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

Steam-driven draught fan full working condition online monitoring model modeling method based on CPSO-LSSVM

A model modeling, induced draft fan technology, applied in special data processing applications, instruments, electrical digital data processing, etc., can solve the problems of no steam induced induced draft fan, increased complexity of variable speed adjustment, etc., to avoid poor accuracy Effect

Inactive Publication Date: 2014-07-02
SOUTHEAST UNIV +1
View PDF1 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there is currently no online monitoring model for steam-driven induced draft fans that can be used
The characteristic curve of the steam-driven induced fan is a complex nonlinear model involving three parameters: specific pressure Y(p / ρ), volumetric flow Q and blade angle. Traditional modeling methods are difficult to accurately determine the working point of the steam-driven induced fan. ; and for the steam-driven induced draft fan, due to the increase of variable speed adjustment, the complexity is further increased

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
  • Steam-driven draught fan full working condition online monitoring model modeling method based on CPSO-LSSVM
  • Steam-driven draught fan full working condition online monitoring model modeling method based on CPSO-LSSVM
  • Steam-driven draught fan full working condition online monitoring model modeling method based on CPSO-LSSVM

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0021] Taking the online monitoring model of a steam-driven induced draft fan of a 660MW unit in a power station as an example, the operating characteristic data of the steam-driven induced draft fan provided by the fan manufacturer are obtained, including data at various openings of 995r / min and data at some other speeds. Modeling mainly includes core modules such as data processing, least squares support vector machine training modeling, retraining model, publishing model and correcting model.

[0022] (1) Data processing: Screen and analyze the 995r / min characteristic data provided by the design manufacturer to select 538 data, and determine the following parameters of the data, specific pressure Y (p / ρ, where p is the total pressure of the fluid, and ρ is the fluid density) , volume flow Q, blade angle β and fan speed n, 152 of them are selected as training data, and all 538 of them are used as test data.

[0023] (2) Least squares support vector machine training modeling,...

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 steam-driven draught fan full working condition online monitoring model modeling method based on a CPSO-LSSVM. The steam-driven draught fan full working condition online monitoring model modeling method based on the CPSO-LSSVM comprises the following steps that firstly, design data from a draught fan factory are analyzed and processed, and actual working condition points are selected as training data; a chaotic particle swarm optimization algorithm is used for optimizing modeling parameters and supporting modeling on a least square support vector machine to obtain a static model; a full working condition model of a steam-driven draught fan is obtained through training based on the existing static model by combining rotating speed variables; the established full working condition model is published in an online website mode by combing a webpage programming technique, so that the working points of the draught fan can be determined on line; finally, the actual operating data of the stem-driven draught fan are obtained by combining an SIS to carry out real-time online correction on the established model. Through the model obtained by using the method, the full working condition operating characteristics of the steam-driven draught fan can be accurately reflected, online correction can be achieved, the draught fan can operate correctly even after the characteristics of the draught fan are changed, and guidance is provided for actual operation.

Description

technical field [0001] The invention discloses a CPSO-LSSVM-based online monitoring model modeling method of a steam-driven induced draft fan in all working conditions, relates to a support vector machine model, and belongs to the field of machine learning modeling. Background technique [0002] After the feed water pump of thermal power plant is driven by steam turbine, the induced draft fan has become the auxiliary machine with the largest power consumption. In the motor-driven mode, the maximum electric power of a single induced draft fan motor of a 1036MW unit reaches 7400kW, accounting for 1.48% of the single-unit power generation. And in the motor drive mode, the induced draft fan is regulated by the stator blades, and the power of the motor remains unchanged. When the load of the unit changes, the extra plant power loss caused by the motor is very large, and the energy waste is serious. Using a steam turbine instead of a motor-driven induced draft fan is an excellent...

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): G06F19/00
Inventor 司风琪邵壮郭俊山阎文生
Owner SOUTHEAST 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