A transformer operation monitoring method, device and electronic equipment

Abstract

The application provides a transformer operation monitoring method, device and electronic equipment, wherein the method comprises: acquiring a sound emitted during transformer operation, the sound comprising: a plurality of audio signals collected by a sound pickup device; processing each audio signal in the plurality of audio signals to obtain a sound intensity characteristic value of each audio signal and a characteristic quantity of a to-be-detected sound signal, and preliminarily identifying whether the sound signal is an abnormal sound; in response to confirming that the to-be-detected sound signal is an abnormal sound, determining that the transformer has a fault, and determining a fault type of the transformer by using the sound intensity characteristic value of each audio signal and the characteristic quantity of the to-be-detected sound signal. Through the transformer operation monitoring method, device and electronic equipment provided in the embodiments of the application, the purpose of judging whether the transformer has a fault without manual inspection is achieved.

Description

Technical Field

[0001] This application relates to the field of transformer operation monitoring technology, and more specifically, to a transformer operation monitoring method, device, and electronic equipment. Background Technology

[0002] Currently, high-voltage and ultra-high-voltage transformers are generally located within large substations. Due to the high-voltage nature of these transformers, surface-mount sensors are unusable. Therefore, various remote-field monitoring solutions are required to monitor the transformer's operational status remotely.

[0003] Traditional transformer remote monitoring solutions rely on dispatching experienced workers to inspect and listen for sounds to diagnose transformer faults. However, in recent years, with the rapid increase in the number of transformers, the number of experienced workers has not kept pace. Therefore, ensuring real-time detection of transformers for obvious vibrations, noise changes, and discharge sounds has become a weakness in transformer inspection and maintenance. Summary of the Invention

[0004] To address the aforementioned problems, the purpose of this application is to provide a transformer operation monitoring method, device, and electronic device.

[0005] In a first aspect, embodiments of this application provide a transformer operation monitoring method, including:

[0006] Acquire the sound emitted during the operation of the transformer, the sound including: multiple audio signals collected by a sound pickup device;

[0007] Each audio signal in the multi-channel audio signal is processed to obtain the sound intensity feature value of each audio signal and the feature quantity of the sound signal to be detected; wherein, the sound intensity feature value is used to characterize the time domain intensity of each audio signal.

[0008] In response to the confirmation that the sound signal to be detected is an abnormal noise, it is determined that the transformer has a fault, and the fault type of the transformer is determined by using the sound intensity characteristic values ​​of each audio signal and the characteristic quantity of the sound signal to be detected.

[0009] Secondly, embodiments of this application also provide a transformer operation monitoring device, comprising:

[0010] The acquisition module is used to acquire the sound emitted during the operation of the transformer, the sound including: multiple audio signals collected by the sound pickup device;

[0011] The processing module is used to process each audio signal in the multi-channel audio signal to obtain the sound intensity feature value of each audio signal and the feature quantity of the sound signal to be detected; wherein, the sound intensity feature value is used to characterize the time domain intensity of each audio signal.

[0012] The determination module is used to determine the transformer fault in response to confirming that the sound signal to be detected is an abnormal noise, and to determine the fault type of the transformer by using the sound intensity characteristic values ​​of each audio signal and the characteristic quantity of the sound signal to be detected.

[0013] Thirdly, embodiments of this application also provide a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps of the method described in the first aspect above.

[0014] Fourthly, embodiments of this application also provide an electronic device, the electronic device including a memory, a processor and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor using the steps of the method described in the first aspect above.

[0015] In the solutions provided in the first to fourth aspects of this application, the audio signals from multiple audio signals collected by the sound pickup device during the transformer's operation are processed to obtain the sound intensity characteristic values ​​of each audio signal and the characteristic quantity of the sound signal to be detected, thus initially identifying whether the sound signal is an abnormal noise. In response to the detection of an abnormal noise, a transformer fault is determined, and the fault type of the transformer is determined using the sound intensity characteristic values ​​of each audio signal and the characteristic quantity of the sound signal to be detected. Compared with the related technology of dispatching experienced workers to inspect and listen for sounds to determine transformer faults, by processing the audio signals from multiple audio signals collected by the sound pickup device during the transformer's operation and obtaining the sound intensity characteristic values ​​of each audio signal and the characteristic quantity of the sound signal to be detected, a fault can be determined in the transformer. This achieves the goal of determining whether a transformer is faulty without manual inspection. Moreover, faults generated during transformer operation can be detected continuously, greatly improving the efficiency of transformer fault detection.

