Alex H. B. Duffy

Integration of decision support systems to improve decision support performance

Decision support system (DSS) is a well-established research and development area. Traditional isolated, stand-alone DSS has been recently facing new challenges. In order to improve the performance of DSS to meet the challenges, research has been actively carried out to develop integrated decision support systems (IDSS). This paper reviews the current research efforts with regard to the development of IDSS. The focus of the paper is on the integration aspect for IDSS through multiple perspectives, and the technologies that support this integration. More than 100 papers and software systems are discussed. Current research efforts and the development status of IDSS are explained, compared and classified. In addition, future trends and challenges in integration are outlined. The paper concludes that by addressing integration, better support will be provided to decision makers, with the expectation of both better decisions and improved decision making processes.

Design co-ordination for concurrent engineering

This paper is the outcome of discussions directed at research issues in supporting design coordination. Design coordination is described as a high-level concept of the planning, scheduling, representation, decision-making and control of product development with respect to time, tasks, resources and design aspects. The need and hypothesis for supporting design coordination is given, and major bottlenecks, related research problems and associated questions are presented. The paper concludes that, while the primary objective of concurrent engineering would seem to be directed at considering aspects of design simultaneously, design coordination provides the means of integrating and controlling disparate activities, i.e. design coordination is a vehicle for the realization of concurrent engineering.

Modelling design development performance

Begins with a brief review of research in the area of performance, with particular emphasis on design and product development, highlighting the main weaknesses in work to date. Then presents a fundamental and generic model of performance, related to knowledge‐based activities in design, which describes performance in terms of its key elements, efficiency and effectiveness, and provides a basis for modelling performance across different process levels. Evolves this model further to describe performance measurement and management in design development. Concludes that it is not possible to distinguish the efficiency of the design activity from that of design management, and that, in addition, efficiency appears to be inherent to an activity, but is difficult to measure.

Identifying component modules

A computer-based system for modelling component dependencies and identifying component modules is presented. A variation of the Dependency Structure Matrix (DSM) representation was used to model component dependencies. The system utilises a two-stage approach towards facilitating the identification of a hierarchical modular structure. The first stage calculates a value for a clustering criterion that may be used to group component dependencies together. A Genetic Algorithm is described to optimise the order of the components within the DSM with the focus of minimising the value of the clustering criterion to identify the most significant component groupings (modules) within the product structure. The second stage utilises a ‘Module Strength Indicator’ (MSI) function to determine a value representative of the degree of modularity of the component groupings. The application of this function to the DSM produces a ‘Module Structure Matrix’ (MSM) depicting the relative modularity of available component groupings within it. The approach enabled the identification of hierarchical modularity in the product structure without the requirement for any additional domain specific knowledge within the system. The system supports design by providing mechanisms to explicitly represent and utilise component and dependency knowledge to facilitate the nontrivial task of determining near-optimal component modules and representing product modularity.

The "what" and "how" of learning in design

Machine learning in design offers tremendous potential to actively support designers in all of their problem solving and knowledge requirement activities. This article surveys what designers and their systems have accomplished so far using machine learning techniques.

The Design Co-ordination Framework: key elements for effective product development

This paper proposes a Design Co-ordination Framework (DCF) i.e. a concept for an ideal DC system with the abilities to support co-ordination of various complex aspects of product development. A set of frames, modelling key elements of co-ordination, which reflect the states of design, plans, organisation, allocations, tasks etc. during the design process, has been identified. Each frame is explained and the co-ordination, i.e. the management of the links between these frames, is presented, based upon characteristic DC situations in industry. It is concluded that while the DCF provides a basis for our research efforts into enhancing the product development process there is still considerable work and development required before it can adequately reflect and support Design Co-ordination.

Engineering management: operational design coordination

Effective engineering management is acknowledged as being fundamental to the successful operation of organizations. While traditional and contemporary approaches to operational engineering management are of great significance, there remains a need to make further advances in this field. Such advances will enable an increase in the competitiveness of an organization by contributing toward delivering quality products in shorter timescales at an acceptable cost. As such, there is a requirement for a more comprehensive and innovative approach that offers a means of improving the operational management of engineering. Existing approaches recognize coordination as an important and pervasive characteristic of operational engineering management; however, they fail to offer a consistent understanding and appreciation of the concept. This paper comprehensively identifies the key elements of operational design coordination, which will provide the basis for an improved approach to engineering management.

A foundation for machine learning in design

This paper presents a formalism for considering the issues of learning in design. A foundation for machine learning in design (MLinD) is defined so as to provide answers to basic questions on learning in design, such as, “What types of knowledge can be learnt?”, “How does learning occur?”, and “When does learning occur?”. Five main elements of MLinD are presented as the input knowledge, knowledge transformers, output knowledge, goals/reasons for learning, and learning triggers. Using this foundation, published systems in MLinD were reviewed. The systematic review presents a basis for validating the presented foundation. The paper concludes that there is considerable work to be carried out in order to fully formalize the foundation of MLinD.

NODES: a numerical and object based modelling system for conceptual engineering design

In the early stages of engineering design a considerable amount of experience and knowledge of past designs is used to build and evaluate new empirical models with known design relationships. However, conventional computer-based systems which aim to assist this stage have tended to concentrate on the analytical aspects of the process and have not been successful in accessing this expertise and benefiting from it during synthesis. The paper presents some of the results of a programme of research into methods of representing the knowledge to support modelling during these early stages of the design process. Key features of the modelling at this stage are the use of abstract representations, reuse of past design information, partitioning of designs, and synthesis of concept structures. The work is based on an experimental system, NODES, which was developed to model knowledge of design objects and their associated numerical relations. The utility of the system in creating, evolving and evaluating design solutions is illustrated through a worked example in a typical engineering design application.

Sharing the learning activity using intelligent CAD

In this paper the need for Intelligent Computer Aided Design (Int.CAD) to jointly support design and learning assistance is introduced. The paper focuses on presenting and exploring the possibility of realizing learning assistance in Int.CAD by introducing a new concept called Shared Learning. Shared Learning is proposed to empower CAD tools with more useful learning capabilities than that currently available and thereby provide a stronger interaction of learning between a designer and a computer. Controlled computational learning is proposed as a means whereby the Shared Learning concept can be realized. The viability of this new concept is explored by using a system called PERSPECT. PERSPECT is a preliminary numerical design tool aimed at supporting the effective utilization of numerical experiential knowledge in design. After a detailed discussion of PERSPECTs numerical design support, the paper presents the results of an evaluation that focuses on PERSPECTs implementation of controlled computational learning and ability to support a designers need to learn. The paper then discusses PERSPECTs potential as a tool for supporting the Shared Learning concept by explaining how a designer and PERSPECT can jointly learn. There is still much work to be done before the full potential of Shared Learning can be realized. However, the authors do believe that the concept of Shared Learning may hold the key to truly empowering learning in Int.CAD.