Intelligent smell recognition method for gas

A technology of intelligent recognition and gas, applied in neural learning methods, character and pattern recognition, instruments, etc., can solve problems such as limited concentration, cross-sensitivity of gas sensors, etc.

Active Publication Date: 2021-09-10
CHINA UNIV OF PETROLEUM (EAST CHINA)
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, relying solely on gas sensor technology is limited by the concentration of the gas or odor to be measured
Moreover, due to the common problem o

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
  • Intelligent smell recognition method for gas
  • Intelligent smell recognition method for gas
  • Intelligent smell recognition method for gas

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0067] The present invention will be described in further detail below.

[0068] see Figure 1-Figure 5 , an olfactory intelligent recognition method for gas, comprising the steps of:

[0069] S100: Collect P kinds of known gases, and build an odor data sample library. The samples in the data sample library are sensor response data and real labels of known gases. The construction process of the odor data sample library is as follows:

[0070] Let the time period be T. In this period of time T, the data value is taken every time at the same interval, and a total of t data values ​​are extracted. When the time period T ends, each sensor will collect t data values.

[0071] For the p-th known gas, use the j-th gas sensor pair to detect the known gas, and transmit the signal detected by the j-th sensor to the amplification circuit to obtain the j-th voltage signal value. For the i-th known gas, at time In section T, t voltage signal values ​​are obtained.

[0072] For the jth s...

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 relates to an intelligent smell recognition method for gas, which comprises the following steps: firstly, collecting P known gases, constructing a smell data sample library, secondly, constructing an intelligent gas recognition model and training by using data in the smell data sample library, and finally, performing signal feature extraction on to-be-detected gas and constructing a feature vector X, and inputting the X into a trained gas intelligent identification model, and outputting a predicted gas type label of the to-be-detected gas. According to the method, the intelligent gas recognition model is constructed on the basis of the neural network, meanwhile, the weight with the additional momentum factor, the threshold with the additional momentum factor and the self-adaptive learning rate are set to influence the training process, and finally intelligence and reliability of gas recognition are obtained.

Description

technical field [0001] The invention relates to the field of computer olfaction, in particular to an olfactory intelligent recognition method for gas. Background technique [0002] At present, the intelligent identification of gases is very important in various fields such as industry, agriculture, and commerce, including the identification of toxic, harmful, flammable and explosive gases in the petrochemical and coal mine gas fields, and the identification of different varieties such as liquor, wine, and coffee in the field of consumer goods. . Gas identification or odor identification has always been a difficult problem in various industries. Different from color recognition based on the wavelength of light, it is difficult for gases or odors to capture obvious physical and chemical characteristics similar to the wavelength of light, and it is difficult to identify different odors only based on specific molecular characteristics of gases. At present, the identification o...

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): G06K9/62G06N3/04G06N3/08
CPCG06N3/04G06N3/08G06F18/241G06F18/253
Inventor 王宇赫余梦琪毛强强刘帅辰
Owner CHINA UNIV OF PETROLEUM (EAST CHINA)
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
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap