Feb. 06, 2023
Researchers at the Georgia Tech Research Institute (GTRI) are using additive manufacturing techniques to create unique waveguide structures that would be difficult or impossible to make using conventional fabrication processes. The new techniques are especially useful for integrating updated components into equipment that might otherwise require significant design changes.
In high-powered millimeter wave and microwave radars and antennas, waveguides direct electromagnetic energy from one component to another inside the equipment. Until recently, the waveguides had been fabricated from extruded copper or aluminum tubing, but these traditional manufacturing techniques can’t always accommodate the complex configurations needed for optimal design with minimal energy transmission losses.
“To propagate electromagnetic waves efficiently, the waveguide must have a very precise internal geometry,” explained GTRI Senior Research Engineer Kyle Azevedo. “Yet, the waveguide must also be very smooth in terms of its internal surface finish. The cavity that transmits the energy has to be very well controlled to avoid significant losses. And the waveguides must also fit into confined spaces.”
Additive Techniques Offer Specific RF Advantages
To allow more complex designs, GTRI researchers are evaluating two alternative fabrication techniques: 3D-printed structures fabricated from metal and 3D-printed polymer components that are metal coated. Each has advantages and disadvantages and must be chosen for the specific application. The researchers are testing waveguides made using both techniques for mechanical performance in resisting fatigue damage, thermal performance in dissipating heat, electrical performance – and their RF energy loss.
Flexibility afforded by additive techniques can help designers accommodate waveguides within a crowded design that includes many other components. In one current project, the researchers found that they needed to move a radar’s feed horn several inches to accommodate other design considerations. But that complicated the waveguide design.
“That was a really big challenge, because we had to change some of the existing waveguides, and we couldn’t do that with traditional tubing pieces that were available without coming up with a whole new design,” Azevedo said. “But by using additive processes that allow more customization, we were able to make things smaller and optimize the design in a single iteration.”
In another project – in consideration for use on Army counter-battery radar – researchers at U.S. Army DEVCOM C5ISR Center used additive techniques to accommodate an updated component of a different size and shape than the original to improve RF performance. The researchers designed a 3D-printed waveguide that accommodated the existing connectors and integrated into its legacy systems, then worked with the Army’s Rock Island Arsenal to optimize fabrication and quality control. That new component was successfully tested at Tobyhanna Army Depot and Yuma Proving Ground, and is now being evaluated as an OEM alternative. This may allow additive manufacturing to augment the supply system.
In addition to facilitating designs that might otherwise have been more challenging, the GTRI researchers expect additive manufacturing will allow them to accelerate the iterative development of prototypes by moving some waveguide fabrication in-house.
Overcoming Challenges with New Fabrication Methods
For all-metal waveguides, additive manufacturing can have some disadvantages, but those may not be as significant as they might first appear. To limit transmission losses, inside surfaces of conventional waveguides are smooth, but because of the way metal 3D printing works, smooth internal surfaces can be difficult to fabricate. The design flexibility of additive processes can make up for that.
“In one of our designs, we found that even though we might have some limitations on the roughness of the surface finish, we could gain back the transmission losses by optimizing the waveguide shape,” Azevedo explained. “The final design would not have been possible using traditional waveguide fabrication techniques.”
Though applying metal coatings to waveguides produced from polymers or resins can provide smoother surfaces, this process comes with its own set of challenges.
“One of the issues we are tackling now is that a lot of the resins and polymers that have desirable properties for plating contain silica,” said Max Tannenbaum, a GTRI research engineer. “They are ceramic-like when cured, but when you remove the resin, a lot of the conventional solvents don’t remove the silica, and you end up with a chalky powder on the surface. If you can’t remove that before you try to plate it, the plating won’t adhere.”
Building a Knowledge Base for RF Applications of Additive Processes
To support expanded applications for waveguides fabricated using additive techniques, the researchers are using both simulation and experimentation to develop comprehensive design information.
