Tag: Pamela Kobryn

Big Data Spurs Bedeviling Questions

Panelists: Moderator Joseph Morrison, associate project manager, Transformational Tools and Technologies, NASA’s Langley Research Center; Jandria Alexander, principal, Booz Allen Hamilton Inc.; David Keyes, director, Extreme Computing Research Center, King Abdullah University of Science & Technology; Pamela Kobryn, principal aerospace engineer, Structures Technology Branch, Aerospace Vehicles Division, Aerospace Systems Directorate, Air Force Research Laboratory; Dimitri Mavris, director, Aerospace Systems Design Laboratory, Georgia Institute of Technology; Mark Valentine, Department of Defense Strategic Initiatives Group, Microsoft

by Michele McDonald, AIAA Communications

An influx of data, driven in part by tiny sensors, is creating a big data transformation that promises to help the aerospace industry get ahead of problems before they happen, panelists discussed Jan. 9 during the “Data, Data Everywhere … the Devil in the Details” session at the 2018 AIAA SciTech Forum in Kissimmee, Florida.

Dimitri Mavris, director of the Aerospace Systems Design Laboratory at the Georgia Institute of Technology, said the area is so new that no one’s an expert.

“We’re going to make this journey together,” he said.

The panelists said the complex problems big data could help solve are spurring more questions, including how to deal with data reliability, threats, privacy and integration.

“The elephant in the room is obviously the protection of data,” said Pamela Kobryn, a principal aerospace engineer with the Aerospace Systems Directorate at the Air Force Research Laboratory. “How do we quantify uncertainty?”

Kobryn wondered on calibration and updating models as well as how to run them efficiently enough to have the data in the time frame needed. She said end users are part of the equation.

“Who’s going to be using the predictions, and what are they going to do with them, and what is the time frame?” Kobryn added.

Collecting personal data adds other layers of complexity, Kobryn said, explaining data will need to be managed, archived, stored and adapted over time.

The panelists said in the past decade, some crucial pieces have fallen into place to help big data move into the daily realm.

Mavris said it’s not just one, but many technologies and that a multidisciplinary approach needs to be taken. Key enabling technology includes surrogate modeling techniques, high performance computing, advanced data analytics and visualization, advanced sensing technology, and machine learning, he said.

“The sensing (technology) is actually leading this parade,” Mavris said.

The aerospace industry has the opportunity to dig deeper and apply big data-related technology to current problems, he said.

Digital twins, which mimic their physical counterparts and help predict outcomes, encounter widely varying degrees of complexity within the same industry, Kobryn said, adding the same general concept can be applied to commercial, general and military aviation but that the problems and complexities are vastly different within the areas.

For example, she said, commercial aircraft have fairly predictable variables, but the military operates from austere bases or aircraft carriers and often in harsh conditions. The average age of the U.S. Air Force fleet is pushing 30 years so, Kobryn said, predictive maintenance is essential.

And then there’s space.

“When you talk about space exploration, it’s a completely different story because you don’t have the chance to perform maintenance,” Kobryn continued. “You have one chance to execute the mission … the ideal scenario is to use digital twin technology to design in ultra-high reliability from the start, and while you’re on the mission, you want to be able to use the data you gather to adapt the mission to any risks you identify, and the digital twin would help you identify risks.”

The audience members seemed to think the industry is in the early stages of the big data revolution. They rated data technology as at the “peak of inflated expectations” of the Gartner Hype Cycle, according to an informal poll of those in the room. While some attendees think we’re in the “trough of disillusionment,” others think we’re moving toward the “slope enlightenment.”

Video

All 2018 AIAA SciTech Forum Videos

Digital Engineering Transforming Manufacturing

Panelists: Moderator Pamela Kobryn, principal aerospace engineer, Structures Technology Branch, Aerospace Vehicles Division, Aerospace Systems Directorate, Air Force Research Laboratory; Brenchley Boden, chief technology officer, Digital Manufacturing and Design Innovation Institute, and senior industrial engineer, AFRL; Michael W. Grieves, executive director, Center for Advanced Manufacturing and Innovative Design, Florida Institute of Technology; Brunon “Dave” Kepczynski, chief information officer, GE Global Research, and engineering product leader, GE Digital; John H. Vickers, principal technologist, Space Technology Mission Directorate, NASA; Chuck Ward, chief, Manufacturing and Industrial Technologies Division, Materials and Manufacturing Directorate, AFRL; Caroline Gorski, global partnership director for digital, Rolls-Royce

by Michele McDonald, AIAA Communications Manager

Dawn-of-Digital-Engineering-Panel-SciTech2018 — Participants in the Jan. 8 discussion “The Dawn of Digital Engineering” at the 2018 Science and Technology Forum in Kissimmee, Fla.

In the dawn of digital engineering, the challenges are daunting, but the rewards extend far beyond manufacturing, panelists said Jan. 8 during the “The Dawn of Digital Engineering?” forum at the 2018 AIAA SciTech Forum in Kissimmee, Florida.

The panelists said digital engineering could boost efficiency, slash costs, increase agility and reveal problems before production begins. However, they pointed out some challenges, including overcoming cultural biases, navigating through massive amounts of data and figuring out how to retain and make accessible digitized data into the future.

Digital twins and models are disrupting the status quo, though, they said. For example, a digital twin of an airplane can move through its physical counterpart’s entire lifecycle from the design stage to manufacturing to service and support, said Chuck Ward, with the Air Force Research Laboratory’s Materials and Manufacturing Directorate.

“You now have a flying laboratory,” Ward said.

