AI-based generative design is no replacement for a product designer or engineer. Instead, think of it more as a right-hand man — or better put, a right-hand team — with countless hours to spend on each task. It allows designers the means to explore options far more exhaustively than they otherwise ever could, make effective decisions more quickly and earlier in the process, and eventually implement a design — from concept all the way to manufacturing.
Workshop is a vehicle for exploring, testing, and proving an AI-driven tool to generate physical designs. Implementing a divergent design flow, Workshop builds off the traditional flow: define, create, explore visualize, analyze and fabricate. Where that flow departs from the norm is in who — or rather, what — is performing or assisting in those development stages, and the extent of that assistance.
With Workshop, engineers and designers specify design goals, along with parameters such as mass, volume, and engineering constraints, as well as materials and manufacturing processes available for production.
All that data gets crunched by AI deep computational networks to create a model it concludes is the optimal balance of the given constraints. More typically, the network will generate many versions, creating tens, hundreds, or even thousands of variants, all of which balance those constraints in slightly different ways.
The computational network proposes options, along with the data to indicate how well that option meets various goals and constraints, but the designer remains the guide of that process, making the key decisions and tradeoffs. Effectively, you tell your team what you’re trying to accomplish and what the limitations are, and that team reports back, “You said you wanted to do this, so here’s the avenue you should probably pursue.”
Workshop delivers that ability for a designer to set objectives and constraints, include limits on geometry, material type and amount, and production methods. With generative design at the fingertips, a designer can then quickly create and integrate hundreds of options, each presenting a different degree of adherence to the constraints given.
This raises a great question: How can the user avoid being overwhelmed by a potentially large number of similar-looking designs, and instead focus effectively on the one or few best suited to the set goals and priorities?
To make all those generative design results easier to consume, Workshop includes filters that let you sort designs using the most relevant and important info up front. Filters let you navigate, compare, and contrast the tens or hundreds of options by the degree to which those designs meet the goals and constraints. Filter by strength, mass, cost, manufacturing type, or stiffness, for example, to narrow in on and eventually identify the best option to pursue.
Arriving at the right model, or at least the best one to explore first, shouldn’t end at creating a conceptual, stand-alone structural representation. Rather, the key is to also allow the means to bridge the gap from that machine-generated model to engineering verification and styling, and eventually on to getting it manufactured.
Some simple outputs are of limited value; it yields an interesting shape, but one that can’t serve any use beyond the visual. A productive workflow needs that geometry embedded with all the rich data sets needed to directly feed into simulation, verification, rendering, and on to prototype and manufacturing.
If the machine integration produced just a shell of geometry, the designer might have to re-create the whole thing manually. Bridging the gap from synthesis to the rest of the workflow was a key design goal for Workshop generative design functionality, and its implementation is unique in the way it automates the integrated design in a complete, usable, and editable format ready for verification, re-design, and ultimately, physical creation.
A generative design–based workflow should seamlessly culminate in a manufacturable model, be it for prototype or volume production. Workshop generative design considers the constraints and capabilities of the manufacturing process and materials available.
The model is particularly relevant in the context of additive methods like 3D printing, especially now given recent advancements in printing with metal. Such methods allow for shapes and structure that conventional manufacturing methods can’t achieve, making it essential for the user to provide generative design guidance on which methods are available or preferred.
But you can’t ask or expect end users to navigate the appropriate performance, features, virtual machine types, or determine when use cases might best for generative design or any other workloads headed to execution space.
As you might guess, Workshop hides the processing wizard behind the curtain so the user doesn’t have to be concerned with how it gets done. Based on the model and constraints, Workshop assesses the workload at hand, “right-sizes” it to the appropriate machine instances, and when complete, hands it back to you inside the application.
Over time, machine learning will permeate virtually every corner of computing technology and applications. Of that, the majority of us have little doubt. In design computing, uses have already popped up to significantly improve the performance of existing 3D graphics and rendering that professionals require. But most certainly, these uses represent but the tip of the iceberg, and the real impact will come in more revolutionary applications.
The demands and workloads product design represent make it fertile ground for AI infiltration. Expect machine learning advancements to both leverage and transform the existing tried-and-true design/verify/iterate/manufacture workflow.
Most of the possibilities we’ve likely not yet imagined, but the same would likely have been said ten years ago for generative design, an approach that offers compelling, undeniable appeal. Combine that with its natural pairing with virtual workstations, and we should see momentum increase for both approaches.
It’s time to pay close attention to what AI offers for product design computing — assisting in design creation itself, leveraging the technology to streamline workflows, improving end products, cutting costs, and shortening time to markets. Your competition likely has.
New developments in generative design can help companies make better decisions about part design by including manufacturability as a key value. Milling, for example, not an additive process, might come up as the better choice for making a complex part.
New generative design applications enables engineers to see results that meet requirements for strength, mass and other properties, including manufacturability. In this case, the design for a lander leg was limited to possibilities producible on a five-axis machining center.
The latest generation of generative design technology includes new ways to set design boundaries and to constrain the algorithms to more quickly identify designs meeting predetermined manufacturability requirements, including requirements defining particular manufacturing processes.
More than just a geometry modeling tool, generative design has become a manufacturing process selection tool as well, along with a tool for making best use of various manufacturing processes available.
Generative design is less and less a tool strictly associated with additive manufacturing. Multi-axis machining might be the best choice, as it turns out, even for a very elaborate part, when certain constraints are in place.
But what is “generative design”? Generative design is a relatively new approach that uses machine intelligence algorithms that solve problems the way the human brain does but much faster and more powerful network computing to generate a broad set of design possibilities that fit within the performance requirements set by engineers.