“The traditional method for making waveguides has been around since World War II, when the original systems got up and running, and those techniques have been refined over the decades since then,” said Azevedo. “As a result, there’s a wealth of detailed data on what works, including the metallurgic properties. We want to develop a comparable depth of understanding for the new additive manufacturing techniques that offer so many advantages.” By putting together what they have learned, the research team plans to share their knowledge with other RF engineers who may be interested in the additive approaches.
“Our effort is focusing on two parallel paths: looking at the mechanical constraints involved with fabrication and the RF limitations,” said GTRI Research Engineer Austin Forgey. “We are merging the new experimental data we’re getting with RF simulations, and combining that with testing mechanical properties. That will give us a full design package that can be used by the designers who need it.”
Beyond waveguides, the GTRI researchers are working on other applications of additive manufacturing to RF design. With researchers in Georgia Tech’s School of Mechanical Engineering, they are fabricating cold plates that are 3D printed from aluminum and used to cool high-powered electronics. The 3D printing allows novel fluid flow in a single part, not possible with conventional fabrication.
Similarly, they are also looking at additive techniques to make shielding needed to protect components from electromagnetic interference.
While they expect to expand their use of additive fabrication approaches to provide new design options for RF applications, the researchers don’t see additive manufacturing doing away with conventional fabrication techniques any time soon.
“My opinion is that there will certainly be a mix because additive manufacturing techniques aren’t the answer for everything,” said Tannenbaum. “But they are solutions to a lot of specific problems that we encounter, allowing us to build parts that are cheaper, lighter, and available more quickly.”
Writer: John Toon
GTRI Communications
Georgia Tech Research Institute
Atlanta, Georgia USA
About GTRI: The Georgia Tech Research Institute (GTRI) is the nonprofit, applied research division of the Georgia Institute of Technology (Georgia Tech). Founded in 1934 as the Engineering Experiment Station, GTRI has grown to more than 2,800 employees, supporting eight laboratories in over 20 locations around the country and performing more than $700 million of problem-solving research annually for government and industry. GTRI's renowned researchers combine science, engineering, economics, policy, and technical expertise to solve complex problems for the U.S. federal government, the state, and industry. For more information, please visit www.gtri.gatech.edu.
News Contact
(Interim) Director of Communications
Michelle Gowdy
Michelle.Gowdy@gtri.gatech.edu
404-407-8060
Jan. 30, 2023
Becky Francosky is the Director of Air Service Development at Hartsfield-Jackson Atlanta International Airport (ATL). She has more than 15 years of experience in strategic planning, market research, analytics and project management that has been refined in roles in both the private and public sector. Ms. Francosky has broad experience in conducting primary and secondary research, analyzing market and competitive intelligence, gap analysis, forecasting and leveraging analytical frameworks to develop forward-looking and extrapolative insights.
Becky rejoined Hartsfield-Jackson in 2022 after working extensively with ATL on several key analytical studies through her company Advanced Aviation Analytics. While in her consulting role, she worked on a variety of projects including the Economic Impact Study, management dashboards and frameworks for gate utilization and forecasting. She has recruited several international passenger and cargo airlines and frequently engages with current and prospective airlines to help build stakeholder engagement.
Additionally, Becky plans and coordinates economic and business development activities with a variety of state and local organizations. From 2008 to 2012, Becky directed the market research program to understand customer’s preferences and needs, which led to expanded product and service offerings and increased non-aeronautical revenue by 40 percent.
We are very excited to have Becky join our board, lend us her expertise, and continue ATL's participation and support of SCL programs.
Jan. 18, 2023
This year, the Novelis Scholars program review committee at the Georgia Institute of Technology selected seven graduate scholars and four undergraduate scholars. This is the second year of the Novelis scholars program.
The Novelis Innovation Hub at Georgia Tech launched the Novelis Scholars program in 2021. The program seeks to recognize and cultivate top graduate students conducting research in various aspects of sustainability, high-throughput materials discovery, surface functionalization, and artificial intelligence (AI)/data science applications in materials, manufacturing, and supply chain technology.
