Intelligent box transformer substation maintenance management system and method

Abstract

The invention relates to the technical field of box-type transformer maintenance, and particularly discloses an intelligent box-type transformer maintenance management system and method, and the system comprises a voltage calculation module which is used for obtaining the power supply voltage of a box-type transformer, and determining a maintenance index according to the power supply voltage of the box-type transformer; the vibration calculation module is used for acquiring a vibration signal of the box-type transformer and determining a maintenance threshold value according to the vibration signal of the box-type transformer; the period setting module is used for determining a maintenance period according to the maintenance index and the maintenance threshold value; and the strategy setting module is used for acquiring internal component parameters of the to-be-maintained box-type transformer and determining a maintenance strategy of the to-be-maintained box-type transformer according to the internal component parameters. According to the invention, the fault of the box-type transformer can be detected in time, the fault part can be positioned, the corresponding maintenance strategy can be generated, and the management and maintenance of equipment can be scientifically guided.

Description

Technical Field

[0001] The present application relates to the technical field of box-type transformer maintenance, and more specifically, to an intelligent box-type transformer maintenance management system and method. Background Art

[0002] As the basic equipment for power transmission and distribution, transformers are widely used in industries, agriculture, transportation, urban communities and other fields. There are about 17 million transformers in operation in my country, with a total capacity of about 11 billion kilovolt-amperes. Transformer losses account for about 40% of power transmission and distribution losses, and have great energy-saving potential. As a complete set of power distribution equipment, the box-type transformer is an organic combination of transformers, high-voltage voltage control equipment, and low-voltage voltage control equipment. Its basic principle is to reasonably assemble the pressure starting system, armored wire, substation automatic system, DC point and corresponding technical equipment in the prescribed order, and install all components in a specific waterproof, dustproof and rat-proof fully sealed tempered box structure to form a specific transformer. At present, box-type transformers have been widely used in power engineering construction.

[0003] The fault detection method for box-type transformers in the prior art is relatively simple, and it is impossible to timely and accurately determine the cause of the fault, and the detection result is poor and the error is high. Summary of the invention

[0004] The present invention provides an intelligent box-type transformer maintenance management system and method, which is used to solve the problem of poor fault detection results and high errors of box-type transformers in the prior art, including:

[0005] A voltage calculation module is used to obtain the power supply voltage of the box-type transformer and determine the maintenance index according to the power supply voltage of the box-type transformer;

[0006] A vibration calculation module is used to obtain a vibration signal of the box-type transformer and determine a maintenance threshold value according to the vibration signal of the box-type transformer;

[0007] A cycle setting module is used to determine the maintenance cycle according to the maintenance index and the maintenance threshold;

[0008] The strategy setting module is used to obtain the internal component parameters of the box-type transformer to be repaired, and determine the maintenance strategy of the box-type transformer to be repaired according to the internal component parameters.

[0009] Furthermore, the voltage calculation module determines the maintenance index according to the power supply voltage of the box-type transformer, including:

[0010] Obtain the historical power supply voltage of the box-type transformer, and determine the historical power supply voltage curve according to the historical power supply voltage of the box-type transformer;

[0011] Based on the k-shape clustering algorithm, the historical power supply voltage change curves are clustered to obtain k voltage curve classifications, and the typical voltage curves of each voltage curve classification are determined according to the clustering results;

[0012] Obtaining the current supply voltage of the box-type transformer, determining the current voltage curve classification according to the current supply voltage of the box-type transformer, and obtaining a typical voltage curve of the current voltage curve classification;

[0013] The voltage deviation coefficient is calculated according to the typical voltage curve classified according to the current voltage curve, and the maintenance index is determined according to the voltage deviation coefficient.

[0014] Furthermore, clustering the historical power supply voltage change curves based on the k-shape clustering algorithm includes:

[0015] Normalizing the historical power supply voltage change curve, and establishing a voltage curve data set according to the normalized historical power supply voltage change curve;

[0016] Obtain a preset k value, determine an initial cluster center according to the preset k value, and calculate a shape distance from a power supply voltage change curve in a voltage curve data set to the initial cluster center;

[0017] Divide each supply voltage change curve into a corresponding cluster according to the shape distance between the supply voltage change curve and the initial cluster center;

[0018] The cluster center is updated and repeated iterations are performed until the degree of change of the new cluster center is less than a first preset threshold, thereby obtaining k voltage curve classifications.

