Equipment Installation Quality Improvement

In an Amazon Fulfillment Center (FC), associates work alongside Material Handling Equipment (MHE) to move products and packages efficiently within the building. As new FCs are constructed and launched to meet changing fulfillment demands, it is essential for Amazon and its vendors to ensure the highest quality installation and integration of MHE to minimize operational issues following site launch. To continuously improve the FC construction and launch process, the Amazon Operations Engineering team seeks to optimize MHE installation qualification by improving existing quality processes while decreasing the time and resources required to complete them. This project launched two separate initiatives to move the needle towards increased quality and lean operation within Amazon’s MHE inspection and qualification process. The first initiative focuses on prioritization of inspection tasks considering risk of post-launch equipment failure using a new unsupervised machine learning approach. Three unique machine learning algorithms were created to connect disparate databases containing equipment inspection tasks and operational equipment failure data. The outputs of each algorithm were compared to understand which model provided the best fit. The new, best-fitting model can be used in the future to identify highest-impact equipment inspection tasks, and to simplify business decisions on how inspection tasks should be prioritized or throttled (not completed). The second initiative seeks to improve the equipment inspection tasks themselves, and explores the impact of increased task standardization using three techniques: • Including photos with examples of good- and poor-quality equipment installations • Including descriptive measurements and specific ’how-to’ instructions for inspection tasks • Separating tasks based on unique resolution actions A pilot test was completed to determine the impact of these techniques on vendor inspection outcome accuracy, and results showed that the increased standardization provided benefit to inspection outcomes overall. Both of these projects introduce novel quality improvements in order to decrease maintenance technician re-work and reduce post-operational equipment failures. This thesis captures the successful techniques that were used in the case study, rationale for why they were chosen, and highlights the general use cases for which these quality improvement methodologies can be applied.

Name thesis:degree_name

Master

Department dc:contributor.department

Massachusetts Institute of Technology. Department of Mechanical Engineering

Grantor dc:publisher

Massachusetts Institute of Technology

Year dc:date.issued

2022

Author dc:creator

• Amlani, Jen

Advisors dc:contributor.advisor

• Zheng, Karen
• Kim, Sang-Gook

Statement dc:rights

• In Copyright - Educational Use Permitted
• Copyright retained by author(s)

Licence dc:rights.uri

• https://rightsstatements.org/page/InC-EDU/1.0/

Handle dc:identifier.uri

https://hdl.handle.net/1721.1/146700

OAI identifier oai:identifier

oai:dspace.mit.edu:1721.1/146700