if you pool enough computing horsepower, your network is capable of completing many iterations of very complex tasks very quickly. Questions about the potential for many designs used to be fairly straightforward. Design teams have a finite amount of time and money at their disposal, and can’t afford to prototype more than a few designs—let alone thousands.
But what are these constraints costing you, in terms of the ideas that never get tested and the solutions that never get prototyped? Are there unexplored methods of building your product that might be lighter, faster or cheaper?
“There’s really not one solution for every problem; there are many. This is where the power of parallel computing is going to help us test more ideas and look at more concepts in a shorter *period of time.
The “secret sauce” is an AI platform that has been “trained” to create solutions to engineering problems. Unlike human engineers—who first design a solution, then determine how to build it, then prototype and test its properties—generative design is capable of carrying out all three of those steps simultaneously.
The process requires human engineers to define the problem by using CAD systems to lay out basic specifications for the component that needs to be designed. “You don’t start with the geometry. You start where it attaches to other components and how.”
After that, engineers further refine the design parameters, specifying load requirements, deflection, rigidity, material preferences, cost of production, weight requirements and even manufacturing methods, attention to detail is critical during the process of defining problem.
“If you input junk you’re going to get back junk, essentially. “But if you actually specify the requirements early and set up to solve the right problems, that’s when you’ll see the benefits of the tools.
“So then, we can push the magic button, hit generate and send it to processing, and it will give you a bunch of different answers.
Working its way through the predefined parameters of the problem, the AI platform solves it over and over, employing a new approach each time. the program sketches out new CAD designs, tests them in simulations and learns from its mistakes and successes.
What results is a collection of hundreds, even thousands, of computer-generated designs, catalogued by the degree to which they meet various criteria. Some designs bear similarities to the components they’re intended to replace, while others look like nothing that’s ever been manufactured before.
“You can even watch as it solves it over and over and over, right in front of you,”
“The bone-like, geometry takes some getting used to. It would have been a nightmare manually modeling this from scratch. “Once you see it, though, it’s impressive, and there’s nothing like it out there in the market. After it has generated solutions for a problem, generative design tool performance tests them in simulations for buckling, fatigue and failure points. It can even account for the wear and tear of specific manufacturing processes.
Faced with a nearly unlimited supply of generative design solutions, engineers will have the responsibility of sorting through the performance characteristics and combining top-performing features from various designs to meet the specific needs of the product in question.
“Using VR, you can start to move and articulate these things, re-shaping your design in real time. “When you’re able to see how a component fits into things on a one-to-one scale in real life, it’s always better.”
Ultimately, engineering is about problem-solving, and the more data engineers have to work with, the more money they can save, the faster they can get to production and the lighter or stronger they can build a component. With generative design and the power of new AI tools, design teams will be able to tap into a data trove that’s deeper than any they’ve seen before.
“There’s really no one solution to any problem. “There are tons of right solutions, and we want the engineer and designer to get the information they need to make better decisions earlier in the design process.”
Generative design takes an approach to engineering that we’ve never seen before in the digital realm. It replicates an changing approach to design, considering all of the necessary characteristics. Couple this with high-performance computing and AI, 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 AI tools 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.
It allows engineers to hand the reins off to their CAD tools to organically find the best solutions to a given set of constraints. 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.
Generative design is a tool that uses machine learning to mimic a design approach similar to designs in the real world. 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 tools 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 optimised for your design end goals and modify from there. In essence, it takes you down a digital shortcut to optimising 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 computing tools 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 flight cockpit. 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 cockpit to 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.
True generative design tools use the power of machine learning to provide sets of solutions to the engineer. This is in stark contrast to tools we’ve seen before, such as topology optimisation, 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 optimisation, you’ve probably been left with an end product that looks great 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 tools will take care of simulating a given design’s feasibility. This only yields designs that meet necessary simulated criteria and is manufacturable.
Computers that creatively come up with ideas on their own are the heart of generative design. In generative design, you share your goal with the computer, tell it what you want to achieve, as well as the constraints involved, and the computer actually explores the solution space to find and create ideas that you would never think of on your own.
