• International Journal of Precision Engineering and Manufacturing
• /
• 제1권2호
• /
• pp.35-42
• /
• 2000

To save time and cost in assembly process and to improve th quality of products, it is very important to choose and optimal assembly sequence. In this paper, we propose a methodology that generates an optimal assembly sequence by using various methods and the knowledge of experts. To illustrate the effectiveness of the proposed methodology, a knowledge-based system is developed, The built system is applied to the case of UBR(Unit Bath Room). The applying result showed the applicability of the developed system.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2004년도 추계학술대회 학술발표 논문집 제14권 제2호
• /
• pp.568-571
• /
• 2004

In this study, we propose an efficient expert system (ES) construction mechanism by using dynamic knowledge map (DKM) and database management systems (DBMS). Generally, traditional ES and ES developing tools has some limitations such as, 1) a lot of time to extend the knowledge base (KB), 2) too difficult to change the inference path, 3) inflexible use of inference functions and operators. First, to overcome these limitations, we use DKM in extracting the complex relationships and causal rules from human expert and other knowledge resources. Then, elation database (RDB) and its management systems will help to transform the relationships from diagram to relational table. Therefore, our mechanism can help the ES or KBS (Knowledge-Based Systems) developers in several ways efficiently. In the experiment section, we used medical data to show the efficiency of our mechanism. Experimental results with various disease show that the mechanism is superior in terms of extension ability and flexible inference.

• Journal of Advanced Marine Engineering and Technology
• /
• 제33권1호
• /
• pp.97-103
• /
• 2009

The process design of forward Extrusion and Upsetting of Axi-symmetric part has been studied in this paper. During the cold forging product; auto transmission Solenoid Valve part, the defects such as folding and under-fill can be appeared by the improperly controlled metal flow. In this study, to reduce the folding and under-fill the design of experiments has been used to find out the significant design variables in the design of forging process. This paper deals with an Process Planning with which designer can determine operation sequences even after only a little experience in Process Planning of Multi-Former products by multi-stage former working. The approach is based on knowledge-based rules, and a process knowledge-base consisting of design rules is built. Based on the systematic procedure of process sequence design, the forming operation of cold forged auto transmission Solenoid Valve part is analyzed by the commercial Finite Element program, DEFORM/2D.

• 한국정밀공학회지
• /
• 제14권5호
• /
• pp.22-33
• /
• 1997

This paper describes a research work of developing a computer-aided design of blanking and piercing for stator and rotor parts. Based on knowledge-based rules, the die design system, STRTDES2, is designed by considering several factors, such as complexities of blank geometry and punch profile, and availability of press equipment and standard parts. Therefore this system can carry out a die design for each process which is obtained from the result of an automated process planning system, STRTDES1 and generate part drawing and the assembly drawing of die set in graphic forms. Knowledges for die layout are extracted from plasticity theories, relevant references and empirical know-hows of experts in blanking industries.

• 한국정밀공학회지
• /
• 제13권8호
• /
• pp.40-51
• /
• 1996

This paper describes some research works of computer-aided design of blanking and piercing progressive die for stator and rotor parts. An approach to the system is based on knowledge based rules. The deveolped system is composed of six modules such as main program, input and shape treatment, production feasibility check, strip layout, die layout and drawing edit module. Using this system, design parameters ( geometric shapes, die and punch dimensions and dimensions of tool elements) are determined and output is gen- erated in graphic from. Knowledges for tool design are extracted from the plasticity theories, handbooks, relevant references and empirical know-hows of experts in blkanking companies. The developed system provides powerful capabilities for process planning and die design of stator and rotor parts.

• 인터넷정보학회논문지
• /
• 제2권2호
• /
• pp.117-126
• /
• 2001

본 논문에서는 지식기반 시스템의 퍼지 생성규칙을 술어논리 수준에서 표현할 수 있는 퍼지 Pr/T 네트를 제안한다. 퍼지 Pr/T 네트는 Pr/T 네트의 퍼지 확장이다. 퍼지 Pr/T 네트를 기반으로 퍼지추론 알고리즘을 제안한다. 퍼지추론 알고리즘은 퍼지 생성규칙에서 퍼지개념에 따라 적절한 믿음 값 함수를 사용하므로 다른 방법보다 더 사람의 직관과 추론에 가깝다.