[0019] Further, the calculating of the voltage deviation coefficient according to the typical voltage curve classified according to the current voltage curve includes:

[0020] Obtaining a current power supply voltage change curve of the box-type transformer, screening out a peak point of the current power supply voltage change curve, and setting a period between two adjacent peak points in the current power supply voltage change curve as a preset period;

[0021] Obtaining the supply voltage of the current supply voltage change curve within a preset period, and calculating the average voltage value according to the supply voltage of the current supply voltage change curve within the preset period;

[0022] Obtaining a typical voltage curve of the current voltage curve classification, and determining a supply voltage of the typical voltage curve within a preset period according to the typical voltage curve of the current voltage curve classification;

[0023] The typical voltage value is determined according to the supply voltage of the typical voltage curve within a preset period, the difference between each average voltage value and the corresponding typical voltage value is calculated, and the difference between each average voltage value and the corresponding typical voltage value on the current supply voltage change curve is summed to obtain the deviation coefficient of the supply voltage.

[0024] Furthermore, the vibration calculation module determines the maintenance threshold according to the vibration signal of the box-type transformer, including:

[0025] Preprocess the vibration signal of the box-type transformer, transform the preprocessed vibration signal from time domain to frequency domain based on fast Fourier transform, and obtain a vibration signal spectrum diagram;

[0026] The vibration signal spectrum is divided into several spectrum segments, and the average amplitude value corresponding to the frequency point in each spectrum segment and the sum of the amplitudes of all frequency points in the spectrum are calculated;

[0027] The ratio of the amplitude average value to the amplitude sum is calculated, the frequency corresponding to the spectrum segment with the largest ratio of the amplitude average value to the amplitude sum is determined as the vibration characteristic value, and the maintenance threshold is determined according to the vibration characteristic value.

[0028] Further, determining the maintenance threshold according to the vibration characteristic value includes:

[0029] The maintenance threshold is calculated using the following formula:

[0030]

[0031] Among them, M is the maintenance threshold, M α is the preset standard maintenance threshold, V is the vibration characteristic value, V α is the preset standard vibration characteristic value, R is the preset range coefficient, and exp is the natural exponential function.

[0032] Furthermore, the cycle setting module determines the maintenance cycle according to the maintenance index and the maintenance threshold, including:

[0033] Calculate the difference between the maintenance index and the maintenance threshold of the box-type transformer, determine whether the difference between the maintenance index and the maintenance threshold is greater than a second preset threshold, and if the difference between the maintenance index and the maintenance threshold is greater than the second preset threshold, set the first preset period as the maintenance period of the box-type transformer;

[0034] If the difference between the maintenance index and the maintenance threshold is less than or equal to the second preset threshold, determining whether the difference between the maintenance index and the maintenance threshold is greater than a third preset threshold;

[0035] If the difference between the maintenance index and the maintenance threshold is greater than the third preset threshold, the second preset period is set as the maintenance period of the box transformer;

[0036] If the difference between the maintenance index and the maintenance threshold is less than or equal to the third preset threshold, the third preset period is set as the maintenance period of the box transformer.

[0037] Furthermore, the strategy setting module determines the maintenance strategy of the box-type transformer to be maintained according to the internal component parameters, including:

[0038] Obtain the temperature value of the internal components of the box-type transformer to be repaired, and calculate the difference between the temperature value of the internal components of the box-type transformer to be repaired and a preset standard temperature threshold;

[0039] The faulty components are located according to the difference between the temperature value of the internal components of the box-type transformer to be repaired and the preset standard temperature threshold, a maintenance strategy model is established, and the temperature value of each faulty component is input into the maintenance strategy model to obtain the maintenance strategy of the box-type transformer to be repaired.

