A transformer fault monitoring method and system based on artificial intelligence

Abstract

The application relates to an artificial intelligence-based transformer fault monitoring method and system, and relates to the field of transformers.The method comprises the following steps: acquiring current data, temperature data, infrared video, load data and an audio waveform diagram of a transformer in a preset historical time period; finding a reference audio waveform diagram from a preset database based on the current data, the temperature data and the load data; comparing the reference audio waveform diagram with the audio waveform diagram to determine an inconsistent waveform segment in the audio waveform diagram; determining the operation stability of the transformer based on the inconsistent waveform segment and the infrared video; and determining a region in which potential faults of the transformer are likely to occur according to the operation stability and the infrared video.The application has the effect of more timely finding the accurate position of potential faults of the transformer.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of transformers, in particular to a transformer fault monitoring method and system based on artificial intelligence. BACKGROUND

[0002] The transformer is an extremely important electrical equipment in the power transmission and distribution system, but sometimes it will fail in operation due to various reasons, so the stable operation of the transformer is crucial. At present, the transformer monitoring is facing many pain points, and at present, the transformer is simply monitored in temperature, and whether a fault has occurred is judged according to the temperature change of the transformer. But in the early stage of failure, it is not possible to accurately find the potential fault position on the transformer, therefore, how to monitor the fault of the transformer and find the accurate position of the potential fault becomes a problem. SUMMARY

[0003] In order to find the accurate position of the potential fault of the transformer more timely, the present application provides a transformer fault monitoring method and system based on artificial intelligence.

[0004] In the first aspect, the present application provides a transformer fault monitoring method based on artificial intelligence, which adopts the following technical scheme:

[0005] A transformer fault monitoring method based on artificial intelligence, comprising:

[0006] Obtaining current data, temperature data, infrared video, load data and audio waveform diagram of the transformer in a preset historical time period;

[0007] Finding a reference audio waveform diagram from a preset database based on the current data, temperature data and load data;

[0008] Comparing the reference audio waveform diagram with the audio waveform diagram to determine the inconsistent waveform segment in the audio waveform diagram;

[0009] Determining the operation stability of the transformer based on the inconsistent waveform segment and the infrared video;

[0010] Determining the area where the transformer may have a potential fault according to the operation stability and the infrared video.

[0011] By adopting the technical scheme, the current data, temperature data, infrared video, load data and audio waveform graph during running in a preset historical time period are obtained, which facilitates subsequent analysis of a possible fault area on the transformer according to the running condition of the transformer in the time period. The current data, temperature data and load data are all key factors representing the running environment of the transformer, the audio waveform graph is the sound emitted by the transformer during running, and the infrared video represents the temperature performance of each area of the transformer during running. That is, the audio waveform graph and the infrared video of each area are responses of the transformer in the running environment. According to the audio waveform graph, the possible fault area of the transformer can be analyzed. Therefore, the reference audio waveform graph is found from the preset database according to the current data and the like, the reference audio waveform graph represents the sound emitted by the transformer during normal running in a condition similar to the running environment of the transformer, the inconsistent waveform segment in the audio waveform graph is obtained by comparing the reference audio waveform graph with the audio waveform graph, the inconsistent waveform graph and the infrared image are comprehensively analyzed to determine the running stability of the transformer. The higher the running stability is, the more stable the overall running condition of the transformer is, and the less likely the potential fault position is. Conversely, the more likely the potential fault position is. Therefore, the potential fault area on the transformer can be analyzed according to the running stability and the infrared image, and the accurate position of the potential fault of the transformer can be found more timely.

[0012] In another possible implementation manner, the reference audio waveform graph is found from the preset database based on the current data, temperature data and load data, and the finding includes:

[0013] The current data, temperature data and load data at the same time are determined.

[0014] The product of the current data and the load data at the same time is calculated, and the ratio of the product to the temperature data at the corresponding time is calculated.

[0015] A first average value of all the ratios is calculated, and a broken line graph of the ratios is generated based on all the ratios of the preset historical time period.

[0016] A first similarity between the broken line graph and a broken line graph in a preset database is calculated. The preset database includes a plurality of audio waveform graphs, and each audio waveform graph corresponds to a broken line graph of the ratios.

[0017] A target broken line graph with a first similarity reaching a preset similarity threshold is determined from the broken line graphs in the preset database.

[0018] A second average value of the ratios in each target broken line graph is calculated, and a first difference between the second average value of each target broken line graph and the first average value is calculated.

[0019] Determine a matching value of each target broken line graph based on the first difference value and the first similarity, and determine the audio waveform graph corresponding to the target broken line graph with the highest matching value as the reference audio waveform graph.

[0020] In another possible implementation manner, the operation stability of the transformer is determined based on the inconsistent waveform segment and the infrared video, and the operation stability of the transformer is determined based on the first abnormal value and the second abnormal value.

[0021] Determine a first number and a total time length of all inconsistent waveform segments;

[0022] Determine a target reference waveform segment from the reference audio waveform graph based on a time interval of each inconsistent waveform segment;

[0023] Determine a distance and an offset angle between a wave crest of each inconsistent waveform segment and a wave crest of the target reference waveform segment;

[0024] Determine the first abnormal value of the transformer based on the first number, the total time length, the distance, and the offset angle;

[0025] Divide the preset historical time period into a plurality of sub time periods, and divide the infrared video according to the sub time periods to obtain a sub video segment corresponding to each sub time period;

[0026] Perform a gray scale transformation on each sub video segment to obtain a corresponding sub gray scale video segment, divide the transformer in each sub gray scale video segment into a plurality of regions, and calculate a gray scale average value and a gray scale variance of each region in each sub gray scale video segment;

[0027] Determine the second abnormal value of the transformer based on each gray scale average value and each gray scale variance of each region;

[0028] Determine the operation stability of the transformer based on the first abnormal value and the second abnormal value.

[0029] In another possible implementation manner, the first abnormal value of the transformer is determined based on the first number, the total time length, the distance, and the offset angle, and the first abnormal value of the transformer is determined based on the distance, the offset angle, and a preset coefficient.

[0030] Calculate a deviation partial value of each inconsistent waveform segment based on the distance and the offset angle;

[0031] Determine a candidate waveform segment with a deviation partial value reaching a preset partial value threshold, and calculate a deviation partial value average value of all candidate waveform segments;

[0032] Calculate the first abnormal value based on the first number, the total time length, the deviation partial value, and respective corresponding coefficients.

[0033] In another possible implementation manner, the area where the potential fault of the transformer is likely to occur is determined according to the operation stability and the infrared video, and the determining comprises:

[0034] determining a maximum value of the gray value of each area in each sub-gray video segment, and calculating a second difference value between the maximum value and an average value of the gray value of the area;

[0035] determining a second quantity of the second difference value of each area reaching a preset difference threshold in all sub-gray video segments;

[0036] calculating a proportion of the second quantity and a quantity of all sub-gray video segments;

[0037] calculating a third difference value between the average value of the gray value of each sub-gray video segment of each area and a preset average threshold of each area;

[0038] calculating a third difference average value based on all third difference values of each area;

[0039] determining a fault value of each area based on the proportion and the third difference average value;

[0040] multiplying the fault value of each area by the operation stability to obtain a probability of a fault of each area;

[0041] determining an area where the probability reaches a preset probability threshold as the area where the potential fault of the transformer is likely to occur.

[0042] In another possible implementation manner, the second abnormal value of the transformer is determined based on the average value of the gray value and the gray variance of each area, and the determining comprises:

[0043] determining a target variance of all average values of the gray value based on the average value of the gray value of each area with respect to all sub-gray video segments;

[0044] determining an average value of all gray variances based on the gray variance of each area with respect to all sub-gray video segments;

[0045] calculating the second abnormal value based on the target variance, the average value of all gray variances and respective corresponding coefficients.

