CDFAM Computational Design Symposium

Deterministic engineering analysis assigns fixed values to loading conditions, geometry, and material properties. The approach is tractable, but it forces a choice between conservative overdesign and exposure to failure modes that fall outside assumed limits. Neither outcome is satisfying.Greg Grigoriadis of Metisec describes a design toolkit that replaces fixed inputs with statistical distributions and runs Monte Carlo simulations across the resulting parameter space. The output is a probabilistic picture of performance: failure probabilities, sensitivity rankings, and the specific conditions that actually drive risk.A sensor mounting bracket for a smart wearable serves as the test case. Traditional optimization cut bracket weight by 30%. Probabilistic analysis revealed the design had been tuned to an improbable drop event and still carried unresolved thermal failure risk. Incorporating that information allowed the team to re-optimize and achieve a 50% weight reduction at a demonstrably low failure probability.Greg is an engineering consultant specializing in consumer electronics, digital twin technologies, and advanced simulation workflows. His practice combines physics-based modeling with data-driven methods across finite element analysis, predictive maintenance, and automated computation pipelines.Presented at CDFAM Barcelona 2026. Learn more at cdfam.com. 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

The gap between geometric modeling and structural simulation has always been a workflow problem as much as a technical one. Every time a designer changes a shape, the mesh breaks, boundary conditions need redefining, and the simulation has to be rerun from scratch. At the scale of iterative or generative design workflows, that overhead compounds quickly.In this episode recorded at CDFAM Barcelona 2026, Johannes Mueller-Roemer presents SubSimX, a pipeline that addresses this by treating subdivision surfaces as a native simulation medium rather than a preprocessing step. Designers work on a standard Catmull-Clark control mesh. Meshing and boundary condition setup happen once. From that point, geometry edits propagate to the existing analysis mesh in seconds, structural feedback is continuous, and the design session never has to stop for remeshing.The technical core is a precomputed mapping between the control mesh and the volumetric interior, combined with a local mesh-repair step that maintains element quality through large deformations without changing mesh topology. Coupled with RISTRA, Fraunhofer’s GPU-accelerated FEM solver, the system delivers real-time or near real-time structural feedback. Johannes demonstrates how this enables dense design sweeps, topology optimization followed by subdivision refinement, and AI-in-the-loop exploration within practical industrial workflows.Johannes Mueller-Roemer is Deputy Head of Interactive Engineering Technologies at the Fraunhofer Institute for Computer Graphics Research IGD. He received his PhD from TU Darmstadt in 2019, where his dissertation introduced GPU data structures for tightly coupled modeling and simulation — the foundation SubSimX is built on.Recorded at CDFAM Barcelona 2026 — https://cdfam.com/barcelona-2026/ 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

Most 3D generative AI has been built to produce things that look right. Hao (Richard) Zhang argues that for the built environment, that is the wrong objective. Buildings must function — and that means AI systems need to reason about spatial relationships, load paths, equipment routing, and regulatory constraints, not just geometry.In this episode recorded at CDFAM Barcelona 2026, Richard introduces Functional AI as a framework for 3D design automation and walks through Augmenta’s work applying it to real building projects. The technical scope covers agentic AI for MEP path finding, generative modeling of complex structural and mechanical layouts, and progress toward a foundation model for building data. He also discusses what makes non-residential construction — commercial, medical, institutional, and mission critical — a particularly hard problem for AI systems to crack.The conversation closes on a concrete milestone: two elementary schools in Michigan where the electrical system was fully modeled and delivered using AI-powered generative design, a first for the industry.Hao (Richard) Zhang is VP of AI and R&D at Augmenta and a Professor in the School of Computing Science at Simon Fraser University. He is a Fellow of the IEEE, a member of the ACM SIGGRAPH Academy, and served as Technical Papers Chair for SIGGRAPH 2025.Recorded at CDFAM Barcelona 2026 — https://cdfam.com/barcelona-2026/ 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

