Transformer soundprint fault monitoring method, device, computer equipment and storage medium

By disaggregating the transformer voiceprint signal and decomposing local feature, combined with the fault identification model, the problem of inaccurate transformer fault detection in the prior art is solved, and the accuracy and efficiency of fault identification are improved.

CN118762715BActive Publication Date: 2024-11-08THREE GORGES GROUP IND DEVELOPMENT (BEIJING) CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411205917.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-30
Publication Date
2024-11-08
Estimated Expiration
2044-08-30

Smart Images

  • Figure CN118762715B_ABST
    Figure CN118762715B_ABST
Patent Text Reader

Abstract

The present invention relates to the technical field of fault detection, and discloses a transformer voiceprint fault monitoring method, device, computer equipment and storage medium. The method obtains multiple sample data by discretely processing a continuous voiceprint signal of a transformer. The multiple sample data include a first sample data and multiple second sample data. The time node of the first sample data is later than the time node of the second sample data. The statistics of each sample data, the variance and the mean of the multiple sample data are calculated. By calculating the statistical information of each sample data, if there is a second sample data whose statistics is greater than the statistics of the first sample data, a target judgment value of the first sample data is calculated according to the variance and the mean of the multiple sample data. If the target judgment value is greater than a preset threshold, it means that there is a change point in the first sample data. The continuous voiceprint signal is subjected to local feature decomposition and then output to a fault recognition model for recognition, thereby improving the accuracy and efficiency of fault recognition.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of fault detection, and in particular to a transformer voiceprint fault monitoring method, device, computer equipment and storage medium. Background Art

[0002] As one of the important equipment in the power system, the normal operation of the transformer is crucial to the stable operation of the power system. Due to long-term operation, load fluctuations, environmental conditions and other reasons, the transformer may have various faults. Therefore, transformer fault diagnosis can improve the reliability of power supply; through transformer fault diagnosis, various types of transformer faults can be discovered and judged in time, and maintenance measures can be taken quickly to avoid further expansion of the fault, thereby improving power supply reliability and reducing power outages. In addition, by pre-continuously monitoring and diagnosing the operating status of the transformer, potential problems and abnormalities can be discovered, and preventive measures can be taken in time to avoid the occurrence of faults, reduce production losses and maintenance costs, and extend equipment life. Using various sensors to monitor transformers online is an operation and maintenance method urgently needed by power production units.

[0003] At present, online monitoring of transformers is generally carried out by collecting the soundprint signal of the transformer through a sound sensor, comparing the soundprint signal with the preset fault threshold, and judging whether the transformer is faulty based on the comparison result. However, the preset fault threshold is based on past fault conditions and is determined based on experience. Using the preset threshold to perform transformer fault detection has the defect that the detection result is not accurate enough. Summary of the invention

[0004] In view of this, the present invention provides a transformer voiceprint fault monitoring method, device, computer equipment and storage medium to solve the problem that the fault detection of the transformer is performed by comparing the voiceprint signal with a preset fault threshold in the related art, and the detection result is not accurate enough.

[0005] In a first aspect, the present invention provides a transformer voiceprint fault monitoring method, the method comprising: obtaining a continuous voiceprint signal of a transformer using a sliding window of a preset time length; performing discrete processing on the continuous voiceprint signal of the transformer to obtain multiple sample data, the multiple sample data comprising a first sample data and multiple second sample data, the time node of the first sample data being later than the time node of the second sample data; calculating the statistics of each sample data, the variance and the mean of the multiple sample data; if there is a second sample data whose statistics is greater than the statistics of the first sample data, calculating a target judgment value of the first sample data according to the variance and the mean of the multiple sample data; if the target judgment value is greater than a preset threshold, performing local feature decomposition on the continuous voiceprint signal to obtain a decomposition result; outputting the decomposition result to a pre-constructed fault identification model so that the model outputs the fault identification result of the transformer, the fault identification model being used to characterize the correlation between the local feature decomposition result of the continuous voiceprint signal and the transformer fault.

