A method, device and electronic equipment for diagnosing mechanical instability fault of transformer

Abstract

The present invention relates to the field of fault diagnosis technology, and specifically to a transformer mechanical instability fault diagnosis method, device and electronic equipment, including: collecting the voiceprint vibration signal of the transformer, preprocessing the voiceprint vibration signal, then calculating the average complexity of the voiceprint vibration signal, normalizing the average complexity of the voiceprint vibration signal to obtain the relative complexity of the voiceprint vibration signal, and determining the transformer mechanical instability fault based on the relative complexity of the voiceprint vibration signal. The present invention realizes the overall mechanical stability monitoring of each transformer winding, improves the overall coverage and performance of the transformer winding mechanical stability monitoring system; and adopts the transformer vibration signal frequency spectrum solution algorithm to establish a transformer vibration frequency domain signal complexity description method, and establishes a winding structure instability fault diagnosis standard based on complexity description, thereby realizing accurate diagnosis of large power transformer winding structure instability faults.

Description

Technical Field

[0001] The present invention relates to the technical field of mechanical fault diagnosis, and in particular to a transformer mechanical instability fault diagnosis method, device and electronic equipment. Background Art

[0002] The large power transformers operated in the ultra-high voltage substation are key equipment in the power grid. They are responsible for the transfer of electric energy and voltage conversion. Their health status directly affects the safe operation of the regional large power grid. During operation, large power transformers are subjected to multiple stresses such as high voltage, strong magnetic field, high temperature, high-frequency mechanical vibration, etc. The internal structural parts are prone to aging. Coupled with external short-circuit shocks and other factors, the mechanical stability of the windings of large power transformers will show a downward trend to varying degrees after long-term operation. Mechanical instability faults such as mechanical loosening, decreased clamping force, and deformation are prone to occur, leaving potential accidents. The decline in the mechanical stability of the transformer windings causes the short-circuit resistance to change from quantitative change to qualitative change. When the transformer's short-circuit resistance drops to a level that is insufficient to withstand a certain short-circuit current, the windings will experience irreversible mechanical deformation failures. Timely and accurate assessment of the mechanical stability of the transformer windings and online diagnosis of winding structure instability faults have a positive effect on improving the pertinence of transformer maintenance, reducing transformer short-circuit damage, and improving the safety of power grid operation.

[0003] The change of mechanical stability of transformer windings is directly reflected in the change of transformer winding shape and geometric dimensions between different windings, and the characteristic quantity of mechanical vibration of transformer windings will also change during operation. The change of winding shape and size is manifested as the change of parameters such as inductance and capacitance in electricity, and the change of parameters such as winding current and electrodynamic elastic modulus in mechanical vibration. The detection methods of mechanical stability of transformer windings based on electrical parameters mainly include transformer winding frequency response analysis and low voltage short circuit impedance test. These methods have played a positive role in discovering transformers with insufficient mechanical stability of windings, and there are also many successful cases. However, these test methods belong to offline test methods for power outages, and all require the transformer to be shut down. Under the background of high power supply reliability requirements, it is difficult to meet the lean control requirements of power grid companies for transformer winding mechanical stability. The main research direction of transformer winding stability detection based on mechanical vibration parameters is to realize live detection of transformer winding stability by detecting the surface vibration of the transformer shell or the sound around the transformer during operation. However, the complex mechanical vibration and noise of existing transformers will affect the accuracy of sensing and monitoring. In addition, the existing monitoring methods mostly monitor local components of the transformer, which is difficult to reflect the mechanical stability level of multiple windings such as high voltage and low voltage of the transformer. There is currently a lack of online diagnostic methods for transformer winding structural instability. Summary of the invention

[0004] The present invention provides a transformer mechanical instability fault diagnosis method, device and electronic equipment for monitoring the overall mechanical stability of each transformer winding, thereby improving the overall coverage and performance of the transformer winding mechanical stability monitoring system and realizing accurate diagnosis of large power transformer winding structure instability faults.

[0005] The embodiment of this specification provides a transformer mechanical instability fault diagnosis method, including:

[0006] Collecting a voiceprint vibration signal of the transformer, and preprocessing the voiceprint vibration signal;

[0007] Performing frequency decomposition on the preprocessed voiceprint vibration signal, storing the decomposed voiceprint vibration signal into a voiceprint vibration signal sequence matrix, and calculating the mean of the voiceprint vibration signal sequence matrix;

[0008] Reconstructing the voiceprint vibration signal sequence matrix based on the mean value of the voiceprint vibration signal sequence matrix to obtain a voiceprint vibration signal reconstruction sequence, and calculating the voiceprint vibration signal complexity based on the voiceprint vibration signal reconstruction sequence;

[0009] Reverse-converting the voiceprint vibration signal reconstruction sequence to obtain a voiceprint vibration signal reverse-construction sequence, and calculating the reverse complexity of the voiceprint vibration signal based on the voiceprint vibration signal reverse-construction sequence;

[0010] Calculating an average complexity of the voiceprint vibration signal according to the complexity of the voiceprint vibration signal and the reverse complexity of the voiceprint vibration signal;

[0011] The average complexity of the soundprint vibration signal is normalized to obtain the relative complexity of the soundprint vibration signal, and the mechanical instability fault of the transformer is determined based on the relative complexity of the soundprint vibration signal.