[0046] In another possible implementation manner, the method further comprises:

[0047] sending the area where the potential fault is likely to occur to a terminal device of a staff.

[0048] In a second aspect, the present application provides a transformer fault monitoring system based on artificial intelligence, which adopts the following technical scheme:

[0049] An artificial intelligence-based transformer fault monitoring system comprises:

[0050] A data acquisition module is configured to acquire current data, temperature data, infrared video, load data and audio waveform diagram during operation of the transformer within a preset historical time period.

[0051] A searching module is configured to search for a reference audio waveform diagram from a preset database based on the current data, temperature data and load data.

[0052] A comparison module is configured to compare the reference audio waveform diagram with the audio waveform diagram to determine an inconsistent waveform segment in the audio waveform diagram.

[0053] A stability determining module is configured to determine the operation stability of the transformer based on the inconsistent waveform segment and the infrared video.

[0054] A region determining module is configured to determine a region where potential faults of the transformer are likely to occur based on the operation stability and the infrared video.

[0055] By using the above technical solution, the data acquisition module acquires the current data, temperature data, infrared video, load data and audio waveform diagram during operation of the transformer within a preset historical time period, which facilitates subsequent analysis of the region where potential faults of the transformer are likely to occur based on the operation of the transformer within the time period. The current data, temperature data and load data are key factors representing the operation environment of the transformer. The audio waveform diagram is the sound emitted by the transformer during operation. The infrared video represents the temperature performance of each region of the transformer during operation. That is, the audio waveform diagram and the infrared video of each region are responses of the transformer to the operation environment. The region where potential faults of the transformer are likely to occur can be analyzed based on the audio waveform diagram. Therefore, the searching module finds the reference audio waveform diagram from the preset database based on the current data and the like. The reference audio waveform diagram represents the sound emitted by the transformer during normal operation in a situation similar to the operation environment of the transformer. The comparison module compares the reference audio waveform diagram with the audio waveform diagram to obtain the inconsistent waveform segment in the audio waveform diagram. The stability determining module comprehensively analyzes the inconsistent waveform diagram and the infrared image to determine the operation stability of the transformer. The higher the operation stability is, the more stable the overall operation of the transformer is, and the less likely the position where potential faults occur is. Conversely, the higher the operation stability is, the more likely the position where potential faults occur is. Therefore, the region determining module can analyze the region where potential faults of the transformer are likely to occur based on the operation stability and the infrared image, thereby achieving more timely and accurate determination of the precise position where potential faults of the transformer occur.

[0056] In another possible implementation manner, when searching for the reference audio waveform diagram from the preset database based on the current data, temperature data and load data, the searching module is specifically configured to:

[0057] determining current data, temperature data and load data at the same time;

[0058] calculating the product of the current data and the load data at the same time, and calculating the ratio of the product and the temperature data at the corresponding time;

[0059] calculating the first average value of all the ratios, and generating a line graph of the ratios based on all the ratios of the preset historical time period;

[0060] calculating the first similarity of the line graph and the line graph in the preset database, the preset database comprising a plurality of audio waveform graphs, each audio waveform graph corresponding to a line graph of the ratios;

[0061] determining a target line graph from the line graphs in the preset database, the first similarity of the target line graph reaching a preset similarity threshold;

[0062] calculating the second average value of the ratios in each target line graph, and calculating the first difference value between the second average value and the first average value of each target line graph;

[0063] determining the matching value of each target line graph based on the first difference value and the first similarity, and determining the audio waveform graph corresponding to the target line graph with the highest matching value as the reference audio waveform graph.

[0064] In another possible implementation, the stability determination module, when determining the operation stability of the transformer based on the inconsistent waveform segment and the infrared video, is specifically configured to:

[0065] determining the first number and the total time length of all the inconsistent waveform segments;

[0066] determining a target reference waveform segment from the reference audio waveform graph based on the time interval of each inconsistent waveform segment;

[0067] determining the distance and the deviation angle between the peak of each inconsistent waveform segment and the peak of the target reference waveform segment;

[0068] determining the first abnormal value of the transformer based on the first number, the total time length, the distance and the deviation angle;

[0069] dividing the preset historical time period into a plurality of sub-time periods, and segmenting the infrared video according to the sub-time periods to obtain a sub-video segment corresponding to each sub-time period;

[0070] performing gray scale transformation on each sub-video segment to obtain a corresponding sub-gray scale video segment, dividing the transformer in each sub-gray scale video segment into a plurality of regions, and calculating the gray scale average value and the gray scale variance of each region in each sub-gray scale video segment;

[0071] determine a second abnormal value of the transformer based on the average value and the variance of the gray scale of each region;

[0072] determine the operation stability of the transformer based on the first abnormal value and the second abnormal value.

[0073] In another possible implementation, the stability determining module, when determining the first abnormal value of the transformer based on the first number, the total time length, the distance and the deviation angle, is specifically configured to:

[0074] calculate a deviation partial value of each inconsistent waveform segment based on the distance and the deviation angle;

[0075] determine a candidate waveform segment whose deviation partial value reaches a preset partial value threshold, and calculate an average value of the deviation partial values of all candidate waveform segments;

[0076] obtain the first abnormal value based on the first number, the total time length, the deviation partial value and respective corresponding coefficients.

[0077] In another possible implementation, the region determining module, when determining the region where the transformer is likely to have a potential fault based on the operation stability and the infrared video, is specifically configured to:

[0078] determine a maximum value of the gray scale of each region in each sub-gray scale video segment, and calculate a second difference value between the maximum value and an average value of the gray scale of the region;

[0079] determine a second number of regions whose second difference values reach a preset difference value threshold in all sub-gray scale video segments;

[0080] calculate a proportion of the second number to a number of all sub-gray scale video segments;

[0081] calculate a third difference value between the average value of each sub-gray scale video segment of each region and a preset average value threshold of each region;

[0082] calculate a third difference value average based on all third difference values of each region;

[0083] determine a fault value of each region based on the proportion and the third difference value average;

[0084] multiply the operation stability by the fault value of each region to obtain a probability of a fault of each region;

[0085] determine a region whose probability reaches a preset probability threshold as the region where the transformer is likely to have a potential fault.

[0086] In another possible implementation manner, the stability determination module is specifically configured for determining the second abnormal value of the transformer based on the average value and the gray variance of each region, and the method comprises the following steps of:

[0087] determining a target variance of all gray average values based on the gray average value of each region with respect to all sub-gray video segments;

[0088] determining an average value of all gray variances based on the gray variance of each region with respect to all sub-gray video segments;

[0089] calculating the second abnormal value based on the target variance, the average value of all gray variances and respective corresponding coefficients.

[0090] In another possible implementation manner, the transformer fault monitoring system based on artificial intelligence further comprises:

[0091] a sending module configured to send the region where the potential fault may occur to a terminal device of a worker.

[0092] In a third aspect, the present application provides an electronic device, which adopts the technical scheme as follows:

[0093] An electronic device, comprising:

[0094] at least one processor;

[0095] a memory;

[0096] at least one application program, wherein the at least one application program is stored in the memory and is configured to be executed by the at least one processor, and the at least one configuration is configured to execute the transformer fault monitoring method based on artificial intelligence according to any one of the possible implementation manners of the first aspect.

[0097] In a fourth aspect, the present application provides a computer readable storage medium, which adopts the technical scheme as follows:

[0098] A computer readable storage medium, when the computer program is executed in the computer, the computer executes the transformer fault monitoring method based on artificial intelligence according to any one of the first aspect.