[0040] Furthermore, the establishment of the maintenance strategy model is specifically as follows:

[0041] Obtain historical maintenance data of the box-type transformer, and determine historical temperature values ​​of faulty components and corresponding historical maintenance strategies based on the historical maintenance data of the box-type transformer;

[0042] Preprocessing the historical temperature values ​​of the faulty components and the corresponding historical maintenance strategies, and establishing a training sample set according to the preprocessed historical temperature values ​​of the faulty components and the corresponding historical maintenance strategies;

[0043] An initial maintenance strategy model is established and trained according to the training sample set, and the trained initial maintenance strategy model is determined as the maintenance strategy model.

[0044] In order to achieve the above object, the present invention also provides an intelligent box-type transformer maintenance management method, comprising:

[0045] Obtain the power supply voltage of the box-type transformer, and determine the maintenance index according to the power supply voltage of the box-type transformer;

[0046] Acquire a vibration signal of the box-type transformer, and determine a maintenance threshold value according to the vibration signal of the box-type transformer;

[0047] Determine the maintenance cycle based on the maintenance index and maintenance threshold;

[0048] The internal component parameters of the box-type transformer to be repaired are obtained, and the maintenance strategy of the box-type transformer to be repaired is determined according to the internal component parameters.

[0049] The beneficial effects of the present invention are:

[0050] By applying the above technical scheme, the present invention obtains the maintenance index and maintenance threshold by real-time detection of the power supply voltage and vibration signal of the box-type transformer, so as to timely judge the abnormal state of the box-type transformer and set the corresponding maintenance cycle, thereby effectively improving the accuracy of the box-type transformer fault judgment, and determining the maintenance strategy through the internal component parameters of the box-type transformer to be repaired, which can accurately judge the cause of the failure of the box-type transformer to be repaired, and scientifically guide the management and maintenance of the equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0052] Figure 1 The following is a structural diagram of an intelligent box-type transformer maintenance management system proposed in an embodiment of the present invention;

[0053] Figure 2 The overall flow chart of an intelligent box-type transformer maintenance management method proposed in an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0054] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0055] The present application embodiment provides an intelligent box-type transformer maintenance management system, such as Figure 1 As shown, including:

[0056] The voltage calculation module is used to obtain the power supply voltage of the box-type transformer and determine the maintenance index according to the power supply voltage of the box-type transformer; the vibration calculation module is used to obtain the vibration signal of the box-type transformer and determine the maintenance threshold according to the vibration signal of the box-type transformer; the cycle setting module is used to determine the maintenance cycle according to the maintenance index and the maintenance threshold; the strategy setting module is used to obtain the internal component parameters of the box-type transformer to be repaired and determine the maintenance strategy of the box-type transformer to be repaired according to the internal component parameters.

[0057] In this embodiment, a voltmeter, a vibration sensor device and a temperature sensor device are arranged on the box-type transformer to collect the output voltage, vibration signal and component temperature of the box-type transformer in real time. The internal components specifically include the core, winding, terminal board, etc. The maintenance cycle of the box-type transformer is determined by the cycle setting module. After the maintenance cycle is reached, the strategy setting module outputs the maintenance strategy through the temperature parameters of the internal components, and the maintenance personnel repair the box-type transformer according to the maintenance strategy.

[0058] In some embodiments of the present application, the voltage calculation module determines the maintenance index based on the power supply voltage of the box-type transformer, including: obtaining the historical power supply voltage of the box-type transformer, and determining the historical power supply voltage curve based on the historical power supply voltage of the box-type transformer; clustering the historical power supply voltage change curve based on the k-shape clustering algorithm to obtain k voltage curve classifications, and determining the typical voltage curve of each voltage curve classification based on the clustering results; obtaining the current power supply voltage of the box-type transformer, determining the current voltage curve classification based on the current power supply voltage of the box-type transformer, and obtaining the typical voltage curve of the current voltage curve classification; calculating the voltage deviation coefficient based on the typical voltage curve of the current voltage curve classification, and determining the maintenance index based on the voltage deviation coefficient.

[0059] In this embodiment, the historical power supply voltage curves of several power supply cycles are obtained according to the historical power supply voltage of the box-type transformer during the power supply cycle, so as to determine the classification of each voltage curve and the corresponding typical voltage curve. The typical voltage curve is the voltage curve that is closest to the shape distance of the cluster center in the voltage curve classification. The voltage curve classification of the current power supply voltage is determined according to the shape distance between the current power supply voltage and the cluster center, so as to obtain the maintenance index of the current box-type transformer.

