Scholarlink

<p>This study presents an Extended Particle Filter (EPF) tailored for state estimation in chaotic nonlinear systems. Traditional estimation techniques, such as the Extended Kalman filter (EKF) and Particle filter (PF), often encounter significant challenges when dealing with chaotic dynamics, which are characterized by extreme sensitivity to initial conditions and strong nonlinearity. The proposed EPF addresses these issues by integrating advanced resampling strategies and adaptive weighting mechanisms, enhancing both accuracy and stability. To validate its effectiveness, the EPF is applied to multiple chaotic systems, and its performance is assessed using various error metrics, including Mean Error (ME) and Integral Absolute Error (IAE) under three different initialization scenarios. The simulation results reveal that the EPF consistently outperforms the EKF and PF, achieving lower estimation errors and improved tracking of system states. Furthermore, the proposed approach demonstrates computational efficiency while maintaining robustness in highly nonlinear environments. These findings confirm that the EPF provides a more reliable and accurate alternative for state estimation in complex dynamical systems, effectively overcoming the limitations of conventional methods.</p>

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

Design of an extended particle filter for state estimation in chaotic nonlinear systems

  • 期刊论文

  • 发表日期：

    2025年11月2日

查看全文
  • Hossein Zahmatkesh

摘要

This study presents an Extended Particle Filter (EPF) tailored for state estimation in chaotic nonlinear systems. Traditional estimation techniques, such as the Extended Kalman filter (EKF) and Particle filter (PF), often encounter significant challenges when dealing with chaotic dynamics, which are characterized by extreme sensitivity to initial conditions and strong nonlinearity. The proposed EPF addresses these issues by integrating advanced resampling strategies and adaptive weighting mechanisms, enhancing both accuracy and stability. To validate its effectiveness, the EPF is applied to multiple chaotic systems, and its performance is assessed using various error metrics, including Mean Error (ME) and Integral Absolute Error (IAE) under three different initialization scenarios. The simulation results reveal that the EPF consistently outperforms the EKF and PF, achieving lower estimation errors and improved tracking of system states. Furthermore, the proposed approach demonstrates computational efficiency while maintaining robustness in highly nonlinear environments. These findings confirm that the EPF provides a more reliable and accurate alternative for state estimation in complex dynamical systems, effectively overcoming the limitations of conventional methods.