Transformer diagnosis method and system based on acoustic signals

Abstract

The invention provides a transformer diagnosis method and system based on an acoustic signal, and belongs to the technical field of sound recognition, and the method specifically comprises the steps: taking the operation data of a transformer in different operation load intervals as the basis, carrying out the determination of the operation load interval of the acoustic fault diagnosis of the transformer, taking the operation load interval as a fault monitoring interval, and carrying out the fault diagnosis of the transformer; and when it is determined that the operation state of the transformer is suspected to be abnormal based on the diagnosis data of the acoustic signal of the transformer in the fault monitoring load interval, determining a control strategy of a heat dissipation device in an operation load interval not belonging to the fault monitoring interval according to the operation load data of the transformer in a future preset time period, and the reliability degree of diagnosis and processing of the fault of the transformer is improved.

Description

Technical Field

[0001] This invention belongs to the field of sound recognition technology, and in particular relates to a transformer diagnosis method and system based on acoustic signals. Background Technology

[0002] To utilize acoustic signals for transformer diagnostic processing, the invention patent application CN202310866686.1, "Transformer Spectral Feature Enhancement Method and System Based on Weight Allocation," analyzes and processes information such as the amplitude and bandwidth of frequency components in the original signal spectrum. This results in a method that can analyze reference weights for different frequencies based on the actual spectrum, thereby guiding spectral feature enhancement. This method optimizes the current model for state recognition using transformer acoustic signatures and effectively improves the accuracy of state recognition.

[0003] When the transformer's heat dissipation device is turned on, it inevitably causes some noise interference to the diagnostic model used for fault diagnosis. Therefore, how to determine the control strategy of the transformer's heat dissipation device based on the fault monitoring data when the transformer's heat dissipation device is not turned on, so as to improve the reliability of fault identification of the transformer in the suspected fault state, has become an urgent technical problem to be solved.

[0004] To address the aforementioned technical problems, this application provides a transformer diagnostic method and system based on acoustic signals. Summary of the Invention

[0005] To achieve the objectives of this invention, the following technical solution is adopted: Specifically, this application provides a transformer diagnostic method based on acoustic signals, which includes: S1 uses the analysis results of the acoustic signal of the transformer to determine that the heat dissipation device of the transformer is in the open state and the noise impact data. Based on the noise impact data, when it is determined that the operating load data of the transformer needs to be considered, the operating load range for acoustic fault diagnosis of the transformer is determined based on the operating data of the transformer in different operating load ranges, and this range is used as the fault monitoring range. S2 determines, based on the diagnostic data of the acoustic signals of the transformer within the fault monitoring load range, that the transformer's operating status is suspected to be abnormal. Then, based on the operating load data of the transformer in a future preset period, S2 determines the control strategy for the heat dissipation device in the operating load range that does not belong to the fault monitoring range.

[0006] The beneficial effects of this invention are as follows: Based on the operating data of the transformer in different operating load ranges, the operating load range for acoustic fault diagnosis of the transformer is determined. This enables the determination of the fault monitoring range by analyzing the frequency of the heat dissipation device's activation in different operating load ranges and the duration of operation in the operating load range where the heat dissipation device is activated more frequently. This not only reduces the impact of the heat dissipation device's activation on the transformer's fault identification results, but also ensures that the transformer can identify faults in multiple operating load ranges, thus improving the reliability of fault identification and processing.

[0007] Based on the transformer's operating load data for a future preset period, a control strategy for the heat dissipation device is determined within the operating load range that is not within the fault monitoring range. This addresses the technical problem of poor reliability in fault diagnosis and handling when the transformer is in a suspected abnormal state due to the short operating time of the fault monitoring range. By controlling the heat dissipation device within the operating load range that is not within the fault monitoring range, the reliability and timeliness of fault diagnosis and handling are improved.

[0008] Furthermore, the noise impact data is determined based on the filtering results of the acoustic signal from the sound sensor.

[0009] Furthermore, it is necessary to determine the transformer's operating load data, specifically including: Based on the noise impact data, it was determined that the transformer's heat dissipation device was in the on state, and the noise signal was monitored by the sound sensor. Based on the analysis results of the noise signal, the signal-to-noise ratio of the transformer's heat dissipation device when it is in the on state is determined; Based on the signal-to-noise ratio, determine whether the transformer's operating load data needs to be considered.

