Breaker operating mechanism intelligent diagnosis method based on intrinsic characteristic scale decomposition and fuzzy entropy

Abstract

The invention provides a circuit breaker operating mechanism intelligent diagnosis method based on intrinsic characteristic scale decomposition and fuzzy entropy, and the method comprises the steps: carrying out the intrinsic characteristic scale decomposition of a vibration signal of a circuit breaker operating mechanism, and carrying out the self-adaptive decomposition of the vibration signal into a plurality of intrinsic characteristic scale components and a monotonous trend signal; the fuzzy entropy of each intrinsic feature scale component is calculated, and the fuzzy entropies of all the intrinsic feature scale components are constructed into a fuzzy entropy feature vector; and taking the fuzzy entropy feature vector as input, and performing fault diagnosis by adopting a multi-classification support vector machine. According to the method, the intrinsic characteristic scale decomposition and the fuzzy entropy are combined, the self-adaptability of the intrinsic characteristic scale decomposition and the nonlinear characteristic and stability of the fuzzy entropy are fully utilized, higher accuracy is achieved in the aspect of fault diagnosis of the high-voltage circuit breaker operating mechanism, and good application prospects are achieved.

Description

Technical Field

[0001] The invention relates to a fault diagnosis method for a high-voltage circuit breaker operating mechanism, in particular to an intelligent diagnosis method for a circuit breaker operating mechanism based on intrinsic characteristic scale decomposition and fuzzy entropy. Background Art

[0002] The power system has the following requirements for high-voltage circuit breakers: (1) The high-voltage circuit breaker can work reliably for a long time under the specified conditions and correctly perform the closing or opening action; (2) When a short-circuit grounding fault occurs in the system, it can cut off the fault current in a short time to reduce the damage of the short-circuit current to electrical equipment and the power system.

[0003] The closing or opening action of the high-voltage circuit breaker is completed by the cooperation of many parts of the operating mechanism, such as cams, pawls, crank arms, ratchets, and opening / closing springs. A large number of cases show that operating mechanism failure is the main failure of high-voltage circuit breakers. At present, the maintenance of high-voltage circuit breaker operating mechanisms mainly relies on maintenance personnel to use portable instruments to perform preventive tests during power outages. This offline maintenance method may cause high-voltage circuit breakers to operate in an ultra-dangerous manner or be over-maintained. In recent years, the Norwegian Electric Power Research Institute or domestic research institutions have analyzed the vibration signals of the operating mechanism and achieved certain results. Typical time-frequency analysis methods for the vibration signals of the operating mechanism are window Fourier transform and wavelet analysis. Due to the limitations of the Heisenberg uncertainty principle, window Fourier transform and wavelet analysis cannot take into account both time resolution and frequency resolution.

[0004] In order to analyze the non-stationary signal of high-voltage circuit breaker vibration signal, scholars at home and abroad have tried to use empirical mode decomposition and local mean decomposition methods. Empirical mode decomposition divides the vibration signal into several intrinsic mode functions, and uses Hilbert transform to calculate the instantaneous frequency and instantaneous amplitude for each intrinsic mode function, thereby obtaining the time-frequency distribution of the original vibration signal. When the empirical mode decomposition uses cubic splines to form the upper and lower envelopes, there are over-envelope or under-envelope phenomena, and Hilbert transform has negative frequency and other problems. The local mean decomposition method uses extreme points to obtain the local mean function and envelope estimation function, and continuously demodulates the original vibration signal into a pure frequency modulation signal and an envelope signal. The pure frequency modulation signal and the envelope signal are multiplied to obtain a product integral component, thereby representing the original vibration signal as the sum of several product integral components. The local mean decomposition method has problems such as endpoint effect, frequency confusion, and signal mutation caused by demodulation.

