Engine Predictive Maintenance

Machine learning model that predicts how close turbofan engines are to failure.

Data & algorithms

Problem

Unexpected aircraft engine failures are costly and dangerous, and calendar-based maintenance can come too early or too late.

Solution

A Python model that classifies proximity to failure with an SVM, using robust scaling, SMOTE class balancing, grid-search hyperparameter tuning and several evaluation metrics.

Key features

SVM classifier with grid-search hyperparameter tuning
Class balancing with SMOTE
Scaling robust to outliers
Accuracy, F1, ROC AUC and confusion matrix metrics
Commented version of the code to follow the execution

Stack

Python
scikit-learn
pandas
NumPy

Platforms

Want a project like this?

Tell us what you need and we will outline the next steps.

Request a quote