Design Of Knowledge-based System Research Articles

Application of ID3 algorithm in knowledge acquisition for tolerance design

Knowledge-processing technology can be used to aid engineering design. This paper presents the application of an ID3 algorithm in knowledge acquisition for the tolerance design of injection-molded parts. The overall structure of a knowledge-based system for tolerance design is briefly illustrated. After a classification of factors that influence tolerance has been made, some key attributes for collecting knowledge cases are studied through fuzzy representation and processing. The detailed procedure of utilizing an ID3 algorithm for tolerance-related knowledge acquisition is introduced, including calculating the information gain measure (entropy) and generating the final decision tree. The method can be easily applied to other engineering areas and the result has great value in practice. The advantages and disadvantages of this method are discussed in Section 5.

Impact of the NSF State/Industry/University Cooperative Research Center on low-cost, high-speed polymer composites processing on the research and educational programs at Michigan State University

The objectives of the National Science Foundation (NSF) State of Michigan/Industry/University Cooperative Research Center on low-cost, high-speed polymer composites processing at Michigan State University (MSU) are design, development and deployment of technology and knowledge-based systems that will reduce costs of polymer composites processing by (a) insuring faster processes, (b) reducing component costs, and (c) reducing implementation times of new composite designs. Significant accomplishments have been made in research, education and technology transfer in the areas of novel processing, liquid molding, thermoplastic processing, intelligent design and process modeling, and interphases and joining. The Center's primary educational activities were supported by the National Institute of Standards and Technology-Advanced Technology Program (NIST-ATP) with General Motors and General Electric, and the Technology Reinvestment Project (TRP) with the University of Delaware and the US Department of Defense. The Center's role in the four-year NIST-ATP was to disseminate injection-molded thermoplastics design methodologies to automotive, appliance, computer and other key US industries. The program enabled the Center to develop course material, a CD-ROM design manual, and workshop materials on state of the art thermoplastics design knowledge. To date, hundreds of individuals have participated in the workshops, and the material developed in this program is being integrated into undergraduate, graduate and continuing education offerings. The TRP program brought together the NSF Center at MSU and the composite materials center at the University of Delaware (UD) in a collaborative composite materials education and training effort for the Department of Defense and the durable goods industry. Educational developments included incorporation of knowledge derived from the TRP program into 49 new or existing engineering courses (23 at MSU and 26 at UD); six experiments for a new teaching laboratory; four workshops; four videotaped instructional modules (two each for liquid molding RTM technology and the injection molding technology); interactive WEB-based simulations and tutorials; and development of knowledge-based software.

Knowledge-based approach and system for assembly-oriented design, Part II: the system implementation

Assembly is one of the most important stages for product development. Assembly-oriented design (AOD) is a new approach to designing assemblies, which uses a number of design and analysis tools to help the designer plan out and analyze candidate assembly schemes prior to having detailed knowledge of the geometry of the parts. Using this approach, many assembly schemes can be inexpensively evaluated for their ability to deliver the important characteristics of the final product. This research proposes a knowledge-based approach and develops an expert design system to support top-down design for assembled products. The presentation of research report is divided into two parts: the knowledge-based approach (Part I) and the knowledge-based expert design system (Part II). This paper is the second part of the report (Part II). It will focus on the development of knowledge-based expert design system for assembly oriented design. The knowledge-based assembly oriented design system, i.e., the assembly oriented design expert system (AODES) is constructed to integrate assembly modeling and design, assembly planning, assemblability analysis and evaluation within a concurrent engineering environment. This intelligent system is implemented by integrating object-oriented representation, constraint-based modeling, rule-based reasoning, truth maintenance, and interfacing to database management system and CAD module, in which fuzzy logic based knowledge representation and inference technique are also applied to deal with uncertain data and knowledge in the design process. The developed system differs from the existing systems adopting part-first bottom-up modeling technique, in which a comprehensive intelligent framework is used for assembly modeling and design in a top-down manner from the conceptual level to the detailed level. It is able to help obtain better design ideas, provide users with suggestions so as to create and improve a design, and therefore give users the possibility to assess and reduce the total production cost at an early stage during the design process. Through the use of the system, the concurrent engineering knowledge can be effectively incorporated into the assembly design process in an integrated manner. A case assembly design shows that the intelligent modeling and design system is feasible.

