Inyong Ham

Computer-Aided Process Planning: The Present and the Future

Abstract This paper examines the current status of, and suggests some future directions for, research efforts in an area important for computer-integrated manufacturing: computer-aided process planning (CAPP). Rather than discuss a specific aspect of the subject or present details of a particular prototype system, the major emphasis is on the global perspectives of fundamental issues involved in developing computer-based planning systems for various manufacturing tasks. In reviewing the current research, references are made to technical papers presented at the 19th CIRP ( International Institution for Production Engineering Research ) International Seminar on Manufacturing Systems held at the Pennsylvania State University, June 1-2, 1987, with the major theme of Computer Aided Process Planning. In suggesting future directions, an integrated planning framework as a logical extension of current CAPP activities is proposed. The need for, and challenges of, such an integrated planning approach to manufacturing problems are summarized, and, specifically the potential role of artificial intelligence (AI) based techniques within this framework are explained. The objective of this paper is to promote a better understanding of the nature and potential of manufacturing-related planning tasks by critiquing the present efforts with respect to the ultimate goals of unmanned production in the future.

Neural networks and their applications in component design data retrieval

Neural networks have gained increased importance in the past few years. One of the basic characteristics of neural networks is the property of associative memory. In this paper we study the possibility of using the ideas of neural networks and associative memory in the manufacturing domain, with specific reference to design data retrieval in group technology. A two-layer feed-forward perceptron with backpropagation is simulated on a Vax-8550 to train example parts. The complete scheme along with the simulation results are explained and future directions indicated.

A top-down approach to integrating the building process

Many computer-aided tools have been developed to assist designers, engineers, and managers with specific well-defined functions, yet they are not well integrated. This paper develops the need for an information architecture to integrate the processes and subsequent software used throughout the life of a building. It then defines a process model of the functions required to provide a facility to the end user, namely, managing, planning, designing, constructing, and operating the facility.This process model implies that the proposed information architecture must support the life-cycle process, effectively capture knowledge, and act as an integrator of industry accepted decision-making tools. Finally, a knowledge-based approach to implementing the information architecture is propsed.

Use of Associative Memory and Self-Organization in Conceptual Design

Experienced human designers store known design solutions. Whenever a new design problem is encountered, the designer uses the known elemental functional requirements and associates them with the known design solutions and retrieves the most closely matching solution. This design solution can be either directly used or mutated to generate a new design solution. In this paper the authors propose a model based on human associative memory as a means for capturing the conceptual design process. The associative memory is modeled as an Artificial Neural Network. The development and implementations of the model are discussed with the help of relevant examples. The two layer perceptron is trained using the back propagation algorithm.

An Integrated Approach to Group Technology Part Family Data Base Design Based on Artificial Intelligence Techniques

Abstract Implementation of Group Technology in Computer Integrated Manufacturing (CIM) demands more advanced methods to satisfy todays requirements imposed by the development of CIM. In this research, an integrated approach for G.T. applications using Artificial Intelligence methods is developed. Pattern recognition methods are applied to generate a customized G.T. coding scheme, to form initial part families, and to classify new parts into part families. The system has been tested using real industrial data with good results.

Feedback of Manufacturing Experience for DFM Design Rules

Abstract In many manufacturing areas, design rules are used to assist in design for manufacturing. These rules are often specific and formal, yet they are usually developed in an ad-hoc manner by design committees and/or design software vendors. This work describes a database architecture and a statistical modeling methodology that enable the formal capture of manufacturing experience as new or revised design rules. The method uses pass/fail or other quality data from the firms own manufacturing experience to update design limits or to introduce new design rules.

Simulation of Manufacturing Systems Using SIMAN

Summary This paper discusses the concepts and methods for simulating manufacturing systems using the new SIMAN simulation language. SIMAN is a powerful general purpose language which incorporates a number of special purpose features which are specifically designed to enhance the modeling of manufacturing systems. These features greatly simplify the task of modeling the material handling component of a manufacturing system. The modeling concepts included in SIMAN are illustrated by several small example models. In addition, a recent application of SIMAN to model a manufacturing system at an industrial plant is discussed. This application involved a comparison of proposed group technology layouts against the existing conventional layout in the plant.

Causal Reasoning and Data Abstraction in Component Design

Abstract This paper deals with a brief review of the various schools of thought on design. One of the major developments in the field of Artificial Intelligence is the idea of causal reasoning. The causality of a system from the basic physical laws needs to be established in order to study the behaviors of the system. The same reasoning extended to component design can be used to delineate the structure-function and behavior of the component and hence the device. Given a function the designer can refer to the basic physical laws to generate the possible configurations (structures). By going through the process of causal reasoning the designer can establish the possible behaviors of the structure. Hence the emerging idea is one of clearly distinguishing the various entities of behavior and structure through a process of data abstraction via hierarchical inheritance. The authors present two example components one for a conveyor control and the other a fastener. The preliminary research ideas are used for illustrating these two component designs.

Database considerations in manufacturing systems integration

Abstract This paper deals with ideas that could form a basis for manufacturing integration. In recent times more attention is being paid to the idea of applying artificial intelligence (AI) techniques to manufacturing. However, very little attention is being paid to the proper use of these techniques. This research work explores three basic ideas: 1. 1. Applications of the entity-relationship approach to knowledge representation. 2. 2. The basic philosophy of expert database systems and 3. 3. Integration of manufacturing systems from the above two concepts. The approaches for 1 and 2 are explained with actual implementation experiences, while a framework for integration is proposed from a more philosophical perspective.

Intelligent computer integrated manufacturing (I-CIM): research perspectives

Abstract Manufacturing automation has progressed through various stages from simple data transfer to the intelligence-intensive systems. The future of CIM relies heavily on intelligence-intensive systems because manufacturing is no longer confined to one local site and manufacturing systems have become complex because of their global nature. In this article, the authors study the future manufacturing environment as a collaborative effort. The essential characteristics-the requirements for integration from a process and communication perspective-are identified as are steps in the process requiring further study. Finally, Intelligent-Computer Integrated Manufacturing (I-CIM) scenarios are presented for specific problems.