Semantic Processing of Engineering D Documents in PLM Environment - - PowerPoint PPT Presentation

semantic processing of engineering d documents in plm
SMART_READER_LITE
LIVE PREVIEW

Semantic Processing of Engineering D Documents in PLM Environment - - PowerPoint PPT Presentation

Semantic Processing of Engineering D Documents in PLM Environment t i PLM E i t * KAIST * KAIST * * / *


slide-1
SLIDE 1

Semantic Processing of Engineering D t i PLM E i t Documents in PLM Environment

* KAIST 산업 및 시스템공학과 * 서효원 교수 * KAIST 산업 및 시스템공학과 * 전상민 박사과정/한국타이어 *김경근 박사과정/국방과학연구소 *최승아 석사과정 *최승아 석사과정

slide-2
SLIDE 2

Contents Contents

1 B k d

  • 1. Background

2 New Approach

  • 2. New Approach
  • 3. Research Trend & Paper Introduction

p

  • 4. Introduction of Basic Algorithm
  • 5. Case Study 1,2,3
  • 6. Conclusion

1

slide-3
SLIDE 3

Contents Contents

1 B k d

  • 1. Background

2 New Approach 2 New Approach

  • 2. New Approach
  • 2. New Approach
  • 3. Research Trend & Paper Introduction
  • 3. Research Trend & Paper Introduction

p

  • 4. Introduction of Basic Algorithm
  • 4. Introduction of Basic Algorithm
  • 5. Case Study 1,2,3
  • 5. Case Study 1,2,3
  • 6. Conclusion
  • 6. Conclusion

2

slide-4
SLIDE 4

1 B k d (AS IS)

  • 1. Background (AS-IS)
  • 제품 개발 시 Engineering 문서 폭증
  • 제품 개발 시 Engineering 문서 폭증
  • 요구사항 설계 해석 제조 시험 양산
  • 어디서? 어떻게? 원하는 문서를 빠르게 얻을 수 있을까?
  • PLM이 보편화/안정화/고도화 단계

문서의 저장/관리 다 탐색/검색이 더 부각

  • 문서의 저장/관리 보다 탐색/검색이 더 부각
  • 기존 Engineering 문서의 검색

기존 Engineering 문서의 검색

  • Keyword 검색 선택의 폭 너무 넓음

3

slide-5
SLIDE 5

1 B k d (TO BE)

  • 효율적인 Engineering 문서 검색을 위해
  • 1. Background (TO-BE)
  • 효율적인 Engineering 문서 검색을 위해,
  • 문서 Package관리가 아닌 Text 기반 Contents 관리
  • Keyword 검색이 아니 의미기반 검색
  • 의미기반 검색을 위해,

정 의 S i 구축 필

  • 정보의 Semantics 구축 필요
  • 이를 기반으로, 문서의 Semantic Processing 진행

*Semantic Processing = Syntax Processing(NLP) + Semantic Processing(Ontology)

Semantic Processing = Syntax Processing(NLP) + Semantic Processing(Ontology)

  • Semantic Processing 기반 Engineering 문서 관리
  • 정보 검색의 효율성 (↑)
  • 정보 재 활용성 (↑)

정보의 통합성 (↑)

  • 정보의 통합성 (↑)

4

slide-6
SLIDE 6

Contents Contents

1 B k d 1 B k d 2 New Approach

  • 1. Background
  • 1. Background
  • 2. New Approach
  • 3. Research Trend & Paper Introduction
  • 3. Research Trend & Paper Introduction

p

  • 4. Introduction of Basic Algorithm
  • 4. Introduction of Basic Algorithm
  • 5. Case Study 1,2,3
  • 5. Case Study 1,2,3
  • 6. Conclusion
  • 6. Conclusion

5

slide-7
SLIDE 7

2 N A h

  • 2. New Approach

UC: user created WS/SS/NS: well/semi/non structured PCD: producer-centric data 의미 분석 구문 분석 Folksonomy Taxonomy

Neutral Data PCD Data Base

PCD: producer centric data CCD: consumer-centric data

Neutral Data CCD Engineering 문서 (WS/SS/NS) 의미기반 검색 Semantic Processor Data & Knowledge Base Engineers Engineer WS data 참조 의미 모델 Engineer

