• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.24 no.9
• /
• pp.675-681
• /
• 2014

This paper proposes a fault diagnosis system for an induction motor. This system uses empirical mode decomposition(EMD) to extract fault signatures and multi-layer perceptron(MLP) neural network to facilitate an accurate fault diagnosis. EMD can not only decompose a signal adaptively but also provide intrinsic mode functions(IMFs) containing natural oscillatory modes of the signal. However, every IMF does not represent fault signature, an IMF selection algorithm based on harmonics and their energy of each IMF is proposed. The selected IMFs are utilized for fault classification using MLP and this system shows approximately 98 % diagnosis accuracy for the fault vibration signal of the induction motor.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2003.11a
• /
• pp.537-543
• /
• 2003

Condition monitoring and fault diagnosis of machines are gaining importance in the industry because of the need to increase reliability and to decrease possible loss of production due to machine breakdown. By comparing the vibration signals of a machine running in normal and faulty conditions, detection of faults like mass unbalance, shaft misalignment and bearing defects is possible. This paper presents a novel approach for applying the fault diagnosis of rotating machinery. To detect multiple faults in rotating machinery, a feature selection method and support vector machine (SVM) based multi-class classifier are constructed and used in the faults diagnosis. The results in experiments prove that fault types can be diagnosed by the above method.

• Industrial Engineering and Management Systems
• /
• v.4 no.2
• /
• pp.192-197
• /
• 2005

Among many amplitude parameters, Kurtosis (4-th normalized moment of probability density function) is recognized to be the sensitive good parameter for machine diagnosis. Kurtosis has a value of 3.0 under normal condition and the value generally goes up as the deterioration proceeds. In this paper, simplified calculation method of kurtosis is introduced for the analysis of impact vibration with one sided affiliated impact vibration which occurs towards the progress of time. That phenomenon is often watched in the failure of such as bearings’ outer race. One sided affiliated impact vibration is approximated by one sided triangle towards the progress of time and simplified calculation method is introduced. Varying the shape of one sided triangle, various models are examined and it is proved that new index is a sensitive good index for machine failure diagnosis. Utilizing this method, the behavior of kurtosis is forecasted and analyzed while watching machine condition and correct diagnosis is executed.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.24 no.7 s.178
• /
• pp.1731-1739
• /
• 2000

The Vibration signals of a gear driving system is often associated with gear tooth faults. Many studies have been done on the detection of impulsive vibration signals, which characterize the breaka ge of a gear tooth. Also, most of the studies on gear fault diagnosis are only about the fault existence at one gear-pair. This study concerns on the several possible faults of a geared motor that has three gear pairs. The measurement and analysis on the vibration signals of a running geared motor shows the relationship between the gear faults and the vibration signals. This study also shows that adaptive interference canceling technique can be appropriately applicable to detect which gear-pair has the fault, and that wavelet is better than spectrogram to figure out the gear fault.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2002.05a
• /
• pp.39-52
• /
• 2002

Research Direction The significant research direction in mechanical fault diagnosis area: Theorles and approaches for fault feature extracting and fault classification. Identification Complicated fault generating mechanism and its model Intelligent fault diagnosis system (including the expert system and network based remote diagnosis system) One of the Key Points： Fault feature extracting techniques based on (modern) signal processing(omitted)

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2000.06a
• /
• pp.1114-1118
• /
• 2000

Impulsive sound and vibration signals in gear are often associated with their faults. Thus these impulsive sound and vibration signals can be used as indicators in the diagnosis of gear fault. The early detection of impulsive signal due to gear fault prevents from complete failure in gear. However it is often difficult to make objective measurement of impulsive signals because of background noise signals. In order to ease the detection of impulsive signals embedded in background noise, we enhance the impulsive signals using adaptive signal processing.

• Journal of the Korean Society for Railway
• /
• v.16 no.1
• /
• pp.26-31
• /
• 2013

The reduction unit is one of the most important components for railway vehicles because the torque of the motor must be transmitted to the wheels of the vehicle by the reduction unit. The faults in the reduction units of high-speed trains are caused by damage such as gear, fatigue. These have serious impacts on safety of the train during operation. To address this development of a system for monitoring, fault diagnosis of the reduction unit is needed to keep the vehicle running safely. Before that can be accomplished, it is most important to understand the vibration characteristics of the reduction unit in a normal state. Vibration diagnosis technology using characteristic-analysis of vibration waveform and frequency is known to be the most effective method for fault diagnosis. In this paper, we analyzed the vibration characteristics of the reduction units two Korean high-speed trains (KTX and KTX II), under normal conditions, by two test methods (driving gear test, full-vehicle test).

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2006.11a
• /
• pp.411-416
• /
• 2006

Fault detection and diagnosis is the most important technology in condition-based maintenance(CBM) system that usually begins from collecting signatures of running machines using multiple sensors for subsequent accurate analysis. With the quick development in industry, there is an increasing requirement of selecting special sensors that are cheap, robust, and easy-installation. This paper experimentally investigated performances of four types of sensors used in induction motors faults diagnosis, which are vibration, current, voltage and flux. In addition, diagnostic effects of five popular classifiers also were evaluated. First, the raw signals from the four types of sensors are collected at the same time. Then the features are calculated from collected signals. Next, these features are classified through five classifiers using artificial intelligence techniques. Finally, conclusions are given based on the experiment results.

• Proceedings of the KSME Conference
• /
• 2007.05a
• /
• pp.1015-1019
• /
• 2007

The necessity of diagnosis of the rotating machinery which is widely used in the industry is increasing. Because vibration diagnosis can avoid sudden breakdown of machine and reduce the maintenance costs. In chemical factory, Air-compressor and refrigerator which can affect the performance and capacity of output is important machine. Therefore, in this paper, the vibration of reassembled air-compressor and refrigerator after explosion is measured for checking the machine condition. The result of diagnosis and solution is discussed in this paper.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1997.04a
• /
• pp.677-682
• /
• 1997

Vibration diagnosis of steam turbine generator is essential for safe operation. For a fast few decades, several data base systems for diagnosis of steam turbine generators have been developed and proved useful. However, there still remains a problem in using data base systems such that they require an expert engineer who has a deep insight or knowledg into the system. Moreover,such data base systems can not give any information if the input is not completely fit with data base. This paper presents an effective method for vibration diagnosis of steam turbine generators using fuzzy inference. The proposed method includes also a strategy to overcome the drawback of data base system such that one cannot obtain any information when the input is insufficient or not exact. A computer program is written to realize the entire procedure for the diagnosis. Three realistic problems are dealt with to show the effectiveness of the proposed method.