Have a UROP opening you would like to submit?
Please fill out the form.
2: Mechanical Engineering
You are supplied with data from 519 production runs from a packaging line. This dataset consists of the IoT machine data which (presumably) contain information about a degrading component (blade) recorded over a duration of 12 months. The blade cannot be inspected visually during operation due to the blade being enclosed in a metal housing and its fast rotation speed. Monitoring the cutting blade’s degradation will increase the machines reliability and reduce unexpected downtime caused by failed cuts. If the “wear” can be predicted accurately, a remaining useful life prediction can be made in order to determine maintenance windows, i.e. predictive maintenance. Your objectives are to: 1) Identify and extract features in the data. 2) Using extracted features, construct several models predicting degradation of the blade. 3) Optimize and/or evaluate predictive ability of models for different design decisions. Impact: This project is of interest to many manufacturers.
1. This project will utilize machine learning and data analytics and predictive maintenance skills. Background/interest in these skills are helpful and students can expect to enhance these skills through the project. 2. This project is offered as part of the MechE Alliance industry connected ELO cohorts. Applicants will be expected to participate in the cohort program to be eligible for the position. More information can be found in this Google Doc: https://drive.google.com/file/d/1YbGwDXGAvPDSN6DEDGBw-VDJWS7jnp65/view?usp=sharing This is a remote UROP opportunity.