SN Data

정보 생산 측면 정보 소비 측면

SNS users

6

S-NL (약식 자연어 처리) 분야별 참조모델 온톨로지 의미표현 의미 유사도 평가 자기기반 검색

slide-8
SLIDE 8

Contents Contents

1 B k d 1 B k d

  • 1. Background
  • 1. Background

2 New Approach 2 New Approach

  • 3. Research Trend & Paper Introduction
  • 2. New Approach
  • 2. New Approach

p

  • 4. Introduction of Basic Algorithm
  • 4. Introduction of Basic Algorithm
  • 5. Case Study 1,2,3
  • 5. Case Study 1,2,3
  • 6. Conclusion
  • 6. Conclusion

7

slide-9
SLIDE 9

R h T d (1/2) Research Trend (1/2)

1. Wu Ying-Han; Shaw Heiu-Jou, “Document based knowledge base engineering method for ship basic design” OCEAN ENGINEERING Volume: 38 Issue: 13 Pages: 1508 1521 SEP 2011 design , OCEAN ENGINEERING Volume: 38 Issue: 13 Pages: 1508-1521, SEP 2011 2. Wang Han-Hsiang; Boukamp Frank; Elghamrawy Tar, “Ontology-Based Approach to Context Representation and Reasoning for Managing Context-Sensitive Construction Information”, JOURNAL OF COMPUTING IN CIVIL ENGINEERING V l 25 I 5 P 331 346 SEP OCT 2011 OF COMPUTING IN CIVIL ENGINEERING Volume: 25 Issue: 5 Pages: 331-346, SEP-OCT 2011 3. Liu S.; McMahon C. A.; Culley S. J., “A review of structured document retrieval (SDR) technology to improve information access performance in engineering document management”, COMPUTERS IN INDUSTRY V l 59 I 1 P 3 16 JAN 2008 INDUSTRY Volume: 59 Issue: 1 Pages: 3-16, JAN 2008 4.

  • S. Liu, C.A. McMahon *, M.J. Darlington, S.J. Culley, P

.J. Wild, “A computational framework for retrieval

  • f document fragments based on decomposition schemes in engineering information management”,

d d i i f i 1 1 Advanced Engineering Informatics 20 (2006) 401–413 5. Zhanjun, L., Karthik, R., A., (2007), " Ontology-based design information extraction and retrieval " Artificial Intelligence for Engineering Design, Analysis and Manufacturing 21, pp. 137–154. 6. Zhanjun Li, Victor Raskin, Karthik Ramani, ”Developing Engineering Ontology for Information Retrieval”, Journal of Computing and Information Science in Engineering, 3.2008, vol 8 7. Zhanjun Li, Maria C.Yang, Karthik Ramani, “A methodology for engineering ontology acquisition and validation”, Artificial Intelligence for Engineering Design, Analysis and Manufacturing, 2009, vol 23

8

slide-10
SLIDE 10

R h T d (2/3) Research Trend (2/3)

8. Zhanjun Li Min Liu David C. Anderson Karthik Ramani, “Semantic-based design knowledge annotation and retrieval” Proceedings of IDETC/CIE 2005 ASME 2005 International Design annotation and retrieval , Proceedings of IDETC/CIE 2005 ASME 2005 International Design Engineering Technical Conferences & Computer and information in Engineering Conference September 24-28, 2005, Long Beach, California, USA 9. Deeptimahanti Deva Kumar, Ratna Sanyal(2008) “ Static UML Model Generator from Analysis of p y ( ) y Requirements(SUGAR)” 2008 Advanced Software Engineering & Its Applications, pp. 77–84.

  • 10. Lin, JX ; Fox, MS ; Bilgic, T(1996) “ A Requirement Ontology for Engineering Design” Concurrent

Engineering-Research and Iapplications, Vol 4, Issue3, pp. 279-291.

