A monitoring system based on probabilistic neural network and its smoothing parameter optimization method
A technology of probabilistic neural network and monitoring system, applied in the direction of neural learning method, biological neural network model, radio wave measurement system, etc., can solve the problem that the receiver cannot analyze the integrity of the satellite
Active Publication Date: 2021-09-10
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0006] The purpose of the present invention is to solve the problem that the receiver cannot independently complete the satellite integrity analysis in the GPS single system in the precision approach navigation (LPV-200), and proposes a monitoring system based on a probabilistic neural network and its smoothing parameter optimization method
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 1
[0087] This embodiment illustrates the present invention in detail figure 1 It is a structural diagram of a monitoring system based on a probabilistic neural network.
[0088] This example describes the specific implementation method and steps in the case of using GPS single-system positioning.
[0089] Step 1 utilizes the receiver to broadcast ephemeris and pseudorange information. The data used in this embodiment was collected on November 10, 2015, and the data includes the ephemeris broadcast by the GPS system and the received pseudorange information;
[0090] Step 2 calculates the altitude angle of the visible satellites according to the ephemeris, and calculates the error distribution of each visible satellite measurement pseudorange according to the altitude angle. In this example, the calculation of the pseudorange error distribution of the GPS system refers to the mathematical model in Table 1;
[0091] Table 1 Pseudorange error model of GPS system
[0092]
[009...
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 relates to a monitoring system based on a probability neural network and a smoothing parameter optimization method thereof, belonging to the technical fields of artificial intelligence and satellite navigation. The monitoring system includes an input layer, a pattern layer, a summation layer, a comparison layer and an output layer module; the parameter optimization method includes: 1) initializing parameters; 2) initializing particle velocity and position; 3) updating particle velocity and position; 4) Calculate the particle fitness; 5) Update the historical optimal value of the particle; 6) Update the global optimal value of the particle; 7) Determine whether the requirements of the monitoring system are met, if true, skip to 10); otherwise, skip to 8); 8) Judging whether all particles have been processed, if it is skip to 9), otherwise skip to 4); 9) judge whether it reaches the maximum number of iterations, if it is skip to 10), otherwise skip to 3); 10) output the fitness function of the particle . The minimum detectable fault in the vertical direction of the present invention can be controlled within 35m; the missed detection rate and false alarm rate can be effectively controlled.
Description
technical field [0001] The invention relates to a monitoring system based on a probability neural network and a smoothing parameter optimization method thereof, belonging to the technical fields of artificial intelligence and satellite navigation. Background technique [0002] When using a satellite navigation system for positioning, the integrity of the received data must be evaluated to ensure the reliability of the positioning results. Receiver Autonomous Integrity Monitoring (RAIM) is a satellite integrity check method performed independently by the receiver to provide real-time protection to the user. When the satellite navigation system fails or cannot provide the necessary positioning accuracy, RAIM will remind the user in time to avoid accidents. According to the fact that the pseudo-range error caused by satellite failure may lead to incorrect positioning, the traditional RAIM based on hypothesis testing uses the measured noise and false alarm probability to detect...
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 Patent Type & Authority Patents(China)
IPC IPC(8): G06N3/04G06N3/08G06N3/00G01S19/23
CPCG06N3/006G06N3/08G01S19/23G06N3/045
Inventor 许承东郑学恩彭雅奇牛飞赵靖
Owner BEIJING INSTITUTE OF TECHNOLOGYGY