[0006] The transformer voiceprint fault monitoring method provided by the present invention obtains multiple sample data by discretely processing the continuous voiceprint signal of the transformer, the multiple sample data include first sample data and multiple second sample data, the time node of the first sample data is later than the time node of the second sample data, the statistics of each sample data, the variance and the mean of the multiple sample data are calculated, if there is a second sample data whose statistics is greater than the statistics of the first sample data, the target judgment value of the first sample data is calculated according to the variance and the mean of the multiple sample data, if the target judgment value is greater than the preset threshold, the continuous voiceprint signal is subjected to local feature decomposition and input into the fault recognition model, so that the fault recognition model outputs a fault recognition result. The method provided by the present invention calculates the statistical information of each sample data. If there is a second sample data whose statistic is greater than the statistic of the first sample data, the target judgment value of the first sample data is calculated according to the variance and mean of the multiple sample data. If the target judgment value is greater than the preset threshold, it indicates that there is a change point in the first sample data. The continuous voiceprint signal is subjected to local feature decomposition and then output to a fault recognition model for recognition. This improves the accuracy of fault recognition and the efficiency of fault analysis. It is not necessary to input all received signals into the fault recognition model for recognition, which effectively shortens the calculation time of the fault recognition model and meets the needs of online fault detection of transformer voiceprints.

[0007] In an optional embodiment, the method further includes: if the statistics of multiple second samples are all lower than the statistics of the first sample data, then there is no fault in the transformer; if the target judgment value is lower than a preset threshold, then there is no fault in the transformer.

[0008] In an optional implementation, calculating the statistics of each sample data includes:

[0009] The statistics of each sample data are calculated by the first relational expression, which is:

[0010]

[0011] in, represents the statistic of the i-th sample data, represents the i-th sample data, Indicates the time node is The sample data before is sgn, and sgn is the sign function.

[0012] In an optional implementation, the step of performing local feature decomposition on the continuous voiceprint signal to obtain a decomposition result includes: inputting the first sample data into a local feature decomposition model so that the model outputs a data decomposition result.

[0013] In an optional embodiment, after the step of outputting the decomposition result to a pre-built fault identification model so that the model outputs the fault identification result of the transformer, the method also includes: if there is a fault in the transformer, storing the fault information to a preset location and generating early warning information; and sending the early warning information to the terminal device.

[0014] In an optional implementation, the fault identification model is obtained by training a preset neural network model, and the preset neural network model includes a recurrent neural network.

[0015] In a second aspect, the present invention provides a transformer voiceprint fault monitoring device, which includes: an acquisition module, which is used to acquire a continuous voiceprint signal of a transformer using a sliding window of a preset time length; a processing module, which is used to discretely process the continuous voiceprint signal of the transformer to obtain multiple sample data, the multiple sample data include a first sample data and multiple second sample data, and the time node of the first sample data is later than the time node of the second sample data; a first calculation module, which is used to calculate the statistics of each sample data, the variance and the mean of the multiple sample data; a second calculation module, which is used to calculate the target judgment value of the first sample data according to the variance and the mean of the multiple sample data if the statistics of the second sample data is greater than the statistics of the first sample data; a decomposition module, which is used to perform local feature decomposition on the continuous voiceprint signal to obtain a decomposition result if the target judgment value is greater than a preset threshold; an identification module, which is used to output the decomposition result to a pre-constructed fault identification model so that the model outputs the fault identification result of the transformer, and the fault identification model is used to characterize the correlation between the local feature decomposition result of the continuous voiceprint signal and the transformer fault.

[0016] In a third aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the transformer voiceprint fault monitoring method of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0017] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the transformer voiceprint fault monitoring method of the first aspect or any corresponding embodiment thereof.

[0018] In a fifth aspect, the present invention provides a computer program product, including computer instructions, and the computer instructions are used to enable a computer to execute the transformer voiceprint fault monitoring method of the above-mentioned first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0020] Figure 1 is a flow chart of a transformer voiceprint fault monitoring method according to an embodiment of the present invention;

[0021] Figure 2 is a flow chart of another transformer voiceprint fault monitoring method according to an embodiment of the present invention;

[0022] Figure 3 is a flowchart of a specific example according to an embodiment of the present invention;

[0023] Figure 4 is a structural block diagram of a transformer voiceprint fault monitoring device according to an embodiment of the present invention;

[0024] Figure 5 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0025] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0026] In the related art, online monitoring of transformers is generally carried out by collecting the soundprint signal of the transformer through a sound sensor, comparing the soundprint signal with a preset fault threshold, and judging whether the transformer is faulty based on the comparison result. However, the preset fault threshold is based on past fault conditions and is determined based on experience. Using the preset threshold to perform transformer fault detection has the defect that the detection result is not accurate enough.

