Expert system approach in design of mechanical components

Academic Press Professional, Inc. eBooks, 1992

Very few expert system applications have been distributed widely beyond the boundaries of the organizations within which they were developed. Instead, ex pert systems typically address problems for which local expertise dominates the methods for solutions to problems, and thus these expert systems represent idiosyncratic solutions that are applicable only within the organization that developed them. The obvious, though not easily attainable, solution to this problem is to provide to the end user of such an expert system the ability to cus tomize its knowledge base. In this paper, we present the Expert Cost and Manufacturability Guide (ECMG) from this perspective. ECM G is an expert system designed to provide mechanical engineers with first-order manufacturing cost estimates and manufacturability feedback very early in the design process, during preliminary design. We describe the architecture of ECMG, particularly those aspects of its design that accommodate the need for customizability. This is followed by a description of the expert systems design methodology we employed to permit us to construct a customizable expert system application.

2015

Decisions made at the conceptual design stage have significant influence on factors such as costs, performance, reliability, safety and environmental impact of a product. However, knowledge of all the design requirements and constraints during this early phase of a product’s life cycle is usually imprecise, approximate or unknown. Faced with such complexity, individual designers have restricted themselves to narrow, well-defined sub-tasks and as a result, progress in this area has been patchy and spasmodic. The purpose of this review is to document the current state of research and development in this crucial design activity and in doing so, to identify avenues of fruitful exploration. In this paper, we provide a comparison of the advantages/disadvantages and limitations between the various techniques/tools and, where applicable, suggest possible future research directions.

Academic Press Professional, Inc. eBooks, 1992

Very few expert system applications have been distributed widely beyond the boundaries of the organizations within which they were developed. Instead, ex pert systems typically address problems for which local expertise dominates the methods for solutions to problems, and thus these expert systems represent idiosyncratic solutions that are applicable only within the organization that developed them. The obvious, though not easily attainable, solution to this problem is to provide to the end user of such an expert system the ability to cus tomize its knowledge base. In this paper, we present the Expert Cost and Manufacturability Guide (ECMG) from this perspective. ECM G is an expert system designed to provide mechanical engineers with first-order manufacturing cost estimates and manufacturability feedback very early in the design process, during preliminary design. We describe the architecture of ECMG, particularly those aspects of its design that accommodate the need for customizability. This is followed by a description of the expert systems design methodology we employed to permit us to construct a customizable expert system application.

During the design phase of large-scale industrial engineering projects, numerous problems usually arise, which are related to the project analysis and methods used in each phase. Such projects are undertaken by multi-disciplinary teams of expert designers and planning managers that often communicate these problems to the members of their team via emails and telephone calls. However, the alignment of efforts towards solving these problems cannot be achieved effectively though these inherently limited communication and collaboration means. In parallel, the operation of manufacturing systems is evolving towards structures that are similar to social networks. The trend is to automatically connect to web-based collaboration platforms in order to search for the appropriate experts to deal with the problem in question. Towards this end, the proposed research work focuses on the development of a knowledge-based method, which is developed into a mobile app, and focuses on providing a collaboration space for reporting, tracking, and solving project-related problems. The methodology adopts concepts from the Root Cause Analysis method, which is further enriched with knowledge reuse features. Already reported and potentially solved problems, as well as other historical data are retrieved from a knowledge repository through advanced indexing techniques in order to support the identification of solutions for newly experienced problems. Results from the interpretation of the natural language that is considered to be used in the problem reporting phase and the accuracy of retrieved solutions are further discussed. Finally, the methodology is validated through a real-life case study obtained from the die construction department of an automotive industry.

Knowledge-Based Systems, 1999

This paper discusses the current limitations of Computer Aided Design (CAD) tools and reports on the use of knowledge Based Engineering (KBE) in the creation of a concept development tool, to organise information flow and as an architecture for the effective implementation of rapid design solutions. The KBE tool along with supporting analytical solutions has been applied to the Body-In-White area of automotive design. The present methods of using CAD and Finite Element Analysis (FEA) systems do not use a unified product/ process model representation and lead to the creation of separate non-relation data models that only capture the result of the engineering process. The KBE method unifies the engineering intent into a single model that allows for existing or novel design solutions to be assessed. These design solutions can then represent themselves in the correct form to the analysis systems. Automeshing is achieved using a rule-base that meshes the model with respect to the analysis solution required, materials and processes. ᭧

Computers in Industry, 1998

This paper presents the framework and development of an expert system to generating alternative products based on the w information of customers' needs and existing products derived from the product realization model S. Myint, M.T. Tabucanon, A multi-attribute approach to product realization, Proc. of Pacific Conference on Manufacturing, 1994, pp. x 553-560. Depending on the specific design, the primitive parts and attributes are derived and stored in a database. The generation of alternative products is based on the combination of primitive parts stored in the database, rules developed from the expert system and the weights of the customers' needs. When deriving alternatives, there can be many possible alternatives and thus, the final selection to narrow down all possible alternatives is done by functional grammar approach. The gearbox design is represented as illustrated example.