[0016] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A flowchart of a transformer operation monitoring method provided in Embodiment 1 of this application is shown;

[0019] Figure 2 A schematic diagram of the structure of a transformer operation monitoring device provided in Embodiment 2 of this application is shown;

[0020] Figure 3 A schematic diagram of the structure of an electronic device provided in Embodiment 3 of this application is shown. Detailed Implementation

[0021] In the description of this application, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this application.

[0022] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0023] In this application, unless otherwise expressly specified and limited, the terms "installation," "connection," "linking," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection between two components. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances.

[0024] Currently, high-voltage and ultra-high-voltage transformers are generally located within large substations. Due to the high-voltage nature of these transformers, surface-mount sensors are unusable. Therefore, various remote-field monitoring solutions are required to monitor the transformer's operational status remotely.

[0025] Traditional transformer remote monitoring solutions rely on dispatching experienced workers to inspect and listen for sounds to diagnose transformer faults. However, in recent years, with the rapid increase in the number of transformers, the number of experienced workers has not kept pace. Therefore, ensuring real-time detection of transformers for obvious vibrations, noise changes, and discharge sounds has become a weakness in transformer inspection and maintenance.

[0026] Based on this, the following embodiments of this application propose a transformer operation monitoring method, device, and electronic device. By processing each audio signal from multiple audio signals collected by a sound pickup device during the transformer operation process, the sound intensity characteristic values ​​of each audio signal and the characteristic quantity of the sound signal to be detected are obtained, and the abnormal noise of the sound signal is initially identified. In response to the abnormal noise of the sound signal to be detected, it is determined that the transformer has a fault, and the fault type of the transformer is determined by using the sound intensity characteristic values ​​of each audio signal and the characteristic quantity of the sound signal to be detected. By processing each audio signal from multiple audio signals collected by a sound pickup device during the transformer operation process, the sound intensity characteristic values ​​of each audio signal and the characteristic quantity of the sound signal to be detected are obtained, so as to determine whether the transformer has a fault, thus achieving the purpose of determining whether the transformer has a fault without manual inspection.

[0027] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and embodiments.

[0028] Example 1

[0029] The transformer operation monitoring method proposed in this embodiment is implemented by monitoring equipment installed near the transformer.

[0030] In one embodiment, the monitoring device can be fixed to the bottom of the transformer without contacting the transformer.

[0031] The monitoring device includes: a processor, a wireless communication module, and multiple microphones; the processor is connected to the wireless communication module and the multiple microphones respectively.

[0032] Multiple microphones are positioned towards the transformer to collect the sounds emitted during its operation, thus acquiring multiple audio signals. Each microphone can collect one audio signal from the sound.

[0033] Components of a transformer that can produce sound during operation include, but are not limited to: the oil tank, windings, core, cooling fan, and bearings of the cooling fan.

[0034] The monitoring equipment interacts with the cloud server via a wireless communication module.

[0035] Sound pickup devices, including but not limited to: microphones, recorders, voice recorders, and microphones.

[0036] See Figure 1 The flowchart shown illustrates a transformer operation monitoring method. This embodiment proposes a transformer operation monitoring method, including the following specific steps:

[0037] Step 100: Obtain the sound emitted during the operation of the transformer, the sound including: multiple audio signals collected by the sound pickup device.

[0038] In step 100 above, after the monitoring device acquires the multiple audio signals collected by the sound pickup device, it first performs analog-to-digital conversion and noise reduction on the multiple audio signals, and then sends the preprocessed multiple audio signals to the processor for further processing.

[0039] The monitoring equipment can perform analog-to-digital conversion and noise reduction on multiple audio signals using existing technologies, which will not be elaborated here.

[0040] Step 102: Process each audio signal in the multi-channel audio signal to obtain the sound intensity feature value of each audio signal and the feature quantity of the sound signal to be detected; wherein, the sound intensity feature value is used to characterize the time domain intensity of each audio signal.

[0041] In step 102 above, in order to obtain the sound intensity characteristic values ​​of each audio signal, the processor can perform the following steps:

[0042] Multiple variance operations are performed on each audio signal to obtain multiple variance operation results for each audio signal. Then, the multiple variance operation results for each audio signal are weighted and processed to obtain the sound intensity characteristic value of each audio signal.