• 대한지리학회지
• /
• 제43권5호
• /
• pp.761-774
• /
• 2008

원격탐사에서 위성 영상의 디지털 처리 기술이 발달하면서 GIS 자료와 지식 기반 전문가 시스템과의 통합에 대한 관심이 증가하고 있다. 본 연구에서는 위성영상을 토지피복 분류하는 과정에서 GIS 자료를 통합하기 위하여 기계 학습 기법과 규칙 기반 분류 기법을 적용하였다. 사례 지역을 대상으로 Landsat ETM+ 영상과 고도, 경사, 향, 수역과의 거리, 도로와의 거리, 인구밀도 등의 GIS 자료를 함께 활용하였다. C5.0 추론 기계 학습 알고리듬을 이용하여 350개의 표본점으로부터 결정 트리와 분류 규칙을 생성하였다. 본 연구에서 도출된 규칙을 이용하여 분류한 결과, 고독 수역과의 거리, 인구밀도 등의 GIS 자료가 규칙 기반 분류에 효과적인 것으로 나타났다. 본 연구에서 제안한 기계 학습과 지식 기반 분류 기법을 이용하면 다양한 GIS 자료들을 통합하여 위성영상을 보다 효과적으로 분류할 수 있다.

• 한국정밀공학회지
• /
• 제20권4호
• /
• pp.29-38
• /
• 2003

This paper deals with an automated computer-aided process planning and die design system with which designer can determine operation sequences even after only a little experience in process planning and die design of multi former-bolt products by multi-stage former working. The approach is based on knowledge-based rules, and a process knowledge base consisting of design rules is built. Knowledge fur the system is formulated from plasticity theories, empirical results and the empirical knowledge of field experts. Programs for the system have been written in AutoLISP for AutoCAD with a personal computer. An attempt is made to link programs incorporating a number of expert design rules with the process variables obtained by commercial FEM softwares, DEFORM and ANSYS, to form a useful package. The system is composed of four main modules. The process planning and die design module considers several factors, such as the complexities of preform geometry, punch and die profiles, specifications of available multi former, and the availability of standard parts. It can provide a flexible process based on either the reduction in the number of forming sequences by combining the possible two processes in sequence, or the reduction of deviation of the distribution and the level of the required forming loads by controlling the forming ratios. The system uses 2D geometry recognition and is integrated with the technology of process planning, die design, and CAE analysis. The standardization of die parts for multi former-bolt products requiring a cold forging process is described. The system developed makes it possible to design and manufacture multi former-bolt products more efficiently.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제29권5호
• /
• pp.289-294
• /
• 2002

다층신경회로망 구조의 재구성은 회로망의 일반화 능력이나 효율성의 관점에서 중요한 문제로 연구되어왔다. 본 논문에서는 신경회로망에 학습된 은닉 지식들을 추출하여 조합함으로써 신경회로망의 구조를 재구성하는 새로운 방법을 제안한다. 먼저, 각 노드별로 학습된 대표적인 지역 규칙을 추출하여 각 노드의 불필요한 연결구조들을 제거한 후, 이들의 논리적인 조합을 통하여 중복 또는 상충되는 노드와 연결구조를 제거한다. 이렇게 학습된 지식을 분석하여 노드와 연결구조를 재구성한 신경회로망은 처음의 신경회로망에 비하여 월등히 감소된 구조 복잡도를 가지며 일반적으로 더 우수한 일반화 능력을 가지게 됨을 실험결과로서 제시하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권10호
• /
• pp.2718-2731
• /
• 2023

This paper presents a method of using syntax and shallow semantic analysis for Vietnamese question generation (QG). Specifically, our proposed technique concentrates on investigating both the syntactic and shallow semantic structure of each sentence. The main goal of our method is to generate questions from a single sentence. These generated questions are known as factoid questions which require short, fact-based answers. In general, syntax-based analysis is one of the most popular approaches within the QG field, but it requires linguistic expert knowledge as well as a deep understanding of syntax rules in the Vietnamese language. It is thus considered a high-cost and inefficient solution due to the requirement of significant human effort to achieve qualified syntax rules. To deal with this problem, we collected the syntax rules in Vietnamese from a Vietnamese language textbook. Moreover, we also used different natural language processing (NLP) techniques to analyze Vietnamese shallow syntax and semantics for the QG task. These techniques include: sentence segmentation, word segmentation, part of speech, chunking, dependency parsing, and named entity recognition. We used human evaluation to assess the credibility of our model, which means we manually generated questions from the corpus, and then compared them with the generated questions. The empirical evidence demonstrates that our proposed technique has significant performance, in which the generated questions are very similar to those which are created by humans.