Academic Journal
Predictive modeling of flexible EHD pumps using Kolmogorov–Arnold Networks
| Title: | Predictive modeling of flexible EHD pumps using Kolmogorov–Arnold Networks |
|---|---|
| Authors: | Yanhong Peng, Yuxin Wang, Fangchao Hu, Miao He, Zebing Mao, Xia Huang, Jun Ding |
| Source: | Biomimetic Intelligence and Robotics, Vol 4, Iss 4, Pp 100184- (2024) |
| Publisher Information: | Elsevier, 2024. |
| Publication Year: | 2024 |
| Collection: | LCC:Electrical engineering. Electronics. Nuclear engineering LCC:Electronic computers. Computer science |
| Subject Terms: | Kolmogorov–Arnold Networks, Electrohydrodynamic pumps, Neural network, Electrical engineering. Electronics. Nuclear engineering, TK1-9971, Electronic computers. Computer science, QA75.5-76.95 |
| More Details: | 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 0.012 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. |
| Document Type: | article |
| File Description: | electronic resource |
| Language: | English |
| ISSN: | 2667-3797 |
| Relation: | http://www.sciencedirect.com/science/article/pii/S2667379724000421; https://doaj.org/toc/2667-3797 |
| DOI: | 10.1016/j.birob.2024.100184 |
| Access URL: | https://doaj.org/article/acf3cd2ba81040e19e378a942a266d14 |
| Accession Number: | edsdoj.f3cd2ba81040e19e378a942a266d14 |
| Database: | Directory of Open Access Journals |
| ISSN: | 26673797 |
|---|---|
| DOI: | 10.1016/j.birob.2024.100184 |
| Published in: | Biomimetic Intelligence and Robotics |
| Language: | English |