Comparative of Genetic Fuzzy regression techniques for aeroacoustic phenomenons

TL;DR

The paper addresses modeling airfoil self-noise for aeroacoustics by comparing genetic fuzzy systems across three paradigms: brute-force TSK regression, cascading GFT, and a clustering-based fuzzy inference. It demonstrates that while brute-force can yield accurate results, its parameter explosion ($18{,}825$ parameters) makes it impractical, and cascading approaches struggle with interpretability and stability. A clustering-based approach, reducing parameters to as few as $90$, delivers strong predictive performance with improved training efficiency and robustness to outliers. Overall, the study provides a scalable, physically relevant regression tool for complex aeroacoustic phenomena with implications for aerospace, automotive, and drone design.

Abstract

This study investigates the application of Genetic Fuzzy Systems (GFS) to model the self-noise generated by airfoils, a key issue in aeroaccoustics with significant implications for aerospace, automotive and drone applications. Using the publicly available Airfoil Self Noise dataset, various Fuzzy regression strategies are explored and compared. The paper evaluates a brute force Takagi Sugeno Kang (TSK) fuzzy system with high rule density, a cascading Geneti Fuzzy Tree (GFT) architecture and a novel clustered approach based on Fuzzy C-means (FCM) to reduce the model's complexity. This highlights the viability of clustering assisted fuzzy inference as an effective regression tool for complex aero accoustic phenomena. Keywords : Fuzzy logic, Regression, Cascading systems, Clustering and AI.

Figures (23)

• Figure 1: Clustering of the dataset
• Figure 2: Training set (blue) and prediction (red)
• Figure 3: Testing set (blue) and prediction (red)
• Figure 4: Fitness evolution
• Figure 5: Clustering of the dataset