  • 11. Soner, K., Ozgur, A., Orkunt, S., Samet, A., Nihan, K.C., Ferda, N.A., (2012), " An ontology-based

retrieval system using semantic indexing," Information Systems, 37, pp. 294-305. 12 Li M H (2009) " A ti l kl d b d d t ll ti h f ltidi k d t b "

  • 12. Lin, M., H., (2009), " An optimal workload-based data allocation approach for multidisk databases"

Data and knowledge Engineering, 68, pp. 499–508.

  • 13. Patricia, L., (2000), " Information extraction from documents for automating software testing,"

Artificial Intelligence in Engineering 14 pp 63-69 Artificial Intelligence in Engineering, 14, pp. 63 69.

  • 14. Module-based Failure Propagation (MFP) model for FMEA, Int J Adv Manuf Technol, Kyoung-Won

Noh, Hong-Bae Jun, Jae-Hyun Lee, Gyu-Bong Lee, Hyo-Won Suh, 2011

  • 15. A Functional Basis for Engineering Design: Reconciling and Evolving Previous Efforts, NIST Technical

Note 1447, Julie Hirtz, Robert B. Stone, Daniel A. McAdams, Simon Szykman, and Kristin L. Wood, 2002

9

slide-11
SLIDE 11

Ontology-based design information gy g extraction and retrieval

ZHANJUN LI and KARTHIK RAMANI Artificial Intelligence for Engineering Design, Analysis and Manufacturing (2007), 21, 137–154.

10

slide-12
SLIDE 12

1 Ab t t

  • 1. Abstract
  • Increasing complexity of product design process

g p y p g p

the number of design documents has exploded

  • To design information retrieval

Shallow natural language process(NLP) Domain-specific design semantics/ontology

Text/unstructured structured/semantic-based representation

Linguistic Patten Design Concept & Relationship DOC (Text) Application Specific Design Semantics

  • To improve the performance of design information retrieval

Developed ontology-based query processing Developed ontology based query processing

Users’ requests are interpreted based on domain-specific meanings

Design Concept Doc Design Concept Scoring & Pairing Doc. Retrieval Query

11

slide-13
SLIDE 13

2 S t A hit t & F ti l Di

  • 2. System Architecture & Functional Diagram

ODART: Ontology-based Design document Analysis and Retrieval Tool gy g y 구문분석 의미 분석 Doc Semantics Query Query Semantics

Processed Query

Query

12

slide-14
SLIDE 14

3 O t l M d li

  • 3. Ontology Modeling

Taxonomy < Linguistic Knowledge> Reference Model < Domain Knowledge>

13

Reference Model

slide-15
SLIDE 15

4 D i S ti E t ti

  • 4. Design Semantic Extraction

< Linguistic Knowledge> < Linguistic Knowledge> < Design Semantic/Taxonomy Model> <Device Taxonomy>

14

< Domain Knowledge>

slide-16
SLIDE 16

4 D i S ti E t ti

  • 4. Design Semantic Extraction
slide-17
SLIDE 17

5 E l ti

  • 5. Evaluation

Find products having DC motors

16

slide-18
SLIDE 18

Contents Contents

1 B k d 1 B k d

  • 1. Background
  • 1. Background

2 New Approach 2 New Approach

  • 3. Research Trend & Paper Introduction
  • 3. Research Trend & Paper Introduction
  • 2. New Approach
  • 2. New Approach

p

  • 4. Introduction of Basic Algorithm
  • 5. Case Study 1,2,3
  • 5. Case Study 1,2,3
  • 6. Conclusion
  • 6. Conclusion

17

slide-19
SLIDE 19

Introduction of Basic Algorithm f ti d t i for semantic document processing

18

slide-20
SLIDE 20

1 알고리즘 O tli

  • 1. 알고리즘 Outline

의미기반 텍스트 프로세싱 문서 프로세싱 프로세싱

19

의미기반 CAD 프로세싱

slide-21
SLIDE 21

2 문서 프로세싱

  • 2. 문서 프로세싱

Engineering Engineering DOC (구조/텍스트) Bayesian classification 분류된 문서 POI Extractor 타이틀 구조 텍스트 POI Extractor 타이틀 (키워드) 구조 (계층) 텍스트 (테이블) TF-IDF Tokenization 단위 문장 텍스트 주제 IE, OP

