Method for monitoring and evaluating mechanical stability of large transformer

Abstract

The present invention relates to the technical field of mechanical stability monitoring of large transformers. Disclosed is a method for monitoring and evaluating the mechanical stability of a large transformer, the method comprising: using Internet-of-Things intelligent sensors to acquire acoustic signature and vibration signals from distributed measurement points of a transformer; conditioning and synchronously collecting multi-channel acoustic signature and vibration signals; calculating the fundamental frequency amplitude, fundamental frequency ratio, 50 Hz amplitude, 50 Hz ratio, dominant frequency amplitude, dominant frequency, dominant frequency ratio, even-order component energy ratio, odd-order component energy ratio, vibration entropy and vibration correlation of the acoustic signature and vibration signal of each channel; and on the basis of a logical OR operation of a neural network output value, the vibration entropy and the vibration correlation, implementing the evaluation and early warning of the mechanical stability of the transformer. The method can implement the monitoring and evaluation of the mechanical stability of the transformer by means of acoustic signature and vibration detection.

Description

A large transformer mechanical stability monitoring and evaluation method TECHNICAL FIELD

[0001] The present application relates to the technical field of large transformer mechanical stability monitoring, and particularly relates to a large transformer mechanical stability monitoring and evaluation method. BACKGROUND

[0002] The transformer plays an important role in voltage transformation and power distribution in the power system, and with the continuous expansion of the power grid scale and the gradual improvement of the voltage level, its safe and stable operation is of great significance to ensure the reliability of power supply. The winding and the core are important components of the transformer, and their failure rates account for about 36% and 4% of the overall transformer failure, respectively. The winding faults mainly include interlayer, interturn, interphase, high and low voltage winding short circuit or grounding, open circuit fault; mechanical damage of the winding caused by system short circuit or impact current; winding damp; insulation aging, etc., all of which will cause the winding deformation. Typical core faults include loose press iron, poor core grounding, loose or damaged clamping piece. Various faults pose a great threat to the short-circuit current impact resistance and safe and stable operation of the transformer, affect the safe and stable operation of the transformer and the entire power grid, and in severe cases, can cause large-scale power outages, electrical fires and other accidents. Therefore, implementing mechanical stability monitoring and fault diagnosis is of great practical significance to ensure the safe and stable operation of the transformer and the entire power grid. SUMMARY

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

[0004] Therefore, the present application provides a large transformer mechanical stability monitoring and evaluation method. When the transformer is running, the electromagnetic force generated by the current passing through the winding causes the winding vibration, the magnetic strain of the silicon steel sheet and the leakage magnetic field between the silicon steel sheet joint and the laminated sheet cause the core vibration. Among them, the winding vibration fundamental frequency is proportional to the square of the current frequency, and the core vibration fundamental frequency is proportional to the square of the voltage, that is, the transformer body vibration signal fundamental frequency is 100Hz. When the mechanical stability of the transformer is abnormal, the vibration signal and the vibration signal spectrum will also change, so the transformer mechanical stability monitoring and evaluation can be realized through voiceprint vibration detection.

[0005] To solve the above technical problems, the present application provides the following technical scheme, a large transformer mechanical stability monitoring and evaluation method, comprising:

[0006] Using the Internet of Things intelligent sensor to obtain the transformer distributed measurement point voiceprint vibration signal; multi-channel voiceprint vibration signal conditioning and synchronous acquisition; calculating the characteristic correlation of each channel voiceprint vibration signal; realizing transformer mechanical stability evaluation and early warning based on neural network output value, vibration entropy and vibration correlation logical or operation.

[0007] As a preferred scheme of the large transformer mechanical stability monitoring and evaluation method, the multi-channel soundprint vibration signal conditioning and synchronous acquisition comprises a signal conditioning circuit, an A / D sampling circuit, a data buffer 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, the calculation of the characteristic correlation of each channel soundprint vibration signal comprises calculation of characteristic parameters of each channel soundprint vibration signal, which are used for large transformer mechanical stability evaluation, and the characteristic parameters comprise a fundamental frequency amplitude, a fundamental frequency proportion, a 50Hz amplitude, a 50Hz proportion, a main frequency amplitude, a main frequency, a main frequency proportion, an even component energy ratio, an odd component energy ratio, a vibration entropy and a vibration correlation.

[0009] As a preferred scheme of the large transformer mechanical stability monitoring and evaluation method, the calculation of the characteristic correlation of each channel soundprint vibration signal comprises definition and calculation of each characteristic parameter as follows:

[0010] The fundamental frequency amplitude is an amplitude corresponding to a 100Hz frequency in a vibration spectrum.

