Method for monitoring and evaluating mechanical stability of large transformer

Abstract

The invention discloses a large-scale transformer mechanical stability monitoring and evaluation method, and relates to the technical field of large-scale transformer mechanical stability monitoring, and the method comprises the steps: obtaining transformer distributed measurement point voiceprint vibration signals through employing an Internet of Things intelligent sensor; multi-channel voiceprint vibration signal conditioning and synchronous acquisition are carried out; calculating the fundamental frequency amplitude, the fundamental frequency proportion, the 50Hz amplitude, the 50Hz proportion, the dominant frequency amplitude, the dominant frequency, the dominant frequency proportion, the even component energy ratio, the odd component energy ratio, the vibration entropy and the vibration relevance of the voiceprint vibration signal of each channel; and realizing transformer mechanical stability evaluation and early warning based on the neural network output value, the vibration entropy and the vibration relevance logic or operation. According to the method, the mechanical stability of the transformer can be monitored and evaluated through voiceprint vibration detection.

Description

Technical Field

[0001] The present invention relates to the technical field of large transformer mechanical stability monitoring, and in particular to a large transformer mechanical stability monitoring and evaluation method. Background Art

[0002] Transformers play an important role in voltage conversion and electric energy distribution in power systems. With the continuous expansion of the scale of power grids and the gradual increase in voltage levels, their safe and stable operation is of great significance to ensuring power supply reliability. As important components of transformers, windings and iron cores have failure rates of about 36% and 4% of the overall transformer failures, respectively. Winding failures mainly include short circuits or grounding and short circuits between winding layers, turns, phases, high and low voltage windings; mechanical damage to windings caused by system short circuits or impact currents; dampness of windings; aging of insulation, etc. All of the above failures will cause winding deformation. Typical core failures include loose pressure irons, poor core grounding, and loose or damaged clamps. Various types of faults pose a huge threat to the transformer's ability to resist short-circuit current impacts and safe and stable operation, affecting the safe and stable operation of transformers and the entire power grid. In severe cases, they will lead to large-scale power outages, electrical fires and other accidents. Therefore, the implementation of mechanical stability monitoring and fault diagnosis is of great practical significance to ensure the safe and stable operation of transformers and the entire power grid. Summary of the invention

[0003] In view of the above existing problems, the present invention is proposed.

[0004] Therefore, the present invention provides a method for monitoring and evaluating the mechanical stability of a large transformer. When the transformer is in operation, the electromotive force generated when the current passes through the winding causes the winding to vibrate, and the magnetostriction of the silicon steel sheet and the magnetic leakage between the joints of the silicon steel sheet and the laminations cause the core to vibrate. Among them, the fundamental frequency of the winding vibration is proportional to the square of the current frequency, and the fundamental frequency of the core vibration is proportional to the square of the voltage, that is, the fundamental frequency of the transformer body vibration signal is 100Hz. When the mechanical stability of the transformer is abnormal, its vibration signal and vibration signal spectrum will also change. Therefore, the mechanical stability of the transformer can be monitored and evaluated through voiceprint vibration detection.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions, a large transformer mechanical stability monitoring and evaluation method, comprising:

[0006] Use IoT smart sensors to obtain the voiceprint and vibration signals of distributed measuring points of the transformer; condition and synchronously collect multi-channel voiceprint and vibration signals; calculate the characteristic correlation of the voiceprint and vibration signals of each channel; and realize the mechanical stability evaluation and early warning of the transformer based on the neural network output value, vibration entropy and vibration correlation logic or operation.

[0007] As a preferred solution of the large transformer mechanical stability monitoring and evaluation method described in the present invention, the multi-channel soundprint vibration signal conditioning and synchronous acquisition include: the multi-channel soundprint vibration signal acquisition device includes a signal conditioning circuit, an A / D sampling circuit, a data cache module, an MCU control system, a GPS timing module, a communication module and a backup module.