[0005] In summary, existing vibration signal analysis methods for high-voltage circuit breaker operating mechanisms, such as window Fourier transform, wavelet analysis, empirical mode decomposition, and local mean decomposition, all have the disadvantage of low intelligence and often require technical intervention. In addition, correct conclusions cannot usually be drawn for early weak faults in the operating mechanism. Summary of the invention

[0006] In view of this, the present invention aims to overcome the shortcomings of the above-mentioned problems in the prior art, and proposes an intelligent diagnosis method for circuit breaker operating mechanism based on intrinsic characteristic scale decomposition and fuzzy entropy. The method first uses intrinsic characteristic scale decomposition to adaptively decompose the original vibration signal, then calculates the fuzzy entropy of the intrinsic characteristic scale component, and finally uses the fuzzy entropy vector as input to perform intelligent fault diagnosis on the circuit breaker operating mechanism using a multi-classification support vector machine. The method combines intrinsic characteristic scale decomposition and fuzzy entropy, making full use of the adaptability of intrinsic characteristic scale decomposition and the nonlinear characteristics and stability of fuzzy entropy, and has a higher accuracy in high-voltage circuit breaker operating mechanism fault diagnosis, and has a good application prospect.

[0007] To achieve the above object, the technical solution of the present invention is achieved as follows:

[0008] A first aspect of the present invention provides an intelligent diagnosis method for a circuit breaker operating mechanism based on intrinsic characteristic scale decomposition and fuzzy entropy, comprising the following steps:

[0009] Step 1: Perform intrinsic characteristic scale decomposition on the vibration signal of the circuit breaker operating mechanism, and adaptively decompose the vibration signal into multiple intrinsic characteristic scale components and a monotonic trend signal;

[0010] Step 2: Calculate the fuzzy entropy of each intrinsic characteristic scale component, and construct the fuzzy entropy of all intrinsic characteristic scale components into a fuzzy entropy feature vector;

[0011] Step 3: Using the fuzzy entropy feature vector as input, a multi-classification support vector machine is used for fault diagnosis.

[0012] Furthermore, the step 1 specifically includes:

[0013] (1) Determine the extreme point x(τ) of the vibration signal x(t) of the circuit breaker operating mechanism k ) and the corresponding time point τ k (k=1,2,…M, M is the number of extreme points);

[0014] (2) Calculate the reference point:

[0015]

[0016] (3) Calculate the local mean point:

[0017] M k =αA k +(1-α)X k (2)

[0018] (4) Perform cubic spline interpolation on the local mean point to obtain m(t);

[0019] (5) Calculate the local envelope point:

[0020] E k =|A k -X k | / 2 (3)

[0021] (6) Perform cubic spline interpolation on the local envelope points to obtain a(t);

[0022] (7) Calculate the signals h(t) and s(t):

[0023] h(t)=x(t)-m(t) (4)

[0024] a(t)=m(t) / a(t) (5)

[0025] (8) Determine whether s(t) is a pure frequency signal. If s(t) is a pure frequency signal, go to step (9); if s(t) is not a pure frequency signal, set x(t) = s(t) and go to step (1);

[0026] (9) Calculate the intrinsic characteristic scale component ISC1 and the residual component r1:

[0027]

[0028] r1=x(t)-ISC1 (7)

[0029] (10) Repeat the above steps until the remaining component r n As a monotonic function, the vibration signal x(t) of the circuit breaker operating mechanism is decomposed into:

[0030]

[0031] Furthermore, for a time series with a data length of N {ISC p (n)}, the fuzzy entropy calculation method is:

[0032] (1) Construct N-m+1 data sequences of length m:

[0033]

[0034]

[0035]

[0036] (2) Calculate the distance between any two time series:

[0037]

[0038] (3) Calculate the similarity of any two time series:

[0039]

[0040] Among them, r and n are similarity calculation parameters;

[0041] (4) Define the function:

[0042]

[0043] (5) Fuzzy entropy is:

[0044] SF(m,n,r)=lnΦ m (n,r)-lnΦ m+1 (n,r) (15).

[0045] Furthermore, it is assumed that the vibration signal x(t) of the circuit breaker operating mechanism is decomposed by the intrinsic characteristic scale method to obtain n intrinsic characteristic scale components ISC1, ISC2, …ISC n , the fuzzy entropy method is used to obtain n fuzzy entropies SF1, SF2, …SF n , the n fuzzy entropies form an n-dimensional feature vector [SF1, SF2, …SF n ], input the multi-classification support vector machine to realize the training and prediction of the multi-classification support vector machine.