[0010] Furthermore, the method for determining the control strategy of the heat dissipation device within the operating load range is as follows: Based on the operating load data of the transformer in a future preset period, the operating time in different fault monitoring intervals in the future preset period is determined; The operating load range that does not belong to the fault monitoring data is regarded as the unmonitored range. Based on the operating load data of the transformer in the future preset period, the operating time in the unmonitored range in the future preset period is determined. Based on the runtime in different fault monitoring intervals and the runtime in the unmonitored intervals within a future preset time period, a control strategy for the heat dissipation device in the unmonitored intervals is determined.

[0011] In a second aspect, the present invention provides a computer system comprising: a memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the aforementioned transformer diagnosis method based on acoustic signals when running the computer program.

[0012] Other features and advantages will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention are realized and obtained through the structures particularly pointed out in the description and the drawings.

[0013] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0014] The above and other features and advantages of the present invention will become more apparent from a detailed description of exemplary embodiments thereof with reference to the accompanying drawings.

[0015] Figure 1 This is a flowchart of a transformer diagnostic method based on acoustic signals; Figure 2 This is a flowchart illustrating the method for determining the operating load data of the transformer that needs to be considered. Figure 3 This is a flowchart illustrating the method for determining the fault monitoring range. Detailed Implementation

[0016] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the embodiments set forth herein; rather, they are provided so that the invention will be thorough and complete, and the concept of the exemplary embodiments will be fully conveyed to those skilled in the art. The same reference numerals in the drawings denote the same or similar structures, and therefore their detailed description will be omitted.

[0017] The terms “a,” “one,” “the,” and “the” are used to indicate the existence of one or more elements / components / etc.; the terms “including” and “having” are used to indicate an open-ended meaning of inclusion and that there may be other elements / components / etc. in addition to the listed elements / components / etc.

[0018] Example 1 To solve the above problems, according to one aspect of the present invention, such as Figure 1 As shown, a transformer diagnostic method based on acoustic signals is provided, specifically including: S1 uses the analysis results of the acoustic signal of the transformer to determine that the heat dissipation device of the transformer is in the open state and the noise impact data. Based on the noise impact data, when it is determined that the operating load data of the transformer needs to be considered, the operating load range for acoustic fault diagnosis of the transformer is determined based on the operating data of the transformer in different operating load ranges, and this range is used as the fault monitoring range. Furthermore, the noise impact data is determined based on the filtering results of the acoustic signal from the sound sensor.

[0019] Specifically, such as Figure 2 As shown, the operating load data of the transformer that needs to be considered includes: Based on the noise impact data, it was determined that the transformer's heat dissipation device was in the on state, and the noise signal was monitored by the sound sensor. Based on the analysis results of the noise signal, the signal-to-noise ratio of the transformer's heat dissipation device when it is in the on state is determined; Based on the signal-to-noise ratio, determine whether the transformer's operating load data needs to be considered.

[0020] It is understandable that when the average signal-to-noise ratio at different monitoring times is less than the preset signal-to-noise ratio threshold, such as less than 30dB, when the heat dissipation device of the transformer is in the on state, the influence of noise is relatively high. Therefore, it is determined that the operating load data of the transformer needs to be considered.

[0021] Optionally, determine which transformer operating load data needs to be considered, specifically including: Based on the noise impact data, it was determined that the transformer's heat dissipation device was in the on state, and the noise signal was monitored by the sound sensor. Based on the analysis results of the noise signal, the signal-to-noise ratio of the transformer's heat dissipation device when it is in the on state is determined; Based on the signal-to-noise ratio, the signal-to-noise ratio at monitoring times in different operating load ranges is determined, and based on the signal-to-noise ratio at monitoring times in different operating load ranges, it is determined whether the transformer's operating load data needs to be considered.

[0022] It is understandable that when there are multiple operating load ranges where the average signal-to-noise ratio at multiple monitoring times is less than the preset signal-to-noise ratio threshold, it is determined that the transformer's operating load data needs to be considered.

