Unlock instant, AI-driven research and patent intelligence for your innovation.

A method for automatic identification of fragment signals based on neural network

An automatic identification and neural network technology, which is applied in the field of automatic identification of fragment signals based on neural networks, can solve the problems of incorrect identification of fragments passing through the target signal, and the inability to remove noise signals, so as to improve the effect of correct identification.

Active Publication Date: 2021-09-28
ZHONGBEI UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] In the process of fragment passing signal acquisition, there will be many noises that interfere with the accurate identification of passing signals. Although the noise in the signal can be removed by the denoising method based on wavelet decomposition and reconstruction, for some frequency components and fragment passing The noise signal with a similar signal cannot be removed, and instead forms a positive signal after wavelet filtering, which makes the subsequent identification of the fragment passing the target signal wrong.

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
  • A method for automatic identification of fragment signals based on neural network
  • A method for automatic identification of fragment signals based on neural network
  • A method for automatic identification of fragment signals based on neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] The present invention will be described in detail below with reference to the accompanying drawings.

[0023] Step 1, collect the original waveform diagram of the evacuation signal, figure 1 Effective target signals in the original map, figure 2 Noise that cannot be removed by wavelet denoising method in the original signal.

[0024] Step 2, filter all effective over-target signals in the original waveform of the collected evacuation signal and all noise to remove high frequency interference to obtain samples for neural network training.

[0025] Step 3: Observe the difference between the detection of the target signal and noise, and extract features and classification rules depending on the pulse width and smoothness of the target signal and the noise.

[0026] Step 4, build a BP neural network in MATLAB. The following is a further description of the BP neural network. The constructed BP neural network is a four-layer neural network. The first layer of the network structur...

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 discloses a method for automatic identification of fragment signals based on a neural network. The invention utilizes the extremely strong nonlinear mapping ability of the BP neural network and the ability of associative memory for external stimuli and input information to improve the detection rate in the fragment speed test system. Correctly identify fragment cross-target signals in large amounts of data.

Description

Technical field [0001] The present invention belongs to the automatic identification technology of the broken film signal, and is specifically involved in the automatic identification method based on the neural network. Background technique [0002] There is a number of noise to accurately identify the target signal during the process of breaking the target signal. Although the noise in the signal can be removed by the wavelet decomposition and the reconstruction method, the signal is used to target some frequency components. The noise signal compared to the signal cannot be removed, and the forward signal is formed after the wavelet filter is formed, and the identification of the subsequent end target signal is erroneous. Inventive content [0003] In view of this, it is an object of the present invention to provide an automatic identification method based on a radical signal signal based on a neural network, which can more efficiently remove the effects of various noise. [00...

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 Patents(China)
IPC IPC(8): G06K9/00G06N3/04
CPCG06N3/045G06F2218/02G06F2218/12G06F2218/08
Inventor 张斌李沅赵冬娥赵辉
Owner ZHONGBEI UNIV