Design Knowledge Acquisition and Re-use Using Genetic Engineering-based Genetic Algorithms

2001 ◽  
pp. 107-121
Author(s):  
John S. Gero ◽  
Vladimir Kazakov
Keyword(s):  
Genetic Algorithms ◽  
Genetic Engineering ◽  
Knowledge Acquisition ◽  
Design Knowledge

Personalized knowledge push system based on design intent and user interest

2015 ◽  
Vol 230 (11) ◽  
pp. 1757-1772 ◽  
Author(s):  
Zhan-Song Wang ◽  
Ling Tian ◽  
Yuan-Hao Wu ◽  
Bei-Bei Liu
Keyword(s):  
Knowledge Acquisition ◽  
Conceptual Design ◽  
Current Knowledge ◽  
Target Function ◽  
Design Knowledge ◽  
Prototype System ◽  
Sorting Algorithm ◽  
Illustrative Case ◽  
User Interest ◽  
Design Intent

Existing knowledge provides important reference for designers in mechanical design activities. However, current knowledge acquisition methods based on information retrieval have the problem of inefficiency and low precision, which mainly meet the requirement for knowledge coverage. To improve the efficiency of knowledge acquisition and ensure the availability of design knowledge, this paper proposes a knowledge push service method based on design intent and user interest. First, the design intent model, which is mainly the formal expression of the target function of conceptual design, is built. Second, the user interest model that consists of domain themes and operation logs is built, and an automatic updating method of user interest is proposed. Third, a matching method of design knowledge based on design intent, and a sorting algorithm of knowledge candidates based on user interest are proposed to realize personalized knowledge active push service. Finally, a prototype system called Personalized Knowledge Push System for Mechanical Conceptual Design (MCD-PKPS) is implemented. An illustrative case demonstrates that the proposed method can successfully improve the efficiency and availability of knowledge acquisition.

Nested Ripple Down Rules (NRDR) as a Design Assistant in Mechanical Dimensional Tolerancing

2010 ◽  
Author(s):  
Ramsey F. Hamade ◽  
Ali H. Ammouri ◽  
G. Beydoun
Keyword(s):  
Knowledge Management ◽  
Knowledge Acquisition ◽  
Management System ◽  
Knowledge Management System ◽  
Design Knowledge ◽  
Mathematical Functions ◽  
Acquisition Process ◽  
Engineering Standards ◽  
To Receive ◽  
Ripple Down Rules

The dimensional tolerancing knowledge management system presented in this paper uses Nested Ripple down Rules (NRDR) targeted towards incrementally capturing expert design knowledge. A demonstrated example of such captured knowledge is that which human designers utilize in order to specify dimensional tolerances on shafts and mating holes in order to meet desired classes of fit as set by relevant engineering standards. In doing so, NRDR interface was designed to receive mathematical functions with their specifications prior and during the KA process. This is necessary to be able to exploit relationships among several classes with respect to certain numerical features of the cases in order to accelerate the convergence of the NRDR knowledge acquisition process by generating artificial cases which are likely to trigger the addition of exception rules. The incorporation of equations constitutes a novel contribution to the field of knowledge acquisition with NRDR. The developed dimensional tolerancing knowledge management system would help mechanical designers become more effective in the time-consuming tolerancing process of their designs in the future.

A methodology of design knowledge acquisition for use in learning expert systems

1987 ◽  
Vol 27 (1) ◽  
pp. 23-32 ◽  
Author(s):  
Tomasz Arciszewski ◽  
M. Mustafa ◽  
Wojciech Ziarko
Keyword(s):  
Expert Systems ◽  
Knowledge Acquisition ◽  
Design Knowledge

Causal Design Knowledge Acquisition by Constructing BBN Through FCM

2008 ◽  
Author(s):  
Yun Seon Kim ◽  
Kyoung-Yun Joseph Kim ◽  
Wooi Ping Cheah ◽  
Hyung-Jeong Yang
Keyword(s):  
Knowledge Acquisition ◽  
Knowledge Engineering ◽  
Product Liability ◽  
Cognitive Map ◽  
Fuzzy Cognitive Map ◽  
Design Knowledge ◽  
Propagation Mechanism ◽  
Causal Knowledge ◽  
Track Record ◽  
The Individual