[0043] In one embodiment of the above steps, the variance calculations of each audio signal can be performed four times, wherein the first positive variance calculation is performed with an interval of 0, the second positive variance calculation is performed with an interval of 1, the third negative variance calculation is performed with an interval of 1, and the fourth positive variance calculation is performed with an interval of 2.

[0044] Forward variance calculation refers to the process by which the processor performs variance processing on each audio signal in the order in which they are input into the processor.

[0045] Inverse variance calculation refers to the process by which the processor performs variance processing on each audio signal in reverse order of the order in which they were input into the processor.

[0046] Interval refers to the number of binary numbers between each audio signal; an interval of 0 means that the number of binary numbers between each audio signal is 0; an interval of n means that the number of binary numbers between each audio signal is n, where n is a natural number.

[0047] In the process of weighted calculation of multiple variance results of each audio signal, in order to ensure the accuracy of the transformer fault type determined by the transformer operation monitoring method proposed in this embodiment, it is necessary to assign weights to the four variance calculation results of each audio signal. The weighting method is as follows:

[0048] The weight of the first positive variance calculation result of each audio signal is much greater than the weight of the subsequent three variance calculation results of each audio signal, and the weight of the second positive variance calculation result of each audio signal should be greater than the weight of the third negative variance calculation result of each audio signal and the weight of the fourth positive variance calculation result of each audio signal.

[0049] For example, the weight of the first positive variance calculation result of each audio signal can be set to 0.8; the weight of the second positive variance calculation result of each audio signal can be set to 0.1; and the weight of the third negative variance calculation result of each audio signal and the weight of the fourth positive variance calculation result of each audio signal can be set to 0.05 respectively.

[0050] The specific process of averaging and weighting the variance calculation results of each audio signal to obtain the sound intensity characteristic value of each audio signal can be carried out using existing average weighting calculation techniques, which will not be elaborated here.

[0051] In order to obtain the feature quantity of the sound signal to be detected, the processor can also perform the following steps (1) to (5): (1) Process the multiple audio signals using a non-average algorithm to obtain the sound signal to be detected;

[0052] (2) Filter the sound signal to be detected to obtain the filtered sound signal;

[0053] (3) Perform a 90-degree phase shift on the filtered signal to obtain the phase shift signal of the sound signal;

[0054] (4) Perform mapping transformation on the phase-shifted signal to obtain the mapping result of the sound signal, and perform Fourier transformation on the mapping result to obtain the spectrum signal of the sound signal;

[0055] (5) Process the spectral signal of the sound signal to obtain the characteristic quantity of the sound signal.

[0056] In step (1) above, in order to process the multiple audio signals using a non-average algorithm to obtain the sound signal to be detected, the following steps (11) to (12) can be performed:

[0057] (11) Perform mapping conversion on the multiple audio signals to obtain multiple mapped signals;

[0058] (12) Perform weighted operations on the multi-path mapped signals to obtain the sound signal to be detected.

[0059] In step (11) above, in order to enhance the weak signals in the multi-channel audio signals and facilitate the subsequent extraction of the weak signals in the multi-channel audio signals, a logarithmic curve 0.23*ln(1+71) is selected. x ) is used as a mapping function.

[0060] The specific process of mapping and converting multiple audio signals to obtain multiple mapped signals can be carried out using existing techniques for mapping and converting multiple audio signals, which will not be elaborated here.

[0061] In step (12) above, the multi-path mapping signals are weighted to obtain the sound signal to be detected. The existing weighting operation process can be used, which will not be elaborated here.

[0062] In one embodiment, in order to ensure the accuracy of the transformer fault type determined by the transformer operation monitoring method proposed in this embodiment, during the weighted operation of the multi-path mapping signals, a weight of 0.8 is assigned to the mapping signal with the largest frequency amplitude among the multi-path mapping signals, and the remaining weight of 0.2 is evenly assigned to the other mapping signals among the multi-path mapping signals excluding the mapping signal with the largest frequency amplitude.

[0063] In step (2) above, in one embodiment, the filtering range for filtering the audio signal is 50 Hz to 20000 Hz in order to filter out noise in the audio signal.

