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

Industrial steam terminal consumption prediction model establishment and prediction method and system

A technique for forecasting models and establishing methods, which is applied in forecasting, biological neural network models, energy industry, etc., and can solve problems such as low precision of forecasting methods, and achieve the effects of avoiding insufficient steam supply, untimely feedback, and high detection accuracy

Pending Publication Date: 2021-04-06
上海全应科技有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to solve the deficiencies in the prior art, the present invention provides an industrial steam terminal consumption forecasting model establishment, forecasting method and system to solve the problem of low accuracy of the existing forecasting methods

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 terminal consumption prediction model establishment and prediction method and system
  • Industrial steam terminal consumption prediction model establishment and prediction method and system
  • Industrial steam terminal consumption prediction model establishment and prediction method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0047] This embodiment discloses a method for establishing a prediction model for end consumption of industrial steam, the method comprising the following steps:

[0048] Step 1, making a sample data set: collect steam consumption data in units of hours to obtain hour-level data sequences; the steam consumption data in this step is historical steam consumption data collected systematically.

[0049] In this example, the historical steam consumption data of a thermal power plant in Xianyang is collected. The steam consumption end of the thermal power plant includes 7 enterprises, and the steam consumption from April 1 to May 30, 2019 is extracted from the database of the monitoring system The data form an hour-level historical steam consumption data sequence, with a total of 1349 historical data.

[0050] Step 2, data preprocessing: If there is missing data in the data, the missing values ​​need to be filled, and then the abnormal values ​​of the overall data after filling the ...

Embodiment 2

[0080] This embodiment discloses a method for predicting the final consumption of industrial steam. The model obtained in Embodiment 1 is used to predict the steam consumption at a certain time in the future. According to the data set L, the input end of the prediction model needs to know The steam consumption of one day, so the method of the present invention can predict the steam consumption of the next day. The prediction method in this embodiment is specifically:

[0081] Step 1, the data in this embodiment are 165 pieces of data in the test set of embodiment 1. Collect data according to the method of step 1 to step 2 in embodiment 1 and carry out abnormal value and missing value processing to data; Calculate {o t ' 1 ,o' t2 ,o' t3 ,o t ' 4 ,o t ' 5 ,o' t6 ,o' t7 ,x' t1 ,x' t2 ,x' t3 ,xt ' 4 ,x' t5 ,x t ' 6 ,x' t7} these data values.

[0082] Step 2: Input the data obtained in Step 1 into the prediction model obtained in Embodiment 1 after one-hot encodi...

Embodiment 3

[0085] This embodiment discloses a system for establishing a prediction model of end consumption of industrial steam, including a data acquisition module, a data preprocessing module, a data calculation module and a model training module.

[0086] Among them, the data acquisition module is used to collect steam consumption data in units of hours to obtain the data sequence, and the DCS system of the boiler in actual production will save the steam consumption in real time; the data preprocessing module is used to convert abnormal values ​​in the data sequence Set to the missing value NaN, and fill the missing value in the data sequence; see the detailed record of step 2 of embodiment 1 for the specific filling and removal process; the data calculation module is used to calculate the difference between the steam consumption at adjacent moments, as in step 3 The difference between steam consumption at time t-1 and steam consumption at time t-2, and the position of time t in one da...

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 terminal consumption prediction model establishment and prediction method and system, and the method comprises the steps: collecting data, and carrying out the preprocessing of the data; constructing a data set according to the processed data and the time features, taking y't1 in the data set as the output of a neural network model, taking other values except the y't1 as the input to train the neural network model, and obtaining a prediction model; for a future moment needing to be predicted, enabling the data collected in the early stage to be included in the prediction model, and obtaining the steam consumption at the future moment. According to the data acquisition thought, the time characteristics of the data are fully considered, the steam consumption in a period of time in the future is effectively predicted, the boiler can be regulated and controlled in advance, and the purpose of optimizing boiler operation is achieved; meanwhile, through active regulation and control, the phenomena of energy waste and insufficient steam supply can be effectively avoided, and energy conservation and emission reduction are achieved; the problems that feedback is not timely and regulation and control are slow due to passive regulation and control means of the boiler are solved.

Description

technical field [0001] The invention belongs to the technical field of energy forecasting, and relates to the establishment of an industrial steam terminal consumption forecasting model, a forecasting method and a system. Background technique [0002] The traditional industrial steam volume prediction mainly focuses on the production end, and predicts the steam production volume by analyzing the correlation between the historical boiler operating condition data and the steam volume produced, and pays little attention to the steam volume required at the end (that is, the consumer side) , In fact, the prediction of industrial steam at the consumer end is of great significance to the safe and economical operation of thermal power plants, but compared with the steam data at the production end, the data quality at the consumer end is worse, more unpredictable, and more technically demanding. [0003] The traditional boiler control method is mainly based on PID feedback control, w...

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 Applications(China)
IPC IPC(8): G06Q10/04G06Q50/06G06F16/2458G06N3/04
CPCG06Q10/04G06Q50/06G06F16/2465G06F16/2474G06N3/049G06N3/044Y02P80/10Y02D10/00
Inventor 阳赛王栋
Owner 上海全应科技有限公司
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