.png){kind=icon}
.png){kind=icon}
Return
Removing Structured Influences in Instrumental-Variable-Based State-Variable-Filter Identification
.png){kind=icon}
OA
AI
DOI：10.1016/j.ejcon.2026.101506.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This paper addresses the impact of structured influences on continuous-time system identification using instrumental variable methods. Structured influences – including initial conditions, trends, localized nonlinearities, and intersample mismatches – violate standard assumptions and lead to biased parameter estimates. Building on the Frisch–Waugh–Lovell Theorem, we derive a projection-based correction framework for instrumental variable methods that handles general nuisance regressors and addresses practical issues such as rank deficiency. The framework is illustrated for common types of structured influences. A simulation study based on the instrumental-variable state-variable filter method confirms that the proposed approach effectively removes effects of structured influences.
Keywords:
Instrumental Variables
Continuous-time
System Identification
Parameter estimation
IVSVF
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.