[0060] In some embodiments of the present application, the clustering of historical power supply voltage change curves based on the k-shape clustering algorithm includes: normalizing the historical power supply voltage change curves, and establishing a voltage curve data set based on the normalized historical power supply voltage change curves; obtaining a preset k value, determining an initial clustering center based on the preset k value, and calculating the shape distance from the power supply voltage change curve in the voltage curve data set to the initial clustering center; dividing each power supply voltage change curve into a corresponding cluster based on the shape distance from the power supply voltage change curve to the initial clustering center; updating the clustering center and performing repeated iterations until the degree of change of the new clustering center is less than a first preset threshold, thereby obtaining k voltage curve classifications.

[0061] In this embodiment, by using the k-shape clustering algorithm to cluster the historical power supply voltage change curves, the time delay and pattern matching problems of the power supply voltage change curves can be better handled, the true shape similarity of the curves is reflected, and the accuracy and reliability of the clustering results are improved.

[0062] In this embodiment, the historical power supply voltage change curve is divided by its corresponding modulus to complete the normalization processing of the historical power supply voltage change curve. The preset k value is set to 3. The calculation formula of the shape distance is as follows:

[0063]

[0064] Among them, SBD(μ,u i ) is the shape distance, C w is the mutual correlation coefficient, w is the sum of the series of supply voltage change curves, R0 is the mutual correlation value when completely similar curves do not have relative displacement, μ is the initial cluster center, u i This is the supply voltage variation curve.

[0065] In this embodiment, the cluster center is updated according to the following formula:

[0066]

[0067] Among them, μ ′ is the updated cluster center, P k is the k-th cluster.

[0068] In some embodiments of the present application, the voltage deviation coefficient is calculated according to the typical voltage curve classified according to the current voltage curve, including: obtaining the current power supply voltage change curve of the box-type transformer, screening out the peak point of the current power supply voltage change curve, and setting the time period between two adjacent peak points in the current power supply voltage change curve as a preset period; obtaining the supply voltage of the current power supply voltage change curve within the preset period, and calculating the average voltage value according to the supply voltage of the current power supply voltage change curve within the preset period; obtaining the typical voltage curve classified by the current voltage curve, and determining the supply voltage of the typical voltage curve within the preset period according to the typical voltage curve classified by the current voltage curve; determining the typical voltage value according to the supply voltage of the typical voltage curve within the preset period, calculating the difference between each average voltage value and the corresponding typical voltage value, and summing the difference between each average voltage value and the corresponding typical voltage value on the current power supply voltage change curve to obtain the deviation coefficient of the supply voltage.

[0069] In this embodiment, when the box-type transformer operates stably, its output voltage shows periodic changes. Therefore, the time period between two adjacent peak points in the current power supply voltage change curve is set as a preset cycle to obtain the average voltage value. The average voltage value within the preset cycle of the typical voltage curve is used as the typical voltage value to calculate the deviation coefficient of the power supply voltage.

[0070] In some embodiments of the present application, the vibration calculation module determines the maintenance threshold based on the vibration signal of the box-type transformer, including: preprocessing the vibration signal of the box-type transformer, transforming the preprocessed vibration signal from time domain to frequency domain based on fast Fourier transform, and obtaining a vibration signal spectrum diagram; dividing the vibration signal spectrum diagram into several spectrum segments, calculating the amplitude average value corresponding to the frequency points in each spectrum segment and the sum of the amplitudes of all frequency points in the spectrum diagram; calculating the ratio of the amplitude average value to the amplitude sum, determining the frequency corresponding to the spectrum segment with the largest ratio of the amplitude average value to the amplitude sum as the vibration characteristic value, and determining the maintenance threshold according to the vibration characteristic value.

[0071] In some embodiments of the present application, determining the maintenance threshold according to the vibration characteristic value includes: calculating the maintenance threshold using the following formula:

[0072]

[0073] Among them, M is the maintenance threshold, M α is the preset standard maintenance threshold, V is the vibration characteristic value, V α is the preset standard vibration characteristic value, R is the preset range coefficient, and exp is the natural exponential function.

