This project develops a data-driven Predictive Maintenance (PdM) system designed
for industrial milling operations. By leveraging Machine Learning through Logistic
Regression, the system analyzes real-time sensor data—including Torque,
Rotational Speed, and Tool Wear—to forecast machine failures before they occur.
The primary goal is to transition from reactive 'Run-to-Failure' strategies to
proactive monitoring, achieving an 86% AUC performance score. The project
focuses on identifying key failure drivers to minimize operational risks.
Technologies utilized include Excel for Exploratory Data Analysis (EDA) and Logistic
Regression for binary classification and predictive modeling.
