Improved bootstrapping fission particle filtering method and DSP (digital signal processor) hardware realization method thereof
A particle filter, particle technology, applied in the field of nonlinear system filtering and electronics
Inactive Publication Date: 2012-06-20
JIANGSU UNIV OF SCI & TECH
View PDF3 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, the practical particle filter algorithm has not yet been successfully developed, and it is the main content of the present invention to design a particle filter algorithm hardware module with fast computing speed, reliable performance and less resource occupation.
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0026] Embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings.
[0027]The calculation amount of the FBPF algorithm is relatively large, which is unfavorable for being applied to a system with high real-time performance. The invention aims at improving the operation speed and filtering precision of the FBPF algorithm, and adopts methods of reducing division operations and improving weight calculation. Through the analysis of the complexity of the FBPF algorithm, we can see that the complexity of the FBPF algorithm is mainly determined by the complexity of the state space model and the complexity of the algorithm itself. To reduce the complexity of an algorithm, it is necessary to start with a simplified algorithm; most nonlinear function calculations in the FBPF algorithm are concentrated in the weight calculation step, and the normalization of weights increases the complexity of the algorithm. On the other hand, be...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses an improved bootstrapping fission particle filtering method and a simulation method thereof. A weight normalization step is consolidated to the steps such as result output, weight sharpening detection, resampling and the like so as to reduce a mass of division operation and reduce the hardware expenditure. According to the characteristic that a particle filtering algorithm is high in computation, a TMS320VC5509A digital signal processor (DSP) of the TI company is used for realizing the particle filtering algorithm, a CCSLink tool integrated in an MATLAB 7.1(matrix laboratory 7.1) is used for connecting the C5509 with the integrated development environment CCS 2.21 (common channel signaling 2.21) thereof, a program for improving an FBPF (bootstrapping fission particle filtering) algorithm is wrote in the DSP, and data is transmitted to the MATLAB through a real-time data exchange (RTDX) channel so as to be stored, analyzed and drawn; the performance of the particle filtering algorithm is analyzed by adopting a method in collaborative simulation of the MATLAB and CCS.
Description
technical field [0001] The invention relates to a method for realizing particle filtering and simulation by using a DSP hardware system, and belongs to the field of nonlinear system filtering and electronic technology. Background technique [0002] Particle filter is a statistical filtering method based on Monte Carlo method and recursive Bayesian estimation, which is suitable for any nonlinear stochastic system with non-Gaussian background that can be represented by state space model and traditional Kalman filter. However, particle filtering has problems such as particle degradation, loss of particle diversity, year-on-year increase in the number of particles and computational complexity. For this reason, many improved methods have been proposed, among which the fission bootstrap particle filter (FBPF) algorithm is to improve the resampling process on the basis of the particle filter algorithm, and introduces weight sharpening detection and "weight sorting (Sorting)-fission...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More IPC IPC(8): G06F17/50
Inventor 朱志宇李阳薄超张冰王建华伍雪冬赵强王敏杨官校
Owner JIANGSU UNIV OF SCI & TECH