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

A Dynamic Threshold Early Warning Method for State Monitoring of Moving Equipment

A technology of dynamic threshold and dynamic equipment, applied in measurement devices, testing of machine/structural components, instruments, etc., can solve problems such as deterioration, false early warning, and enterprise loss, and achieve the effect of reducing false alarm rate and eliminating acquisition errors.

Active Publication Date: 2021-03-02
北京博华安创科技有限公司
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, most of the large-scale dynamic equipment in enterprises have installed online monitoring systems. However, the current online monitoring systems cannot realize early warning of mechanical failures, mainly because of the following problems in routine alarms: (1) The alarm threshold is provided by the OEM and pre-warned. It is set in the monitoring system, when the unit alarms, the fault has deteriorated to a certain extent, and the early warning cannot be realized in the early stage of the fault; (2) If the alarm threshold is lowered in order to enable the monitoring system to realize early warning, it may be due to The influence of noise and acquisition error makes the monitoring data collected in real time repeatedly cross the alarm line, resulting in a large number of false alarms; (3) if the traditional smoothing filter technology is used to eliminate the influence of noise and acquisition error, key fault information may be lost, resulting in serious Accidents bring huge losses to the enterprise

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
  • A Dynamic Threshold Early Warning Method for State Monitoring of Moving Equipment
  • A Dynamic Threshold Early Warning Method for State Monitoring of Moving Equipment
  • A Dynamic Threshold Early Warning Method for State Monitoring of Moving Equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0043] The conventional alarm value of a flue gas turbine in an enterprise is 80 μm, and the danger value is 100 μm. The monitoring trend of a measuring point of the unit began to climb slowly from the beginning of June 2017. Before that, the trend of the measuring point had been stable at about 73 μm. By the beginning of July 2017, it had climbed to about 95 μm, and the trend had climbed abnormally by 22 μm within a month. After checking the cause of the failure, it was found that the flue gas contained a catalyst, which made the catalyst gradually adhere to the blades of the hood, resulting in a gradual increase in the imbalance, resulting in a slow rise in the trend.

[0044] Calculate the dynamic self-learning early warning threshold in the normal operation stage according to the dynamic self-learning early warning threshold algorithm. When α=0.05, the two shape parameters of the fitted Beta distribution are respectively γ=2.7256 and η=2.4191. The early warning threshold of...

Embodiment 2

[0047] The sudden failure of a compressor in a certain company was caused by the fact that the compression medium was not clean. During long-term operation, dirt accumulated on the blades. The instant the dirt fell off, it caused the rotor unbalance to change, resulting in a sudden change in the vibration trend.

[0048] Based on the dynamic threshold warning method for dynamic equipment state monitoring proposed in this patent, the dynamic self-learning threshold in the normal operation stage is calculated. When α=0.05, the two shape parameters of the fitted Beta distribution are γ=1.9181 and η respectively. =2.6425, and then the lower threshold Thd1=34.9532 and the upper limit Thd2=41.7177 of the trend data are obtained, that is, the self-learning alarm threshold range is [34.9532,41.7177]. Then use the l1 trend filtering technology to filter the vibration trend data to obtain the vibration trend of the moving equipment without fluctuation interference.

[0049] Such as Fi...

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 mobile device state monitoring dynamic threshold early warning method. The method comprises the following steps: carrying out statistic analysis on a large amount of monitoring data of an on-line monitoring system, calculating an early warning threshold by using a dynamic self-learning threshold algorithm, and eliminating random errors by using an l1 trend filtering technology to obtain the filtered trend; replacing a conventional warning threshold in the monitoring system by using a dynamic self-learning threshold, and comparing a self-learning early warning threshold with the filtered trend to carry out early warning of faults of mobile devices. The mobile device state monitoring dynamic threshold early warning method can make up the defects of the conventionalwarning manner in the aspect of early warning of early faults, and is capable of monitoring the trend abnormality when the conventional warning is not sent in the early stage of fault occurrence so asto achieve early warning.

Description

technical field [0001] The invention belongs to the technical field of equipment health monitoring applications, and more specifically relates to a dynamic threshold early warning method for state monitoring of dynamic equipment. Background technique [0002] Motors, pumps, diesel engines, reciprocating compressors, internal combustion engines, gas turbines, gas engines, etc. are widely used machinery in petrochemical, electric power and other process industries. The safe and stable operation of such equipment will produce good economic and social benefits. At present, most of the large-scale dynamic equipment in enterprises have installed online monitoring systems. However, the current online monitoring systems cannot realize early warning of mechanical failures, mainly because of the following problems in routine alarms: (1) The alarm threshold is provided by the OEM and pre-warned. It is set in the monitoring system, when the unit alarms, the fault has deteriorated to a c...

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 Patents(China)
IPC IPC(8): G01M99/00
CPCG01M99/005
Inventor 高晖赵大力李星王牮
Owner 北京博华安创科技有限公司
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