Knowledge-based approach and system for assembly oriented design, Part I: the approach

Assembly is one of the most important stages for product development. Assembly-oriented design (AOD) is a new approach to designing assemblies, which uses a number of design and analysis tools to help the designer plan out and analyze candidate assembly schemes prior to having detailed knowledge of the geometry of the parts. Using this approach, many assembly schemes can be inexpensively evaluated for their ability to deliver the important characteristics of the final product. This research proposes a knowledge-based approach and develops an expert design system to support top-down design for assembled products. The presentation of research report is divided into two parts: the knowledge-based approach (Part I) and the knowledge-based expert design system (Part II). This paper is the first part of the report (Part I), which mainly proposes a knowledge-based approach and framework for intelligent assembly oriented design. The proposed approach focuses on the integration of product design, assemblability analysis and evaluation, and design for assembly with economical analysis. It differs from the existing approaches adopting the part-first bottom-up modeling technique, in which a hybrid model related to design problem-solving including function–behavior–structure model, feature-based geometric model, and parametric constraint model is used as a comprehensive intelligent framework for assembly modeling and design in a top-down manner from the conceptual level to the detailed level. Through the use of intelligent approach and framework, concurrent engineering knowledge can be effectively incorporated into the assembly design process, and a knowledge-based expert design system can be implemented.

From on-line sketching to 2D and 3D geometry: a system based on fuzzy knowledge

The paper describes the development of a fuzzy knowledge-based prototype system for conceptual design. This real time system is designed to infer user's sketching intentions, to segment sketched input and generate corresponding geometric primitives: straight lines, circles; arcs, ellipses, elliptical arcs, and B-spline curves. Topology information (connectivity, unitary constraints and pairwise constraints) is received dynamically from 2D sketched input and primitives. From the 2D topology information, a more accurate 2D geometry can be built up by applying a 2D geometric constraint solver. Subsequently, 3D geometry can be received feature by feature incrementally. Each feature can be recognised by inference knowledge in terms of matching its 2D primitive configurations and connection relationships. The system accepts not only sketched input, working as an automatic design tool, but also accepts user interactive input of both 2D primitives and special positional 3D primitives. This makes it easy and friendly to use. The system has been tested with a number of sketched inputs of 2D and 3D geometry.

Augmented Intensional Reasoning in Knowledge-Based Accounting Systems

A limitation of existing accounting systems is their lack of knowledge sharing and knowledge reuse, which makes the design and implementation of new accounting systems time-consuming and expensive. An important requirement for knowledge sharing and reuse is the existence of a common semantic infrastructure. In this article we use McCarthy's (1982) Resource-Event-Agent (REA) model as a common semantic infrastructure in an accounting context. The objective is to make knowledge-intensive use of REA to share accounting concepts across functional boundaries and to reuse these concepts in different applications and different systems, an approach we call augmented intensional reasoning. Intensional reasoning is the active use of conceptual structures in information systems operations such as design and information retrieval. For augmented intensional reasoning, the conceptual structures are extended with domain-specific REA knowledge. Sections II and III describe different dimensions of augmented intensional reasoning: the REA primitives, the technological features needed to support augmented intensional reasoning, the need for epistemologically adequate representations to make augmented intensional reasoning feasible, and the practical necessity of implementation compromises. Sections IV and V explore two uses of augmented intensional reasoning: design and operation of knowledge-based accounting systems. The example in Section V explains how augmented intensional reasoning works: (1) define the conceptual schema, (2) structure the conceptual schema in terms of REA (knowledge augmentation), (3) define a shareable and reusable accounting concept (claim), and (4) use the concept (claim) to derive information in different accounting cycles (revenue and acquisition).

Integrated Design System for Lattice Domes

In structural design, the preliminary synthesis stage derives judgmental knowledge from engineering heuristic and experience which are usually expressed in symbolic form. On the other hand, detailed design involves extensive numerical processing. An integrated computer-aided design system should be able to handle both symbolic and numerical processings. It must also be able to integrate engineering databases and CAD packages within a single environment. The knowledge-based system approach provides a venue for achieving all these requirements. This paper presents a prototype knowledge-based system for lattice design that can perform several essential tasks including preliminary synthesis, numerical model generation, nonlinear finite element analysis, code compliance checking and member sizing. The system user is guided throughout the design session by interactive graphical user interfaces which facilitate the design process.

Correctness in hierarchical knowledge-based requirements

As expert system technology gains broader acceptance, the need to build and maintain large-scale knowledge bases will assume greater importance. Traditional approaches to knowledge-based systems (KBSs) verification have generally adopted a pairwise comparison of rules, making them slow for large-scale KBSs. This paper introduces the least fixpoint semantics of a predicate/transition (pr/t) net model into the KBSs for the purposes of speeding up the computation and saving the design time of KBSs. An efficient fault diagnosis algorithm is presented to locate some fault(s) made in the KBS design. The significance of this work is that frame- and rule-based hardware description language (FARHDL) can easily form a KBS, and the pr/t net model provides a T-invariant technique to verify the correctness of KBS requirements. Thus, the performance of a computer-aided design (CAD) tool for digital systems can be improved to some extent.

