Introducing Data Analytics into Mechanical Engineering Curriculum

Xiyuan Liu

Download Paper | Permalink

Conference: 2022 ASEE Annual Conference & Exposition
Location: Minneapolis, MN
Publication Date: August 23, 2022
Start Date: June 26, 2022
End Date: June 29, 2022
Conference Session: Mechanical Engineering: Fluids, Heat Transfer
Page Count: 13
DOI: 10.18260/1-2--40967
Permanent URL: https://peer.asee.org/40967
Download Count: 722

Paper Authors

biography

Xiyuan Liu Syracuse University

visit author page

Xiyuan Liu is currently an assistant teaching professor in the Department of Mechanical and Aerospace Engineering in College of Engineering. She received B.S. in Electrical Engineering in China in 2009 and then completed her M.S. in Mechanical Engineering at Clemson University. She received her PhD degree in Mechanical Engineering at Michigan State University. Her PhD work mainly focused on developing biosensing, lab-on-a-chip systems for the emerging applications in clinical diagnosis, wearable sensing and mobile heath (mHeath) technology. In 2017, she joined Syracuse University as an assistant teaching professor for a joint position between the Department of Biomedical and Chemical Engineering and the Department of Mechanical and Aerospace Engineering. Since 2020, she becomes a full-time assistant teaching professor in the Department Mechanical and Aerospace Engineering. As an instructor, she teaches courses at different levels, from first-year undergraduate engineering programming course to graduate level technical elective courses. She particularly interests in improving engineering education through enhancing students learning experience, cultivating an active learning environment and promoting diversity, equity and inclusion (DEI).

visit author page

Download Paper | Permalink

Abstract

The advancements in information technology, computing power, data mining and artificial intelligence have enabled all the engineering disciplines to take the advantages of large datasets to model, classify, and make proper predictions for numerous engineering applications. To educate next-generation mechanical engineers in the new era of data science and artificial intelligence, engineering educators have been urged to integrate these new technological advancements into existing curriculum to adapt to the fast-changing needs from the future workplace. My effort primarily focuses on implementing an interdisciplinary approach to introduce the concepts and principles of data science to the undergraduate students of mechanical engineering. I re-designed the class of Statistics for Engineering as Data Analytics for Engineering, in which the students can practice new tools used in data analytics applications while they are still learning the basic statistical principles behind these techniques.

In this class, the students are exposed to the real-world examples of how data analytics has been applied in the field of mechanical engineering. The course content arrangement is based on the data analytics lifecycle: problem discovery – data understanding – data preparation – data visualization – model building – conclusion/decision making. Statistical concepts related to each stage are introduced to the students along with the corresponding programming basics in R-studio. Parallelly, the semester-long project is assigned to the student groups from the first day of lecture. Each group is required to select a real-world dataset and complete the data analysis using data cleaning, data preparation, data visualization, regressions, and several machine learning algorithms. To help the student better complete the project, I develop interactive activities at different development stages, including project proposal, proposal peer review, project interview, preliminary report, and final report. The assessment of the effectiveness of this new class was conducted by comparing exams and feedback of students by the end of the semester. This class provides students with sufficient knowledge of both fundamental statistics and practical data analytical techniques for engineering fields, comprehensive experience in data analytic workflow, and the opportunity to exercise their data analytical skills in engineering applications.

Citation
Format

Liu, X. (2022, August), Introducing Data Analytics into Mechanical Engineering Curriculum Paper presented at 2022 ASEE Annual Conference & Exposition, Minneapolis, MN. 10.18260/1-2--40967

TY  - CPAPER
AB  - The advancements in information technology, computing power, data mining and artificial intelligence have enabled all the engineering disciplines to take the advantages of large datasets to model, classify, and make proper predictions for numerous engineering applications. To educate next-generation mechanical engineers in the new era of data science and artificial intelligence, engineering educators have been urged to integrate these new technological advancements into existing curriculum to adapt to the fast-changing needs from the future workplace. My effort primarily focuses on implementing an interdisciplinary approach to introduce the concepts and principles of data science to the undergraduate students of mechanical engineering. I re-designed the class of Statistics for Engineering as Data Analytics for Engineering, in which the students can practice new tools used in data analytics applications while they are still learning the basic statistical principles behind these techniques. 

In this class, the students are exposed to the real-world examples of how data analytics has been applied in the field of mechanical engineering. The course content arrangement is based on the data analytics lifecycle: problem discovery – data understanding – data preparation – data visualization – model building – conclusion/decision making. Statistical concepts related to each stage are introduced to the students along with the corresponding programming basics in R-studio. Parallelly, the semester-long project is assigned to the student groups from the first day of lecture. Each group is required to select a real-world dataset and complete the data analysis using data cleaning, data preparation, data visualization, regressions, and several machine learning algorithms. To help the student better complete the project, I develop interactive activities at different development stages, including project proposal, proposal peer review, project interview, preliminary report, and final report. The assessment of the effectiveness of this new class was conducted by comparing exams and feedback of students by the end of the semester. This class provides students with sufficient knowledge of both fundamental statistics and practical data analytical techniques for engineering fields, comprehensive experience in data analytic workflow, and the opportunity to exercise their data analytical skills in engineering applications.

AU  - Xiyuan Liu
CY  - Minneapolis, MN
DA  - 2022/08/23
PB  - ASEE Conferences
TI  - Introducing Data Analytics into Mechanical Engineering Curriculum
UR  - https://peer.asee.org/40967
DO  - 10.18260/1-2--40967
ER  -