  • TF-IDF : Term Frequency - Inverse Document Frequency

인덱스/인스턴스/ 구조 문장

  • IE : Information Extraction
  • OP : Ontology Population

20

slide-22
SLIDE 22

2 1 주요 알고리즘

Input Algorithm Output

2.1. 주요 알고리즘

문서 ex) FMEA Doc. Bayesian classification 분류된 문서 ex) Class 1 Brief Algorithm Description

D Training Data Set Feature generation Classifier (model) Doc Prediction Classification

Example

( )

Training data sets

w1 w2 … Class FMEA Failure Analysis 1 Evaluation Measure 1 Concept Design 2

(FMEA, Failure Analysis…) 사용 R f

p g Detail Design 2 CAD Drawing 3 … … ..

Output : Class 1 Training data sets 사용 Reference

21

slide-23
SLIDE 23

2 2 주요 알고리즘

Input Algorithm Output

2.2. 주요 알고리즘

분류된 문서 Apache POI Extractor API 타이틀, 구조, Text 추출 Example Output :

  • Title : FMEA(FAILURE MODE AND EFFECTS ANALYSIS) Doc.
  • Structure :

Structure

Meta-data : Image : 0 개, Table : 1개, Text : 11줄, 작성자 : Mr.An, 문서생성일 : 2010.3.20 …

  • Text : FMEA(FAILURE MODE AND EFFECTS ANALYSIS) Doc.

Reporting Person : Mr An Reporting Person : Mr. An Reporting Date : 2010.05.01

  • Overall assessment : There are mal-functions

in Filtering to collect dust and remove gas. It makes a fan not purifying polluted air…

사용 R f 사용 Reference

22

slide-24
SLIDE 24

2 3 주요 알고리즘

Input Algorithm Output

2.3. 주요 알고리즘

문서(Text) Inverted Index Inverted index Brief Algorithm Description

문서 Tokenization 문서의 Token List 생성 Token Normalization Token 별 문서 정보 색인

Example

FMEA (FAILURE MODE AND EFFECTS Term Docum ent ID FMEA

Stopword list

  • A

FMEA (FAILURE MODE AND EFFECTS FMEA (FAILURE MODE AND EFFECTS ANALYSIS) Doc. Reporting Person : Mr.

  • An. Reporting Date : 2010.05.01.

There are mal-functions in Filtering to collect dust and remove gas. It makes a fan not purifying polluted air 1 FMEA 1 2 FAILURE 1.2 3 Design 1,3 4 Reporting 1,2,4

A

  • And
  • Around
  • Every
  • For
  • From
  • In

FMEA (FAILURE MODE AND EFFECTS ANALYSIS) Doc. Reporting Person : Mr.

  • An. Reporting Date : 2010.05.01.

There are mal-functions in Filtering to collect dust and remove gas. It makes a FMEA (FAILURE MODE AND EFFECTS ANALYSIS) Doc. Reporting Person : Mr.

  • An. Reporting Date : 2010.05.01.

There are mal-functions in Filtering to collect dust and remove gas. It makes a

사용 R f

fan not purifying polluted air… … … … … … …

In

  • Is
  • It

...

fan not purifying polluted air… collect dust and remove gas. It makes a fan not purifying polluted air…

사용 Reference

23

slide-25
SLIDE 25

2 4 주요 알고리즘

Input Algorithm Output

2.4. 주요 알고리즘

문서(Text) TF-IDF Text Weighting (중요도) Brief Algorithm Description Example

Doc.1 Doc.2 Doc.3 … FMEA FMEA 4 2 1 Failure 5 2 4 Lack 3 Fan 13 … … … …

FMEA (FAILURE MODE AND EFFECTS ANALYSIS) Doc. Reporting Person : Mr.

  • An. Reporting Date : 2010.05.01.

There are mal-functions in Filtering to collect dust and remove gas It makes a FMEA (FAILURE MODE AND EFFECTS ANALYSIS) Doc. Reporting Person : Mr.

  • An. Reporting Date : 2010.05.01.

There are mal-functions in Filtering to ll t d t d It k FMEA (FAILURE MODE AND EFFECTS ANALYSIS) Doc. Reporting Person : Mr.