[0012] Preferably, collecting the voiceprint vibration signal of the transformer and preprocessing the voiceprint vibration signal includes:

[0013] Multiple vibration acceleration sensors arranged in a matrix are used to collect the transformer's soundprint vibration signals;

[0014] Deleting the missing values ​​in the voiceprint vibration signal of the transformer;

[0015] Identifying and deleting isolated points in the voiceprint vibration signal of the transformer that do not conform to data characteristics;

[0016] The voiceprint vibration signal of the transformer is smoothed, and the smoothing formula is as follows:

[0017]

[0018] Wherein, h is the sampling window number of the vibration acceleration sensor, m is the number of the voiceprint vibration signals in the unit window, that is, the window time is mTs, a(h) is the amplitude value of the voiceprint vibration signal after sliding average in the hth window, Ts is the sampling period of the vibration acceleration sensor, and the sliding average window time is h*Ts, a r is the amplitude of the voiceprint vibration signal at the rth sampling point in the sampling period, r = 1, 2, 3, ..., m.

[0019] Preferably, the frequency decomposition of the preprocessed voiceprint vibration signal includes:

[0020] The pre-processed voiceprint vibration signal is subjected to discrete Fourier decomposition, and the decomposition formula is as follows:

[0021]

[0022] Wherein, i is a unit complex number, At(k) is the amplitude value of the voiceprint vibration signal at frequency k after Fourier transform, and N is the total number of sensor sliding average windows in the Fourier analysis window, that is, the Fourier window time is N*h*Ts, which is N times the sliding average window time.

[0023] Preferably, reconstructing the voiceprint vibration signal sequence matrix based on the mean value of the voiceprint vibration signal sequence matrix to obtain a voiceprint vibration signal reconstructed sequence includes:

[0024] Each value of the voiceprint vibration signal sequence matrix is ​​compared with the mean value of the voiceprint vibration signal sequence matrix, and the sequence is reconstructed according to the comparison result to obtain the voiceprint vibration signal reconstructed sequence.

[0025] Preferably, the calculating the complexity of the voiceprint vibration signal based on the voiceprint vibration signal reconstruction sequence includes:

[0026] Create a binary pointer sequence;

[0027] Loop through the voiceprint vibration signal reconstruction sequence, and when a sequence corresponding to the pointer sequence exists in the voiceprint vibration signal reconstruction sequence, update the pointer sequence; when a sequence corresponding to the pointer sequence does not exist in the voiceprint vibration signal reconstruction sequence, do not calculate the complexity of the voiceprint vibration signal;

[0028] When the updated pointer sequence is greater than the pointer sequence maximum value, the complexity of the voiceprint vibration signal is output.

[0029] Preferably, the normalizing the average complexity of the voiceprint vibration signal to obtain the relative complexity of the voiceprint vibration signal includes:

[0030] Calculate the ultimate complexity of the voiceprint vibration signal using the following formula:

[0031]

[0032] Wherein, b(k) is the ultimate complexity of the voiceprint vibration signal, and n is the number of elements in the reconstructed sequence of the voiceprint vibration signal;

[0033] The average complexity of the voiceprint vibration signal is normalized according to the limit complexity of the voiceprint vibration signal to calculate the relative complexity of the voiceprint vibration signal. The calculation formula of the relative complexity of the voiceprint vibration signal is as follows:

[0034]

[0035] Among them, c(k) is the relative complexity of the voiceprint vibration signal, is the average complexity of the voiceprint vibration signal, and b(k) is the maximum complexity of the voiceprint vibration signal.

[0036] Preferably, the determining of the transformer mechanical instability fault based on the relative complexity of the soundprint vibration signal includes:

[0037] When the relative complexity of the voiceprint vibration signal is less than or equal to a first preset complexity threshold, the transformer is mechanically stable;

[0038] When the relative complexity of the voiceprint vibration signal is greater than or equal to a second preset complexity threshold, the transformer is mechanically unstable;

[0039] When the relative complexity of the voiceprint vibration signal is greater than a first preset complexity and less than a threshold and less than a second preset complexity threshold, the mechanical stability of the transformer has a tendency to deteriorate.

[0040] The embodiment of this specification also provides a transformer mechanical instability fault diagnosis device, including:

[0041] A signal acquisition module, used to collect the voiceprint vibration signal of the transformer and pre-process the voiceprint vibration signal;

[0042] A signal decomposition module, used for performing frequency decomposition on the preprocessed voiceprint vibration signal, storing the decomposed voiceprint vibration signal into a voiceprint vibration signal sequence matrix, and calculating the mean of the voiceprint vibration signal sequence matrix;

[0043] A sequence reconstruction module, configured to reconstruct the voiceprint vibration signal sequence matrix based on the mean value of the voiceprint vibration signal sequence matrix to obtain a voiceprint vibration signal reconstruction sequence, and calculate the voiceprint vibration signal complexity based on the voiceprint vibration signal reconstruction sequence;

[0044] A sequence conversion module, configured to reverse the sequence of the voiceprint vibration signal reconstruction to obtain a reverse sequence of the voiceprint vibration signal reconstruction, and calculate the reverse complexity of the voiceprint vibration signal based on the reverse sequence of the voiceprint vibration signal reconstruction;

[0045] A complexity calculation module, used to calculate the average complexity of the voiceprint vibration signal according to the complexity of the voiceprint vibration signal and the reverse complexity of the voiceprint vibration signal;

[0046] The mechanical instability judgment module is used to normalize the average complexity of the soundprint vibration signal to obtain the relative complexity of the soundprint vibration signal, and determine the transformer mechanical instability fault based on the relative complexity of the soundprint vibration signal.