[0064] The processor uses a filtering algorithm to filter the audio signal, resulting in a filtered audio signal.

[0065] The processor uses a filtering algorithm to filter the audio signal. The specific process of obtaining the filtered audio signal can be carried out using existing techniques for filtering audio signals, which will not be elaborated here.

[0066] In step (3) above, in order to extract the frequency components of the signal more effectively, the filtered signal is subjected to a 90-degree phase shift to obtain the phase shift signal of the sound signal.

[0067] In step (4) above, in the process of mapping and converting the phase-shifted signal to obtain the mapping result of the sound signal, in order to perform nonlinear filtering on the phase-shifted signal, the sign function is selected as the mapping function.

[0068] The specific process of mapping and converting phase-shifted signals to obtain the mapped sound signals can be carried out using existing mapping and conversion techniques, which will not be elaborated here.

[0069] In step (5) above, the characteristic quantities of the sound signal include: the specific frequency of the sound signal to be detected, the peak value of the reference frequency band of the sound signal to be detected, the peak-to-frequency ratio of the sound signal to be detected, and the number of specific frequencies of the sound signal to be detected.

[0070] To obtain the feature quantities of the sound signal to be detected, the following steps (51) to (54) can be performed:

[0071] (51) Extract the reference frequency of the transformer operation from the spectrum signal of the sound signal to be detected, perform a frequency multiplication operation on the reference frequency, and determine at least two specific frequencies;

[0072] (52) Based on the obtained reference frequency, determine the amplitude of the reference frequency, and determine the amplitude of the reference frequency as the reference frequency peak value of the sound signal to be detected;

[0073] (53) Determine the amplitude of each specific frequency among the at least two specific frequencies, and calculate the peak-to-peak ratio of each specific frequency by dividing the amplitude of each specific frequency by the amplitude of the reference frequency, and determine the calculated peak-to-peak ratio of each specific frequency as the peak-to-peak ratio of the sound signal to be detected.

[0074] (54) Among the at least two specific frequencies, the specific frequency with a peak-to-peak ratio greater than the peak-to-peak ratio threshold is determined as the specific frequency of the sound signal to be detected, and the number of specific frequencies of the sound signal to be detected is counted.

[0075] In step (51) above, in one embodiment, those skilled in the art of transformers will know that the reference frequency of the transformer is twice the frequency of the national power grid, which is 100 Hz.

[0076] Depending on the type of fault, at least two specific frequencies are required, which can be: 300 Hz, 500 Hz, and 700 Hz. Alternatively, they can be: 200 Hz, 300 Hz, 400 Hz, and 500 Hz.

[0077] Of course, in addition to at least two specific frequencies, other reference frequencies can be selected as multipliers based on other fault types, which will not be elaborated here.

[0078] In step (52) above, the specific process of determining the amplitude of the reference frequency based on the obtained reference frequency can be carried out by existing techniques for amplitude extraction from signal frequency, which will not be elaborated here.

[0079] In step (53) above, the specific process of determining the amplitude of each of the at least two specific frequencies can be carried out using existing techniques for amplitude extraction from signal frequencies, which will not be elaborated here.

[0080] In step (54) above, the peak-to-frequency ratio threshold is pre-cached in the processor.

[0081] Optionally, after obtaining the sound intensity characteristic values ​​of each audio signal and the characteristic quantities of the sound signal to be detected through step 102 above, the singularity detection method commonly used in the field of signal processing can also be used to obtain the singularity characteristic values ​​of each audio signal. In the transformer operation monitoring method proposed in this embodiment, the singularity characteristic values ​​of each audio signal can also be obtained through the following steps:

[0082] Singularity detection is performed on each of the multiple audio signals included in the sound to obtain the singularity feature value of each audio signal.

[0083] In the above steps, the processor performs singularity detection on each audio signal and obtains the singularity feature value of each audio signal. The specific process can be carried out using existing techniques for obtaining the singularity feature value of each audio signal, which will not be elaborated here.

[0084] Of course, the process of obtaining the singularity feature values ​​of each audio signal can also be performed before step 102 to obtain the sound intensity feature values ​​of each audio signal and the feature quantity of the sound signal to be detected. In this embodiment, the order of obtaining the singularity feature values ​​of each audio signal and step 102 to obtain the sound intensity feature values ​​of each audio signal and the feature quantity of the sound signal to be detected is not limited.

