• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.19 no.9
• /
• pp.47-52
• /
• 2020

With the 4th industrial revolution, condition monitoring using machine learning techniques has become popular among researchers. An overload due to complex operations causes several irregularities in MOSFETs. This study investigated the acquired voltage to analyze the overcurrent effects on MOSFETs using a failure mode effect analysis (FMEA). The results indicated that the voltage pattern changes greatly when the current is beyond the threshold value. Several features were extracted from the collected voltage signals that indicate the health state of a switched-mode power supply (SMPS). Then, the data were reduced to a smaller sample space by using a principal component analysis (PCA). A robust machine learning algorithm, the support vector machine (SVM), was used to classify different health states of an SMPS, and the classification results are presented for different parameters. An SVM approach assisted by a PCA algorithm provides a strong fault diagnosis framework for an SMPS.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2012.10a
• /
• pp.388-393
• /
• 2012

Vibration condition monitoring at low rotational speeds is still a challenge. Acoustic emission (AE) is the most used technique when dealing with low speed bearings. At low rotational speeds, the energy induced from surface contact between raceway and rolling elements is very weak and sometimes buried by interference frequencies. This kind of issue is difficult to solve using vibration monitoring. Therefore some researchers utilize artificial damage on inner race or outer race to simplify the case. This paper presents vibration signal analysis of low speed slewing bearings running at a low rotational speed of 15 rpm. The natural damage data from industrial practice is used. The fault frequencies of bearings are difficult to identify using a power spectrum. Therefore the relatively improved method of empirical mode decomposition (EMD), ensemble EMD (EEMD) is employed. The result is can detect the fault frequencies when the FFT fail to do it.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.20 no.9
• /
• pp.28-34
• /
• 2021

The Fourth Industrial Revolution has led to the development of drones for commercial and private applications. Therefore, the malfunction of drones has become a prominent problem. Failure mode and effect analysis was used in this study to analyze the primary cause of drone failure, and blade breakage was observed to have the highest frequency of failure. This was tested using a vibration sensor placed on drones along the breakage length of the blades. The data exhibited a significant increase in vibration within the drone body for blade fracture length. Principal component analysis was used to reduce the data dimension and classify the state with machine learning algorithms such as support vector machine, k-nearest neighbor, Gaussian naive Bayes, and random forest. The performance of machine learning was higher than 0.95 for the four algorithms in terms of accuracy, precision, recall, and f1-score. A follow-up study on failure prediction will be conducted based on the results of fault diagnosis.

• The Journal of Engineering Geology
• /
• v.22 no.1
• /
• pp.113-121
• /
• 2012

The mechanical characteristics of a fault gouge from near Mt. Kumjung in Kumjung-Gu, Busan, were estimated from laboratory tests on different joint models. Fault gouge samples and joint samples in biotite granite were obtained from boreholes in the study area that had penetrated small faults associated with the Dongnae and Yangsan faults. XRD and SEM analyses revealed that for the fault gouge consists of several clay minerals with tabular structure (kaolinite, montmorillonite, illite, sericite), which could cause the considerable reduction of shear strength when wet. The shear strength of the fault gouge was obtained from direct shear tests of the fault gouge itself and from direct shear tests of several natural/artificial joint surfaces coated with fault gouge. The results indicate that the reduction of shear strength is more abrupt for the joint surfaces coated with fault gouge compared with uncoated joint surfaces, and that the friction angle of the fault gouge between joint surfaces is much lower than the internal friction angle of the fault gouge itself. Fault gouges in contact with rock, therefore, could have a stronger negative effect on the stability of structures in rock masses than the fault gouge itself.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.32 no.7
• /
• pp.556-560
• /
• 2008

As higher reliability and accuracy on production facilities are required to detect incipient faults, a diagnostic system for predictive maintenance of the facility is highly recommended. In this paper, we present a study on the application of vibration signals to diagnose faults for a Rotating Machinery using the Mahalanobis Distance-Taguchi System. RMS, Crest Factor and Kurtosis that is known as the Statistical Methods and the spectrum analysis are used to diagnose faults as parameters of Mahalanobis distance.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2007.05a
• /
• pp.319-323
• /
• 2007

Acoustic emission (AE) was originally developed for non-destructive testing of static structure, but over the year its application has been extended to health monitoring of rotating machines and bearings. It offers the advantage of earlier defect detection in comparison with monitoring bearing. This study was diagnosed low-speed machine which had a fault bearing for early detection by AE. And the artificial faults in a experimentation bearing was made for the bearing signals from difference speed and load were compared and analyzed by AE.

• International Journal of Aeronautical and Space Sciences
• /
• v.8 no.1
• /
• pp.79-86
• /
• 2007

In this paper, an adaptive control algorithm using system identification is proposed for an aircraft fault tolerant control system. A discrete state-space system is reformulated to be the ARX model which has the advantage in handing variable structure systems. Discrete model reference adaptive control is used to make the output of fault system follow the output of reference model. To validate the performance of the proposed control scheme, numerical simulations are performed for the high performance aircraft with control surface damage.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.7 no.3
• /
• pp.241-248
• /
• 1983

In the present work a time-dependent reliability model for a typical solar domestic hot water and heating system is developed using the method of Fault Tree Analysis and existing mathematical techniques. The reference system used in this analysis is a typical solar heating system. The system reliability structure has been identified with the aid of Fault Tree methods. In addition, a simulation of the solar system reliability has been performed employing the Monte Carlo method. In the computer simulation, failure rate data such as WASH-1400, MIL-HDBK-217B, and Green and Bourne are used as input data. These results show that the developed reliability model is capable of expressing the primary failure phenomena of the solar heating and domestic hot water system.

• 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.

• International Journal of Aeronautical and Space Sciences
• /
• v.17 no.2
• /
• pp.214-221
• /
• 2016

An attitude estimation algorithm which integrates gyroscope and vision measurements using an adaptive complementary filter is proposed in this paper. In order to make the filter more tolerant to vision measurement fault and more robust to system dynamics, fuzzy interpolator is applied. For recognizing the dynamic condition of the system and vision measurement fault, the cut-off frequency of the complementary filter is determined adaptively by using the fuzzy logic with designed membership functions. The performance of the proposed algorithm is evaluated by experiments and it is confirmed that proposed algorithm works well in the static or dynamic condition.