• IEMEK Journal of Embedded Systems and Applications
• /
• v.14 no.6
• /
• pp.287-294
• /
• 2019

With the automation of production lines in the manufacturing industry, the importance of real-time fault diagnosis of facility is increasing. In this paper, we propose a fault diagnosis algorithm of LM (Linear Motion)-guide based on deep learning using vibration signals. Generally, in order to guarantee the performance of the deep learning, it is necessary to have a sufficient amount of data, but in a manufacturing industry, it is often difficult to obtain enough data due to physical and time constraints. To solve this problem, we propose a convolutional neural networks (CNN) model based on transfer learning. In addition, the spectrogram image is input to the CNN to reflect the frequency characteristic of the vibration signals with time. The performance of fault diagnosis according to various load condition and transfer learning method was compared and evaluated by experiments. The results showed that the proposed algorithm exhibited an excellent performance.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.67 no.5
• /
• pp.626-634
• /
• 2018

These days, widespread use of sensitive loads and distributed generators makes static transfer switch (STS) an essential component in power circuits to achieve a good power quality for AC Grids. In case of a short-circuit fault, previous STS cannot break the fault current. However, the proposed STS has the capability of breaking it quickly as a circuit breaker. Also if there are power quality problems such as Sag/Swell, the proposed STS can quickly transfers the load to the good quality source. Furthermore it is proved that the transfer time of the proposed STS is within one half of period of 3-phase source frequency regardless of the type of load. It is anticipated that the proposed STS may be utilized to realize many stable and reliable AC grid systems.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.43 no.2
• /
• pp.179-188
• /
• 1994

This paper deals with implementation of an expert system to obtain an optimal plan of load transfer for fault restoration with the capability of security monitoring and assessment in distribution systems. Based on the technique of load transfer tree analysis, the proposed expert system can afford to assist system operators in proposing an optimal plan of load transfer for fault restoration, In paticular, an application of the proposed ES to practical distribution systems yields an optimal load transfer plan which ensures system security by considering security assessment for contingency of feeders and main transformers in the knowledge based sense.

• Journal of the Microelectronics and Packaging Society
• /
• v.31 no.2
• /
• pp.45-53
• /
• 2024

The maintenance of semiconductor equipment is crucial for the continuous growth of the semiconductor market. System management is imperative given the anticipated increase in the capacity and complexity of industrial equipment. Ensuring optimal operation of manufacturing processes is essential to maintaining a steady supply of numerous parts. Particularly, monitoring the status of substrate transfer robots, which play a central role in these processes, is crucial. Diagnosing failures of their major components is vital for preventive maintenance. Fault diagnosis methods can be broadly categorized into physics-based and data-driven approaches. This study focuses on data-driven fault diagnosis methods due to the limitations of physics-based approaches. We propose a methodology for data acquisition and preprocessing for robot fault diagnosis. Data is gathered from vibration sensors, and the data preprocessing method is applied to the vibration signals. Subsequently, the dataset is trained using Gradient Tree-based XGBoost machine learning classification algorithms. The effectiveness of the proposed model is validated through performance evaluation metrics, including accuracy, F1 score, and confusion matrix. The XGBoost classifiers achieve an accuracy of approximately 92.76% and an equivalent F1 score. ROC curves indicate exceptional performance in class discrimination, with 100% discrimination for the normal class and 98% discrimination for abnormal classes.

• 한국지구물리탐사학회:학술대회논문집
• /
• 2008.10a
• /
• pp.149-154
• /
• 2008

We analyzed the Coulomb stress transfer near a small-scale reverse fault. For the modeling we used the geometry of a Quaternary fault in Gyeongju area, Eupcheon fault. For an assumed reverse faulting slip of 10cm, the resulting values of the Coulomb stress change are relatively higher (>2 bar) near the edges (both downward and lateral) of the fault, and diminish slightly upward and downward. The equivalents are negative in the zone immediately below and above the fault, exhibiting a "T" shape of low stress zone in the vertical profile of the fault. This study demonstrates the possible ranges and directions the aftershock energy would propagates after a reverse faulting.

• 한국초전도학회:학술대회논문집
• /
• v.16
• /
• pp.61-61
• /
• 2006

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.2570-2575
• /
• 2003

Monitoring a power transmission line is significant for power electric companies. In this paper, we propose a new method for detecting an fault point of power transmission line by use of M-sequence correlation technique. In this method, detecting signal is used as one or plural M-sequences ( same characteristic polynomial, including normal and reverse mark, synchronized ). In receiving point, we make same sequence with the input one and take crosscorrelation function between M-sequence and the received signal. We can see transfer fanctions of plural paths between inputs and a output taps separated from different of delay times on the crosscorrelation function, and from these transfer fanctions, so we compare them when fault occurred with in usual.

• Journal of the Korean Society for Precision Engineering
• /
• v.26 no.11
• /
• pp.47-54
• /
• 2009

Spin coaters are the essential instruments in micro-fabrication processes, which apply uniform thin films to flat substrates. In this research, a spin coater diagnosis system is developed to detect the abnormal operation of TFT-LCD process in real time. To facilitate the real-time data acquisition and analysis, the circular-buffered continuous data transfer and the short-time Fourier transform are applied to the fault diagnosis system. To determine whether the system condition is normal or not, a steady-state detection algorithm and a frequency spectrum comparison algorithm using confidence interval are newly devised. Since abnormal condition of a spin coater is rarely encountered, algorithm is tested on a CD-ROM drive and the developed program is verified by a function generator. Actual threshold values for the fault detection are tuned in a spin coater in process.

• Journal of the Korean Society of Safety
• /
• v.21 no.1 s.73
• /
• pp.6-14
• /
• 2006

The development of automatic production systems have required intelligent diagnostic and monitoring functions to overcome system failure and reduce production loss by the failure. In order to perform accurate operations of the intelligent system, implication about total system failure and fault analysis due to each mechanical component failures are required. Also solutions for repair and maintenance can be suggested from these analysis results. As an essential component of a mechanical system, a bearing system is investigated to define the failure behavior. The bearing failure is caused by lubricant system failure, metallurgical deficiency, mechanical condition(vibration, overloading, misalignment) and environmental effects. This study described slab transfer equipment fault train due to stress variation and metallurgical deficiency from lubricant failure by using FTA.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.58 no.9
• /
• pp.1681-1688
• /
• 2009

This paper proposes a new fault restoration method which adopts the recloser as top agent to release the problems of the data concentration and fault processing delay of the existing DAS(distribution Automation System) under the ubiquitous distribution system. In proposed method, top agent collects the data based on the multi-casting communication with the tie switches of the interconnection point, and then selects a closed switch(tie switch) to transfer the sound outage load to other feeders based on the heuristic search strategy step by step until the load transfer work is finished. Here, a new heuristic rule is developed which can guarantee the relational load balancing and line loss from the collected voltage data. Finally, the several faults are simulated for typical multi-section and multi-interconnection distribution system to prove the effectiveness of the proposed strategy, in particular, for each simulation cases, the load balancing index and line loss index of the obtained solution from the proposed method is compared with those of all of feasible solutions.