Marina Novak

Intelligent decision support for structural design analysis

Abstract Many comprehensive composite computer-aided design systems with special analysis tools have been developed in order to make the product development process more effective. However, these computer-aided tools still concentrate mainly on the numerical aspects of analysis whilst, in most of cases, they fail to provide any kind of expert advice during the decision-making process. It is obvious that the existing computer tools in this field need to be extended in order to reach a higher level of performance by adding some intelligent behaviour. This paper discusses a framework for intelligent decision support for structural design analysis using a finite element method. The intelligent environment presented is composed of several knowledge-based modules in order to address some major bottlenecks within the analysis-based design improvement process. The prototypes of four intelligent modules are presented within this context. These are: an intelligent module for supporting some initial decisions within the design analysis process, an intelligent module for finite elements’ selection, an intelligent module for finite element mesh design, and an intelligent module for supporting the results’ interpretation process. According to the feedbacks of those experts who participated in the evaluation process, these prototypes could be applied as useful supporting tools for inexperienced designers in design practice, as shown in certain examples presented in this paper.

Intelligent FEA-based design improvement

Structural analysis using the finite element method is an integrate part of the design process for many components. Finite element analysis is the most extensively used numerical analysis in mechanical engineering practice and is incorporated into many computer-aided design systems. The existing commercial software is very helpful when supporting realisation of the analysis process but still fails to provide adequate support during the post-processing phase. The results of analysis should be studied and decisions made regarding the designs suitability with respect to its engineering specifications. In general, design changes are indispensable and designers need help to design them properly. The prototype of an intelligent rule-based consultative system is being developed by the authors to provide such advice when considering a description of the design structures critical area. This system is encoded in Prolog. It can deal with the results of prior strain-stress or thermal analysis. It presents a short list of proposed design changes that should be taken into account when improving the design.

Expert System for Design Optimisation Using Results of Finite Element Analysis

Design optimisation has a very important role in modem technology. In practice, the results of finite element analysis are often the basic parameters for the optimising process. If the structure does not satisfy given criteria, certain optimisation steps, such as redesign, use of other materials, etc., have to be taken. However, the existing software for finite element analysis sti11 fails to provide advice about any optimisation steps based on the results of the analysis. Thus, redesign steps sti11 depend mostly on the user’s knowledge and experience. In this paper, we present our vision of an expert system for advising the designer which redesign steps should be taken into account in particular cases. The system is sti11 in the development phase. The knowledge acquisition process is described in detail. It is anticipated that the system will be used not only for optimising new products in practice, but also in design education, where the students are typical representatives of inexperienced designers.

PROPOSE - Intelligent Advisory System for supporting Redesign

Optimal design reached in the first attempt is rare in engineering. Design is an iterative process. How many iterations/cycles are needed directly depends on the initial design and appropriateness of the later redesign actions. The results of engineering analysis are often basic parameters for the redesign actions in design process. If the structure does not satisfy given criteria, certain optimisation steps, such as redesign, have to be taken. Yet, the existing CAD software still fails to provide any advice about these redesign steps. Thus, the selection of the appropriate redesign actions still depends mostly on the designer’s knowledge and experience. The idea for our research work was to collect this kind of knowledge and experiences, organise them, and write them into a knowledge base of the intelligent system. The aim of this paper is to present PROPOSE, the intelligent consultative system for supporting modification of the design parameters during the embodiment design phase considering the results of the engineering analysis. The results of the evaluation of the system show that the prototype of the presented intelligent system can be applied either to design new products in practice or as an educational tool.

Intelligent Advisory System for Supporting Redesign

AbstractIt is the designer’s dream to be guided by decisions based on physical and mathematical modeling simulations, which are computationally intensive but offer immense insight into developing product. Nevertheless, dealing with these kinds of multi-disciplinary analyses is still a tremendous challenge. The main purpose of the intelligent consultative system for supporting analysis-based redesign, which is presented in this paper, is to engage with this challenge. The results of engineering analysis are often basic parameters for the optimization process. If the structure does not satisfy given criteria, certain optimization steps, such as redesign, have to be performed. Yet, the existing software still fails to provide any advice about these redesign steps. Thus, the selection of the appropriate redesign actions still depends mostly on the designer’s knowledge and experience. The idea for our research work was to collect, organize, and write this kind of knowledge and experience into a knowledge base ...