Downloads · 30 days
0
engine-predictive-maintenance-model
indianakhil/engine-predictive-maintenance-model
engine-predictive-maintenance-model is a machine learning model from indianakhil. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
Binary classifier predicting engine health (Normal vs Faulty) from six sensor readings.
Access
Public
Updated Apr 8, 2026
Repo size
273 KB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.pkl33.8 KB · 92%
At a glance
- License
- mit
- Access
- Public
- Created
- Mar 25, 2026
- Updated
- Apr 8, 2026
- SHA
- f47a6dd4
Model card
From the Hugging Face model README
Engine Predictive Maintenance Model
Model Description
Binary classifier predicting engine health (Normal vs Faulty) from six sensor readings.
- Model Type: AdaBoostClassifier
- Task: Binary Classification (0=Normal, 1=Faulty)
- Training Data:
indianakhil/engine-predictive-maintenance(19,535 records) - Best Hyperparameters:
{'learning_rate': 0.5, 'n_estimators': 50}
Performance (Test Set — 20% holdout)
| Metric | Score |
|---|---|
| Accuracy | 0.6644 |
| Precision | 0.6787 |
| Recall | 0.8883 |
| F1-Score | 0.7695 |
| ROC-AUC | 0.6960 |
| CV F1 (5-fold) | 0.7663 |
Input Features
Engine_RPM, Lub_Oil_Pressure, Fuel_Pressure, Coolant_Pressure, Lub_Oil_Temperature, Coolant_Temperature
Usage
from huggingface_hub import hf_hub_download
import joblib, pandas as pd
model = joblib.load(hf_hub_download(
repo_id='indianakhil/engine-predictive-maintenance-model',
filename='best_model.pkl'))
pred = model.predict(X) # 0=Normal, 1=Faulty
prob = model.predict_proba(X)[:, 1] # Fault probability
- License
- mit
- Languages
- en
- Created
- Mar 25, 2026
- Updated
- Apr 8, 2026