• The KSFM Journal of Fluid Machinery
• /
• v.7 no.2 s.23
• /
• pp.41-49
• /
• 2004

Condition monitoring is very important in turbo machinery because single failure could cause critical damages to its plant. So, automatic fault recognition has been one of the main research topics in condition monitoring area. We have used a relatively new fault recognition method, Hidden Markov Model(HMM), for mechanical system. It has been widely used in speech recognition, however, its application to fault recognition of mechanical signal has been very limited despite its good potential. In this paper, discrete HMM(DHMM) was used to recognize the faults of rotor system to study its fault recognition ability. We set up a rotor kit under unbalance and oil whirl conditions and sampled vibration signals of two failure conditions. DHMMS of each failure condition were trained using sampled signals. Next, we changed the setup and the rotating speed of the rotor kit. We sampled vibration signals and each DHMM was applied to these sampled data. It was found that DHMMs trained by data of one rotating speed have shown good fault recognition ability in spite of lack of training data, but DHMMs trained by data of four different rotating speeds have shown better robustness.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.14 no.6
• /
• pp.287-294
• /
• 2019

With the automation of production lines in the manufacturing industry, the importance of real-time fault diagnosis of facility is increasing. In this paper, we propose a fault diagnosis algorithm of LM (Linear Motion)-guide based on deep learning using vibration signals. Generally, in order to guarantee the performance of the deep learning, it is necessary to have a sufficient amount of data, but in a manufacturing industry, it is often difficult to obtain enough data due to physical and time constraints. To solve this problem, we propose a convolutional neural networks (CNN) model based on transfer learning. In addition, the spectrogram image is input to the CNN to reflect the frequency characteristic of the vibration signals with time. The performance of fault diagnosis according to various load condition and transfer learning method was compared and evaluated by experiments. The results showed that the proposed algorithm exhibited an excellent performance.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.16 no.1 s.106
• /
• pp.27-33
• /
• 2006

Fault diagnosis and condition monitoring for rotating machines are important for efficiency and accident prevention. The process of fault diagnosis is to extract the feature of signals and to classify each state. Conventionally, fault diagnosis has been developed by combining signal processing techniques for spectral analysis and pattern recognition, however these methods are not able to diagnose correctly for certain rotating machines and some faulty phenomena. In this paper, we add a minimum detection error algorithm to the previous method to reduce detection error rate. Vibration signals of the induction motor are measured and divided into subband signals. Each subband signal is processed to obtain the RMS, standard deviation and the statistic data for constructing the feature extraction vectors. We make a study of the fault diagnosis system that the feature extraction vectors are applied to K-means clustering algorithm and minimum detection error algorithm.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.21 no.1
• /
• pp.33-39
• /
• 2012

The tool wear and failure in automatic production system directly influences the quality and productivity of a product, thus it is essential to monitor the tool state in real time. For such purpose, an ART2-based remote monitoring system has been developed to predict the appropriate tool change time in accordance with the tool wear, and this study aims to experimently find the relationship between the tool wear and the monitoring signals in cutting processes. Also, the roughness of workpiece according to the wool wear is examined. Here, the tool wear is indirectly monitored by signals from a vibration senor attached to a machining center. and the wear dimension is measured by a microscope at the start, midways and the end of a cutting process. A series of experiments are carried out with various feedrates and spindle speeds, and the results show that the sensor signal properly represents the degree of wear of a tool being used, and the roughnesses measured has direct relation with the tool wear dimension. Thus, it is concluded that the monitoring signals from the vibration sensor can be used as a useful measure for the tool wear monitoring.

• 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.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2001.11b
• /
• pp.1162-1165
• /
• 2001

Operational Modal Analysis also known as Output Only Modal Analysis has in the recent years been used for extracting modal parameters of civil engineering structures and is now becoming popular for mechanical structures. The advantage of the method is that no artificial excitation need to be applied to the structure or force signals to be measured. All the parameter estimation is based upon the response signals, thereby minimising the work of preparation for the test. This test case is a controlled lab set-up enabling different parameter estimation methods techniques to be used and compared to the Operational Modal Analysis. For Operational Modal Analysis two different estimation techniques are used： a non-parametric technique based on Frequency Domain Decomposition (FDD), and a parametric technique working on the raw data in time domain, a data driven Stochastic Subspace Identification (SS!) algorithm. These are compared to other methods such as traditional Modal Analysis.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2000.11a
• /
• pp.431-436
• /
• 2000

Adaptive feed forward control algorithms based largely upon LMS approach have developed in recent two decades, and they have been widely applied to practical sound and vibration control problems in the case of the reference signal is available. Feedforward control can be applied only when reference signals can be measured or regenerated, while feedback controllers are used to reduce; sound and vibration when reference signals are not available. In recent years, hybrid control schemes in which adaptive feed forward controllers are combined with feedback ones have been studied based on simulations and experiments. The results have shown that the hybrid control may have better control performances in convergence speed and steady state error than the single control schemes. Hybrid control has the advantages of improving stability and performance as well as the disturbance rejection property. However, little effort has been made to the analysis or interpretation of hybrid control systems. In this study, we discussed the feedback controller effects on the stability of feed forward control algorithm in the presence of uncertain error path and a simple example showed that a stable feedback controller could make the feedforward controller unstable. A design criterion of feedback controllers is proposed in order to guarantee the stability of feedforward algorithms in the presence of error paths with uncertainties.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2002.11b
• /
• pp.617-622
• /
• 2002

This paper presents that the Wavelet Transform can be used to detect the various local defects in a gearbos. Two types of defects which are broken tooth and localized wear, are experimented and the signals are collected by accerometer and analyzed. Because of the complecity of the signals acquired from sensor, it is needed to identify the interesting signal. The natural frequencies of shafts and the gear mesh frequency(GMF) is calculated theretically. DWT, CWT and the aplication are used to extract a gear-localized defect feature from the vibration signal of the gearbox with the defective gear. The results shows the transform is more effective to detect the failures than the Fourier Transform.

• Proceedings of the KSME Conference
• /
• 2003.04a
• /
• pp.370-375
• /
• 2003

Optical fiber vibrations sensors (OFVSs) and extrinsic Fabry-Perot interferometer (EFPI) were used in damage monitoring of fiber-metal laminates(FML). The optical fiber vibration sensor and EFPI were applied in order to detect and evaluate the strain, damage and failure of FML. Damages in composites, such as matrix cracks, delamination and fiber breakage may occur as a result of excessive load, fatigue and low-velocity impacts. Tensile and indentation test was performed with the measurement of optical signal and acoustic emission (AE). The signals of the optical fiber vibration sensor due to damages were quantitatively evaluated by wavelet transform. It was found that damage information of comparable in quality to acoustic emission data could be obtained from the optical fiber vibration sensor signals.

• The Journal of the Acoustical Society of Korea
• /
• v.16 no.6
• /
• pp.41-47
• /
• 1997

Beating phenomenon which is generated by two closely located natural frequencies is one of research tenet for King Song-Dok bell. In this paper, we investigate the vibration shape of these natural frequencies using very extensive experimental data. Vibration signals are sampled at 108 points around the bell using accelerometers. Measured signals are anlayzed in time and frequency domain. Twelve natural shapes under 800Hz are plotted.