for the diesel engine power tiller. 4) For both diesel and kerosene engine power tiller 8 HP power tiller required the least time for repairing by owner himself a break down compared with any other horse power tiller. It was 2.78 hours for kerosene engine power tiller and 8.25 hours fur diesel engine power tiller. 5) For the cylinder system of power tiller 32.02 hours were required for repairing a break down by the owner himself. Power tiller could not be used 39.30 hours a year due to the break down of the cylinder system.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.14 no.1
• /
• pp.47-52
• /
• 2000

Redundant programmable logic controllers are used in practice with the aim of achieving a higher degree of availability or fault tolerance. Redundancy system is fault tolerant programmable logic controller for machine and plant. It is event synchronized master-standby system with a 2 channel(1-out-of-2) structure. A data link connects line the master to the standby controller.Fault tolerant systems should always be used when it is necessary to keep the probability of a total control system failure to a minimum. The objective of using high availability programmable logic controller is a reduction of losses of fault tolerant system are quickly compensated by the avoidance of loss of production.

• Proceedings of the KIEE Conference
• /
• 2005.11a
• /
• pp.18-20
• /
• 2005

일반적으로 저압계통의 고장전류를 차단하기 위해 설치된 차단기의 차단원리는 주로 역전압발생법올 이용하고 있다. 역전압발생법은 효과적으로 저압계통의 고장전류를 차단할 수 있으나, 제한된 한류성능과 긴 아킹 시간은 차단기는 물론 주변 전력기기에 전기적/열적/기계적 스트레스를 주게 된다. 국내외 업체는 고장전류를 보다 빠르고 효과적으로 제한 및 차단을 할 수 있는 한류형 차단기를 제안하고 있는 실정이다. 저압계통의 경우, 정온도계수 (Positive Temperature Coefficient, PTC) 특성을 가지는 한류소자를 기존 차단기에 직렬 혹은 병렬로 연결하여 저압계통의 고장전류를 매우 빠르고 효과적으로 제한 및 차단하는 추세에 있으며, 또한 PTC 한류소자를 이용함으로써 저압계통의 차단보호협조를 효과적으로 구현하고자 하고 있다. PTC 한류소자는 소자는 열팽창이 큰 비전도성 성분과 열팽창이 작은 전도성 성분이 혼합되어 구성되며, 소자의 온도가 증가함에 따라 비전도성 성분이 상대적으로 큰 부피 팽창을 하여 저항이 증가하게 된다. 이러한 PTC 소자를 전력계통에 적용함으로써 고장전류에 따른 줄열에 의한 저항증가로 고장전류를 제한하게 된다. 본 연구에서는 일반적으로 배터리 보호용으로 사용되는 폴리에틸렌 수지 및 카본블랙으로 구성된 폴리머 PTC 한류소자를 이용하여, 기존의 저전력 배터리 보호 폴리머 PTC 소자로부터, 저압계통의 단락사고시 발생하는 단락전류를 효과적으로 제한할 수 있는 대전력 폴리머 PTC 소자를 개발하였다.

• Journal of the Institute of Convergence Signal Processing
• /
• v.6 no.3
• /
• pp.143-147
• /
• 2005

Monitoring and diagnosis of the operating machines are very important for safety operation and maintenance in the industrial fields. These machines are most rotating machines and the diagnosis of the machines has been researched for long time. We can easily see the faulted signal of the rotating machines from the changes of the signals in frequency. The Linear Predictive Coding(LPC) is introduced for signal analysis in frequency domain. In this paper, we propose fault detection and diagnosis method using the Linear Predictive Coding(LPC) and residual signal energy. We applied our method to the induction motors depending on various status of faulted condition and could obtain good results.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.24 no.8
• /
• pp.55-61
• /
• 2010

In this paper, we proposed selective extraction method of frequency information and PCA-ELM based diagnosis system for three-phase induction motors. As the first step for diagnosis procedure, DFT is performed to transform the acquired current signal into frequency domain. And then, frequency components are selected according to discriminate order calculated by variance As the next step, feature extraction is performed by principal component analysis (PCA). Finally, we used the classifier based on Extreme Learning Machine (ELM) with fast learning procedure. To show the effectiveness, the proposed diagnostic system has been intensively tested with the various data acquired under different electrical and mechanical faults with varying load.