EDA University Center

The focus of the Auraria Campus Advanced Manufacturing University Center program is to conduct research and offer technical assistance through applied research and partnership to all parts of the State including underserved areas around the Auraria campus. This University Center helps the manufacturing industry develop new products or create new and better manufacturing processes, on a fee-for-service basis, using Artificial Intelligence (AI) and Machine Learning (ML) technologies.

Metropolitan State University of Denver

University of Colorado Denver

Colorado School of Mines

MSU Denver has partnered with Reata Engineering & Machine Works and Big Metal Additive to address key problems in aligning with industry needs. Partnership activities include exchange of expertise, best practices, and lessons learned in areas of mutual interest such as algorithm development.

Reata Engineering & Machine Works sponsored two Senior Design projects for mechanical engineering students with the opportunity to work on real-world challenges. This partnership bridged the gap between academia and industry, offering students hands-on experience while delivering innovative solutions to industrial problems.

• Reata Engineering and Machine Works
• Big Metal Additive

The MSU Denver team prepared survey questions and investigated how to integrate AI techniques in manufacturing. The study aimed to provide insights into how AI/ML is transforming manufacturing processes, enhancing efficiency, and supporting data-driven decision-making.

In July 2024, the  University partners hosted a workshop on Additive Manufacturing to provide an interdisciplinary platform for students, researchers, and industry professionals to explore the latest technologies, trends, research findings, and applications in the field of Additive Manufacturing (AM).

Dr. Devi Kalla presented on the topic “AI in Digital Manufacturing”.

The acquisition of an Xact Metal Accessible Metal Powder-Bed Fusion 3D printer will enhance the University Center’s research capabilities in additive manufacturing and provide valuable training opportunities for students, researchers and industry partners. The printer will help researchers develop new machine learning models with instrinsic interpretability and increased adaptablity to support metal additive manufacturing.

In high-performance mechanical systems, efficient thermal management and mechanical load support are critical for reliability and performance. This project aimed to design, prototype, and evaluate a conical bearing heat exchanger that maximizes heat transfer while supporting mechanical loads under real-world operating conditions.

The Student Team developed a unique conical bearing structure to optimize surface area and fluid dynamics for improved heat transfer integrating compact design principles in aerospace, automotive, and industrial machinery. The Team achieved a 20–30% improvement in heat transfer efficiency compared to traditional cylindrical configurations (validated via prototype testing).

The Team successfully fabricated a working prototype using CNC machining and high-temperature-resistant materials. The project was selected for presentations at the National Conference for Undergraduate Research (NCUR) 2025,

The sport of combat robotics is always evolving which provides new and unique challenges to overcome each year. The Student Team was tasked with designing and building a combat robot to compete in conduct by National Robotics League Colorado. The robot had to conform to all competition rules, most importantly the weight and safety rules set by Reata Engineering. The Team used knowledge of kinematics, material science, Additive Manufacturing, CAD, and innovation to improve on past years’ robots.

The Team presented this project to the Engineering and Enginnering Technology Symposium in May 2025.

Problem statement and Objectives

Metal additive manufacturing enables the production of complex, lightweight, and high‑performance components but often results in surface roughness that requires significant post‑processing. This project focused on developing a machine learning model capable of predicting surface roughness of metal additively manufactured parts based on key process parameters. A structured dataset was generated by printing test specimens with varied build orientations and surface geometries while systematically adjusting parameters such as scan speed, hatch spacing, and layer height. Surface roughness was measured using scanning electron microscopy to ensure high‑resolution, non‑contact characterization. After data cleaning and preprocessing, correlation analysis was used to identify influential parameters and guide feature selection. Machine learning models were then trained and evaluated to capture the relationships between process settings and resulting surface texture.

This project demonstrated that a structured data‑collection workflow and a consistent preprocessing method could support the development of a predictive model for surface‑roughness estimation in metal additive manufacturing. The work established a usable dataset, implemented a preliminary modeling framework, and confirmed that machine‑learning methods could capture meaningful relationships between process parameters and surface texture. Further research should expand the dataset beyond what was accomplished in this second consecutive year; potentially incorporating additional process variables and refining model architectures to improve predictive reliability. Continued validation through repeated print trials and broader parameter sweeps will be necessary to build confidence in long‑term algorithmic model performance. These steps will support the further development of the predictive tool for uture additive‑manufacturing applications.

The Annual Conference is the single largest gathering of the year for ASEE members. For many who attend the conference, it is their best opportunity to share their individual and collective work in engineering education.

Dr. Devi Kalla presented research in a presentation entitled Adoption of Digital Twin and Artificial Intelligence in Metal Additive Manufacturing – Current Status and Vision for Future.

As part of our ongoing efforts to promote undergraduate research and professional development under the EDA- funded initiative, we are proud to report that our student-led projects were selected for presentations at the National Conference for Undergraduate Research (NCUR) 2025, April 7-9th at Pittsburgh, PA. This prestigious recognition reflects the quality and impact of the experiential learning opportunities made possible by the grant.

The selected project, titled “Predictive Modeling of Surface Roughness in Metal Additive Manufacturing using Machine Learning”, focusd on Machine learning algorithm to predict surface roughness in metal additive manufacturing, and was conducted under the mentorship of Dr. Devi Kalla, with support from the EDA program’s resources. The students involved presented their research to a national audience of peers, faculty, and industry experts, gaining valuable experience in scholarly communication and networking. Their participation helps raise the visibility of our University Center commitment to economic development and innovation.

This accomplishment underscores the grant’s impact not only on institutional capacity-building, but also on student success and regional engagement.

As part of our ongoing efforts to promote undergraduate research and professional development under the EDA- funded initiative, we are proud to report that our student-led projects have been selected for presentations at the National Conference for Undergraduate Research (NCUR) 2026, April 13-17th at Richmond, Virginia. This prestigious recognition reflects the quality and impact of the experiential learning opportunities made possible by the grant. Three Mechanical Engineering Technology (MET) students recently represented the program at the National Conference on Undergraduate Research 2026, one of the premier undergraduate research conferences in the United States. The event, hosted this year in Richmond, brings together thousands of undergraduate students from across the country to showcase their scholarly and creative work in a professional conference setting.

MET students delivered a poster presentation titled “Design and Development of a Two-Axis Demonstration Gimbal for Engineering Education.” Their project focused on the design, fabrication, and testing of a functional two-axis gimbal system intended to support hands-on learning in engineering classrooms. The work highlights the integration of mechanical design principles, manufacturing processes, and practical problem-solving; core elements of the MET curriculum.

Participation in NCUR provides students with a valuable opportunity to engage with a national community of researchers, gain experience in technical communication, and receive feedback from peers and faculty across a wide range of disciplines. Presenting at such a prestigious venue reflects the students’ dedication, technical competency, and commitment to applied engineering education.

This achievement also underscores the strength of the MET program in fostering undergraduate research, experiential learning, and industry-relevant project development. Their participation raises the visibility of our University Center commitment to economic development and innovation.

This accomplishment underscores the grant’s impact not only on institutional capacity-building but also on student success and regional engagement.