[0011] The fundamental frequency proportion is P100 = S100 / Smax.

[0012] P100 = S100 / Smax. f＝100 P100 = S100 / Smax. f Sf is an amplitude corresponding to a frequency f in the vibration spectrum, f = 100, 200, …, 1200.

[0013] The 50Hz amplitude is an amplitude corresponding to a 50Hz frequency in the vibration spectrum.

[0014] The 50Hz proportion is P50 = S50 / Smax.

[0015] P50 = S50 / Smax. f＝50 P50 = S50 / Smax. f Sf is an amplitude corresponding to a frequency f in the vibration spectrum, f = 100, 200, …, 1200.

[0016] As a preferred scheme of the large transformer mechanical stability monitoring and evaluation method, the calculation of the characteristic correlation of each channel soundprint vibration signal comprises,

[0017] The main frequency amplitude is an amplitude corresponding to a frequency with the highest amplitude in the vibration spectrum.

[0018] The main frequency is a frequency with the highest amplitude in the vibration spectrum.

[0019] Main frequency proportion:

[0020] In the formula, P fm is the main frequency proportion; f is the frequency; S f is the amplitude corresponding to the frequency f in the vibration spectrum, f = 100, 200,..., 1200;

[0021] Even component energy ratio: the energy ratio of 100Hz and its integral multiple harmonic energy to the characteristic frequency point energy;

[0022] In the formula, E even is the even component energy ratio; S f is the amplitude corresponding to the frequency f in the vibration spectrum, f = 50, 100,..., 1150, 1200.

[0023] As a preferred scheme of the large transformer mechanical stability monitoring and evaluation method, wherein the calculation of the feature correlation of the soundprint vibration signals of each channel comprises,

[0024] Odd component energy ratio: the energy ratio of 50Hz and its odd multiple harmonic energy to the characteristic frequency point energy;

[0025] In the formula, E odd is the odd component energy ratio; S f is the amplitude corresponding to the frequency f in the vibration spectrum, f = 50, 100,..., 1150, 1200.

[0026] Vibration entropy: a parameter for characterizing the complexity of the frequency components in the spectrum, the lower the value, the more concentrated the energy in the spectrum is at certain characteristic frequencies, and the higher the value, the more dispersed the energy in the spectrum is;

[0027] In the formula, P f is the frequency proportion; 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;

[0028] Vibration correlation: representing the vibration correlation degree between multiple measuring points.

[0029] As a preferred scheme of the large transformer mechanical stability monitoring and evaluation method, wherein the calculation of the feature correlation of the soundprint vibration signals of each channel further comprises,

[0030] The vibration change amount matrix w is constructed as follows:

[0031] In the formula, Δw ijis the vibration variation, n is the number of samples, and m is the number of sensors;

[0032] The standardization processing is performed to obtain a standard matrix W, and the mean value is calculated according to the column and the standard deviation S j ;

[0033] The standardized element AW and the matrix W are obtained:

[0034] Step 3: Calculate the standard matrix covariance matrix R:

[0035] In the formula, R ij is an element in the standard matrix covariance matrix R;

[0036] Calculate the eigenvalue Λ of the covariance matrix: Λ = diag{λ1, λ2, λ3,...., λ m}

[0037] The eigenvalues are arranged in descending order as λ1≥λ2≥λ3,...., ≥λ m ;

[0038] Calculate the vibration correlation RR:

[0039] As a preferred scheme of the large transformer mechanical stability monitoring and evaluation method, the transformer mechanical stability evaluation and early warning includes that 8-channel vibration signal base frequency amplitude, base frequency proportion, 50Hz amplitude, 50Hz proportion, main frequency amplitude, main frequency, main frequency proportion, even component energy ratio, and odd component energy ratio are used as a total of 72 characteristic parameters, as an input layer of a trained neural network model, and a neural network output layer is R1, R1=0 is recorded as normal transformer mechanical stability, and R1=1 is recorded as abnormal transformer mechanical stability.

[0040] The normal transformer vibration entropy is in the interval of 0-3, and when the vibration entropy exceeds the critical value 3, it is considered that the transformer may have a mechanical stability fault hidden danger; for multiple vibration measuring points, when the vibration entropy of 2 or more than 2 measuring points exceeds the critical value 3, the transformer mechanical stability is determined to be abnormal. The transformer mechanical stability determination result based on the 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.