  • An. Reporting Date : 2010.05.01.

There are mal-functions in Filtering to

… … … … Doc.1 Doc.2 Doc.3 … FMEA 0.365 0.5228 0.157 Failure 0.406 0.5228 0.365

collect dust and remove gas. It makes a fan not purifying polluted air… collect dust and remove gas. It makes a fan not purifying polluted air… g collect dust and remove gas. It makes a fan not purifying polluted air…

Lack 0.602 Fan 1.146 … … … … … … … …

Output : ‘Fan’ is the most important word 사용 Reference Output : Fan is the most important word.

24

slide-26
SLIDE 26

3 의미기반 텍스트 프로세싱 & 검색

  • 3. 의미기반 텍스트 프로세싱 & 검색

단위 문장 Query (문장) 단위 문장 Tokenization 단어 Lexicon y (문장) 단어 Tokenization POS Tagged 단어 POS tagging POS Tagged 단어 POS tagging gg 단어 Concept Concept Disambiguation Domain Ontology 단어 Concept Concept Disambiguation Concept Joining p 추출 Semantic Doc. Representation 추출 Concept Joining p Relationship Concept Indexing Relationship Similarity 계산 Vector Space Model Document 획득 25 Vector Space Model

slide-27
SLIDE 27

3 1 주요 알고리즘

Input Algorithm Output

3.1. 주요 알고리즘

문장 Tokenization Token(단어) Brief Algorithm Description

문장 단어 구분자 (하이픈, 생략부호, 마침표..) Token 생성

Example A second DC motor rotates air that makes a smell removed A/ second/ DC/ motor / rotates/ air/ that/ makes/ a/ smell/ removed/ 사용 R f A/ second/ DC/ motor / rotates/ air/ that/ makes/ a/ smell/ removed/ 사용 Reference

26

slide-28
SLIDE 28

3 2 주요 알고리즘

Input Algorithm Output

3.2. 주요 알고리즘

문장 POS(Part-of-Speech) tagging POS tagging Brief Algorithm Description

Lexicon DB POS Tagging

Example A/ second/ DC/ motor / rotates/ air/ that/ makes/ a/ smell/ removed

DT – Determiner JJ - Adjective

A/ second/ DC/ motor / rotates/ air/ that/ makes/ a/ smell/ removed. A<DT> second<JJ> DC<NN> motor > rotates<VBZ> air<NN> that<TDT> makes<VBZ> a<DT> smell<NN> removed<VBZ>

NN - Noun, singular or mass VBZ - Verb, 3rd person singular present TO – to CD - Cardinal number NNS - Noun, plural

사용 R f air<NN> that<TDT> makes<VBZ> a<DT> smell<NN> removed<VBZ>.

NNS Noun, plural RB – Adverb CC - Coordinating conjunction …

Lexicon DB 사용 Reference

27

slide-29
SLIDE 29

3 3 주요 알고리즘

Input Algorithm Output

3.3. 주요 알고리즘

한글 문장 한글 형태소 분석 한글 POS tagging Brief Algorithm Description

텍스트 내용 읽음 Number Dictionary 한국어 형태소 분석 (Korean Morphological Analysis) System Dictionary (283 948단어) Tag Set Table User Dictionary (Domain Lexicon DB) 한국어 품사 태깅(POS Tagging) (283,948단어)

한나눔 한글 형태소 분석기 (HanNanum v0 8 4)

Example

한나눔 한글 형태소 분석기 (HanNanum v0.8.4)

유도탄 중량을 현재 100kg에서 80kg으로 감량 설계 추진 요망 사용 R f 유도탄 중량을 현재 100kg에서 80kg으로 감량 설계 추진 요망 유도탄/NC 중량/NC 100/NN kg/F 에/PV 80/NN kg/F 감량/NC 설계/NC 추진/NC 요망/NC System Dictionary, User Dictionary, Number Dictionary, Tag Set Table

28

사용 Reference

slide-30
SLIDE 30

3 4 주요 알고리즘

Input Algorithm Output

3.4. 주요 알고리즘

문장 Concept Disambiguation 문장과 가장 유사한 Concept Brief Algorithm Description

  • Wm : weight of phrase

( contain only one word : Wm = 1, No match : Wm = 0, Rightmost matched : 0.55 [가장 매칭되는 단어에게 높은 점수]