[0023] Furthermore, the operating load range is divided into a preset number of operating load ranges according to the historical operating load range of the transformer, in an equally spaced manner. In one possible embodiment, the preset number is 10.

[0024] Specifically, such as Figure 3 As shown, the method for determining the fault monitoring interval is as follows: Based on the operating data of the transformer in different operating load ranges, the activation data of the heat dissipation device in different operating load ranges are determined; Based on the activation data, determine the frequently activated load range of the heat dissipation device within the operating load range; Based on the operating data of the frequently activated load range and the activation data of the heat dissipation device within the operating load range, it is determined whether the operating load range is a fault monitoring range.

[0025] Specifically, the activation data refers to the historical runtime of the cooling device being in the activated state within the operating load range.

[0026] Furthermore, the frequently activated load range is the operating load range in which the duration of operation of the heat dissipation device in the activated state in history does not meet the requirements. In one possible embodiment, if the proportion of the duration of operation of the heat dissipation device in the activated state in history within the operating load range is greater than a preset threshold, such as 0.6, then the operating load range is determined to be a frequently activated load range.

[0027] It should be noted that when the operating data of the frequently opened load range does not meet the requirements, that is, when the total operating time of different frequently opened load ranges in history accounts for a greater than the proportion of the transformer's operating time in the history, the operating time of the frequently opened load range is too long. In order to ensure the reliability of fault monitoring, analysis and processing, all operating load ranges that do not belong to the frequently opened load range are determined to belong to the fault monitoring range.

[0028] Furthermore, when the operating data of the frequently activated load range meets the requirements, the activation data of the heat dissipation device within the operating load range is determined. If there is no historical period in the operating load range during which the heat dissipation device is activated, then the operating load range is determined to belong to the fault monitoring range.

[0029] Furthermore, when there are periods in the history where the heat dissipation device is in the on state within the operating load range, the maximum value of the duration of the period in the operating load range where the heat dissipation device is in the on state is determined. If the maximum value of the duration of the period in the history where the heat dissipation device is in the on state within the operating load range does not meet the requirements, for example, if it is greater than a preset duration threshold, then the operating load range is determined not to belong to the fault monitoring range.

[0030] Additionally, it should be noted that if the maximum duration of the time when the heat dissipation device is in the on state within the operating load range meets the requirements, then the operating load range belonging to the fault monitoring range is determined. The proportion of the operating time of all operating load ranges belonging to the fault monitoring range in history to the operating time of the transformer is used as the monitoring matching coefficient. When the monitoring matching coefficient is greater than the preset matching coefficient threshold, then the operating load range is determined not to belong to the fault monitoring range.

[0031] Furthermore, when the monitoring matching coefficient is not greater than the preset matching coefficient threshold, the proportion of the total time the heat dissipation device is in the on state within the operating load range to the total operating time within the operating load range is determined based on the total time the heat dissipation device is in the on state within the operating load range, and this proportion is used as the heat dissipation activation coefficient. When the heat dissipation activation coefficient within the operating load range is less than the preset activation coefficient threshold, the operating load range is determined to belong to the fault monitoring range.

[0032] It can also be understood that when the heat dissipation activation coefficient within the operating load range is not less than the preset activation coefficient threshold, the operating load range is determined not to belong to the fault monitoring range.

[0033] S2 determines, based on the diagnostic data of the acoustic signals of the transformer within the fault monitoring load range, that the transformer's operating status is suspected to be abnormal. Then, based on the operating load data of the transformer in a future preset period, S2 determines the control strategy for the heat dissipation device in the operating load range that does not belong to the fault monitoring range.

[0034] Furthermore, it was determined that the transformer's operating status exhibited suspected abnormalities, specifically including: Based on the diagnostic data of the acoustic signals of the transformer within the fault monitoring load range, when it is determined that the operating status of the transformer is suspected of being abnormal... Based on the diagnostic data of the acoustic signals of the transformer within the fault monitoring load range, the time period during which a transformer fault was detected within the fault monitoring load range is determined and designated as a suspected abnormal time period. Based on data from suspected abnormal periods within different fault monitoring load ranges, it is determined whether the transformer's operating status exhibits any suspected abnormalities.

[0035] It should be noted that the time period during which the transformer fault was detected is the time period with fault monitoring time, where the fault monitoring time is the time when the output result of the acoustic diagnostic model indicates that a fault exists.

[0036] Specifically, the acoustic diagnostic model is constructed based on a neural network model, which can be constructed using one or more of the following: BP neural network, Hopfield network, ART network, and Kohonen network. The neural network model takes the frequency features extracted from the acoustic signal as input and outputs whether the transformer has a fault.

[0037] It should be noted that, based on data from suspected abnormal periods within different fault monitoring load ranges, the determination of whether the transformer's operating status exhibits suspected abnormalities specifically includes: Based on the data of suspected abnormal periods in different fault monitoring load intervals, the fault monitoring load intervals with suspected abnormal periods are determined. If there are suspected abnormal periods in different fault monitoring load ranges, it is determined that the transformer's operating status is abnormal. If there are suspected abnormal periods in different fault monitoring load ranges, and if there are no suspected abnormal periods in any of the different fault monitoring load ranges, then it is determined that the operating status of the transformer is not suspected of being abnormal. If there is a fault monitoring load range with a suspected abnormal period, then the operating status of the transformer is determined to be suspected abnormal.

[0038] It should be noted that when the transformer's operating status is abnormal, a warning signal will be output directly.

[0039] Furthermore, the method for determining the control strategy of the heat dissipation device within the operating load range is as follows: Based on the operating load data of the transformer in a future preset period, the operating time in different fault monitoring intervals in the future preset period is determined; The operating load range that does not belong to the fault monitoring data is regarded as the unmonitored range. Based on the operating load data of the transformer in the future preset period, the operating time in the unmonitored range in the future preset period is determined. Based on the runtime in different fault monitoring intervals and the runtime in the unmonitored intervals within a future preset time period, a control strategy for the heat dissipation device in the unmonitored intervals is determined.

[0040] Furthermore, the operating load data of the transformer in the future preset period is determined according to the operating plan of the transformer in the future preset period. In one possible embodiment, the preset period is 3 days.

[0041] Furthermore, when the running time in different fault monitoring intervals within a future preset period meets the requirements, that is, when the running time in different fault monitoring intervals within a future preset period is greater than the specified time, then the fault identification and processing of the transformer can be reliably achieved in different fault monitoring intervals. Therefore, it is determined that there is no need to perform heat dissipation device control processing in the unmonitored interval.

[0042] Furthermore, if there are fault monitoring intervals whose operating time does not meet the requirements within a future preset time period, the number of fault monitoring intervals whose operating time does not meet the requirements within the future preset time period is determined. If the number of fault monitoring intervals whose operating time does not meet the requirements within the future preset time period is greater than the preset threshold for the number of monitoring intervals, then since the reliability of transformer fault identification and processing within the fault monitoring interval is not high, it is determined that the cooling device needs to be controlled in all unmonitored intervals. That is, the cooling device is turned on only after the top oil temperature of the transformer does not meet the requirements. Specifically, according to the regulations, the cooling device is turned on when the top oil temperature of the transformer is greater than 55 degrees Celsius.

[0043] Additionally, it can be understood that if the number of fault monitoring intervals whose running time does not meet the requirements is not greater than the preset threshold for the number of monitoring intervals within a future preset time period, then the total running time of different fault monitoring intervals is determined. When the total running time of different fault monitoring intervals meets the requirements, i.e., is greater than the time threshold, then it is determined that no control processing of the heat dissipation device is required in the unmonitored interval.

[0044] Furthermore, when the total operating time of different fault monitoring intervals does not meet the requirements, the heat dissipation activation coefficient in the operating load interval is determined. When the heat dissipation activation coefficient in the operating load interval does not meet the requirements, i.e., it is greater than the activation coefficient threshold, the probability of the top oil temperature overheating is high due to the large operating load in the operating load interval. Therefore, in order to ensure the operating stability of the transformer, it is determined that no heat dissipation device control is required in the unmonitored interval.