Novelis has partnered with Georgia Tech to collaborate on research and development, and promote the education of the next generation of engineers dedicated to making better products that lead to a more sustainable world. Novelis is headquartered in Atlanta with a global footprint, over 12,500 employees, and recorded $17.1 billion in net sales for its 2022 fiscal year. Novelis expanded its research partnership with Georgia Tech in 2021.
The 2022-2023 Novelis Scholars are:
Graduate
- Bettina Arkhurst - Ph.D. candidate in the George W. Woodruff School of Mechanical Engineering
- Juanita Hidalgo - Ph.D. candidate in the School of Materials Science and Engineering
- Conlain Kelly – Ph.D. candidate in Computational Science and Engineering Undergraduate
- Walter Parker - Ph.D. candidate in the George W. Woodruff School of Mechanical Engineering
- Sushree Jagriti Sahoo - Ph.D. candidate in the School of Chemical and Biomolecular Engineering
- Alexandra (Lexie) Schueller - Ph.D. candidate in the George W. Woodruff School of Mechanical Engineering
- Sakshi Sharma - Master’s student in the School of Materials Science and Engineering
Undergraduate
- Daniel Johnson - pursuing his B.S. in mechanical engineering
- Suemin Lee - pursuing her B.S. in civil engineering with minors in sustainable cities and computer science
- Brandon Perry - pursuing his B.S. in materials science and engineering
- Sarang Pujari – pursuing his B.S/M.S. in computer science with a minor in climate change
Detailed profiles for this year’s 2022-2023 Novelis Scholars can be found here.
The Novelis Innovation Hub expects to issue its next call for Novelis Scholars for the 2023‐2024 Academic Year in late Spring/early Summer 2023.
News Contact
Jan. 10, 2023
Artificial intelligence is already making headlines in the new year with the box office success of the movie M3GAN. Along with a TikTok dance craze and lots of laughs, the over-the-top horror movie/dark comedy about an AI-powered robot that runs amok is also inspiring discussion about the growing presence and impact of artificial intelligence in everyday life.
From the movie house to the warehouse to your house, AI seems like it's everywhere. That's because with a steady stream of new research and innovative applications reaching into nearly every industry and business sector, it is everywhere. Nevertheless, AI still holds enormous potential as the field continues to evolve.
To get a sense of what this evolution could look like in 2023, we turned to a small group of Ph.D. students from the College of Computing community that are currently pushing foundational and applied AI research forward in a broad spectrum of disciplines and fields.
The students shared their opinions on where AI might be headed in the new year, what some of the big tech stories could be, and why ethics in AI are so critically important.
Where will artificial intelligence and machine learning have the most impact in 2023?
"Artificial intelligence and machine learning will continue to have a huge impact on manufacturing and warehouses with labor shortages and worker turnover continuing to be a concern as more manufacturing and operations jobs are brought back to the United States from overseas. Additionally, AI/ML will continue to help ensure that manufacturing and warehouse facilities are operating as efficiently as possible from energy and material savings to worker safety and parts quality." – Zoe Klesmith Alexander, computational science and engineering Ph.D. student
"Right now, deep learning is on a trajectory to transform the creation space. Artwork and images, videos, data representation and storytelling, co-authoring, and summarizing documents... It's gotten really good." – Ben Hoover, machine learning Ph.D. student
"I think machine learning and AI will keep playing a huge role in how the world and society will be shaped over the next decade in many ways. It will make many other fields more efficient through ML and AI tools we are developing. In 2023, I think ML and AI will have the most impact on social media platforms, helping reduce hate speech, rumor spread, etc." – Agam A. Shah, machine learning Ph.D. student
"One of the big impacts this year may be driverless cars being in your neighborhood. Otherwise, it will be a slow steady drip of GPT3 and other OpenAI models suffusing all applications, making programmers much faster, making journalists faster, making academic articles and lit reviews much faster. We're at a 4th grader level, and I hope by the end of this year we'll be at the 6th grader level. Also, indoor turn-by-turn navigation will be everywhere in 2023 as well." – Brandon Biggs, human-centered computing Ph.D. student
What will be some of the big tech stories in 2023?