[0074] In this embodiment, the energy ratio of each spectrum segment is obtained by calculating the ratio of the amplitude average value to the amplitude sum of each spectrum segment, and the frequency corresponding to the spectrum segment with the highest energy ratio is screened out to obtain the vibration characteristic value. The preset standard maintenance threshold is corrected by the vibration characteristic value, so that the system can promptly determine whether the vibration signal of the box-type transformer is abnormal.

[0075] In some embodiments of the present application, the cycle setting module determines the maintenance cycle based on the maintenance index and the maintenance threshold, including: calculating the difference between the maintenance index and the maintenance threshold of the box-type transformer, judging whether the difference between the maintenance index and the maintenance threshold is greater than a second preset threshold, if the difference between the maintenance index and the maintenance threshold is greater than the second preset threshold, setting the first preset cycle as the maintenance cycle of the box transformer; if the difference between the maintenance index and the maintenance threshold is less than or equal to the second preset threshold, judging whether the difference between the maintenance index and the maintenance threshold is greater than a third preset threshold; if the difference between the maintenance index and the maintenance threshold is greater than the third preset threshold, setting the second preset cycle as the maintenance cycle of the box transformer; if the difference between the maintenance index and the maintenance threshold is less than or equal to the third preset threshold, setting the third preset cycle as the maintenance cycle of the box transformer.

[0076] In this embodiment, the greater the difference between the maintenance index and the maintenance threshold, the higher the degree of abnormality of the box-type transformer. Therefore, the first preset period is set to be less than the second preset period and less than the third preset period. The maintenance period of the box-type transformer is set by the difference between the maintenance index and the maintenance threshold, so that maintenance personnel can repair the abnormal box-type transformer in time.

[0077] In some embodiments of the present application, the strategy setting module determines the maintenance strategy of the box-type transformer to be repaired based on the internal component parameters, including: obtaining the temperature value of the internal component of the box-type transformer to be repaired, and calculating the difference between the temperature value of the internal component of the box-type transformer to be repaired and a preset standard temperature threshold; locating the faulty component based on the difference between the temperature value of the internal component of the box-type transformer to be repaired and the preset standard temperature threshold, establishing a maintenance strategy model, inputting the temperature value of each faulty component into the maintenance strategy model, and obtaining the maintenance strategy of the box-type transformer to be repaired.

[0078] In some embodiments of the present application, the establishment of the maintenance strategy model is specifically: obtaining historical maintenance data of the box-type transformer, determining the historical temperature value of the faulty component and the corresponding historical maintenance strategy based on the historical maintenance data of the box-type transformer; preprocessing the historical temperature value of the faulty component and the corresponding historical maintenance strategy, and establishing a training sample set based on the preprocessed historical temperature value of the faulty component and the corresponding historical maintenance strategy; establishing an initial maintenance strategy model based on the training sample set and training it, and determining the trained initial maintenance strategy model as the maintenance strategy model.

[0079] In this embodiment, after the box-type transformer reaches the maintenance cycle, a preset standard temperature threshold is set for each component, and the internal component whose temperature value exceeds the preset standard temperature threshold is determined as a faulty component and the location of the faulty component is obtained. By inputting the temperature value of each faulty component into the maintenance strategy model, the corresponding maintenance strategy is obtained.

[0080] Based on the same technical concept, such as Figure 2 As shown, the present invention also provides an intelligent box-type transformer maintenance management method, comprising:

[0081] S101, obtaining a power supply voltage of the box-type transformer, and determining a maintenance index according to the power supply voltage of the box-type transformer;

[0082] S102, obtaining a vibration signal of the box-type transformer, and determining a maintenance threshold according to the vibration signal of the box-type transformer;

[0083] S103, determining a maintenance cycle according to the maintenance index and the maintenance threshold;

[0084] S104, obtaining parameters of internal components of the box-type transformer to be repaired, and determining a maintenance strategy for the box-type transformer to be repaired according to the parameters of the internal components.

