• 대한기계학회논문집A
• /
• 제26권9호
• /
• pp.1772-1778
• /
• 2002

This paper describes inference architecture of an intelligent CAD system that is to be used for design tasks in which complex and large amount of knowledge is used. In order to investigate the issue of handling huge and complex knowledge, design knowledge is categorized into four types and inference methods for them are identified respectively: original design problems are decomposed into several modules of design processes and finally into sub-problems with the four types of knowledge as basic elements in a top-down manner. We demonstrate the implementation of the architecture with the result of the machining center - a sort of machine tools - design.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2001년도 춘계학술대회 논문집
• /
• pp.59-62
• /
• 2001

Reliability engineering is regarded as the major and important roll for all industry. And advanced manufacturing systems with high speed and intelligent have been developing for the betterment of machining ability. In this study, we have systemized evaluation of reliability for machinery system. We proposed the reliability assessment and design review method using analyzing critical units of high speed and intelligent machine system. In addition, we have not only designed and developed test bed system for acquiring reliability data, but also apply QFD technique for satisfying quality function which is provided in design phase. From this study, we will expect to guide and introduce the reliability engineering in developing and processing phase of high quality product.

• 한국정밀공학회지
• /
• 제17권5호
• /
• pp.41-50
• /
• 2000

NC(Numerical Control)는 1949년 미 공군이 Parson (Fig. 1 (a))이라는 사람에게 프로펠러 (Propeller)용 블레이드(Blade)의 윤곽을 검사하기 위한 판 게이지(Gauge)(Fig. 1 b)) 개발을 의뢰한 것이 계기가 되어 발명되었다. 이후, 신시나티 미라크론(Cincinati Miracle)이라는 공작기계 업체가 NC 사업에 참여하게 되고, 1952년 최초로 MIT(Massachusetts Institute of Technology)의 서보기구연구소(Servo-mechanism laboratory)에 의해 NC 공작기계가 탄생(Fig. 1 (c)) 되었다.(중략)

• 한국기계가공학회지
• /
• 제20권9호
• /
• pp.90-96
• /
• 2021

As real-time data of factories can be collected using various sensors, the adaptation of intelligent unmanned processing systems is spreading via the establishment of smart factories. In intelligent unmanned processing systems, data are collected in real time using sensors. The equipment is controlled by predicting future situations using the collected data. Particularly, a technology for the prediction of tool wear and for determining the exact timing of tool replacement is needed to prevent defected or unprocessed products due to tool breakage or tool wear. Directly measuring the tool wear in real time is difficult during the cutting process in milling. Therefore, tool wear should be predicted indirectly by analyzing the cutting load of the main spindle, current, vibration, noise, etc. In this study, data from the current and acceleration sensors; displacement data along the X, Y, and Z axes; tool wear value, and shape change data observed using Newroview were collected from the high-speed, two-edge, flat-end mill machining process of SKD11 steel. The support vector machine technique (machine learning technique) was applied to predict the amount of tool wear using the aforementioned data. Additionally, the prediction accuracies of all kernels were compared.

• 지능정보연구
• /
• 제4권1호
• /
• pp.1-10
• /
• 1998

Process planning is a very complex task and requires the dynamic informatioon of shop foor and market situations. Process plan selection is one of the main problems in the process planning. In this paper, we propose a new process plan selection model considering operation flexibility for the computer aided process planing. The model is formulated as a 0-1 integer programming considering realistic shop factors such as production volume, machining time, machine capacity, transportation time and capacity of tractors such as production volume, machining time, machine capacity, transportation time capacity of transfer device. The objective of the model is to minimize the sum of the processing and transportation time for all parts. A genetic algorithm a, pp.oach is developed to solve the model. The efficiency of the proposed a, pp.oach is verified with numerical examples.