[0046] Furthermore, the kernel function of the multi-classification support vector machine uses the Gaussian kernel function:

[0047]

[0048] Where σ is the variance.

[0049] Furthermore, it also includes spring fatigue testing.

[0050] Furthermore, it also includes performing an axle pin fall-off test.

[0051] Furthermore, it also includes electromagnet jamming test.

[0052] A second aspect of the present invention provides an intelligent diagnosis device for a circuit breaker operating mechanism based on intrinsic characteristic scale decomposition and fuzzy entropy, which is used to implement the above-mentioned diagnosis method, including:

[0053] The first module is used to perform intrinsic characteristic scale decomposition on the vibration signal of the circuit breaker operating mechanism, and adaptively decompose the vibration signal into multiple intrinsic characteristic scale components and a monotonic trend signal;

[0054] The second module is used to calculate the fuzzy entropy of each intrinsic characteristic scale component, and construct the fuzzy entropy of all intrinsic characteristic scale components into a fuzzy entropy feature vector;

[0055] The third module is used to perform fault diagnosis using a multi-classification support vector machine with the fuzzy entropy feature vector as input.

[0056] A third aspect of the present invention provides an electronic device, comprising a processor and a memory connected to the processor for storing executable instructions of the processor, wherein the processor is used to execute the above-mentioned intelligent diagnosis method for circuit breaker operating mechanism based on intrinsic characteristic scale decomposition and fuzzy entropy.

[0057] Compared with the prior art, the intelligent diagnosis method for circuit breaker operating mechanism based on intrinsic characteristic scale decomposition and fuzzy entropy described in the present invention has the following advantages:

[0058] (1) The present invention proposes to perform intrinsic characteristic scale decomposition on the vibration signal of the circuit breaker operating mechanism. The method is adaptive and can avoid the shortcomings of the existing methods such as window Fourier transform, wavelet analysis, empirical mode decomposition and local mean decomposition.

[0059] (2) In view of the nonlinear and non-stationary characteristics of the intrinsic characteristic scale component of the vibration signal of the operating mechanism, fuzzy entropy is selected to perform complexity analysis on the intrinsic characteristic scale component. Compared with correlation dimension, approximate entropy and sample entropy, fuzzy entropy has stronger stability and continuity, and has better dependence on data length.

[0060] (3) Construct an n-dimensional fuzzy entropy feature vector [SF1, SF2, …SF n ], input the multi-classification support vector machine to realize the training and prediction of the multi-classification support vector machine. Compared with the nested binary support vector machine, the multi-classification support vector machine has the advantage of short classification time. In addition, the fuzzy entropy characteristics are more obvious at different faults, and the classification accuracy of the multi-classification support vector machine is high enough. The recognition accuracy of this method in the fault diagnosis of the high-voltage circuit breaker operating mechanism is higher than 95%. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] The accompanying drawings constituting a part of the present invention are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the accompanying drawings:

[0062] Figure 1 It is a schematic diagram of the intelligent diagnosis process of the circuit breaker operating mechanism of the present invention;

[0063] Figure 2 It is a schematic diagram of the process flow of decomposing the intrinsic characteristic scale of the vibration signal of the operating mechanism of the present invention;

[0064] Figure 3 It is a schematic diagram of the fatigue test results of the spring of the present invention;

[0065] Figure 4It is a schematic diagram of the test result of the shaft pin falling off of the present invention;

[0066] Figure 5 It is a schematic diagram of the electromagnet jamming test result of the present invention. DETAILED DESCRIPTION

[0067] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features in the embodiments may be combined with each other.

[0068] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", and the like are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, features defined as "first", "second", and the like may explicitly or implicitly include one or more of the features. In the description of the present invention, unless otherwise specified, "multiple" means two or more.

[0069] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood by specific circumstances.

[0070] The present invention will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0071] The present invention proposes an intelligent diagnosis method for a circuit breaker operating mechanism based on intrinsic characteristic scale decomposition and fuzzy entropy. The method firstly uses intrinsic characteristic scale decomposition to adaptively decompose the original vibration signal, then calculates the fuzzy entropy of the intrinsic characteristic scale component, and finally uses the fuzzy entropy vector as input to perform intelligent fault diagnosis on the circuit breaker operating mechanism using a multi-classification support vector machine.

