• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.5
• /
• pp.718-723
• /
• 2008

Bearing is one of the important mechanical elements used in various industrial equipments. Most of failures occurred during the equipment operation result from bearing defects and breakages. Therefore, monitoring of bearings is essential in preventing equipment breakdowns and reducing unexpected loss. The purpose of this paper is to present an online monitoring method to predict bearing states using vibration signals. Bearing vibrations, which are collected as a form of profile signal, are first analyzed by a discrete wavelet transform. Next, some statistical features are obtained from the resultant wavelet coefficients. In order to select significant ones among them, analysis of variance (ANOVA) is employed in this paper. Statistical features screened in this way are used as input variables to support vector machine (SVM). An hierarchical SVM tree is proposed for dealing with multi-class problems. The result of numerical experiments shows that the proposed SVM tree has a competent performance for classifying bearing fault states.

• Earthquakes and Structures
• /
• v.7 no.6
• /
• pp.1141-1169
• /
• 2014

This study is aimed to investigate the seismic performance of low-rise precast wall system with base isolation. Three types of High Damping Rubber Bearing (HDRB) were designed to provide effective isolation period of 2.5 s for three different kinds of structure in terms of vertical loading. The real size HDRB was manufactured and tested to obtain the characteristic stiffness as well as damping ratio. In the vertical stiffness test, it was revealed that the HDRB was not an ideal selection to be used in isolating lightweight structure. Time history analysis using 33 real earthquake records classified with respective peak ground acceleration-to-velocity (a/v) ratio was performed for the remaining two types of HDRB with relatively higher vertical loading. HDRB was observed to show significant reduction in terms of base shear and floor acceleration demand in ground excitations having a/v ratio above $0.5g/ms^{-1}$, very much lower than the current classification of $0.8g/ms^{-1}$. In addition, this study also revealed that increasing the damping ratio of base isolation system did not guarantee better seismic performance particularly in isolation of lightweight structure or when the ground excitation was having lower a/v ratio.

• Proceedings of the KSME Conference
• /
• 2003.11a
• /
• pp.1458-1463
• /
• 2003

This paper presents an improved identification algorithm of active magnetic bearing rotor systems considering sensor and actuator dynamics. An AMB rotor system has both real and complex poles so that it is very hard to identify them together. In previous research, a linear transformation through a fictitious proportional feedback was used in order to shift the real poles close to the imaginary axis. However, the identification result highly depends on the fictitious feedback gain, and it is not easy to identify the additional dynamics including sensor and actuators at the same time. First, this paper discusses the necessity and a selection criterion of the fictitious feedback gain. An appropriate feedback gain minimizes dominant SVD(Singular Value Decomposition) error through maximizing rank deficiency. Second, more improvement in the identification is achieved through separating the common additional dynamics in all elements of frequency response matrix. The feasibility of the proposed identification algorithm is proved with two theoretical AMB rotor models. Finally, the proposed scheme is compared with previous identification methods using experimental data, and a great improvement in model quality and large amount of time saving can be achieved with the proposed method.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.5
• /
• pp.1186-1207
• /
• 2024

Bearings are one of the main components of mechanical equipment and one of the primary components prone to faults. Therefore, conducting fault diagnosis on bearings is a key issue in mechanical equipment research. Belief rule base (BRB) is essentially an expert system that effectively integrates qualitative and quantitative information, demonstrating excellent performance in fault diagnosis. However, class imbalance often occurs in the diagnosis task, which poses challenges to the diagnosis. Models with interpretability can enhance decision-makers' trust in the output results. However, the randomness in the optimization process can undermine interpretability, thereby reducing the level of trustworthiness in the results. Therefore, a hierarchical BRB model based on extreme gradient boosting (XGBoost) feature selection with interpretability (HFS-IBRB) is proposed in this paper. Utilizing a main BRB alongside multiple sub-BRBs allows for the conversion of a multi-classification challenge into several distinct binary classification tasks, thereby leading to enhanced accuracy. By incorporating interpretability constraints into the model, interpretability is effectively ensured. Finally, the case study of the actual dataset of bearing fault diagnosis demonstrates the ability of the HFS-IBRB model to perform accurate and interpretable diagnosis.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2003.06a
• /
• pp.1807-1810
• /
• 2003

The formed tool is used to machine the unique shape of rubber seal for geometrical shaping and reduction of cutting time. The bearing rubber seal produced by hot press forming has complex geometry for the complex geometrical shape to prevent leakage of lubricant oil and influx of the dust effectively. Because it is difficult to machine the unique shape exactly by the conventional tool, the formed tool is used in machining mold of the seal. In this paper, It is performed for selection of the formed tool to investigate cutting edge wear, cutting force, and surface quality. Also, an efficient high precision machining is proposed on the experiment data.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2002.11a
• /
• pp.379.2-379
• /
• 2002

The support bearing requires high DN to raise specific energy efficiency for the state of the art rotating machine with high speed. Especially for the system has a big rotor(750 kgf) with high speed(about one mi i lion DNs) such as the pulsed generator, tin selection of the bearing and lubrication method are very important. (omitted)

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 1996.03a
• /
• pp.124-131
• /
• 1996

The use of small hemispherical high-speed precision bearing has increased drastically these days in the field of computer disk driver, highteech devices as well as communication and electronic device drivers. It was suggested that the new polishing process adopting the diamond grinding wheel and polishing tool instead of multi stage lapping processes, which enables the mass production of the bearing by reduction of polishing time. Polishing mechanism was analysed and the results were applied to the design and manufacturing of the polishing system. Experiments for selection of optimal polishing conditions were carried out using the polishing system.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.14 no.6
• /
• pp.37-44
• /
• 2005

This paper presents fabrication techniques of the optical fiber position sensor (or spindle state monitoring. These include selection of components such as optical fibers, a laser-diode, a photo-diode, and op-amp IC of the signal process circuit. We also describe electric runout problem. The fabricated sensor has a linearity of $1.7\%$ FSO in the air gap range $0.1\~0.6mm$, a resolution of $0.37{\mu}m$ and a bandwidth of 6.3kHz. Finally, we have successfully operated a magnetic bearing spindle system using the sensors.

• Journal of Korean Port Research
• /
• v.10 no.2
• /
• pp.69-90
• /
• 1996

This study is related to save the bearing capacity from using Meyerhof formula namely, static mechanics formula with the S.P.T(N value) of the soft ground and is to choose the soft ground improvement method by the using of total load for the proper method of the pile foundation and then to design the most suitable pile foundation to fit the actual circumstance. The purpose of this study is calculating the diameter of the pile foundation by static mechanics formula and introducing the optimum design condition from the result of the bearing capacity for using N value of the S.P.T obtained from the deep soft ground about the piles such as P.H.C pile, pipe and cast-in-place pile of big diameter, etc. As above-mentioned, it is considered that the use of P.H.C pile or pipe pile is advisable on the synthetical investigation and that the selection of cast-in-place pile method is desirable in terms of the constructive safety and durability.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.10 no.4
• /
• pp.30-37
• /
• 2007

In this paper, Water Entry Point Selection Algorithm(WEPSA) for selecting an optimal Water Entry Point of anti-submarine missiles which maximizes Detection Probability about a given target was investigated. WEPSA is a method which decides the position of an optimal Water Entry Point with calculating the target Detection Probability of a torpedo in the whole domain which centered by the target, performing the Monte-Carlo Simulations which include errors for the target informations and for weapon delivery. We can decide an optimal Water Entry Point of anti-submarine missiles which maximizes Detection Probability about a given target with WEPSA, if we get target informations about target range, target bearing, target speed and target course from Combat Systems.