[0041] The vibration correlation represents the vibration correlation degree between each measuring point, and ranges from 0 to 1; the transformer mechanical stability determination result based on the vibration correlation is recorded as R3, when the vibration correlation of the plurality of measuring points is less than 0.5, R3=0 is recorded as the transformer mechanical stability being normal, and when the vibration correlation of the plurality of measuring points is greater than or equal to 0.5, R3=1 is recorded as the transformer mechanical stability being abnormal.

[0042] Based on the analysis, the large transformer mechanical stability monitoring and evaluation method is as follows: R=R1 AND R2 AND R3

[0043] That is, the transformer mechanical stability evaluation and early warning are realized based on the logical or operation of the neural network output value, the vibration entropy and the vibration correlation, R=0 is determined as the transformer mechanical stability being normal, and R=1 is determined as the transformer mechanical stability being abnormal.

[0044] A computer device comprises a memory and a processor, the memory stores a computer program, and the processor implements the steps of the large transformer mechanical stability monitoring and evaluation method when executing the computer program.

[0045] A computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the steps of the large transformer mechanical stability monitoring and evaluation method.

[0046] The method of the present application is based on a feedback loop model, and a nonlinear convolution model of uplink and downlink waves of seabed node data is obtained, which shows that the primary reflection Green function of the underground can be extracted by deconvolution of the uplink and downlink waves, the method assumes that the multiple wave prediction relationship of the plane wave components in different directions in the seabed node data is independent of each other, so that the deconvolution can be performed in the plane wave domain at each frequency and in each plane wave direction, the calculation efficiency is high, and only local plane wave decomposition of the common receiver point gather of the seabed node data is required, thereby avoiding the problem of sparse spatial sampling of the common shot gather data of the seabed node data. BRIEF DESCRIPTION OF DRAWINGS

[0047] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced as follows, and obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0048] Fig. 1 is a flowchart of a large transformer mechanical stability monitoring and evaluation method provided by an embodiment of the present application.

[0049] Fig. 2 is a schematic diagram of a collection device structure of a large transformer mechanical stability monitoring and evaluation method according to an embodiment of the present application.

[0050] Fig. 3 is a schematic diagram of a normal state transformer voiceprint vibration signal spectrum of a large transformer mechanical stability monitoring and evaluation method according to an embodiment of the present application.

[0051] Fig. 4 is a schematic diagram of an abnormal state transformer voiceprint vibration signal spectrum of a large transformer mechanical stability monitoring and evaluation method according to an embodiment of the present application. DETAILED DESCRIPTION

[0052] In order to make the above objectives, features and advantages of the present application more apparent, specific embodiments of the present application will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative work should fall within the protection scope of the present application.

[0053] In the following description, a large number of specific details are set forth in order to provide a thorough understanding of the present application. However, the present application can be practiced in other manners different from those described herein, and those of ordinary skill in the art can make similar generalizations without departing from the spirit and scope of the present application. Therefore, the present application is not limited to the specific embodiments disclosed below.

[0054] Secondly, the "one embodiment" or "embodiment" referred to herein means that a specific feature, structure or characteristic can be included in at least one implementation of the present application. The "in one embodiment" appearing in different places in the specification does not mean the same embodiment, nor is it an embodiment that is independent of or selected from other embodiments.

[0055] The present application is described in detail in conjunction with the schematic diagram. In the detailed description of the embodiments of the present application, the cross-sectional view of the device structure is locally enlarged without the general proportion for the convenience of description, and the schematic diagram is only an example, which should not limit the scope of protection of the present application herein. In addition, the three-dimensional spatial dimensions of length, width and depth should be included in actual manufacturing.

[0056] Meanwhile, in the description of the present application, it should be noted that the terms "up, down, in and out" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the indicated device or element must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation on the present application. In addition, the terms "first, second or third" are only for the purpose of description, and cannot be understood as indicating or implying relative importance.

[0057] Unless otherwise defined, the terms "mounting, connecting, associating" in the present application should be interpreted broadly, for example: it can be fixed connection, detachable connection or integral connection; it can also be mechanical connection, electrical connection or direct connection, it can also be indirectly connected through intermediate medium, or it can be the communication inside two elements. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0058] Embodiment 1, referring to Figures 1-4, is the first embodiment of the present application, which provides a large transformer mechanical stability monitoring and evaluation method, comprising:

[0059] S1: using Internet of Things intelligent sensor to obtain transformer distributed measurement point voiceprint vibration signal.

[0060] S2: multi-channel voiceprint vibration signal conditioning and synchronous acquisition.

