Enabling Design Re-use through Predictive CAD

Lead Research Organisation: University of Strathclyde
Department Name: Design Manufacture and Engineering Man


Engineering Design work typically consists of reusing, configuring, and assembling of existing components, solutions and knowledge. It has been suggested that more than 75% of design activity comprises reuse of previously existing knowledge. However in spite of the importance of design reuse activities researchers have estimated that 69% of companies have no systematic approaches to preventing the "reinvention of the wheel". The major issue for supporting design re-use is providing solutions that partially re-use previous designs to satisfy new requirements. Although 3D Search technologies that aim to create "a Google for 3D shapes" have been increasing in capability and speed for over a decade they have not found widespread application and have been referred to as "a solution looking for a problem"! This project is motivated by the belief that, with a new type of user interface, 3D search could be the solutions to the design reuse problem.

The novel user interface proposed can be best understood in term of an analogy to the text message systems of mobile phones. On mobile phones 'Predictive text' systems complete words or phrases by matching fragments against dictionaries or phrases used in previous messages. Similarly a 'predictive CAD' system would complete 3D models using 'shape search' technology to interactively match partial CAD features against component databases. In this way the system would prompt the users with fragments of 3D components that complete, or extend, geometry added by the user. Such a system could potential increase design productivity by making the reuse of established designs an efficient part of engineering design.

Although feature based retrieval of components from databases of 3D components has been demonstrated by many researchers so far the systems reported have been relatively slow and unable to be components of an interactive design system. However recent breakthroughs in sub-graph matching algorithms have enabled the emergence of a new generation of shape retrieval algorithms, which coupled with multi-core hardware, are now fast enough to support interactive, predictive design interfaces. This proposal aims to investigate the hypothesis that a "Predictive CAD" system would allow engineers to more effectively design new components that incorporate established, or standard, functional or manufacturing geometries. This would find commercial applications within large or distributed engineering organizations.

This project can be regarded as an example of "big data" being employed to increase design productivity because even small engineering companies will have many hundreds of megabytes of CAD data that a "Predictive CAD" system would effectively pattern match against.

Planned Impact

The research will impact on the following commercial and societal benefits:

1) Engineering Businesses: Commercially business engaged in the design of engineering products will potentially benefit both from increases in the productivity of their design staff and the reduction in manufacturing costs associated with reuse.

2) CAD/CAM software developers: will potentially benefit from the creation of a user interface that directly mines the big-data of a company's product catalog to deliver a step change in the levels of reuse.

3) Circular Economy: Beyond the immediate economic impacts there are societal benefits associate with increased levels of reuses as a contribution to the emerging circular economy (e.g. reductions in carbon and energy).

Dissemination to industry beyond those involved directly in the project will be facilitated though involvement with national networks (i.e. HVM Catapult).


10 25 50

publication icon
Vasantha G (2020) A Probabilistic Design Reuse Index for Engineering Designs in Journal of Mechanical Design

Description The feasibility project has successfully established that shape analysis systems can successfully analyse the feature content of over sixty thousand 3D CAD models of engineering components in only a few minutes. This system has allowed us to generate the statistical information necessary to propose likely choices of feature sizes to designers (in a manner analogous to the predictive text systems used on mobile phones). Perhaps the most surprising discovery to emerge from this initial project is that the frequency distribution of design features appears to be very similar to words in the English language. No one had expected that this would be the pattern of usage and we are excited at the prospect of expanding the scope of the work to see if this finding is true in other companies and areas of engineering.

One practical implication of this finding is that the project has been able to adapt many of the statistical concepts developed for text analysis for use in CAD applications. Consequently the academic work of the project has focused on the generation of statistical data to support this approach to predictive calculations. As our understanding of the research challenge increased during the project, two things became clear:

1) The same statistical information used to predict a user's choice of parameter value could also have applications in making global assessments about the properties of a company's design portfolio (e.g. what is the potential and actual levels of design reuse with-in their products).

2) As the scope of the analysis increased the complexity of statistical mathematics involved requires expert guidance to ensure that the methods being applied are justifiable in the context of the problem.
Exploitation Route We submitted a successfull EPSRC a proposal (Design the Future 2: Enabling Design Re-use through Predictive CAD) for a follow-on project.
Sectors Aerospace, Defence and Marine,Creative Economy,Digital/Communication/Information Technologies (including Software),Manufacturing, including Industrial Biotechology

URL https://youtu.be/ly9BORCSUW0
Description Design the Future 2: Enabling Design Re-use through Predictive CAD
Amount £587,009 (GBP)
Funding ID EP/R004226/1 
Organisation Engineering and Physical Sciences Research Council (EPSRC) 
Sector Public
Country United Kingdom
Start 08/2017 
End 07/2020