Avsnitt
-
Recorded at CDFAM Computational Design Symposium, NYC 2024
Presentation Abstract
Boundary representation (B-rep) 3D models are the standard 3D representation used in the manufacturing industry. However, only recently has machine learning research begun to make progress on generative models capable of producing B-rep models. This talk will give a summary of the current state of the art for generating B-rep models. In particular it will cover, BrepGen, our recent work using diffusion models, that have proved extremely successful in the image domain, to the problem of B-rep generation.
Speaker Bio
Karl is a Senior Research Manager at Autodesk Research focused on data-driven design software for manufacturing. He holds a Ph.D. in Computational Design from Carnegie Mellon University and has presented his research internationally at conferences such as ICML, CVPR, ACM SIGGRAPH, ACM UIST, and ACM CHI. His work at Autodesk has won numerous awards including Fast Company Innovation By Design Honoree and Core77 Design Awards Research and Strategy Honoree.
CDFAM Computational Design Symposium series brings together leading experts in computational design from industry, academia and software development for two days of knowledge sharing and networking.
Visit CDFAM.COM to learn about upcoming events around the world.
This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.designforam.com -
Recorded at CDFAM Computational Design Symposium, NYC 2024
Presentation Abstract
This presentation explores how brands like CCM are partnering with software platforms like Toolkit3D, and using additive manufacturing tools from Carbon to offer customization to consumers with groundbreaking products like the AXIS XF Goalie Mask and the SUPER TACKS X Total Custom helmet.
While designers at CCM used Carbon’s Design Engine Pro to create superior lattice pads that increase breathability in the AXIS XF Goalie Mask and the SUPER TACKS X Total Custom helmet, developers at Toolkit3D integrated the Scan-to-Fit Design Engine with Carbon Custom Production Software to build an automated workflow for custom parts, including computational design techniques and automated production preparation.
In summary, CCM with Toolkit3D built an automated pipeline for products with Carbon’s dual-cure materials and advanced additive manufacturing processes that yield custom fit products automatically and at scale for all athletes– elite to amateur.
Speaker Bio
Puneet Jhaveri is a Senior Applications Engineer at Carbon 3D where he leverages his expertise and training in mechanical engineering and physiology to develop custom products. Originally on a medical track, Puneet’s interests shifted after being exposed to architecture and industrial design, sparking a passion for blending technical skills, aesthetics, and creative problem-solving. Puneet now focuses on pushing the boundaries of product design through innovative, cross-disciplinary approaches.
CDFAM Computational Design Symposium series brings together leading experts in computational design from industry, academia and software development for two days of knowledge sharing and networking.
Visit CDFAM.COM to learn about upcoming events around the world.
This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.designforam.com -
Saknas det avsnitt?
-
Recorded at CDFAM Computational Design Symposium, NYC 2024
Presentation Abstract
Engineering creativity and innovation are too often stifled by the tedious process of building simulation models. The process adds no value, can take weeks or months to complete, and far too often results in a model that has gotten out of sync with the design model.
Coreform’s new Flex product accelerates engineering design by reducing the meshing burden through easier and more powerful FEA. Coreform Flex leverages cutting-edge techniques from FEA and computational geometry to streamline the process of setting up FEA models. At the same time, Flex provides simulation results that are more accurate and robust than traditional low-order FEA across linear, nonlinear, static and dynamic simulation regimes. In most cases, users report that simulation models that usually take several weeks to build can now be built in less than a day.
In this presentation, Matthew Sederberg will give a concrete and accessible overview of the technical underpinnings of the Flex approach to FEA. He will also outline a few of the ways the Flex approach can accelerate engineering design and unleash the creativity of engineers.
Speaker Bio
Mr. Matt Sederberg is a pioneer in introducing new technologies to the CAD/CAE industry and has successfully started and sold a company in this space. Mr. Sederberg introduced T-Splines to the CAD market as its CEO in 2005, bootstrapping that company on SBIR funding to create plugins and integrated components used by over 2000 customers, sold through a channel with over 50 resellers. He created the premier brand in the industry, leading to a successful acquisition by market leader Autodesk in 2011, then led Autodesk’s \$40M automotive design product line. In 2016 Mr. Sederberg left Autodesk to join Coreform, where he now serves as Chief Strategy Officer.
CDFAM Computational Design Symposium series brings together leading experts in computational design from industry, academia and software development for two days of knowledge sharing and networking.
Visit CDFAM.COM to learn about upcoming events around the world.
