A method, medium and device for predicting the life of a shunt releaser based on multi-information fusion

Abstract

The present invention is a life prediction method for a shunt release based on multi-information fusion, comprising the following steps: obtaining a monitoring image of a shunt release within a certain sampling period, and obtaining a continuous image of each opening action in the monitoring image; obtaining a vibration signal of the shunt release within a certain sampling period and preprocessing it, dividing the vibration signal into different areas according to the opening initial frame and the opening end frame of each action, performing frame processing on the vibration signal in the area to obtain the vibration signal of each frame, calculating the energy entropy of each frame of the vibration signal, feeding back the change point obtained according to the energy entropy to the continuous image of each opening action, dividing the continuous image into the opening initial frame, the opening end frame and the intermediate frame through the frame where the change point is located; calculating the driving energy between adjacent frames, obtaining the number of opening actions within the sampling period, and comparing the driving energy between adjacent frames of each opening action, thereby predicting the life of the shunt release.

Description

Technical Field

[0001] The present invention relates to the technical field of shunt releases, and in particular to a method, a medium and a device for predicting the life of a shunt release based on multi-information fusion. Background Art

[0002] With the rapid development of my country's electric power industry, the application of automatic switchgear in substations is becoming more and more extensive, and the reliability of shunt release, a key component, is attracting more and more attention.

[0003] During the operation of the shunt release, its functional characteristics will gradually decline due to changes in internal mechanical movement and electrical characteristics. This decline process is the result of long-term accumulation, and it is difficult to discover its changing pattern.

[0004] Therefore, how to correctly evaluate the performance status and health level of the shunt release and establish a reliable prediction model to predict its life has long been a difficult problem that has troubled technical personnel in this field. Summary of the invention

[0005] The purpose of the present invention is to provide a method, medium and device for predicting the life of a shunt releaser based on multi-information fusion to solve the above technical problems.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A method for predicting the life of a shunt release based on multi-information fusion comprises the following steps:

[0008] S100, obtaining a monitoring image of the shunt release within a certain sampling period, and obtaining a continuous image of each opening action in the monitoring image;

[0009] S200, obtaining a vibration signal of the shunt release within a certain sampling period and preprocessing the vibration signal, then dividing the vibration signal into different regions according to the initial opening frame and the end opening frame of each action, and performing frame processing on the vibration signal in the region to obtain the vibration signal of each frame, calculating the energy entropy of each frame of the vibration signal, and feeding back the change point obtained according to the energy entropy to the continuous image of each opening action, dividing the continuous image into the initial opening frame, the end opening frame and the intermediate frame according to the frame where the change point is located;

[0010] S300, calculating the driving energy between adjacent frames, obtaining the number of opening actions within a sampling period, and comparing the driving energy between adjacent frames of each opening action, thereby predicting the life of the shunt release.

[0011] The present invention is further configured to perform preprocessing through CEEMDAN after the vibration signal is acquired.

[0012] The present invention further arranges that the vibration signal is decomposed and expressed as: ;

[0013] In the formula, k=1,2···K, where K is the number of eigenmode components obtained by decomposition; R ( n ) is the final remaining amount.

[0014] The present invention further arranges that the vibration signal obtained in the region is y(n), the length is N, and when the vibration signal is framed, the Haining window function is used for processing, and the formula is as follows: W (k) = (1 -α) - α cos (2πk / (N-1)), 0≤k≤N-1, α=0.46, N is the frame length in the region, and k is the sequence number of the window function; after y(n) is framed, the vibration signal of the i-th frame is obtained as follows: ;

[0015] In the formula: l=1, 2,...N, i=1, 2,...I, I is the total number of frames after frame shift; τ is the frame shift length.

[0016] The present invention further arranges that the vibration signal z of the i-th frame i (l) Perform Fourier transform, where the energy spectrum of the frequency component of the qth spectral line is denoted by S i (q), then each frequency component is normalized, and the formula is as follows: ;

[0017] According to the above calculation signal energy entropy per frame, the energy entropy calculation formula is as follows: ;

[0018] The present invention further arranges that the change point is determined according to the energy entropy, and the change point includes the time point of the initial frame of the gate opening and the end frame of the gate opening, and the sequence is: t={t 初始 , t1, ··· t i , t 结束}, different frame images are acquired according to the above sequence and sorted according to the above sequence, and the driving energy of adjacent frames is calculated.