[0099] In summary, the present application includes at least one of the following beneficial technical effects:

[0100] The current data, temperature data, infrared video, load data and audio waveform diagram during running in a preset historical time period are acquired, so that the area where the transformer is likely to malfunction can be analyzed according to the running condition of the transformer in the time period. The current data, temperature data and load data are key factors representing the running environment of the transformer, the audio waveform diagram is the sound emitted by the transformer during running, and the infrared video represents the temperature performance of each area of the transformer during running. That is, the audio waveform diagram and the infrared video of each area are responses of the transformer in the running environment. According to the audio waveform diagram, the area where the transformer is likely to malfunction can be analyzed. Therefore, the reference audio waveform diagram is found from the preset database according to the current data and the like. The reference audio waveform diagram represents the sound emitted by the transformer during normal running in a condition similar to the running environment of the transformer. The reference audio waveform diagram is compared with the audio waveform diagram to obtain the inconsistent waveform segment in the audio waveform diagram. The inconsistent waveform and the infrared image are comprehensively analyzed to determine the running stability of the transformer. The higher the running stability is, the more stable the overall running condition of the transformer is, and the less likely the potential fault position is. Conversely, the potential fault position is more likely. Therefore, the area where the transformer is likely to have a potential fault can be analyzed according to the running stability and the infrared image, so that the accurate position where the transformer is likely to have a potential fault can be found more timely. BRIEF DESCRIPTION OF DRAWINGS

[0101] Figure 1 is a flowchart of a transformer fault monitoring method based on artificial intelligence according to an embodiment of the present application.

[0102] Figure 2 is a structural schematic diagram of a transformer fault monitoring system based on artificial intelligence according to an embodiment of the present application.

[0103] Figure 3 is a structural schematic diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0104] The present application will be further described in detail below with reference to the accompanying drawings.

[0105] Those skilled in the art can make modifications to the present embodiment without creative contribution after reading the present specification, but as long as the modifications are within the scope of the claims of the present application, they are protected by the patent law.

[0106] In order to make the purposes, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some but not all of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0107] In addition, the term "and / or" in this paper is only a description of the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B, which can represent the three cases of A alone, A and B together, and B alone. In addition, the character " / " in this paper generally represents an "or" relationship between the associated objects before and after it, unless otherwise specified.

[0108] The embodiments of the present application will be described in further detail below with reference to the drawings of the specification.

[0109] The embodiments of the present application provide a transformer fault monitoring method based on artificial intelligence, which is executed by an electronic device. The electronic device can be a server or a terminal device. The server can be a standalone physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smartphone, a tablet computer, a notebook computer, a desktop computer, etc., but is not limited thereto. The terminal device and the server can be directly or indirectly connected through wired or wireless communication, and the embodiments of the present application do not limit this. As shown in the figure, the method comprises steps S101, S102, S103, S104 and S105, wherein, Figure 1

[0110] S101, obtaining current data, temperature data, infrared video, load data and audio waveform diagram during running of the transformer in a preset historical time period.

[0111] ​For the embodiments of the present application, the preset historical time period can be the past half hour, the past one hour, etc. of the current time. The transformer is provided with a current sensor, a temperature sensor, a load sensor, a pickup or a microphone, so as to be able to collect current data, temperature data, load data and the sound emitted when the transformer is running. In other embodiments, the load data can also be obtained by calculation through current, voltage, etc. The temperature sensor can be arranged inside the transformer, for collecting the temperature inside the transformer, and then using the temperature to represent the running environment of the transformer. An infrared camera is also arranged in the area near the transformer, for collecting the infrared video of the whole transformer, which records the specific temperature of each part of the device when the transformer is running. The above-mentioned sensor collecting device and the electronic device are connected through wires or wirelessly, so that the electronic device obtains the above-mentioned data. The above-mentioned sensor collecting device can also be connected wirelessly with the cloud server, and the above-mentioned data is uploaded to the cloud server, and then the electronic device obtains it from the cloud server.

[0112] The current data, temperature data and load data represent the running environment of the transformer, and the audio waveform graph and the infrared video represent the specific reaction and performance of the transformer when it is running.

[0113] S102, finding the reference audio waveform graph from the preset database based on the current data, temperature data and load data.

[0114] For the embodiments of the present application, the preset database stores a plurality of audio waveform graphs, and each audio waveform graph is the sound emitted when the transformer is running normally under different running environments. Since the current data, temperature data and load data represent the running environment of the transformer, the electronic device can find the reference audio waveform graph similar to the running environment of the transformer in the preset historical time period from the preset database according to the current data, temperature data and load data. Comparing the reference audio waveform graph with the audio waveform graph in the preset time period facilitates the analysis of the fault condition of the transformer.

[0115] S103, comparing the reference audio waveform graph with the audio waveform graph to determine the inconsistent waveform segment in the audio waveform graph.

[0116] For the embodiments of the present application, the electronic device compares the reference audio waveform graph with the audio waveform graph in the preset time period, so as to be able to eliminate the overlapping part and obtain the inconsistent waveform segment. Analyzing the inconsistent waveform segment can obtain the abnormal condition and the running stability of the transformer.

[0117] S104, determining the running stability of the transformer based on the inconsistent waveform segment and the infrared video.

[0118] For the embodiment of the present application, the inconsistent waveform diagram represents the difference between the sound emitted by the transformer during operation and the sound emitted by the transformer during normal operation, thereby affecting the operation stability of the transformer. The infrared video records the temperature performance of different positions in different areas of the transformer, and the positions with different temperatures affect the stable operation of the transformer. Therefore, the electronic device can accurately obtain the operation stability of the transformer by comprehensively analyzing the inconsistent waveform segment and the infrared video.

[0119] In S105, the area where the transformer may have a potential fault is determined according to the operation stability and the infrared video.

[0120] For the embodiment of the present application, the operation stability affects the probability of faults occurring on the transformer, and the infrared video can determine the temperature performance changes of different positions in different areas of the transformer. The operation stability of the transformer as a whole and the infrared video can accurately determine the area where the transformer may have a potential fault, thereby realizing more timely discovery of the precise position of the potential fault of the transformer.

[0121] In one possible implementation of the embodiment of the present application, the step S102 of searching for the reference audio waveform diagram from the preset database based on the current data, the temperature data, and the load data specifically includes the following steps: S1021 (not shown in the figure), S1022 (not shown in the figure), S1023 (not shown in the figure), S1024 (not shown in the figure), S1025 (not shown in the figure), S1026 (not shown in the figure), and S1027 (not shown in the figure), wherein,

[0122] In S1021, the current data, the temperature data, and the load data at the same time are determined.

[0123] For the embodiment of the present application, the current data, the temperature data, and the load data in the preset time period can be represented on the coordinate axis, thereby forming respective corresponding line graphs. The respective line graphs are compared together to determine the current data, the temperature data, and the load data at the same time.

[0124] In S1022, the product of the current data and the load data at the same time is calculated, and the ratio of the product to the temperature data at the corresponding time is calculated.

[0125] In this embodiment, current data, temperature data, and load data at the same time represent the transformer's operating environment at that moment. Current and load data represent the impact of power grid distribution on the operating environment, while temperature data represents the transformer's own impact. Therefore, the electronic device calculates the product of the current and load data at the same time to obtain a value, which represents the combined impact of current and load on the transformer. Then, the product is divided by the corresponding temperature data to obtain a ratio, which represents the operating environment at that moment. Different operating environments correspond to different ratios; therefore, this ratio is the characteristic value of the operating environment at each moment. The ratio at each moment facilitates the subsequent finding of a reference audio waveform diagram that more closely approximates the operating environment of a preset historical time period.