[0061] S3: calculating 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 each channel voiceprint vibration signal.

[0062] S4: realizing transformer mechanical stability evaluation and early warning based on neural network output value, vibration entropy and vibration correlation logical or operation.

[0063] In step S1, the Internet of Things intelligent sensor is composed of a piezoelectric acceleration sensing module, a wireless sending module and a battery module, and is installed on the surface of the transformer oil tank in a magnetic attraction manner. The installation positions include the bottom of the high-voltage side oil tank wall heart column clamp, the left side oil tank wall yoke middle part corresponding oil tank surface, the right side oil tank wall yoke middle part corresponding oil tank surface and the center point of the tank top. The vibration signal frequency measurement range of the Internet of Things intelligent sensor is 5Hz-3000Hz, the vibration acceleration measurement range is 0.1g-5g, and the vibration sensor sensitivity is 100mV / g.

[0064] Figure 2 is a multi-channel voiceprint vibration signal acquisition device structure diagram of the present application.

[0065] In step S2, the multi-channel voiceprint vibration signal acquisition device includes a signal conditioning circuit, an A / D sampling circuit, a data buffer 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 function. 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.

[0066] Figure 3 is a normal state transformer voiceprint vibration signal spectrum diagram of the present application.

[0067] Figure 4 is a spectrum of an abnormal state transformer voiceprint vibration signal of the present application.

[0068] In step S3, the characteristic parameters of each channel voiceprint vibration signal are calculated for large transformer mechanical stability evaluation, including the fundamental frequency amplitude, the fundamental frequency proportion, the 50Hz amplitude, the 50Hz proportion, the main frequency amplitude, the main frequency, the main frequency proportion, the even component energy ratio, the odd component energy ratio, the vibration entropy and the vibration correlation, the definition and calculation process of each characteristic parameter are as follows:

[0069] (a) Fundamental frequency amplitude: the amplitude corresponding to the frequency of 100Hz in the vibration spectrum.

[0070] (b) Fundamental frequency proportion:

[0071] In the formula, 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.

[0072] (c) 50Hz amplitude: the amplitude corresponding to the frequency of 50Hz in the vibration spectrum.

[0073] (d) 50Hz proportion:

[0074] In the formula, 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.

[0075] (e) Main frequency amplitude: the amplitude corresponding to the frequency with the highest amplitude in the vibration spectrum.

[0076] (f) Main frequency: the frequency with the highest amplitude in the vibration spectrum.

[0077] (g) Main frequency proportion:

[0078] In the formula, 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.

[0079] (h) Even component energy ratio: the energy ratio of 100Hz and its integer harmonic energy to the characteristic frequency point energy.

[0080] In the formula, E even is the even component energy ratio; S fAmplitude corresponding to frequency f in the vibration spectrum, f = 50, 100, …, 1150, 1200.

[0081] (i) Odd component energy ratio: the energy of 50Hz and its odd harmonic components accounts for the proportion of the energy of the characteristic frequency point.

[0082] In the formula, E odd Odd component energy ratio; S f Amplitude corresponding to frequency f in the vibration spectrum, f = 50, 100, …, 1150, 1200.

[0083] (j) Vibration entropy: a parameter representing the complexity of the frequency components in the spectrum. The lower the value, the more concentrated the energy in the spectrum is at certain characteristic frequencies, and the higher the value, the more dispersed the energy in the spectrum is.

[0084] In the formula, P f Frequency proportion; H is the vibration entropy; f is the frequency; S f Amplitude corresponding to frequency f in the vibration spectrum, f = 100, 200, …, 1200.

[0085] (k) Vibration correlation: represents the degree of vibration correlation between multiple measurement points.

[0086] Step 1: Construct the vibration change matrix w

[0087] In the formula, Δw ij Vibration change, n is the number of samples, and m is the number of sensors.

[0088] Step 2: Standardization processing, obtain the standard matrix W. Calculate the mean value by column and the standard deviation S j

[0089] Obtain the standardized element ΔW and the matrix W

[0090] Step 3: Calculate the standard matrix covariance matrix R

[0091] In the formula, R ij Element in the standard matrix covariance matrix R.

[0092] Step 4: Calculate the eigenvalue of the covariance matrix Λ Λ = diag{λ1, λ2, λ3, …, λ m} (7.8)

[0093] The eigenvalues are arranged in descending order as λ1≥λ2≥λ3, …, ≥λm .

