Predictive Modeling of Flexible EHD Pumps using Kolmogorov-Arnold Networks

TL;DR

This paper introduces a Kolmogorov-Arnold Network that predicts pressure and flow rate in flexible EHD pumps with high accuracy, outperforming traditional models and providing interpretable symbolic formulas.

Contribution

The paper presents a novel KAN model with learnable spline activation functions that improves nonlinear function approximation in EHD pump prediction tasks.

Findings

KAN outperforms RF and MLP models in accuracy

Symbolic formulas from KAN offer insights into pump behavior

KAN demonstrates both high accuracy and interpretability

Abstract

We present a novel approach to predicting the pressure and flow rate of flexible electrohydrodynamic pumps using the Kolmogorov-Arnold Network. Inspired by the Kolmogorov-Arnold representation theorem, KAN replaces fixed activation functions with learnable spline-based activation functions, enabling it to approximate complex nonlinear functions more effectively than traditional models like Multi-Layer Perceptron and Random Forest. We evaluated KAN on a dataset of flexible EHD pump parameters and compared its performance against RF, and MLP models. KAN achieved superior predictive accuracy, with Mean Squared Errors of 12.186 and 0.001 for pressure and flow rate predictions, respectively. The symbolic formulas extracted from KAN provided insights into the nonlinear relationships between input parameters and pump performance. These findings demonstrate that KAN offers exceptional accuracy and interpretability, making it a promising alternative for predictive modeling in electrohydrodynamic pumping.