Example

[ ] Rest of : split 0.45 equally ) ex) phrase : “second DC Motor” ) p 0.225 0.225 0.55 Concept 이 “Motor” 일 경우, Tscore= (1*(0+0+0.55) )/ 3 = 0.183 Concept이 “AC Motor”일 경우, Tscore= (1*(0+0+0 55) )/ 3 = 0 183

AC-Motor DC-Motor Motor

사용 R f

Tscore= (1 (0+0+0.55) )/ 3 = 0.183 Concept이 “DC Motor”일 경우 Tscore= (2*(0+0.225+0.55) )/ 3 = 0.516 DC Motor 가 가장 높은 점수로 선택됨.

사용 Reference

29

slide-31
SLIDE 31

3 5 주요 알고리즘

Input Algorithm Output

3.5. 주요 알고리즘

문장 Joining Concept Relationship Brief Algorithm Description

Syntax Rule Joining

Example Input : DC motor rotates fan. DC<NN> motor<NN> rotates<VBZ> fan<NN>. Syntax Rule : NN^VBZ^NN -> VBZ(NN,NN) 사용 R f Syntax Rule : NN VBZ NN VBZ(NN,NN) Rotate(DC Fan, air) 사용 Reference

30

slide-32
SLIDE 32

3 6 주요 알고리즘

Input Algorithm Output

3.6. 주요 알고리즘

문서(Text) Concept Index Concept index Brief Algorithm Description

문서 Concept 추출 Concept Disambiguation 문서 내 Concept List Concept 별 문서 정보 색인

Example

FMEA (FAILURE MODE AND EFFECTS Term Docum ent ID FMEA FMEA (FAILURE MODE AND EFFECTS

Report

FMEA (FAILURE MODE AND EFFECTS ANALYSIS) Doc. Reporting Person : Mr.

  • An. Reporting Date : 2010.05.01.

There are mal-functions in Filtering to collect dust and remove gas. It makes a fan not purifying polluted air 1 FMEA 1 2 FAILURE 1.2 3 Dust 1,3 4 Gas 1,2,4 FMEA (FAILURE MODE AND EFFECTS ANALYSIS) Doc. Reporting Person : Mr.

  • An. Reporting Date : 2010.05.01.

There are mal-functions in Filtering to collect dust and remove gas. It makes a FMEA (FAILURE MODE AND EFFECTS ANALYSIS) Doc. Reporting Person : Mr.

  • An. Reporting Date : 2010.05.01.

There are mal-functions in Filtering to collect dust and remove gas. It makes a

FEMA Failure

사용 R f

fan not purifying polluted air… … … … … … … fan not purifying polluted air… collect dust and remove gas. It makes a fan not purifying polluted air…

Dust Gas

사용 Reference

31

slide-33
SLIDE 33

3 7 주요 알고리즘

Input Algorithm Output

3.7. 주요 알고리즘

Query, 문서들 Vector Space Model (Similarity) Query와 가장 유사한 문서 Brief Algorithm Description Example 문서 내 각 단어의 Score, ex) FMEA, Failure, Dust, Gas…) D2와 D3가 가장 유사함 문서 내 각 단어의 Score, ex) FMEA, Failure, Dust, Gas ) 사용 R f 가장 유사함 사용 Reference

32

slide-34
SLIDE 34

4 의미기반 CAD 모델 추출 및 검색

  • 4. 의미기반 CAD 모델 추출 및 검색

DOC DOC

CAD

주요 Parameter 추출 Lexicon Feature 추출 Domain Ontology Feature 속성 추출 F Ontology Feature Disambiguation F t XML Feature Indexing

Query

Feature XML Feature Indexing

Query

33

slide-35
SLIDE 35

Contents Contents

1 B k d 1 B k d

  • 1. Background
  • 1. Background

2 New Approach 2 New Approach

  • 3. Research Trend & Paper Introduction
  • 3. Research Trend & Paper Introduction
  • 2. New Approach
  • 2. New Approach

p

  • 4. Introduction of Basic Algorithm
  • 4. Introduction of Basic Algorithm
  • 5. Case Study 1,2,3
  • 6. Conclusion
  • 6. Conclusion

