GE and partners at the Oak Ridge National Laboratory and Xerox-owned PARC have been granted over $1.3 million through ARPA-E’s DIFFERENTIATE program. The funding will enable the partners to pursue a research project aimed at reducing design and validation timelines for additive manufacturing by as much as 65%. If successful, the project could influence the adoption of industrial 3D printing technologies for energy systems, as it would effectively make AM faster than many traditional manufacturing processes.
The DIFFERENTIATE program (Design Intelligence Fostering Formidable Energy Reduction and Enabling Novel Totally Impactful Advanced Technology Enhancements) is aimed at supporting the work of energy engineers to develop next-gen (and more sustainable) energy technologies. GE and its partners have received a grant through the program for their work aimed at improving the energy efficiency of 3D printing for turbomachinery components.
Today, it takes an extraordinary amount of effort and resources to design new components for complex power products like wind turbines, jet engines and gas turbines using AM. The workflow involves many experts and comes with many considerations about structural, thermal and fluid properties, among others. Overall, it can take between 2 and 5 years to design, develop and validate a new energy component using AM.
Understandably, GE, ORNL and PARC want to speed this process up significantly. Working together, the partners are developing a way to accelerate the AM design and design validation process for turbomachinery components. The goal, they say, is to make AM faster than traditional casting.
“One of the keys to enabling the widespread use and benefits of 3D printing is the reduction of the time it takes to create and validate defect-free 3D component designs,” explained Brent Brunell, leader of GE Research’s Additive efforts. “Using multi-physics enabled tools and AI, we think we can beat the timeline for some traditional manufacturing processes by automating the entire process.”
How will the partners speed up the AM process for energy components? One key aspect of the work is centered on automating the optimization of thermal and fluid properties. GE and PARC researchers are reportedly working on integrating thermal and fluid properties with structural characteristic optimization using artificial intelligence (AI), which can generate surrogate models from additive producibility data and combine it with multi-physics design optimization techniques.
The research will rely on the use of ORNL’s Summit supercomputer, which will enable the generation of AI-based surrogates. ORNL will also provide access to its High Flux Isotope Reactor, which will be used to analyze 3D printed parts and generate data for training and evaluating the AI-based models.
“This is the type of project that leverages the unique capabilities at ORNL—experimental and computational facilities—as well as expertise in computational science and additive manufacturing,” said John Turner, Computational Engineering Program Director at ORNL.
Ultimately, the project aims to deliver a demonstration of a defect-free, high-performance 3D printed multi-functional design that is able to withstand high temperatures and stresses and is superior in performance to a casted component.
“The combination of model-based and data-driven AI to accelerate generative design is a key innovation that will dramatically reduce the time to synthesize and fabricate quality parts,” added Saigopal Nelaturi, Manager of Computation for Automation in Systems Engineering area in the System Sciences Lab at PARC. “Surrogate models (built using machine learning) that encapsulate complex couplings between process physics and part quality will help guide the optimization models in feasible regions of very high dimensional design spaces. This combination of AI techniques enables automatic multi-functional part synthesis to meet real-world application demands, for which AM can provide truly novel solutions.”