.png){kind=icon}
返回
Instrumental variable framework for nonlinear continuous-time system identification
.png){kind=icon}
OA
AI
DOI：10.1016/j.jfranklin.2026.108619.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
This paper presents NLIVSVF, an iterative instrumental variable estimator for nonlinear continuous-time output-error models based on sampled input-output data. The method uses continuous-discrete extended Kalman filter-based derivative estimates to compute the nonlinear terms required for forming a linear regression used in parameter estimation. The resulting regression is solved using an instrumental variable procedure. Sparse model structures are identified through regression over libraries of candidate nonlinear terms, enabling parsimonious model discovery. By formulating the identification problem directly in continuous time, the approach avoids intermediate discretization. The method is evaluated on a simulated nonlinear system with both known and unknown nonlinearities, demonstrating reliable performance under stiff dynamics and noisy measurements.
Keyword:
Control systems
Continuous-time models
Instrumental variable
Nonlinear systems
Parameter estimation
Sparse regression
System identification
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
J
IF:
4.2
论文数:
925
被引数:
0
机构
引用论文
.png){kind=icon}
分享收藏Discovering governing equations from data by sparse identification of nonlinear dynamical systems通过非线性动力系统的稀疏识别从数据中发现控制方程OAAI
OAAI分享收藏
查看更多内容