This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.designforam.com -
Recorded at CDFAM Computational Design Symposium, NYC 2024
Presentation Abstract
In the context of traditional and advanced industrial settings, the adoption of Scientific Machine Learning (SciML) requires operating in digital-physical environments governed by large-scale, three-dimensional, multi-modal data streams that are confounded with noise, sparsity, irregularities and other complexities that are common with machines and sensors interacting with the real, physical world. Digital engineering domains—that is CAD, CAM, CFD, and so on—and advanced manufacturing settings provide exemplary environments to separate tried & tested SciML from unreliable “AI” and game engines. This talk elaborates on such digital-physical environments and the non-trivial needs from computational design and engineering tools. Special attention is given to differentiable programming in multi-physics settings, which done well is the catalyst for bringing autonomous, data-driven, machine-learnable techniques to advanced manufacturing and digital engineering worlds.
Speaker Bio
Alexander Lavin is a leading expert in AI-for-science and probabilistic computing. He’s Founder & CEO of Pasteur Labs (and non-profit “sister” Institute for Simulation Intelligence), reshaping R&D with a new class of AI-native simulators, commercializing in energy security, aerospace, materials & manufacturing sectors. For the last dozen years, Lavin has focused on artificial general intelligence (AGI) research with top startups in neuroscience and robotics (Vicarious, Numenta), and sold his prior ML-simulation startup Latent Sciences to undisclosed pharmaco in neurodegeneration R&D.
Lavin also serves as AI Advisor for NASA, overseeing physics-ML efforts for the NASA-ESA “Digital Twin Earth” projects. Previously, Lavin was a spacecraft engineer with NASA and Blue Origin, and won several international awards for work in rocket science and space robotics (including Google Lunar XPrize during graduate studies at Carnegie Mellon). Lavin was named Forbes 30 Under 30 in Science, and a Patrick J. McGovern Tech for Humanity Changemaker.
CDFAM Computational Design Symposium series brings together leading experts in computational design from industry, academia and software development for two days of knowledge sharing and networking.
Visit CDFAM.COM to learn about upcoming events around the world.
This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.designforam.com -
Recorded at CDFAM Computational Design Symposium, NYC 2024
Presentation Abstract
Sandia National Labs is a systems integrator and design agency with additional production responsibility for critical components. As such, advanced and additive manufacturing offer significant potential value to our mission responsibilities. Novel functionality and efficiencies can be achieved through complex part geometries, design of new or functionally graded composites or nano-structured materials, and the leveraging of data via a “network of things” and machine-learned models for integrated AI controls and process optimization. Taken together, if fully realized, these developments hold out promise for a new era of digitally integrated product realization that is precise, responsive, and “smart”. However, shortcomings in establishing the technical basis for determining reliable performance margins persist due to the complex, coupled physical processes that create the final material as the part itself is being built. Developing sufficient scientific understanding of these processes to achieve the levels of control required for rapid realization and qualification of processes or parts is itself a challenge. A true design for AM methodology must further invert this scientific understanding to achieve targeted performance margins. This presentation details a number of ongoing efforts to develop a physics-based modeling framework for advanced and additive manufacturing that is predictive of process outcomes based on settings and can be used to provide optimized design workflows. Examples are shown for DIW stress pads and cushions and metal laser powder bed fusion.
This work was supported by the LDRD program at SNL, managed and operated by NTESS under DOE NNSA contract DE-NA0003525.
Speaker Bio
Jeremy Lechman is manager of the Energetics, Multiphase and Soft Matter Sciences Department, Engineering Sciences Center, Sandia National Laboratories
CDFAM Computational Design Symposium series brings together leading experts in computational design from industry, academia and software development for two days of knowledge sharing and networking.
Visit CDFAM.COM to learn about upcoming events around the world.
This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.designforam.com -
Recorded at CDFAM Computational Design Symposium, NYC 2024
Presentation Abstract
Presentation Abstract
LifEnabled makes custom-fit prosthetic devices for the developing world that are simple, durable and new. Partner with LifEnabled to impact the world.
Speaker Bio
Brent Wright, CP, BOCO, is a Partner and Designer at Advanced 3D, and a clinician for patients on the ground at Eastpoint Prosthetics and Orthotics in Raleigh, NC. While he has a background with Fused Deposition Modeling (FDM), Brent has been utilizing new methods using MultiJet Fusion and Selective Laser Sintering lately, looking to create prostheses that are not only functional but light and flexible.