Pablo Hermoso Moreno, Senior Solutions Architect at NVIDIA, joins CDFAM Barcelona 2026 to discuss how AI is reshaping Computer-Aided Engineering workflows.Pablo draws on his background in aerospace engineering, aerodynamics at Mercedes F1, and cloud-scale AI at AWS to frame where CAE bottlenecks actually live - and what NVIDIA is doing about them. The conversation covers AI physics and surrogate models for real-time simulation feedback, the role of digital twins, and how agentic AI built on the NVIDIA NeMo stack is automating end-to-end engineering workflows.He also walks through the AI-Q Blueprint, a production-ready enterprise research agent, and explains how the NeMo Agent Toolkit manages LLM call prioritization to reduce latency without additional hardware investment.Full presentation and archive at cdfam.com/barcelona-2026/ 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, October 29-30, 2025https://cdfam.com/nyc-2025/OrganizationPrinceton UniversityPresenter:Tuo ZhaoSuper-Modular Chiral Origami MetamaterialsPresentation AbstractMetamaterials with multimodal deformation mechanisms resemble machines, especially when endowed with autonomous functionality. A representative architected assembly, with tunable chirality, converts linear motion into rotation (1). These chiral metamaterials with a machine-like dual modality have potential use in areas such as wave manipulation, optical activity related to circular polarization and chiral active fluids. However, the dual motions are essentially coupled and cannot be independently controlled. Moreover, they are restricted to small deformation, that is, strain ≤2%, which limits their applications. Here we establish modular chiral metamaterials (2), consisting of auxetic planar tessellations and origami-inspired columnar arrays, with decoupled actuation. Under single-degree-of-freedom actuation, the assembly twists between 0° and 90°, contracts in-plane up to 25% and shrinks out-of-plane more than 50%. Using experiments and simulations, we show that the deformation of the assembly involves in-plane twist and contraction dominated by the rotating-square tessellations and out-of-plane shrinkage dominated by the tubular Kresling origami arrays. Moreover, we demonstrate two distinct actuation conditions: twist with free translation and linear displacement with free rotation. Our metamaterial is built on a highly modular assembly, which enables reprogrammable instability, local chirality control, tunable loading capacity and scalability. Our concept provides routes towards multimodal, multistable and reprogrammable machines, with applications in robotic transformers, thermoregulation, mechanical memories in hysteresis loops, non-commutative state transition and plug-and-play functional assemblies for energy absorption and information encryption.References:(1) Frenzel, T., Kadic, M. & Wegener, M. Three-dimensional mechanical metamaterials with a twist. Science 358, 1072–1074 (2017).(2) Zhao, Tuo (presenter), Dang, X., Manos, K., Zang, S., Mandal, J., Chen, M., & Paulino, G. H. Modular chiral origami metamaterials. Nature, 640(8060), 931-940 (2025).Speaker BioTuo Zhao is a postdoctoral research associate at Princeton University. His expertise is in computational mechanics, nonlinear topology optimization, soft robotics, and mechanical metamaterials. Tuo is currently addressing the scalability challenge for developing useful metamaterials. By integrating an untethered actuation scheme (e.g., three-dimensional magnetic fields and micro-magnetic responsive materials), he designs micro-robotic machines with tunable properties on demand. 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, October 29-30, 2025https://cdfam.com/nyc-2025/OrganizationTetmethttps://www.tetmet.net/Presenter:Rachel AzulayConformal Lattice Design Made Easy: A CAD-Integrated ApproachPresentation AbstractTETMET has developed an innovative process to produce large-scale lattice structures in an automated way, enabling applications across multiple industries.However, existing lattice design software has significant limitations, particularly when it comes to creating efficient, manufacturable conformal lattice structures. Most available tools were developed with general 3D printing in mind, offering only basic latticing capabilities that fail to meet the demands of more advanced applications.Our approach takes a different path by integrating lattice design seamlessly into traditional CAD workflows. By combining the flexibility of CAD with the specific requirements of lattice generation, we significantly enhance the design process—allowing engineers to work with familiar tools while unlocking new possibilities for complex, high-performance structures.Speaker BioRachel holds a PhD in Lattice Structure Design and leads the Application Engineering team at TETMET. She specializes in transforming complex customer challenges into innovative, lightweight lattice solutions, bridging cutting-edge research with real-world applications. 