34

slide-36
SLIDE 36

C St d O tli Case Study Outline

CASE 3. 유사한 과거 CASE 2. Conceptual design of Semantic Issue management system FMEA 문서 추출 CASE 1. 문서기반 CAD Model 검색

PCD Neutral Data CCD Engineering 문서 Data Base 의미기반 검색 Semantic Processor Data & Knowledge E i WS data 문서 (WS/SS/NS) 검색 Processor Knowledge Base Engineers 참조 Engineer data

SN

35

정보 생산 측면 정보 소비 측면

참조 의미 모델

SN Data

SNS users

slide-37
SLIDE 37

CASE STUDY 1 : 문서 기반 CAD Model 검색

36

slide-38
SLIDE 38

1 재사용을 위한 CAD M d l 검색의 문제점

Case Study 1 : 문서기반 CAD Model 검색 (1/16)

  • 1. 재사용을 위한 CAD Model 검색의 문제점
  • CAD Model의 재사용
  • CAD Model의 재사용
  • 제품 설계 시 80%의 CAD Model이 재사용 되고 있음.
  • 성공적인 재사용은 50%의 비용 절감 효과 발생.
  • 현재 CAD Model 검색 방법
  • CAD File 이름을 통해
  • CAD File 이름을 통해
  • 정보 시스템(PLM,PDM)의 정보(BOM) 기반 검색

사용자가 의도한 검색에 한계 (검색 결과 중 48%는 사용 불가[1])

  • 보다 효과적인 검색 및 재사용을 위해서
  • 단순 이름 및 정보 기반이 아닌 Semantic CAD Model검색 필요
  • 단순 이름 및 정보 기반이 아닌 Semantic CAD Model검색 필요
  • CAD Model에 대한 Knowledge 추출 및 재사용 필요

[1] LI, M, Y F Zhang*, J Y H Fuh and Z M Qiu, "Towards effective mechanical design reuse: feature-based CAD model retrieval on general shapes and partial shapes". JOURNAL OF MECHANICAL DESIGN, (2009).

37

slide-39
SLIDE 39

2 CAD M d l 재 사용 예

Case Study 1 : 문서기반 CAD Model 검색 (2/16)

  • 2. CAD Model 재 사용 예

<PLM>

Update Simulation Accuracy <Detail Design>

QFD, DFEMA, B/M Report Basic Spec. (Dimension, Construction, Material) Test Result Test Result

Update Simulation Accuracy Re-design

Drawing M-BOM Tire

<Detail Design>

Engineering Requirement Design Concept Design Simulation Test Production Performance Test Manuf. Spec.

Sub Process

CAD Report CAD Report

<CAD&CAE>

Report

Drawing

CAD Mesh ODB Report CAD Mesh ODB Report Pattern Simulation Pattern Design Mold Drawing FEA Simulation Post-Process (Report) p

: Output Legend

Construction Design Pre-Process (Meshing) CAD

: Output : Process

Sidewall Design

38

slide-40
SLIDE 40

3 문서 기반 CAD 모델 검색 프로세스 (1/2)

Case Study 1 : 문서기반 CAD Model 검색 (3/16)

3.문서 기반 CAD 모델 검색 프로세스 (1/2)

유사 유사도 계산

Concept 문서 Semantic 문서 모델 Semantic CAD 모델 CAD 모델 39

slide-41
SLIDE 41

3 문서 기반 CAD 모델 검색 프로세스 (1/2)

Case Study 1 : 문서기반 CAD Model 검색 (4/16) Doc Representation Syntactic Analysis Semantic Analysis

3.문서 기반 CAD 모델 검색 프로세스 (1/2)

문서 Text 추출 (Table 정보) Tokenization Concept 추출 Concept Concept XML 생성 Concept Indexing

DOC

Tokenization Sentence Segmentation p Disambiguation Concept Joining Concept Indexing Semantic 문서 모델 생성 (OWL)

