Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

RBF neural network optimization method based on improved particle swarm optimization

A technology for improving particle swarm and neural network, applied in the field of RBF neural network optimization based on improved particle swarm algorithm, can solve the problem of local optimal convergence speed of PSO algorithm, avoid falling into local optimal, enhance accuracy and stability, good adaptability

Pending Publication Date: 2021-11-09
JIANGSU UNIV OF SCI & TECH
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to solve the technical problem that the existing PSO algorithm is easy to fall into the local optimum and the late convergence speed is slow, and on this basis, it provides a RBF neural network optimization method based on the improved particle swarm optimization algorithm

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • RBF neural network optimization method based on improved particle swarm optimization
  • RBF neural network optimization method based on improved particle swarm optimization
  • RBF neural network optimization method based on improved particle swarm optimization

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] Exemplary embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the specific implementations shown and described in the drawings are only exemplary, and are intended to illustrate the application principle of the present invention, not to limit the application scope of the present invention.

[0039] The invention discloses an RBF neural network optimization method based on an improved particle swarm algorithm, figure 2 The topology of the RBF neural network is given, and the RBF neural network model for sea clutter prediction is used as an example to illustrate, figure 1 The specific steps of this embodiment are given:

[0040] Step 1: Determine the topology of the RBF neural network. The RBF neural network is a simple three-layer structure, in which the number of nodes in the input and output layers is determined by specific problems, and the number of hidden layers is generally cluster...

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

No PUM Login to View More

Abstract

The invention belongs to the technical field of neural network optimization, and particularly relates to an RBF (Radial Basis Function) neural network optimization method based on an improved particle swarm algorithm, which takes a piecewise function as a particle swarm inertia weight change strategy and takes a transformed sigmoid function as a change strategy of a particle swarm learning factor. An optimal RBF neural network initial parameter is searched through an improved particle swarm algorithm, so that a more accurate prediction model is trained to predict sea clutters. According to the method, a particle swarm optimization process is divided into three stages: the first stage is mainly used for searching a global optimal general position, the second stage is evolved from global search to local exploration, and the third stage is mainly used for local fine exploration. The three optimization stages are clear in division of labor, so that the particle swarm has relatively strong global search and local exploration capabilities, the optimization precision and convergence speed are improved, and the precision and stability of the RBF neural network are improved.

Description

technical field [0001] The invention belongs to the technical field of neural network optimization, and specifically relates to an RBF neural network optimization method based on an improved particle swarm algorithm. Background technique [0002] With the continuous upgrading of radar technology, all kinds of radars are more and more widely used in civil and military fields. When radar detects at sea, the echo is mixed with high-intensity sea clutter, which has a great impact on both the monitoring of the marine environment and the detection of sea targets. In this context, the realization of low-cost, high-precision sea clutter prediction and suppression will greatly improve the radar's ability to monitor the ocean, and play a key role in the observation of the national marine environment and the enhancement of national defense forces. [0003] Scholars have established many classic statistical models of sea clutter through in-depth research on the statistical characterist...

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
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06N3/08G06N3/00
CPCG06N3/08G06N3/006
Inventor 尚尚何康宁王召斌杨童刘明李维燕陈康宁李朕
Owner JIANGSU UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products