[0019] The present invention is further configured to determine the stroke change ∆X of the shunt release top rod according to the images of adjacent frames, calculate the force F exerted on the top rod during the movement according to the parameters of the shunt release, and calculate the driving energy W=F·∆X according to the force.

[0020] The present invention further provides that the force is evaluated by the magnitude of the electromagnetic attraction exerted on the moving iron core, that is, the magnitude of the force F is: ;

[0021] In the above formula,F —Electromagnetic attraction on the moving iron core; Ac — Cross-sectional area of ​​the moving iron core; R C —Radius of the moving iron core; B δ — working air gap flux density; μ 0—Magnetic permeability of vacuum.

[0022] The present invention also provides a computer device, which includes a memory and a processor. The memory is used to store computer instructions, and the processor executes the computer instructions to execute the method for predicting the life of a shunt release based on multi-information fusion.

[0023] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the method for predicting the life of a shunt release based on multi-information fusion.

[0024] Beneficial effects of the present invention: The present invention predicts the life of a shunt release by combining images and vibration signals, wherein a push rod is used in conjunction with the opening and closing components of a circuit breaker in the shunt release, and the movement of the push rod drives the opening and closing components to open and close, so the entire movement process of the shunt release can be obtained through the image, thereby analyzing the movement state of the push rod, and then combined with the vibration signal analysis, through the calculation of energy entropy, the change point of the vibration signal can be more accurately identified, and the action process is divided into several different stages according to the change points, and the driving energy of the push rod is calculated according to the different stages. According to the corresponding stage of each action and the corresponding driving energy, the life trend of the shunt release is judged, thereby predicting it. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0026] Figure 1 Schematic diagram of a flow chart of an embodiment of the present invention. DETAILED DESCRIPTION

[0027] The following will describe the implementation methods of the present application in detail with the help of accompanying drawings and examples, so that the implementation process of how the present application uses technical means to solve technical problems and achieve technical effects can be fully understood and implemented accordingly. Example

[0028] like Figure 1 As shown, the present invention provides a method for predicting the life of a shunt releaser based on multi-information fusion, comprising the following steps:

[0029] S100, obtaining a monitoring image of the shunt release within a certain sampling period, and obtaining a continuous image of each opening action in the monitoring image, the continuous image is obtained by a high-speed camera, that is, the image of the shunt release of a certain number of opening actions is obtained within a certain sampling period, and when performing analysis, the object is the top rod part of the shunt release; in this embodiment, it is first necessary to determine the positions of the opening initial frame and the opening end frame of each action to perform rough image positioning;

[0030] S200, obtaining a vibration signal of the shunt release within a certain sampling period and preprocessing it, wherein the vibration signal is obtained by using a vibration sensor, and the vibration sensor is set on the top rod of the shunt release; wherein the preprocessing method is as follows: in this embodiment, after the vibration signal is obtained, it is preprocessed by CEEMDAN, and the vibration signal is preprocessed by CEEMDAN and decomposed to be expressed as: ;

[0031] In the formula, k=1,2···K, where K is the number of eigenmode components obtained by decomposition; R ( n ) is the final remaining amount.

[0032] Secondly, since the opening initial frame and the opening end frame are determined in step S100 in this embodiment, the vibration signal x(n) is divided into different regions according to the opening initial frame and the opening end frame of each action, and the vibration signal in the region is processed by framing to obtain the vibration signal of each frame. Since there are multiple component functions in x(n), and the first component function can represent the rapid change of the signal, the first component function is processed in this embodiment and its processing method is as follows:

[0033] The vibration signal obtained in the region is y(n) (i.e., the first component function), with a length of N. When the vibration signal is framed, the Hening window function is used for processing, and its formula is as follows: W (k) = (1 -α ) - α cos (2πk / (N-1)), 0≤k≤N-1, α=0.46, N is the frame length in the region, and k is the sequence number of the window function; after y(n) is framed, the vibration signal of the i-th frame is obtained as follows: In the formula, l=1, 2, ···N, i=1, 2, ···I, I is the total number of frames after frame shift; τ is the frame shift length.

