Thesis (M.S.)--Ohio University, November, 2007. / Title from PDF t.p. Includes bibliographical references.

Thesis (Ph. D.)--Illinois State University, 2002. / Title from title page screen, viewed January 24, 2006. Dissertation Committee: Graham A. Jones (chair), Cynthia Langrall, Kenneth Berk, Edward S. Mooney. Includes bibliographical references (leaves 180-186) and abstract. Also available in print.

Dissertation (Ph.D.)--Worcester Polytechnic Institute. / Keywords: axiomatic design, case-based reasoning, fixture design, retrieval-by-adaptabilty. Includes bibliographical references (p.273-281).

Thesis (M.S.)--Ohio University, March, 2007. / Title from PDF t.p. Includes bibliographical references.

Over the past three decades, modelling packages for chemical processes have become more advanced and widely used. For example, equation-oriented dynamic simulators, such as gPROMS are useful for simulating plantwide processes as well as unit operations, and are widely used by process engineers. Whereas, other types of simulator (e.g. Simulink) are often used by control engineers to solve complex control problems. However, both these types of simulator rely on the user being proficient in modelling and familiar with their syntax beforehand. A useful development would be the integration of some knowledge into the formation of the process models and automatic syntax code generation. This would lead to the design engineers having a library of knowledge to check on first, much as an expert engineer uses their past experiences to help guide them through a design. If this could be incorporated into a modelling interface this would greatly help the design engineer, especially when tackling problems in areas that they have little, or no experience. The thesis addresses this problem and describes the design of an intelligent modelling interface that incorporates a knowledge base using some form of a priori case library and recall facility. The interface also incorporates an automatic input file generation stage. At present, the user can: specify a single unit operation problem to search for, retrieve similar cases from the database, specify their solution in the database based on past cases and experience, and then automatically generate an input file for either gPROMS or Simulink. These features are demonstrated through four case studies.

This thesis describes the development of a prototype Case-Based Reasoning (CBR) enabled intelligent component system, called Architectural General Object System (ARGOS), to facilitate the storage of design information in lightweight cases that can be used on the desktop computer over the total life of the facility. It uses CBR techniques combined with Microsoft ActiveX controls (object technology) to provide a useful autonomous component to implement some of the software requirements of such a system within the context of the global design and construction environment. These technologies ensure a platform independent environment and integration into the Internet. The use of XML (Extensible Mark-up Language) as a design language is explored to facilitate the storage of design data in a persistent and neutral manner independent from the software that originally created it. This ensures a long data life and the enables different actors over the life cycle of a facility to use their own relevant software to process the design information. During the development of AEDES (Architectural Evaluation and Design System), the research team realised that the problem of structuring design knowledge in such a way to support relevant software systems across the life cycle of a facility is far more complex than originally anticipated. Although there are many similarities between the construction and the manufacturing industries, there are also significant and problematic differences. Architectural design tasks take place in an open world where the reasoner's knowledge is incomplete or inconsistent. Due to this the focus in computer-aided architectural design research has shifted back and forth from attempts to totally automate the entire design process to its partial support through drafting tools. In an attempt to overcome some of the enormous complexities, that researchers struggled with over the past 35 years, a prototype intelligent autonomous design component ARGOS is developed in this research. It is clear that automated design methods are not tractable and it is therefore more worthwhile to pursue the creation of a neutral design language and the creation of intelligent and flexible design tools to manipulate these design fragments. An in-depth study is made of various important out-of-industry manufacturing techniques, CBR and object technology and to establish clearly what the desirable characteristics of ARGOS should be. An important requirement is that ARGOS should be generic and non-prescriptive and should work in a Microsoft Windows compliant environment. A solution without the use of CAD is proposed that ensure a generic solution that could add value to many different construction industry actors in many different environments. More recently attempts are being made to introduce post-modern Artificial Intelligence (AI) into design and architecture. Despite all these efforts it is clear that architectural briefing and design has not reached the status of a science and it is unlikely ever to. This is confirmed by recent breakthroughs in the field of Artificial Intelligence (AI) and Knowledge Management that provide deeper insights into the cognitive processes of the designer. This study indicates that XML is a viable means of expressing design knowledge and a feasible alternative for the complex Building Product Models currently proposed whilst at the same time supporting operations in the Internet environment. Design information and the ability to retrieve it is now more important than the software application that originally created it. The autonomous intelligent component ARGOS provides a method to encapsulate design knowledge at both tacit and explicit cognitive levels whilst at the same time providing global communication in a convenient desktop environment. ARGOS is designed in a parametric way that supports any design process that requires positional, volumetric and spatial relationship analysis in both 2D and 3D. Multiple autonomous copies can be placed in a container environment such as Excel. Any process written in any computer language that supports the use of ActiveX controls can be used to manipulate the ARGOS instances. / Dissertation (Ph.D. (Applied Sciences))--University of Pretoria, 2000. / Architecture / unrestricted

Over 70% of final product costs are determined by initial product design. Hence, to depict a capable and reliable part design is important during the part conceptual design phase. Case-Based Reasoning (CBR), based on analogical reasoning, is a problem solving methodology. This paper proposes the CBR architecture applied to assembly part design for effectively managing previous design experience and evaluating assemblability and manufacturability of assembly part design. The results can provide a useful reference for novices to reuse and revise previous experience and experienced designers to impart their expertise through CBR methodology.

Concrete design rules can facilitate the designer to depict capable design and reliable products. However, it is difficult to deduce systematic design rules from previous experience and to modify the rules in a rule-based system. In the last decade, Case-Based Reasoning (CBR) has become an important methodology to solve the problem. The objective of this paper is to determine the appropriate case representation used in assembly part design for developing a CBR system. The designer can obtain real-time Early experimental results indicate that the case representation can appropriately represent the expertise and experience of assembly part design based on CBR methodology.

Artificial intelligence (AI) approaches have been successfully applied to many fields. Among the numerous AI approaches, Case-Based Reasoning (CBR) is an approach that mainly focuses on the reuse of knowledge and experience. However, little work is done on applications of CBR to improve assembly part design. Similarity measures and the weight of different features are crucial in determining the accuracy of retrieving cases from the case base. To develop the weight of part features and retrieve a similar part design, the research proposes using Genetic Algorithms (GAs) to learn the optimum feature weight and employing nearest-neighbor technique to measure the similarity of assembly part design. Early experimental results indicate that the similar part design is effectively retrieved by these similarity measures.

Classification is a general framework that can be applied tovarious tasks such as object recognition, prediction, diagnosis or learning. There exist at least two different approaches for classification, namely rule-based and similarity-based classification. The two approaches have different strengths and weaknesses. The former requires a domain theory in order to make inferences from the test instance to its class. The latter does not have this requirement and approximates the class of a test instance via its similarity to a set of known instances.In this thesis the above two approaches are integrated in the realm of Case-Based Reasoning (CBR). CBR treats new cases according to their similarity to stored cases. Similarity is calculated by a similarity measure, which is the crucial factor for classification accuracy. In this work, rule-based domain knowledge is incorporated into the similarity measures of CBR in order to increase classification accuracy. Several novel integration methods are introduced, implemented and evaluated. Since knowledge about real world domains is typically imperfect, the approach does not assume that the domain theories are accurate or complete. Rather, a systematic analysis of different knowledge types is presented that shows the effect of imperfect knowledge on classification accuracy. The analysis is conducted partly empirically in artificial and in real world domains, and partly formally.