=Paper=
{{Paper
|id=Vol-2456/paper78
|storemode=property
|title=On the Use of Cloud and Semantic Web Technologies for Generative Design
|pdfUrl=https://ceur-ws.org/Vol-2456/paper78.pdf
|volume=Vol-2456
|authors=Daniel Mercier,Ali Hashemi
|dblpUrl=https://dblp.org/rec/conf/semweb/MercierH19
}}
==On the Use of Cloud and Semantic Web Technologies for Generative Design==
https://ceur-ws.org/Vol-2456/paper78.pdf
On the Use of Cloud and Semantic Web
Technologies for Generative Design
Daniel Mercier[0000−0003−1239−9728] and Ali Hashemi
Autodesk Research, Toronto ON M5G 1M1, Canada
{daniel.mercier,ali.hashemi}@autodesk.com
http://autodeskresearch.com/
Abstract. The emergence of the Cloud has transformed the way we
approach data. It created a convergence of heterogeneous data and an
opportunity to link data at scale. This transformation came with chal-
lenges; some related to the migrating of historical data, some with the
adoption of service-oriented architecture. In this work1 , we introduce
three challenges that we addressed with semantic web technologies during
the recent development of Generative Design services for manufacturing.
Keywords: Semantic web · Generative design · Cloud · Data conver-
gence · Linked data · Simulation.
Introduction. Generative Design(GD) is a relatively new concept. It challenges
traditional design processes by automatically generating valid designs through
computation. Each of these designs fulfills given desired goals and complies to
specified rules and constraints. As a whole, they provide a broad view over the
space of valid solutions to substantially complex problems that would otherwise
be resource-exhaustive through traditional approaches.
Context. In our domain of interest, Computer Aided Design(CAD) for manufac-
turing, GD accelerates the design cycle by generating new shapes, geometries or
assemblies that are digitally validated for a specific environment. At the core,
there are traditional numerical simulation solvers such as the ones for struc-
tural, thermal, and fluid analysis. The GD process generates an initial set of
designs with noticeable variations and optimizes each design using the simu-
lation solvers towards compliance. The whole process uses simulation at scale
which is inherently provided by Cloud technologies. During the composition of
our GD services, we faced three challenges that were resolved using Semantic
Web Technologies.
The first challenges is related to the unification of data sources. Autodesk
has a rich portfolio of historically independent CAD and simulation software;
each with its own data sources. Now located on the Cloud, these data sources
are centralized and easy to maintain. However, these data sources often have
1
Copyright c 2019 for this paper by its authors. Use permitted under Creative Com-
mons License Attribution 4.0 International (CC BY 4.0).
2 D. Mercier et al.
commonalities; for example, sources on material properties or manufacturing
specifications. The first challenge was to unify these data sources to take ad-
vantage of the aggregated knowledge. For this purpose, we developed a service
using ontology as an intermediary taxonomy to correlate sources and aggregate
data without interfering with the original formatting of the data sources2 .
The second challenge is related to data validation. The creation of a GD
problem is a complex step by step operation which can benefit from regular
validation of user-provided data. The types of validation vary from simple logic
to complex mathematical transformations that are usually best distributed over
dedicated computing units. This challenge can be broken down in two parts. The
first part was to offer the largest diversity of validation methods, for example,
geometric analyses for early feasibility evaluation. For this purpose, we stored
our knowledge base in ontology to leverage descriptive logic, executed simple
validation locally, and connected to Cloud service-meshes through plugins for
advanced processing. The second part of the challenge was to structure the
knowledge base in a re-usable fashion to support commonalities between the
various forms of Generative Design applied to different disciplines. For example,
most geometric validations are shared between GD for manufacturing and GD
for building construction. To support these commonalities, the knowledge base
was split in two layers; one for applications and one for domain-specific content
consumed by the application layer.
Finally, the third challenge relates to the storage and management of GD
content. Simulation data was historically encapsulated for consistency and porta-
bility. It often led to very large files or groups of files. The GD process naturally
scales up this storage requirement. Moreover, in GD, the individual simulations
often share content whether geometries, material properties, boundary condi-
tions or process parameters which leads to redundancies. The third challenge
which is still under investigation, tackles the design of an efficient architecture
to store GD data by optimizing content distribution and reducing redundancies.
This management of data is a switch from managing all-encompassing files to
managing metadata pointing to smaller content. In this context, semantic web
technologies are suitable for the coordination of metadata, the verification of
content integrity, and the fast exploration and retrieval of data. Finally, this ar-
chitecture is also an opportunity to integrate advanced analyses and automatic
generation of knowledge to support the GD process.
Conclusion. Generative Design is a new design paradigm. It goes beyond tradi-
tional processes and has been made available to the masses through the emer-
gence of Cloud technologies. This work is a report on the challenges that we
encountered during the design and creation of GD services and how we used
Semantic Web technologies to address those challenges.
2
Mercier, D., Cheong, H., Tapaswi, C.: Unified access to heterogeneous data sources
using an ontology. In: Semantic technology: 8th Joint International Conference.
pp.104-118 (Nov 2018)