Beyond digital twin prototypes, there are digital twin aggregates, said Michael W. Grieves, executive director of the Center for Advanced Manufacturing and Innovative Design at Florida Institute of Technology. He said these aggregates can help engineers predict when equipment needs to be replaced and that it’s all about prognostics and learning so “later versions of a product don’t have to go through the same learning curves as earlier versions.”

Digital twins and digital engineering may help NASA reach Mars and beyond while cutting costs and saving time, said John H. Vickers, principal technologist with NASA’s Space Technology Mission Directorate. The traditional building block approach can take decades and tens of millions of dollars to get equipment into space.

The Department of Defense is shifting to a digital engineering ecosystem from initial research and development all the way to maintenance and eventually retirement, said Pam Kobryn, with the Aerospace Systems Directorate at AFRL. She said the DOD is working with traditional modeling and simulation while leveraging high-performance computing and software networking.

“The dawn of digital engineering — the questions are all around the unknowns,” Korbyn said, adding that the DOD is looking at the portability of the models, value across the lifecycle, how to speed up the pace of delivery and how to provide simple support to complex problems.

And then terabytes of data must be managed. For that, engineers are borrowing from the field of biology and bundling information into packets, similar to the DNA code, Ward said.

“We need to figure out how to learn from all that data,” said Brenchley Boden, chief technology officer of the Digital Manufacturing and Design Innovation Institute, and senior industrial engineer at AFRL.

The factory floor needs to become more intelligent, he said, adding that sensors could be a solution for older equipment.

In addition, the industry needs to move to an ecosystem approach in which all the functions can be seen at the same time, away from its current focus on parts and subsystem levels, said Brunon “Dave” Kepczynski, chief information officer at GE Global Research and engineering product leader with GE Digital.

Building such an ecosystem means companies need to think beyond their own walls and collaborate with players from across systems, said Caroline Gorski, global partnership director for digital at Rolls-Royce. Industrial “internet of things,” artificial intelligence, advance analytics and blockchain are figuring into the new digital engineering ecosystem.

But, the panelists said, the next generation of engineers may hold the answer.

“They come digitally ready,” Vickers said.

Video

All 2018 AIAA SciTech Forum Videos

Big Data’s Power Starting to Reach Potential

by Michele McDonald, AIAA Communications Manager

Data-Data-Everywhere-Pane-SciTech2018-350 — Participants in the discussion, “Data, Data Everywhere…the Power & Potential,” Jan. 9 at the 2018 Science and Technology Forum in Kissimmee, Fla.

The aerospace industry can be a leader in how best to apply big data to real-world critical missions, speakers discussed in a series of presentations Jan. 9 during the “Data, Data Everywhere … the Power & Potential” session at the 2018 AIAA SciTech Forum in Kissimmee, Florida

The influx of digital data is changing everything from improving how we buy cars to space exploration. For example, Pamela Kobryn, a principal aerospace engineer with the Aerospace Systems Directorate at the Air Force Research Laboratory, said digital twins — digital counterparts to physical things — could change how we buy and maintain cars.

Your digital twin would know your driving habits, including the routes you take and how much you hit the brakes, she said, explaining the information would be “personalized to how you are going to drive that vehicle.”

Kobryn explained automakers would have simulations to match driving habits and requirements with vehicles and that you’d know how your new car would handle, how much gas it would use and future maintenance costs.

“Now imagine if that simulation capability was free, easy to use and access, and readily available — it would be pretty cool,” she said.

But the journey doesn’t stop there. Your new car would have its digital counterpart continually updated about maintenance needs and could predict possible breakdowns during trips, Korbyn said, adding that when it’s time to buy a new car, the digital twin could inform the timing of that decision, too.

The same concept of digital twins can be applied to aircraft, spacecraft and other complex systems, Korbyn said.

Big data also is changing digital assistants, said Mark Valentine, with the Department of Defense Strategic Initiatives Group at Microsoft.

“There are millions of decision points, and the data is overwhelming, so it sounds to me like we need some help,” he said.

And Valentine said we’re already familiar with the perfect digital assistant.

“I think George Lucas gave us the best blueprint for a digital assistant back in 1975, and his name was R2-D2,” Valentine said. “R2-D2 could do almost everything.”

He said future assistants will take action.

“Much like Luke (Skywalker) would tell R2 to go do something and R2 would go do it,” Valentine said.

Digital assistants are drawing data from sensors, context and our actions.

“Our assistants now know me — they know us — our preferences,” Valentine said. “And not just what we say we like, but they learn from our actions. There’s a complete difference between what we say we like and what we actually like. Digital assistants now know my context because of the proliferation of sensors … now the digital assistant can anticipate what I need to know in the future.”

This deep knowledge of our lives leaves us vulnerable when paired with cybersecurity concerns and questioning if we can trust the data, said Jandria Alexander, principal at Booz Allen Hamilton.

She said computer systems constantly are under attack, and the attackers don’t have to be sophisticated to cause damage. Legacy systems are easy targets, Alexander said, adding that newer complex systems are connected to these vulnerable systems.

No system is safe from attack, she said, explaining that the new approach is to be resilient and continue to operate through attacks. Alexander said big data is giving us some detailed answers about how to build resiliency against cyberattacks into the systems.

But planning for cybersecurity becomes thornier when it takes decades to build a spacecraft while technology keeps evolving.

“What we’re fielding has to be sound and has to protect from threats we can’t even predict,” Alexander said. “We don’t even know what those threats are. But the good news is if we build these in an architecturally sound fashion, we can actually prevent classes of attacks.”

Video

All 2018 AIAA SciTech Forum Videos