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

Industrial steam quantity prediction method and device based on machine learning

A technology of machine learning and prediction methods, applied in neural learning methods, neural architectures, biological neural network models, etc., can solve problems such as difficult to achieve results, difficult to construct significant features of prediction models, and little improvement in the accuracy of prediction results, etc., to achieve The effect of high accuracy

Inactive Publication Date: 2019-10-22
INSPUR ARTIFICIAL INTELLIGENCE RES INST CO LTD SHANDONG CHINA
View PDF5 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, these simple and direct feature construction methods are difficult to construct the salient features required by the prediction model, and the improvement in the accuracy of the prediction results of the prediction model is very small, and it is difficult to be effective

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
  • Industrial steam quantity prediction method and device based on machine learning
  • Industrial steam quantity prediction method and device based on machine learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0058] Attached figure 1 This embodiment proposes an industrial steam volume prediction method based on machine learning. The prediction method is based on the historical operating condition data collected by the boiler sensor and the actual exhaust steam volume. First, the historical operating condition data is decomposed by time series to obtain the historical operating condition The inherent trend and period information of the data are two characteristic data, and then the LSTM algorithm is used to learn the inherent trend and period information of the historical operating condition data, and then the LSTM algorithm prediction model is constructed with the aid of the actual emission training corresponding to the historical operating condition data. Finally, The newly collected working condition data of the boiler sensor is decomposed into the LSTM algorithm prediction model after time series decomposition, and the predicted steam volume of the boiler can be output.

[0059] In ...

Embodiment 2

[0080] Attached figure 2 In this embodiment, an industrial steam volume prediction device based on machine learning is proposed, and the prediction device includes:

[0081] The collection module 1 is used to collect the historical working condition data collected by the boiler sensor, the actual amount of steam discharged, and the newly collected working condition data of the boiler sensor;

[0082] Time series decomposition module 2, used to decompose the collected historical working condition data and new working condition data in time series, and obtain the two characteristic data of internal trend and period information of historical working condition data and new working condition data;

[0083] LSTM algorithm module 3, used to learn the inherent trend and cycle information of historical working condition data;

[0084] The training building module 4 is used to input the actual emissions corresponding to the historical working condition data into the LSTM algorithm module 3 to ...

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 an industrial steam quantity prediction method based on machine learning and relates to the technical field of industrial thermal power generation. The prediction method is based on historical working condition data collected by a boiler sensor and the actually discharged steam amount. The method comprises the following steps of carrying out time series decomposition on historical working condition data to obtain two characteristic data including an internal trend and periodic information of the historical working condition data; learning the internal trend and period information of the historical working condition data and the actual discharge amount corresponding to the historical working condition data through an LSTM algorithm; finally, training and constructingan LSTM algorithm prediction model, inputting working condition data newly collected by a boiler sensor into the LSTM algorithm prediction model after being subjected to time sequence decomposition,and outputting the predicted steam amount of the boiler. The invention further provides an industrial steam quantity prediction device based on machine learning. The prediction device is combined withthe prediction method, and a steam quantity prediction result with higher accuracy can be output.

Description

Technical field [0001] The invention relates to the technical field of industrial thermal power generation, in particular to a method and device for predicting the amount of industrial steam based on machine learning. Background technique [0002] In the traditional steam forecast of industrial thermal power generation, forecasters simply perform routine analysis on the data provided by sensors, such as routine outlier processing, data smoothing, data standardization, correlation analysis and other data cleaning and preprocessing , And in terms of feature construction, it is usually just a simple four arithmetic operations between two features to construct a new feature by simply using the feature data collected by the sensor. However, these simple and direct feature construction methods are difficult to construct the salient features required by the prediction model, and the accuracy of the prediction results of the prediction model is minimally improved, and it is difficult to ...

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): G06N3/04G06N3/08
CPCG06N3/049G06N3/08G06N3/045
Inventor 安程治李锐于治楼
Owner INSPUR ARTIFICIAL INTELLIGENCE RES INST CO LTD SHANDONG CHINA
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