[0126] S1023, calculate the first average of all ratios, and generate a line graph of the ratios based on all ratios over a preset historical time period.

[0127] In this embodiment of the application, the electronic device calculates the first average value of all ratios using an average value calculation formula. The first average value represents the level of the operating environment, facilitating the subsequent search for reference audio waveforms at the same or similar levels. The electronic device maps the ratios and their corresponding times onto a preset Cartesian coordinate system, and then connects the lines sequentially to obtain a line graph of the ratios.

[0128] S1024, Calculate the first similarity between the line chart and the line chart in the preset database.

[0129] The preset database includes multiple audio waveforms, each corresponding to a line graph of the ratio.

[0130] In the embodiments of this application, the electronic device can calculate the first similarity between the line graph and the line graph in the preset database by calculating cosine similarity, Euclidean distance, and Pearson correlation coefficient. The higher the first similarity, the closer the trend of the operating environment over time is.

[0131] S1025, determine the target line graph whose first similarity reaches the preset similarity threshold from the line graphs in the preset database.

[0132] In the embodiments of this application, the preset similarity threshold represents the dividing point of whether the first similarity is high, such as the preset similarity threshold being 95%. Reaching the preset similarity threshold indicates that the changing trend of the operating environment over time is relatively similar. Therefore, the electronic device is screened using 95% to obtain the target line graph that reaches the preset similarity threshold, and the most suitable reference audio waveform is further selected from the target line graph.

[0133] S1026, calculate a second average value of the ratio in each target line graph, and calculate a first difference value between the second average value and the first average value of each target line graph.

[0134] For the embodiment of the application, the second average value is calculated according to the average value calculation formula of the ratio at each time in each target line graph, and then the first difference value is obtained by subtracting the first average value from the second average value. The electronic device can take the absolute value of the first difference value, and the smaller the absolute value, the closer the level of the running environment, and the higher the first similarity, which is more suitable for being regarded as a similar running environment.

[0135] S1027, determine the matching value of each target line graph based on the first difference value and the first similarity, and determine the audio waveform graph corresponding to the target line graph with the highest matching value as the reference audio waveform graph.

[0136] For the embodiment of the application, the first difference value and the first similarity are both key factors affecting the matching degree of the running environment of the target line graph and the running environment of the transformer in the preset historical time period, so different coefficients are set for the first difference value and the first similarity, and then the electronic device performs weighted calculation according to the respective coefficients to obtain the matching value. Since the first difference value is inversely proportional to the matching degree, the electronic device can take the reciprocal of the absolute value of the first difference value for weighted calculation, so that the matching value is more in line with the actual logic. The higher the matching value, the closer the running environment, and the more suitable the corresponding audio waveform graph as the reference audio waveform graph. The characteristic value related to the running environment is determined through the related data in the preset historical time period, and the line graph is further determined, so that the reference audio waveform graph found through the line graph is more accurate.

[0137] In one possible implementation of the embodiment of the application, the running stability of the transformer is determined based on the inconsistent waveform segments and the infrared video in step S104, which specifically includes steps S1041 (not shown in the figure), S1042 (not shown in the figure), S1043 (not shown in the figure), S1044 (not shown in the figure), S1045 (not shown in the figure), S1046 (not shown in the figure), S1047 (not shown in the figure), and S1048 (not shown in the figure), wherein,

[0138] S1041, determine the first number and the total duration of all inconsistent waveform segments.

[0139] For the embodiment of the application, the more the first number of inconsistent waveform graphs, the more unstable the running of the transformer. The electronic device sums the duration of all inconsistent waveform segments to obtain the total duration, and the longer the total duration, the longer the time when the transformer running is inconsistent with the sound emitted when running normally, which also indicates that the running is more unstable.

[0140] S1042, determine a target reference waveform segment from the reference audio waveform graph based on the time interval of each inconsistent waveform segment.

[0141] For the embodiments of the present application, each inconsistent waveform segment corresponds to a start time and an end time, and the time interval of the inconsistent waveform segment is between the start time and the end time. The electronic device can segment the target reference waveform segment corresponding to each inconsistent waveform segment from the reference audio waveform graph according to the time interval.

[0142] S1043, determine the distance and the offset angle between the peak of each inconsistent waveform segment and the peak of the target reference waveform segment.

[0143] For the embodiments of the present application, by comparing the inconsistent waveform segment and the target reference waveform segment, the difference between the sound emitted when the transformer is running suspiciously and the sound emitted when the transformer is running normally can be compared. The electronic device can map the inconsistent waveform segment and the target reference waveform segment into the coordinate system, and then calculate the distance between the peaks of the inconsistent waveform segment and the target reference waveform segment using the distance formula between two points. The greater the distance, the greater the difference between the sound emitted when the transformer is running and the sound emitted when the transformer is running normally. The electronic device determines the coordinate points of the two peaks in the coordinate system, and then calculates the offset angle between the two peaks. The greater the offset angle, the greater the difference between the sound emitted when the transformer is running and the sound emitted when the transformer is running normally. Therefore, both the distance and the offset angle can indicate the running stability of the transformer. In other embodiments, the electronic device can also calculate the similarity between the inconsistent waveform segment and the target reference waveform segment. The size of the similarity also affects the running stability of the transformer.

[0144] S1044, determine the first abnormal value of the transformer based on the first quantity, the total duration, the distance, and the offset angle.

[0145] For the embodiments of the present application, in summary, the first quantity, the total duration, the distance, and the offset angle are all key factors affecting the running stability and abnormal situation of the transformer, and these factors are all in the aspect of audio representing the running stability and abnormal situation. Therefore, the electronic device determines the first abnormal value of the transformer in the aspect of audio more accurately according to the above four factors.

[0146] S1045, divide the preset historical time period into a plurality of sub-time periods, and segment the infrared video according to the sub-time periods to obtain a sub-video segment corresponding to each sub-time period.

[0147] For the embodiments of the present application, the electronic device can divide the preset historical time period into a plurality of sub-time periods. Then, the electronic device segments the infrared video according to each sub-time period to obtain a sub-video segment of each sub-time period.

[0148] S1046, perform a gray scale transformation on each sub-video segment to obtain a corresponding sub-gray scale video segment, divide the transformer in each sub-gray scale video segment into multiple regions, and calculate the gray scale average value and the gray scale variance of each region in each sub-gray scale video segment.

[0149] For the embodiments of the present application, the electronic device can perform denoising processing on each sub-video segment to obtain a denoised sub-video segment, and then perform a gray scale transformation on the denoised sub-video segment to obtain a corresponding sub-gray scale video segment, and the size of the gray scale value represents the high and low of the temperature. The model of the transformer can be stored in the electronic device, and the worker can divide the model into multiple regions, which can be equal division or division according to requirements, functional modules, etc. Then the electronic device processes the gray scale value in each frame of picture of each sub-gray scale video segment, thereby calculating the gray scale average value and the gray scale variance of each region in each frame of picture, and then calculating the gray scale average value and the gray scale variance of each region in each sub-gray scale video segment in combination with the gray scale average value and the gray scale variance of all frames of pictures of the entire sub-video segment. The gray scale average value represents the average temperature high and low of each region in the time period of the sub-gray scale video segment, and the gray scale variance represents the difference of temperature distribution of each region in the sub-gray scale video segment.

[0150] S1047, determine the second abnormal value of the transformer based on the gray scale average value and the gray scale variance of each region.