[0034] The energy entropy of each frame of vibration signal is calculated. The energy entropy is calculated in the following way:

[0035] For the vibration signal z of the i-th frame i(l) Perform Fourier transform, where the energy spectrum of the frequency component of the qth spectral line is denoted by S i (q), then each frequency component is normalized, and the formula is as follows: ;

[0036] According to the above calculation signal energy entropy per frame, the energy entropy calculation formula is as follows: The change point obtained according to the energy entropy is fed back to the continuous image of each opening action, and the continuous image is divided into the opening initial frame, the opening end frame and the intermediate frame by the frame where the change point is located. The change point includes the time point of the opening initial frame and the time point of the opening end frame, and the sequence is: t={t 初始 , t1, ··· t i , t 结束}, obtain different frame images according to the above sequence and sort them according to the above sequence.

[0037] S300, calculating the driving energy between adjacent frames, obtaining the number of opening actions within a sampling period, and comparing the driving energy between adjacent frames of each opening action, wherein the driving energy is calculated based on the stroke change ∆X of the top rod of the shunt release, and the force exerted on the top rod during the movement is calculated based on the parameters of the shunt release, and the driving energy W=F·∆X is calculated based on the force.

[0038] The force is evaluated by the magnitude of the electromagnetic attraction on the moving iron core, that is, the magnitude of the force is: In the above formula, F —Electromagnetic attraction on the moving iron core; Ac — Cross-sectional area of ​​the moving iron core; R C —Radius of the moving iron core; B δ — working air gap flux density; μ 0—Magnetic permeability of vacuum.

[0039] Among them, the number of change points after the first action is 6 (including the two points of the initial frame and the end frame of the gate opening). The first action image is divided into 6 frames, recorded as {P1, P2, P3, P4, P5, P6}, and the stroke change ∆X={∆X1, ∆X2, ∆X3, ∆X4, ∆X5} is calculated according to the above image sequence; then W1= F·∆X1; W2= F·∆X2, W3=F·∆X3, W4= F·∆X4, W5= F·∆X5; the second action image is also divided into 6 frames, recorded as: {P1', P2', P3', P4', P5', P6'}, and the stroke change ∆X'={∆X'1, ∆X'2, ∆X'3, ∆X' 4, ∆X'5} is calculated according to the above image sequence, then W'1= F·∆X'1; W'2= F·∆X'2, W'3= F·∆X'3, W'4= F·∆X'4, W'5= F·∆X'5; then the comparison is to compare the size of W1 with W'1, the size of W2 with W'2, the size of W3 with W'3, the size of W4 with W'4, the size of W5 with W'5. When there are multiple actions following the above judgment, the life of the shunt release can be judged; for the above situation, in order to facilitate data processing, the corresponding curve can be combined to establish a curve to describe the life situation. Example

[0040] The present invention also provides a computer device, which includes a memory and a processor. The memory is used to store computer instructions, and the processor executes the computer instructions to execute the method for predicting the life of a shunt release based on multi-information fusion. Example

[0041] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the method for predicting the life of a shunt release based on multi-information fusion.

[0042] The present invention predicts the life of a shunt release by combining images and vibration signals, wherein a push rod is used in conjunction with the opening and closing components of a circuit breaker in the shunt release, and the movement of the push rod drives the opening and closing components to open and close. Therefore, the entire movement process of the shunt release can be obtained through the image, so as to analyze the movement state of the push rod, and then combined with the vibration signal analysis, through the calculation of energy entropy, the change point of the vibration signal can be more accurately identified, and the action process is divided into several different stages according to the change points, and the driving energy of the push rod is calculated according to the different stages. According to the corresponding stage of each action and the corresponding driving energy, the life trend of the shunt release is judged, so as to predict it.

[0043] For example, certain words are used in the specification and claims to refer to specific components. Those skilled in the art should understand that hardware manufacturers may use different terms to refer to the same component. This specification and claims do not use differences in names as a way to distinguish components, but use differences in the functions of components as the criteria for distinction. For example, "including" mentioned throughout the specification and claims is an open term, so it should be interpreted as "including but not limited to". "Approximately" means that within an acceptable error range, those skilled in the art can solve technical problems within a certain error range and basically achieve technical effects.

[0044] It should be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a product or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such product or system. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the product or system including the elements.

