Design and Implementation of a New Generation Multi-Agent Task Environment Framework

Abstract

The Multi-Disciplinary Design Optimisation (MDO) process of products can be supported by automation of analysis and optimisation steps. The Design and Engineering Engine (DEE) is a useful concept to structure this automation. Within the DEE, a product is parametrically defined using Knowledge Based Engineering (KBE) techniques. The analysis of a particular product instantiation of this product model is performed by discipline analysis tools and a search engine provides a strategy to drive the design toward a feasible design, satisfy functional and performance requirements and constraints. To power the automatic analysis in this MDO setting an Agent Based Framework (ABF) has been developed. From the first release agent implementation several positive and negative aspect were found and addressed. It appeared that the framework requirements from literature often have a holistic approach, striving for integration of the MDO problem on the desktop of the engineer, rather than make use of distributed design capabilities in teams of engineers. In this perspective four levels of scoping are identified; organisational scoping level, framework or integration level, tool or engineering service level and data scoping level. These four scoping levels are a good frame of reference to link the identified actors, the four main established functions of a framework and the recent contributions in engineering framework development. Moreover the four levels of scoping helped to show not only the existence of product and process knowledge but also pointed out that there is a need to glue these independent knowledge areas together by using problem knowledge. Whit this problem knowledge, in form of a problem definition language, it should be possible to dictate the behaviour of the MDO framework. Conclusively, the second release agent software is described and various industrial use cases and accompanying network architectures are described for which the framework software will be made compatible with. Finally a status update to the implementation is provided.

Engineering design optimization using services and workflows

“…Some recent publications in the MDO literature have reached similar conclusions to ourselves about the desirability of workflow approaches (e.g. Shi et al 2005;Bereneds et al 2008;Moore et al 2008), but we observe that the published descriptions appear to use bespoke software rather than workflow tools.…”

Application of a knowledge based design methodology to support fuselage panel design

“…Since execution of the application requires a running CAD system, they are usually deployed directly onto stand-alone desktop systems. In contrast, the integration of software tools using dedicated KBE systems is fully service-based enabled through loose coupling of software agents and enables distributed web-based deployment [15].…”

Application of a Knowledge Engineering Process to Support Engineering Design Application Development

“…The environment integrates the KBE software modules into a framework and provides communication between the KBE modules through software agents [4]. The design of the multi-agent task environment is inspired by the issues posed by earlier generation design support frameworks experienced addressing the automation of Multi-disciplinary Design and Optimization (MDO) problems often as a top-down execution of a string of individual discipline analysis tools.…”

“…The framework should prevent waste of CPU resources when partial re-execution of discipline analysis tools is required. Moreover, instead of upfront fixing the tool chain definition, the problem is communicated to the framework and each agent and tool combination is using its communication skills and knowledge of the problem to request information through a specified, but not tool and address specific, call [2,3,4].…”