[0045] Additionally, it can be understood that when the heat dissipation activation coefficient within the operating load range meets the requirements, the operating time within the unmonitored range in the future preset time period is determined. If the operating time within the unmonitored range in the future preset time period exceeds the preset time value, it is determined that control processing of the heat dissipation device is required within the unmonitored range.

[0046] Furthermore, if the running time in the unmonitored interval is not greater than the preset duration value within a future preset time period, it is determined that no control processing of the heat dissipation device is required within the unmonitored interval.

[0047] Example 2 In a second aspect, the present invention provides a computer system comprising: a memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the aforementioned transformer diagnosis method based on acoustic signals when running the computer program.

[0048] Optionally, the method for determining the fault monitoring interval is as follows: Based on the operating data of the transformer in different operating load ranges, the activation data of the heat dissipation device in different operating load ranges are determined; Based on the activation data, the frequently activated load range of the heat dissipation device in the operating load range is determined. Based on the activation data, the total duration of the heat dissipation device in the activated state in the operating load range is determined as the proportion of the total operating time in the operating load range, and this proportion is used as the heat dissipation activation coefficient. Based on the operating data of the frequently activated load range and the heat dissipation activation coefficient within the operating load range, it is determined whether the operating load range is a fault monitoring range.

[0049] Furthermore, when the operating data of the frequently opened load range does not meet the requirements, that is, when the proportion of the total operating time in different frequently opened load ranges in the transformer's operating time is greater than the preset time proportion threshold, for example, greater than 0.5, then the operating time in the frequently opened load range is too long. In order to ensure the reliability of fault monitoring, analysis and processing, all operating load ranges that do not belong to the frequently opened load range are determined to belong to the fault monitoring range.

[0050] Additionally, it should be noted that if, in the past, the total operating time within different frequently activated load ranges accounts for no more than a preset time percentage threshold in the total operating time of the transformer, and the heat dissipation activation coefficient within the operating load range is less than a preset activation coefficient threshold, for example, less than 0.2, then the operating load range is determined to belong to the fault monitoring range.

[0051] It can also be understood that when the heat dissipation activation coefficient within the operating load range is not less than the preset activation coefficient threshold, the operating load range is determined not to belong to the fault monitoring range.

[0052] Example 3 Optionally, the method for determining the control strategy of the heat dissipation device within the operating load range is as follows: Based on the operating load data of the transformer in a future preset period, the operating time in different fault monitoring intervals in the future preset period is determined; The operating load range that does not belong to the fault monitoring data is regarded as the unmonitored range. Based on the operating load data of the transformer in the future preset period, the operating time in the unmonitored range in the future preset period is determined. Based on the runtime in different fault monitoring intervals within a future preset time period, fault monitoring intervals whose runtime does not meet the requirements are identified. Using the fault monitoring intervals whose runtime does not meet the requirements and the runtime in the unmonitored intervals, a control strategy for the heat dissipation device in the unmonitored intervals is determined.

[0053] Furthermore, when the running time in different fault monitoring intervals within a future preset period meets the requirements, that is, when the running time in different fault monitoring intervals within a future preset period is greater than the specified duration, such as 1 hour, then the fault identification and processing of the transformer can be reliably achieved in different fault monitoring intervals. Therefore, it is determined that there is no need to perform heat dissipation device control processing in the unmonitored interval.

[0054] Additionally, it is understandable that when there is a fault monitoring interval where the operating time does not meet the requirements within a future preset period, and when the heat dissipation activation coefficient within the operating load interval does not meet the requirements, i.e., when it is greater than the activation coefficient threshold, for example, greater than 0.7, then because the operating load is large within the operating load interval, the probability of the top oil temperature exceeding the limit is high. Therefore, in order to ensure the operating stability of the transformer, it is determined that there is no need to perform heat dissipation device control processing within the unmonitored interval.

[0055] Additionally, it can be understood that when the heat dissipation activation coefficient within the operating load range meets the requirements, the operating time within the unmonitored range in the future preset time period is determined. If the operating time within the unmonitored range in the future preset time period is greater than the preset time value, such as more than 2 hours, then it is determined that the heat dissipation device needs to be controlled within the unmonitored range.

