Scholarlink

This paper focuses on the parameter and state estimation problems for linear single-input single-output errors-in-variables systems, which are modeled through observable canonical state-space representations. The system dynamics are subject to process disturbances, while the input and output measurements are corrupted by white noise. A parametric model structure is constructed for the parameter estimation. Based on the bias compensation principle and Kalman filtering technique, a hybrid algorithm is developed to jointly estimate system parameters and states. The numerical simulation example tests the effectiveness of the proposed algorithm.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Recursive Parameter and State Estimation of Dynamical Models for Errors-in-Variables State-Space Systems

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Jingsheng Chen,
  • Xiao Zhang,
  • Feng Ding,
  • Yanjun Liu,
  • Siyu Liu

摘要

This paper focuses on the parameter and state estimation problems for linear single-input single-output errors-in-variables systems, which are modeled through observable canonical state-space representations. The system dynamics are subject to process disturbances, while the input and output measurements are corrupted by white noise. A parametric model structure is constructed for the parameter estimation. Based on the bias compensation principle and Kalman filtering technique, a hybrid algorithm is developed to jointly estimate system parameters and states. The numerical simulation example tests the effectiveness of the proposed algorithm.