[0047] An electronic device, wherein the electronic device comprises:

[0048] A processor and a memory storing computer executable instructions, wherein when the executable instructions are executed, the processor executes any of the methods described above.

[0049] A computer-readable storage medium stores one or more instructions, and when the one or more instructions are executed by a processor, any of the above methods is implemented.

[0050] The present invention realizes the overall mechanical stability monitoring of each transformer winding, improves the overall coverage and performance of the transformer winding mechanical stability monitoring system; and adopts the transformer vibration signal frequency spectrum solution algorithm to establish the transformer vibration frequency domain signal complexity description method, and establishes the winding structure instability fault diagnosis standard based on the complexity description, thereby realizing the accurate diagnosis of large power transformer winding structure instability fault. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] 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:

[0052] Figure 1 A schematic diagram of the principle of a transformer mechanical instability fault diagnosis method provided in an embodiment of this specification;

[0053] Figure 2 A typical layout diagram of vibration detection points for a single transformer provided in the embodiments of this specification;

[0054] Figure 3 The complexity calculation process of the voiceprint vibration signal provided in the embodiments of this specification;

[0055] Figure 4A schematic diagram of the structure of a transformer mechanical instability fault diagnosis device provided in an embodiment of this specification;

[0056] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of this specification;

[0057] Figure 6 A schematic diagram of a computer-readable medium provided in accordance with an embodiment of the present specification. DETAILED DESCRIPTION

[0058] Exemplary embodiments of the present invention will now be described more fully with reference to the accompanying drawings. However, exemplary embodiments can be implemented in a variety of forms, and should not be construed as limiting the present invention to the embodiments set forth herein. On the contrary, providing these exemplary embodiments enables the present invention to be more comprehensive and complete, and is more convenient for fully conveying the inventive concept to those skilled in the art. The same reference numerals in the figures represent the same or similar elements, components or parts, and thus their repeated description will be omitted.

[0059] Under the premise of being consistent with the technical concept of the present invention, the features, structures, characteristics or other details described in a specific embodiment do not exclude that they can be combined in one or more other embodiments in a suitable manner.

[0060] In the description of specific embodiments, the features, structures, characteristics or other details described in the present invention are intended to enable those skilled in the art to fully understand the embodiments. However, it does not exclude that those skilled in the art can practice the technical solutions of the present invention without one or more of the specific features, structures, characteristics or other details.

[0061] The figures shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor must they be performed in the order described. For example, some operations / steps can be decomposed, while some operations / steps can be combined or partially combined, so the actual execution order may change according to actual conditions.

[0062] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0063] The term "and / or" or "and / or" includes all combinations of any one or more of the associated listed items.

[0064] Reference Figure 1A schematic diagram of a transformer mechanical instability fault diagnosis method provided in an embodiment of this specification includes:

[0065] S101: collecting a voiceprint vibration signal of a transformer, and preprocessing the voiceprint vibration signal;

[0066] In this embodiment, if Figure 2 As shown, a single transformer is used as an example to arrange the vibration acceleration sensor. A high-sensitivity vibration acceleration sensor is used. The vibration acceleration sensor has a built-in piezoelectric element and an analog conversion chip to realize the perception and electrical conversion of vibration signals. The vibration acceleration sensor quantifies the vibration soundprint mechanical wave sensed by the front end into an acceleration value and converts it into a current signal output. The transformer vibration soundprint monitoring and sensing device collects the signal output by the vibration acceleration sensor through a high-speed acquisition channel, and uses the host computer to monitor and record the signal to realize the transmission and collection of the transformer soundprint vibration signal. In addition, Figure 2 As shown in the figure, a matrix distribution method is adopted for the transformer housing to apply multiple vibration acceleration sensors. Figure 2 The digital serial number in represents the number of the vibration acceleration sensor, and the vibration acceleration state quantity at multiple positions of 20% to 80% of the long axial height of the transformer body is measured synchronously. When the transformer is energized, 8 voiceprint vibration acceleration sensors are adsorbed on the surface of the transformer body in a multi-point matrix installation manner. The installation height is about 20% to 80%. It can be installed without power outage and does not affect the safe operation of the transformer. It is a non-invasive, safe and reliable monitoring method. It should be noted that the voiceprint vibration signal includes necessary data information such as voiceprint vibration frequency, voiceprint vibration acceleration, and voiceprint vibration displacement.

[0067] Furthermore, the collecting of the voiceprint vibration signal of the transformer and preprocessing of the voiceprint vibration signal include:

[0068] Multiple vibration acceleration sensors arranged in a matrix are used to collect the transformer's soundprint vibration signals;

[0069] Deleting the missing values ​​in the voiceprint vibration signal of the transformer;

[0070] Identifying and deleting isolated points in the voiceprint vibration signal of the transformer that do not conform to data characteristics;

[0071] The voiceprint vibration signal of the transformer is smoothed, and the smoothing formula is as follows:

[0072]

[0073] Wherein, h is the sampling window number of the vibration acceleration sensor, m is the number of the soundprint vibration signals in the unit window, that is, the window time is mTs, a(h) is the amplitude value of the soundprint vibration signal after sliding average in the hth window, Ts is the sampling period of the vibration acceleration sensor, and the sliding average window time is h*Ts, a r is the amplitude of the voiceprint vibration signal at the rth sampling point in the sampling period, r = 1, 2, 3, ..., m.

