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

Small sample gas concentration prediction method based on improved GAN and LSTM

A technology of gas concentration and prediction method, applied in prediction, neural learning method, data processing application, etc., to solve the problem of small sample gas concentration prediction, good learning ability, and the effect of improving accuracy

Pending Publication Date: 2022-05-10
TONGJI UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a small-sample gas concentration prediction method based on improved GAN (Generative Adversarial Network, generating confrontation network) and LSTM (Long Short Term Memory Network, long-short-term memory network) in order to overcome the defects in the above-mentioned prior art , to solve the problem of small sample gas concentration prediction and improve the accuracy and efficiency of gas concentration prediction

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
  • Small sample gas concentration prediction method based on improved GAN and LSTM
  • Small sample gas concentration prediction method based on improved GAN and LSTM
  • Small sample gas concentration prediction method based on improved GAN and LSTM

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0061] Such as figure 1 As shown, a small sample gas concentration prediction method based on improved GAN and LSTM includes the following steps:

[0062] S1. Obtain historical data of the target gas concentration;

[0063] S2. Preprocessing the historical data of the target gas concentration (first time aligning the data, then performing missing value processing, noise processing, and finally data integration), and constructing a historical data set;

[0064] S3. Expand the historical data set through the improved GAN to obtain the expanded data set, wherein the improved GAN includes a generating network and a discriminant network, the generating network is composed of a gated recurrent unit network, and the discriminant network is a convolutional neural network. The convolutional neural network includes a maximum pooling layer and a fully connected layer, and uses the Wasserstein distance to construct a loss function. The Wasserstein distance expression is as follows:

[0...

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 a small sample gas concentration prediction method based on improved GAN and LSTM. The method comprises the following steps: acquiring historical data of target gas concentration; preprocessing the historical data of the target gas concentration, and constructing to obtain a historical data set; a historical data set is expanded through the improved GAN, an expanded data set is obtained, and in order to avoid the gradient disappearance problem of the GAN in the training process, a Wasserstein distance is used for constructing a loss function to improve the GAN; dividing the expanded data set into a training set and a test set according to a set proportion; training the LSTM network by using the training set and the test set to obtain a gas concentration prediction model; and inputting gas data which actually needs to be predicted into the gas concentration prediction model, and outputting to obtain a corresponding predicted gas concentration. Compared with the prior art, the method has the advantages that negative effects caused by insufficient samples can be eliminated, the problem of small sample gas concentration prediction can be effectively solved, and the gas concentration prediction precision is improved.

Description

technical field [0001] The invention relates to the technical field of pollutant gas detection, in particular to a small-sample gas concentration prediction method based on improved GAN and LSTM. Background technique [0002] With the large-scale development of the shipbuilding industry, my country has successively built a number of large-scale shipbuilding bases. While promoting the development of my country's maritime economy and port trade and improving national defense strength, it also has a certain negative impact on the environmental quality around the shipyard. . Due to the large amount of pollutants discharged in the process of ship construction and repair, it is easy to become the main source of environmental pollution in the region. Especially in the process of painting ships in painting workshops, docks and other open places, the pollutants emitted are mainly volatile organic compounds (Volatile Organic Compounds, VOCs), which are toxic and fugitive. [0003] In...

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): G06Q10/04G06N3/04G06N3/08
CPCG06Q10/04G06N3/08G06N3/044G06N3/045
Inventor 罗崔月凌卫青
Owner TONGJI UNIV
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