Managing design knowledge is an important concern for industry, including engineering. Engineering firms are facing pressures to increase the quality of their products, to have even shorter lead times and reduced costs. There is also a trend towards globalization resulting in complex supply chains and the need to manage teams that are not necessarily co-located. Design knowledge needs to be exchanged and accessed efficiently. Other motivations for managing design knowledge are to provide a trail for product liability legislation and to retain design knowledge and experience as engineering designers retire. Fuzzy Cognitive Map (FCM) is one of the main formalisms for modeling, representing and reasoning about causal knowledge. Despite the fact that FCM has been used extensively in causal knowledge engineering, there is a lack of methodology for the systematic construction of FCM. Although some techniques were used in the individual construction processes, these techniques were either not systematically documented or too specific to the problem at hand. FCM and Bayesian Belief Network (BBN) are two major frameworks for modeling, representing and reasoning about causal design knowledge. Despite their extensive use in causal design knowledge engineering, there is no reported work which compares their respective roles. This paper deals with three topics, which are systematic constructing FCM, a methodology for FCM-BBN conversion, and comparison FCM and BBN. BBN has a sound mathematical foundation and reasoning capabilities, also it has an efficient evidence propagation mechanism and a proven track record in industryscale applications. However, BBN is less friendly and flexible, and often very time-consuming to generate appropriate conditional probabilities. Thus, Fuzzy Cognitive Map (FCM) is used for the indirect knowledge acquisition, and the causal knowledge in FCM is systematically converted to BBN. Finally, we compare BBNs directly generated by domain experts and generated from FCM, with a realistic industrial example, a fuel nozzle for an aerospace engine.

Research on Ontology-Based Knowledge Acquisition and Reuse for Fixture Design

2008 ◽  
Vol 392-394 ◽  
pp. 177-183
Author(s):  
L. Wang ◽  
Guo Fu Yin ◽  
L. Xu
Keyword(s):  
Knowledge Acquisition ◽  
Lead Time ◽  
Design System ◽  
Design Knowledge ◽  
Fixture Design ◽  
Knowledge Processing ◽  
Related Case ◽  
Computer Aided ◽  
Design Systems

Management of fixture design knowledge is vital for improving product quality and reducing product lead time, but there is no efficient and effective mechanism in current computer-aided fixture design systems to integrate fixture design process, to share design resource as well as acquisition and reuse knowledge. Ontology is increasingly seen as a key technology for enabling semantics-driven knowledge processing. On the background of a architecture of fixture design system based on knowledge introduced in the paper, we presented and expatiated a fixture design knowledge acquisition and reuse technology based on ontology, which embeds ontology in current computer-aided fixture design based on knowledge. Finally, the related case study was given.

A Genetic Engineering Approach to Genetic Algorithms

2001 ◽  
Vol 9 (1) ◽  
pp. 71-92 ◽  
Author(s):  
John S. Gero ◽  
Vladimir Kazakov
Keyword(s):  
Genetic Algorithm ◽  
Genetic Algorithms ◽  
Genetic Engineering ◽  
Genetic Material ◽  
Evolutionary Process ◽  
Automatic Generation ◽  
Engineering Approach ◽  
Standard Genetic Algorithm

We present an extension to the standard genetic algorithm (GA), which is based on concepts of genetic engineering. The motivation is to discover useful and harmful genetic materials and then execute an evolutionary process in such a way that the population becomes increasingly composed of useful genetic material and increasingly free of the harmful genetic material. Compared to the standard GA, it provides some computational advantages as well as a tool for automatic generation of hierarchical genetic representations specifically tailored to suit certain classes of problems.

Sign in / Sign up

Export Citation Format

Share Document