[0085] After obtaining the sound intensity characteristic values ​​of each audio signal and the characteristic quantities of the sound signal to be detected through the above step 102, the following step 104 can be performed to determine the fault type of the transformer.

[0086] Step 104: In response to confirming that the sound signal is an abnormal noise, determine that the transformer has a fault, and determine the fault type of the transformer by using the sound intensity characteristic values ​​of each audio signal and the characteristic quantity of the sound signal to be detected.

[0087] Specifically, in order to determine that a transformer has failed, step 104 above can be performed by following steps (1) to (2):

[0088] (1) Compare the statistically obtained number of specific frequencies with the numerical value of the number threshold to obtain the comparison result;

[0089] (2) When the comparison result indicates that the number of the specific frequency is greater than the number threshold, it is determined that the sound signal is abnormal and that the transformer has failed.

[0090] In step (1) above, the quantity threshold is pre-cached in the processor.

[0091] After confirming that the transformer has failed, step 104 above can also perform the following steps (3) to (4):

[0092] (3) Input the sound intensity feature value and singularity feature value of each audio signal and the feature quantity of the sound signal into the pre-trained transformer fault classification model. Process the sound intensity feature value and singularity feature value of each audio signal and the feature quantity of the sound signal through the transformer fault classification model to determine the fault type of the transformer.

[0093] (4) When the comparison result indicates that the number of the specific frequency is less than or equal to the number threshold, the result is that the sound signal is a normal sound and the process ends.

[0094] In step (3) above, the pre-trained transformer fault classification model runs in the processor.

[0095] The transformer fault classification model is obtained by inputting known transformer fault types and matching audio signals into a deep learning computational model and training the deep learning computational model.

[0096] The specific process of inputting the transformer fault type and the matched audio signal into an existing deep learning computing model and training the deep learning computing model to obtain a transformer fault classification model can be carried out using existing techniques for training deep learning computing models, which will not be elaborated here.

[0097] The specific process of determining the fault type of the transformer by processing the sound intensity feature value, singularity feature value, and sound signal feature quantity of each audio signal through the transformer fault classification model can be achieved by using existing deep learning computing models to classify the fault types of the transformer, which will not be elaborated here.

[0098] Transformer fault types include, but are not limited to: core vibration fault, winding vibration fault, tank wall vibration fault, and bearing fault.

[0099] After determining the transformer's fault type, the processor uses a wireless communication module to send the determined fault type and the acquired multi-channel audio signals back to the cloud server.

[0100] In summary, this embodiment proposes a transformer operation monitoring method. By processing the audio signals from multiple audio signals collected by a sound pickup device during the transformer's operation, the method obtains the sound intensity characteristic values ​​of each audio signal and the characteristic quantity of the sound signal to be detected, thus initially identifying whether the sound signal is an abnormal noise. In response to confirming that the sound signal to be detected is an abnormal noise, the method determines that the transformer has a fault. Furthermore, by using the sound intensity characteristic values ​​of each audio signal and the characteristic quantity of the sound signal to be detected, the method determines the type of transformer fault. Compared with related technologies that rely on experienced workers to inspect and listen for sounds to determine transformer faults, this method, by processing the audio signals from multiple audio signals collected by the sound pickup device during the transformer's operation and obtaining the sound intensity characteristic values ​​of each audio signal and the characteristic quantity of the sound signal to be detected, can determine whether the transformer has a fault, achieving the goal of determining whether a transformer has a fault without manual inspection. Moreover, it allows for continuous detection of faults generated during transformer operation, greatly improving the efficiency of transformer fault detection.

[0101] Example 2

[0102] This embodiment proposes a transformer operation monitoring device for executing the transformer operation monitoring method proposed in Embodiment 1.

[0103] See Figure 2 The diagram shows the structure of a transformer operation monitoring device. This embodiment proposes a transformer operation monitoring device, comprising:

[0104] The acquisition module 200 is used to acquire the sound emitted during the operation of the transformer, the sound including: multiple audio signals collected by the sound pickup device;

[0105] The processing module 202 is used to process each audio signal in the multi-channel audio signal to obtain the sound intensity feature value of each audio signal and the feature quantity of the sound signal to be detected; wherein, the sound intensity feature value is used to characterize the time domain intensity of each audio signal.