[0027] In view of this, a transformer voiceprint fault monitoring method provided in an embodiment of the present application can be applied to a server to realize transformer voiceprint fault monitoring. The method provided in an embodiment of the present invention calculates the statistical information of each sample data. If there is a second sample data whose statistic is greater than the first sample data, the target judgment value of the first sample data is calculated according to the variance and mean of the multiple sample data. If the target judgment value is greater than the preset threshold, it indicates that there is a change point in the first sample data. The continuous voiceprint signal is subjected to local feature decomposition and then output to the fault recognition model for recognition. While improving the accuracy of fault recognition, the efficiency of fault analysis is improved. It is not necessary to input all received signals into the fault recognition model for recognition, which effectively shortens the calculation time of the fault recognition model and meets the needs of online fault detection of transformer voiceprint.

[0028] According to an embodiment of the present invention, an embodiment of a transformer voiceprint fault monitoring method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0029] In this embodiment, a transformer voiceprint fault monitoring method is provided, which can be used for the above-mentioned server. Figure 1 is a flow chart of a transformer voiceprint fault monitoring method according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0030] Step S101, obtaining a continuous voiceprint signal of the transformer using a sliding window of a preset time length.

[0031] Exemplarily, the preset time length can be any time length as long as it meets the requirement of obtaining the continuous voiceprint signal. The continuous voiceprint signal of the transformer can be collected by a sound sensor such as a microphone or a pickup.

[0032] Step S102, discretely process the continuous voiceprint signal of the transformer to obtain a plurality of sample data, wherein the plurality of sample data includes first sample data and a plurality of second sample data, and the time node of the first sample data is later than the time node of the second sample data.

[0033] For example, in the embodiment of the present application, the length of the sliding window may be L, the continuous voiceprint signal of the transformer is the signal within the sliding window of length L, and the signal is processed with N snapshots, and the sampling frequency is , get N sample data , ,…, In the embodiment of the present application, the time node of the first sample data may be the current time point.

[0034] Step S103, calculating the statistics of each sample data, the variance and the mean of multiple sample data.

[0035] Exemplarily, in the embodiment of the present application, the statistics of each sample data are calculated by a first relational expression, and the first relational expression is:

[0036]

[0037] in, represents the statistic of the i-th sample data, represents the i-th sample data, Indicates the time node is The sample data before, sgn is the sign function, is the statistic of the first sample data. The variance and mean of multiple sample data are calculated by conventional calculation methods.

[0038] Step S104: if the statistics of the second sample data are greater than the statistics of the first sample data, the target judgment value of the first sample data is calculated according to the variance and mean of the plurality of sample data.

[0039] For example, in the present application, if ,in, , then the target judgment value of the first sample data is calculated based on the variance and mean of multiple sample data. The target judgment formula can be calculated by the following formula:

[0040]

[0041] in, represents the target judgment value, Indicates Sample data, represents the mean of multiple sample data. Represents the variance of multiple sample data.

[0042] Step S105: if the target judgment value is greater than a preset threshold, local feature decomposition is performed on the continuous voiceprint signal to obtain a decomposition result.

[0043] Exemplarily, the preset threshold may include but is not limited to 0.05. In the embodiment of the present application, empirical mode decomposition (EMD) may be used to perform local feature decomposition on the first sample data to obtain a decomposition result.

[0044] Step S106, outputting the decomposition result to a pre-built fault identification model so that the model outputs the fault identification result of the transformer. The fault identification model is used to characterize the correlation between the local feature decomposition result of the continuous voiceprint signal and the transformer fault.

[0045] Exemplarily, the fault identification model is obtained by training a preset neural network model, and the preset neural network model includes a recurrent neural network (RNN). In the embodiment of the present application, if no fault occurs, monitoring continues, and if a fault occurs, the fault is reported and recorded.

