Particle filter method based on multiple advice distribution

A proposed distribution and particle filter technology, applied in special data processing applications, instruments, electrical digital data processing, etc., can solve problems affecting particle filter estimation accuracy, estimation accuracy impact, high time consumption, etc.

CN101055563AInactive Publication Date: 2007-10-17BEIJING INSTITUTE OF TECHNOLOGYGY
0 Cites 22 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Publication Date
2007-10-17
Estimated Expiration
Not applicable · inactive patent

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention relates to a method of particle filtering based on multi-suggesting distribution, which belongs to fields of signal processing, artificial intelligence and machine vision. The invention uses various suggesting distribution in the frame of particle filter: checking, firstly, probability distribution, extended Kalman filter, unscented Kalman filter etc., treating a sample particle using dividing and conquering sampling strategy, dividing total particle numbers into a plurality of portions, extracted from different suggesting distribution respectively. To this end, the run time of particle filter can reduced and the operating efficiency is able to be improved, while the estimated precision of particle filter can not be lost. User may carry out parameter arrangement according to the demand for time and precision. The invention has extensive application prospect in the field which relates to nonlinear filtering problem.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to a particle filter method based on multi-suggestion distribution, and the claimed technical solution belongs to the fields of signal processing, artificial intelligence and computer vision. Background technique

[0002] Nonlinear filtering problems are involved in problems in many fields, including signal processing, finance, artificial intelligence, and computer vision, among others. One of the most common methods to solve nonlinear filtering problems is to use Extended Kalman Filter (EKF), but EKF is only suitable for weak nonlinear systems, and it is easy to cause divergence for strong nonlinear systems. Another solution to the nonlinear filtering problem is the Unscented Kalman Filter (UKF). Unlike EKF, UKF does not use local linearization technology, but directly uses the nonlinear equation of the system for calculation, so as to avoid the error introduced by local linearization and avoid divergence in strong nonlinear sys...

Examples

Embodiment 1

[0083] Embodiment 1. is as follows by the state-space model of a nonlinear dynamical system:

[0084] x k =1+sin(0.04π(k-1))+0.5x k-1 +v k-1 (state transition model)

[0085] z k = 0.2 x k 2 + u k k ≤ 30 0.5 x k - 2 + u k k > 30 (measurement model)

[0086] The present inven...

Embodiment 2

[0091] Embodiment 2. Implement the present invention in a logging-while-drilling tool in a drilling system. The LWD instrument is divided into an uphole part and a downhole part. The measurement signal of the downhole part is transmitted to the surface through the mud. The uphole part first needs to filter the received downhole signal, and then decode and calculate the physical parameter value. The function of the invention is to filter the coded signal with noise to obtain the denoised signal. The invention is implemented in the uphole portion of the instrument. The present invention can obtain an ideal filtering effect (Fig. 4, Fig. 5), which provides a basis for subsequent data processing.