arXiv 2506.104342025-06-12cs.LGcs.SYeess.SY

基于Kolmogorov-Arnold网络的系统辨识：以Buck变换器为例的案例研究

System Identification Using Kolmogorov-Arnold Networks: A Case Study on Buck Converters

Eindhoven University of Technology（埃因霍温理工大学）

Nart Gashi, Panagiotis Kakosimos, George Papafotiou

备注：: 2025 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works
发表信息：: IEEE PHM 2025 conference

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本研究将Kolmogorov-Arnold网络（KAN）应用于buck变换器的系统辨识，通过可学习激活函数逼近状态导数、构建可解释状态空间模型，实验验证其能准确辨识动力学、验证一致性并检测参数变化。

摘要：

Kolmogorov-Arnold网络（KAN）正作为一种强大框架，用于动态系统中可解释且高效的系统辨识。借助Kolmogorov-Arnold表示定理，KAN可通过可学习激活函数实现函数逼近，相较传统神经网络具备更优的可扩展性、准确性与可解释性。本文研究KAN在buck变换器系统动力学建模与分析中的应用，聚焦状态空间参数估计及系统方程发现。该方法利用仿真数据，通过KAN逼近状态导数，构建可解释的状态空间表示，并通过数值实验验证这些模型。结果表明KAN能够准确辨识系统动力学、验证模型一致性并检测参数变化，为其在现代工业系统中的系统辨识应用提供了宝贵见解。

英文摘要：

Kolmogorov-Arnold Networks (KANs) are emerging as a powerful framework for interpretable and efficient system identification in dynamic systems. By leveraging the Kolmogorov-Arnold representation theorem, KANs enable function approximation through learnable activation functions, offering improved scalability, accuracy, and interpretability compared to traditional neural networks. This paper investigates the application of KANs to model and analyze the dynamics of a buck converter system, focusing on state-space parameter estimation along with discovering the system equations. Using simulation data, the methodology involves approximating state derivatives with KANs, constructing interpretable state-space representations, and validating these models through numerical experiments. The results demonstrate the ability of KANs to accurately identify system dynamics, verify model consistency, and detect parameter changes, providing valuable insights into their applicability for system identification in modern industrial systems.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。