DOC

DOC Lexicon DB Ontology DB Semantic Model DB

Feature Extraction

주요 Parameter 추출 Feature XML 생성

CAD Representation Feature Analysis

Feature Parameter 추출 Feature 추출 Feature Relationship추출 Feature Indexing

DOC DOC

CAD Disambiguation Feature 속성 추출 Semantic CAD 모델 생성

40

slide-42
SLIDE 42

CASE STUDY 2 : Conceptual design of S ti I t t Semantic Issue management system

41

slide-43
SLIDE 43

1 AS IS

Case Study 2 : Conceptual design of Semantic Issue management system (1/19)

  • 1. AS-IS

AS-IS AS-IS

① 매일 매일 시스템 개발 프로젝트와 관련한 다양한 형태의 회의, 토의, 의사결정이 이루 어지고 있지만, 이에 대한 내용은 참석자 및 관련자(회의록 등을 메일로 전달받은 사람) 들에게만 전달되고 있음. ② 시스템 또는 서브시스템의 규격, 설계사항과 관련하여 토의되는 내용이 대부분이지만, 이와 관련한 분류(시스템 구성에 따른) 및 변 이와 관련한 분류(시 템 구성에 따른) 및 변 경사항 반영은 현재는 모두 데이터베이스 관 리자가 직접 수행하여야 하는 상태임. ③ 심각한 overhead 발생 ③ 심각한 overhead 발생. ④ 변경사항 반영이 실시간으로 이루어지지 못 하고 있으며, 누락사항 발생도 충분히 가능 한 상태임 한 상태임.

42

slide-44
SLIDE 44

2 TO BE

Case Study 2 : Conceptual design of Semantic Issue management system (2/19)

  • 2. TO-BE
  • 제안 사항

① 조직 구성(OBS), 업무분할구조(WBS), 시스템 분해구조(SBS), 요구사항 전 개구조(RBS)를 Ontology 모델 등으로 구축. Reference Ontology Model gy ② 회의 및 의사결정 데이터 입력 : 회의록 (document) 또는 SE 도구를 이용한 well-structured data. ③ 입력 데이터를 Reference Ontology ③ 입력 데이터를 Reference Ontology model을 이용, 각 조직, 업무, 시스템 에 대하여 Semantic하게 할당, 재정리.

TO-BE

① 엔지니어가 출근하여 PLM시스템에 로 그인하게 되면, 항상 자기자신의 업무 (또는 조직, 담당 시스템, 요구사항)와 관련하여 토의되거나 의사 결정된 내용 을 실시간으로 확인 가능. ② 자기자신이 현재 해결하여야 할 이슈 ② 자기자신이 현재 해결하여야 할 이슈 (회의의 경우 Action item)을 실시간으 로 확인 가능. 43

slide-45
SLIDE 45

3 TO BE W k Fl

Case Study 2 : Conceptual design of Semantic Issue management system (3/19)

  • 3. TO-BE Work Flow

44

slide-46
SLIDE 46

Contents Contents

1 B k d 1 B k d

  • 1. Background
  • 1. Background

2 New Approach 2 New Approach

  • 3. Research Trend & Paper Introduction
  • 3. Research Trend & Paper Introduction
  • 2. New Approach
  • 2. New Approach

p

  • 4. Introduction of Basic Algorithm
  • 4. Introduction of Basic Algorithm
  • 5. Case Study 1,2,3
  • 5. Case Study 1,2,3
  • 6. Conclusion

45

slide-47
SLIDE 47

C l i Conclusion

  • 제품 개발 관련 Engineering 문서 폭증 효율적 검색 방안 필요
  • 제품 개발 관련 Engineering 문서 폭증 효율적 검색 방안 필요
  • PLM이 보편화/안정화/고도화 단계 탐색/검색 기능 부각
  • Keyword 검색 선택의 폭 너무 넓음
  • Semantic Processing 기반 Engineering 문서 관리/검색
  • 정보 검색의 효율성 (↑)
  • 정보 검색의 효율성 (↑)
  • 정보 재 활용성 (↑)
  • 정보의 통합성 (↑)

46

slide-48
SLIDE 48

Question and Answer Q THANK YOU ☺

47