Pratyush130194/predictive-maintenance-best-model

Predictive Maintenance Best Model

Model Description

This repository contains the best-performing machine learning model developed for predicting engine maintenance requirement using engine sensor data.

The model was trained to classify whether an engine is operating normally or requires maintenance.

Problem Statement

The objective of this project is to support predictive maintenance by identifying abnormal engine conditions based on operational sensor readings.

Input Features

The model uses the following input variables:

• Engine_rpm
• Lub_oil_pressure
• Fuel_pressure
• Coolant_pressure
• lub_oil_temp
• Coolant_temp

Target Variable

• Engine_Condition

Model Type

The best-performing model selected during experimentation was used for this repository.

Evaluation

The model was selected based on the best F1-score achieved on the test dataset after comparing multiple tree-based classifiers.

Files Included

• best_model.joblib
• best_model_summary.txt
• experiment_results.csv

Project Context

This model was developed as part of an academic capstone project on predictive maintenance for engine failure.