H13
Education

Back to overview

15:30
conference time (CEST, Berlin)
Evolving to Help Engineers Develop Methods that Greatly Increase Productivity
27/10/2021 15:30 conference time (CEST, Berlin)
Room: H
C. Wolfe (Ansys, Inc., USA)
C. Wolfe (Ansys, Inc., USA)
In today’s product development processes, engineering analysts are valued for their skills with engineering simulation. They are also in high demand and hard to develop with education and training. Years of experience are needed to reach their level of expertise. Increasingly, these engineers are being asked to leverage their knowledge by developing methods and solutions for others to use in solving repetitive, yet often complex, engineering problems. Engineering software companies can help by providing simulation platforms that allow engineers to develop methods and solutions that can solve arbitrary problems so they can accomplish these goals. A method is an integrated, simplified workflow, data model, UI and set user objects that allows someone to accomplish a task or achieve a goal. The underlying set of engineering applications that enable the solution may externalize 100s of concepts/objects, menus, data objects, navigations, and more. The method filters and maps objects into a problem focused set of objects, tasks and steps, which under the covers uses the products’ APIs and capabilities. A set of related methods makes up a solution, focused on solving an engineering problem or closely related applications. By developing and employing methods, engineering teams can unlock incredible increases in productivity, with one team reducing engineering design time to 2 hours from 4 week while also enabling 10x more design engineers to use simulation for a key multiphysics design problem, an 800% increase in productivity. A simulation platform must make the development of methods and sets of methods accessible to these engineers and others. The architecture must enable these methods to be run where they are needed, whether that is on-premise or via cloud and integrated into the engineer’s systems and environment. Standard APIs, crafted to make it easier to access and integrate with other services, are essential to method development success.
15:50
conference time (CEST, Berlin)
Augmenting and Amplifying Engineering Education and Research Through RealTime 3D Analysis Tools
27/10/2021 15:50 conference time (CEST, Berlin)
Room: H
D. Choudhury, R. Borker (Ansys Inc., USA)
D. Choudhury, R. Borker (Ansys Inc., USA)
Digital transformation is impacting every industry - automotive, agriculture, logistics, healthcare and manufacturing, to name a few. Concurrently, digital technologies are increasingly being used in high schools, colleges and universities for in-person and remote learning. While, in the past, engineering education coupled classroom lectures with experiments in physical laboratories, in the future, lectures will be a blend of brick and mortar classroom teaching augmented by online resources and engineering simulation tools. Laboratory experiments, design projects and physical prototyping will be complemented by simulation and software based experiential learning. While traditional engineering simulation tools such as the leading CFD, CSM and CEM packages are extremely accurate and capable of detailed modeling, they are not as easy to use, particularly for undergraduate or high school students. Hence, our team has developed a simulation tool called Ansys Discovery that introduces designers and undergraduate students to the art and practice of simulation, allowing them to create concepts leading to designs, as well as perform design space exploration while learning the underlying physics and simulation principles. The main breakthroughs have been in achieving an unprecedented level of usability and the high performance computing capacity of GPUs. While the simulation tools in the past were generally restricted to run on engineering workstations, on powerful personal computers, or on university servers, with Ansys Discovery it is possible to get near-instantaneous results utilizing the capabilities of GPUs on the local machine or on the Cloud. Ansys Discovery's capabilities are supported by digital learning system (online courses with simulation tools provided on the cloud) allowing students around the world to be trained in the most complex engineering disciplines. In this talk, we will provide details of the underlying technologies and methods that are suitable for meeting the evolving needs of the many millions of engineering and STEM students by providing educators and students with high quality education assets and simulation tools accessible to everyone.
Engineering Education, Simulation Tools, GPU Computing, Computational Methods
16:10
conference time (CEST, Berlin)
Development of a Simulation-based Knowledge Representation for the Simplification of Structural Aero Engine Components
27/10/2021 16:10 conference time (CEST, Berlin)
Room: H
B. Spieß, K. Höschle (BTU Cottbus-Senftenberg, DEU); M. Fanter (Rolls-Royce Deutschland Ltd. & Co KG, DEU)
B. Spieß, K. Höschle (BTU Cottbus-Senftenberg, DEU); M. Fanter (Rolls-Royce Deutschland Ltd. & Co KG, DEU)
Computer simulations are one of the most important tools in the product development cycle. The generation of simulation models for these, however, can be a complicated and tedious task. Especially in complex assemblies the need for model and boundary condition simplifications rises. These simplifications can reduce the computational effort on the one hand but increase the effort for the model creation on the other hand. Besides involved tedious manual steps, engineering knowledge and experience are important keys for choosing modelling techniques to reduce model complexity while maintaining a sufficient result quality. This aspect of drawing profit from experience for modelling decisions is difficult to capture and to integrate digitally in an automated process. This scientific work is presenting an approach towards a knowledge and experience base for building a digital model understanding. This experience is gained from data which associates geometric information to simulation results. After learning from this data, the algorithm is able to select appropriate Finite-Element (FE) modelling representations while considering the resulting simulation accuracy. The developed knowledge representation is then guiding simplification decisions in the automated CAD-to-FE process. In the scope of this work, the focus is set on the converting and simplifying aero engine casing structures for structural simulations. The starting point is an automated process to transfer quasi-axisymmetric components to analysis models of various level of detail. This segments the geometry into substructures and provides a feature vector containing information about the structure along. Afterwards, the geometric information is coupled with data regarding the associated FE entities and the final simulation result. The simulation model quality is evaluated by composing basic dynamic properties and simulation model properties, e.g. number of degrees of freedom, as conflicting objective. These processes are combined with parametric CAD models and implemented in design-of-experiments studies to build the training data. Finally, self-learning algorithms take this information as input to build the digital knowledge representation.
Geometry-Based Simulation, Knowledge Representation, Machine Learning, Automation
×

[TITLE]

[LISTING

[ABSTRACT]

[DATE]

[ROOM]

[KEYWORDS]