[0008] As a preferred scheme of the large transformer mechanical stability monitoring and evaluation method described in the present invention, wherein: the calculation of the characteristic correlation of the soundprint vibration signals of each channel includes calculating the characteristic parameters of the soundprint vibration signals of each channel for mechanical stability evaluation of the large transformer, and the characteristic parameters include fundamental frequency amplitude, fundamental frequency proportion, 50Hz amplitude, 50Hz proportion, main frequency amplitude, main frequency, main frequency proportion, even component energy ratio, odd component energy ratio, vibration entropy and vibration correlation.

[0009] As a preferred solution of the large transformer mechanical stability monitoring and evaluation method described in the present invention, wherein: the calculation of the characteristic correlation of the soundprint vibration signal of each channel includes the definition and calculation process of each characteristic parameter as follows:

[0010] Fundamental frequency amplitude: the amplitude corresponding to the 100Hz frequency in the vibration spectrum;

[0011] Fundamental frequency ratio:

[0012]

[0013] Where P f＝100 is the fundamental frequency proportion; f is the frequency; S f is the amplitude corresponding to the frequency f in the vibration spectrum, f = 100, 200, ..., 1200;

[0014] 50Hz amplitude: the amplitude corresponding to the 50Hz frequency in the vibration spectrum;

[0015] 50Hz specific gravity:

[0016]

[0017] Where P f＝50 is the fundamental frequency proportion; f is the frequency; S f is the amplitude corresponding to the frequency f in the vibration spectrum, f=100, 200,…, 1200.

[0018] As a preferred solution of the large transformer mechanical stability monitoring and evaluation method described in the present invention, wherein: the calculation of the characteristic correlation of the soundprint vibration signal of each channel includes:

[0019] Main frequency amplitude: the amplitude corresponding to the frequency with the highest amplitude in the vibration spectrum;

[0020] Main frequency: the frequency with the highest amplitude in the vibration spectrum;

[0021] Main frequency ratio:

[0022]

[0023] Where P fm is the fundamental frequency proportion; f is the frequency; S f is the amplitude corresponding to the frequency f in the vibration spectrum, f = 100, 200, ..., 1200;

[0024] Even-order component energy ratio: the ratio of 100Hz and its integer multiple harmonic energy to the energy of the characteristic frequency point;

[0025]

[0026] In the formula, E even is the energy ratio of even-order components; S f is the amplitude corresponding to the frequency f in the vibration spectrum, f = 50, 100,…, 1150, 1200.

[0027] As a preferred solution of the large transformer mechanical stability monitoring and evaluation method described in the present invention, wherein: the calculation of the characteristic correlation of the soundprint vibration signal of each channel includes:

[0028] Odd component energy ratio: the ratio of 50Hz and its odd multiple harmonic energy to the energy of characteristic frequency point;

[0029]

[0030] In the formula, E odd is the energy ratio of odd components; S f is the amplitude corresponding to the frequency f in the vibration spectrum, f = 50, 100, ..., 1150, 1200;

[0031] Vibration entropy: a parameter that characterizes the complexity of frequency components in a spectrum. The lower the value, the more concentrated the energy in the spectrum is in certain characteristic frequencies, and the higher the value, the more dispersed the energy in the spectrum is.

[0032]

[0033]

[0034] Where P f is the frequency specific gravity; H is the vibration entropy; f is the frequency; S f is the amplitude corresponding to the frequency f in the vibration spectrum, f = 100, 200, ..., 1200;

[0035] Vibration correlation: Indicates the degree of vibration correlation between multiple measuring points.