[0046] The transformer voiceprint fault monitoring method provided in the present embodiment calculates the statistical information of each sample data. If there is a second sample data whose statistic is greater than the statistic of the first sample data, the target judgment value of the first sample data is calculated according to the variance and mean of the multiple sample data. If the target judgment value is greater than the preset threshold, it indicates that there is a change point in the first sample data. The continuous voiceprint signal is subjected to local feature decomposition and then output to the fault recognition model for recognition. This improves the accuracy of fault recognition and the efficiency of fault analysis. It is not necessary to input all received signals into the fault recognition model for recognition, which effectively shortens the calculation time of the fault recognition model and meets the needs of online fault detection of transformer voiceprints.

[0047] In this embodiment, a transformer voiceprint fault monitoring method is provided, which can be used for the above-mentioned server. Figure 2 is a flow chart of a transformer voiceprint fault monitoring method according to an embodiment of the present invention. Figure 2 As shown, the process includes the following steps:

[0048] Step S201, using a sliding window of preset duration to obtain a continuous voiceprint signal of the transformer. Figure 1Step S101 of the illustrated embodiment will not be described in detail here.

[0049] Step S202: discretely process the continuous voiceprint signal of the transformer to obtain a plurality of sample data, wherein the plurality of sample data includes a first sample data and a plurality of second sample data, and the time node of the first sample data is later than the time node of the second sample data. Figure 1 Step S102 of the illustrated embodiment will not be described in detail here.

[0050] Step S203, calculate the statistics of each sample data, the variance and mean of multiple sample data. Figure 1 Step S103 of the illustrated embodiment will not be described in detail here.

[0051] Step S204: If the statistics of the second sample data are greater than the statistics of the first sample data, the target judgment value of the first sample data is calculated according to the variance and mean of the plurality of sample data. Figure 1 Step S104 of the illustrated embodiment will not be described in detail here.

[0052] Specifically, if the statistics of the plurality of second samples are all lower than the statistics of the first sample data, then there is no fault in the transformer. , indicating that there is no change point at the current time point, and there is no fault in the transformer.

[0053] Step S205: if the target judgment value is greater than a preset threshold, local feature decomposition is performed on the continuous voiceprint signal to obtain a decomposition result.

[0054] Specifically, if the target judgment value is below the preset threshold, the transformer does not have a fault. Exemplarily, if the target judgment value is less than or equal to the preset threshold, it means that no change point occurs at the current time point, and the transformer does not have a fault.

[0055] Specifically, the above step S205 includes:

[0056] Step S2051: input the first sample data into the local feature decomposition model so that the model outputs a data decomposition result.

[0057] For example, in the embodiment of the present application, if a change point occurs, the local transformer voiceprint signal in the window at that moment is sent to the local feature decomposition module for feature decomposition, as follows: Figure 3 As shown. The embodiment of the present application uses the intrinsic mode functions (IMF) after EMD decomposition as the feature decomposition method. The specific steps are:

[0058] Step a1: Perform EMD modal decomposition on the voiceprint signal with change points in the window to obtain a series of IMF intrinsic mode components.

[0059] Step a2, specifically find all the extreme points of the voiceprint signal, fit the envelope through the extreme points, specifically fit the upper envelope through the cubic spline interpolation method for the upper extreme point, and fit the lower envelope through the cubic spline interpolation method for the lower extreme point, calculate the average value of the upper and lower envelopes, and use the original signal minus the average value to obtain the output signal.

[0060] Step a3, determine whether the output signal meets the following two conditions: (1) the number of extreme points and the number of zero-crossing points of the signal must be equal or the difference cannot exceed one; (2) the average value of the upper envelope and the lower envelope of the signal is zero.

[0061] Step a4, if the conditions are met, the first IMF intrinsic mode component is obtained and recorded as IMF1. If the conditions are not met, the output signal is used as the original signal to perform EMD modal decomposition again. For the output signal that meets the conditions, the original signal minus the output signal is used to continue EMD modal decomposition to find IMF2 until all intrinsic mode functions are found.

[0062] Step S206: Output the decomposition result to the pre-built fault identification model, so that the model outputs the fault identification result of the transformer. The fault identification model is used to characterize the correlation between the local feature decomposition result of the continuous voiceprint signal and the transformer fault. Figure 1 Step S106 of the illustrated embodiment will not be described in detail here.

[0063] In some optional embodiments, the method further comprises:

[0064] Step b1: if the transformer has a fault, store the fault information in a preset location and generate an early warning message. For example, in the embodiment of the present application, the preset location may be a pre-set storage area. The embodiment of the present application does not limit the specific content of the preset location, and those skilled in the art may determine it according to needs.