[0151] For the embodiments of the present application, the gray scale average value represents the average temperature high and low, that is, represents the heating condition of each region, and the average temperature of a certain region being too high indicates that the possibility of an abnormality occurring in the region on the transformer is larger, thereby affecting the running stability degree of the transformer. The gray scale variance represents the temperature distribution difference in each region. The temperature distribution difference being too large indicates that the possibility of an abnormality occurring in the region on the transformer is larger, thereby affecting the running stability degree of the transformer. That is, the gray scale average value and the gray scale variance are the influencing factors of the running stability degree of the transformer as a whole in terms of temperature performance of each region, and therefore the electronic device comprehensively analyzes to obtain an accurate second abnormal value according to the gray scale average value and the gray scale variance.

[0152] S1048, determine the running stability degree of the transformer based on the first abnormal value and the second abnormal value.

[0153] For the embodiment of the present application, after the electronic device determines the first abnormal value and the second abnormal value, if the first abnormal value and the second abnormal value are both proportional to the operation stability, that is, the greater the two abnormal values, the higher the operation stability, the electronic device can directly sum the first abnormal value and the second abnormal value to obtain a total value, and the total value can represent the operation stability of the transformer. If the first abnormal value and the second abnormal value are both inversely proportional to the operation stability, that is, the greater the two abnormal values, the lower the operation stability, the electronic device can take the reciprocal of the first abnormal value and the second abnormal value to sum to obtain the operation stability. The operation stability of the transformer determined by comprehensively determining the audio performance and the temperature performance is more accurate.

[0154] In a possible implementation of the embodiment of the present application, the step S1044 of determining the first abnormal value of the transformer based on the first quantity, the total time length, the distance, and the deviation angle specifically includes steps Sa (not shown in the figure), step Sb (not shown in the figure), and step Sc (not shown in the figure), wherein,

[0155] Sa, the distance and the deviation angle are used to calculate the deviation partial value of each inconsistent waveform segment.

[0156] For the embodiment of the present application, the distance and the deviation angle are both key factors affecting the difference degree between the inconsistent waveform and the waveform during the normal operation in the corresponding time period, and the influence degrees are different, so the staff can set different coefficients for the distance and the deviation angle and store them in the electronic device, and then the electronic device can call the respective corresponding coefficients to perform weighted calculation on the distance and the deviation angle to obtain the deviation partial value of each inconsistent waveform.

[0157] Sb, the selected waveform segment whose deviation partial value reaches a preset partial value threshold is determined, and the average value of the deviation partial values of all the selected waveform segments is calculated.

[0158] For the embodiment of the present application, the preset partial value threshold is used as a demarcation point for whether the deviation partial value is too large, and reaching the preset partial value threshold indicates that the inconsistent waveform segment has a relatively large influence on the operation stability of the transformer, and not reaching the preset partial value threshold indicates that the inconsistent waveform segment has a relatively small influence on the operation stability of the transformer, so a part of the inconsistent waveform segments with a relatively small influence on the operation stability is filtered out according to the preset partial value threshold to obtain the selected waveform segment that sufficiently affects the operation stability of the transformer. Then, the electronic device calculates the average value of the deviation partial values of all the selected waveform segments by using the average value calculation formula, and the greater the average value of the deviation partial values, the worse the operation stability of the transformer and the greater the probability of abnormality. Compared with analyzing all the inconsistent waveform segments, analyzing the selected waveform segment reduces the amount of analysis.

[0159] Sc, the first abnormal value is calculated based on the first quantity, the total time length, the deviation partial value, and the respective corresponding coefficients.

[0160] For the embodiments of the present application, in summary, the first quantity, the total time length and the deviation score are key factors affecting the transformer operation stability in the audio aspect, and the influence degree is different, so the staff can set the respective corresponding coefficients of the above three factors and store them in the electronic device, and the electronic device calls the respective corresponding coefficients to perform weighted calculation on the first quantity, the total time length and the deviation score to obtain the first abnormal value. The first abnormal value is calculated by the first quantity and other characteristics, which is more accurate. In other embodiments, the first quantity can also be replaced by the number of the to-be-selected waveform segment, and the total time length can also be replaced by the ratio of the total time length to the preset historical time period.

[0161] In a possible implementation of the embodiments of the present application, the step S105 of determining the area where the transformer may have a potential fault according to the operation stability and the infrared video specifically includes steps S1051 (not shown in the figure), S1052 (not shown in the figure), S1053 (not shown in the figure), S1054 (not shown in the figure), S1055 (not shown in the figure), S1056 (not shown in the figure), S1057 (not shown in the figure) and S1058 (not shown in the figure), wherein,

[0162] S1051, determining the maximum gray value of each area in each sub-gray video segment, and calculating a second difference value between the maximum gray value and the average gray value of the area.

[0163] For the embodiments of the present application, the temperature at the maximum gray value is the highest, and the higher the maximum gray value of a certain area, the greater the probability of abnormality and potential fault of the area. The electronic device obtains the second difference value by subtracting the average gray value of the area from the maximum gray value, and the greater the second difference value, the greater the difference from the general temperature of the area, and the greater the probability of abnormality or potential fault.

[0164] S1052, determining the second quantity of the second difference value reaching a preset difference threshold in all sub-gray video segments of each area.

[0165] For the embodiments of the present application, the preset difference threshold is a demarcation point for whether the second difference value is too large, and the second difference value reaching the preset difference threshold indicates that the maximum gray value is more likely to be abnormal or have a potential fault, so the electronic device determines the sub-gray video segments in which the second difference value reaches the preset difference threshold in all sub-gray video segments of each area, and determines the number of these sub-gray video segments, that is, the second quantity. The greater the number of these sub-gray video segments, the longer the time when the position with the excessively high temperature in the area appears, and the higher the probability of abnormality and potential fault of the area.

[0166] S1053, calculating the proportion of the second quantity to the number of all sub-gray video segments.

[0167] For the embodiment of the present application, the electronic device divides the second quantity by the total number of sub-gray video segments to obtain a proportion, and the greater the proportion, the longer and more frequent the position of the temperature that is too high in the region, and the greater the probability of abnormality and potential failure. The proportion is more accurate in representing the probability of abnormality and potential failure of the region.

[0168] In S1054, the electronic device calculates a third difference value between the average gray value of each sub-gray video segment of each region and a preset average value threshold of each region.

[0169] For the embodiment of the present application, the preset average value threshold is used as a temperature threshold of the overall temperature performance of each region during normal operation of the transformer, and the electronic device subtracts the corresponding preset average value threshold from the average gray value of each sub-gray video segment of each region to obtain a third difference value about each sub-gray video segment. The greater the third difference value, the greater the difference between the temperature performance of the region and the temperature performance during normal operation of the transformer, and the greater the possibility of abnormality and potential failure of the region.

[0170] In S1055, the electronic device calculates a third difference value average based on all the third difference values of each region.

[0171] For the embodiment of the present application, after the electronic device determines all the third difference values of each region, the electronic device calculates the third difference value average of each region by using the average value calculation formula. The third difference value average represents the overall difference between the temperature performance of each region in the preset historical time period and the temperature performance of the region during normal operation of the transformer. The greater the third difference value average, the greater the possibility of abnormality and potential failure.

[0172] In S1056, the electronic device determines a failure value of each region based on the proportion and the third difference value average.

[0173] For the embodiment of the present application, the proportion and the third difference value average are both key factors affecting the abnormality and potential failure of each region. Therefore, the electronic device can comprehensively determine the failure value of each region according to the proportion and the third difference value average, that is, the failure value is more accurate according to the infrared video (temperature performance) of each region in the preset historical time period. Specifically, the staff can set respective corresponding coefficients of the proportion and the third difference value average and store the coefficients in the electronic device, and then the electronic device calls the respective corresponding coefficients for weighted calculation to obtain the failure value of each region.

