• 한국표면공학회지
• /
• 제56권6호
• /
• pp.353-370
• /
• 2023

Corrosion detection and analysis is a very important topic in reducing costs and preventing disasters. Recently, image processing techniques have been widely applied to corrosion identification and analysis. In this work, we briefly introduces traditional image processing techniques and machine learning algorithms applied to detect or analyze corrosion in various fields. Recently, machine learning, especially CNN-based algorithms, have been widely applied to corrosion detection. Additionally, research on applying machine learning to region segmentation is very actively underway. The corrosion is reddish and brown in color and has a very irregular shape, so a combination of techniques that consider color and texture, various mathematical techniques, and machine learning algorithms are used to detect and analyze corrosion. We present examples of the application of traditional image processing techniques and machine learning to corrosion detection and analysis.

• 전기학회논문지
• /
• 제61권2호
• /
• pp.223-230
• /
• 2012

This paper deals with an design of axial flux electric machine which is a key element for a compact size in a portable and manual generator system. It is expected that the generator system with an axial flux electric machine is more light and has higher efficiency than other types of generator systems. And it is used the soft magnetic composite core instead of silicon steel core in the axial flux electric machine for more compact size. The weight and efficiency of the generator system are the main keys to select the value of design variables. In this paper, the overall design process to meet the design goals, and the design results are presented with experiment results.

• 한국기계가공학회지
• /
• 제6권3호
• /
• pp.112-118
• /
• 2007

Recently, the machine tools called multi-task machines, which mounted rotary axes on the table or spindle are used increasingly. Accordingly, multi-task machine tool takes a growing interest on the motion accuracy of feed drive system. In this study, measurement and diagnosis of motion errors ware attempted from circular pattern obtained by using DBB (Double ball bar) device. Those were obtained at both clockwise and counter clockwise motions in mutually perpendicularly intersecting three planes. The reliability of error measurement system for multi-task machine tool was verified by the direct test cutting.

• 한국기계가공학회지
• /
• 제6권3호
• /
• pp.31-37
• /
• 2007

Recently, the machine tools called multi-task machines, which mounted rotary axes on the table or spindle are used increasingly. Accordingly, multi-task machine tool takes a growing interest on the motion accuracy of feed drive system. In this study, measurement and diagnosis of motion errors ware attempted from circular pattern obtained by using DBB (Double ball bar) device. Those were obtained at both clockwise and counter clockwise motions in mutually perpendicularly intersecting three planes. The reliability of error measurement system for multi-task machine tool was verified by the direct test cutting.

• 한국공작기계학회논문집
• /
• 제11권5호
• /
• pp.7-14
• /
• 2002

In order to achieve high precision machine tools, the research for performance enhancement of feed drive systems is required. Development of the high speed feed drive system has been a major issue for the past few decades in machine tool indestries. Because table levitation system decrease the table weight, an effect of reaction by weight is minimized and lost motion can be removed at maximum. In case fled system is designed with drive motor, ball screw and support bearing load capacity selection, an effect of decrease of the table weight exist. So, the table weight through an effect of decrease call it into the realization of cost down. Stick-slip friction has a great influence on the contouring accuracy of CNC machine tools. In this paper table levitation system has been developed for the stick-slip in a fled drive systems.

• International Journal of Precision Engineering and Manufacturing
• /
• 제6권3호
• /
• pp.8-12
• /
• 2005

The positioning system for an ultra precision machine tool must be accurate to the order of a nanometer. Various feed drive devices have been proposed to achieve this resolution; currently, most attention is directed towards hydrostatic lead screws and friction drives. It has been reported that a positioning resolution accurate to an angstrom can be achieved using a twist-roller friction drive. Therefore, we manufactured an ultra precision positioning system driven by a twist-roller friction drive and assessed its performance when defining problems and finding solutions. Our study showed that the twist-roller friction drive is mechanically suitable for ultra precision positioning, but some considerations are required to obtain a higher resolution.

• International Journal of Precision Engineering and Manufacturing
• /
• 제3권3호
• /
• pp.82-89
• /
• 2002

The need of ultra-precision machine tools, which manufacture and machine the high precision parts used in computers, semi-conductors and other precision machines, has been increased over years. Therefore it is important to design the driving parts, which affect significantly on their performances. In this paper, the dynamic analyses on the belt-driven system were explored. Relation of the acoustical natural frequency and the tension of belt was derived and presented through experiments. Also, while the dynamic loads on motor system were changed, dynamic deflections were calculated through finite element analysis. Nonlinear characteristics of the bearings having an effect on the dynamic performance were studied and the belt connecting the motor (driving part) to spindle of a machine tool (driven part) was modeled as truss and beam elements fur simulations under various conditions, and a beam element model was verified to be more useful.

• 대한기계학회논문집A
• /
• 제30권6호
• /
• pp.713-721
• /
• 2006

Micro-drill wear deteriorates accuracy and productivity of the micro components. In order to improve productivity and qualify of micro components, it is required to investigate micro-drill wear exactly. In this study, a machine vision system is proposed to measure the wear of micro-drills using a precision servo stage. Calibration experiments are conducted to compensate for the machine vision system. In this paper, worn volume, area and length are defined as wear amounts. Micro-drill wear is reconstructed as the 3D topography and the quantized wear amount by using the shape from focus (SFF) method and wear parameters. Experiments have been conducted with HSS twist micro-drills and SM45C carbon steel workpieces. Validity of the proposed machine vision system is confirmed through experiments.

• International Journal of Precision Engineering and Manufacturing
• /
• 제8권2호
• /
• pp.3-8
• /
• 2007

A machining system that generates accurate relative motions between the tool and workpiece is required to realize ultra precise machining or measurements. Accuracy improvements for each element of the machine are also required. This paper proposes a machining system that uses a compensation device for the six-degree-of-freedom (6-DOF) motion error between the tool and workpiece. The compensation device eliminates elastic and thermal errors of the joints and links due to temperature fluctuations and external forces. A hexapod parallel kinematics mechanism installed between the tool spindle and surface plate is passively actuated by a conventional machine. Then the parallel mechanism measures the 6-DOF motions. We describe the conception and fundamentals of the system and test a passively extensible strut with a compensation device for the joint errors.

• 대한상한금궤의학회지
• /
• 제14권1호
• /
• pp.41-50
• /
• 2022

Objective : The purpose of this study is to explore the most suitable machine learning model algorithm for Shanghanlun diagnostic system classification using natural language processing (NLP). Methods : A total of 201 data items were collected from 『Shanghanlun』 and 『Clinical Shanghanlun』, 'Taeyangbyeong-gyeolhyung' and 'Eumyangyeokchahunobokbyeong' were excluded to prevent oversampling or undersampling. Data were pretreated using a twitter Korean tokenizer and trained by logistic regression, ridge regression, lasso regression, naive bayes classifier, decision tree, and random forest algorithms. The accuracy of the models were compared. Results : As a result of machine learning, ridge regression and naive Bayes classifier showed an accuracy of 0.843, logistic regression and random forest showed an accuracy of 0.804, and decision tree showed an accuracy of 0.745, while lasso regression showed an accuracy of 0.608. Conclusions : Ridge regression and naive Bayes classifier are suitable NLP machine learning models for the Shanghanlun diagnostic system classification.