Generative Design: A Faster Approach to Design

Imagine you lead a discrete manufacturer, perhaps a company whose products need weeks of lead time to manufacture or one that finds itself facing new customer demands and rejuvenated competitors. You know innovation must be part of your strategy.

Here’s the question: what are you doing to make that all-important innovation more likely?

One idea - bring artificial intelligence (AI) to bear on your product design process with generative design software and use is not just as a tool, but also as an approach. 

Your product designers construct a ‘study’ – that is, they define the problem they want to solve, using the language of design constraints, loads, materials, and manufacturing methods. The software then studies that problem, doing countless iterations, and returns an optimum set of solutions to the product designers, who then choose which ones they wish to refine. Remember, each of those solutions meets requirements, with countless iterations resulting in solutions the design team could not have devised in the time they had and might never have thought of.

A design for a bracket on an office chair before (left) and after using generative design (middle).  The right-most image shows the part in the context of the chair assembly.

From a strategic point of view, the result can be better, high-quality designs that get to market faster with efficient material usage and a positive impact on cost of goods sold (COGS).

Cummins, the world’s leader in diesel and natural gas engines, power generation equipment, and related products, used generative to reduce the material in parts by 10-15%. This helped them meet both cost and sustainability targets.

The generative design story gets better because the software’s purpose is to iterate faster than human beings could possibly do and to do it without bias.

What Makes Generative Design in Creo More Reliable?

It’s no secret that generative design and the closely related Topology Optimization tools have been available for several versions in Creo. Four aspects, however, mean that a workflow with generative design can be more reliable than traditional CAD workflows.

You’re building requirements into the design. All products start with requirements. These requirements could be driven by system engineering models tied into the product’s requirements and managed in PLM, as is possible in Creo. Or you can use requirements you’ve validated yourself in the course of earlier design work. The point is that with generative design, applying requirements to your model is part of setting up your study. Again, every solution that study returns will meet those requirements.

The manufacturing method informs the design. Typically you’d design your part, validate it using simulation and analysis tools, probably do more design work, and then turn the part over to the process engineer for the first of several rounds of feedback before the design was finalized.

Using generative design saves time because you add manufacturing criteria to your study. This ensures you’ve gotten the design off to the best possible start before you call in your colleague’s valuable, specialized expertise.

These include:

• A build direction for parts that will be 3D printed.
• A parting line for parts that will be cast or molded.
• A linear extrude for parts that will be extruded or machined

You generate multiple concepts quickly. Think back to how you handle the initial design phase. Maybe a handful of concepts? If you’re like most professionals, you’re also going to go back to what your hard-won experience shows you is likely to work. With generative design, the software iterates far faster than humans can - and without bias. Now your professional judgment goes in to setting up that well-conceived study.

You can modify the resulting model in the Creo design environment. The part model that generative design creates produces B-rep (boundary representation) geometry.  Work on it in Creo just as you would any of your models.

The Generative Design Workflow

Set up a study in minutes. The general process is this:

1. Define load cases. These represent the operating environments that your model must survive.
2. Specify design goals. This could be a target safety factor or a minimum fundamental frequency.
3. Add constraints. These include the manufacturing constraints as well as geometry constraints like symmetry and factors to create thinner or thicker regions and reduce webs.
4. Select materials. Creo currently allows up to 10 materials per design criterion, and a study can contain many design criteria.
5. Run the optimization on the desktop before pushing an array of studies to the cloud. Apply the study settings to control the time and resources used.
6. Run the optimization.
7. View the results.
8. Select the design(s) you want and keep working in Creo.

Can Generative Design Help You?

We’re the first to say that no software can guarantee innovation, but generative design is a proven approach that can help you bring better products to market faster and at less cost. If you want to explore what’s possible, visit the Generative Design page today.