[0174] In S1057, the electronic device multiplies the running stability by the failure value of each region to obtain a probability of failure of each region.

[0175] For the embodiment of the present application, the possibility of each region appearing abnormal and potential failure is related to the temperature performance of the region itself and the operation stability of the transformer as a whole. The more unstable the operation of the transformer as a whole, the more the failure value determined by the temperature performance of each region is superimposed, so that the probability of each region appearing potential failure is more accurate. Therefore, the electronic device can calculate the probability of each region appearing potential failure by multiplying the operation stability of the transformer by the failure value of each region. Specifically, the electronic device can normalize the product of the operation stability and the failure value, map the product of each region to between 0 and 1 to obtain the probability of each region.

[0176] In S1058, the region whose probability reaches the preset probability threshold is determined as the region where the transformer is likely to appear potential failure.

[0177] For the embodiment of the present application, the preset probability threshold is used as a demarcation point for appearing potential failure. Assuming that the preset probability threshold is 70%, the electronic device can compare the probability of each region appearing potential failure with 70%, and the region reaching the preset probability threshold is the region where the transformer is likely to appear potential failure. By superimposing the temperature performance of each region and the operation stability of the transformer as a whole, the region with potential failure can be more accurately determined.

[0178] Further, since different regions of the transformer contain different components, the corresponding functions and roles are also different. Therefore, the electronic device can determine the priority of each region according to the number of components in each region and the importance of the functions implemented by the components. After the electronic device determines the region with potential failure, the danger level of the transformer is determined comprehensively according to the priority of the region with potential failure and the probability of the region appearing failure. When multiple regions with potential failure are determined, the danger level of the transformer is determined according to the priority of the multiple regions with potential failure, the probability of appearing failure, and the total number of the regions with potential failure. Then, the upcoming nearest power consumption valley is determined according to the power consumption change graph of the management region covered by each transformer, and the nearest power consumption valley period is determined as the maintenance time of the transformer. Alternatively, the importance level of each transformer is determined according to the size of the management region covered by each transformer and the average power consumption. When there are multiple transformers with regions with potential failure, the maintenance priority of each transformer is determined according to the importance level and the danger level of each transformer.

[0179] In one possible implementation of the embodiment of the present application, the second abnormal value of the transformer is determined based on the average value and the variance of the gray scale of each region in S1047, specifically including steps one, two, and three, wherein,

[0180] In step one, the target variance of all gray scale average values is determined based on the gray scale average values of all sub-gray scale video segments of each region.

[0181] For the embodiment of the present application, the electronic device calculates the target variance of each region with respect to the average value of all gray scales by using the variance calculation formula on the average value of all gray scales of each region, and the target variance represents the fluctuation between the temperature performance of each region and the temperature performance of the region when it is running normally. The greater the target variance is, the greater the difference between the temperature performance of the region and the temperature performance of the region when it is running normally, and the worse the running stability of the transformer is.

[0182] Step two, the average value of the variance of all gray scales is determined based on the variance of all sub-gray scale video segments of each region.

[0183] For the embodiment of the present application, the variance of gray scales represents the temperature difference between each position in the region during the sub-gray scale video segment. The smaller the temperature difference between each position in the region is, the more uniform the heat generation in the region is, and the higher the running stability of the transformer is. Therefore, the electronic device calculates the average value of all the variances of gray scales in the preset historical time period of each region to obtain the average value of the variance of all gray scales. The greater the average value of the variance of gray scales of a region is, the greater the temperature change difference of each position in the region in the preset historical time period is, the more uneven the heat generation is, and the worse the running stability of the transformer is.

[0184] Step three, the second abnormal value is calculated based on the target variance, the average value of the variance of all gray scales, and the respective corresponding coefficients.

[0185] For the embodiment of the present application, as summarized above, the target variance and the average value of the variance of all gray scales are both key factors that affect the running stability of the transformer in terms of temperature performance. The electronic device can sum the target variances of all regions to obtain a target variance sum, and sum the average values of the variances of all regions to obtain an average value sum. The coefficients of the two sums are set in advance by the staff and stored in the electronic device. The electronic device calls the respective coefficients to perform weighted calculation to obtain the second abnormal value. The second abnormal value of the transformer in terms of temperature performance is more accurate through the calculation of the target variance and other data.

[0186] It should be noted that the coefficients and the threshold values in the present embodiment can be adaptively modified according to actual conditions and requirements.

[0187] In one possible implementation of the embodiment of the present application, step S105 is followed by step S106 (not shown in the figure), in which,

[0188] S106, the region where the potential fault may occur is sent to the terminal device of the staff.

[0189] For the embodiment of the present application, the terminal device of the staff can be a telephone, a personal computer, or other devices. The electronic device is connected to the terminal device of the staff wirelessly, so that the electronic device can determine the area where the transformer may have a potential fault and send it to the terminal device of the staff, so that the staff can know the operation of the transformer in time.

[0190] The above embodiment introduces a transformer fault monitoring method based on artificial intelligence from the perspective of method flow. The following embodiment introduces a transformer fault monitoring system 20 based on artificial intelligence from the perspective of virtual modules or virtual units. For details, see the following embodiment.

[0191] The embodiment of the present application provides a transformer fault monitoring system 20 based on artificial intelligence, as shown in Figure 2 The transformer fault monitoring system 20 based on artificial intelligence can specifically include:

[0192] The data acquisition module 201 is configured to acquire current data, temperature data, infrared video, load data, and audio waveform diagram of the transformer in a preset historical time period.

[0193] The search module 202 is configured to search for a reference audio waveform diagram from a preset database based on the current data, the temperature data, and the load data.

[0194] The comparison module 203 is configured to compare the reference audio waveform diagram with the audio waveform diagram to determine an inconsistent waveform segment in the audio waveform diagram.

[0195] The stability determination module 204 is configured to determine the operation stability of the transformer based on the inconsistent waveform segment and the infrared video.

[0196] The area determination module 205 is configured to determine an area where the transformer may have a potential fault according to the operation stability and the infrared video.

[0197] This application discloses an artificial intelligence-based transformer fault monitoring system 20. The data acquisition module 201 acquires current data, temperature data, infrared video, load data, and audio waveforms from a preset historical time period. This facilitates subsequent analysis of the transformer's operating conditions during this period to identify potential fault areas. Current, temperature, and load data are key factors characterizing the transformer's operating environment. The audio waveform represents the sound emitted by the transformer during operation, and the infrared video characterizes the temperature performance of different areas of the transformer during operation. In other words, the audio waveform and infrared video of each area represent the transformer's response to its operating environment. Based on the audio waveform, potential fault areas can be identified. Therefore, the search module 202 uses the current data... The reference audio waveform is retrieved from a preset database. The reference audio waveform represents the sound emitted by the transformer during normal operation under conditions similar to the transformer's operating environment. The comparison module 203 compares the reference audio waveform with the audio waveform to obtain inconsistent waveform segments in the audio waveform. The stability determination module 204 performs a comprehensive analysis of the inconsistent waveform and the infrared image to determine the transformer's operating stability. The higher the operating stability, the more stable the overall operation of the transformer, and the lower the probability of a potential fault location. Conversely, the lower the stability, the higher the probability of a fault location. Therefore, the area determination module 205 analyzes the areas on the transformer that may have potential faults based on the operating stability and the infrared image, ultimately enabling more timely and accurate detection of potential fault locations on the transformer.