[0056] Furthermore, if the running time in the unmonitored interval is not greater than the preset duration value within a future preset time period, it is determined that no control processing of the heat dissipation device is required within the unmonitored interval.

[0057] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments of apparatus, devices, and non-volatile computer storage media are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0058] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0059] The above description is merely one or more embodiments of this specification and is not intended to limit this specification. Various modifications and variations can be made to the one or more embodiments of this specification by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of one or more embodiments of this specification should be included within the scope of the claims of this specification.

Claims

1. A transformer diagnostic method based on acoustic signals, characterized in that, Specifically, it includes: Based on the analysis results of the acoustic signal of the transformer, it is determined that the heat dissipation device of the transformer is in the open state and the noise impact data is obtained. Based on the noise impact data, it is determined that the operating load data of the transformer needs to be considered. Based on the operating data of the transformer in different operating load ranges, the operating load range for acoustic fault diagnosis of the transformer is determined and used as the fault monitoring range. Based on the diagnostic data of the acoustic signals of the transformer within the fault monitoring load range, when it is determined that the operating status of the transformer is suspected to be abnormal, a control strategy for the heat dissipation device in the operating load range that does not belong to the fault monitoring range is determined according to the operating load data of the transformer in the future preset period.

2. The transformer diagnostic method based on acoustic signals as described in claim 1, characterized in that, The noise impact data is determined based on the filtering results of the acoustic signal from the sound sensor.

3. The transformer diagnostic method based on acoustic signals as described in claim 1, characterized in that, Determine the transformer's operating load data that needs to be considered, specifically including: Based on the noise impact data, it was determined that the transformer's heat dissipation device was in the on state, and the noise signal was monitored by the sound sensor. Based on the analysis results of the noise signal, the signal-to-noise ratio of the transformer's heat dissipation device when it is in the on state is determined; Based on the signal-to-noise ratio, determine whether the transformer's operating load data needs to be considered.

4. The transformer diagnostic method based on acoustic signals as described in claim 3, characterized in that, When the average signal-to-noise ratio at different monitoring times does not meet the requirements when the transformer's heat dissipation device is in the on state, it is determined that the transformer's operating load data needs to be considered.

5. The transformer diagnostic method based on acoustic signals as described in claim 1, characterized in that, The operating load range is divided into a predetermined number of operating load ranges according to the range of the transformer's historical operating load, using an equally spaced method.

6. The transformer diagnostic method based on acoustic signals as described in claim 1, characterized in that, The method for determining the fault monitoring interval is as follows: Based on the operating data of the transformer in different operating load ranges, the activation data of the heat dissipation device in different operating load ranges are determined; Based on the activation data, determine the frequently activated load range of the heat dissipation device within the operating load range; Based on the operating data of the frequently activated load range and the activation data of the heat dissipation device within the operating load range, it is determined whether the operating load range is a fault monitoring range.

7. The transformer diagnostic method based on acoustic signals as described in claim 6, characterized in that, The activation data refers to the historical operating time of the heat dissipation device being in the activated state within the operating load range.

8. The transformer diagnostic method based on acoustic signals as described in claim 6, characterized in that, The frequently activated load range refers to the operating load range in which the duration of operation of the heat dissipation device in the activated state in history does not meet the requirements.

9. The transformer diagnostic method based on acoustic signals as described in claim 1, characterized in that, The method for determining the control strategy of the heat dissipation device within the operating load range is as follows: Based on the operating load data of the transformer in a future preset period, the operating time in different fault monitoring intervals in the future preset period is determined; The operating load range that does not belong to the fault monitoring data is regarded as the unmonitored range. Based on the operating load data of the transformer in the future preset period, the operating time in the unmonitored range in the future preset period is determined. Based on the runtime in different fault monitoring intervals and the runtime in the unmonitored intervals within a future preset time period, a control strategy for the heat dissipation device in the unmonitored intervals is determined.

10. A computer system, comprising: A memory and processor connected in communication, and a computer program stored in the memory and capable of running on the processor, characterized in that, when the processor runs the computer program, it executes a transformer diagnostic method based on acoustic signals as described in any one of claims 1-9.

Images