[0036] As a preferred solution of the large transformer mechanical stability monitoring and evaluation method described in the present invention, wherein: the calculation of the characteristic correlation of the soundprint vibration signal of each channel also includes:

[0037] The vibration variation matrix w is constructed as follows:

[0038]

[0039] In the formula, Δw ij is the vibration variation, n is the number of samples, and m is the number of sensors;

[0040] Perform standardization to obtain the standard matrix W and calculate the mean by column and standard deviation S j ;

[0041]

[0042] Get the standardized element ΔW and matrix W:

[0043]

[0044] Step 3: Calculate the standard matrix covariance matrix R:

[0045]

[0046] In the formula, R ij is the element in the standard matrix covariance matrix R;

[0047] Calculate the covariance matrix eigenvalue Λ:

[0048] Λ=diag{λ1,λ2,λ3,····,λ m}

[0049] The eigenvalues ​​are arranged in descending order as λ1≥λ2≥λ3,····,≥λ m ;

[0050] Calculate the vibration correlation RR:

[0051]

[0052] As a preferred solution of the large transformer mechanical stability monitoring and evaluation method described in the present invention, the transformer mechanical stability evaluation and early warning includes using 8-channel vibration signal fundamental frequency amplitude, fundamental frequency ratio, 50Hz amplitude, 50Hz ratio, main frequency amplitude, main frequency, main frequency ratio, even component energy ratio, odd component energy ratio, a total of 72 characteristic parameters, as the input layer of the trained neural network model, the output layer of the neural network is R1, R1=0 is recorded as the normal mechanical stability of the transformer, and R1=1 is recorded as the abnormal mechanical stability of the transformer;

[0053] Normally, the vibration entropy of a transformer is in the range of 0-3. If the vibration entropy exceeds the critical value of 3, it is considered that the transformer may have a hidden danger of mechanical stability failure. For multiple vibration measurement points, when the vibration entropy of 2 or more measurement points exceeds the critical value of 3, the transformer is judged to have abnormal mechanical stability. The result of the transformer mechanical stability judgment based on vibration entropy is recorded as R1, R2=0 is recorded as normal transformer mechanical stability, and R2=1 is recorded as abnormal transformer mechanical stability.

[0054] The vibration correlation indicates the degree of vibration correlation between each measuring point, and its range is between 0 and 1; the transformer mechanical stability judgment result based on the vibration correlation is recorded as R3. When the vibration correlation of multiple measuring points is less than 0.5, R3=0 is recorded as normal transformer mechanical stability; when the vibration correlation of multiple measuring points is greater than or equal to 0.5, R3=1 is recorded as abnormal transformer mechanical stability.

[0055] Based on the analysis, the monitoring and evaluation method of mechanical stability of large transformers is as follows:

[0056] R=R1∧R2∧R3

[0057] That is, the transformer mechanical stability evaluation and early warning are realized based on the neural network output value, vibration entropy and vibration correlation logic or operation. When R=0, the transformer mechanical stability is judged to be normal, and when R=1, the transformer mechanical stability is judged to be abnormal.

[0058] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and is characterized in that when the processor executes the computer program, steps of a method for monitoring and evaluating the mechanical stability of a large transformer are implemented.

[0059] A computer-readable storage medium stores a computer program, wherein the computer program, when executed by a processor, implements the steps of a method for monitoring and evaluating the mechanical stability of a large transformer.

[0060] Beneficial effects of the present invention: The method of the present invention is based on a feedback loop model, and obtains a nonlinear convolution model of up and down waves of seabed node data. The model shows that the underground primary reflection Green's function can be extracted by deconvolution of the up and down waves. The method assumes that the multiple wave prediction relationships of plane wave components in different directions in the seabed node data are independent of each other, so deconvolution can be performed frequency by frequency and plane wave direction by plane wave in the plane wave domain, with high computational efficiency, and only local plane wave decomposition of the common detection point gathers of the seabed node data is required, thus avoiding the problem of sparse spatial sampling of the common shot gathers of the seabed node data. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0062] Figure 1 A schematic flow chart of a method for monitoring and evaluating the mechanical stability of a large transformer provided by an embodiment of the present invention.