[0198] In one possible implementation of this application embodiment, when the search module 202 searches for a reference audio waveform diagram from a preset database based on current data, temperature data, and load data, it is specifically used for:

[0199] Determine the current, temperature, and load data at the same time point;

[0200] Calculate the product of the current data and the load data at the same time, and calculate the ratio of the product to the temperature data at the corresponding time.

[0201] Calculate the first average of all ratios and generate a line graph of the ratios based on all ratios over a preset historical time period;

[0202] Calculate the first similarity between the line graph and the line graph in the preset database, which includes multiple audio waveform graphs, each of which corresponds to a line graph about the ratio;

[0203] Identify the target line chart whose first similarity reaches the preset similarity threshold from the line charts in the preset database;

[0204] a second average value of the ratios in each target line graph is calculated, and a first difference value between the second average value and the first average value of each target line graph is calculated;

[0205] a matching value of each target line graph is determined based on the first difference value and the first similarity, and an audio waveform graph corresponding to a target line graph with the highest matching value is determined as the reference audio waveform graph.

[0206] In a possible implementation of the embodiment, the stability determination module 204 is specifically configured to:

[0207] a first number and a total time length of all inconsistent waveform segments are determined;

[0208] a target reference waveform segment is determined from the reference audio waveform graph based on a time interval of each inconsistent waveform segment;

[0209] a distance and an offset angle between a wave crest of each inconsistent waveform segment and a wave crest of the target reference waveform segment are determined;

[0210] a first abnormal value of the transformer is determined based on the first number, the total time length, the distance, and the offset angle;

[0211] a preset historical time period is divided into a plurality of sub-time periods, and the infrared video is segmented according to the sub-time periods to obtain a sub-video segment corresponding to each sub-time period;

[0212] a grayscale transformation is performed on each sub-video segment to obtain a corresponding sub-grayscale video segment, the transformer in each sub-grayscale video segment is divided into a plurality of regions, and a grayscale average value and a grayscale variance of each region in each sub-grayscale video segment are calculated;

[0213] a second abnormal value of the transformer is determined based on each grayscale average value and grayscale variance of each region;

[0214] a running stability of the transformer is determined based on the first abnormal value and the second abnormal value.

[0215] In a possible implementation of the embodiment, the stability determination module 204 is specifically configured to:

[0216] a deviation score of each inconsistent waveform segment is calculated based on the distance and the offset angle;

[0217] a candidate waveform segment whose deviation score reaches a preset score threshold is determined, and a deviation score average value of all candidate waveform segments is calculated;

[0218] The first abnormal value is obtained by performing calculation based on the first quantity, the total time length, the bias difference value and respective corresponding coefficients.

[0219] In a possible implementation of the embodiment of the application, the area determination module 205 is specifically configured to:

[0220] determine a maximum value of the gray scale of each area in each sub-gray scale video segment, and calculate a second difference value between the maximum value of the gray scale and an average value of the gray scale of the area;

[0221] determine a second quantity of the second difference value of each area that reaches a preset difference threshold in all sub-gray scale video segments;

[0222] calculate a proportion of the second quantity and a quantity of all sub-gray scale video segments;

[0223] calculate a third difference value between the average value of the gray scale of each sub-gray scale video segment of each area and a preset average threshold value of each area;

[0224] calculate a third difference average value based on all third difference values of each area;

[0225] determine a fault value of each area based on the proportion and the third difference average value;

[0226] multiply the running stability by the fault value of each area to obtain a probability of failure of each area;

[0227] determine an area in which the probability reaches a preset probability threshold as the area in which the transformer is likely to have a potential fault.

[0228] In a possible implementation of the embodiment of the application, the stability determination module 204 is specifically configured to:

[0229] determine a target variance of all gray scale average values based on the gray scale average values of each area about all sub-gray scale video segments;

[0230] determine an average value of all gray scale variances based on the gray scale variances of each area about all sub-gray scale video segments;

[0231] obtain the second abnormal value by performing calculation based on the target variance, the average value of all gray scale variances and respective corresponding coefficients.

[0232] In a possible implementation of the embodiment of the application, the transformer fault monitoring system 20 based on artificial intelligence further comprises:

[0233] The sending module is configured to send the area in which the potential fault is likely to occur to a terminal device of a worker.

[0234] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described transformer fault monitoring system 20 based on artificial intelligence can refer to the corresponding process in the foregoing method embodiments, which will not be repeated here.

[0235] An electronic device is provided in the embodiments of the present application, such as Figure 3 As shown in the figure, Figure 3 The electronic device 30 shown in the figure includes a processor 301 and a memory 303. Wherein, the processor 301 and the memory 303 are connected, such as connected through a bus 302. Optionally, the electronic device 30 can also include a transceiver 304. It should be noted that the transceiver 304 is not limited to one in actual application, and the structure of the electronic device 30 does not constitute a limitation on the embodiments of the present application.

[0236] The processor 301 can be a CPU (Central Processing Unit, central processor), a general-purpose processor, a DSP (Digital Signal Processor, data signal processor), an ASIC (Application Specific Integrated Circuit, application specific integrated circuit), an FPGA (Field Programmable Gate Array, field programmable gate array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It can realize or execute various exemplary logical blocks, modules and circuits described in combination with the disclosure content of the present application. The processor 301 can also be a combination of computing functions, such as one or more microprocessor combinations, combinations of DSP and microprocessor, etc.

[0237] The bus 302 can include a channel for transmitting information between the above-mentioned components. The bus 302 can be a PCI (Peripheral Component Interconnect, peripheral component interconnect) bus or an EISA (Extended Industry Standard Architecture, extended industry standard architecture) bus, etc. The bus 302 can be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, Figure 3 In the figure, only one thick line is used to represent, but it does not mean that there is only one bus or one type of bus.

[0238] The memory 303 can be a ROM (Read Only Memory) or other type of static storage device that can store static information and instructions, a RAM (Random Access Memory) or other type of dynamic storage device that can store information and instructions, an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer, but is not limited thereto.

[0239] The memory 303 is configured to store application program codes for implementing the solutions of the present application, and the processor 301 is configured to control the execution of the application program codes. The processor 301 is configured to execute the application program codes stored in the memory 303 to implement the content shown in the foregoing method embodiments.

[0240] The electronic device includes, but is not limited to, a mobile terminal such as a mobile phone, a notebook computer, a digital broadcast receiver, a PDA (Personal Digital Assistant), a PAD (Tablet Personal Computer), a PMP (Portable Multimedia Player), a car terminal (e.g., a car navigation terminal), and the like, and a stationary terminal such as a digital TV, a desktop computer, and the like. It can also be a server or the like. Figure 3 The electronic device shown is merely an example, and should not bring any limitation to the functions and use range of the embodiments of the present application.

[0241] The computer readable storage medium provided in the embodiment of the present application stores a computer program, and when the computer program runs on a computer, the computer can execute the corresponding content in the foregoing method embodiment. Compared with the related art, the current data, temperature data, infrared video, load data and audio waveform graph during running in the preset historical time period in the embodiment of the present application facilitate subsequent analysis of the area where the transformer may fail according to the running condition of the transformer in this period of time. The current data, temperature data and load data are all key factors representing the running environment of the transformer, the audio waveform graph is the sound emitted by the transformer during running, and the infrared video represents the temperature performance of each area of the transformer during running. That is, the audio waveform graph and the infrared video of each area are responses made by the transformer in the running environment. According to the audio waveform graph, the area where the transformer may fail can be analyzed. Therefore, the reference audio waveform graph is found from the preset database according to the current data and the like, the reference audio waveform graph represents the sound emitted by the transformer during normal running in a situation similar to the running environment of the transformer, the inconsistent waveform segment in the audio waveform graph is obtained by comparing the reference audio waveform graph with the audio waveform graph, and the running stability of the transformer can be determined by comprehensively analyzing the inconsistent waveform graph and the infrared image. The higher the running stability is, the more stable the overall running condition of the transformer is, and the less likely the potential failure position is. Conversely, the more likely the failure position is. Therefore, the area where the transformer may have a potential failure can be analyzed according to the running stability and the infrared image, and the accurate position where the transformer may have a potential failure is finally found.

