Authors:

Jizheng Li

Date Created:

Not specified

Course Title:

Professor:

Not specified

About Paper:

This project aims to enhance predictive maintenance in drilling operations by forecasting drill bit failures using machine learning. Using the XAI Drilling Dataset, we developed a model to predict failures based on operational parameters like cutting speed, spindle speed, feed rate, and cooling levels. The goal is to reduce operational costs, prevent downtime, and increase productivity. Our Random Forest model, refined through hyperparameter tuning and cross-validation, showed high accuracy in predicting failures. This predictive maintenance approach promises significant cost savings and operational improvements for industries relying on drilling processes. Keywords: Predictive Maintenance; Data Mining

Source:

Purdue University / 2024

Topics:

No topics listed

Co-authors:

Jizheng Li