[0063] Figure 2 A schematic diagram of the structure of a data acquisition device for a large transformer mechanical stability monitoring and evaluation method provided by an embodiment of the present invention.

[0064] Figure 3 A schematic diagram of a transformer soundprint vibration signal spectrum in a normal state according to a method for monitoring and evaluating the mechanical stability of a large transformer provided by an embodiment of the present invention.

[0065] Figure 4 A schematic diagram of a transformer soundprint vibration signal spectrum in an abnormal state according to a method for monitoring and evaluating the mechanical stability of a large transformer provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0066] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0067] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0068] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0069] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0070] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the 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 direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0071] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or 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 according to specific circumstances.

[0072] Example 1, reference Figure 1-Figure 4 , which is the first embodiment of the present invention, provides a large transformer mechanical stability monitoring and evaluation method, comprising:

[0073] S1: Use IoT smart sensors to obtain transformer distributed measurement point soundprint vibration signals.

[0074] S2: Multi-channel voiceprint vibration signal conditioning and synchronous acquisition.

[0075] S3: Calculate the fundamental frequency amplitude, fundamental frequency proportion, 50Hz amplitude, 50Hz proportion, main frequency amplitude, main frequency, main frequency proportion, even component energy ratio, odd component energy ratio, vibration entropy, and vibration correlation of the voiceprint vibration signal of each channel.

[0076] S4: Transformer mechanical stability assessment and early warning are realized based on the neural network output value, vibration entropy and vibration correlation logic OR operation.

[0077] In step S1, the IoT smart sensor is composed of a piezoelectric acceleration sensor module, a wireless transmission module and a battery module, and is installed on the surface of the transformer tank by magnetic attraction. The installation positions include the bottom of the clamp on the core column of the high-voltage side tank wall, the tank surface corresponding to the middle of the side yoke of the left tank wall, the tank surface corresponding to the middle of the side yoke of the right tank wall and the center point of the tank top. The IoT smart sensor vibration signal frequency measurement range is 5Hz~3000Hz, the vibration acceleration measurement range is 0.1g~5g, and the vibration sensor sensitivity is 100mV / g.

[0078] Figure 2 This is a structural diagram of a multi-channel voiceprint vibration signal acquisition device of the present invention.

[0079] In step S2, the multi-channel voiceprint vibration signal acquisition device includes a signal conditioning circuit, an A / D sampling circuit, a data cache module, an MCU control system, a GPS timing module, a communication module and a backup module. Among them, the signal conditioning module has sensor power supply and signal filtering functions. The signal sampling rate is 100kS / s, the signal sampling accuracy is 16bit, and 8-channel vibration signal synchronous processing and acquisition can be realized.

[0080] Figure 3 This is a spectrum diagram of the transformer soundprint vibration signal in a normal state of the present invention.

[0081] Figure 4 This is a spectrum diagram of the transformer voiceprint vibration signal in an abnormal state according to the present invention.

[0082] In step S3, the characteristic parameters of the soundprint vibration signal of each channel are calculated for the mechanical stability assessment of large transformers. The characteristic parameters include fundamental frequency amplitude, fundamental frequency ratio, 50Hz amplitude, 50Hz ratio, main frequency amplitude, main frequency, main frequency ratio, even component energy ratio, odd component energy ratio, vibration entropy and vibration correlation. The definition and calculation process of each characteristic parameter are as follows:

[0083] (a) Fundamental frequency amplitude: the amplitude corresponding to a frequency of 100 Hz in the vibration spectrum.

[0084] (b) Fundamental frequency ratio:

[0085]

[0086] Where P f＝100 is the fundamental frequency proportion; f is the frequency; S f is the amplitude corresponding to the frequency f in the vibration spectrum, f=100, 200,…, 1200.

[0087] (c) 50 Hz amplitude: The amplitude corresponding to the 50 Hz frequency in the vibration spectrum.

