Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Mixed gas identification method based on convolutional neural network

A convolutional neural network and mixed gas technology, which is applied in the field of time series classification of data collected by sensors, can solve problems such as the inability to directly classify mixed gas data, and achieve the effect of high speed and high accuracy.

Active Publication Date: 2019-10-08
BEIJING TECHNOLOGY AND BUSINESS UNIVERSITY +1
View PDF8 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The present invention can overcome the problem that VGG applied to image classification and CNN networks such as Google-Net cannot be directly applied to classify mixed gas data due to the limitation of input data in the prior art

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
  • Mixed gas identification method based on convolutional neural network
  • Mixed gas identification method based on convolutional neural network
  • Mixed gas identification method based on convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0089] In the following, the present invention will be further described as an embodiment by illustrating the process of identifying the gas mixture in the UCI public data set "Gas sensor array exposed toturbulent gas mixtures Data Set" in conjunction with the accompanying drawings.

[0090] Method flow chart as figure 1 shown. The inventive method comprises:

[0091] 1) Analyze and process the original time-series data: search for missing values ​​and abnormal values ​​in the original data collected by the MOX gas sensor, and analyze the characteristics of the data;

[0092] 2) Map the two-dimensional raw data into a picture-like matrix: design a data mapping mode, map the processed data into a picture-like matrix according to different modes, and generate a corresponding sample set (Sample-set);

[0093] 3) Utilize the convolutional neural network to train the image-like matrix: select a convolutional neural network model to train the training set of a plurality of sample ...

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 mixed gas recognition method based on a convolutional neural network, and the method comprises the steps of mapping the original gas time sequence data obtained through a sensor into a similar image matrix in different modes, and carrying out the feature extraction and classification through a convolutional neural network model CNN, thereby achieving the classification ofthe mixed gas. The method is based on the classification advantages of the convolutional neural network, is applied to the classification field of the mixed gas of the time sequence, extracts more comprehensive features of the matrix data by using the convolution operation of the CNN, is high in speed, and also can obtain the higher accuracy. According to the method, the problem that in an existing mixed gas classification technology, due to the limitation of the input data, the VGG, Google-Net and other CNN networks for the image classification cannot be directly applied to classify the mixed gas data, can be solved.

Description

technical field [0001] The invention relates to a mixed gas type identification technology, in particular to a mixed gas identification method based on a convolutional neural network, and belongs to the technical field of time series classification of data collected by sensors. Background technique [0002] MOX (metal oxide) gas sensor is a gas sensor using metal oxide gas sensor as a sensitive element. It has the advantages of small size, fast response speed, low cost and long service life, so it is widely used in toxic gas , flammable and explosive gases, industrial waste gas and other gas detection fields. The MOX gas sensor reacts with the gas to be measured physically and chemically, causing a change in resistance, and converting information related to gas type, concentration, etc. into a single signal output. The gas sensor reacts differently in different single gases, resulting in different sensor response values. Therefore, the time series data collected by the MOX...

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
IPC IPC(8): G06K9/62G06N3/04
CPCG06N3/044G06N3/045G06F18/2155
Inventor 于重重韩璐肖开泰孟祥宁赵霞
Owner BEIJING TECHNOLOGY AND BUSINESS UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com