Towards the design and development of a knowledge-based universal modular jigs and fixtures system

Jigs and fixtures are one of the important aspects of manufacturing. Parts may have different sets of fixturing requirements and call for different design strategies. Although there are numerous possibilities for fixture designs, a few basic configurations are clearly identifiable. Computer aided design (CAD) has done a little in assisting designers to design jigs and fixtures, making decisions of the best design selection, and providing designers with suggestions. The goal of this paper is to develop and document the design parameters and specifications utilized in jigs and fixtures design using universal modular jigs and fixtures design system (UMJFS). This is the first step to develop a knowledge-based Jigs and Fixture design and selection system. This application has the advantages of making the fixture design information completely modular and transparent, providing better match to the working conditions, reducing lead-time, and generally providing a significant enhancement of fixture productivity and economy. UMJFS has different standard and modular elements. This makes jigs and fixtures elements interchangeable and reusable. Designing a UMJFS then becomes a task of selecting and assembling the proper elements together.

Knowledge-based system development for assisting structural design

The development of software systems that really assist engineering design requires an important modelling effort. Computational treatment of these problems is carried out through the application of software engineering and knowledge engineering techniques. Both fields have significantly evolved during the last few years, and now advanced methodologies for the development of conventional software systems and knowledge-based systems, emphasizing different modelling principles, are available. In particular, both object-oriented modelling and knowledge modelling present useful individual characteristics that are complementary. The article analyses the need for integration of those useful modelling aspects, and presents an integrated scheme for the development of knowledge-based design systems (KBDS’s). By way of illustration, the modelling scheme proposed is applied to the development of a KBDS in a specific domain of structural design.

Fuzzy-logic-based ranking of steel grades generated by material design KBS

A material design system has been developed, utilising mathematical modeling and knowledge-based approaches. The Knowledge-Based System (KBS) generates about 15–30 different target compositions for steelmaking for each customer order. Fuzzy logic is applied in the system for the design of steel plates, to rank the alternative target compositions for steelmaking according to the degree to which they will satisfy the customer’s requirements of chemical and mechanical properties, with due consideration given to the economic aspects and the complexity involved in the production. Statistical data regarding the performance of the grades produced in the past are also utilised in this process. The development of individual, composite and Weighted Sum Membership Functions (WSMFs) has been identified as very important in realistically ranking the target compositions for steelmaking.

Knowledge-Based Expert System for Optimal Stacking Sequence Design of Composite Structures

This paper expounds the development of a knowledge-based expert system for the optimal strength design of composite structures subjected to various loading conditions and rules of design heuristics. The optimal stacking sequences are obtained by integration of a knowledge-based expert system, genetic algorithm and finite element analysis. Because this expert system in optimal stacking sequence design adopts a finite element method as a stress analysis tool, it isn't limited to laminate design but can be applied to a general composite structure. The optimal stacking sequence combination is drawn from discrete ply angles and rules of design heuristics stored in the knowledge-base for the given application of interest. Results of this study were verified through comparison with quasi-isotropic lay-ups.

A numeric-heuristic system for plant wide pipe routing

Higher requirements in quality management, in the reduction of design time and manpower as well as more extensive, life-cycle spanning documentation are resulting in an increasing demand on modern information technologies. Computer-aided, integrated, knowledge-based design systems are an approach to build a new generation of IT-support for plant design and optimisation. As a contribution to this field a design system for computer-aided piping layout is being developed. Piping design is subject to many rules and constraints whose violation or satisfaction have to be described and weighted. Therefore routines generating multiple feasible alternatives for pipe routes are programmed. In a rating and decision system (numeric-heuristic system) these alternatives will be evaluated and ranked.

A knowledge-based expert system for roll pass and profile design for shape rolling of round and square bars

Abstract In shape rolling, the determination of roll pass and profile design is of importance. In the present investigation, a knowledge-based expert system is developed for the design of roll pass and profile sequences for the shape rolling of round and square bars. For development of the program, C++ language and an object oriented programming technique were utilized in consideration of the flexibility and expandability of the program. A backward chaining algorithm was employed for the inference engine to determine the manufacturing sequences in reverse order based on design rules extracted from the literature. For optimization of the process sequence design, the number of roll passes was minimized by comparing the error between the inferred roll passes and the initial error provided as input. In the currently developed expert system, five geometries such as box, square, diamond, oval and round were introduced as a basic geometry to describe the intermediate roll geometries. In addition, the roll separating force, area reduction and change of length at each stage of shape rolling were determined and displayed on the monitor of a personal computer. The system was applied for the shape rolling of round and square bars. The process sequences determined were proven to be reasonable compared to those available at practice.