[0088] (d) 50Hz specific gravity:

[0089]

[0090] Where P f＝50 is the fundamental frequency proportion; f is the frequency; S f is the amplitude corresponding to the frequency f in the vibration spectrum, f=100, 200,…, 1200.

[0091] (e) Main frequency amplitude: the amplitude corresponding to the frequency with the highest amplitude in the vibration spectrum.

[0092] (f) Main frequency: The frequency with the highest amplitude in the vibration spectrum.

[0093] (g) Main frequency ratio:

[0094]

[0095] Where P fm is the fundamental frequency proportion; f is the frequency; S f is the amplitude corresponding to the frequency f in the vibration spectrum, f=100, 200,…, 1200.

[0096] (h) Even-order component energy ratio: the ratio of 100 Hz and its integer multiple harmonic energy to the energy of the characteristic frequency point.

[0097]

[0098] In the formula, E even is the energy ratio of even-order components; S f is the amplitude corresponding to the frequency f in the vibration spectrum, f = 50, 100,…, 1150, 1200.

[0099] (i) Odd-order component energy ratio: the ratio of 50 Hz and its odd-order harmonic energy to the energy of the characteristic frequency point.

[0100]

[0101] In the formula, E odd is the energy ratio of odd components; S f is the amplitude corresponding to the frequency f in the vibration spectrum, f = 50, 100,…, 1150, 1200.

[0102] (j) Vibration entropy: A parameter that characterizes the complexity of frequency components in a spectrum. The lower the value, the more concentrated the energy in the spectrum is in certain characteristic frequencies, and the higher the value, the more dispersed the energy in the spectrum is.

[0103]

[0104] Where P f is the frequency specific gravity; H is the vibration entropy; f is the frequency; S f is the amplitude corresponding to the frequency f in the vibration spectrum, f=100, 200,…, 1200.

[0105] (k) Vibration correlation: indicates the degree of vibration correlation between multiple measuring points.

[0106] Step 1: Construct the vibration variation matrix w

[0107]

[0108] In the formula, Δw ij is the vibration variation, n is the number of samples, and m is the number of sensors.

[0109] Step 2: Standardization process to obtain the standard matrix W. Calculate the mean by column and standard deviation S j

[0110]

[0111] Get the standardized element ΔW and matrix W

[0112]

[0113] Step 3: Calculate the standard matrix covariance matrix R

[0114]

[0115] In the formula, R ij is the element in the standard matrix covariance matrix R.

[0116] Step 4: Calculate the covariance matrix eigenvalue Λ

[0117] Λ=diag{λ1, λ2, λ3,····,λ m} (7.8)

[0118] The eigenvalues ​​are arranged in descending order as λ1≥λ2≥λ3, ..., ≥λ m .

[0119] Step 5: Calculate the vibration correlation RR

[0120]

[0121] In step S4, a total of 72 characteristic parameters including fundamental frequency amplitude, fundamental frequency ratio, 50 Hz amplitude, 50 Hz ratio, main frequency amplitude, main frequency, main frequency ratio, even component energy ratio and odd component energy ratio of 8-channel vibration signals are used as the input layer of the trained neural network model. The output layer of the neural network is R1. R1=0 indicates that the mechanical stability of the transformer is normal, and R1=1 indicates that the mechanical stability of the transformer is abnormal.

[0122] The vibration entropy of a normal transformer is in the range of 0-3. If the vibration entropy exceeds the critical value of 3, it is considered that the transformer may have a hidden danger of mechanical stability failure. For multiple vibration measurement points, when the vibration entropy of 2 or more measurement points exceeds the critical value of 3, the transformer mechanical stability is judged to be abnormal. The result of the transformer mechanical stability judgment based on vibration entropy is recorded as R1, R2=0 is recorded as normal transformer mechanical stability, and R2=1 is recorded as abnormal transformer mechanical stability.

