2023 ASEE Annual Conference & Exposition

Infusing Data Science into Mechanical Engineering Curriculum with Course-Specific Machine Learning Modules

Presented at Mechanical Engineering Division (MECH) Technical Session 15: Automation and Machine Learning

Recent advances in data science algorithms and libraries have made an impact on approaches and strategies for research and development in the industrial sector, which necessitates the integration of data science into engineering education. Data science courses offered by programs such as mathematics, computer science, and data science in academic institutions normally lack the implementation in solving engineering problems. We have developed a project-based technical elective course “Machine Learning for Mechanical Engineers” and offered it to undergraduate and graduate students at the University of Arkansas. While this course is received very well by the students and has led to fruitful presentations and publications, it has a low enrollment volume from undergraduate students due to its relatively high programming requirements. A more sophisticated strategy is required to equip mechanical engineering students with data science skills without disturbing the existing curriculum. Inspired by the success of computer-aided design education at the University of Arkansas and the DIFUSE program at Dartmouth College, we have developed course-specific machine learning modules to be integrated into mechanical engineering core courses rather than dedicated data science courses. This effort includes a nonparametric regression module for Computer Methods in Mechanical Engineering, a generative design module for Computer-Aided Design, a genetic algorithms module for Thermal Systems Analysis and Design, among others. Through this practice, students will practice programming and machine learning skills every semester since their sophomore year and will be ready for the project-based technical elective machine learning course.

Authors

Prof. Yuhao Xu Prairie View A&M University [biography]

Yuhao Xu received a Ph.D. in Mechanical Engineering from Cornell University in 2017. He is currently an Assistant Professor in the Department of Mechanical Engineering at Prairie View A and M University. He was previously employed by ASML-HMI North America Inc., where he worked on the industrial applications of focused ion beams. His current research includes experiments on high-pressure combustion of petroleum-based liquid fuels and bio-derived fuels, digital image processing of experimental data, and studies of microfluidics in energy systems.
Bo Zhao
Prof. Steve Tung University of Arkansas [biography]

Dr. Steve Tung is currently a professor and associate department head at the Department of Mechanical Engineering of the University of Arkansas. He was a postdoctoral fellow at UCLA Mechanical and Aerospace Engineering Department from 1993-1997, and an engineer specialist at Litton Guidance and Control Systems from 1997-1999. He joined the University of Arkansas as an assistant professor in 2000. Dr. Tung’s research interest is in the development of micro- and nanofluidic systems for engineering applications. His work has been funded by the National Science Foundation and National Institute of Health. He was named a Fellow of the American Society of Mechanical Engineers (ASME) in 2016.
Prof. Han Hu http://orcid.org/0000-0002-9667-1698 University of Arkansas [biography]

Han Hu is an Assistant Professor in the Department of Mechanical Engineering at the University of Arkansas. He received his Ph.D. from Drexel University in 2016 and B.S. from the University of Science and Technology of China in 2011. Before he joined the University of Arkansas, he worked at the Cooling Technologies Research Center at Purdue University as a postdoc on two-phase electronics cooling. His current research is focused on the development of experimental and numerical tools to address research and development needs in the thermal management of IT and power electronics. The specific areas include single-phase and two-phase cooling with textured surfaces, remote sensing using acoustic emissions and optical imaging, and data-driven modeling of transport processes and multimodal data fusion. His research is supported by federal and state agencies including NSF, NASA, AEDC, and ASGC as well as industrial companies including Google and Safe Foods.

Download paper (1.47 MB)

Are you a researcher? Would you like to cite this paper? Visit the ASEE document repository at peer.asee.org for more tools and easy citations.

» Download paper

« View session

For those interested in:

engineering
Graduate
undergraduate