• Journal of the Korean Society for Railway
• /
• v.2 no.2
• /
• pp.13-20
• /
• 1999

The vibration signals of driving parts of electric train are distorted its signal patterns due to the impact components, which occurs when wheel passes rail joints. An elimination method of the impact components is investigated using adaptive signal processing technique in this study The result shows that adaptive interference canceling method seems to be more effective than line enhancement technique. The application of adaptive interference canceling method to the signal measured at bogie shows that the extractions of the signals of driving parts of traction motor, reduction gear, and axle bearing are successful. Therefore, only the signals of bogie, which is the place to attach an accelerometer easily, is sufficient for the fault diagnosis and the safety evaluation of electric train. Also, adaptive interference canceling method can be applicable to evaluate the performance of vibration isolation between bogie and car body and to investigate the characteristics of indoor sound.

• Journal of Power Electronics
• /
• v.14 no.5
• /
• pp.859-865
• /
• 2014

This study presents an electromagnetic model for predicting shaft voltages in a 2-pole field-excited synchronous generator. After the first observations on shaft voltages were made more than a century ago, extensive work has been conducted on eliminating, mitigating, and integrating the aforementioned phenomena. Given that emphasis has been placed on modeling shaft- and bearing-induced voltages in AC motors driven by variable frequency drives, similar efforts toward a model that is dedicated to generators are insubstantial. This work endeavors to improve current physical interpretation and prediction methods for shaft-induced voltages in generators through semi-analytical derivation. Aside from the experimental validation of the model, investigations regarding the behavior of shaft voltages under varying machine complexities and operating conditions clarify previous uncertainties regarding these phenomena. The performance of the numerical method is also assessed for application in eccentricity fault diagnosis.

• Smart Structures and Systems
• /
• v.29 no.6
• /
• pp.757-766
• /
• 2022

To train deep learning algorithms, a sufficient number of data are required. However, in most engineering systems, the acquisition of fault data is difficult or sometimes not feasible, while normal data are secured. The dearth of data is one of the major challenges to developing deep learning models, and fault diagnosis in particular cannot be made in the absence of fault data. With this context, this paper proposes an anomaly detection methodology for rotating machines using only normal data with self-labeling. Since only normal data are used for anomaly detection, a self-labeling method is used to generate a new labeled dataset. The overall procedure includes the following three steps: (1) transformation of normal data to self-labeled data based on a pretext task, (2) training the convolutional neural networks (CNN), and (3) anomaly detection using defined anomaly score based on the softmax output of the trained CNN. The softmax value of the abnormal sample shows different behavior from the normal softmax values. To verify the proposed method, four case studies were conducted, on the Case Western Reserve University (CWRU) bearing dataset, IEEE PHM 2012 data challenge dataset, PHMAP 2021 data challenge dataset, and laboratory bearing testbed; and the results were compared to those of existing machine learning and deep learning methods. The results showed that the proposed algorithm could detect faults in the bearing testbed and compressor with over 99.7% accuracy. In particular, it was possible to detect not only bearing faults but also structural faults such as unbalance and belt looseness with very high accuracy. Compared with the existing GAN, the autoencoder-based anomaly detection algorithm, the proposed method showed high anomaly detection performance.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.4 no.5
• /
• pp.951-961
• /
• 2000

A diagnosis system that provides early warnings regarding machine malfunction is very important for rolling mill so as to avoid great losses resulting from unexpected shutdown of the production line. But it is very difficult to provide early warnings in rolling mill. Because dynamics of rolling mill is non-linear. This Paper proposes a new method for diagnosis of rolling mill using wavelet transform(W) to solve this problem. Proposed method that measures the vibration signals of rolling mill on-line and analyze it using wavelet to acquire pattern data. And we design a fault-diagnosis system that diagnose a rolling mill using this data. Validity of the new method is asserted by real numerical data experiment.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.19 no.3
• /
• pp.151-158
• /
• 2024