[0074] In this embodiment, the missing values ​​in the recorded transformer voiceprint vibration signal data are deleted, and the isolated points in the voiceprint vibration signal data that obviously do not meet the data characteristics are identified and deleted. In order to eliminate the influence of white noise of the electrical signal during the external vibration noise level measurement process, the voiceprint vibration signal data needs to be smoothed. The specific operation method is to use the following formula to perform sliding average on the recorded voiceprint vibration signal data:

[0075]

[0076] Preferably, the window time 1 / (mTs) is not higher than twice the vibration frequency of interest.

[0077] S102: performing frequency decomposition on the preprocessed voiceprint vibration signal, storing the decomposed voiceprint vibration signal into a voiceprint vibration signal sequence matrix, and calculating the mean of the voiceprint vibration signal sequence matrix;

[0078] Furthermore, the performing frequency decomposition on the preprocessed voiceprint vibration signal includes:

[0079] The pre-processed voiceprint vibration signal is subjected to discrete Fourier decomposition, and the decomposition formula is as follows:

[0080]

[0081] Where i is a unit complex number, A t (k) is the amplitude value of the soundprint vibration signal at frequency k after Fourier transform, and N is the total number of sensor sliding average windows in the Fourier analysis window, that is, the Fourier window time is N*h*Ts, which is N times the sliding average window time.

[0082] In this embodiment, discrete Fourier decomposition is performed on the collected voiceprint vibration signal, and the calculation formula is as follows:

[0083]

[0084] Then, the vibration acceleration sensor data decomposed at frequency k is stored in the voiceprint vibration signal sequence matrix A(k) = {A1(k), A2(k), ..., An(k)}, where n is the corresponding sensor number, and then the mean of the voiceprint vibration signal sequence matrix corresponding to each frequency band is calculated. Provide data support for subsequent sequence matrix reconstruction.

[0085] S103: reconstructing the voiceprint vibration signal sequence matrix based on the mean value of the voiceprint vibration signal sequence matrix to obtain a voiceprint vibration signal reconstructed sequence, and calculating the voiceprint vibration signal complexity based on the voiceprint vibration signal reconstructed sequence;

[0086] Furthermore, the reconstructing the voiceprint vibration signal sequence matrix based on the mean of the voiceprint vibration signal sequence matrix to obtain a voiceprint vibration signal reconstructed sequence includes:

[0087] Each value of the voiceprint vibration signal sequence matrix is ​​compared with the mean value of the voiceprint vibration signal sequence matrix, and the sequence is reconstructed according to the comparison result to obtain a voiceprint vibration signal reconstructed sequence.

[0088] In this embodiment, the voiceprint vibration signal sequence matrix A(k) = {A1(k), A2(k), ..., An(k)} is reconstructed so that the value greater than the mean of the voiceprint vibration signal sequence matrix Ai(k) is "1", which is smaller than the mean of the matrix of the voiceprint vibration signal sequence Ai(k) is "0", and a "0, 1" sequence is obtained, which is recorded as the soundprint vibration signal reconstruction sequence {s1, s2, ..., sn}, where i = 1, 2, 3, ..., n. The reconstruction of the sequence matrix is ​​achieved in the above manner to improve the overall mechanical stability monitoring of each transformer winding, thereby improving the overall coverage and performance of the transformer winding mechanical stability monitoring system.

[0089] Furthermore, the calculating the complexity of the voiceprint vibration signal based on the voiceprint vibration signal reconstruction sequence includes:

[0090] Create a binary pointer sequence;

[0091] Loop through the voiceprint vibration signal reconstruction sequence, and when a sequence corresponding to the pointer sequence exists in the voiceprint vibration signal reconstruction sequence, update the pointer sequence; when a sequence corresponding to the pointer sequence does not exist in the voiceprint vibration signal reconstruction sequence, do not calculate the complexity of the voiceprint vibration signal;

[0092] When the updated pointer sequence is greater than the pointer sequence maximum value, the complexity of the voiceprint vibration signal is output.

[0093] In this embodiment, if Figure 3 As shown, a binary pointer sequence p = {0} is first established, the initial value of the pointer sequence is the sequence set {1}, and the maximum value of the pointer sequence is a set of n 1s, that is, {11...1}, where n is the number of elements in the soundprint vibration signal reconstruction sequence in the previous step. The pointer sequence p starts from 0 and loops through the soundprint vibration signal reconstruction sequence {s1, s2, ..., sn} in turn to find whether it contains the sequence corresponding to the pointer sequence p. If it contains the sequence, the value of the soundprint vibration signal complexity C(k) of the soundprint vibration signal at the frequency point k is added by 1, that is, the soundprint vibration signal complexity C(k) = C(k-1)+1, and the pointer sequence p is added by 1 to form a new sequence; if it does not contain the sequence in the pointer sequence p, the soundprint vibration signal complexity is not calculated; if the pointer sequence p is greater than the maximum value of the pointer sequence, the soundprint vibration signal complexity value C(k) is output. By establishing a transformer vibration frequency domain signal complexity description method, the accurate diagnosis effect of large power transformer winding structure instability faults can be improved.