[0094] Step 5: Calculate the vibration correlation RR

[0095] In step S4, 8-channel vibration signal base frequency amplitude, base frequency proportion, 50Hz amplitude, 50Hz proportion, main frequency amplitude, main frequency, main frequency proportion, even component energy ratio, odd component energy ratio, a total of 72 characteristic parameters are used as the input layer of the trained neural network model, and the output layer of the neural network is R1, R1=0 is recorded as normal transformer mechanical stability, and R1=1 is recorded as abnormal transformer mechanical stability.

[0096] The normal transformer vibration entropy is in the interval of 0-3, and the vibration entropy exceeding the critical value 3 is considered to have a potential mechanical stability fault of the transformer. For multiple vibration measuring points, when the vibration entropy of 2 or more measuring points exceeds the critical value 3, the transformer mechanical stability is determined to be abnormal. The transformer mechanical stability determination result based on the 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.

[0097] The vibration correlation represents the vibration correlation degree between each measuring point, and its range is between 0 and 1. The transformer mechanical stability determination 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, and 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.

[0098] Based on the above analysis, the large transformer mechanical stability monitoring and evaluation method is as follows R=R1^R2^R3

[0099] That is, the transformer mechanical stability evaluation and early warning are realized based on the logical or operation of the neural network output value, the vibration entropy and the vibration correlation, R=0 is determined as normal transformer mechanical stability, and R=1 is determined as abnormal transformer mechanical stability.

[0100] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and not to limit it. Although the present application 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 application can be modified or replaced by equivalents without departing from the spirit and scope of the present application, which should be covered in the scope of the claims of the present application.

[0101] Example 2

[0102] The second embodiment of the present application is different from the previous embodiment:

[0103] If the functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the parts that contribute to the prior art or parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0104] The present application is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices produce a device that implements the functions specified in one or more flows in the flowcharts and / or one or more blocks in the block diagrams.

[0105] These computer program instructions can also be stored in a computer readable storage medium that can guide the computer or other programmable data processing devices to work in a specific way, so that the instructions stored in the computer readable storage medium produce a product including instruction devices, which implement the functions specified in one or more flows in the flowcharts and / or one or more blocks in the block diagrams.

[0106] These computer program instructions can also be loaded into a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to produce a computer implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more flows in the flowcharts and / or one or more blocks in the block diagrams.

[0107] Although the preferred embodiments of the present application have been described, those skilled in the art can make additional changes and modifications to the embodiments once they know the basic inventive 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.

[0108] Obviously, numerous modifications and variations of the present application are possible in light of the above teachings. It is therefore to be understood that within the scope of the appended claims and their equivalents, the application can be practiced otherwise than as specifically described.

Claims

1. A method for monitoring and evaluating the mechanical stability of large power transformers, characterized by: The application relates to a large transformer mechanical stability monitoring and evaluation method. Obtain transformer distributed measuring point voiceprint vibration signals by using an Internet of Things intelligent sensor; Multi-channel voiceprint vibration signal conditioning and synchronous acquisition; Calculate the correlation of each channel voiceprint vibration signal feature; Realize transformer mechanical stability evaluation and early warning based on neural network output value, vibration entropy and vibration correlation logical or operation.

2. The method for monitoring and evaluating mechanical stability of large transformers according to claim 1, characterized in that: The multi-channel voiceprint vibration signal conditioning and synchronous acquisition comprises, The multi-channel voiceprint vibration signal acquisition device comprises a signal conditioning circuit, an A / D sampling circuit, a data buffer module, an MCU control system, a GPS timing module, a communication module and a backup module.

3. The method for monitoring and evaluating mechanical stability of large power transformers according to claim 2, characterized in that: The calculation of the correlation of each channel voiceprint vibration signal feature comprises calculation of each channel voiceprint vibration signal feature parameter, which is used for large transformer mechanical stability evaluation, and the feature parameters comprise a fundamental frequency amplitude, a fundamental frequency proportion, a 50Hz amplitude, a 50Hz proportion, a main frequency amplitude, a main frequency, a main frequency proportion, an even component energy ratio, an odd component energy ratio, vibration entropy and vibration correlation.