[0065] Step b2, sending the warning information to the terminal device. Exemplarily, the warning information is sent to the terminal device so that the terminal device can perform a warning operation based on the received warning information.

[0066] The transformer soundprint fault monitoring method provided by the present invention is described in detail below through a specific embodiment.

[0067] Example:

[0068] The specific process of the transformer soundprint fault monitoring method includes:

[0069] 1. Use sound sensors such as microphones and pickups to monitor the voiceprint signal of a given transformer online.

[0070] 2. When monitoring voiceprint signals, set a sliding window with a time length of L at the current time point as the end, and perform change point analysis on the signal at the current time point and the signals at other time points in the sliding window. Optionally, Bayesian change point analysis, variance change point analysis, mean change point analysis, etc. can be used.

[0071] 3. Determine whether a change point occurs at the current time point. If no change point occurs, continue to monitor the voiceprint signal of the transformer.

[0072] 4. If a change point occurs, the local transformer voiceprint signal in the window at that moment is sent to the local feature decomposition module for feature decomposition.

[0073] 5. Send the signal characteristics in the window to the fault identification module to determine whether a fault has occurred at the current moment. If no fault has occurred, continue monitoring. If a fault has occurred, report and record the fault.

[0074] In this embodiment, a transformer voiceprint fault monitoring device is also provided, which is used to implement the above embodiments and preferred implementations, and will not be repeated here. As used below, the term "module" can implement a combination of software and / or hardware for a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0075] This embodiment provides a transformer voiceprint fault monitoring device, such as Figure 4 As shown, including:

[0076] An acquisition module 401 is used to acquire a continuous voiceprint signal of the transformer using a sliding window of a preset time length;

[0077] The processing module 402 is used to perform discrete processing on the continuous voiceprint signal of the transformer to obtain a plurality of sample data, wherein the plurality of sample data includes a first sample data and a plurality of second sample data, and a time node of the first sample data is later than a time node of the second sample data;

[0078] The first calculation module 403 is used to calculate the statistics of each sample data, the variance and the mean of multiple sample data;

[0079] A second calculation module 404 is used to calculate the target judgment value of the first sample data according to the variance and mean of the plurality of sample data if the statistic of the second sample data is greater than the statistic of the first sample data;

[0080] The decomposition module 405 is used to perform local feature decomposition on the continuous voiceprint signal to obtain a decomposition result if the target judgment value is greater than a preset threshold;

[0081] The identification module 406 is used to output the decomposition result to a pre-built fault identification model so that the model outputs the fault identification result of the transformer. The fault identification model is used to characterize the correlation between the local feature decomposition result of the continuous voiceprint signal and the transformer fault.

[0082] In some optional embodiments, the above device further includes:

[0083] A first determination module, configured to determine that there is no fault in the transformer if the statistics of the plurality of second samples are all lower than the statistics of the first sample data;

[0084] The second determination module is used to determine that there is no fault in the transformer if the target judgment value is below a preset threshold.

[0085] In some optional implementations, calculating the statistics of each sample data includes:

[0086] The statistics of each sample data are calculated by the first relational expression, which is:

[0087]

[0088] in, represents the statistic of the i-th sample data, represents the i-th sample data, Indicates the time node is The sample data before is sgn, and sgn is the sign function.

[0089] In some optional implementations, the decomposition module 405 includes:

[0090] The decomposition submodule is used to input the first sample data into the local feature decomposition model to obtain the model data decomposition result.

[0091] In some optional embodiments, the device further comprises:

[0092] A storage module is used to store fault information in a preset location and generate early warning information if there is a fault in the transformer;

[0093] The sending module is used to send the warning information to the terminal device.

[0094] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0095] The transformer voiceprint fault monitoring device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0096] The embodiment of the present invention also provides a computer device having the above Figure 4 The transformer sound print fault monitoring device shown.

[0097] See also Figure 5 , Figure 5 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 5 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 5 A processor 10 is taken as an example.

[0098] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0099] The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0100] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0101] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0102] The computer device further comprises a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0103] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0104] A part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of the computer program instruction in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc., and accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the computer.

