• Journal of Korea Multimedia Society
• /
• v.25 no.11
• /
• pp.1547-1556
• /
• 2022

As mechanical facilities are interacting with each other, the failure of some equipment can affect the entire system, so it is necessary to quickly detect and diagnose the abnormality of mechanical equipment. This study proposes a deep learning model that can effectively diagnose abnormalities in rotating machinery and equipment. CNN is widely used for feature extraction and LSTMs are known to be effective in learning sequential information. In LSTM, the number of parameters and learning time increase as the length of input data increases. In this study, we propose a method of segmenting an input segment signal into shorter-length sub-segment signals, sequentially inputting them to CNN through a time-distributed method for extracting features, and inputting them into LSTM. A failure diagnosis test was performed using the vibration data collected from the motor for ventilation equipment installed at the urban railway station. The experiment showed an accuracy of 99.784% in fault diagnosis. It shows that the proposed method is effective in the fault diagnosis of rotating machinery and equipment.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.26 no.2
• /
• pp.113-121
• /
• 2023

High-precision lasers and anti-aircraft radars are the main equipment to protect the Korean Peninsula, and require preemptive maintenance before signs of failure. Of the key components in the drive sector, bearings do not have a fault alarm function. Therefore, the technology for diagnosing defects in bearings before the performance degradation of equipment occurs is becoming more important. In this paper, for the experimental analysis, we measured the acceleration of the four sets of the same lot using acceleration sensors. Through periodic measurements, the factors that changed until the bearing stopped rotating were analyzed. To determine the replacement time, the main factors and threshold values of the bearing signal were analyzed. The error of the theoretical and experimental analysis results of the defect frequency was within 2.8 %, and the validity of the theoretical analysis results could be confirmed. Based on the results, it is possible to remotely transmit trouble alerts to users through the system check function.

• Proceedings of the KIEE Conference
• /
• 2006.04b
• /
• pp.182-184
• /
• 2006

A down-scaled simulator is developed to simulate typical faults in induction motor such as short-turn stator winding, broken rotor bar, dynamic and static air-gap eccentricity, bearing trouble, and mechanical unbalance. The simulator is used as an initial builder to develop design algorithm for real-time faults detecting system by processing an abnormal signal and characteristics in each fault.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.41 no.9
• /
• pp.973-983
• /
• 1992

A very fast algorithm, using fast Haar transformation with half a cycle dc-offset free data, to extract the power frequency components and to detect faults in power systems is proposed. For the speed-up, two important techniques are used. First, according to the symmetric characteristics of sine and cosine functions, fundamental frequency components are calculated with only half a cycle sample data. For using these characteristics, post-fault de-offset components must be removed beforehand. Therefore, secondly, a newly designed digital filter is used to remove exponentially decaying dc-offset from the post-fault signal. In accordance with series simulations, transmission line faults can be detected in around half a cycle after faults.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2006.11a
• /
• pp.411-416
• /
• 2006

Fault detection and diagnosis is the most important technology in condition-based maintenance(CBM) system that usually begins from collecting signatures of running machines using multiple sensors for subsequent accurate analysis. With the quick development in industry, there is an increasing requirement of selecting special sensors that are cheap, robust, and easy-installation. This paper experimentally investigated performances of four types of sensors used in induction motors faults diagnosis, which are vibration, current, voltage and flux. In addition, diagnostic effects of five popular classifiers also were evaluated. First, the raw signals from the four types of sensors are collected at the same time. Then the features are calculated from collected signals. Next, these features are classified through five classifiers using artificial intelligence techniques. Finally, conclusions are given based on the experiment results.

• Proceedings of the Korean Institute of IIIuminating and Electrical Installation Engineers Conference
• /
• 2007.05a
• /
• pp.274-279
• /
• 2007

The fault identification of electrical rotating machinery have been special interests due to one of important elements in the industrial production line. It is directly related with products quality and production costs. The sudden breakdown of a motor will affect to the shut down of the whole processes. Therefore, rotating machines are required to a periodic diagnosis and maintenance for improving its reliability and increasing their lifetime. The objective of this work is to develop the diagnosis system with current signals for the effective identification of healthy and faulty motors using the developed diagnosis algorithm, which consists of the feature calculation, feature extraction, and feature classification procedures.

• 제어로봇시스템학회:학술대회논문집
• /
• 1987.10a
• /
• pp.836-841
• /
• 1987

Many kinds of conditioning monitoring technique have been studied, so this study has investigated the possibility of checking the trend in the fault diagnosis of ball bearing, one of the elements of rotating machine, by applying the cepstral analysis method using the adaptive noise cancelling (ANC) method. And computer simulation is conducted in oder to identify obviously the physical meaning of ANC. The optimal adaptation gain in adaptive filter is estimated, the performance of ANC according to the change of the signal to noise ratio and convergence of LMS algorithm is considered by simulation. It is verified that cepstral analysis using ANC method is more effective than the conventional cepstral analysis method in bearing fault diagnosis.

• Journal of Mechanical Science and Technology
• /
• v.20 no.7
• /
• pp.929-940
• /
• 2006

Early detection and diagnosis of incipient induction machine faults increases machinery availability, reduces consequential damage, and improves operational efficiency. However, fault detection using analytical methods is not always possible because it requires perfect knowledge of a process model. This paper proposes a neural network based expert system for diagnosing problems with induction motors using vibration analysis. The short-time Fourier transform (STFT) is used to process the quasi-steady vibration signals, and the neural network is trained and tested using the vibration spectra. The efficiency of the developed neural network expert system is evaluated. The results show that a neural network expert system can be developed based on vibration measurements acquired on-line from the machine.

• Journal of the Korean Society for Railway
• /
• v.9 no.5 s.36
• /
• pp.612-617
• /
• 2006

As the on-board electric devices determine the performances of vehicles, production of reliable devices is important. To keep the reliability of devices constant, management of performance evaluation of the on-board devices is crucial. Because temperature has a serious effect on failures of the components of the devices, its measurement is the first step for good management. In this study, we described performance characteristics of domestic auxiliary block developed through G7 project. We measured the performances of auxiliary block during test running by the developed on-line measurement system. After we save the input real-time data from each signal of Korean High Speed Train through the network line, we can acquire necessary information through post-processing program. We verify the motor block characteristics of Korean High Speed Train by this system.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2002.05a
• /
• pp.453-459
• /
• 2002

In this paper. the correlation among vibration. wear and temperature are experimentally investigated when rubbing is caused by static and dynamic forces. Each measurement reflects the characteristics of the system and is useful in detecting and diagnosing the current status of rotating machinery. For experiment, the rotor system with lubricating equipment such as trochoid pump, oil tank and wear detecting sensor is implemented to simulate the rubbing condition. Experimental results show that significant change in wear quantity can be notified when vibration signal is changed by rubbing. The results can be applied to system monitoring and fault diagnosis in rotating machinery.