aimen-ameer/airfoil-noise-model

Airfoil Self-Noise Predictor

A Random Forest regression model trained on the UCI Airfoil Self-Noise dataset.

Task

Predict the scaled sound pressure level (dB) of an airfoil given 5 aerodynamic features.

Features

Feature	Description
frequency	Frequency in Hz
angle_of_attack	Angle of attack in degrees
chord_length	Chord length in metres
free_stream_velocity	Free-stream velocity in m/s
displacement_thickness	Suction side displacement thickness in metres

Performance

Metric	Value
Test RMSE	1.9788 dB
Test R2	0.9218

Usage

import joblib, numpy as np
model  = joblib.load("rf_model.pkl")
scaler = joblib.load("scaler.pkl")

# Example input: [frequency, angle_of_attack, chord_length, velocity, thickness]
X = np.array([[800, 0.0, 0.3048, 71.3, 0.00266]])
X_scaled = scaler.transform(X)
predicted_db = model.predict(X_scaled)
print(predicted_db)

Training

Trained with MLflow tracking and deployed via GitHub Actions CI/CD.