CDFAM Computational Design Symposium series brings together leading experts in computational design from industry, academia and software development for two days of knowledge sharing and networking.
Visit CDFAM.COM to learn about upcoming events around the world.
This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.designforam.com -
Recorded at CDFAM Computational Design Symposium, NYC 2024
Presentation Abstract
For the additive manufacturing industry to grow, unlocking production applications is critical. Building web applications targeting the AM industry is needed to make 3D printing easier to use in production settings. However, developing cloud-based applications that deal with complex geometries and CAD-like capabilities typically requires specialized expertise and a lengthy development process.
This talk describes how two AM startups worked together to bring a web application for additive manufacturing to market in a compressed timeframe. We will present General Lattice’s Frontier web application for digital materials and describe their use of the Metafold implicit geometry kernel API.
This collaboration allowed General Lattice to focus on their differentiated IP: offering validated materials and geometries from partner vendors to facilitate expedited path to commercialization.
Speaker Bios
Daniel is an entrepreneur and mathematician with extensive experience in geometric computing for the Additive Manufacturing industry. Before co-founding Metafold, Daniel held numerous roles in engineering firms working on complex geometric challenges in large-scale commercial construction. He is passionate about solving problems arising in industry with geometry and computation.
Marek Moffett, co-founder General Lattice, leading General Lattice’s computational design and additive manufacturing team, focusing on the generation of lattice architectures and DFAM techniques.
Leveraging years of research across several aspects of latticing, my goal is to deliver advanced material solutions to the industry, ultimately driving a wide spread adoption of superior performing products.
CDFAM Computational Design Symposium series brings together leading experts in computational design from industry, academia and software development for two days of knowledge sharing and networking.
Visit CDFAM.COM to learn about upcoming events around the world.
This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.designforam.com -
Recorded at CDFAM Computational Design Symposium, NYC 2024
Presentation Abstract
KPF’s computational geometry processes, whether generating complex building components, documenting, optimizing, rationalizing, or form-finding, consistently rely on a set of core common methods.
Across geometrically and computationally diverse projects, we have identified a repeated pattern and codified 5 distinct methods that form the logical underpinning of almost every bespoke computational task. These methods—data branching, point sorting, plane-based calculation, cross-referencing, and surface rebuilding—form the foundation of our architectural geometric computation process, much like the unseen bulk of an iceberg beneath the water’s surface.
The majority of the work in each computational project involves a combination of these five methods; only after establishing these foundational logics can we implement the bespoke computational logic that handles the specific geometric tasks.
Despite their apparent simplicity, these core functions can become extraordinarily complex in large projects due to the vast number of conditions and edge cases which require our core methods to be standardize and scalable. As project complexity increases, these elemental functions become much more important than bespoke computational logics to ensure that all geometric conditions are accounted for. In this presentation, we will define the main foundational methods of computational geometry and then use several geometrically and logically diverse megaprojects to illustrate how these foundational methods form the majority of the computational logic in each.
Through classification and case studies, we will codify the core geometric computational methods required to develop any large architectural project at scale
Speaker Bio
Madeleine Metawati Eggers is a computational design specialist at KPF who specializes in parametric modeling and computational problem solving on large-scale and complex buildings. As a core member of the KPF computational design team, she has worked with leadership to guide the computational design team’s role in the office as collaborators in the design process, particularly in representing qualitative design problems such that they can be solved computationally.
CDFAM Computational Design Symposium series brings together leading experts in computational design from industry, academia and software development for two days of knowledge sharing and networking.
Visit CDFAM.COM to learn about upcoming events around the world.
This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.designforam.com -
Recorded at CDFAM Computational Design Symposium, NYC 2024
Presentation Abstract
Prosthetic sockets for people with amputation are traditionally provided using a manual, plaster-based process where the clinician captures the shape of the limb using a plaster cast, makes modifications to this surface to load and off-load particular biomechanical regions, before this modified shape is used as the base to fabricate the final device.
While digital processes have been around for several decades, which use 3D scanning and surface-based sculpting tools to replicate the traditional processes, using this digital record to learn from and support the socket design processes has been limited. With increasing adoption of 3D printing in the industry, the need for data to support in device design and fitting is increasing.
Radii Devices are a UK-based startup using machine learning techniques to learn from historical records and support fitting of these devices within a clinical setting. By providing clinicians access to this technology at the point-of-care, their aim is to provide an improved fitting process for both clinicians and prosthetic users.
