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

Compressor surge early fault feature extraction method based onenhanced entropy weight

A technology for early failures and compressors, which is applied in the testing of machine/structural components, instruments, measuring devices, etc., can solve the problems of information redundancy, small discrimination of characteristic parameter values, vibration and noise interference, etc. Maintain stable operation and ensure the effect of continuous production

Active Publication Date: 2021-06-25
BEIJING UNIV OF CHEM TECH
View PDF6 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] There is overlap of fault information between multi-dimensional feature parameters, resulting in redundant information, which not only fails to improve the accuracy of fault identification, but also increases the complexity of the algorithm, and brings about the problem that the features cannot be visualized
At present, the commonly used feature selection method can play an ideal effect when there are obvious differences between the characteristics of different types of data, but the characteristics of the surge signal are weak in the early stage, coupled with the interference of vibration and noise, resulting in a gap between normal and fault states. The distinction degree of the characteristic parameter values ​​between is extremely small, and it is difficult to accurately select sensitive features by using the above feature selection method, which cannot be used for the extraction of early features of surge faults.
[0005] Therefore, there are still some deficiencies in the research on the early fault characteristics of compressor surge, and the problem of how to effectively extract the fault characteristics that accurately and timely reflect the compressor surge state needs to be solved urgently

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
  • Compressor surge early fault feature extraction method based onenhanced entropy weight
  • Compressor surge early fault feature extraction method based onenhanced entropy weight
  • Compressor surge early fault feature extraction method based onenhanced entropy weight

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0066] This embodiment is carried out on an actual gas turbine-compressor set. The vibration speed signal of the compressor sliding the housing is measured by a speed sensor, and the sensor is fixed to the bearing housing by bolts. During the experiment, the rotor runs near 3000 rpm and the sampling frequency is 1024 Hz.

[0067] Flowchart flow diagram of early fault feature extraction method based on enhanced entropy rights figure 1 As shown, the specific steps are as follows:

[0068] S1, using the vibration sensor to acquire the original vibration signal to be monitored in normal state and early surge; mount the vibration speed sensor with bolts to be monitored in the sliding bearing housing to be monitored, set the sampling frequency f. s No less than 10 times the transition.

[0069] In this embodiment, the rotor speed N is 3000 rpm, so according to F s ≥10 × N / 60 calculates the sampling frequency cannot be less than 500 Hz, and 1024 Hz is taken in this embodiment.

[0070]...

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 compressor surge early fault feature extraction method based on enhanced entropy weight dimensionality reduction, belongs to the technical field of mechanical equipment fault diagnosis, and can extract surge early-stage fault sensitive features more accurately and effectively. The method comprises the following steps: acquiring m groups of normal vibration data samples of a compressor to be monitored and fault vibration data samples of surge early faults, wherein the surge early failure refers to a rotating stall failure. respectively extracting n time domain and frequency domain feature parameters from the normal vibration data sample and the fault vibration data sample, and constructing a sample feature matrix; normalizing the sample feature matrix, and calculating enhanced information entropy values of the n feature parameters. based on the enhanced information entropy values of the feature parameters, measuring weight coefficients of the n feature parameters representing the surge early failure capability; and according to the size relationship of the weight coefficients, extracting the feature parameters of which the weight coefficients exceed a set threshold value as sensitive features of the surge early fault to be monitored.

Description

Technical field [0001] The present invention relates to the field of mechanical equipment fault diagnosis, and more particularly to an early fault feature extraction method for compressor surges based on enhanced entropy. Background technique [0002] Compressors are widely used in petrochemical, smelting, mechanical, power and other fields. In the actual operation, it is extremely vulnerable due to improper working conditions, environmental changes, and other factors, and a surge fault occurs. Once the breath fault occurs, it is often damaged by important components such as compressor spindle, impeller, bearing, seal, and the safety and stability of serious threat equipment. Therefore, how to quickly and accurately identify the asthma failure to become a key factor in maintaining a stable operation of the unit and ensuring the continuous production of the enterprise. [0003] Based on the maneuvement fault mechanism, the on-site personnel often determines based on the abnormal s...

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): G01M99/00G01H17/00
CPCG01M99/005G01H17/00
Inventor 贺雅胡明辉江志农冯坤王钟李昊泽
Owner BEIJING UNIV OF CHEM TECH
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