[0094] S104: performing reverse conversion on the voiceprint vibration signal reconstruction sequence to obtain a voiceprint vibration signal reverse reconstruction sequence, and calculating the reverse complexity of the voiceprint vibration signal based on the voiceprint vibration signal reverse reconstruction sequence;

[0095] S105: Calculating an average complexity of the voiceprint vibration signal according to the complexity of the voiceprint vibration signal and the reverse complexity of the voiceprint vibration signal;

[0096] In this embodiment, the voiceprint vibration signal reconstruction sequence is reversed, that is, the voiceprint vibration signal reconstruction sequence is converted into {sn, sn-1, ..., s1}, the above-mentioned voiceprint vibration signal complexity calculation process is repeated for the voiceprint vibration signal reverse reconstruction sequence, and the voiceprint vibration signal reverse complexity C'(k) is output, and then the average complexity of the voiceprint vibration signal is calculated according to the voiceprint vibration signal complexity C(k) and the voiceprint vibration signal reverse complexity C'(k) A complexity description method of transformer vibration frequency domain signal is established to improve the accurate diagnosis effect of large power transformer winding structure instability faults.

[0097] S106: normalizing the average complexity of the soundprint vibration signal to obtain a relative complexity of the soundprint vibration signal, and determining a transformer mechanical instability fault based on the relative complexity of the soundprint vibration signal.

[0098] Furthermore, the normalizing the average complexity of the voiceprint vibration signal to obtain the relative complexity of the voiceprint vibration signal includes:

[0099] Calculate the ultimate complexity of the voiceprint vibration signal using the following formula:

[0100]

[0101] Wherein, b(k) is the ultimate complexity of the voiceprint vibration signal, and n is the number of elements in the reconstructed sequence of the voiceprint vibration signal;

[0102] The average complexity of the voiceprint vibration signal is normalized according to the limit complexity of the voiceprint vibration signal to calculate the relative complexity of the voiceprint vibration signal. The calculation formula of the relative complexity of the voiceprint vibration signal is as follows:

[0103]

[0104] Among them, c(k) is the relative complexity of the voiceprint vibration signal, is the average complexity of the voiceprint vibration signal, and b(k) is the maximum complexity of the voiceprint vibration signal.

[0105] In this embodiment, before solving the relative complexity of the voiceprint vibration signal, it is necessary to first calculate the limit complexity of the voiceprint vibration signal. The relative complexity calculation formula of the voiceprint vibration signal is as follows:

[0106]

[0107] Then, the average complexity of the voiceprint vibration signal calculated above is calculated based on the relative complexity b(k) of the voiceprint vibration signal obtained by solving Normalize to get the relative complexity c(k) of the voiceprint vibration signal. The calculation formula of the relative complexity c(k) of the voiceprint vibration signal is as follows:

[0108]

[0109] By averaging the complexity of the voiceprint vibration signal Normalization processing is performed to improve the convergence effect of data and the diagnostic accuracy of structural instability faults of large power transformer windings.

[0110] Further, the determining of the transformer mechanical instability fault based on the relative complexity of the soundprint vibration signal includes:

[0111] When the relative complexity of the voiceprint vibration signal is less than or equal to a first preset complexity threshold, the transformer is mechanically stable;

[0112] When the relative complexity of the voiceprint vibration signal is greater than or equal to a second preset complexity threshold, the transformer is mechanically unstable;

[0113] When the relative complexity of the voiceprint vibration signal is greater than a first preset complexity and less than a threshold and less than a second preset complexity threshold, the mechanical stability of the transformer has a tendency to deteriorate.

[0114] In this embodiment, a fault diagnosis criterion for the instability of the winding structure based on complexity description is established. According to the solution result of the relative complexity c(k) of the acoustic vibration signal, the mechanical instability of the transformer is judged. When c(k) ≤ 1.7, it is diagnosed that the mechanical stability performance of the transformer is good and it can operate; when 1.7 < c(k) < 2.1, it is diagnosed that the mechanical stability of the transformer shows a deteriorating trend, there are signs of loose clamping force or slight deformation of the winding, and tracking detection should be carried out and relevant tests should be combined with power outage; when c(k) ≥ 2.1, it is diagnosed that the mechanical stability of the transformer has become unstable, and symptoms such as winding deformation, forced warping of the winding, and loosening and aging of the iron core appear, and relevant tests should be carried out after power outage to judge the severity of the abnormality.

[0115] The present invention realizes the overall mechanical stability monitoring of each winding of the transformer, improves the overall coverage and performance of the transformer winding mechanical stability monitoring system; and adopts an algorithm for solving the frequency spectrum of the transformer vibration signal, establishes a method for describing the complexity of the transformer vibration frequency-domain signal, and establishes a fault diagnosis criterion for the instability of the winding structure based on complexity description, so as to realize the accurate diagnosis of the instability fault of the winding structure of large power transformers.