[0072] The existing vibration signal analysis methods for circuit breaker operating mechanisms mainly include window Fourier transform, wavelet analysis, empirical mode decomposition and local mean decomposition methods. Due to the limitations of the Heisenberg uncertainty principle, window Fourier transform and wavelet analysis cannot take into account both time resolution and frequency resolution; when empirical mode decomposition uses cubic splines to form upper and lower envelopes, there is an over-envelope or under-envelope phenomenon, and the Hilbert transform has problems such as negative frequency; the local mean decomposition method has problems such as endpoint effect, frequency confusion, and signal mutation caused by demodulation. Existing vibration signal analysis methods often draw wrong conclusions for early weak faults of the operating mechanism. Therefore, it is very necessary to perform adaptive and accurate decomposition of the circuit breaker operating mechanism. The patent of the present invention first uses adaptive intrinsic characteristic scale decomposition to decompose the vibration signal of the circuit breaker operating mechanism.

[0073] Aiming at the nonlinear and non-stationary characteristics of the intrinsic characteristic scale component of the vibration signal of the operating mechanism, fuzzy entropy is selected to perform complexity analysis on the intrinsic characteristic scale component. Compared with correlation dimension, approximate entropy and sample entropy, fuzzy entropy has stronger stability and continuity, and better dependence on data length.

[0074] Construct n-dimensional fuzzy entropy feature vector [SF1, SF2, …SF n ], input the multi-classification support vector machine to realize the training and prediction of the multi-classification support vector machine. Compared with the nested binary support vector machine, the multi-classification support vector machine has the advantage of short classification time. In addition, the fuzzy entropy characteristics of different circuit breaker operating mechanisms are more obvious, and the classification accuracy of the multi-classification support vector machine is high enough. This method has a higher accuracy in the fault diagnosis of high-voltage circuit breaker operating mechanisms.

[0075] Embodiment 1:

[0076] The intelligent diagnosis process of circuit breaker operating mechanism based on intrinsic characteristic scale decomposition and fuzzy entropy is as follows: Figure 1 As shown in FIG, the main steps include: (1) performing intrinsic characteristic scale decomposition on the vibration signal of the circuit breaker operating mechanism, and adaptively decomposing the vibration signal into multiple intrinsic characteristic scale components and a monotonic trend signal; (2) calculating the fuzzy entropy of each intrinsic characteristic scale component, and constructing the fuzzy entropy of all intrinsic characteristic scale components into a fuzzy entropy feature vector; (3) taking the fuzzy entropy feature vector as input, a multi-classification support vector machine is used for fault diagnosis.

[0077] The collected vibration signal of the circuit breaker operating mechanism is x(t), and the intrinsic characteristic scale decomposition process is as follows: Figure 2 The specific steps are:

[0078] (1) Determine the extreme point x(τ) of the vibration signal x(t) of the circuit breaker operating mechanism k ) and the corresponding time point τk (k=1,2,…M, M is the number of extreme points);

[0079] (2) Calculate the reference point:

[0080]

[0081] (3) Calculate the local mean point:

[0082] M k =αA k +(1-α)X k (2)

[0083] (4) Perform cubic spline interpolation on the local mean point to obtain m(t);

[0084] (5) Calculate the local envelope point:

[0085] E k =|A k -X k | / 2 (3)

[0086] (6) Perform cubic spline interpolation on the local envelope points to obtain a(t);

[0087] (7) Calculate the signals h(t) and s(t):

[0088] h(t)=x(t)-m(t) (4)

[0089] a(t)=m(t) / a(t) (5)

[0090] (8) Determine whether s(t) is a pure frequency signal. If s(t) is a pure frequency signal, go to step (9); if s(t) is not a pure frequency signal, set x(t) = s(t) and go to step (1);

[0091] (9) Calculate the intrinsic characteristic scale component ISC1 and the residual component r1:

[0092]

[0093] r1=x(t)-ISC1 (7)

[0094] (10) Repeat the above steps until the remaining component r n As a monotonic function, the vibration signal x(t) of the circuit breaker operating mechanism can be decomposed into:

[0095]

[0096] For a time series with a data length of N {ISC p (n)}, the fuzzy entropy calculation method is:

[0097] (1) Construct N-m+1 data sequences of length m:

[0098]

[0099]

[0100]

[0101] (2) Calculate the distance between any two time series:

[0102]

[0103] (3) Calculate the similarity of any two time series:

[0104]

[0105] Where r and n are similarity calculation parameters.