With generative design technology, users can simultaneously generate and explore hundreds or even thousands of manufacturing-ready solutions based on product constraints and requirements such as strength, cost and materials. Manufacturers can leverage real-time performance data and smart manufacturing processes to accelerate the delivery of innovative new products to market.
Rapidly evaluating thousands of design possibilities yields more than the optimum ones to consider. It also sparks engineers imagination. Users are reporting that applying the application helps them “come up with something we hadn’t thought of,” including ideas for new additive-manufacturing technology and the practical capabilities of existing, at-hand technology such as machining.
Generative design applications includes new capabilities that sort through design possibilities that reflect manufacturability considerations. This enables engineers to compare how different manufacturing processes influence how easily, quickly and cost-effectively components can be produced.
Formerly, generative design applications most often pointed to possibilities that were producible only by means of additive manufacturing processes, because the resulting organic, nature-like forms that were commonly created did not lend themselves well to processes such as machining, casting or fabrication.
By applying constraints that sort design possibilities according to limits that favor selected processes, design options can be evaluated in a new light. The results can be surprising and significant in terms of the importance of generative design applications as a decision-making tool.
A custom version of the generative design applcation was developed to solve for multiple manufacturing constraints at once. The goal was to design lightweight components that could meet the car’s aerodynamic performance requirements yet be producible with existing subtractive manufacturing equipment such as a machining center. One test part, an aluminum lower wishbone suspension arm, exemplified the potential for applying manufacturability constraints in generative-design studies.
Generative design’s strong association with 3D printing or additive manufacturing will give way to a broader appreciation of it as a tool to discern the value of other manufacturing processes. A key benefit of generative design, over and above improvements in component performance characteristics, is how rapidly new designs can be iterated.
Generative design enables manufacturers to make trade-off decisions that balance market requirements, product capabilities and considerations for cost, quality and manufacturers can arrive at these decisions working in a unified, integrated platform that includes a 3D mechanical design and simulation application.
Using generative design technology, the engineers can stipulate manufacturing processes, define design requirements and materials, and then leverage the power of computing. Clearly, generative design should not be of interest primarily to manufacturers with a strictly additive mindset. As manufacturers acquire new options for making parts, they must also acquire the means to make the best decisions about applying these options.
Finally, a Metal Additive Manufacturing System That’s Built for Production
For more than a century, weight reduction for automotive parts—when sought at all—has been an incremental process. Lightweighting a single part by 40 percent is unheard of. The same can be said for consolidating the bracket’s eight assembly components into one piece. 3D-printed engine fuel nozzles are the most famous example of an assembly consolidation made possible by AM.
Success is achieved not only through faster printers, but through a reimagined digital workflow. It’s possible the time its engineers perfect a new process flow between generative design, setup for additive manufacturing and simulation testing—a process being refining right now- the value proposition and throughput capacity for metal AM will enable mass production.
It’s only a matter of time before generative design and additive manufacturing are the primary technologies driving these lightweighting efforts. Using the seat bracket as an example, by tradition we would start with the last version’s model, maybe tweak it a little bit and come up with two or three design iterations. We might achieve a five percent mass saving and make it a little stronger.”
But generative design entails a different kind of approach. It involves not modeling geometry directly, but setting inputs around constraints so application can propose the geometry. This starts with the “hard points” for the bracket design, the regions of the part where material is necessary and needs to conform to specific requirements. “Areas where the bracket attaches to the floor, for instance, or where the seat buckle attaches to the bracket. “So you set those hard points and say, ‘we have to have material here, in this shape, on the entire side, and that attachment point has to be this big.’”
Static load requirements are then programmed where those hard points attach to other parts or assemblies. Engineers then input data for the surrounding components, such as the floor, the seat and the plastic trim bezel that covers part of the bracket. These are the keep-out zones, the areas where the application knows that material is not allowed. Finally, designers input data regarding the additive setup itself, primarily around build orientation, support structures, and any extra material that might be needed to enable postprocessing such as five-axis machining.
Throughout all of these steps, engineers can manipulate materials to test for performance across each new iteration. “You're not getting rid of the engineer in this process. “What you're doing is giving the engineer a broader design space and more options to consider. In the traditional design scenario, maybe we iterate from the last version of that seat bracket and maybe we get two or three different iterations to choose from.
Using generative design for the seat bracket, we asked ourselves what the most important criteria was. We could’ve chosen stiffness, but we said our number one priority is to get the lowest mass that we could test in our simulation model—because it’s got to still pass our requirements when we run into through crash simulations and other tests.”.
“What we’re doing now is taking example designs and running these designs through a new workflow. So we set up the generative part, create the first generative outcome, then we optimize this outcome for an additive manufacturing process. We then take that back and run nonlinear or crash simulations on these parts.”
“We don't have to speculate. “It is already there. The only thing holding us back, at least for the most part, is the efficiency of the process to get there. Until now the design and simulation processes have taken a long time.
They have involved a lot of manual work by the engineer. While additive is still evolving, the application needs to adapt and shape the process. But we're engineers. We can do it.”
1. “How long have you been using the application?”
2. “How often do you access the application?”
3. “When accessed, how much time do you spend in the application?”
4. “How are you using the application during deployments?”
5. “What features of the application do you routinely use?”
6. “How do you rate usability/accessibility of the application?”
7. “What reports do you routinely use in the application?”
8. “Do you still need to produce local reports with the application?”
9. “Have you ever used the application to brief readiness from site?”
10.“Would you say the application saves you time?”