[0106] The determination module 204 is used to determine that the transformer has a fault in response to the abnormal noise of the sound signal to be detected, and to determine the fault type of the transformer by using the sound intensity characteristic values ​​of each audio signal and the characteristic quantity of the sound signal to be detected.

[0107] Specifically, the processing module is used to process each audio signal in the multi-channel audio signals to obtain the sound intensity characteristic value of each audio signal, including:

[0108] Multiple variance operations are performed on each audio signal to obtain multiple variance operation results for each audio signal. Then, the multiple variance operation results for each audio signal are weighted and processed to obtain the sound intensity characteristic value of each audio signal.

[0109] In summary, this embodiment proposes a transformer operation monitoring device. By processing the audio signals from multiple audio signals collected by a sound pickup device during the transformer's operation, the device obtains the sound intensity characteristic values ​​of each audio signal and the characteristic quantity of the sound signal to be detected, thus initially identifying whether the sound signal is an abnormal noise. In response to the detection of an abnormal noise, the device determines that the transformer has a fault. Furthermore, it uses the sound intensity characteristic values ​​of each audio signal and the characteristic quantity of the sound signal to determine the type of transformer fault. Compared to related technologies that rely on experienced workers to inspect and listen for sounds to determine transformer faults, this device, by processing the audio signals from multiple audio signals collected by the sound pickup device during the transformer's operation and obtaining the sound intensity characteristic values ​​of each audio signal and the characteristic quantity of the sound signal to be detected, can determine whether the transformer has a fault. This achieves the goal of determining whether a transformer has a fault without manual inspection. Moreover, it can continuously detect faults generated during transformer operation, greatly improving the efficiency of transformer fault detection.

[0110] Example 3

[0111] This embodiment proposes a computer-readable storage medium storing a computer program. When the computer program is run by a processor, it executes the steps of the transformer operation monitoring method described in Embodiment 1 above. For specific implementation details, please refer to Method Embodiment 1, which will not be repeated here.

[0112] In addition, see Figure 3 The diagram shows the structure of an electronic device. This embodiment also proposes an electronic device, which includes a bus 51, a processor 52, a transceiver 53, a bus interface 54, a memory 55, and a user interface 56. The electronic device includes a memory 55.

[0113] In this embodiment, the electronic device further includes: one or more programs stored in the memory 55 and executable on the processor 52, configured to be executed by the processor to perform the one or more programs for steps (1) to (3):

[0114] (1) Acquire the sound emitted during the operation of the transformer, wherein the sound includes: multiple audio signals collected by the sound pickup device;

[0115] (2) Process each audio signal in the multi-channel audio signal to obtain the sound intensity feature value of each audio signal and the feature quantity of the sound signal to be detected; wherein, the sound intensity feature value is used to characterize the time domain intensity of each audio signal.

[0116] (3) In response to confirming that the sound signal to be detected is an abnormal noise, the transformer is determined to have a fault, and the fault type of the transformer is determined by using the sound intensity characteristic value of each audio signal and the characteristic quantity of the sound signal to be detected.

[0117] Transceiver 53 is used to receive and send data under the control of processor 52.

[0118] The bus architecture (represented by bus 51) can include any number of interconnected buses and bridges, linking various circuits including one or more processors represented by processor 52 and memory represented by memory 55. Bus 51 can also link various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be further described in this embodiment. Bus interface 54 provides an interface between bus 51 and transceiver 53. Transceiver 53 can be a single element or multiple elements, such as multiple receivers and transmitters, providing a unit for communicating with various other devices over a transmission medium. For example, transceiver 53 receives external data from other devices. Transceiver 53 is used to transmit data processed by processor 52 to other devices. Depending on the nature of the computing system, a user interface 56 may also be provided, such as a keypad, display, speaker, microphone, or joystick.

[0119] Processor 52 is responsible for managing bus 51 and general processing, such as running general-purpose operating system 551 as described above. Memory 55 can be used to store data used by processor 52 during operation.

[0120] Optionally, the processor 52 may be, but is not limited to, a central processing unit, a microcontroller, a microprocessor, or a programmable logic device.

[0121] It is understood that the memory 55 in the embodiments of this application can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), Synchronous DRAM (SDRAM), Double Data Rate Synchronous DRAM (DDRSDRAM), Enhanced Synchronous DRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), and Direct Rambus RAM (DRRAM). The memory 55 of the systems and methods described in this embodiment is intended to include, but is not limited to, these and any other suitable types of memory.

