Session: CIE–31: Graduate Student Poster Symposium

Paper Number: 148314

148314 - Expertise in Engineering Design: A Predictive Modeling Framework for Performance 

Expertise has been studied across disciplines over the years, including engineering design, a domain that is dominated by experts. The study of expertise in the engineering design community has involved research to understand the difference in the behavior of solvers and the design process outcomes. While the existing literature has identified many differences between experts and novices through these empirical studies, a predictive modeling framework that links solvers' expertise to design outcomes is lacking. In this study, we want to propose a predictive modeling framework that represents expertise in design in a mathematical space, unlike classifying them as experts and novices. We want to use this representation of expertise to predict the performance of a given solver on a given problem using a particular design process. The model for predicting performance based on the expertise of a solver will be used to quantify the effects of the solver pool on the design outcomes, along with the effects of system architecture and contract mechanisms. The predictions using the model will help structure the complex systems design process to promote innovation and leverage contributions from a solver pool with diverse expertise. We plan to validate the proposed framework using the Astrobee dataset, which contains data from a series of open innovation challenges linking solver characteristics, solving processes, and solution attributes.

Presenting Author: Athul Chakkithara Dharmarajan Purdue University

Presenting Author Biography: Athul Chakkithara Dharmarajan completed his Bachelor's and Master's in Mechanical Engineering from the Indian Institute of Technology, Bombay. He worked with Prof. Dwaipayan Mukherjee and Prof. Anirban Guha on the design of multi-robot systems. He joined Purdue in August 2022 and has been working with Prof. Jitesh Panchal at the Design and Engineering Lab since then. His research interests are modeling human behavior in engineering design and using computational methods to support system architecting.

Authors:

Athul Chakkithara Dharmarajan Purdue University