IoT-Enabled Manufacturing Testbeds for Democratizing SM Knowledge, Technology and Innovation​

Project Lead: Auburn University
Partners: Rayonier & Linde

Member % Cost Share: 50.3%
CESMII % Cost Share: 49.7%
Duration: 12 Months

Problem Statement

There is a lack of interactive hands-on SM training materials based on real SM data and applications, which presents a challenge to advancing CESMII’s goal of democratizing SM knowledge, technology and innovation.

Project Goal

To establish and validate a novel model of SM training, including content creation, delivery and evaluation. Specifically, a suite of interactive SM training modules using real data and applications will be developed. In addition, we propose a metacognitive awareness gain (MAG) metric for evaluating the effectiveness of the SM training modules.

Technical Approach

The team leverages on two Internet-of-Things (IoT) enabled SM testbeds (SMTT) previously developed at Auburn, which provide real data and applications for SM training modules. We propose to develop data-enabled engineering project (DEEP) based SM (DEEP-SM) modules on Jupyter Notebook platform and integrated into the SM PlatformTM to train future and current SM workforces, respectively.

Deliverables/Outcomes/SM Marketplace

  •  ​Delivered Complete Smart Manufacturing Testbed Documentation Package
  • Delivered Complete Smart Manufacturing Profiles
  • Delivered complete interactive Jupyter Notebook modules covering the entire data science life cycle
  • Raw data, video and documentation packages are available for other CESMII members training and research needs
  • Low-cost, noninvasive sensing system documentation package

Potential Impact

  • The Jupyter SM training modules can be easily incorporated into existing education programs, therefore significantly advance the preparation of future SM workforce with new SM skill set and expertise
  • The SM Platform training modules with real industrial applications can be easily adopted by different member organizations for re-training of current SM workforce.


  • A validated effective model for SM training, including content creation, delivery and evaluation;
  • The SMTTs and their associated applications are not commercial but rather educational, which allow full access to all CESMII members for adaptation and generalization to their specific applications;
  • The open source DEEP-SM Jupyter Notebook modules make them easily adoptable by other universities, which will help CESMII achieve the goal of “increasing the SM workforce capability by five-fold by 2030”.​

Project Selection & Announcements


Leverage project outcomes for your manufacturing operations

Learn More