[0116] Figure 2 FIG. is a schematic structural diagram of a device for diagnosing transformer mechanical instability faults provided by an embodiment of this specification, including:

[0117] A signal acquisition module 201, configured to acquire the acoustic vibration signal of the transformer and preprocess the acoustic vibration signal;

[0118] A signal decomposition module 202, configured to perform frequency decomposition on the preprocessed acoustic vibration signal, store the decomposed acoustic vibration signal into an acoustic vibration signal sequence matrix, and calculate the mean value of the acoustic vibration signal sequence matrix;

[0119] A sequence reconstruction module 203, configured to reconstruct the acoustic vibration signal sequence matrix based on the mean value of the acoustic vibration signal sequence matrix to obtain an acoustic vibration signal reconstruction sequence, and calculate the complexity of the acoustic vibration signal based on the acoustic vibration signal reconstruction sequence;

[0120] A sequence conversion module 204, configured to perform an inverse order conversion on the acoustic vibration signal reconstruction sequence to obtain an acoustic vibration signal inverse reconstruction sequence, and calculate the reverse complexity of the acoustic vibration signal based on the acoustic vibration signal inverse reconstruction sequence;

[0121] A complexity calculation module 205, configured to calculate the average complexity of the acoustic vibration signal according to the complexity of the acoustic vibration signal and the reverse complexity of the acoustic vibration signal;

[0122] The mechanical instability judgment module 206 is used to normalize the average complexity of the soundprint vibration signal to obtain the relative complexity of the soundprint vibration signal, and determine the transformer mechanical instability fault based on the relative complexity of the soundprint vibration signal.

[0123] Furthermore, the signal acquisition module 201 includes:

[0124] A signal acquisition unit, used to collect the voiceprint vibration signal of the transformer using a plurality of vibration acceleration sensors arranged in a matrix;

[0125] A first data processing unit, used to delete the missing values ​​in the voiceprint vibration signal of the transformer;

[0126] A second data processing unit is used to identify and delete isolated points that do not conform to data characteristics in the voiceprint vibration signal of the transformer;

[0127] The smoothing processing unit is used to smooth the voiceprint vibration signal of the transformer. The smoothing processing formula is as follows:

[0128]

[0129] Wherein, h is the sampling window number of the vibration acceleration sensor, m is the number of the soundprint vibration signals in the unit window, that is, the window time is mTs, a(h) is the amplitude value of the soundprint vibration signal after sliding average in the hth window, Ts is the sampling period of the vibration acceleration sensor, and the sliding average window time is h*Ts, a r is the amplitude of the voiceprint vibration signal at the rth sampling point in the sampling period, r = 1, 2, 3, ..., m.

[0130] Furthermore, the performing frequency decomposition on the preprocessed voiceprint vibration signal includes:

[0131] The pre-processed voiceprint vibration signal is subjected to discrete Fourier decomposition, and the decomposition formula is as follows:

[0132]

[0133] Where i is a unit complex number, A t (k) is the amplitude value of the soundprint vibration signal at frequency k after Fourier transform, and N is the total number of sensor sliding average windows in the Fourier analysis window, that is, the Fourier window time is N*h*Ts, which is N times the sliding average window time.

[0134] Furthermore, the signal decomposition module 202 includes:

[0135] The signal decomposition unit is used to compare each value of the voiceprint vibration signal sequence matrix with the mean value of the voiceprint vibration signal sequence matrix, reconstruct the sequence according to the comparison result, and obtain the voiceprint vibration signal reconstructed sequence.

[0136] Furthermore, the sequence reconstruction module 203 includes:

[0137] A pointer sequence establishing unit, used for establishing a binary pointer sequence;

[0138] a pointer sequence updating unit, configured to loop through the voiceprint vibration signal reconstruction sequence, and update the pointer sequence when a sequence corresponding to the pointer sequence exists in the voiceprint vibration signal reconstruction sequence; and not calculate the complexity of the voiceprint vibration signal when a sequence corresponding to the pointer sequence does not exist in the voiceprint vibration signal reconstruction sequence;

[0139] The complexity output unit is used to output the complexity of the voiceprint vibration signal when the updated pointer sequence is greater than the maximum value of the pointer sequence.

[0140] Furthermore, the mechanical instability judgment module 206 includes:

[0141] The extreme complexity calculation unit is used to calculate the extreme complexity of the voiceprint vibration signal. The calculation formula is as follows:

[0142]

[0143] Wherein, b(k) is the ultimate complexity of the voiceprint vibration signal, and n is the number of elements in the reconstructed sequence of the voiceprint vibration signal;

[0144] The relative complexity calculation unit is used to normalize the average complexity of the voiceprint vibration signal according to the limit complexity of the voiceprint vibration signal, and calculate the relative complexity of the voiceprint vibration signal. The relative complexity calculation formula of the voiceprint vibration signal is as follows:

[0145]

[0146] Among them, c(k) is the relative complexity of the voiceprint vibration signal, is the average complexity of the voiceprint vibration signal, and b(k) is the maximum complexity of the voiceprint vibration signal.

[0147] Furthermore, the mechanical instability judgment module 206 further includes:

[0148] A first determination unit, configured to determine that the transformer is mechanically stable when the relative complexity of the voiceprint vibration signal is less than or equal to a first preset complexity threshold;

[0149] A second determination unit, configured to determine that the transformer is mechanically unstable when the relative complexity of the voiceprint vibration signal is greater than or equal to a second preset complexity threshold;

[0150] The third judgment unit is used to determine that the mechanical stability of the transformer has a deterioration trend when the relative complexity of the voiceprint vibration signal is greater than a first preset complexity and less than a threshold and less than a second preset complexity threshold.

[0151] The functions of the device in the embodiment of the present invention have been described in the above method embodiment, so for details not provided in the description of this embodiment, please refer to the relevant description in the above embodiment, and no further description will be given here.

[0152] Based on the same inventive concept, an embodiment of this specification also provides an electronic device.

[0153] The following describes an electronic device embodiment of the present invention, which can be regarded as a specific physical implementation of the method and device embodiments of the present invention. The details described in the electronic device embodiment of the present invention should be regarded as a supplement to the above method or device embodiments; details not disclosed in the electronic device embodiment of the present invention can be implemented with reference to the above method or device embodiments.

