Generative design takes an approach towards engineering that we’ve never seen before in the digital realm. It replicates an evolutionary approach to design, considering all of the necessary characteristics. Couple this with high-performance computing and the cloud, and you’re left with capabilities that engineers never thought they would have.
The way in which engineers design is being brought into question with new generative design tools. If you’re an engineer and haven’t seen your workflows altered yet, prepare for the coming future.
The onset of practical artificial intelligence algorithms has enabled the possibility of mainstream generative design tools. That means engineers can create thousands of design options inherent to their digital design and choose which design meets their needs to the fullest. From here, you can solve manufacturability constraints and ultimately build better products.
If you’ve been in the CAD and engineering design space for any period of time, you know that generative design has long been a buzzword of the industry. To the everyday engineer, it might seem like practical usage of the technology is far off in the future and can’t handle be something to concern yourself with. That couldn’t be further from the truth.
Companies like Under Armour, Airbus, Black & Decker, and other massive corporations are embracing generative design as a trend shaping the future of the engineering industry. It allows engineers to hand the reins off to their CAD software to organically find the best solutions to a given set of constraints. It augments the engineer’s imagination.
Through generative design, collaboration with technology can be organic and flowing. It results in ideas that are better than what you could come up with on your own, and products that are lighter and accomplish their directives better. It simply results in better engineers.
With all of that said, let’s escape the showy buzz around the tech and see what’s really possible.
What Can it Do?
Generative design is a tool that uses machine learning to mimic a design approach similar to nature. It interfaces with engineers by allowing input design parameters to problem-solving. If you have loads in certain locations, you need to maintain certain material thicknesses, or even keep certain costs, all that can be fed into generative design tools.
After you press run and let the algorithms do their thing, you’re left with generative designs that meet your input criteria. From there, you can cycle through, pick which design is the most optimized for your design end goals and modify from there. In essence, it takes you down a digital shortcut to optimizing the perfect design.
The advantages of generative design become apparent when you consider just what it takes to get started with any design. You approach problems with a general understanding of what your design needs to do, but you’re left to your own creative devices to find a solution. Instead of starting a design based on the idea you have in your mind, you can start by offloading that data into a computer and allowing it to kickstart the design process.
One of the best examples of how this methodology and thus generative workflows can be practically implemented is by examining how to build a chair. Instead of starting with some sketches, creating various designs, and picking the best one, you can start by feeding a computer some constraints. Input the cost, the weight it needs to support, and what material you’d like your chair made out of. Then the computer can deliver thousands of design options that take into account manufacturability for you to select from. This is what generative design offers to the modern engineer.
Refining Generative Further
True generative design is software that uses the power of cloud computing and true machine learning to provide sets of solutions to the engineer. This is in stark contrast to tools we’ve seen before, such as topology optimization, latticing, or other similar CAD tools. All of these previous tools improve existing designs, whereas generative creates a new design.
Generative design is also different from other existing CAD tools in that it can consider manufacturability. If you’ve ever used tools like topology optimization or other fancy “generative” tools, you’ve probably been left with an end product that looks cool on paper but isn’t easily manufacturable in the real world.
Coupled with this account for manufacturability, true generative design takes into account simulation throughout the entire design process. On the front end, that means taking into account your manufacturing method, and the software will take care of simulating a given design’s feasibility. This only yields designs that meet the necessary simulated criteria and are manufacturable.
Generative Design in the Real World
Generative design is a new tool at the forefront of engineering tech, but companies are already taking full advantage of what’s in front of them. Notably, Airbus used generative design to redesign partitions in their aircraft. The result was impactful lightweighting that cut 45% of the weight of the part.
Generative design tools have also been used to design things that traditionally wouldn’t be thought of as product design. Architects have used the tool to create the best possible office design new building in Toronto. The algorithms factored in employees' wants and needs, and even their preferences on where they work.
The generative tools laid out 10,000 options for the space and architects sorted through to find the best option. It’s the ultimate melding of computer-human design.
Examples of generative design being used in this way are becoming more common, and this tool is being further integrated into our workflows as engineers. The way products are made and engineered is continually being augmented by programs that will shape our future. The future of making things is moving forward at a blistering pace.