Evaluating Strategies for Wide Scale Replacement of Human Inspection with Machine Vision
Name
sakerka_lsakerka_mba_mgt_2022_thesis.pdf
Description
Thesis PDF
Size
3.15 MB
Format
Adobe PDF
Checksum (MD5)
bdc59fd53e4d3be3bce35bf7a4cc547c
Author(s)
Sakerka, Lauren
Advisor(s)
Welsch, Roy
Simchi-Levi, David
Date Issued
May 2022
Publisher
Massachusetts Institute of Technology
Abstract
A stable and cost-effective workforce is key to manufacturing life-saving medical devices. However, an ongoing global labor shortage is causing national economic challenges and causing companies to have significant workforce shortages, delaying operations and production activities. Additionally, human visual inspections of medical devices are less reliable and effective than new technological inspections with machine and artificial intelligence vision systems. This research explores the efficiency of human visual inspections, the impact new technology, such as machine and AI vision, can add, how to lead technological change, and an approach to implementing this change at a medical device manufacturing company.
Specifically, it examines best practices and a specific strategy for identifying machine and AI vision opportunities at a large manufacturing company where quality is extremely important. It also examines strategies to quickly identify improvement areas and get manufacturing excited about new technology. Finally, it compares a traditional field visit approach to a data driven opportunity identification approach. Ultimately, it proposes a data-driven approach using visual tools to communicate opportunities to management in order to get the buy-in to proceed with these technological improvements.
MIT Department
Sloan School of Management
Massachusetts Institute of Technology. Department of Civil and Environmental Engineering
Terms of Use
In Copyright - Educational Use Permitted
Copyright retained by author(s)
Persistent DSpace Link
