Machine algorithm-based turbine low-pressure cylinder exhaust enthalpy real-time calculation method

A real-time calculation and steam turbine technology, applied in calculation, computer parts, computer-aided design, etc., can solve problems that affect learning accuracy, large amounts of data, and inability to determine input variables, so as to improve prediction accuracy and avoid complexity

Inactive Publication Date: 2018-04-13
XIAN THERMAL POWER RES INST CO LTD
View PDF5 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] Modern large-scale thermal power generation steam turbine units often require the economy of an online computer group. The calculation of the relative internal efficiency of the low-pressure cylinder is a major difficulty restricting the calculation of the efficiency of the steam turbine. It is mainly due to the difficulty of online calculation of the exhaust enthalpy of the low-pressure cylinder.
The exhaust steam of the low-pressure cylinder is different from the exhaust steam of the high-pressure cylinder and the medium-pressure cylinder. It is in the wet steam area and needs to be obtained from the wet steam dryness, saturated steam pressure, and saturated steam temperature. However, most units are not equipped with low-pressure steam at present. On-line measurem

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
  • Machine algorithm-based turbine low-pressure cylinder exhaust enthalpy real-time calculation method
  • Machine algorithm-based turbine low-pressure cylinder exhaust enthalpy real-time calculation method
  • Machine algorithm-based turbine low-pressure cylinder exhaust enthalpy real-time calculation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0057] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0058] A method for real-time calculation of exhaust enthalpy of steam turbine low-pressure cylinder based on machine algorithm provided by the present invention comprises the following steps:

[0059] 1) Collect historical steady-state data

[0060] In the information system of the power plant, the historical data (unit load, main steam flow, main steam pressure, main steam temperature, pressure and temperature after regulating stage, inlet steam pressure and inlet steam temperature of the intermediate pressure cylinder, etc.) Steam parameters, high-pressure cylinder exhaust pressure and exhaust temperature, low-pressure cylinder exhaust steam and exhaust temperature and other exhaust steam parameters, steam turbine extraction parameters such as the first to eighth stage extraction pressure and extraction steam temperature, steam turbine low-pressure c...

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 machine algorithm-based turbine low-pressure cylinder exhaust enthalpy real-time calculation method. According to the method, steam inlet parameters such as a unit load, mainsteam flow, a main steam pressure, a main steam temperature, and a steam inlet pressure and a steam inlet temperature of a medium-pressure cylinder and the like are selected as input variables; meanwhile, steam exhaust parameters such as a steam exhaust pressure and a steam exhaust temperature of a low-pressure cylinder and the like are selected as input variables; in addition, steam extraction parameters such as steam extraction pressures, steam extraction temperatures and the like of first to eighth stages of a turbine are selected as input variables; 28 parameters in total serve as the input variables; after data preprocessing, principal component analysis is performed to obtain n principal components with an accumulated contribution value greater than 99.95%; and by taking the n principal components as input variables of a BP neural network and taking an exhaust enthalpy of the turbine as an output variable, a turbine exhaust enthalpy calculation model based on a principal component analysis and neural network composite model is built; and by training the model, the turbine exhaust enthalpy calculation model is obtained, so that real-time calling in online monitoring is facilitated.

Description

technical field [0001] The invention belongs to the field of the power industry, and in particular relates to a real-time calculation method for the exhaust enthalpy of a low-pressure cylinder of a steam turbine based on a machine algorithm. Background technique [0002] Modern large-scale thermal power generation steam turbine units often require the economy of an online computer group. The calculation of the relative internal efficiency of the low-pressure cylinder is a major difficulty restricting the calculation of the efficiency of the steam turbine. The main reason is that the exhaust enthalpy of the low-pressure cylinder is difficult to calculate online. The exhaust steam of the low-pressure cylinder is different from the exhaust steam of the high-pressure cylinder and the medium-pressure cylinder. It is in the wet steam area and needs to be obtained from the wet steam dryness, saturated steam pressure, and saturated steam temperature. However, most units are not equip...

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): G06F17/50G06N3/04G06K9/62
CPCG06F30/333G06F30/20G06N3/044G06F18/2135
Inventor 杨斌杨永军张亚黄猛李昆仑邓新亮白欢庆
Owner XIAN THERMAL POWER RES INST CO LTD
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