Project that lets designers describe the forces that act on an object and then lets computers go off and make it. These forces can be structural loads or even manufacturing methods. You start by sharing the goal with the computer, telling it not what you want it to do, but what you are trying to achieve. You describe your well-stated problem, and then, using generative methods, the computer creates a large set of potential solutions, automatically putting them together.
But here’s the key: In the time it would have taken you to do just one design, the machine has done all of them. Its design proposals are delivered back to you in an explore tool, and you can then start steering through the various designs and understanding the tradeoffs between various solutions. This process may enable you to find something interesting, helping you redefine the problem so you can repeat the loop, but, ultimately, you’re going to select one of the computer’s designs to fabricate.
Good results and bad results that have a lesson in them all disappear, and the computer treats the next question as if it had never seen anything like it before. But what if there were a machine-learning system in the loop so that every time you analyzed something for its aerodynamics, the computer got an impression of the connection between cause and effect? What would the results be if that happened over and over again?
Eventually, you won’t need a deep analysis to arrive at an opinion, because you will have deep-learning system that can tell you its hunch. It can always ask if you want a more serious investigation, based on tried-and-true analysis code.
Engineers like having that second opinion available, but you can be satisfied with the quicker one sooner: an basic understanding what aerodynamics means. Then you can show the computer a brand-new thing it had never seen before, and it could give me an opinion about whether or not it was aerodynamic.
it’s remarkable that computers are going to start having opinions. But here’s the really interesting part: Imagine if the computer were doing this in its off hours. What if it were generating new forms on its own, putting them through analyses, and seeing the relationship of cause and effect? The systems that understand those linkages will start getting hunches about things that a company is working on.
Pretty much every company offering new tools is exploring the potential of generative design , and they all have really pretty pictures of prototypes that have been designed with their various tool packages. But is there more to the technology than fancy prototyping? When are we going to see these products appearing on our shelves? Is generative design even suited to mass production?
After all, generative design has been enabled by the growth of additive manufacturing, which currently still has a long way to go before reaching production run levels equal to those of the traditional manufacturing techniques used in mass production.
Additive manufacturing has been a powerful driver behind the recent surge of interest in generative design, and given that additive manufacturing is not exactly well suited for mass production yet , you could be forgiven for thinking that generative design’s dependency on additive manufacturing is hindering the breakout of these products into mass production.
“Physics-driven design can be tailored to produce designs that can be made with traditional manufacturing techniques, such as extrusion, forging, casting, etc.,” “While often not as optimal as designs driven without traditional manufacturing constraints, the unit costs can make optimisation viable for lower cost/higher production run components.
“We are seeing this already and have been driven by customers to enhance tool capabilities so that techniques like casting, extrusion, etc., are viable alternatives for a physics-driven optimal design.”
So, it’s clearly not a case of traditional manufacturing not being up to the job. It seems to be a case of how you adapt the generative design tools to be used with traditional manufacturing techniques. After all, if you use less material and still manage to reduce the number of tooling operations, the unit cost will still be reduced. Generative design is providing designers with new ways of looking at old problems.
New generative design tools are leading to productivity gains and higher-performing designs, and some technology only recently become available, so we haven’t yet seen many examples of commercial products. However, we believe customers are well underway in adding and benefiting from generative design in their product development workflows.”
What is it going to take for designers to migrate these designs from prototypes into actual large-scale production? There are technological hurdles to overcome first.
“The outputs of generative design tools, at first glance, can be unusual and non-intuitive to engineers accustomed to more traditional-looking design. But our customers are beginning to appreciate that the technology allows them to explorer huge amounts of practical, manufacturable solutions by simply specifying the engineering problem they aim to solve unlike traditional tools such as topology optimisation that merely enable incremental improvements to traditional designs.
We are observing that once engineers have performed comprehensive validation using traditional simulation tools, they build trust in the outputs of generative design. This growing trust along with an increasing rate of adoption and ever-decreasing costs of advanced manufacturing techniques means that generatively designed parts will soon be in production. We’ll also see an increase in production parts created generatively once our technology starts creating designs suited to traditional, lower-cost manufacturing processes.”
