Predictive modeling of flexible EHD pumps using Kolmogorov-Arnold Networks  

作　　者：Yanhong Peng Yuxin Wang Fangchao Hu Miao He Zebing Mao Xia Huang Jun Ding 

机构地区：[1]College of Mechanical Engineering,Chongqing University of Technology,Chongqing 400054,China [2]Department of Mechanical Systems Engineering,Nagoya University,Tokai National Higher Education and Research,Nagoya 464-8603,Japan [3]School of Energy and Power,Jjiangsu University of Science and Technology,Zhenjiang 212100,China [4]Faculty of Engineering,Yamaguchi University,Yamaguchi 755-8611,Japan

出　　处：《Biomimetic Intelligence & Robotics》2024年第4期109-111,共3页仿生智能与机器人(英文)

基　　金：supported by Innovative Research Group of Chongqing Municipal Education Commission(CXQT19026);Cooperative Project between Chinese Academy of Sciences and University in Chongqing(Hz2021011);supported by the Research Startup Fund of Chongqing University ofTechnology(0119240197).

摘　　要：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 predic-tions,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.

关 键 词：Kolmogorov-Arnold Networks Electrohydrodynamic pumps Neural network 

分 类 号：O17[理学—数学]