[0045] The above description shows and describes several preferred embodiments of the present invention, but as before, it should be understood that the present invention is not limited to the form disclosed herein, and should not be regarded as excluding other embodiments, but can be used in various other combinations, modifications and environments, and can be modified within the scope of the invention concept of this article through the above teachings or the technology or knowledge of the relevant field. And the changes and modifications made by those skilled in the art do not depart from the spirit and scope of the present invention, and should be within the scope of protection of the claims attached to the present invention.

Claims

1. A method for predicting the life of a shunt release based on multi-information fusion, characterized in that: The steps include: S100, obtaining a monitoring image of the shunt release within a certain sampling period, and obtaining a continuous image of each opening action in the monitoring image; S200, obtaining a vibration signal of the shunt release within a certain sampling period and preprocessing the vibration signal, then dividing the vibration signal into different regions according to the initial opening frame and the end opening frame of each action, and performing frame processing on the vibration signal in the region to obtain the vibration signal of each frame, calculating the energy entropy of each frame of the vibration signal, and feeding back the change point obtained according to the energy entropy to the continuous image of each opening action, dividing the continuous image into the initial opening frame, the end opening frame and the intermediate frame according to the frame where the change point is located; S300, calculating the driving energy between adjacent frames, obtaining the number of opening actions within a sampling period, and comparing the driving energy between adjacent frames of each opening action, thereby predicting the life of the shunt release.

2. A method for predicting the life of a shunt release based on multi-information fusion according to claim 1, characterized in that: After obtaining the vibration signal, it is preprocessed by CEEMDAN.

3. The method for predicting the life of a shunt release based on multi-information fusion according to claim 2 is characterized in that: The vibration signal is decomposed into: ; In the formula, k=1,2…K, where K is the number of eigenmode components obtained by decomposition; R ( n ) is the final remaining amount.

4. The method for predicting the life of a shunt release based on multi-information fusion according to claim 1, characterized in that: The vibration signal obtained in the region is y(n), with a length of N. When the vibration signal is framed, the Heining window function is used for processing, and the formula is as follows: W (k) = (1 -α ) - α cos (2πk / (N-1)), 0≤k≤N-1, α=0.46, N is the frame length in the region, and k is the serial number of the window function; After y(n) is framed, the vibration signal of the i-th frame is obtained as follows: ; Where: l=1, 2…N, i=1, 2…I, I is the total number of frames after frame shift; τ is the frame shift length.

5. The method for predicting the life of a shunt release based on multi-information fusion according to claim 3 is characterized in that: For the vibration signal z of the i-th frame i (l) Perform Fourier transform, where the energy spectrum of the frequency component of the qth spectral line is denoted by S i (q), then each frequency component is normalized, and the formula is as follows: ; According to the above calculation signal energy entropy per frame, the energy entropy calculation formula is as follows: .

6. The method for predicting the life of a shunt release based on multi-information fusion according to claim 1 is characterized in that: The change point is determined according to the energy entropy, and the change point includes the time point of the initial frame of the gate opening and the end frame of the gate opening, and the sequence is: t={t 初始 , t1, ··· t i , t 结束 }, different frame images are acquired according to the above sequence and sorted according to the above sequence, and the driving energy of adjacent frames is calculated.

7. A method for predicting the life of a shunt release based on multi-information fusion according to claim 1 or 5, characterized in that: The stroke change ∆X of the shunt release push rod is determined based on the images of adjacent frames, and the force applied to the push rod during the movement is calculated based on the parameters of the shunt release. The driving energy W=F·∆X is calculated based on the force.

8. The method for predicting the life of a shunt release based on multi-information fusion according to claim 6, characterized in that: The force is evaluated by the magnitude of the electromagnetic attraction on the moving iron core, that is, the magnitude of the force is: ; In the above formula, F —Electromagnetic attraction on the moving iron core; Ac — Cross-sectional area of ​​the moving iron core; R C —Radius of the moving iron core; B δ — working air gap flux density; μ 0—Magnetic permeability of vacuum.

9. A computer device, characterized in that: The device includes a memory and a processor, wherein the memory is used to store computer instructions, and the processor executes the computer instructions to execute the method for predicting the life of a shunt release based on multi-information fusion as described in any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute a method for predicting the life of a shunt release based on multi-information fusion according to any one of claims 1 to 8.

Images