[0154] Reference Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this specification. Figure 5 The electronic device 300 according to the embodiment of the present invention is described. Figure 5 The electronic device 300 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0155] like Figure 5 As shown, the electronic device 300 is in the form of a general computing device. The components of the electronic device 300 may include, but are not limited to: at least one processing unit 310, at least one storage unit 320, a bus 330 connecting different device components (including the storage unit 320 and the processing unit 310), a display unit 340, etc.

[0156] The storage unit stores program codes, which can be executed by the processing unit 310, so that the processing unit 310 performs the steps according to various exemplary embodiments of the present invention described in the above processing method section of this specification. For example, the processing unit 310 can perform the following steps: Figure 1 Steps shown.

[0157] The storage unit 320 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 3201 and / or a cache memory unit 3202 , and may further include a read-only memory unit (ROM) 3203 .

[0158] The storage unit 320 may also include a program / utility 3204 having a set (at least one) of program modules 3205, such program modules 3205 including but not limited to: operating means, one or more application programs, other program modules and program data, each of which or some combination may include the implementation of a network environment.

[0159] Bus 330 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0160] The electronic device 300 may also communicate with one or more external devices 400 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), one or more devices that enable a user to interact with the electronic device 300, and / or any device that enables the electronic device 300 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed through an input / output (I / O) interface 350. Furthermore, the electronic device 300 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through a network adapter 360. The network adapter 360 may communicate with other modules of the electronic device 300 through the bus 330. It should be understood that although Figure 5 Not shown, other hardware and / or software modules may be used in conjunction with the electronic device 300, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID devices, tape drives, and data backup storage devices.

[0161] Through the description of the above implementation methods, it is easy for those skilled in the art to understand that the exemplary embodiments described in the present invention can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation method of the present invention can be embodied in the form of a software product, which can be stored in a computer-readable storage medium (which can be a CD-ROM, USB flash drive, mobile hard disk, etc.) or on a network, including a number of instructions to enable a computing device (which can be a personal computer, server, or network device, etc.) to execute the above method according to the present invention. When the computer program is executed by a data processing device, the computer-readable medium can implement the above method of the present invention, that is: Figure 1 The method shown.

[0162] Reference Figure 6 A schematic diagram of a computer-readable medium provided in accordance with an embodiment of the present specification.

[0163] accomplish Figure 1 The computer program of the method shown can be stored on one or more computer readable media. The computer readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor device, device or component, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0164] The computer readable storage medium may include a data signal propagated in a baseband or as part of a carrier wave, wherein a readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The readable storage medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in combination with an instruction execution device, device, or device. The program code contained on the readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the above.

[0165] Program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0166] In summary, the present invention can be implemented in hardware, or in a software module running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that general data processing devices such as microprocessors or digital signal processors (DSPs) can be used in practice to implement some or all of the functions of some or all of the components in the embodiments of the present invention. The present invention can also be implemented as a device or apparatus program (e.g., a computer program and a computer program product) for executing part or all of the methods described herein. Such a program implementing the present invention can be stored on a computer-readable medium, or can have the form of one or more signals. Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0167] The specific embodiments described above further describe the purpose, technical solutions and beneficial effects of the present invention in detail. It should be understood that the present invention is not inherently related to any specific computer, virtual device or electronic device, and various general devices can also implement the present invention. The above description is only a specific 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 principles of the present invention should be included in the protection scope of the present invention.

[0168] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0169] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A transformer mechanical instability fault diagnosis method, characterized in that: include: Collecting a voiceprint vibration signal of the transformer, and preprocessing the voiceprint vibration signal; Performing frequency decomposition on the preprocessed voiceprint vibration signal, storing the decomposed voiceprint vibration signal into a voiceprint vibration signal sequence matrix, and calculating the mean of the voiceprint vibration signal sequence matrix; Compare each value of the voiceprint vibration signal sequence matrix with the mean value of the voiceprint vibration signal sequence matrix, reconstruct the voiceprint vibration signal sequence matrix according to the comparison result, obtain a voiceprint vibration signal reconstruction sequence, and establish a binary pointer sequence; loop through the voiceprint vibration signal reconstruction sequence, and when a sequence corresponding to the pointer sequence exists in the voiceprint vibration signal reconstruction sequence, update the pointer sequence; when a sequence corresponding to the pointer sequence does not exist in the voiceprint vibration signal reconstruction sequence, do not calculate the voiceprint vibration signal complexity; when the updated pointer sequence is greater than the maximum value of the pointer sequence, output the voiceprint vibration signal complexity; Reverse-converting the voiceprint vibration signal reconstruction sequence to obtain a voiceprint vibration signal reverse-construction sequence, and calculating the reverse complexity of the voiceprint vibration signal based on the voiceprint vibration signal reverse-construction sequence; Calculating an average complexity of the voiceprint vibration signal according to the complexity of the voiceprint vibration signal and the reverse complexity of the voiceprint vibration signal; Calculate the ultimate complexity of the voiceprint vibration signal using the following formula: Where b(k) is the ultimate complexity of the voiceprint vibration signal, and n is the number of elements in the reconstructed sequence of the voiceprint vibration signal; Normalizing the average complexity of the soundprint vibration signal according to the limit complexity of the soundprint vibration signal, calculating the relative complexity of the soundprint vibration signal, and determining the mechanical instability fault of the transformer based on the relative complexity of the soundprint vibration signal; The formula for calculating the relative complexity of the voiceprint vibration signal is as follows: Among them, c(k) is the relative complexity of the voiceprint vibration signal, is the average complexity of the voiceprint vibration signal, and b(k) is the maximum complexity of the voiceprint vibration signal.