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, October 29-30, 2025https://cdfam.com/nyc-2025/nTopBradley RothenbergFrom 3 Configurations to 300: Rapid Trades for Advanced Aircraft DesignPresentation AbstractAircraft development timelines have collapsed from 7 years to 18 months, but design tools still assume you have years to iterate. The result: teams freeze architecture in week 2, before they understand the design space, and spend the rest of the program managing the consequences.The core problem is going from requirements-to-design is just too slow. Serial design evaluations, manual CAD updates that fail to parametrize correctly, and expensive simulation cycles create weeks-long iteration loops.nTop solves this through three architectural principles: Parametric models that remain robust under any design change. No geometry failures, no manual repairs; integrated notebooks capturing engineering knowledge in executable form; and GPU-native solvers enabling interactive design-analysis cycles with performance feedback in minutes.What’s the alternative? Exploring 3-4 hand-crafted configurations slowly or quickly committing to a single concept. Neither is likely to win. nTop enables systematic exploration of hundreds of variants in the time that traditional approaches evaluate three.This presentation demonstrates real examples: Group 1-3 UAS configurations generated and flight-tested in weeks, hypersonic vehicle trade studies evaluating hundreds of variants, and rapid weapons platform sizing with integrated CFD.The result: teams explore more, fail fast, and learn faster—improving win rates through comprehensive trade studies and defensible performance predictions.About CDFAM:CDFAM is a global symposium series at the forefront of computational design, advanced manufacturing, and performance-driven engineering. With a strong emphasis on innovation, CDFAM highlights how leading companies and researchers are leveraging AI, machine learning, and simulation technologies to drive the next generation of design tools, workflows, and digital fabrication methods.The symposium fosters cross-disciplinary collaboration and knowledge exchange between designers, engineers, and technologists exploring the cutting edge of digital design — from generative workflows.Past presenters and partners include companies such as NVIDIA, NASA, New Balance, BMW, ARUP, Foster +, Partners, BIG, Autodesk, Dassault Systèmes, nTopology, PyhicsX, Neural Concept, Siemens and more, showcasing how computation and AI are transforming everything from aerospace to footwear.Learn more at https://cdfam.com 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, October 29-30, 2025https://cdfam.com/nyc-2025/Organization:ARENA-AIPresenter:Pratap RanadeArtificial Intuition: Building an AI Mind for Electromagnetic DesignPresentation AbstractMost advances in computational design focus on mechanical structure — domains we can visualize and have evolved an intuition for. But as modern hardware becomes increasingly software defined, the unseen and unintuitive world of electromagnetism is taking center stage. Conventional solvers can simulate fields, yet they cannot imagine new ones. In this talk, I’ll share how we’re pushing past that frontier by creating artificial intuition — AI systems that learn physical behavior inductively, not deductively. Drawing inspiration from quantum experiments like the Kondo mirage, where discovery outpaced simulation, I’ll show how our team built Atlas: an AI that learns directly from electromagnetic test data to verify, optimize, and eventually postulate new designs. We’ll share results from realworld applications in semiconductors and aerospace, and offer a teaser of what’s to come over the next twelve months.Speaker BioPratap Ranade, CEO and Founder of ARENA-AIJoin us at CDFAM Barcelona April 8-9, 2026, the premier symposium for computational design, AI, and engineering innovation.Don’t miss your chance to connect with global leaders in design and technology.Register by February 1st to secure the early bird rate and be part of the conversation shaping the future of design, architecture, and advanced 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

Recorded at CDFAM Computational Design Symposium, NYC, October 29-30, 2025https://cdfam.com/nyc-2025/Organization:CORE studio | Thornton TomasettiPresenter:Sergey PigachEngineering Intelligence: Practical Applications of AI in Structural Engineering PracticePresentation AbstractArtificial Intelligence is no longer a distant future. It is actively shaping how structural engineers work, collaborate, and innovate. This session offers a practical look into how Thornton Tomasetti’s CORE studio is advancing AI integration within the firm, with a focus on real-world tools and workflows that enhance engineering practice. Attendees will explore the firm’s hands-on experimentation with generative models, domain-specific co-pilots, and applications of agentic workflows, as well as strategies for cross-disciplinary collaboration that ensure AI tools align with engineering priorities. The presentation will also share lessons learned in promoting firmwide adoption, cultivating technical fluency, and building an inclusive innovation culture that empowers all team members to contribute to AI-driven transformation.Speaker BioSergey Pigach is a Senior Associate Applications Engineer at CORE studio | Thornton Tomasetti. Sergey’s work builds on his architectural training by bridging the domains of technology and design, driving him to develop computational tools for architects, designers, and engineers. Since joining CORE studio he has worked on desktop and web-based projects including Swarm, a cloud compute solution for Grasshopper; ShapeDiver, a desktop client integration following a merger; and—most recently—Cortex, CORE Studio’s new MLOps platform. 