• Journal of the Korean Society for Precision Engineering
• /
• v.21 no.12
• /
• pp.75-83
• /
• 2004

With the rotating machinery getting more accurate and diversified, the necessity fur an appropriate diagnosis technique and maintenance system has been greatly recognized. However, until now, the operator has executed a monitoring of the machine by the senses or simple the change of RMS (root mean Square) value. So, the diagnostic expert system using the fuzzy inference which the operator can judge easily and expertly a condition of the machine is developed through this study. In this paper, the hardware and software of the diagnostic expert system was composed and the identification of the diagnostic performance of the developed system for 5 fault phenomena was carried out.

• Tribology and Lubricants
• /
• v.3 no.1
• /
• pp.52-60
• /
• 1987

Many kinds of condition monitoring technique as the preventive maintenance technique have been studied, so this study has investigated the possibility of chbcking the trend in the fault diagnosis of ball bearing, one of the important elements of rotating machine, by applying the cepstral analysis method. And computer simulation is conducted in order to identify obviously the physical meaning of cepstral analysis. It is identified that cepstral analysis is effective method to distinguish between the basic and reflected wave by computer simulation, and we know that it is possible to apply the cepstral analysis to the arbitrary elements of rotating machine which are different in fundamental frequency. It is verified that cepstral analysis method is more effective than the other conventional method in bearing fault diganosis.

• Journal of Power Electronics
• /
• v.8 no.3
• /
• pp.228-238
• /
• 2008

Many induction motor broken bar diagnosis methods are based on evaluating special components in machine signals spectrums. Current, power, flux, etc are among these signals. Frequencies related to a broken rotor fault are slip dependent, therefore, correct diagnosis of fault - especially when obtrusive frequency components are present - depends on accurate determination of motor velocity and slip. The traditional methods typically require several sensors that should be pre-installed in some cases. This paper presents a diagnosis method based on only a vibration sensor. Motor velocity oscillation due to a broken rotor causes frequency components at twice slip frequency difference around speed frequency in vibration spectrum. Speed frequency and its harmonics as well as twice supply frequency, can easily and accurately be found in a vibration spectrum, therefore th motor slip can be computed. Now components related to rotor fault can be found. It is shown that a trained neural network - as a substitute for an expert person - can easily categorize the existence and the severity of a fault according to the features extracted from the presented method. This method requires no information about th motor internal and has been able to diagnose correctly in all the laboratory tests.

• Transactions of the Korean hydrogen and new energy society
• /
• v.34 no.5
• /
• pp.478-489
• /
• 2023

In this study, fault diagnosis and detection methods developed to ensure the reliability of polymer electrolyte membrane (PEM) hydrogen electrolysis systems have been proposed. The proposed method consists of model development and data generation of the PEM hydrogen electrolysis system, and data-driven fault diagnosis learning model development. The developed fault diagnosis learning model describes how to detect and classify faults in the sensors and components of the system.

• 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.

• Journal of the Korean Society for Precision Engineering
• /
• v.12 no.11
• /
• pp.82-90
• /
• 1995

This paper pressents a condition-based maintenance (CBM) method through bibration analysis. The well known frequency analysis is employed for performing machine fault diagnosis. The statistical control chart is also applied for analyzing the trend of the bearing wear. Vibration sensors are attached to prototype machine and signals are continuously monitored. The sampled data are utilized to evaluate how well the fast fourier transform(FFT) and the statistical control chart techniques could be used to identify defects of machine and to analyze the machine degradation. Experimental results show that the propowed approach could classify every mal-function and could be utilized for real machine diagnosis system.

• Journal of Applied Reliability
• /
• v.14 no.4
• /
• pp.208-212
• /
• 2014

An experimental gear-box was set-up to simulate the real situation of the wind-turbine. Artificial cracks of different sizes were machined into the gear. Vibration signals were acquired to diagnose the different crack fault conditions. Time-domain features such as root mean square, variance, kurtosis, normalized 6th central moments were used to capture the characteristics of different crack conditions. Normal condition, 1 mm crack condition, 2mm crack condition, 6mm crack condition, and tooth fault condition were compared using ANFIS and DAG-SVM methods, and three different DAG-SVM models were compared. High-pass filtering improved the success rates remarkably in the case of DAG-SVM.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2003.10a
• /
• pp.137-142
• /
• 2003

A fundamental study for developing a system of fault diagnosis of a pump is performed by using neural network. The acoustic signals were obtained and converted to frequency domain for normal products and artificially deformed products. The signals were obtained in various driving frequencies in order to obtain many types of data from a limited number of pumps. The acoustic data in frequency domain were managed to multiples of real driving frequency with the aim of easy comparison. The neural network model used in this study was 3-layer type composed of input, hidden, and output layer. The normalized amplitudes at the multiples of real driving frequency were chosen as units of input layer, Various sets of teach signals made from original data by eliminating some random cases were used in the training. The average errors were approximately proportional to the number of untaught data. The results showed neural network trained by acoustic signals can be used as a simple method far a detection of machine malfunction or fault diagnosis.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2000.05a
• /
• pp.639-642
• /
• 2000

Chemical facility system have dangerous elements that can injure the human like an explosion and a fire, gas poisoning by a leakage of the harmful chemical material. In addition to a vibration of the machine occurs the leakage. Therefore, the chemical factory requires for periodic monitoring of the vibration. But, until now, the operator has executed a monitoring of the machine by the senses. So, the diagnostic expert system by which the operator can judge easily and expertly a condition of the machine is developed. This paper describes the structure of diagnostic system and the diagnostic algorithm using fuzzy inference

• Journal of Electrical Engineering and Technology
• /
• v.10 no.6
• /
• pp.2315-2325
• /
• 2015

Induction motors are widely used in industrial processes since they offer a very high degree of reliability. But like any other machine, they are vulnerable to faults, which if left unmonitored, might lead to an unexpected interruption at the industrial plant. Therefore, the condition monitoring of the induction motors have been a challenging topic for many electrical machine researchers. Indeed, the effectiveness of the fault diagnosis and prognosis techniques depends very much on the quality of the fault features selection. However, in induction-motor drives, rotor defects are the most complex in terms of detection since they interact with the supply frequency within a restricted band around this frequency, especially in the no-loaded case. To overcome this drawback, this paper deals with an efficient and new method to diagnose the induction-motor rotor fault based on the digital implementation of the monitoring algorithm based on the association of the Time Synchronous Averaging technique and Discrete Wavelet Transform. Experimental results are presented in order to show the effectiveness of the proposed method. The obtained results are largely satisfactory, indicating a promising industrial application of the combined “Time Synchronous Averaging – Discrete Wavelet Transform” approach.