Although on-device artificial intelligence (AI) has gained attention to diagnosing machine faults in real time, most previous studies did not consider the model retraining and redeployment processes that must be performed in real-world industrial environments. Our study addresses this challenge by proposing an on-device AI-based real-time machine fault diagnosis system that utilizes continual learning. Our proposed system includes a lightweight convolutional neural network (CNN) model, a continual learning algorithm, and a real-time monitoring service. First, we developed a lightweight 1D CNN model to reduce the cost of model deployment and enable real-time inference on the target edge device with limited computing resources. We then compared the performance of five continual learning algorithms with three public bearing fault datasets and selected the most effective algorithm for our system. Finally, we implemented a real-time monitoring service using an open-source data visualization framework. In the performance comparison results between continual learning algorithms, we found that the replay-based algorithms outperformed the regularization-based algorithms, and the experience replay (ER) algorithm had the best diagnostic accuracy. We further tuned the number and length of data samples used for a memory buffer of the ER algorithm to maximize its performance. We confirmed that the performance of the ER algorithm becomes higher when a longer data length is used. Consequently, the proposed system showed an accuracy of 98.7%, while only 16.5% of the previous data was stored in memory buffer. Our lightweight CNN model was also able to diagnose a fault type of one data sample within 3.76 ms on the Raspberry Pi 4B device.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2013.10a
• /
• pp.331-337
• /
• 2013

Acoustic Emission technique is widely applied to develop the early fault detection system, and the problem about a signal processing method for AE signal is mainly focused on. In the signal processing method, envelope analysis is a useful method to evaluate the bearing problems and Wavelet transform is a powerful method to detect faults occurred on rotating machinery. However, exact method for AE signal is not developed yet. Therefore, in this paper two methods which are Hilbert transform and DET for feature extraction. In addition, we evaluate the classification performance with varying the parameter from 2 to 15 for feature selection DET, 0.01 to 1.0 for the RBF kernel function of SVR, and the proposed algorithm achieved 94% classification accuracy with the parameter of the RBF 0.08, 12 feature selection.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2000.06a
• /
• pp.1102-1107
• /
• 2000

The signals that can be obtained from a rotating machine often convey the information of machine. For example, if the machine under investigation has faults, then we can measure the signal which has a pulse train, embedded in noise. Therefore the ability to detect the fault signal in noise determines the degree of diagnosis level of rotating machine. In this paper, minimum variance cepstrum (MV cepstrum), which can easily detect impulse in noise, has been applied to detect the type of faults of ball bearing system. To test the performance of this technique, experiment has been performed for ball bearing elements that have man made faults. Results show that minimum variance cepstrum can easily detect the periodicity due to faults.

• Journal of the Korean Society of Safety
• /
• v.15 no.2
• /
• pp.1-7
• /
• 2000

This paper presents the approach involving fault detection and diagnosis of gears using pattern recognition and Wavelet transform. It describes result of the comparison between KDI (Kullback Discrimination Information) with the nearest neighbor classification rule as one of pattern recognition methods and Wavelet transform to know a way to detect and diagnosis of gear damages experimentally. To model the damages 1) Normal (no defect), 2) one tooth is worn out, 3) All teeth faces are worn out 4) One tooth is broken. The vibration sensor was attached on the bearing housing. This produced the total time history data that is 20 pieces of each condition. We chose the standard data and measure distance between standard and tested data. In Wavelet transform analysis method, the time series data of magnitude in specified frequency (rotary and mesh frequency) were earned. As a result, the monitoring system using Wavelet transform method and KDI with nearest neighbor classification rule successfully detected and classified the damages from the experimental data.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.15 no.4
• /
• pp.134-140
• /
• 2016

Main Spindle System has effect on performance of machine tools and working quality as well as is required of high reliability. Especially, it takes great importance in producing automobiles which includes a large number of working processes. However, main spindle unit in Machine tools are often cases where damage occurs do not meet the design life due to driving in harsh environments. This is when excessive maintenance and repair of machine tools or for damage stability has resulted in huge economic losses. Therefore, this studying propose a method of accelerated life test for diagnosing and prognosis the state of life assessment main spindle system. Time status monitoring of diagnostic data - through the analysis of the frequency band signals were carried out inside the main spindle bearing condition monitoring and fault diagnosis.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.28 no.5
• /
• pp.23-30
• /
• 2014

This paper presents an on-line diagnosis system for identifying health and faulted conditions in squirrel-cage induction motors using stator current, temperature, and partial discharge signals. The proposed diagnosis system can diagnose induction motor faults such as broken rotor bars, air-gap eccentricities, stator winding insulations, and bearing faults. Experimental results obtained from induction motors show that the proposed system is capable of detecting induction motor faults.