"ChatGPT and the GitHub Copilot lawsuit will keep making it into the news and cause more controversies. In general, AI ethics will become more important and get more focus as the technology keeps advancing." – Fabian Fleischer, cybersecurity, and privacy Ph.D. student
"Driverless car fleets will be coming to a city near you. A new battery technology will allow phones to keep their charge for a week. Meta realizes virtual reality (VR) head-mounted displays are for a limited market and uses headphones and phones to provide VR experiences." – Brandon Biggs
What’s an issue or industry that you think could benefit from a computing solution?
"Our reinterpretation of modern deep learning as energy-based associative memories has the potential to transform any industry that relies on foundation models -- giant architectures that require models that are "self-supervised" (learn on their own from data)." – Ben Hoover
"Inclusion in everything. Over 90 percent of websites on the internet have elements that are inaccessible to 25 percent of the world's population who have disabilities. Inclusive design will be the most important area where technology can be redesigned and created to have multiple sensory modalities and be properly programmed." – Brandon Biggs
"Currently, financial markets are far from efficient because they do not fully incorporate information available in large unstructured text data. With the latest development in natural language processing techniques, we can better understand the economy and therefore price financial markets better." – Agam A. Shah
There’s been increasing recognition of the vital role ethics should play in artificial intelligence. How do you see this issue evolving in the next year?
"Specifically in my research, I think explainable AI (XAI) is very important, especially if non-experts in ML will be using black-box ML solutions in a factory. It will be important for humans to trust and to understand the models especially if the models are being using to monitor quality on a safety-critical part.
"Additionally, using XAI for human interaction with robots that utilize deep learning to make decisions will be increasingly important as technologies like collaborative robots (cobots) are integrated into factories. I think in my area of research that it is always important to use automation to aid humans in jobs that are safe for humans to do and not to replace them." – Zoe Klesmith Alexander
"Big data is pretty much at its peak. Deep data, where your Alexa knows everything about you, or your phone knows everything about you, and rather than saying 'other people who watched this show liked this show,' it's going to say, 'I know you liked these shows, I think you'll like this show because of these reasons, one of which is because other people who liked all these other shows liked this show.' The ethical element will be how much of this data should these models use, and are people going to build a personal dataset that they can share with other apps, or is each app going to need to build their own dataset? The ethical question is who owns this data." – Brandon Biggs
"I think ethics will become more and more important going forward. We are making huge breakthroughs in machine learning and artificial intelligence, but the systems we are creating are producing racist, sexist, and stereotypical results. For example, a recent system, Galactica, developed by Facebook (Meta) is powerful. It can produce research articles by just simply providing it with the title. It comes with some serious ethical concerns, in some cases, it produces racist, sexist text. So, as we will keep developing better models and making success in parallel, we need to always keep in mind the ethical implications of these models." – Agam A. Shah
What research are you working on that you think people should know about or will have impact in 2023?
"Part of my research focuses on data-driven modeling of additive manufacturing processes to better control dimensional quality of the final part. Another part of my research focuses on detecting anomalies in real-time using computer vision and machine learning for both warehouses and manufacturing processes." – Zoe Klesmith Alexander
"Right now, deep learning is built on feed-forward mathematical operations that have little resemblance to the brain. I am working on a physics inspired approach to deep learning built around recurrent networks and energy functions. These architectures have the same mathematical foundation as the famous, biologically plausible Hopfield Network." – Ben Hoover
"I am currently working on two projects which, in my opinion, will have an impact in 2023. In one project, we are measuring the exposure of public firms to ongoing inflation. We are also understanding how inflation affects different firms differently based on the pricing power of the firm. As inflation is the highest in the last 40 years, our study is highly relevant now and in the coming years till we get inflation back in control.