2. A transformer mechanical instability fault diagnosis method as claimed in claim 1, characterized in that: The collecting the voiceprint vibration signal of the transformer and preprocessing the voiceprint vibration signal include: Multiple vibration acceleration sensors arranged in a matrix are used to collect the transformer's soundprint vibration signals; Deleting the missing values ​​in the voiceprint vibration signal of the transformer; Identifying and deleting isolated points in the voiceprint vibration signal of the transformer that do not conform to data characteristics; The voiceprint vibration signal of the transformer is smoothed, and the smoothing formula is as follows: Wherein, h is the sampling window number of the vibration acceleration sensor, m is the number of the voiceprint vibration signals in the unit window, that is, the window time is mTs, a(h) is the amplitude value of the voiceprint vibration signal after sliding average in the hth window, Ts is the sampling period of the vibration acceleration sensor, and the sliding average window time is h*Ts, a r is the amplitude of the voiceprint vibration signal at the rth sampling point in the sampling period, r=1, 2, 3, ..., m.

3. A transformer mechanical instability fault diagnosis method as claimed in claim 2, characterized in that: The performing frequency decomposition on the pre-processed voiceprint vibration signal comprises: The pre-processed voiceprint vibration signal is subjected to discrete Fourier decomposition, and the decomposition formula is as follows: Where i is a unit complex number, A t (k) is the amplitude value of the soundprint vibration signal at frequency k after Fourier transform, and N is the total number of sensor sliding average windows in the Fourier analysis window, that is, the Fourier window time is N*h*Ts, which is N times the sliding average window time.

4. A transformer mechanical instability fault diagnosis method as claimed in claim 1, characterized in that: The determining of the transformer mechanical instability fault based on the relative complexity of the soundprint vibration signal includes: When the relative complexity of the voiceprint vibration signal is less than or equal to a first preset complexity threshold, the transformer is mechanically stable; When the relative complexity of the voiceprint vibration signal is greater than or equal to a second preset complexity threshold, the transformer is mechanically unstable; When the relative complexity of the voiceprint vibration signal is greater than a first preset complexity and less than a threshold and less than a second preset complexity threshold, the mechanical stability of the transformer has a tendency to deteriorate.

5. A transformer mechanical instability fault diagnosis device, characterized in that: include: A signal acquisition module, used to collect the voiceprint vibration signal of the transformer and pre-process the voiceprint vibration signal; A signal decomposition module, used for performing frequency decomposition on the preprocessed voiceprint vibration signal, storing the decomposed voiceprint vibration signal into a voiceprint vibration signal sequence matrix, and calculating the mean of the voiceprint vibration signal sequence matrix; A sequence reconstruction module is used to compare each value of the voiceprint vibration signal sequence matrix with the mean value of the voiceprint vibration signal sequence matrix, reconstruct the voiceprint vibration signal sequence matrix according to the comparison result, obtain a voiceprint vibration signal reconstruction sequence, and establish a binary pointer sequence; loop through the voiceprint vibration signal reconstruction sequence, and when a sequence corresponding to the pointer sequence exists in the voiceprint vibration signal reconstruction sequence, update the pointer sequence; when a sequence corresponding to the pointer sequence does not exist in the voiceprint vibration signal reconstruction sequence, do not calculate the complexity of the voiceprint vibration signal; when the updated pointer sequence is greater than the maximum value of the pointer sequence, output the complexity of the voiceprint vibration signal; A sequence conversion module, configured to reverse the sequence of the voiceprint vibration signal reconstruction to obtain a reverse sequence of the voiceprint vibration signal reconstruction, and calculate the reverse complexity of the voiceprint vibration signal based on the reverse sequence of the voiceprint vibration signal reconstruction; A complexity calculation module, used to calculate the average complexity of the voiceprint vibration signal according to the complexity of the voiceprint vibration signal and the reverse complexity of the voiceprint vibration signal; The mechanical instability judgment module is used to calculate the ultimate complexity of the soundprint vibration signal. The calculation formula is as follows: Where b(k) is the ultimate complexity of the voiceprint vibration signal, and n is the number of elements in the reconstructed sequence of the voiceprint vibration signal; The mechanical instability judgment module is further used to normalize the average complexity of the soundprint vibration signal according to the limit complexity of the soundprint vibration signal, calculate the relative complexity of the soundprint vibration signal, and determine the mechanical instability fault of the transformer based on the relative complexity of the soundprint vibration signal; The formula for calculating the relative complexity of the voiceprint vibration signal is as follows: Among them, c(k) is the relative complexity of the voiceprint vibration signal, is the average complexity of the voiceprint vibration signal, and b(k) is the maximum complexity of the voiceprint vibration signal.

6. An electronic device, wherein: The electronic device includes: A processor and a memory storing computer executable instructions, which when executed cause the processor to perform the method according to any one of claims 1 to 4.

7. A computer-readable storage medium, wherein: The computer-readable storage medium stores one or more instructions, which, when executed by a processor, implement the method of any one of claims 1 to 4.

Images