[0106] (4) Define the function:

[0107]

[0108] (5) Fuzzy entropy is:

[0109] SF(m,n,r)=lnΦ m (n,r)-lnΦ m+1 (n,r) (15)

[0110] Assume that the vibration signal x(t) of the circuit breaker operating mechanism can be decomposed into n intrinsic characteristic scale components ISC1, ISC2, …ISC n , using the fuzzy entropy method, we can get n fuzzy entropies SF1, SF2, …SF n , the n fuzzy entropies form an n-dimensional feature vector [SF1, SF2, …SF n ]. Input the multi-classification support vector machine to realize the training and prediction of the multi-classification support vector machine. The kernel function of the multi-classification support vector machine uses the Gaussian kernel function:

[0111]

[0112] Where σ is the variance.

[0113] Figure 3 is the spring fatigue test result. Figure 3 It can be seen that the recognition accuracy of spring fatigue fault by the intelligent diagnosis method of circuit breaker operating mechanism based on intrinsic characteristic scale decomposition and fuzzy entropy is 98%.

[0114] Figure 4This is the result of the shaft pin fall-off test. Figure 4 It can be seen that the accuracy of pin fall-off fault identification using the intelligent diagnosis method for circuit breaker operating mechanism based on intrinsic characteristic scale decomposition and fuzzy entropy is 98%.

[0115] Figure 5 This is the result of the electromagnet stuck test. Figure 5 It can be seen that the accuracy of identifying electromagnet jamming faults using the intelligent diagnosis method for circuit breaker operating mechanism based on intrinsic characteristic scale decomposition and fuzzy entropy is 95%.

[0116] Embodiment 2:

[0117] An intelligent diagnosis device for circuit breaker operating mechanism based on intrinsic characteristic scale decomposition and fuzzy entropy, used to implement the above-mentioned diagnosis method, comprises:

[0118] The first module is used to perform intrinsic characteristic scale decomposition on the vibration signal of the circuit breaker operating mechanism, and adaptively decompose the vibration signal into multiple intrinsic characteristic scale components and a monotonic trend signal;

[0119] The second module is used to calculate the fuzzy entropy of each intrinsic characteristic scale component, and construct the fuzzy entropy of all intrinsic characteristic scale components into a fuzzy entropy feature vector;

[0120] The third module is used to perform fault diagnosis using a multi-classification support vector machine with the fuzzy entropy feature vector as input.

[0121] Embodiment three:

[0122] An electronic device comprises a processor and a memory which is in communication with the processor and is used to store executable instructions of the processor, wherein the processor is used to execute the above-mentioned intelligent diagnosis method for circuit breaker operating mechanism based on intrinsic characteristic scale decomposition and fuzzy entropy.

[0123] All matters not mentioned above are prior art.

[0124] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. An intelligent diagnosis method for circuit breaker operating mechanism based on intrinsic characteristic scale decomposition and fuzzy entropy, characterized by: The steps include: Step 1: Perform intrinsic characteristic scale decomposition on the vibration signal of the circuit breaker operating mechanism, and adaptively decompose the vibration signal into multiple intrinsic characteristic scale components and a monotonic trend signal; Step 2: Calculate the fuzzy entropy of each intrinsic characteristic scale component, and construct the fuzzy entropy of all intrinsic characteristic scale components into a fuzzy entropy feature vector; Step 3: Using the fuzzy entropy feature vector as input, a multi-classification support vector machine is used for fault diagnosis.