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, October 29-30, 2025https://cdfam.com/nyc-2025/OrganizationDavid Burpee DesignPresenter:David BurpeeComputational Morphogenesis: Leveraging Proceduralism to Unlock Temporal DesignPresentation AbstractCurrent paradigms of design and engineering operate on the premise that realized designs are static – that is once they are designed and manufactured they exist in their final state. Likewise even flexible computational systems tend to not incorporate the dimension of time as a design tool. Despite dozens or hundreds of sliders, variables, and graphs, most products – even those designed computationally – are “frozen” at a certain point and designed as a static object.New advancements in material science research particularly around Engineered Living Materials or ELMs have elucidated these shortcomings in our design and engineering workflows. How can we model, simulated, validate, product performance or behavior in this dynamic, temporal environment? We need new processes, workflows, methods, and tools in order to effectively utilize this new dimension of material typologies, as well as continue to design in ways that are more connected to engineering simulation and validation.In this presentation I will explore the use of proceduralism as an essential creation environment that is uniquely able to design in conjunction with these temporal constructs. I will present a subset of my work that utilizes computationally-driven simulations for the creation of physical product, as well as some of my teaching and research through the NSF grant project designing with Engineered Living Materials at the University of Washington.Speaker BioDavid Burpee is a multidisciplinary Computational Design Leader based in the Pacific Northwest, with expertise spanning Footwear, Apparel, Consumer Goods, Automotive, Medical, and Architecture industries. He lectures on Computational Design and Algorithmic Thinking at the University of Washington and is a Computational Researcher on a National Science Foundation grant exploring Engineered Living Materials (ELMs).With over a decade of Computational Design experience, David has delivered advanced design strategy, tools, and training for companies including Nike, PUMA, FILA, General Motors, Harry’s Razors, and EQLZ. His work demonstrates a proven methodology that merges creativity, deep technical capabilities, and broad market impact.Originally trained as an Architectural Designer with a Master of Architecture from USC, David has contributed to highrise and supertall projects in Los Angeles, Seattle, and across Asia. His work integrates computational approaches at every scale, from skyscrapers to small installations.Driven by a passion for biomimicry, generative systems, and sustainable innovation, David applies computational design to address complex ecological and social challenges through creative, high-performance solutions.Join us at CDFAM Barcelona, where the forefront of computational design and advanced manufacturing comes alive. This gathering brings together innovators, researchers, and industry leaders to explore the future of design through simulation, generative tools, and performance-driven workflows. Set in one of Europe’s most dynamic creative hubs, CDFAM Barcelona is the place to connect, learn, and be inspired by what's next in the world of computational fabrication. 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, October 29-30, 2025https://cdfam.com/nyc-2025/Organization:New BalancePresenter:Samuel WhitworthComputational Craft: One Footwear Designer’s Quest To Replace HimselfPresentation AbstractFootwear design, like many design domains, has long been defined by the combination of two-dimensional drawings and designers’ intuition. While these remain important elements of the field, various digital design methods are currently surging and have significantly altered the traditional footwear design process. This presentation will explore the opportunities presented by this shift through the lens of my own experience as an industrial designer turned computational designer—specifically how the application of computational methods has allowed me to expand the types of design solutions I can explore. In this sense, it’s been a journey of “replacing” my traditional industrial design role with a new hybrid role defined by what I call “computational craft.”Computational craft can be defined as a collaborative human/computer design approach, where the computer extends the reach of the human designer, while the human grounds computational results in the real world of manufactured objects and human sensibility. I will demonstrate several examples of this method in Grasshopper, including Kangaroo-based simulations, multi-objective optimization, and mesh generation/manipulation. Audience members will be able to take away new inspiration for using computational methods in their design workflows, and a feeling of confidence that computational design is accessible to anyone regardless of academic or professional background.Speaker BioSamuel Whitworth is a Computational Designer II at New Balance Athletics, where he has contributed to both inline and innovation projects for the past six years (recent releases include the SuperComp Elite v4 and More v5.) Sam focuses on the intersection of footwear geometry and function using scripting, simulation and functional prototyping, leveraging deep skillsets in both Grasshopper and Blender. He holds a Bachelor of Fine Arts in Industrial Design from Brigham Young University. 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

