Improving Students’ Modeling Skills for Engineering Complex Systems

This project aims to serve the national interest by helping students learn the necessary skills to manage the full lifecycle for complex engineering systems in collaborative virtual environments. Model-based Systems Engineering (MBSE) is an emerging methodology that addresses the need to increase productivity, improve quality, reduce risk, and improve communications in the engineering of complex systems that include both hardware and software components.

This project will help students learn how to use MBSE in each phase of the system development cycle including requirements, design, analysis, verification, and validation, by developing a new course using project-based learning. Students will work in geographically distributed teams that will include members from the University of Texas Rio Grande Valley and the University of Texas at El Paso to learn how to work in a virtual collaborative environment.

A machine learning algorithm will be developed to measure student sentiment during the course to identify opportunities for improving how the course is taught in a timely manner. Project results will be disseminated to the engineering education community through the annual ASEE conference, systems engineering conferences, IEEE journal publications, and an open-source website with information on MBSE training materials, manuals developed, and a design and development guide of machine learning algorithms.

The goal of this project is to improve the technical skills of the STEM workforce in systems engineering with a focus on MBSE. The project will pursue four complementary objectives. First is to develop an undergraduate MBSE course for third and fourth year students in industrial and systems engineering, manufacturing engineering, and engineering technology.

Second is to provide a collaborative self-organizing dynamic team experience for geographically separated student teams. Third is to develop a machine learning technique to analyze and understand student perceptions of using MBSE in geographically separated student teams. Fourth is to create an open-source platform to share project materials and insights with academic institutions that are interested in teaching MBSE.

The machine learning model for the analysis of text data from online technical discussion forums and team communications in the course will help characterize students’ learning experience. Student learning will be assessed at multiple levels of Bloom’s Taxonomy including: (1) Are students able to create system diagrams and models of engineered systems using Systems Modeling Language notations? (2) Are students able to generate system requirements, model architectures, and define specifications using MBSE? (3) Are students able to generate system verification and test plans based on system models they generate?

The models and documents will be assessed by instructors to determine to what extent the students have achieved the learning outcomes. This project is expected to advance knowledge about working in collaborative virtual environments and the use of machine learning to assess students’ perceptions. Through its Engaged Student Learning track, the IUSE program supports the creation, exploration, and implementation of promising practices and tools.

This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.