"The second work is related to the first work in some ways. As inflation is rising, to control the inflation Federal Reserve Bank is tightening its monetary policy. In our second work, we are measuring the stance of monetary policy (measuring hawkish vs dovish stance) of the Fed using state-of-the-art NLP models to see its impact in various financial markets (Treasury market, Stock market, Crypto market, etc.)" – Agam A. Shah
News Contact
Ben Snedeker, Comms. Mgr. II
albert.snedeker@cc.gatech.edu
Dec. 13, 2022
4 Questions with the IDEaS Leadership Team | Featuring Xiaoming Huo; A. Russell Chandler III Professor, H. Milton Stewart School of Industrial and Systems Engineering
This week we introduce Xiaoming Huo, A. Russell Chandler III Professor in the H. Milton Stewart School of Industrial and Systems Engineering at Georgia Tech and Associate Director for Research in the Institute for Data Science and Engineering.
Dr. Huo's research interests include statistical theory, statistical computing, and issues related to data analytics. He has made numerous contributions on topics such as sparse representation, wavelets, and statistical problems in detectability.
1. What is your field of expertise and what questions, or challenges sparked your current research?
My research is focused on the foundational principles of data sciences (also known as machine learning, artificial intelligence, etc.). A large spectrum of algorithms has been developed in the data science field, however, there remains a challenge to understand the performance and limitations of these algorithms and then provide helpful, practical guidelines for their usage by researchers. I began my journey to data science as an undergraduate mathematics major. I have been motivated by the emergence of data sciences and the fact that many of these challenging foundational problems are naturally mathematical. What I am doing now seems to be a perfect spot for someone who wants to explore fundamental mathematics while still making an impact in deployable applications.
2. Why is the field of Data Science and Engineering important to the development of Georgia Tech’s broader research strategy?
In the most recent science and engineering research endeavors, no matter the discipline, large amounts of data are generated and collected. Consequently, more and more research finding across colleges and schools at Georgia Tech, and globally, are data-driven. The ability to correlate and make meaningful connections within data will be essential for future researchers. Additionally, the innovative breakthroughs in science and engineering of the future are likely to rely heavily on the utilization of tools from data science and the availability of new data types.
3. What are the global and social benefits of the research you and your team conduct?
Currently, my research is primarily mathematical. Our end goal is to provide data handling principles, guidelines, and best practices that researchers and students can apply.
4. What are your plans on engaging a wider GT faculty pool with IDEaS research?
I am the executive director of the Transdisciplinary Research Institute for Advancing Data Science (TRIAD) (triad.gatech.edu). In 2017, we won an NSF TRIPODS Phase 1 award to establish this Center. TRIAD is housed under the Institute of Data Engineering and Sciences (IDEaS). I am currently serving as the Associate Director for Research (ADR) of IDEaS. As an ADR, I organize campus-wide activities related to data science research at Georgia Tech, aiming to catalyze collaborative activities. My current project is to organize a Georgia Tech workshop on the foundations of data science. We hope to provide a brainstorming event for relevant researchers in early 2023.
Learn More About the Team’s Work Here: https://sites.gatech.edu/xiaoming-huo/
Apr. 17, 2017
Devyon wasn't having success landing interviews or getting call backs for job applications. A mentor at the National Urban League encouraged him to apply to Juma, an employment and job training program which helps youth overcome the hardships of poverty and aspire to career success. As part of its social enterprise operations in Atlanta, Juma offers year-round employment to over 140 Atlanta youth at SunTrust Park, Mercedes-Benz Stadium, and State Farm Arena—home of the Braves, Falcons, Hawks, and Dream—as well as the Georgia World Congress Convention Center.
Devyon applied and successfully enrolled in Juma, and found a path to earn money, build his resume, and pave his future. As part of the program, Devyon took Georgia Tech LEAP courses to learn more about supply and logistics and the career paths the field has to offer. His dedication to the job, his willingness to go above what was expected of him and his attention to detail were characteristics that made him stand out to Juma’s Enterprise Managers. After successfully completing Juma’s training program, Devyon secured a job at UPS, a Juma Atlanta job placement partner. Today, Devyon has stable employment and, after successfully passing UPS’ Supervisor Exam, became a Shift Manager.
