• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.9
• /
• pp.2927-2941
• /
• 2022

The primary task of machine fault diagnosis is to judge whether the current state is normal or damaged, so it is a typical binary classification problem with mutual exclusion. Mutually exclusive events and out-of-domain detection have one thing in common: there are two types of data and no intersection. We proposed a fusion model method to improve the accuracy of machine fault diagnosis, which is based on the mutual exclusivity of events and the commonality of out-of-distribution detection, and finally generalized to all binary classification problems. It is reported that the performance of a convolutional neural network (CNN) will decrease as the recognition type increases, so the variational auto-encoder (VAE) is used as the primary model. Two VAE models are used to train the machine's normal and fault sound data. Two reconstruction probabilities will be obtained during the test. The smaller value is transformed into a correction value of another value according to the mutually exclusive characteristics. Finally, the classification result is obtained according to the fusion algorithm. Filtering normal data features from fault data features is proposed, which shields the interference and makes the fault features more prominent. We confirm that good performance improvements have been achieved in the machine fault detection data set, and the results are better than most mainstream models.

• Journal of the Korean Society for Precision Engineering
• /
• v.18 no.7
• /
• pp.46-52
• /
• 2001

This study describes the precision control of the torque standard machine using a self-tuning fuzzy controller. The torque standard machine should generate the accurate torque for calibrating a torque sensor. In order to reduce the relative expanded uncertainty of the torque standard machine, when a weight is hanged to the end of the torque arm for generating the torque, the sloped torque arm should be accurately controlled to the horizontal level. If the slope of the torque arm is larger from the inaccurate control, the uncertainty of the torque standard machine due to control will be larger. This applies the inaccurate torque to a torque sensor to calibrate, and the measuring error of the torque sensor generate from it. Therefore the torque arm of the torque standard machine is accurately controlled. In this paper, the self-tuning fuzzy controller was designed using a fuzzy theory, and the torque arm of the torque standard machine was accurately controlled. The control gain of the fuzzy controller, that is the membership function size of the error, the membership function size of the error change and the membership function size of the controller were determined from the self-tuning. The control results of the torque standard machine were the overshoot within 0.0076mm, the rise time within 16.70sec and the steady state error within 0.0076mm.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.5
• /
• pp.509-514
• /
• 2015

In this paper, we introduce a new pattern classifier which is based on the learning algorithm of Extreme Learning Machine the sort of artificial neural networks and fuzzy set theory which is well known as being robust to noise. The learning algorithm used in Extreme Learning Machine is faster than the conventional artificial neural networks. The key advantage of Extreme Learning Machine is the generalization ability for regression problem and classification problem. In order to evaluate the classification ability of the proposed pattern classifier, we make experiments with several machine learning data sets.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2001.10a
• /
• pp.185-189
• /
• 2001

In order to prevent the production defects the optimum design of product, jig and fixture putting in the field is very significant manufacturing method. Drilling Jig is the device according to industrial demand for multi manufacturing products on the growing at alarming rate. In the field of design and making for machine tool working, welding, assembling with jig and fixture for mass production is a specific division. They require analysis of many kinds of important factors, theory and practice of machine tool operating process and jig & fixture structure, machining condition for tool making, tool materials, heat treatment of jig & fixture components, know-how and so on. In this study we designed and constructed a drilling jig of mass production and performed tryout under the Auto CAD, Auto Lisp database, that we made by database, and window environment. Especially this study is reveals with the analysis of part drawing, jig planning, jig design etc, and then the result of drill jig's making try out.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.9 no.4
• /
• pp.99-107
• /
• 2000

In this study, a static and dynamic characteristics analysis system for machine tool spindle systems with 3 lobe sliding bearing is developed based on Timoshenko theory, finite element method and windows programming techniques. And the characteristics value of 3 lobe sliding bearing such as eccentricity ratio, attitude angle, friction coefficient , stiffness coefficients, damping coefficients and so on, are determined by using the thermal equilibrium conditions of spindle systems. Since the developed system has various analysis modules related to static deformation analysis, modal analysis, frequency responses analysis and so on, it can be utilized to perform systematically the design an devaluation process of spindle systems with 3 lobe sliding bearing under windows GUI environment.

• Journal of the Korean Society for Precision Engineering
• /
• v.6 no.4
• /
• pp.126-135
• /
• 1989

In this study, in order to perform dynamic design of machine tools reasonably and effectively, a method was formulated to be applicable to the structures connected by joints having elasticity and damping by using substructure synthesis method. And to analyze chatter-free performance, a 3 dimensional cutting dynamics theory was used. Computer program package for the dynamic design of machine tools was developed by combining those and spplied to improvement of performance of NC lathe. Also, the optimization in the structural modifications of machine tool substructure was studied by evaluating the effects of the substructural modifications on total system performance.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2000.04a
• /
• pp.641-646
• /
• 2000

A milling process with 45 degree chamfered inserts produces a perfect flat surface only in theory. It is due to many unwanted factors including thermal effect, dynamic effect, the problem of the controller used and the problem of accuracy of the machine tool. In this study, introduced is a method to improve the surface roughness by redesigning of the chamfer angle of the insert, which traditionally has been 45 degree. First, the relationship between the fixed machine coordinate and the relative coordinate on the insert is derived. This transfer matrix is used to determine the new insert angle to maximize the flatness of the machined surface. A newly designed insert is manufactured, and used to carry out the experiment. It is proved that the insert designed by the proposed method produced a much flatter surface than a traditional one.

• 전기의세계
• /
• v.25 no.4
• /
• pp.68-72
• /
• 1976

This study is initiated to solve the problem that the development of an electric machine to drive heavy horse-power load required in the rural district, where only single phase supply is available, is very urgent. As a method for this purpose, the single/three phase converter by single phase induction machine with a tapped auxiliary winding, running unloaded mechanically under single-phase source and supplying three-phase output to a loaded 3-phase induction motor, is devised and the pilot machine is put into test. Analysis based on hybrid equivalent circuit for the phase converter and symmertical component theory for the 3-phase load motor and practical experiment result in that optimum auxiliary winding ratio is to be 1.25 rather than theoretical .root.3/2 in order to keep the voltage unbalance ratio of 3-phase output from the converter as low as possible in both cases of starting and running the load motor.

• Proceedings of the KIPE Conference
• /
• 2007.07a
• /
• pp.412-414
• /
• 2007

In motor driving, one of the most important consideration is the load characteristic and variation. Generally, the motor drive should be made enough for the current by load variation, and it should be controlled by the load weight. However, the drum washing machine's load variation is irregular and large. Therefore, we want to make the motor drive that considering this load pattern, this paper describes the drum washing machine's load pattern modeling by the mathematical theory.

• Proceedings of the KIEE Conference
• /
• 1998.11a
• /
• pp.61-63
• /
• 1998

Disk type single phase SRM (DSPSRM) has a specific property of axial flux machine and radial flux machine simultaneously. So, this DSPSRM has a complicated magnetic circuit and it is difficult to analyze characteristics. Therefore, in this paper, the design specification of DSPSRM was calculated based on conventional design theory of electric machine and analyzed by 3D FEM. As the result of analysis, the approximated torque characteristics was obtained by finding the magnetic flux and energy distribution with the rotor position.