Asee peer logo

Predictive Data Analytic Approaches for Characterizing Design Behaviors in Design-Build-Fly Aerospace and Aeronautical Capstone Design Courses

Download Paper |

Conference

2016 ASEE Annual Conference & Exposition

Location

New Orleans, Louisiana

Publication Date

June 26, 2016

Start Date

June 26, 2016

End Date

August 28, 2016

ISBN

978-0-692-68565-5

ISSN

2153-5965

Conference Session

Technology-Related Educational Research

Tagged Division

Computers in Education

Tagged Topic

Diversity

Page Count

16

DOI

10.18260/p.25938

Permanent URL

https://peer.asee.org/25938

Download Count

204

Request a correction

Paper Authors

biography

Krishna Madhavan Purdue University - West Lafayette

visit author page

Dr. Krishna Madhavan is an Associate Professor in the School of Engineering Education. In 2008 he was awarded an NSF CAREER award for learner-centric, adaptive cyber-tools and cyber-environments using learning analytics. He leads a major NSF-funded project called Deep Insights Anytime, Anywhere (http://www.dia2.org) to characterize the impact of NSF and other federal investments in the area of STEM education. He also serves as co-PI for the Network for Computational Nanotechnology (nanoHUB.org) that serves hundreds of thousands of researchers and learners worldwide. Dr. Madhavan served as a Visiting Researcher at Microsoft Research (Redmond) focusing on big data analytics using large-scale cloud environments and search engines. His work on big data and learning analytics is also supported by industry partners such as The Boeing Company. He interacts regularly with many startups and large industrial partners on big data and visual analytics problems. He was one of 49 faculty members selected as the nation’s top engineering educators and researchers by the U.S. National Academy of Engineering to the Frontiers in Engineering Education symposium.

visit author page

biography

Michael Richey The Boeing Company

visit author page

Dr. Michael Richey is a Boeing Associate Technical Fellow currently assigned to support technology and innovation research at The Boeing Company. Michael is responsible for leading a team conducting engineering education research projects that focus on improving the learning experience for students, incumbent engineers and technicians. His research encompasses, Sociotechnical Systems, Learning Curves, and Engineering Education Research.
Additional responsibilities include providing business leadership for engineering technical and professional educational programs. This includes development of engineering programs (Certificates and Masters) in advanced aircraft construction, composites structures, systems engineering, product lifecycle management and digital manufacturing. The educational programs and research focus on practical understanding of human learning and the design of technology-enhanced learning environments and promoting global excellence in engineering and learning technology to develop future generations of entrepreneurially-minded engineers. This is achieved by partnering and investing in educational initiatives and programs between industry and institutions of higher learning. Under Michael’s leadership, The Boeing Company has won the multiple Awards for Excellence and Innovation for their industry academic partnerships and joint programs
Michael has served on various advisory groups including, the editorial board of the Journal of Engineering Education, Boeing Higher Education Integration Board, American Society for Engineering Education Project Board and the National Science Foundation I-UCRC Industry University Collaborative Research Center Advisory Board. Michael has authored or co-authored over 25 publications in leading journals including Science Magazine, The Journal of Engineering Education and INCOSE addressing topics in large scale system integration, learning sciences and systems engineering. Michael often represents Boeing internationally and domestically as a speaker - presenter and has authored multiple patents on Computer-Aided Design and Computer-Aided Manufacturing, with multiple disclosures focused on system engineering and elegant design.Michael holds a B.A and M.Sc. from ESC Lille in Program Project Management and Ph.D. from SKEMA Business School with a focus on Engineering Education Research.

visit author page

biography

Barry McPherson The Boeing Company

visit author page

Barry McPherson is the Senior Business Partner for education programs in the Technical and Professional Learning Solutions organization within The Boeing Company. His focus is on building customized learning solutions for both on-hours and off-hours programs that bring Boeing quality and innovation into the learning space. Barry manages a multimillion dollar research and delivery portfolio focused on advanced manufacturing (e.g. composites) and Product Lifecycle Management (PLM) disciplines, providing technical excellence to Boeing engineers regarding technical foundations and cutting-edge applications. 

visit author page

Download Paper |

Abstract

Introduction: Predictive data models and interactive visualizations can be highly effective in understanding workload and skills assignment issues within design-build-fly teams in the aerospace industry. Capturing data that is needed to build predictive models in usable forms and then subsequently applying appropriate data mining techniques to derive insights from such data is a significant challenge. The ultimate goal of our work is to understand design behaviors among engineers that can lead to cost reductions and expediting product development in complex engineering environments. The present study is a first step towards this overall vision. In this paper, we characterize how engineering students interact and perform on complex engineering tasks commonly seen in the aerospace industry. We use course clickstreams, social networking and collaborations as the basis for our observations. Context of the study: AerosPACE is an engineering education program developed by a large US aerospace company. The primary goal of this program is help students understand the process of designing, building, and flying an unmanned aerial vehicle (UAV) capable of assisting first responders. Multi-disciplinary, multi-university teams consisting of students from 5 US universities undertake this real-world engineering project. Collaboration between students at different universities is a major theme of the project. It is expected that each design will address technical areas of aerodynamics, materials, propulsion, manufacturing, structures, and controls among others. Major milestones include a Mission Concept Review, Preliminary Design Review, Critical Design Review/Production Readiness Review, Flight Readiness Review, and Post Launch Assessment Review in addition to a flight demonstration. The overall theme of the UAV’s mission is to help various first responders protecting citizens in this country and across the world. First responders fulfill various missions, many of which can benefit from the use of small-unmanned aerial vehicles. As part of this project students define specific missions they will design their vehicle for to support first responders.

Methods: The challenge for this study begins with instrumenting the design environment effectively. When engaging in the build-design-fly engineering process, students typically have to interact with a number of online learning and design environments (for example, learning management system, design environments for the aircrafts, simulation environments to test the design, and specification documentation capture systems). Developing an architecture needed to address this data pipeline is the first aspect that this paper addresses in significant depth. Secondly, using clickstream data, our analyses contain a mapping over time of students’ interactions with faculty and industrial partners and time series distribution of skills and collaborative messages. Additionally, text mining and web log mining techniques allows researchers to gain deep insights on the major discussion topics. Further exploration based on the analysis of the behavior of the users by clustering them and extracting most important patterns is also enabled by our research. Learner behavioral similarity is computed using a page co-occurrence method. Topics are found within the messages using the Latent Dirichlet Allocation model.

Outcomes: This study is implemented in a fully automated framework under R giving access to the analysis via a web application. This application allows researchers to interact with the results permitting executives and decision makers to go deeper into the training data. Our work also lowers significantly the information management barriers in how engineers are trained to participate in production-oriented teams

Madhavan, K., & Richey, M., & McPherson, B. (2016, June), Predictive Data Analytic Approaches for Characterizing Design Behaviors in Design-Build-Fly Aerospace and Aeronautical Capstone Design Courses Paper presented at 2016 ASEE Annual Conference & Exposition, New Orleans, Louisiana. 10.18260/p.25938

ASEE holds the copyright on this document. It may be read by the public free of charge. Authors may archive their work on personal websites or in institutional repositories with the following citation: © 2016 American Society for Engineering Education. Other scholars may excerpt or quote from these materials with the same citation. When excerpting or quoting from Conference Proceedings, authors should, in addition to noting the ASEE copyright, list all the original authors and their institutions and name the host city of the conference. - Last updated April 1, 2015