4. The method for monitoring and evaluating mechanical stability of large power transformers according to claim 3, characterized in that: The calculation of the correlation of each channel voiceprint vibration signal feature comprises the following definition and calculation process of each feature parameter: The fundamental frequency amplitude is the amplitude corresponding to the 100Hz frequency in the vibration spectrum; Fundamental frequency proportion: where P f＝100 is the base frequency proportion; f is the frequency; S f is the amplitude corresponding to the frequency f in the vibration spectrum, f = 100, 200,..., 1200; The 50Hz amplitude is the amplitude corresponding to the 50Hz frequency in the vibration spectrum; 50 Hz specific gravity: where P f＝50 is the base 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 method of monitoring and evaluating the mechanical stability of large power transformers as claimed in claim 4, characterized in that: The calculation of the correlation of each channel voiceprint vibration signal feature comprises, The main frequency amplitude is the amplitude corresponding to the frequency with the highest amplitude in the vibration spectrum; The main frequency is the frequency with the highest amplitude in the vibration spectrum; Main frequency ratio: where P fm is the base frequency proportion; f is the frequency; S f is the amplitude corresponding to the frequency f in the vibration spectrum, f = 100, 200, …, 1200; Odd component energy ratio: the energy ratio of 100 Hz and its integer multiple harmonic energy to the characteristic frequency point energy; where E even is the even component energy ratio; S f is the amplitude corresponding to the frequency f in the vibration spectrum, f = 50, 100, …, 1150, 1200.

6. A method of monitoring and evaluating the mechanical stability of large power transformers as claimed in claim 5, characterized in that: The calculation of the correlation of each channel voiceprint vibration signal feature comprises, Odd component energy ratio: the energy ratio of 50Hz and its odd harmonic to the energy of the characteristic frequency point; wherein E odd is the odd component energy ratio; S f is the amplitude corresponding to the frequency f in the vibration spectrum, f = 50, 100, …, 1150, 1200; Vibrational entropy: parameter characterizing the complexity of the frequency components in the spectrum, the lower the value, the more concentrated the energy in certain characteristic frequencies in the spectrum, the higher the value, the more dispersed the energy in the spectrum; In the formula, P f H is the frequency proportion; H is the vibration entropy; f is the frequency; S f Let f be the amplitude corresponding to frequency f in the vibration spectrum, where f = 100, 200, ..., 1200; The vibration correlation represents the vibration correlation degree between multiple measuring points.

7. A method of monitoring and evaluating the mechanical stability of large power transformers as claimed in claim 6, characterized in that: The calculation of the correlation of each channel voiceprint vibration signal feature further comprises, The vibration change amount matrix w is constructed as follows: where Δw ij is the vibration change amount, n is the number of samples, and m is the number of sensors. Standardization is performed to obtain a standard matrix W, and the mean value is calculated by column and standard deviation S j ; The standardized elements ΔW and the matrix W are obtained: Compute the standard matrix covariance matrix R: where R ij is the standard matrix of the covariance matrix R. Calculate the covariance matrix eigenvalue Lambda: Λ = diag{λ1, λ2, λ3,...., λ m} The eigenvalues are arranged in descending order as λ1≥λ2≥λ3,....,≥λ m ; Computing the vibrational relevance RR:

8. The method for monitoring and evaluating mechanical stability of large power transformers according to claim 7, characterized in that: The transformer mechanical stability evaluation and early warning comprises that 72 feature parameters including the fundamental frequency amplitude, the fundamental frequency proportion, the 50Hz amplitude, the 50Hz proportion, the main frequency amplitude, the main frequency, the main frequency proportion, the even component energy ratio and the odd component energy ratio of the 8-channel vibration signal are used as the input layer of the trained neural network model, the output layer of the neural network is R1, R1=0 is recorded as normal transformer mechanical stability, and R1=1 is recorded as abnormal transformer mechanical stability; The vibration entropy of the normal transformer is in the interval of 0-3, and when the vibration entropy exceeds the critical value 3, it is considered that the transformer may have a mechanical stability fault hidden danger; for multiple vibration measuring points, when the vibration entropy of two or more than two measuring points exceeds the critical value 3, the transformer mechanical stability is determined to be abnormal; the transformer mechanical stability determination result based on the 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 represents the vibration correlation degree between each measuring point, and the range is between 0 and 1; the transformer mechanical stability determination 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, and 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 large transformer mechanical stability monitoring and evaluation method is shown in the following formula: ​ That is, based on the neural network output value, vibration entropy and vibration correlation logic or operation, the transformer mechanical stability evaluation and early warning are realized, R=0, the transformer mechanical stability is determined to be normal, and R=1, the transformer mechanical stability is determined to be abnormal. 9.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-8 when the computer program is executed by the processor. The computer program, when executed by the processor, implements the steps of the method of any one of claims 1 to 8.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program, when executed by the processor, implements the steps of the method of any one of claims 1 to 8.

Images