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

Power plant blower fault early warning method based on multivariate state estimation

A technology of fault early warning and multi-state, which is applied in the direction of measuring electricity, measuring electrical variables, and testing of machine/structural components, etc. It can solve problems such as large fault early warning, low model applicability, and low learning rate, so as to ensure accuracy , Improve the operation speed, improve the effect of accuracy

Pending Publication Date: 2020-12-11
华能国际电力股份有限公司玉环电厂 +1
View PDF6 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] When the blower operates in a complex and changeable environment, various failures will occur, causing the power plant unit to be shut down for maintenance, which directly affects the power generation of the thermal power plant, reduces the economic benefits of the power plant, and may cause equipment accidents in severe cases
[0003] Therefore, it is necessary to monitor the blower equipment of the power plant. Once an abnormality is found in the equipment data, it should be shut down immediately for inspection and maintenance to avoid the occurrence of failures and minimize the economic loss and casualties of the power plant. Due to uncertain factors, it is difficult to carry out real-time and accurate fault early warning for blowers. The existing early warning method BP algorithm takes a long time to train and has a low learning rate, and all monitoring parameters are modeled, resulting in excessive matrix dimensions. The calculation speed is reduced due to the large size, which makes the model less applicable

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
  • Power plant blower fault early warning method based on multivariate state estimation
  • Power plant blower fault early warning method based on multivariate state estimation
  • Power plant blower fault early warning method based on multivariate state estimation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0069] from figure 1 It can be seen from the figure that the estimated residual error of the horizontal bearing vibration on the end side of the blower in normal operation is less than 0.005mm, and the relative residual error is less than 0.7%. from figure 2 It can be seen from the figure that the estimated residual error of the vertical bearing vibration on the end side of the blower under normal operating conditions is less than 0.004mm, and the relative residual error is less than 0.57%. from image 3 It can be seen that the estimated residual error of the end-side bearing temperature in normal operating state is less than 0.05°C, and the relative residual error is less than 0.09%. from Figure 4 It can be seen from the figure that the estimated residual error of the waist bearing temperature under normal operating conditions is less than 0.05°C, and the relative residual error is less than 0.09%. The above results show that the estimated residual error and relative r...

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 power plant blower fault early warning method based on multivariate state estimation, and the method comprises the following steps: 1) constructing a historical data set according to the normal operation historical data of a power plant blower, and obtaining the operation data of the power plant blower in a to-be-predicted time period as an observation set; 2) performingnormalization processing on the historical data set and the observation set; 3) constructing the normalized historical data set into a memory matrix D through multivariate state estimation, and establishing an MSET model; and 4) inputting the observation vector Xobs at each moment in the observation set into the MSET model to obtain a corresponding estimation vector Xest, representing the deviation degree between the observation vector Xobs and the estimation vector Xest through a deviation degree function, and immediately giving an alarm when the deviation degree exceeds a fault early warning threshold, thereby realizing fault early warning of the power plant blower. The method has the advantages of high early warning precision, comprehensive consideration and the like.

Description

technical field [0001] The invention relates to the technical field of blower fault diagnosis, in particular to a method for early warning of blower faults in power plants based on multivariate state estimation. Background technique [0002] When the blower operates in a complex and changeable environment, various failures will occur, causing the power plant unit to be shut down for maintenance, which directly affects the power generation of the thermal power plant, reduces the economic benefit of the power plant, and may cause equipment accidents in severe cases. [0003] Therefore, it is necessary to monitor the blower equipment of the power plant. Once an abnormality is found in the equipment data, it should be shut down immediately for inspection and maintenance to avoid the occurrence of failures and minimize the economic loss and casualties of the power plant. Due to uncertain factors, it is difficult to carry out real-time and accurate fault early warning for blowers....

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): G01M99/00G01R31/00G06F17/16G06F17/18
CPCG01M99/005G01R31/00G06F17/16G06F17/18
Inventor 傅望安常志李来春张剑飞鲍克勤冀平
Owner 华能国际电力股份有限公司玉环电厂
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