Developing digital design data

Engineering faculty awarded NSF grant to study digital manufacturing and machine learning

10/25/18

UNIVERSITY PARK, Pa. — Manufacturing technology, the various devices and systems that enable the production of manufactured goods, is evolving rapidly. Due to its digital nature, the accelerated pace at which manufacturing technology advances often makes it difficult for engineers to incorporate the latest technology and production processes into product designs. 

Researchers at Penn State have received a $424,743 grant from the National Science Foundation to investigate how the size and quality of datasets created by digital models relate to machine learning and how this impacts the support provided to engineering designers.

The three-year project, “Investigating the Effectiveness of Machine Learning Paradigms for Supporting Engineering Designers in Rapidly Evolving Digital Manufacturing,” is led by principal investigator Christopher McComb, assistant professor of engineering design, industrial engineering, and mechanical engineering. Nicholas Meisel, assistant professor of engineering design and mechanical engineering, and Timothy Simpson, Paul Morrow Professor in Engineering Design and Manufacturing, serve as co-principal investigators. Mechanical engineering doctoral candidate Glen Williams has also recently joined the project.

It is known that current manufacturing machines often rely on digital models which produce large amounts of data. The researchers’ approach centers around a two-step process that uses these existing datasets to build design knowledge.

“In the first step, we’ll use deep learning to extract features, or commonly reoccurring patterns, from the database,” he said. “In the second step, we again use deep learning to learn how to use these patterns to predict performance and behavior — things like strength and manufacturability.”

Datasets vary greatly in quantity and quality, making the usefulness of machine learning somewhat unknown. The team will use additive manufacturing, or 3D printing, to investigate how the amount and value of the datasets relate to the accuracy and usefulness of machine learning capabilities and how this relates to the support provided to engineering designers.

McComb said additive manufacturing was chosen as the case study due to its status as an emerging mainstream manufacturing technology.

“Using additive manufacturing, we will develop methodologies that will help us better support novice engineers and designers when the next revolutionary manufacturing technology comes around,” he said.

Through the combination of additive manufacturing, machine learning and explainable artificial intelligence, McComb and his team will use data collected from existing 3D printing design challenges to investigate the use of automated design feedback. Part designs will be gathered from online, open sources and engineering course design challenges.

To test the effect dataset size has on feedback accuracy and level of detail, the team will create a machine learning pipeline that will pull out patterns from the design datasets.

As the final step in the project, studies with engineering students will be conducted in order to provide them with skill training and to collect data. McComb defines the students as key stakeholders and said by involving them in the research, the team is helping to prepare them for work in the manufacturing industry.

“At the end of the day, our goal is to better serve them [engineering students] by helping them more quickly and effectively design for new manufacturing technologies,” he said. “By taking part in one of our studies, we want them to learn about additive manufacturing and also recognize that they’re helping us to better support other learners in the future.”

Results from the research will lead to a dataset of mechanical part designs stored as voxels, the 3D equivalent of pixels; a deeper understanding of how a dataset’s quantity and quality impact a machine’s learning and feedback capabilities; and first-hand experience of the impact real-time additive manufacturing feedback has on the solutions created by engineering designers.

“For corporations, this work is going to help them understand what types of insights they can expect to extract from the design and engineering data that they already have,” McComb said. “For students and novices, this work will provide some foundational approaches for supporting them as they learn how to use new manufacturing technologies.”

 

Share this story:

facebook linked in twitter email

MEDIA CONTACT:

Samantha Chavanic

smh5218@psu.edu

Chris McComb headshot

Christopher McComb, assistant professor in engineering design, industrial engineering and mechanical engineering

“For corporations, this work is going to help them understand what types of insights they can expect to extract from the design and engineering data that they already have. For students and novices, this work will provide some foundational approaches for supporting them as they learn how to use new manufacturing technologies.”

 
 

About

The School of Engineering Design, Technology, and Professional Programs (SEDTAPP) delivers effective engineering education through active, collaborative, project-based, and professionally oriented classroom experiences. SEDTAPP offers a variety of programs that partner faculty, students, and industry in the study of real-life engineering problems. Our programs teach students to solve real-life problems with innovative solutions. 

School of Engineering Design, Technology, and Professional Programs

213 Hammond Building

The Pennsylvania State University

University Park, PA 16802

Phone: 814-865-2952