Materials & Design, 2013

Selection of proper materials for a diverse mechanism is one of the hardest tasks in the design and product improvements in various industrial applications. Materials play a vital and important function during the entire design and manufacturing process. The wrong selection of materials often leads to huge prices and ultimately results in product breakdown. Hence, the designers need to identify and select suitable materials with specific functionalities in order to attain the preferred output with the minimum cost concern and specific applicability. This paper tries to solve the materials selection problem by means of an expert system approach to manufacturing. According to this method either four or five different properties are inspected for each automotive part such as impact resistance, lightness, formability, corrosion resistance and low prices for bumpers; strength, formability, vibration absorption and low cost for flywheels; and strength, formability, corrosion resistance, biocompatibility and a small price for implants. Then, these were made more efficient using the expert system approach. Due to performing most of the above mentioned properties, polymeric materials {such as PP (polypropylene), HDPE (high density polyethylene) and PMMA (polymethyl methacrylate)} are selected for the bumpers; GFRP (glass fiber reinforced plastics) and CFRP (carbon fiber reinforced plastics) composites for high speed running, and cast iron and steel for low speeds for the flywheels; and finally stainless steel and polymeric materials {such as PVC (polyvinyl chloride) and PE (polyethylene)} were found to be the best materials for automotive parts. The selected materials were almost identical to those obtained by previous authors.

Journal of Materials Processing Technology, 2000

Design is a complicated area consisting of a combination of rules, technical information and personal judgement. The quality of design depends highly on the designer's knowledge and experience. This system attempts to simulate the design process and to capture design expertise by combining artificial neural networks (ANNs) and knowledge based system (KBS) together with multi-media (MM). It has been applied to the design of gears. Within the system the knowledge based system handles clearly defined design knowledge, the artificial neural networks capture knowledge which is difficult to quantify and multi-media provides a user-friendly interface prompting the user to input information and to retrieve results during design process. The finished system illustrates how features of different Artificial Intelligence techniques, KBS, ANNs and MM, are combined in a hybrid manner to conduct complicated design tasks.

Advances in Engineering Software, 2001

This paper describes a knowledge based engineering system (KBES) to extend the current capabilities of automotive body-in-white (BIW) engineers. It allows them to respond dynamically to changes within a rapid timeframe and to assess the effects of change with respect to the constraints imposed upon them by other product cycle factors. The system operates by creating a uni®ed model description that queries rules as to the suitability of the concept design and is built using a standard KBES to reduce project costs and system implementation. Knowledge from expert engineers and technical literature are captured and represented within the KBE application framework. q

Expert systems have experienced tremendous growth and popularity since their commercial introduction in the early 1980's. Today, expert systems are used in business, science, engineering, manufacturing, medical diagnosing, chemical, and many other fields. Mechanical engineers are the major users, expert systems, are finding rapid application in industry for such tasks as analysis of quality control data, assisting manufacturing personnel to safely operate machinery and accurately tune instruments. The design of gearbox requires good design decisions and design calculations, which are often interrelated with the various parameters. By using an expert system, which has various advantages, gearbox design will take less time and be easier. It will provide an important advantage in today's competition conditions since it decreases human power and workday waste as well as cost. Hence an expert system has been developed for gearbox design in this study.

Cybernetics and Systems, 2007

The advancements in internet technology have had a tremendous impact on the development of knowledge-based engineering systems that support concurrent engineering. Not only the conventional knowledge acquisition and representation techniques need to be improved to adapt the new situation, but the information retrieval and distribution have arisen to be new questions to answer. This article addresses these issues of management and handling of knowledge in a knowledge-based intelligent design system. A search algorithm based on the computation of a similarity index is proposed to retrieve a design case from the project library. An initial design report is used to distribute design information so that the information such as a designer's intent which cannot be included in a standard CAD file, can be retained. In addition, a simple constraint definition frame is presented to define the relationships between critical design parameters, and two information representation schemas, information matrix and constraint tree, are described. The presented research efforts in this article aim to provide promising tools to harness the full potential of ontologies in knowledge management within an intelligent design system.

Design Automation Conference, 1986

2000

Design and manufacturing are two very fundamental engineering processes in mechanical related fields. Traditionally design has been a manual process separated from manufacturing but concept of Concurrent Engineering with Design For Manufacture (DFM) and Design For Assembly (DFA) not only coupled both these but also increased complexity of design and thus brought about the application of computers. Expert systems have enabled designers to incorporate huge knowledge bases in a rule base system for domain specific problems thereby helping to automate the process of design.

Artificial Intelligence for Engineering, Design, Analysis and Manufacturing, 1988

Linkage-type mechanisms have numerous applications in industry especially for automation Unfortunately, they are less popular due to lack of proper design tools. This paper describes our efforts to remove the technological barrier in mechanisms design automation. Although the ideas presented apply to automation of mechanisms design in general, the paper discusses the development of an expert system for a particular sub-set of mechanisms called Dwell mechanisms.Many essential and desirable motion characteristics of mechanisms are so implicit that they are difficult to control by analytical methods. By systematically and extensively studying the entire motion characteristics of hundreds of linkages, a comprehensive classification system and heuristics were developed. This qualitative classification scheme led to a finite set of linkage models that cover the entire design space in the sense that any possible design falls under one or more of the models. Our system, called Dwell-Expert,...

Computer-Aided Design, 1986

Rule-based expert system shells are demonstrated to be useful m elementary design dec/s/on making. Two applications are presented which ut/llse the BUILD shell. The first is concerned with the selection and design of earth-retaining structures and makes use of passive graphics in descriptions. The second is concerned with the analysis and synthesis of kitchens and uses graphics to allow the user to interact with the system. Such systems are useful when the range of options is small. computer-aided design, rule-based expert system shells, BUlL D