2. The intelligent diagnosis method for circuit breaker operating mechanism based on intrinsic characteristic scale decomposition and fuzzy entropy according to claim 1 is characterized by: The step 1 specifically includes: (1) Determine the extreme point x(τ) of the vibration signal x(t) of the circuit breaker operating mechanism k ) and the corresponding time point τ k (k=1,2,…M, M is the number of extreme points); (2) Calculate the reference point: (3) Calculate the local mean point: M k =αA k +(1-α)X k (2) (4) Perform cubic spline interpolation on the local mean point to obtain m(t); (5) Calculate the local envelope point: AND k =|A k -X k | / 2 (3) (6) Perform cubic spline interpolation on the local envelope points to obtain a(t); (7) Calculate the signals h(t) and s(t): h(t)=x(t)-m(t) (4) a(t)=m(t) / a(t) (5) (8) Determine whether s(t) is a pure frequency signal. If s(t) is a pure frequency signal, go to step (9); if s(t) is not a pure frequency signal, set x(t) = s(t) and go to step (1); (9) Calculate the intrinsic characteristic scale component ISC1 and the residual component r1: r1=x(t)-ISC1 (7) (10) Repeat the above steps until the remaining component r n As a monotonic function, the vibration signal x(t) of the circuit breaker operating mechanism is decomposed into:

3. The intelligent diagnosis method for circuit breaker operating mechanism based on intrinsic characteristic scale decomposition and fuzzy entropy according to claim 2 is characterized by: For a time series with a data length of N {ISC p (n)}, the fuzzy entropy calculation method is: (1) Construct N-m+1 data sequences of length m: (2) Calculate the distance between any two time series: (3) Calculate the similarity of any two time series: Among them, r and n are similarity calculation parameters; (4) Define the function: (5) Fuzzy entropy is: SF(m,n,r)=lnΦ m (n,r)-lnΦ m+1 (n,r) (15)。 4. The intelligent diagnosis method for circuit breaker operating mechanism based on intrinsic characteristic scale decomposition and fuzzy entropy according to claim 3 is characterized in that: The vibration signal x(t) of the circuit breaker operating mechanism is decomposed by the intrinsic characteristic scale method to obtain n intrinsic characteristic scale components ISC1, ISC2, ... ISC n , the fuzzy entropy method is used to obtain n fuzzy entropies SF1, SF2, …SF n , the n fuzzy entropies form an n-dimensional feature vector [SF1, SF2, …SF n ], input the multi-classification support vector machine to realize the training and prediction of the multi-classification support vector machine.

5. The intelligent diagnosis method for circuit breaker operating mechanism based on intrinsic characteristic scale decomposition and fuzzy entropy according to claim 4 is characterized by: The kernel function of the multi-classification support vector machine uses the Gaussian kernel function: Where σ is the variance.

6. The intelligent diagnosis method for circuit breaker operating mechanism based on intrinsic characteristic scale decomposition and fuzzy entropy according to claim 1, characterized in that: This also includes performing spring fatigue tests.

7. The intelligent diagnosis method for circuit breaker operating mechanism based on intrinsic characteristic scale decomposition and fuzzy entropy according to claim 1, characterized in that: It also includes a pin fall-off test.

8. The intelligent diagnosis method for circuit breaker operating mechanism based on intrinsic characteristic scale decomposition and fuzzy entropy according to claim 1, characterized in that: Also includes solenoid jam test.

9. An intelligent diagnosis device for circuit breaker operating mechanism based on intrinsic characteristic scale decomposition and fuzzy entropy, used to implement the diagnosis method according to any one of claims 1 to 8, characterized in that: include: The first module is used to perform intrinsic characteristic scale decomposition on the vibration signal of the circuit breaker operating mechanism, and adaptively decompose the vibration signal into multiple intrinsic characteristic scale components and a monotonic trend signal; The second module is used to calculate the fuzzy entropy of each intrinsic characteristic scale component, and construct the fuzzy entropy of all intrinsic characteristic scale components into a fuzzy entropy feature vector; The third module is used to perform fault diagnosis using a multi-classification support vector machine with the fuzzy entropy feature vector as input.

10. An electronic device, comprising a processor and a memory connected to the processor for storing instructions executable by the processor, characterized in that: The processor is used to execute the intelligent diagnosis method for circuit breaker operating mechanism based on intrinsic characteristic scale decomposition and fuzzy entropy as described in any one of claims 1 to 8.

Images