Speaker Bios
Nathan Shirley, Lead Computational & Industrial Designer, HP Computational Design
Nathan helps lead a tactical Design, Engineering, UX and SW team that implements mass customization design engines for HP’s 3D printing customers. We operate as a highly specialized consultancy to help them navigate the complex design and integration path to customizable production at scale in Multi-Jet Fusion, HP’s industrial 3D printing Technology. We focus mainly on Medical & Consumer Body Fitment use cases like orthotics, prosthetics, eyewear, footwear and performance sporting gear, as well as on engineered lattice meta-material behaviors.
Joshua Steer, PhD is the Founder and CEO of Radii Devices Ltd.
He completed his PhD in the Bioengineering department of the University of Southampton, UK in 2019, where he continues as a Visiting Research Follow. His prior academic research and subsequent work at Radii focuses on using software and data, such as 3D scans, to support the fitting of Prosthetics and Orthotics, and has contributed to 17 peer-reviewed journal articles. He collaborates on projects with multiple partners including the Department of Veteran Affairs Office of Advanced Manufacturing and National Health Service in the UK.
Full Presentation on Youtube
CDFAM Computational Design Symposium brings together leading experts in computational design from industry, academia and software development for two days of knowledge sharing and networking.
This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.designforam.com -
This keynote presentation at CDFAM Computational Design Symposium in NYC, 2024, introduces the innovative ‘Text-to-Spaceship’ concept by Ryan McClelland at NASA Goddard, focusing on the pivotal role of AI in transforming text-based science objectives into mission designs. We discuss how leveraging current and near-term AI technologies can accelerate the entire mission development process, from initial concept through to hardware realization.
Specific attention is given to AI-driven computational design of systems, illustrating how these technologies can improve design agility and performance. By deploying AI to accelerate the translation of scientific goals into tangible mission outputs, we aim to revolutionize spacecraft design and development, unlocking new capabilities and propelling the aerospace industry into a new era of technical innovation and expanded mission capacities.
CDFAM Computational Design Symposium series brings together leading experts in computational design from industry, academia and software development for two days of knowledge sharing and networking.
Visit CDFAM.COM to learn about upcoming events around the world.
This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.designforam.com -
Presentation Title: Scaling & Standardizing Patient-Specific Design
This recording of the presentation at the CDFAM Computational Design (+DfAM) Symposium, held in New York City in 2023. The speaker is Adam Wentworth, a notable figure in the healthcare and additive manufacturing field, associated with the Mayo Clinic.
Abstract: Adam Wentworth, a key contributor to the advancements in patient-specific design at the Mayo Clinic, provides an insightful presentation that explores the challenges and solutions associated with scaling and standardizing patient-specific design in healthcare. In his presentation, Wentworth discusses the criticality of personalized healthcare solutions and the role of computational design and additive manufacturing in delivering highly specific and effective treatment options. Drawing from his extensive experience at the Mayo Clinic, Wentworth presents case studies that exemplify the transformative potential of these technologies in healthcare. He explores both the technical and practical aspects of standardizing patient-specific design, offering insights into regulatory considerations, manufacturing processes, and the impact on patient outcomes.
Audience: This presentation is designed for professionals, researchers, and academics in the fields of computational design, additive manufacturing, and healthcare, particularly those with an interest in patient-specific design and personalized healthcare. Individuals seeking a deep understanding of the intersection between healthcare and advanced manufacturing technologies will find this presentation extremely valuable.
Please note: The CDFAM Symposium serves as a renowned platform for the exchange of knowledge among experts in computational design and additive manufacturing. This recording is intended for educational and professional development purposes.
This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.designforam.com -
In this CDFAM presentation, Alex Roschli, research staff member at Oak Ridge National Laboratory (ORNL) Manufacturing Demonstration Facility (MDF), discusses his background in robotics, the progression of his research, and the various aspects of his work on advanced toolpath generation for large scale additive manufacturing (AM).
Alex shares his insights on the challenges of materials and processes in additive manufacturing, as well as the potential applications and technology transfer of this process.
Read the full interview with Alex.
This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.designforam.com -
Innovative design requires innovative tools to help engineer advanced solutions. André A.R. Wilmes, CEO of Rafinex describes their novel optimization approach with the Möbius Design Workflow at the CDFAM Computational Design (+DfAM) Symposium in NYC, June 14-15 2023.
This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.designforam.com -
Recorded live at CDFAM 23
Chelsea Cummings is a Senior Additive Manufacturing Engineer and Digital Applications ADDvisor with The Barnes Global Advisors. Drawing on years of experience at Honeywell Aerospace and Arconic, Chelsea leads projects supporting the design process, advising clients on the effective use of digital tools to augment their additive manufacturing (AM) strategies.