[0105] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A transformer soundprint fault monitoring method, It is characterized in that The method comprises: A sliding window of preset duration is used to obtain a continuous voiceprint signal of the transformer; Discretely process the continuous voiceprint signal of the transformer to obtain a plurality of sample data, wherein the plurality of sample data includes first sample data and a plurality of second sample data, and a time node of the first sample data is later than a time node of the second sample data; Calculate the statistics of each sample data, the variance and mean of multiple sample data; If there is a statistic of the second sample data that is greater than the statistic of the first sample data, calculating the target judgment value of the first sample data according to the variance and mean of the plurality of sample data; If the target judgment value is greater than a preset threshold, local feature decomposition is performed on the continuous voiceprint signal to obtain a decomposition result; Outputting the decomposition result to a pre-built fault identification model so that the model outputs a transformer fault identification result, wherein the fault identification model is used to characterize the correlation between the local feature decomposition result of the continuous voiceprint signal and the transformer fault; The calculating of the statistics of each sample data includes: The statistics of each sample data are calculated by the first relational expression, which is: in, represents the statistic of the i-th sample data, represents the i-th sample data, Indicates the time node is The sample data before, sgn is the sign function; like ,in, , then the target judgment value of the first sample data is calculated according to the variance and mean of multiple sample data, and the target judgment value is calculated by the following formula: in, represents the target judgment value, Indicates Sample data, represents the mean of multiple sample data. Represents the variance of multiple sample data.

2. The method according to claim 1, It is characterized in that The method further comprises: If the statistics of the plurality of second samples are all lower than the statistics of the first sample data, then there is no fault in the transformer; If the target judgment value is below the preset threshold, there is no fault in the transformer.

3. The method according to claim 1, It is characterized in that The step of performing local feature decomposition on the continuous voiceprint signal to obtain a decomposition result comprises: The first sample data is input into the local feature decomposition model so that the model outputs a data decomposition result.

4. The method according to claim 1, It is characterized in that After the step of outputting the decomposition result to a pre-built fault identification model so that the model outputs the fault identification result of the transformer, the method further includes: If the transformer fails, the failure information is stored in a preset location and a warning message is generated; The warning information is sent to the terminal device.

5. The method according to claim 3, It is characterized in that The fault identification model is obtained by training a preset neural network model, and the preset neural network model includes a recurrent neural network.

6. A transformer voiceprint fault monitoring device, It is characterized in that The device comprises: An acquisition module, used for acquiring a continuous voiceprint signal of the transformer using a sliding window of a preset time length; A processing module, configured to perform discrete processing on the continuous voiceprint signal of the transformer to obtain a plurality of sample data, wherein the plurality of sample data includes first sample data and a plurality of second sample data, wherein a time node of the first sample data is later than a time node of the second sample data; The first calculation module is used to calculate the statistics of each sample data, the variance and the mean of multiple sample data; A second calculation module, configured to calculate a target judgment value of the first sample data according to a variance and a mean of the plurality of sample data if the statistic of the second sample data is greater than the statistic of the first sample data; A decomposition module, configured to perform local feature decomposition on the continuous voiceprint signal to obtain a decomposition result if the target judgment value is greater than a preset threshold; An identification module, used to output the decomposition result to a pre-built fault identification model so that the model outputs the fault identification result of the transformer, wherein the fault identification model is used to characterize the correlation between the local feature decomposition result of the continuous voiceprint signal and the transformer fault; The calculating of the statistics of each sample data includes: The statistics of each sample data are calculated by the first relational expression, which is: in, represents the statistic of the i-th sample data, represents the i-th sample data, Indicates the time node is The sample data before, sgn is the sign function; like ,in, , then the target judgment value of the first sample data is calculated according to the variance and mean of multiple sample data, and the target judgment value is calculated by the following formula: in, represents the target judgment value, Indicates Sample data, represents the mean of multiple sample data. Represents the variance of multiple sample data.

7. A computer device, It is characterized in that include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the transformer voiceprint fault monitoring method according to any one of claims 1 to 5 by executing the computer instructions.

8. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the transformer soundprint fault monitoring method according to any one of claims 1 to 5.

9. A computer program product, It is characterized in that The method comprises computer instructions, wherein the computer instructions are used to enable a computer to execute the transformer soundprint fault monitoring method according to any one of claims 1 to 5.