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

Real-time valve fault diagnosis system and method based on time sequence analysis

A technology of time series analysis and real-time diagnosis, which is applied in mechanical valve testing, pattern recognition in signals, instruments, etc., can solve problems such as inconvenient maintenance and inability to obtain fault categories, so as to facilitate maintenance and rectification, and reduce complex calculations degree, the effect of simplifying the eigenvalues

Active Publication Date: 2019-10-25
CHINA PETROLEUM & CHEM CORP +2
View PDF12 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At the same time, the existing methods can only detect whether the valve is faulty, but cannot obtain the type of fault, which has great limitations and is inconvenient for later maintenance.

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
  • Real-time valve fault diagnosis system and method based on time sequence analysis
  • Real-time valve fault diagnosis system and method based on time sequence analysis
  • Real-time valve fault diagnosis system and method based on time sequence analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0052] Such as figure 1 As shown, the valve fault real-time diagnosis system based on time series analysis provided by the present invention, the valve fault real-time diagnosis system based on time series analysis, includes a vibration acceleration sensor and a sound pressure sensor, and the vibration acceleration sensor and sound pressure sensor assembly On the circuit board, the circuit board is installed on the valve to be detected, and is used to monitor the vibration acceleration signal and the sound pressure signal from the valve; the signal acquisition chip is connected to the circuit board through a cable, and is used to connect the vibration acceleration sensor and the sound pressure signal to the circuit board. The signal when the pressure sensor is monitored is collected into the diagnostic processor; the diagnostic processor is electrically connected to the signal acquisition chip, and is used to receive the signal of the signal acquisition chip and process it to o...

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 real-time valve fault diagnosis system and method based on time sequence analysis, and belongs to the technical field of valve fault detection and diagnosis. The method concretely comprises that a vibration accelerometer and a sound pressure sensor monitor a valve in real time; a signal collection chip collects monitored vibration acceleration and sound pressure signalsto a diagnosis processor; five-point three-times smooth denoising is carried out on the data; diagnosis data training sets of different fault diagnosis types are generated; a fault diagnosis sequential model is established; a forward algorithm is used to calculate the likelihood probabilities of different HMM models successively, and a fault diagnosis result is obtained; and a Bluetooth model transmits the fault diagnosis result to an industrial display screen for display. Fault of the valve is diagnosed by time sequence analysis, fault information can be identified and the corresponding faulttype can be obtained at initial stage of the fault, the limit that fault can only be observed in single time is changed, the false detecting rate of faults is reduced, and the using performance of the valve is substantially improved.

Description

technical field [0001] The invention belongs to the technical field of valve fault detection and diagnosis, and in particular relates to a valve fault real-time diagnosis system and a diagnosis method based on time series analysis. Background technique [0002] In most industrial fields, the valve is one of the essential components. If the valve fails seriously, the entire operating system will not work normally, which may easily lead to serious work accidents. Time series is a sequence formed by sorting the values ​​of some statistical indicators in chronological order. The identification and prediction of time series is to analyze the time series, and according to the development process, direction and trend reflected in the time series, carry out analogy or extension, identify or predict the level that may be reached in the next period of time or in the next few years. The anomaly detection of time series is to analyze the historical data to check whether the current dat...

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): G01M13/003G06K9/00G06K9/62
CPCG01M13/003G06F2218/04G06F2218/08G06F2218/12G06F18/295
Inventor 田中山杨昌群赖少川牛道东仪林林元文蒋通明李永钧
Owner CHINA PETROLEUM & CHEM CORP
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