With a career that includes qualifying the first of its kind Inconel 718 L-PBF flight hardware with the FAA in 2015 at Honeywell, flight hardware part family into AM production for Airbus A320neo upgrade in 2018 and first Army-developed, metal AM, flight safety component flown on a U.S. Army rotorcraft in 2022, Chelsea has a wealth of experience in the DfAM, but also the essential qualification process required to validate critical.
But not every design can start with a clean sheet, as Chelsea and her colleagues often help their clients how to adopt MfAM (Modify for Additive Manufacturing), so they can learn and gain experience and confidence before fully embracing DfAM (Design for Additive Manufacturing).
This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.designforam.com -
Daniel Hambleton, CTO of Metafold at the CDFAM Computational Design (+DfAM) Symposium.
Presentation Title: Geometry Streaming: Hardware First Software for Digital Manufacturing
Abstract: Daniel Hambleton, CTO and co-founder of Metafold, presents his groundbreaking work on 'Geometry Streaming', a hardware first approach to software for digital manufacturing. Hambleton delves into the intricacies of this pioneering concept, exploring its implications and transformative potential in the digital manufacturing landscape. Drawing upon his extensive experience at Metafold, he provides a comprehensive overview of the capabilities of geometry streaming, demonstrating its real-world applications and the benefits it brings to digital manufacturing.
Audience: This presentation is particularly suited for professionals, researchers, and academics in the fields of computational design, additive manufacturing, hardware design, and digital manufacturing.
Please note: The CDFAM Computational Design (+DfAM) Symposium is a distinguished platform for the dissemination of innovations and insights in computational design and additive manufacturing. This recording is provided for educational and professional development purposes.
This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.designforam.com -
This recording of Natalie Alima, a pioneering figure in the convergence of biology, robotics, and computational design from Biolab + Adidas presenting at the CDFAM Computational Design (+DfAM) Symposium, held in New York City in 2023. Presentation
Title: Interspecies Forms: Robotic Feedback Systems, Mycelia Growth & Computational Form: Redefining Design through Biological Integration
Abstract: Natalie Alima, a leading innovator at Biolab + Adidas, delivers a thought provoking presentation on 'Interspecies Forms' – a groundbreaking exploration of the integration of robotic feedback systems, mycelia growth, and computational form in design. Alima presents her in-depth research and experiments with mycelia – the root structure of mushrooms – and how its interaction with robotic systems and computational design methods can lead to novel design forms. Through her work, Alima challenges traditional design boundaries and introduces a new realm where biology, robotics, and computational design interplay to create sustainable and adaptive design solutions.
Audience: This presentation is specifically designed for professionals, researchers, and academics in the fields of computational design, additive manufacturing, biological design, and robotics. Individuals intrigued by the intersections of biology, robotics, and computational design will find this presentation particularly enriching.
Please note: The CDFAM Computational Design (+DfAM) Symposium is a prestigious forum for the exchange of knowledge and expertise among specialists in computational design and additive manufacturing. This recording is shared for educational and professional development purposes.
This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.designforam.com -
Francis Bitonti, working at the intersection of computer vision, synthetic data, and computational design at Lexset, presentation at the CDFAM Computational Design (+DfAM) Symposium, held in New York City in 2023.
Abstract: Francis Bitonti, CEO and co-founder of Lexset, explores the transformative capabilities of computer vision and synthetic data in the realm of computational design in his presentation titled 'From Simulation to Reality'. Bitonti delves into the practical applications of these technologies, showcasing how the convergence of computer vision and synthetic data can turn digital simulations into tangible realities. Bitonti offers an in-depth view of these technologies' role in advancing computational design, illustrating their potential with real-world examples from his work at Lexset.
His presentation outlines the potential challenges and solutions associated with implementing these technologies, providing a comprehensive overview of this cutting-edge field.
Audience: This presentation is tailored for professionals, researchers, and academics in the fields of computational design, additive manufacturing, computer vision, and synthetic data. Individuals with an interest in understanding the practical applications of computer vision and synthetic data in computational design will find this presentation highly beneficial.
Please note: The CDFAM Computational Design (+DfAM) Symposium is a renowned platform for the exchange of knowledge among specialists in computational design and additive manufacturing. This recording is intended for educational and professional development purposes.
This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.designforam.com - Visa fler