OrganizationEaton + Intact SolutionsPresenter:Karthik Rajan VenkatesanNeel KumarAccelerating Metal-to-Plastic Conversion with AI, Implicit CAD, and Mesh-Free SimulationPresentation AbstractThis work presents a simulation-driven generative design framework for reengineering a metallic explosion-proof enclosure into a lightweight, injection-molded fiber-reinforced plastic alternative. The methodology integrates advanced process and performance simulations with AI-guided optimization to enable rapid, intelligent design iteration.Central to this workflow is the use of implicit CAD modeling in nTop, which allows for highly flexible and parameterized geometry generation, seamlessly integrated with a robust, mesh-free simulation engine from Intact Solutions. This combination eliminates traditional meshing bottlenecks and enables direct evaluation of complex geometries without meshing or format conversion.The workflow is executed in two stages. Stage I establishes baseline using Moldflow for plastic flow simulation, Digimat for fiber orientation mapping, and ABAQUS for traditional FEA, culminating in a stress field point cloud. Stage II transitions to an AI-driven design space exploration loop, where models are trained and evaluated through a Bayesian optimization framework. The implicit CAD models are directly analyzed using Intact.Simulation for Automation without any manual pre-processing, enabling a seamless feedback loop between design and performance while supporting rapid, large-scale design iterations.This approach exemplifies the power of computational design at scale—reducing turnaround time from over 48 hours with traditional CAD and FEA methods to under 1.5 hours with the full AI-driven pipeline with implicit modeling and automated, mesh-free simulation.Speaker BioKarthik Venkatesan is a Lead Engineer in Computational and Digital Product Development at Eaton’s Center for Materials & Manufacturing Innovation in Southfield, Michigan. His work focuses on bridging advanced simulation, AI, and generative design to accelerate the development of next-generation engineered systems. Karthik leads R&D initiatives that span simulation-driven design automation, lightweighting, and digital workflows for both traditional and additive manufacturing (AM) processes.He holds a Ph.D. in Mechanical Engineering from Arizona State University, where he led multiscale modeling efforts for composite materials under DoD- and industry-funded programs. His broader research spans geometry compensation for binder jet AM, performance prediction for polymer extrusion-based AM, virtual design of experiments, and generative AI for material discovery.Karthik is also passionate about computational creativity, with interests spanning astro photography, AI-generated media, and music production 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, October 29-30, 2025https://cdfam.com/nyc-2025/Organization:Alloy EnterprisesPresenter:Ryan O’HaraShaping Flow: Computational Design Strategies for High-Performance Liquid Heat ExchangersPresentation AbstractAt Alloy Enterprises, we combine traditional CAD, implicit geometry modeling, and advanced simulation workflows to engineer high-performance cold plates tailored to the unique thermal and dimensional requirements of each customer. Our approach begins with a curated library of optimized, periodic internal geometries that serve as a foundation for thermal performance and manufacturability. Using computational design tools, we scale and adapt these geometries through parametric controls and implicit modeling techniques, enabling rapid customization across a wide range of form factors. Simulation-driven iteration ensures that each design meets target pressure drop and heat transfer criteria before it reaches the build stage. This integrated workflow allows us to balance design flexibility, performance, and production efficiency in delivering scalable liquid heat exchangers for demanding applications.Speaker BioI am a results-oriented business development leader with over 20 years of DoD acquisition experience. I have extensive experience in advanced manufacturing, aerospace engineering, and federal contracting. I have a proven track record of driving significant revenue growth and securing substantial funding through strategic proposals and federal contracts. With expertise in technical hardware and software sales, I enable cross-functional collaboration in aerospace application development. My technical experience includes transitioning research and development activities from concept to full-scale production, leveraging advanced design and manufacturing concepts. I have demonstrated success in initiating and developing processes, including the certification of materials, equipment, and procedures that comply with aerospace and maritime standards. 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