So, we are seeing some sort of consensus among the CAD people—lowered costs in manufacturing will enable the move from expensive prototypes into cheap mass production. And slowly but surely, engineers and consumers are becoming accustomed to the strange new forms that generative design allows.
Therefore, which industries will be the first to bring these generative-designed parts to market?
“The adoption of generative tool design is happening most quickly in industry segments where a premium is put on high-performance and uniqueness of designs. the most practical cost benefits are realised when multiple parts are consolidated into one unique and original component. Part consolidation simplifies the customers’ supply chain and reduces downstream assembly costs.”
Generally speaking, when we think of parts being consolidated like this, we tend to be speaking of parts manufactured with additive manufacturing. The printing of multiple parts at one time means a reduction in assembly time, inventory and fastenings. But is the growth in generative design driven exclusively by additive manufacturing? This was definitely the case in the beginning, this is no longer necessarily the case.
Generative design tools produce geometrically complex designs that are manufacturable and practical with additive manufacturing. “With every passing year, additive manufacturing is becoming more mainstream and accessible as costs come down and more materials are supported. And, as we expand to producing designs that are suited to processes like machining, casting, etc., we will enable more and more customers to mass produce their generatively designed products.
“Generative design is inherently about understanding requirements, from performance to materials to manufacturing processes, and providing engineers with a variety of practical, manufacturable options to make informed trade-offs between time to market, cost and performance. “Ultimately, our goal is to enable designers and engineers to produce more, better, with less—more new ideas, products that better meet the needs of users, in less time and with less negative impact on the environment. generative design will not be tied to one manufacturing method in the future.
That’s good news for traditional manufacturers. Generative design is not just for those with high-end metal printers, but for anybody with a CNC-enabled workshop and access to generative-designed tools.
“As soon as generative design starts creating designs that are suited to multiple manufacturing methods, we expect mainstream adoption to grow rapidly. “We also see large potential in industries where high-value, low-volume products are produced, , such as those in aerospace.
“What you’re seeing with 3D printing is they prefer to take traditional manufacturing out and put 3D printing in without changing anything around that, and this approach isn’t going to work. These new technologies will only be allowed to work if you allow the context around it to also adapt, and it’s not as simple as people want it to be sometimes. It may take a little bit of time.
There are multiple reasons for low production adoption working at the same time. One is the time frame we are working at with the development of designs and the construction of large aerospace products. If we have an idea now, you will only see that built on-site in say several years.
We work in a complex value chain where no one has complete control over the final results, so it is a lot of different people and a lot of different companies that have to move at the same time or at least following in a series, and what you see in these processes is that they all start with great ideas and throughout the years and the phases they become victim to planning pressure and costs so a lot of new ideas and challenges are just designed out.
“So, its not to do with 3D printing not manifesting itself—more it is to do with change being difficult to establish because change is difficult, change might be costly, and change has to always be better in every single way than what we have now—and that is something that is very difficult to foresee and to guarantee, so it’s little steps.”
Its less to do with how the parts look and more to do with how they perform and at what investment. For each application, we will evaluate cost and performance benefits as compared to a more traditional manufacturing process.
We may choose to invest more to 3D print a part if the added value in terms of performance merits the additional cost. If a traditional manufacturing process is less expensive than 3D printing and there is not a substantial performance benefit, then traditional manufacturing processes will be used.”
Great potential for generative design combined with additive manufacturing processes to enable part designs that are lightweight with the performance criteria we expect. Metal 3D printing costs are still relatively high in comparison to traditional manufacturing methods.
“Generative design can be used to design parts for some traditional processes. For example, casting processes could be used to manufacture some of the generatively designed parts.” Additive manufacturing is about to become even more critical to manufacturers in highly competitive industries thanks to generative design capabilities.
Generative design leverages tools based on previous design knowledge and high-performance computing to autonomously generate or modify design geometry based on requirements for or constraints on product performance.
