Steam feed pump state monitoring system based on data mining

A condition monitoring system, a technology for steam-driven feed water pumps, applied in pump testing, machine/engine, biological neural network models, etc., can solve problems such as mining valuable information, and achieve the effect of reducing workload

Pending Publication Date: 2021-11-30
HUANENG POWER INT INC
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Faced with these high-parameter, strongly correlated, and multi-dimensional historical data, it is difficult to dig out valuable information from these massive and rich data by manual analysis.

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 feed pump state monitoring system based on data mining
  • Steam feed pump state monitoring system based on data mining
  • Steam feed pump state monitoring system based on data mining

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0044] A data mining-based state monitoring system for steam-driven feedwater pumps, such as figure 1, including a data acquisition module 1, a performance monitoring module 3, a fault diagnosis module 4 and an interface display module 2;

[0045] The data acquisition module 1 includes a data acquisition unit 11, a data transmission unit 12 and a data storage unit 13. The data acquisition unit 11 collects the operation data set of the number of steam-driven feed water pumps, and stores the operation data set to the data storage unit through the data transmission unit 12. 13. The operation data set includes the inlet and outlet pressure of the steam-driven feedwater pump, the inlet and outlet temperature of the steam pump, the outlet flow rate of the front pump of the steam pump, the differential pressure of the inlet filter of the steam pump, the speed of the steam turbine of the feedwater pump, the pressure of the deaerator and the deaerator pressure of the reheater. amount o...

Embodiment 2

[0111] In this embodiment, the formula for calculating the head of the front pump is:

[0112]

[0113] Among them, H qz is the head of the front pump, p qz,in is the inlet pressure of the front pump, p qz,out is the outlet pressure of the front pump, ρ qz is the average density of the medium in the front pump, g is the earth's gravitational acceleration;

[0114] Others are the same as in Example 1.

[0115] Embodiments 1 and 2 propose a data mining-based state monitoring system for steam-driven feedwater pumps. The system is based on the LSTM prediction model and supplemented by the KPCA algorithm, which solves the problem of gradients in the fault prediction model during long-sequence training The problem of explosion and gradient disappearance makes up for the problems in the planned maintenance of steam-driven feed water pumps, such as lack of pertinence, unclear primary and secondary, and rigid maintenance methods, and meets the needs of real-time status monitorin...

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 steam feed pump state monitoring system based on data mining. The steam feed pump state monitoring system comprises a data acquisition module, a performance monitoring module, a fault diagnosis module and an interface display module, the data acquisition module comprises a data acquisition unit, a data transmission unit and a data storage unit, and the data acquisition unit acquires an operation data set of the number of steam feed pumps and stores the operation data set to the data storage unit through the data transmission unit; the performance monitoring module calculates a performance data set according to the operation data set; the fault diagnosis module comprises a parameter screening unit and a fault prediction unit, the parameter screening unit performs dimension reduction processing on the operation data set through a KPCA algorithm to obtain a dimension reduction data set, and the fault prediction unit inputs the dimension reduction data set into a trained fault prediction model to obtain a fault prediction result of the steam feed pumps; and the interface display module is used for displaying the performance data set and the fault prediction result. Compared with the prior art, the requirements for real-time state monitoring and fault diagnosis of the steam feed pumps are met.

Description

technical field [0001] The invention relates to a state monitoring technology of a steam-driven water feed pump, in particular to a state monitoring system of a steam-driven water feed pump based on data mining. Background technique [0002] On the one hand, while large-scale thermal power generating units bring huge benefits, due to the increased complexity and correlation between equipment and the improvement of operating parameter requirements, the failure rate of thermal power generating unit equipment continues to increase, and annual unplanned shutdowns of thermal power plants The frequency is also increasing. This has just resulted in thermal power plants needing to invest a considerable part of the cost each year for the maintenance of power plant equipment, which directly affects the safety and economy of thermal power plant production. For the maintenance of steam-driven feed water pumps, planned maintenance is generally adopted, and there are problems such as poo...

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): F04B51/00G06N3/04
CPCF04B51/00G06N3/044
Inventor 陆春晖施晨翔艾杨林程婷婷
Owner HUANENG POWER INT INC
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap