Auburn Develops IoT Testbeds to Train the Next Generation of Manufacturing Engineers BENEFITS TO OUR NATION Training engineering students in smart manufacturing techniques is a strategic
Project Objective
The goal of this project is to develop a suite of data-enabled Smart Manufacturing (SM) Jupyter Notebook modules using real data and applications from two Internet- of-Things (IoT) enabled laboratory- scale SM technology testbed examples.
Benefits to Industry
By providing engineers with expertise in cutting-edge technologies like IoT, advanced sensing, and data analytics, American industry gains a skilled talent pool that can drive efficiency, innovation, and competitiveness. These engineers will have the skills needed to develop and implement advanced manufacturing processes, reducing operational costs, and improving product quality. This not only bolsters the strength of individual industries but enhances the nation's overall industrial capabilities. Ultimately, training young engineers on smart manufacturing technology makes American manufacturers more agile, adaptable, and prosperous.
Technical Approach
Internet-of-Things (IoT) enabled Smart Manufacturing testbeds, which provide real data and applications for SM training modules, are leveraged to develop Smart Manufacturing modules on the Jupyter Notebook platform. The modules are integrated into the CESMII Smart Manufacturing Innovation Platform.
Accomplishments
-
Demonstrated implementation of the SM testbed utilizing IoT vibration sensors for pump-flow condition monitoring
-
Demonstrated implementation of the IoT Wi-Fi sensors for estimating moisture content in wood chips
-
Developed reusable machine learning models for pump motor speed and water flow rate
-
Developed reusable artificial neural network models for moisture content prediction
-
Demonstrated feasibility of implementing low-cost, contact free IIoT sensors
Deliverables
• 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: o Data preparation and processing Data exploration and visualization o o Data transformation and feature engineering Machine learning o o Deep learning Performance metrics in machine learning o
Reusable Outcomes
- Raw data, video and documentation packages
- Low-cost, noninvasive sensing system documentation package