[0122] In some implementations, memory 55 stores elements such as executable modules or data structures, or subsets thereof, or extended sets thereof: operating system 551 and application programs 552.

[0123] The operating system 551 includes various system programs, such as the framework layer, core library layer, and driver layer, used to implement various basic business functions and handle hardware-based tasks. The application program 552 includes various applications, such as a media player and a browser, used to implement various application functions. Programs implementing the methods of the embodiments of this application can be included in the application program 552.

[0124] In summary, this embodiment proposes a computer-readable storage medium and electronic device. By processing the audio signals from multiple audio signals collected by a sound pickup device during the transformer's operation, the intensity characteristic values ​​of each audio signal and the characteristic quantity of the sound signal to be detected are obtained, initially identifying whether the sound signal is an abnormal noise. In response to the sound signal being an abnormal noise, a transformer fault is determined, and the fault type of the transformer is determined using the intensity characteristic values ​​of each audio signal and the characteristic quantity of the sound signal to be detected. Compared with the related technology of dispatching experienced workers to inspect and listen for sounds to determine transformer faults, by processing the audio signals from multiple audio signals collected by the sound pickup device during the transformer's operation and obtaining the intensity characteristic values ​​of each audio signal and the characteristic quantity of the sound signal to be detected, the fault of the transformer can be determined, achieving the goal of determining whether the transformer is faulty without manual inspection. Moreover, faults generated during transformer operation can be detected continuously, greatly improving the fault detection efficiency of the transformer.

[0125] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for monitoring transformer operation, characterized in that, include: Acquire the sound emitted during the operation of the transformer, the sound including: multiple audio signals collected by a sound pickup device; Each audio signal in the multi-channel audio signal is processed to obtain the sound intensity feature value of each audio signal and the feature quantity of the sound signal to be detected; wherein, the sound intensity feature value is used to characterize the time domain intensity of each audio signal. The characteristic quantities of the sound signal to be detected include: A non-average algorithm is used to process multiple audio signals to obtain the sound signal to be detected; The sound signal to be detected is filtered to obtain the filtered signal of the sound signal to be detected; The filtered signal is subjected to a 90-degree phase shift to obtain the phase-shifted signal of the sound signal to be detected; The phase-shifted signal is mapped and converted to obtain the mapping result of the sound signal to be detected, and the mapping result is Fourier transformed to obtain the spectral signal of the sound signal to be detected. The spectral signal of the sound signal to be detected is processed to obtain the feature quantity of the sound signal to be detected; The characteristic quantities of the sound signal to be detected include: a specific frequency of the sound signal to be detected, a reference frequency peak value of the sound signal to be detected, a frequency-to-peak ratio of the sound signal to be detected, and a number of specific frequencies of the sound signal to be detected. The spectral signal of the sound signal to be detected is processed to obtain the feature quantities of the sound signal to be detected, including: The reference frequency for transformer operation is extracted from the spectral signal of the sound signal to be detected, and the reference frequency is multiplied to determine at least two specific frequencies. Based on the obtained reference frequency, the amplitude of the reference frequency is determined, and the amplitude of the reference frequency is determined as the reference frequency peak value of the sound signal to be detected. The amplitude of each specific frequency among the at least two specific frequencies is determined, and the peak-to-peak ratio of each specific frequency is calculated by dividing the amplitude of each specific frequency by the amplitude of the reference frequency. The calculated peak-to-peak ratio of each specific frequency is then determined as the peak-to-peak ratio of the sound signal to be detected. Among the at least two specific frequencies, the specific frequency with a peak-to-peak ratio greater than the peak-to-peak ratio threshold is determined as the specific frequency of the sound signal to be detected, and the number of specific frequencies of the sound signal to be detected is counted. In response to confirming that the sound signal to be detected is an abnormal noise, and determining that the transformer has a fault, the fault type of the transformer is determined by using the sound intensity characteristic values ​​of each audio signal and the characteristic quantity of the sound signal to be detected.

2. The method according to claim 1, characterized in that, The audio signals from the multiple audio signals are processed to obtain the sound intensity characteristic values ​​of each audio signal, including: Multiple variance operations are performed on each audio signal to obtain multiple variance operation results for each audio signal. Then, the multiple variance operation results for each audio signal are weighted and processed to obtain the sound intensity feature value of each audio signal.

