Session: 18-01-03: AI Implementation in Industry - II

Paper Number: 150972

150972 - Enhancing Manufacturing Efficiency Through Iiot: An Industrial Case Study in Data-Driven Process Improvement 

The advent of the Industrial Internet of Things (IIoT) has unlocked vast amounts of data from the shop floor. While impressive, raw data alone lacks inherent value unless effectively leveraged. This research focuses on implementing a comprehensive IIoT system in a manufacturing environment to drive process improvements and enhance operational efficiency through data.

The primary objective of this project was to enhance manufacturing efficiency by reducing downtime, addressing slow run rates, and improving quality. These goals were achieved by harnessing IIoT data to diagnose equipment performance issues. Additionally, real-time operator input is prompted when problems arise, providing context to issues and facilitating better insight. This information is aggregated in real-time and reviewed through a sophisticated web application, enabling engineering and supervisory teams to quickly address problems and identify trends, leading to overall enhanced productivity.

Connectivity starts at the machine level to extract equipment data, typically from PLCs, robots, or other machine controllers. Edge devices are employed due to their flexibility in connecting disparate data sources, their reliability at the edge, and their potential security benefits. Once extracted, the data is forwarded to a centralized server for shop-wide access and analysis.

At the core of the IIoT system, a centralized server houses all data and employs business logic operations to transform raw data into actionable insights. Utilizing industry-standard technologies and open-source software packages the system is both robust and cost-effective, avoiding proprietary lock-in. While cloud solutions are also viable, on-premise hosting offers high availability and low latency.

To facilitate user interaction with the insights generated, a cross-platform web application was developed. This application includes performance logs segmented by shift, day, and month, highlighting key metrics such as efficiency, Overall Equipment Effectiveness (OEE), and its components of availability, performance, and quality. These metrics are updated in real-time and automatically derived from IIoT data, with contextual operator reports also captured. The logs are easily navigable, and visualizations are provided in a dashboard format for intuitive use.

The implementation of an IIoT system in a manufacturing environment demonstrates tangible benefits, moving beyond data collection to provide a tool for continuous process improvement. By leveraging IIoT for data-driven insights, manufacturers can significantly enhance equipment performance, and empower operators by integrating their input into the data analysis process. This case study offers a replicable framework for manufacturers aiming to achieve operational excellence and suggests future research on integrating predictive maintenance capabilities to further improve manufacturing efficiency and reliability.

Presenting Author: Seth Ramsey The MK Morse Company

Presenting Author Biography: Seth Ramsey is currently a Mechatronics & Control Systems Engineer at The MK Morse Company in Canton, Ohio. He graduated with a degree in Electrical & Computer Engineering from The Ohio State University in 2022.

Authors:

Seth Ramsey The MK Morse Company
Roan Kirwin The MK Morse Company