[0123] The vibration correlation indicates the degree of vibration correlation between each measuring point, and its range is between 0 and 1. The result of the transformer mechanical stability determination based on vibration correlation is recorded as R3. When the vibration correlation of multiple measuring points is less than 0.5, R3=0 is recorded as normal transformer mechanical stability. When the vibration correlation of multiple measuring points is greater than or equal to 0.5, R3=1 is recorded as abnormal transformer mechanical stability.

[0124] Based on the above analysis, the monitoring and evaluation method of mechanical stability of large transformers is as follows:

[0125] R=R1∧R2∧R3

[0126] That is, the transformer mechanical stability evaluation and early warning are realized based on the neural network output value, vibration entropy and vibration correlation logic or operation. When R=0, the transformer mechanical stability is judged to be normal, and when R=1, the transformer mechanical stability is judged to be abnormal.

[0127] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

[0128] Example 2

[0129] The second embodiment of the present invention is different from the previous embodiment in that:

[0130] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0131] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0132] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0133] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0134] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0135] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A method for monitoring and evaluating the mechanical stability of a large transformer, characterized in that: include, Use IoT smart sensors to obtain the soundprint vibration signals of transformer distributed measurement points; Multi-channel voiceprint vibration signal conditioning and synchronous acquisition; Calculate the characteristic correlation of the voiceprint vibration signal of each channel; Transformer mechanical stability assessment and early warning are realized based on neural network output value, vibration entropy and vibration correlation logic OR operation.

2. A large transformer mechanical stability monitoring and evaluation method as claimed in claim 1, characterized in that: The multi-channel voiceprint vibration signal conditioning and synchronous collection includes: The multi-channel voiceprint vibration signal acquisition device includes a signal conditioning circuit, an A / D sampling circuit, a data cache module, an MCU control system, a GPS timing module, a communication module and a backup module.

3. A large transformer mechanical stability monitoring and evaluation method as claimed in claim 2, characterized in that: The calculation of the characteristic correlation of the soundprint vibration signals of each channel includes calculating the characteristic parameters of the soundprint vibration signals of each channel for mechanical stability assessment of large transformers, wherein the characteristic parameters include fundamental frequency amplitude, fundamental frequency proportion, 50 Hz amplitude, 50 Hz proportion, main frequency amplitude, main frequency, main frequency proportion, even component energy ratio, odd component energy ratio, vibration entropy and vibration correlation.

4. A large transformer mechanical stability monitoring and evaluation method as claimed in claim 3, characterized in that: The calculation of the characteristic correlation of the voiceprint vibration signal of each channel includes the definition and calculation process of each characteristic parameter as follows: Fundamental frequency amplitude: the amplitude corresponding to the 100Hz frequency in the vibration spectrum; Fundamental frequency ratio: Where P f＝100 is the fundamental frequency proportion; f is the frequency; S f is the amplitude corresponding to the frequency f in the vibration spectrum, f = 100, 200, ..., 1200; 50Hz amplitude: the amplitude corresponding to the 50Hz frequency in the vibration spectrum; 50Hz specific gravity: Where P f＝50 is the fundamental frequency proportion; f is the frequency; S f is the amplitude corresponding to the frequency f in the vibration spectrum, f =100, 200,…, 1200.

5. A large transformer mechanical stability monitoring and evaluation method as claimed in claim 4, characterized in that: The calculation of the characteristic correlation of the voiceprint vibration signal of each channel includes: Main frequency amplitude: the amplitude corresponding to the frequency with the highest amplitude in the vibration spectrum; Main frequency: the frequency with the highest amplitude in the vibration spectrum; Main frequency ratio: Where P fm is the fundamental frequency proportion; f is the frequency; S f is the frequency in the vibration spectrum f The amplitude corresponding to the location, f =100, 200, ..., 1200; Even-order component energy ratio: the ratio of 100Hz and its integer multiple harmonic energy to the energy of the characteristic frequency point; In the formula, E even is the energy ratio of even-order components; S f is the frequency in the vibration spectrum f The amplitude corresponding to the location, f =50, 100,…, 1150, 1200.