3. The method according to claim 1, characterized in that, In response to confirming that the sound signal is an abnormal noise, determining that the transformer has malfunctioned includes: The statistically obtained number of specific frequencies is compared with the value of the quantity threshold to obtain the comparison result; When the comparison result indicates that the number of specific frequencies is greater than the number threshold, it is determined that the sound signal is abnormal and that the transformer has malfunctioned.

4. The method according to claim 1, characterized in that, After acquiring the sound emitted during transformer operation, the method further includes: Singularity detection is performed on each of the multiple audio signals included in the sound to obtain the singularity feature value of each audio signal; Determining the fault type of the transformer using the sound intensity feature values ​​of each audio signal and the feature quantity of the sound signal to be detected includes: inputting the sound intensity feature values ​​and singularity feature values ​​of each audio signal and the feature quantity of the sound signal to be detected into a pre-trained transformer fault classification model; processing the sound intensity feature values ​​and singularity feature values ​​of each audio signal and the feature quantity of the sound signal through the transformer fault classification model to determine the fault type of the transformer.

5. A transformer operation monitoring device, characterized in that, include: The acquisition module is used to acquire the sound emitted during the operation of the transformer, the sound including: multiple audio signals collected by the sound pickup device; The processing module is used to process each audio signal in the multi-channel audio signals to obtain the sound intensity feature values ​​of each audio signal and the feature quantities of the sound signal to be detected; wherein, the sound intensity feature values ​​are used to characterize the time-domain intensity of each audio signal; wherein, obtaining the feature quantities of the sound signal to be detected includes: processing the multi-channel audio signals using a non-average algorithm to obtain the sound signal to be detected; filtering the sound signal to be detected to obtain a filtered signal of the sound signal to be detected; performing a 90-degree phase shift processing on the filtered signal to obtain a phase-shifted signal of the sound signal to be detected; performing a mapping transformation on the phase-shifted signal to obtain a mapping result of the sound signal to be detected, and performing a Fourier transform on the mapping result to obtain a spectral signal of the sound signal to be detected; processing the spectral signal of the sound signal to be detected to obtain the feature quantities of the sound signal to be detected; wherein, the feature quantities of the sound signal to be detected include: a specific frequency of the sound signal to be detected, a reference frequency of the sound signal to be detected, and a reference frequency of the sound signal to be detected. The method involves processing the spectrum of the sound signal to be detected to obtain characteristic quantities, including: extracting the reference frequency of the transformer operation from the spectrum of the sound signal to be detected; performing a frequency multiplication operation on the reference frequency to determine at least two specific frequencies; determining the amplitude of the reference frequency based on the obtained reference frequency, and determining the amplitude of the reference frequency as the reference frequency peak value of the sound signal to be detected; determining the amplitude of each specific frequency among the at least two specific frequencies, and calculating the peak-to-frequency ratio of each specific frequency by dividing the amplitude of each specific frequency by the amplitude of the reference frequency, and determining the calculated peak-to-frequency ratio of each specific frequency as the peak-to-frequency ratio of the sound signal to be detected; and determining the specific frequencies among the at least two specific frequencies whose peak-to-frequency ratio is greater than the peak-to-frequency ratio threshold as the specific frequencies of the sound signal to be detected, and counting the number of specific frequencies of the sound signal to be detected. The determination module is used to determine the transformer fault in response to confirming that the sound signal to be detected is an abnormal noise, and to determine the fault type of the transformer by using the sound intensity characteristic values ​​of each audio signal and the characteristic quantity of the sound signal to be detected.

6. The apparatus according to claim 5, characterized in that, The processing module is used to process each audio signal in the multi-channel audio signal to obtain the sound intensity characteristic value of each audio signal, including: Multiple variance operations are performed on each audio signal to obtain multiple variance operation results for each audio signal. Then, the multiple variance operation results for each audio signal are weighted and processed to obtain the sound intensity characteristic value of each audio signal.

7. A computer-readable storage medium storing a computer program thereon, characterized in that, When the computer program is run by the processor, it performs the steps of the method described in any one of claims 1-4.

8. An electronic device, characterized in that, The electronic device includes a memory, a processor, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor of the steps of the method according to any one of claims 1-4.

Images