• Journal of Institute of Control, Robotics and Systems
• /
• v.20 no.6
• /
• pp.635-640
• /
• 2014

Detection and diagnosis of incipient bearing fault in an induction motor is important for the prevention of serious motor failure. This paper presents an analysis of the effect of a faulty bearing on the stator current of an induction motor. A bearing fault leads to torque oscillations which result in phase modulation of the stator current. Since the torque oscillations cause specific frequency components at the stator current spectrum to rise sharply, the bearing fault can be detected by checking out the faultrelated frequency. In this paper, a mathematical model of the load torque oscillation caused by a bearing fault is presented. The proposed model can be used to analyze the physical phenomenon of a bearing fault in an induction motor. In order to represent the bearing fault effect, the proposed model is combined with an existing model of vector-controlled induction motors. A set of simulation results demonstrate the effectiveness of the proposed model and represent that bearing fault detection using a stator current is useful for vector-controlled induction motors.

• Smart Media Journal
• /
• v.6 no.2
• /
• pp.33-41
• /
• 2017

Railway point machines act as actuators that provide different routes to trains by driving switchblades from the current position to the opposite one. Since point failure caused by the aging effect can significantly affect railway operations with potentially disastrous consequences, replacement detection of point machine at an appropriate time is critical. In this paper, we propose a replacement condition detection method of point machine in railway condition monitoring systems using electrical current signals, after analyzing and relabeling domestic in-field replacement data by means of OLAP(On-Line Analytical Processing) operations in the multidimensional data cube into "does-not-need-to-be replaced" and "needs-to-be-replaced" data. The system enables extracting suitable feature vectors from the incoming electrical current signals by DWT(Discrete Wavelet Transform) with reduced feature dimensions using PCA(Principal Components Analysis), and employs SVM(Support Vector Machine) for the real-time replacement detection of point machine. Experimental results with in-field replacement data including points anomalies show that the system could detect the replacement conditions of railway point machines with accuracy exceeding 98%.

• Journal of Korean Society for Quality Management
• /
• v.49 no.4
• /
• pp.581-594
• /
• 2021

Purpose: The purpose of this study is to compare machine learning models for anomaly detection of mechanical facility equipment and suggest an anomaly detection system for mechanical facility equipment in subway stations. It helps to predict failures and plan the maintenance of facility. Ultimately it aims to improve the quality of facility equipment. Methods: The data collected from Daejeon Metropolitan Rapid Transit Corporation was used in this experiment. The experiment was performed using Python, Scikit-learn, tensorflow 2.0 for preprocessing and machine learning. Also it was conducted in two failure states of the equipment. We compared and analyzed five unsupervised machine learning models focused on model Long Short-Term Memory Variational Autoencoder(LSTM-VAE). Results: In both experiments, change in vibration and current data was observed when there is a defect. When the rotating body failure was happened, the magnitude of vibration has increased but current has decreased. In situation of axis alignment failure, both of vibration and current have increased. In addition, model LSTM-VAE showed superior accuracy than the other four base-line models. Conclusion: According to the results, model LSTM-VAE showed outstanding performance with more than 97% of accuracy in the experiments. Thus, the quality of mechanical facility equipment will be improved if the proposed anomaly detection system is established with this model used.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.7 no.2
• /
• pp.102-108
• /
• 2007

The issues of preventive and condition-based maintenance, online monitoring, system fault detection, diagnosis, and prognosis are of increasing importance. This study introduces a technique to detect and identify faults in induction motors. Stator currents were measured and stored by time domain. The time domain is not suitable for representing current signals, so wavelet transform is used to convert the signal; onto frequency domain. The raw signals can not show the significant feature, therefore difference values are applied. The difference values were transformed by wavelet transform and the features are extracted from the transformed signals. The dynamic time warping method was used to identify the four fault types. This study describes the results of detecting fault using wavelet analysis.

• Proceedings of the KIEE Conference
• /
• 2008.04a
• /
• pp.199-200
• /
• 2008

Demand for reliability and safety in modem systems has been increased in the research on fault detection and isolation. At traditional approaches to fault detection, redundant sensors have been used. More advanced methods are the residual analysis of signals which are created by the comparison between the actual plant behavior and the output response of a mathematical model. However, mathematical system models are difficult to obtain by using physical laws. These problems can be solved by system identification. In this paper, the transfer function of a direct current motor is estimated by using the system identification. And, the efficiency of the fault detector design is verified by using experiments.

• Proceedings of the KIPE Conference
• /
• 2001.10a
• /
• pp.365-368
• /
• 2001

The advantage of the squirrel cage induction motor is the brush less rotor. This advantage for operation and maintenance turns out to be a disadvantage for the detection of the cage rotor bar and endring defects, which means that the detection of cage faults is due to the measurement and analysis of only the stator input signals. The monitoring task in an inverter drive is complicated mainly because the voltage and current waveforms are nonsinusoidal and the high dv/dt values from fast switching inverterd distort the measurements. In this paper, we are going to discuss the detection method of broken rotor bar of the inverter fed squirrel cage induction motor by the motor current signature analysis(MCSA) and the opening terminal voltage signal analysis.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.9 no.2
• /
• pp.261-266
• /
• 2014

The current status of domestic monitoring centers was reviewed and the pattern-based security monitoring system and the centralized security monitoring system, both of which are the characteristics of security monitoring systems, were analyzed together with their advantages and disadvantages. In addition, as for a development plan of domestic security monitoring systems, in order to improve the problems of the existing pattern-based centralized monitoring system, Honeynet and Darknet, which are based on anomalous behavior detection, were analyzed and their application plans were described.

• Journal of Electrical Engineering and Technology
• /
• v.2 no.4
• /
• pp.485-493
• /
• 2007

This paper deals with the problem of detection of induction motor incipient faults. Artificial Neural Network (ANN) approach is applied to detect two types of incipient faults (1). Interturn insulation and (2) Bearing wear faults in single-phase induction motor. The experimental data for five measurable parameters (motor intake current, rotor speed, winding temperature, bearing temperature and the noise) is generated in the laboratory on specially designed single-phase induction motor. Initially, the performance is tested with two inputs i.e. motor intake current and rotor speed, later the remaining three input parameters (winding temperature, bearing temperature and the noise) were added sequentially. Depending upon input parameters, the four ANN based fault detectors are developed. The training and testing results of these detectors are illustrated. It is found that the fault detection accuracy is improved with the addition of input parameters.

• Journal of Magnetics
• /
• v.13 no.1
• /
• pp.30-33
• /
• 2008

A highly sensitive, giant magnetoresistance-spin valve (GMR-SV) biosensing device with high linearity and very low hysteresis was fabricated by photolithography. The detection of magnetic nanoparticles and Fe-hemoglobin inside red blood cells using the GMR-SV biosensing device was investigated. When a sensing current of 1 mA was applied to the current electrode in the patterned active devices with an area of $2{\times}6{\mu}m^2$, the output signals were about 13.35 mV. The signal from even one drop of human blood and nanoparticles in distilled water was sufficient for their detection and analysis.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2010.06a
• /
• pp.95-95
• /
• 2010

Because of the environmental matters the importance of the city railroad is as time goes by increasing. The case of obstacle of the power equipment which supplies electric power to city railroad will occur social and economical enormous loss. Thus, I studied on the preventing method in advance which makes it possible for us to maintain facilities efficiently. The main check points of the power facilities are voltage, current, humidity, partial discharge, move current. These points are gathered by sensor and transmitting to data acquisition device. These data are used to check equipment status in real time. In this paper I described in brief test process and results of the detection system.