Estimation method of continuous-discrete maximum correlation entropy distributed cubature kalman filter
By employing the continuous-discrete maximum correlation entropy distributed capillary Kalman filter method in a multi-sensor network, the error and non-Gaussian noise problems of traditional algorithms when dealing with continuous-discrete nonlinear models are solved, achieving accurate state estimation and wide adaptability for aircraft targets.
Patent Information
- Application Number
- CN202310639934.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-05-31
- Publication Date
- 2026-07-28
- Estimated Expiration
- 2043-05-31
AI Technical Summary
Existing target tracking algorithms suffer from problems such as large discretization errors, limited application range, and inability to handle non-Gaussian noise when dealing with continuous-discrete nonlinear models, resulting in inaccurate state estimation.
The continuous-discrete maximum correlation entropy distributed capacitive Kalman filter method is adopted. By establishing a continuous-discrete target tracking model of a multi-sensor network, and combining the maximum correlation entropy criterion, 1.5-order ITO Taylor expansion, cubic capacitive rule and average consensus method, accurate target state information is calculated, non-Gaussian noise is processed and estimation accuracy is improved.
It improves the accuracy and reliability of target state estimation, breaks through the limitation of sampling interval, has a wide range of applications, and can perform accurate aircraft target tracking in non-Gaussian noise environments.