Using generative design, engineers specify parameters, such as weight-to-strength ratios, efficient material use, and temperature, pressure and force ranges. The generative design engine creates sever design options through an iterative. Engineers then evaluate and select from among the generatively designed options—more options than would be humanly possible with traditional design tools, and likely many options that the engineers would never have considered.
Together, generative design and the additive manufacturing processes give engineers powerful tools that speed prototype, and finished part and tooling development and production; as well as parts with unique characteristics or functionality.
Both generative design and the 3D printing process make possible entirely new geometries and topologies, including more organic designs than ever could be realised with traditional manufacturing. Many shapes coming from generative design are difficult or impossible to produce using traditional methods, while additive manufacturing processes can directly print these shapes.
In addition, by pairing generative design with additive manufacturing, companies can build products with optimum functionality. For example, many parts for aerospace industry require materials that are heat resistant, which are expensive.
Additive manufacturing processes, when paired with generative design, will become even more critical as design and production processes compress to meet customer demands for faster delivery of more complex, often customised products at lower cost.
The power of generative design and additive manufacturing processes is compounded when adopted as part of an end-to-end product lifecycle management strategy that integrates design, engineering, manufacturing and maintenance through unified solutions and data.
Manufacturers must frequently and quickly deliver new and innovative designs of complex products, such as those in aerospace, industrial machinery and heavy equipment, and make sure you are moving quickly to adopt them.
Generative design both uses and adds to product knowledge in the digital thread, as simulation results are stored, ready to be applied to optimise future designs. Generative design, Convergent Modeling and additive manufacturing have become critical tools that support digital and team-driven workflow.
1. Increased Customer Satisfaction
Being able to generate multiple designs at a faster pace means more satisfied customers. Since the delivered designs are also of higher quality and meet all the customer’s requirements, it is a great way to increase customer loyalty and build an solid reputation.
2. Large amounts of Design Concepts at the Touch of a Button
Thanks to powerful artificial intelligence tools, designers no longer need to think up designs the old-fashioned way. For example, when designing a coffee mug for a fighter jet, the designer can input desired parameters such as the weight, material, and volume and the tool will deliver all possible designs that meet those criteria.
3. Rapid Approach to an Optimal Solution
Since more designs can be created within a shorter time frame, the optimal design solution can also be found quickly. This is because designers can compare and contrast all the different designs generated by the tool before selecting the best one.
4. Customised Constraints
Using the designer’s inputs and artificial intelligence, the latest design tools can produce highly customised build plans based on preset parameters. After the initial design is produced, engineers can then adjust the tool creating different designs that satisfy certain criteria such as the build size and cost.
5. Increased Productivity
An increase in productivity is to be expected as a result of the many design variants available at the touch of a button. Instead of taking precious time to come up with the various possibilities of a design, designers can use this time on other projects.
6. Consolidation of Multiple Parts
The ability to consolidate multiple parts into a single part is another benefit of generative design. This is because highly complex information can be processed at a rate that is not possible for workers. As a result, a single part can now be created to replace assemblies of two or more separate parts.
7. Decreased Manufacturing Costs
Due to the consolidation of multiple parts into a single part, decreased manufacturing costs can be expected because the supply chain will be simplified due to the elimination of unnecessary parts, reducing the overall manufacturing cost of the product.
8. Reduced Material Consumption
This is another benefit resulting from the consolidation of multiple parts. By creating models that require fewer parts, less materials are also required. This helps reduce material costs.
9. Avoids Expensive Manufacturing Rework
Manufacturing rework is a costly process that can reduce production output significantly. Rework requires extra time and energy to coordinate and complete. With the help of simulation and built-in testing functions, most rework can be eliminated and a final design can be reached within a shorter amount of time.
10. Reduced Weight
Reducing the weight of manufactured parts is another benefit and a real game changer for aerospace industries. In one recent case, engineers used generative design to produce a new bracket that combined many components into one, resulted in large weight reduction and strength increase compared to the original design.