[0242] It should be understood that although each step in the flowchart of the accompanying drawings is displayed in sequence according to the indication of the arrow, these steps are not necessarily executed in sequence according to the indication of the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and they can be executed in other sequences. Moreover, at least part of the steps in the flowchart of the accompanying drawings can include multiple sub-steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence is not necessarily sequential, but can be executed in rotation or alternation with at least part of other steps or sub-steps or stages of other steps.

[0243] The above only describes some embodiments of the present application, and it should be noted that those skilled in the art can make some improvements and refinements without departing from the principles of the present application, and these improvements and refinements should also be regarded as the protection scope of the present application.

Claims

1. An artificial intelligence based transformer fault monitoring method, characterized by, The method comprises: obtaining current data, temperature data, infrared video, load data and audio waveform diagram of the transformer in a preset historical time period; finding a reference audio waveform diagram from a preset database based on the current data, temperature data and load data; comparing the reference audio waveform diagram with the audio waveform diagram to determine an inconsistent waveform segment in the audio waveform diagram; determining the operation stability of the transformer based on the inconsistent waveform segment and the infrared video; determining the area where potential failure of the transformer may occur according to the operation stability and the infrared video; wherein the operation stability of the transformer is determined based on the inconsistent waveform segment and the infrared video, comprising: determining a first number and a total time length of all inconsistent waveform segments; determining a target reference waveform segment from the reference audio waveform diagram based on the time interval of each inconsistent waveform segment; determining the distance and the offset angle between the peak of each inconsistent waveform segment and the peak of the target reference waveform segment; determining a first abnormal value of the transformer based on the first number, the total time length, the distance and the offset angle; dividing the preset historical time period into a plurality of sub-time periods, and segmenting the infrared video according to the sub-time periods to obtain a sub-video segment corresponding to each sub-time period; performing gray scale transformation on each sub-video segment to obtain a corresponding sub-gray scale video segment, segmenting the transformer in each sub-gray scale video segment into a plurality of areas, and calculating the average gray scale value and the gray scale variance of each area in each sub-gray scale video segment; determining a second abnormal value of the transformer based on each average gray scale value and each gray scale variance of each area; determining the operation stability of the transformer based on the first abnormal value and the second abnormal value.

2. The method of claim 1, wherein the method is based on artificial intelligence. The reference audio waveform diagram is found from the preset database based on the current data, temperature data and load data, comprising: determining the current data, temperature data and load data at the same time; calculating the product of the current data and the load data at the same time, and calculating the ratio of the product to the temperature data at the corresponding time; calculating a first average value of all ratios, and generating a ratio line graph based on all ratios of the preset historical time period; calculating a first similarity between the line graph and the line graphs in the preset database, wherein the preset database includes a plurality of audio waveform graphs, and each audio waveform graph corresponds to a ratio line graph; determining a target line graph with a first similarity reaching a preset similarity threshold from the line graphs in the preset database; calculating a second average value of the ratio in each target line graph, and calculating a first difference value between the second average value and the first average value of each target line graph; determining a matching value of each target line graph based on the first difference value and the first similarity, and determining the audio waveform graph corresponding to the target line graph with the highest matching value as the reference audio waveform graph.

3. The method of claim 1, wherein the method further comprises: The first abnormal value of the transformer is determined based on the first number, the total time length, the distance and the offset angle, comprising: calculating an offset score of each inconsistent waveform segment based on the distance and the offset angle; determine a candidate waveform segment whose offset score reaches a preset score threshold, and calculate an average value of offset scores of all candidate waveform segments; the first abnormal value is calculated based on the first number, the total time length, the offset score, and respective corresponding coefficients.

4. The method of claim 1, wherein the method is based on artificial intelligence. determine the area where the transformer is likely to have a potential fault according to the operation stability and the infrared video, including: determine a maximum gray value of each area in each sub-gray video segment, and calculate a second difference value between the maximum gray value and a gray average value of the area; determine a second number of each area whose second difference value reaches a preset difference threshold in all sub-gray video segments; calculate a proportion of the second number to a number of all sub-gray video segments; calculate a third difference value between a gray average value of each sub-gray video segment of each area and a preset average value threshold of each area; calculate a third difference average value based on all third difference values of each area; determine a fault value of each area based on the proportion and the third difference average value; multiply the operation stability by the fault value of each area to obtain a probability of failure of each area; determine the area where the probability reaches a preset probability threshold as the area where the transformer is likely to have a potential fault.

5. The method of claim 1, wherein the method further comprises: the second abnormal value of the transformer is determined based on each gray average value and a gray variance of each area, including: determine a target variance of all gray average values based on the gray average values of each area with respect to all sub-gray video segments; determine an average value of all gray variances based on the gray variances of each area with respect to all sub-gray video segments; the second abnormal value is calculated based on the target variance, the average value of all gray variances, and respective corresponding coefficients.

6. The method of claim 1, wherein the method is based on artificial intelligence. the method further includes: send the area where the potential fault is likely to occur to a terminal device of a worker.

7. An artificial intelligence based transformer fault monitoring system characterized in that, including: a data acquisition module configured to acquire current data, temperature data, infrared video, load data, and an audio waveform graph during operation of the transformer in a preset historical time period; a search module configured to search for a reference audio waveform graph from a preset database based on the current data, the temperature data, and the load data; a comparison module configured to compare the reference audio waveform graph with the audio waveform graph to determine an inconsistent waveform segment in the audio waveform graph; a stability determination module configured to determine an operation stability of the transformer based on the inconsistent waveform segment and the infrared video; an area determination module configured to determine an area where the transformer is likely to have a potential fault according to the operation stability and the infrared video; when determining the operation stability of the transformer based on the inconsistent waveform segment and the infrared video, the stability determination module is specifically configured to: determine a first number and a total time length of all inconsistent waveform segments; determine a target reference waveform segment from the reference audio waveform graph based on a time interval of each inconsistent waveform segment; determine a distance and an offset angle between a wave peak of each inconsistent waveform segment and a wave peak of the target reference waveform segment; determine a first abnormal value of the transformer based on the first number, the total time length, the distance, and the offset angle; The preset historical time period is divided into a plurality of sub time periods, and the infrared video is segmented according to the sub time periods to obtain a sub video segment corresponding to each sub time period; Each sub video segment is subjected to a gray scale transformation to obtain a corresponding sub gray scale video segment, the transformer in each sub gray scale video segment is divided into a plurality of regions, and the gray scale average value and the gray scale variance of each region in each sub gray scale video segment are calculated; The second abnormal value of the transformer is determined based on each gray scale average value and the gray scale variance of each region; The running stability of the transformer is determined based on the first abnormal value and the second abnormal value.

8. An electronic device, comprising: It comprises: at least one processor; a memory; at least one application program, wherein the at least one application program is stored in the memory and is configured to be executed by the at least one processor, and the at least one application program is used to execute an artificial intelligence-based transformer fault monitoring method according to any one of claims 1-6.

9. A computer-readable storage medium having stored thereon a computer program, characterized in that, When the computer program is executed in the computer, the computer executes an artificial intelligence-based transformer fault monitoring method according to any one of claims 1-6.

Images