6. A large transformer mechanical stability monitoring and evaluation method as claimed in claim 5, characterized in that: The calculation of the characteristic correlation of the voiceprint vibration signal of each channel includes: Odd component energy ratio: the ratio of 50Hz and its odd multiple harmonic energy to the energy of characteristic frequency point; In the formula, E odd is the energy ratio of odd components; S f is the frequency in the vibration spectrum f The amplitude corresponding to the location, f =50, 100, ..., 1150, 1200; Vibration entropy: a parameter that characterizes the complexity of frequency components in a spectrum. The lower the value, the more concentrated the energy in the spectrum is in certain characteristic frequencies, and the higher the value, the more dispersed the energy in the spectrum is. Where P f is the frequency specific gravity; H is the vibration entropy; f is the frequency; S f is the frequency in the vibration spectrum f The amplitude corresponding to the location, f =100, 200, ..., 1200; Vibration correlation: Indicates the degree of vibration correlation between multiple measuring points.

7. A large transformer mechanical stability monitoring and evaluation method as claimed in claim 6, characterized in that: The calculating of the characteristic correlation of the voiceprint vibration signals of each channel also includes: The vibration variation matrix w is constructed as follows: In the formula, Δw ij is the vibration variation, n is the number of samples, and m is the number of sensors; Perform standardization to obtain the standard matrix W and calculate the mean by column and standard deviation S j ; Get the standardized element ΔW and matrix W: Step 3: Calculate the standard matrix covariance matrix R: In the formula, R ij is the element in the standard matrix covariance matrix R; Calculate the covariance matrix eigenvalue Λ: Λ=diag{λ1,λ2,λ3,……,λ m } The eigenvalues ​​are arranged in descending order as λ1≥λ2≥λ3, ..., ≥λ m ; Calculate the vibration correlation RR:

8. A large transformer mechanical stability monitoring and evaluation method as claimed in claim 7, characterized in that: The transformer mechanical stability assessment and early warning includes using 8-channel vibration signal fundamental frequency amplitude, fundamental frequency ratio, 50Hz amplitude, 50Hz ratio, main frequency amplitude, main frequency, main frequency ratio, even component energy ratio, odd component energy ratio, a total of 72 characteristic parameters as the input layer of the trained neural network model, the neural network output layer is R1, R1=0 is recorded as the normal mechanical stability of the transformer, and R1=1 is recorded as the abnormal mechanical stability of the transformer; Normally, the vibration entropy of a transformer is in the range of 0-3. If the vibration entropy exceeds the critical value of 3, it is considered that the transformer may have a hidden danger of mechanical stability failure. For multiple vibration measurement points, when the vibration entropy of 2 or more measurement points exceeds the critical value of 3, the transformer is judged to have abnormal mechanical stability. The result of the transformer mechanical stability judgment based on vibration entropy is recorded as R1, R2=0 is recorded as normal transformer mechanical stability, and R2=1 is recorded as abnormal transformer mechanical stability. The vibration correlation indicates the degree of vibration correlation between each measuring point, and its range is between 0 and 1; the transformer mechanical stability judgment result based on the vibration correlation is recorded as R3. When the vibration correlation of multiple measuring points is less than 0.5, R3=0 is recorded as normal transformer mechanical stability; when the vibration correlation of multiple measuring points is greater than or equal to 0.5, R3=1 is recorded as abnormal transformer mechanical stability. Based on the analysis, the monitoring and evaluation method of mechanical stability of large transformers is as follows: R=R1∧R2∧R3 That is, the transformer mechanical stability evaluation and early warning are realized based on the neural network output value, vibration entropy and vibration correlation logic or operation. When R=0, the transformer mechanical stability is judged to be normal, and when R=1, the transformer mechanical stability is judged to be abnormal.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images