• 한국CDE학회논문집
• /
• 제2권2호
• /
• pp.111-121
• /
• 1997

This study intends to develop a fixture planning module as a part of the planning system for cutting. The fixture module uses machine learning method to reuse previous failure results so that the system can reduce the repeated failures. Machine learning is one of efforts to incorporate human reasoning ability into a computerized system. A human expert designs better than a novice does because he has a wide experience in a specific area. This study implements the machine learning algorithm to have a wide experience in the fixture planning area as a human expert does. When the fixture planner finds a setup failure for the suggested operations by a process planner, it makes the process planner store its attributes and other information for the failed setup. Then the process planner applies the learned knowledge when it meets a similar case so that the planner can reduce possibility of setup failure. Also the system can teach a novice user by showing a failed setup with a modified setup.

• 전자통신동향분석
• /
• 제34권4호
• /
• pp.32-42
• /
• 2019

The performance of machine learning algorithms significantly depends on how a configuration of hyperparameters is identified and how a neural network architecture is designed. However, this requires expert knowledge of relevant task domains and a prohibitive computation time. To optimize these two processes using minimal effort, many studies have investigated automated machine learning in recent years. This paper reviews the conventional random, grid, and Bayesian methods for hyperparameter optimization (HPO) and addresses its recent approaches, which speeds up the identification of the best set of hyperparameters. We further investigate existing neural architecture search (NAS) techniques based on evolutionary algorithms, reinforcement learning, and gradient derivatives and analyze their theoretical characteristics and performance results. Moreover, future research directions and challenges in HPO and NAS are described.

• 대한임베디드공학회논문지
• /
• 제15권6호
• /
• pp.307-316
• /
• 2020

Machine learning model data is highly affected by performance. preprocessing is needed to enable analysis of various types of data, such as letters, numbers, and special characters. This paper proposes a development environment that aims to process categorical and continuous data according to the type of missing values in stage 1, implementing the function of selecting the best performing algorithm in stage 2 and automating the process of checking model performance in stage 3. Using this model, machine learning models can be created without prior knowledge of data preprocessing.

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 1996년도 추계학술대회 논문
• /
• pp.85-90
• /
• 1996

In order to detect and suppress chatter in turning processes a stability control methodology was studied through manipulation of spindle speeds regarding to chatter frequencies. The chatter frequency was identified by monitoring and signal processing of sound pressure during turning on a lathe. The stability control methodology can select stable spindle speeds without knowing a prior knowledge of machine compliances and cutting dynamics. Teliability of the developed stability control methodology was verified through turning experiments on an engine lathe. Experimental results show that a microphone is an excellent sensor for chatter detection and control

• 한국안전학회지
• /
• 제12권1호
• /
• pp.129-132
• /
• 1997

The effectiveness of an ensuring the facility safety depends on the ability to find abnormal part(s) and remove that part(s). This requires the knowledge of that machine and ability to recover that machine. In this paper, it is discribed how to design the fuzzy based self organizing neural network expert system in order to find syptom source(s).

• 한국언어정보학회지:언어와정보
• /
• 제2권1호
• /
• pp.79-105
• /
• 1998

This paper aims to describe a German-Korean machine translation system for nominal phrases. Besides, we have two subgoals. First, we are going to revea linguistic differences between two languages and propose a language-informational method fo overcome the differences. The method is based on an integrated model of translation knowledge, efficient information structure, and concordance selection. Then, we will show the statistical results about translation experiment and its evaluation as an evidence for the adequacy of our linguistic method and translation system itself.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1992년도 한국자동제어학술회의논문집(국제학술편); KOEX, Seoul; 19-21 Oct. 1992
• /
• pp.636-641
• /
• 1992

In the human cognitive activity, experiencing plays a basic role. This is modeled by the idea of experience sequence here, which has been proposed by the author for the incorporation of the factor of experiencing in man-machine communication. Experience sequence is for modeling the human concept formation through experiencing. Knowledge manipulation requires concept understanding as its basis. An experience sequence deals with such a process of concept formation.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1993년도 Fifth International Fuzzy Systems Association World Congress 93
• /
• pp.798-801
• /
• 1993

This paper presents the decision support system using fuzzy knowledge to adapt the cutting conditions chosen by a conventional expert system to a particular machine tool, workpiece and clamping system. These preliminary results demonstrate the capability of fuzzy logic to adjust cutting parameters taking into account parameters difficult to quantify.

• 한국정밀공학회지
• /
• 제18권9호
• /
• pp.192-203
• /
• 2001

The design of gate and runner(delivery system) is one of the most important subject in injection molding. Delivery system is a channel to flow the polymer melt from the injection molding machine to the mold cavities. Also, delivery system affect quality and productivity of the part. The synthesis of delivery system of injection molding has been done empirically, since it requires profound knowledge about the moldability and causal effects on the properties of the part, which are not available to designers through the current CAD systems. GATEWAY is a knowledge module which contains knowledge to permit non-experts as well as mold design experts to generate the acceptable geometries of gate and runner far injection molded parts. A knowledge-based CAD system is constructed by adding the knowledge module, GATEWAY, to an existing geometric modeler. A knowledge-based CAD system is a new tool which enables the concurrent design and CIM with integrated and balanced design decisions at the initial design of injection molding.

• 복식
• /
• 제54권4호
• /
• pp.129-144
• /
• 2004

The modems who lives complicated society, the silence which the Orient thought asserts leads and to get comfortable. It is becoming, the like this social atmosphere will in the interest regarding a manual example and the Orient material, the use of the embroidery textile goods is increasing specially. The purpose of this article is to suggest a model for development of machine embroidery fabric material and highly value added apparel industries. The multi-headed embroidery machine where the application scope is wide from the dissertation, we are requested' NaNa company'. The multiheaded embroidery machine uses TAJIMA TMFD-G620 and SUNSTAR SWF-／B-WD(X) 620-100 the embroidery textile uses the silk, the cotton and the synthesis fertile goods etc 24 type, the embroidery thread Maraton thread(viscose rayon 100％) with used the cord. The 8 Korean motives are made on 23 fabrics, 6 of which are full-sized manufactured one-pieces and the other 17 of which are produced to home interior goods such as curtains or fashion accessories like handbags as simulations. Among the products, the pattern-4-1 and the pattern-4-2 are contracted with local fashion industry, and the pattern-1-1～3 are dealing with other companies in Japan. The computerized machine-embroidering and simulation producing of fashion items are available to reduce the cost in making samples and transfer the old labor ＆ toil-centered industry into the new technique ＆ knowledge centered one.