Manufacturing today benefits from three waves of innovation: new production techniques (like 3-D printing), new design methods (like generative design, also driven by A.I.) and new materials, said Marco Annunziata , Co-Founder of Annunziata.
These three waves of innovation are interdependent and mutually reinforcing: 3-D printing allows us to fabricate any complex object, yielding greater resistance, lighter weight and better performance; Generative Design autonomously produces mechanical designs to satisfy objectives and constraints, where A.I. helps us break free from the mental constraints acquired through decades of traditional manufacturing methods; new materials can in turn broaden the range of possible design solutions.
Generative design tools that produce optimum forms for products and buildings without human intervention are set to transform both the physical world and the role of the designer, according to software experts. The software can automatically make aircraft lighter, buildings stronger and trainers more comfortable – with the designer acting as a “curator”, rather than making all the decisions.
Many designers are experimenting with generative design to produce new forms and improve existing products. Under Armor is taking the lead in using this procedure in the manufacture of more efficient sports shoes. However, other companies such as Airbus and Lightning Motorciyle are receiving assistance from Autodesk to improve efficiency in their products. These processes are proving to save time, increase creativity, save money and, finally, create very efficient geometries.
You—of limited creativity, favoring tradition, the straight and square, clinging to the tried and true with a predilection towards parts that can be machined or molded, etc.—are never going to think of breakthrough designs. Generative design, by comparison, is the free spirit, able to explore the full range of possibility.
Traditional Vs Generative Design
The traditional design starts with a person and a computer and, based on the knowledge of the user and the power of the machine, take advantage of everything together to produce an optimal product. The use of CAD software to model an engineer’s idea is considered explicit design. It is the designer, architect or product inventor who decides what they want the product to look like, and then they explicitly tell the software how to draw it. This drawing is used as the basis for manufacturing.
Alternately, generative design starts with the design intent– what the object is intended to do – and then creates many possible shapes to fulfill that objective. It’s able to do this by linking together the computing power of thousands or even millions of processors in the cloud, coordinated by the software’s unique algorithm.
The product engineer is responsible for inputing the various design parameters or constraints. When making a chair, the designer might say how tall they want the seat height, or how much weight it should bear – whatever is critical to that component.
Using that set of initial rules, the software is free to generate multiple possible solutions to fulfill the conditions. The engineer can then study the mechanical properties of these solutions while also deciding which one looks best or meets some other subjective requirement, which is something the computer can’t do.
The value of this approach is that thousands of iterations can be done much more quickly than any designer could possibly draw them. Even more importantly, when working with advanced materials and sophisticated processes like 3D printing, generative design can crunch the huge computations necessary to calculate the mechanical stresses and thermal loads on complex shapes like lattice structures.
It is characterized by a number of traits:
- Component Focused: Currently, this capability is applied to the design of individual components. In the future, the scope of its application may expand.
- Autonomous Execution: Once initiated, it works autonomously of additional user input. In this way, it operates similarly to a gradient-based structural optimization capability.
- Goal Driven: The decision-making algorithm that MCAD applications use is driven to achieve an explicitly defined goal or implicit objective. Examples might include minimizing deflection under load or total weight.
- Constraint Bound: This decision-making algorithm is also bound by constraints defined by the user. The breadth and depth of constraints can vary from solution to solution. This can include design constraints related to engineering physics, such as peak stress. It can include manufacturing constraints, such as producing geometry that can be pulled from a plastic injection mold.
GENERATIVE DESIGN DECISION-MAKING ALGORITHMS
While running, Generative Design capabilities leverage a decision-making algorithm to determine the shape of the design’s geometry. Today, there is not one such algorithm in use. Instead there are many that vary from solution to solution. These types of algorithms include:
- Topology Optimization: Developed in the mid-1980s, this engineering structure-based algorithm conducts an analysis of an existing piece of user-defined geometry and then removes material not carrying significant loads. This procedure is run progressively, removing material repeatedly over time, ultimately producing a final design.
- Biomimicry: Established more recently, this algorithm mimics behaviors seen in nature, such as replicating growth of bacteria colonies, the growth of roots and branches in trees, or the evolution of bone structures, to optimize weight-to-strength ratios.
- Morphogenesis: This algorithm leverages research on how groups of cells respond to their environment. Cells actively loaded grow stronger. Cells that are not loaded are discarded.
Topology Optimization is considered a Subtractive Generative Design method because it progressively removes material. Biomimicry and Morphogenesis are considered Additive Generative Design methods because they grow or add material to the design.
COMPUTE PLATFORMS FOR GENERATIVE DESIGN
When first introduced, Generative Design capabilities were closely associated with Cloud-Based MCAD applications. However, this technology is now also available with desktop offerings. Note that compute power is an important consideration for this technology.
Cloud platforms offer access to elastic compute resources. Additional cores and storage space can be allocated to Generative Design capabilities. An alternative to such cloud-based resources, however, can be found in high-performance computing on local networks. Generative Design runs on local desktop resources as well. However, as a user requests more designs to be generated, more of a desktop’s compute resources will be required.
Autodesk and NASA Create Interplanetary Lander Using Generative Design
Jet Propulsion Laboratory (JPL) is working with American multinational software corporation, Autodesk, to design an interplanetary lander which is futuristic in appearance but also more energy and cost efficient than previous designs.
They were clear that they weren’t interested in incremental gains: if they were only able to improve performance by 10%, they basically weren’t interested. If we could deliver software tools to help them achieve a performance improvement of 30% or more, then we had their attention. This project demonstrates that Autodesk technologies may deliver mass savings at this level,” says Davis.