Oct. 09, 2017
Zaria participated in Juma, an employment and job training program which helps youth overcome the hardships of poverty and aspire to career success. As part of its social enterprise operations in Atlanta, Juma offers year-round employment to over 140 Atlanta youth at SunTrust Park, Mercedes-Benz Stadium, and State Farm Arena—home of the Braves, Falcons, Hawks, and Dream—as well as the Georgia World Congress Convention Center.
Zuma promotes participants to earn while they learn, so while going to school during the week to pursue her GED, Zaria took GT LEAP courses at night and worked in the Juma Atlanta concessions operations group on the weekend. Through perseverance and her will to succeed, she later secured fulltime employment within the JUMA organization.
At the Future of Work 2017 summit sponsored by The Atlantic, Zaria was asked about her experience. She commented, “sometimes, people just need a second chance and an opportunity to take advantage of it.” The experience has opened her eyes to the possibilities and Ms. Walker has aspirations to be a crime scene investigator. Zaria plan to pursue further education and make that dream a reality some day.
Dec. 09, 2019
On a journey for knowledge and self-development, Marine Corporal Phillip Davis completed the Supply Chain Management Principles, Customer Service Operations, Warehousing Operations, and Transportation Operations courses as part of the LEAP program.
“The courses have given me more tools towards helping build my critical thinking skills and the necessary skills and training to help me apply information about good supply chain management. It also gives me certainty in performing my duties as a Marines administrator to ensure required supplies and materials are delivered in a timely and right way.”
Corporal Davis commented that one day he would like to own his own business. By taking the LEAP courses, he has gotten closer to that goal through a better understanding of the importance of supply chain. “It helps me think about how to have things ready when and before people need them, to meet and exceed internal and external customers' demands. Being an administrator, there are things that I need to stay informed about, and acquiring awards, certificates help me do that. Responsibility wise, I constantly keep track of what we use, have and when we are down to half supplies. I put in orders for new supplies and replacement. The courses that I have taken definitely help me perform my duties at a high level above expectation. Overall, this program has helped me add on to my organization and accounting skills as in the military accountability is a big thing.”
Dec. 06, 2022
Todd Ullom has over 30 years' experience as an entrepreneur, developer, general contractor, technologist, and market strategist holding senior executive positions with both private and public companies. He is currently vice president for MiTek, a wholly owned subsidiary of Berkshire Hathaway, leading the development of the company’s distributed construction platform which is initially focused on offsite volumetric assembly of hotels. He joined MiTek as part of the acquisition of Innovation Builder, a technology company founded by Todd with a focus on solving the construction industry's toughest problems. Throughout his career, Todd has managed both growth and turnaround companies, developed new business opportunities, designed industry leading business processes and developed innovative marketing strategies. His experience includes founder and president of a bespoke building company; senior leadership positions in large private and public construction companies including COO, region president, VP of strategy and operations; and VP of strategy and business development for a technology firm.
Todd has developed more than $2.5 billion in real estate with annual P&L responsibility of more than $500 million and developed turnaround programs for over 50 projects during the financial crisis. He has developed industry leading processes for scheduling, purchasing and trade relationships. Todd created the Martha Stewart and Ralph Lauren branded home programs and has developed creative customer centric product designs and selling strategies. He has provided business and technology consulting for more than 200 builders and contractors of all sizes throughout North America. Todd has also served in numerous capacities constructing large scale commercial projects that include major medical research facilities, hospitals, dormitories, hotels and club houses.
Todd has a B.S. in Building Construction from the Georgia Institute of Technology, is a licensed Florida general contractor and sales associate, certified in advanced design thinking through IDEO and is a certified leadership coach with John Maxwell. He is a former president of the Atlanta Homebuilders Association, was named as one of Seattle’s Top Business Executives Under 40 in 1999, received the Lee Evans Award for Management Excellence in 2012, was named America’s Best Builder in 2013 and currently serves on the Board of Governors for the non-profit Opportunity International.
