Rotary machine fault feature extraction method based on improved variational mode extraction
A technique of variational mode and fault characteristics, applied in the testing of mechanical components, testing of machine/structural components, instruments, etc., can solve problems such as difficulty in determining the initial value of the center frequency of the desired mode, difficulty in optimizing penalty parameters, etc., to achieve Achieve the effect of rotating machinery fault diagnosis
Active Publication Date: 2022-05-31
ZHEJIANG COLLEGE OF ZHEJIANG UNIV OF TECHOLOGY
View PDF15 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Even so, VME still has the problems of determining the initial value of the desired mode center frequency and optimizing the penalty parameters, especially in the analysis of rotating machinery vibration signals. The solution of these two problems is the key to successfully extracting fault features and realizing fault diagnosis
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0066] The present invention will be further described below in conjunction with drawings and embodiments.
[0067] refer to figure 1 , a feature extraction method for rotating machinery faults based on improved variational mode extraction, including the following steps:
[0068] S1: On rotating mechanical equipment, f s is the sampling frequency, collect a section of vibration signal x(t);
[0069] S2: Perform time-frequency transformation processing on the vibration signal x(t) to obtain time-frequency spectrum TFP(t,f), where t represents time and f represents frequency;
[0070] S3: Use the time spectrum TFP(t,f) to determine the frequency range of the fault impact feature, and select a frequency value f in the middle of the frequency range 0 ;
[0071] S4: Set the variation range of the penalty parameter α to [α min ,α max ], let α start from α min start with step size s α Increase, the value when it increases to the i-th step:
[0072] alpha i = α min +(i-1) s...
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
Login to View More Abstract
The invention discloses a rotating machine fault feature extraction method based on improved variational mode extraction. The method comprises the following steps: S1, collecting a vibration signal; s2, carrying out time-frequency transformation processing to obtain a time-frequency spectrum; s3, selecting a frequency value from a frequency range in which the fault impact characteristics are located; s4, setting a change range and an increase step length of a penalty parameter; s5, variational modal extraction is executed for each step value of penalty parameter increase, and an SDE index value corresponding to an expected modal is calculated; s6, drawing a relation curve between the penalty parameters and the SDE indexes; s7, enabling the minimum value of the SDE index to correspond to the optimal value of the penalty parameter; s8, variational mode extraction after parameter optimization is executed; and S9, carrying out square envelope spectrum analysis on the optimal expected mode, and extracting a fault feature frequency. According to the method, the problem that parameters are difficult to select in existing variational mode decomposition and variational mode extraction is solved, the fault features can be conveniently and effectively extracted from the vibration signals of the rotating machine, and fault diagnosis of the rotating machine is achieved.
Description
technical field [0001] The invention belongs to the technical field of mechanical fault diagnosis, in particular to a method for extracting fault features of rotating machinery based on improved variational mode extraction. Background technique [0002] Gears and bearings are important components of rotating machinery, and their health status has an important impact on the normal operation of the equipment. However, in actual work, these parts are often subjected to dynamic loads or even overloads, which are prone to various types of fault damage and affect the use efficiency of the equipment. Therefore, it is very necessary to carry out condition monitoring and fault diagnosis on them. However, since the equipment usually contains multiple rotating parts, the vibrations excited by different parts are coupled and superimposed on each other, and the shock characteristic signal excited by the fault damage will be attenuated to a large extent when it is transmitted from the dam...
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
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G01M13/028G01M13/045
CPCG01M13/028G01M13/045
Inventor 郭远晶姜少飞杨友东鲍雨梅
Owner ZHEJIANG COLLEGE OF ZHEJIANG UNIV OF TECHOLOGY