• 한국정밀공학회지
• /
• 제22권10호
• /
• pp.39-48
• /
• 2005

As the industrial development is accelerated, a new machining process and system are keenly required to achieve super precision surface finish. Especially to get ground surface finish fer complicated and narrow inner shape of molds, it is impossible with the existing methods so that a new method is being required to be developed. A new material, called Magic(MAGnetic Intelligent Compounds), is finally made and it is called Magic machining that uses this material. There is a way to make a material as follows, the mixture of magnetic particles, bonding material and particles of abrasive grain should be melt down by proper heat, and then this mixture put in a mold and cool down in magnetic field which has a uniform direction. This new polishing method is spotlighted as an excellent solution to the existing problems. However it hasn't reported any study about the influence of the machining conditions of polishing velocity, amplitude and polishing pressure to the surface roughness yet. This study would examine closely the influence of polishing conditions of the Magic polishing tool to the surface finish to decide the optimum polishing condition and to standardize the Magic polishing work.

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 2002년도 추계학술대회 논문집
• /
• pp.319-323
• /
• 2002

Recently, new polishing system which was made by magnetic intelligent compound (MAGIC) was invented and, the study is going on for practical use the analysis of factors, that is, the kind of polishing grain, composition ratio of wheel elements, machining frequency, polishing pressure, which the main influence for polishing efficiency are the first step. In this study, analyzed influence of wheel raw material composition ratio on surface roughness.

• 한국정밀공학회지
• /
• 제9권4호
• /
• pp.22-35
• /
• 1992

In highly automated machining centers, intelligent sensor fddeback systems are indispensable on order to monitor their operations, to ensure efficient metal removal, and to initate remedial action in the event of accident. In this study, an on-line tool wear detection system for thrning operations is developed, and experimentally evaluated. The system employs multiple sensors and the signals from these sensors are processed using a multichannel autoegressive (AR) series model. The resulting output from the signal processing block is then fed to a previously tranied artificial neural network (multiayered perceptron) to make a final decision on the state of the cutting tool. To learn the necessary input/output mapping for tool wear detection, the weithts and thresholds of the network are adjusted according to the back propagation (BP) method during off-line training. The results of experimental evaluation show that the system works well over a wide range of cutting conditions, and the ability of the system to detect tool wear is improved due to the generalization, fault-tolearant and self-ofganizing properties of the neural network.

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 2004년도 춘계학술대회 논문집
• /
• pp.398-403
• /
• 2004

The demand of high speed machining is increasing because the high speed cutting providers high efficiency of process, short process time, improved metal removal capacity and better surface finish. Active magnetic bearings allow much high surface speed than conventional ball bearings and therefore greatly suitable for high speed cutting. The automatic control concept of magnetic bearing system provides ability of intelligent control of spindle system to increase accuracy and flexibility by means of adaptive vibration control. This paper describes a design and development of a milling spindle system which includes built-in motor with power 5.5㎾ and maximum speed 70,000rpm, HSK-32C tool holer and active magnetic bearing system. Magnetic actuators are designed for satisfying static load condition. The Performances of manufactured spindle system was examined for its static and dynamic stiffness, load capacity, and rotational accuracy. This spindle was run up to 70,000 rpm stably, which is 3.5 million DmN.

• 한국기계가공학회지
• /
• 제18권9호
• /
• pp.29-35
• /
• 2019

The structure of the machinery industry due to the 4th industrial revolution is changing from precision and durability to intelligent and smart machinery through sensing and interconnection(IoT). There is a growing need for research on prognostics and health management(PHM) that can prevent abnormalities in processing machines and accurately predict and diagnose conditions. PHM is a technology that monitors the condition of a mechanical system, diagnoses signs of failure, and predicts the remaining life of the object. In this study, the vibration generated during machining is measured and a classification algorithm for normal and fault signals is developed. Arbitrary fault signal is collected by changing the conditions of un stable supply cutting oil and fixing jig. The signal processing is performed to apply the measured signal to the learning model. The sampling rate is changed for high speed operation and performed machine learning using raw signal without FFT. The fault classification algorithm for 1D convolution neural network composed of 2 convolution layers is developed.