Nov. 21, 2022
Shreyes N. Melkote, who holds the Morris M. Bryan, Jr. Professorship in the George W. Woodruff School of Mechanical Engineering, has been awarded a $3 million Future Manufacturing Research Grant from the National Science Foundation (NSF). Melkote, who is also the Associate Director of the Georgia Tech Manufacturing Institute and Executive Director of the Novelis Innovation Hub, will act as principal investigator alongside four other researchers, including Woodruff School Professor Emeritus David Rosen, and will explore a data-driven approach to cyber manufacturing. The grant will also support Melkote’s efforts to work with academic and industry partners to develop educational tools to train a future manufacturing workforce from diverse backgrounds.
“We are excited to have the resources that the NSF has provided,” Melkote said. “It’s the best type of resource because it allows us to do basic research.”
Cyber manufacturing looks to leverage recent advances in artificial intelligence and machine learning, cloud technology and the expanding reach of the Internet-of-Things to reduce the cost and time of producing discrete parts. Presently, the manufacturing process is compartmentalized, with design, fabrication, and distribution heavily reliant on direct communication between the parties, and often involves multiple iterations of a design before the customer’s needs are met.
In a future cyber manufacturing ecosystem, the process is digitally unified across the supply chain and potential issues in fabrication can be flagged automatically and early in the design process, minimizing the need for multiple prototypes. The final design can then swiftly be routed to those best equipped to produce the product based on the specifications.
This vision of a fully automated, interconnected process has long been sought after and is considered the ‘holy grail’ of discrete parts manufacturing.
“It's an old problem,” Melkote said. “But we have new ways of potentially trying to solve it, and we have a critical mass of people and resources to help solve, or at least make a significant dent, in solving the problem.”
A crucial step in solving the problem requires digitizing and automating the complex series of decisions that begin when a new design for a product is completed. What are the manufacturing processes (and machines) required to produce the design? What processes create the most durable build, or the most cost-efficient? Can the design be altered for manufacturability without compromising functionality and quality?
For mass-produced discrete products or parts built to universal standards, these are questions to which suitable answers have been found through trial-and-error, but bespoke or new designs often require specialized knowledge about manufacturing processes and their capabilities. A company or individual will use their current level of understanding to discern how to move forward with a brand-new design.
“Fundamentally they are harnessing the knowledge derived from data they have tucked away somewhere and then using that to actually take a shot at figuring out how to make it,” Melkote explained. “But it would be great if they had all of these capabilities in an automated way. This grant is focused on how you generate the complex knowledge that individuals have acquired through experience.”
Melkote’s interdisciplinary approach will use generative machine learning and other artificial intelligence techniques to help automate this complex decision-making process. If a computer can infer the capabilities and limitations of an industrial manufacturing process and associated machines, then it should be able to make intelligent deductions about the entire manufacturing process, at least in theory. Extracting the data necessary to make this happen requires new methods that Melkote and his co-investigators will research.
“If I can teach a computer to be able to learn these things, the more data from successfully produced parts I can provide it, then its learning will improve and its ability to get close to telling me what all the types of things I can produce using a given process on a given machine will improve.”
The models and algorithms that would run this process could then be embedded in an automated cyber manufacturing service, which can analyze an uploaded design and provide a customer with instant feedback regarding recommended modifications, and projected costs, or even generate instructions and send them to the right machine. The work could see sweeping changes made to several manufacturing industries and democratize the way products are designed and made.
Alongside Rosen, Melkote will work closely with three other researchers, two of which have ties to Georgia Tech, including Matthew Gombolay, an assistant professor in the School of Interactive Computing, and Mahmoud Dinar, a former postdoctoral fellow at the Woodruff School and current Assistant Professor at California State University-Sacramento. Dr Gaurav Ameta, a research scientist at Siemens Corporate Technology will also work as co-principal investigator.
The grant is part of a wider national initiative that saw more than $30 million awarded to university-based research projects on advanced manufacturing and preparation of the manufacturing and STEM workforce for the future.
Article by Ian Sargent