Rule-based systems formalized within a software architectural style

This article considers the utilization of architectural styles in the formal design of knowledge-based systems. The formal model of a style is an approach to systems modeling that allows software developers to understand and prove properties about the system design in terms of its components, connectors, configurations, and constraints. This allows commonality of design to be easily understood and captured, leading to a better understanding of the role that an architectural abstraction would have in another complex system, embedded context, or system integration. In this article, a formal rule-based architectural style is presented in detail using the Z notation. The benefits of depicting the rule-based system as an architectural style include reusability, understandability, and the allowance for formal software analysis and integration techniques. The ability to define the rule-based architectural style in this way, illustrates the power, clarity, and flexibility of this specification form over traditional formal specification approaches. In addition, it extends current verification approaches for knowledge-based systems beyond the knowledge base only.

A knowledge-based system for the conceptual design of grippers for handling fabrics

The paper presents a knowledge-based system (KBS) for the conceptual design of grippers for handling fabrics. Its main purpose is the integration of the domain knowledge in a single system for the systematic design of this type of grippers. The knowledge presented, in terms of gripper, material and handling process, are classified. The reasoning strategy is based upon a combination of a depth-first search method and a heuristic method. The heuristic search method finds a final solution from a given set of feasible solutions and can synthesize new solutions to accomplish the required specifications. Details of the main features of the system are given, including its ability to take critical design decisions according to four criteria, weighted by the designer. The knowledge-based system was implemented in the Kappa P. C. 2.3.2 environment. Two examples are given to illustrate some critical aspects concerning the KBS development, to explain the operation of the proposed searching heuristic method, and to show its effectiveness in producing design concepts for grippers.

Integrated knowledge-based approach and system for product design for assembly

Due to the complexity of assembly and product design, there is an increasing need to integrate artificial intelligence (AI), e.g., expert systems, more harmoniously with the designer intelligence for maximum benefits from expediting advanced design, automation and manufacturing. This paper discusses a knowledge-based approach and an expert system (DFAES) for integrated product design for assembly (DFA), which concurrently integrates product design, assembly modelling and process planning, assemblability analysis and evaluation. Key issues on the development of DFAES are addressed in greater detail, which include the system structure, knowledge representation, knowledge base design, problem solving paradigms, knowledge base management system and knowledge acquisition. DFAES integrates frame-based representation, constraint-based language, rule-based reasoning, truth-maintenance systems and object-oriented composite values, and has an interface to analysis and evaluation program, database and CAD systems. Fuzzy logic-based knowledge representation and inference technique are also applied to deal with uncertainties in both data and knowledge in DFAES. This intelligent system is able to provide users with suggestions to improve a design and also to offer design ideas. The concurrent engineering knowledge can be effectively incorporated into the preliminary design process through the use of the developed approach and system. The applications in assembly design show that the integrated approach and intelligent system are feasible.

Artificial intelligence and expert systems applications in new product development—a survey

The authors review and categorize the research in applications of artificial intelligence (AI) and expert systems (ES) in new product development (NPD) activities. A brief overview of NPD process and AI is presented. This is followed by a literature survey in regard to AI and ES applications in NPD, which revealed twenty four articles (twenty two applications) in the 1990–1997 period. The applications are categorized into five areas: expert decision support systems for NPD project evaluation, knowledge-based systems (KBS) for product and process design, KBS for QFD, AI support for conceptual design and AI support for group decision making in concurrent engineering. Brief review of each application is provided. The articles are also grouped by NPD stages and seven NPD core elements (competencies and abilities). Further research areas are pointed out.

ExpertFlex: A knowledge-based system for flexible manufacturing system design

ExpertFlex: A knowledge-based system for flexible manufacturing system design

Intelligent approach to a CAD system for the layout design of a ship engine room

The current layout design of a ship engine room not only depends on a skilled designer but also has many design constraints and regulations to be considered. At preliminary design stage CAD systems need to be intelligent in the sense that they must be able to use knowledge to achieve the designer’s goal. In this paper, we present an approach to implement a practical knowledge-based system for the machinery layout design of a ship engine room. The knowledge-base is implemented and verified in the actual CAD environment of a ship engine room, named MADES (Machinery ArrangementDesign Expert System), which we develop in this study. Design knowledge is represented byobject-oriented concept, and nonmonotonic reasoning enables the values of closely related objects to be consistent. The approaches presented in this paper provide a practical example of a knowledge-based system for complex design problems, and can also provide guidance on implementing an integrateddesign expert system that extends the capability of existing CAD systems.