[0085] By applying the above technical solutions, the present invention uses a voltage calculation module to obtain the power supply voltage of the box-type transformer, and determines the maintenance index according to the power supply voltage of the box-type transformer; a vibration calculation module to obtain the vibration signal of the box-type transformer, and determines the maintenance threshold according to the vibration signal of the box-type transformer; a cycle setting module to determine the maintenance cycle according to the maintenance index and the maintenance threshold; a strategy setting module to obtain the internal component parameters of the box-type transformer to be repaired, and determine the maintenance strategy of the box-type transformer to be repaired according to the internal component parameters. The present invention can detect the fault of the box-type transformer in time and locate the faulty component, and generate the corresponding maintenance strategy at the same time, and scientifically guide the management and maintenance of the equipment.

[0086] Through the description of the above implementation methods, those skilled in the art can clearly understand that the present invention can be implemented by hardware, or by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each implementation scenario of the present invention.

[0087] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. An intelligent box-type transformer maintenance management system, characterized in that: include: A voltage calculation module is used to obtain the power supply voltage of the box-type transformer and determine the maintenance index according to the power supply voltage of the box-type transformer; A vibration calculation module is used to obtain a vibration signal of the box-type transformer and determine a maintenance threshold value according to the vibration signal of the box-type transformer; A cycle setting module is used to determine the maintenance cycle according to the maintenance index and the maintenance threshold; The strategy setting module is used to obtain the internal component parameters of the box-type transformer to be repaired, and determine the maintenance strategy of the box-type transformer to be repaired according to the internal component parameters.

2. The intelligent box-type transformer maintenance management system according to claim 1 is characterized in that: The voltage calculation module determines the maintenance index according to the power supply voltage of the box-type transformer, including: Obtain the historical power supply voltage of the box-type transformer, and determine the historical power supply voltage curve according to the historical power supply voltage of the box-type transformer; Based on the k-shape clustering algorithm, the historical power supply voltage change curves are clustered to obtain k voltage curve classifications, and the typical voltage curves of each voltage curve classification are determined according to the clustering results; Obtaining the current supply voltage of the box-type transformer, determining the current voltage curve classification according to the current supply voltage of the box-type transformer, and obtaining a typical voltage curve of the current voltage curve classification; The voltage deviation coefficient is calculated according to the typical voltage curve classified according to the current voltage curve, and the maintenance index is determined according to the voltage deviation coefficient.

3. The intelligent box-type transformer maintenance management system according to claim 2 is characterized in that: The clustering of the historical power supply voltage change curve based on the k-shape clustering algorithm includes: Normalizing the historical power supply voltage change curve, and establishing a voltage curve data set according to the normalized historical power supply voltage change curve; Obtain a preset k value, determine an initial cluster center according to the preset k value, and calculate a shape distance from a power supply voltage change curve in a voltage curve data set to the initial cluster center; Divide each supply voltage change curve into a corresponding cluster according to the shape distance between the supply voltage change curve and the initial cluster center; The cluster center is updated and repeated iterations are performed until the degree of change of the new cluster center is less than a first preset threshold, thereby obtaining k voltage curve classifications.

4. The intelligent box-type transformer maintenance management system according to claim 2 is characterized in that: The calculating of the voltage deviation coefficient according to the typical voltage curve classified according to the current voltage curve includes: Obtaining a current power supply voltage change curve of the box-type transformer, screening out a peak point of the current power supply voltage change curve, and setting a period between two adjacent peak points in the current power supply voltage change curve as a preset period; Obtaining the supply voltage of the current supply voltage change curve within a preset period, and calculating the average voltage value according to the supply voltage of the current supply voltage change curve within the preset period; Obtaining a typical voltage curve of the current voltage curve classification, and determining a supply voltage of the typical voltage curve within a preset period according to the typical voltage curve of the current voltage curve classification; The typical voltage value is determined according to the supply voltage of the typical voltage curve within a preset period, the difference between each average voltage value and the corresponding typical voltage value is calculated, and the difference between each average voltage value and the corresponding typical voltage value on the current supply voltage change curve is summed to obtain the deviation coefficient of the supply voltage.

5. The intelligent box-type transformer maintenance management system according to claim 1 is characterized in that: The vibration calculation module determines the maintenance threshold according to the vibration signal of the box-type transformer, including: Preprocess the vibration signal of the box-type transformer, transform the preprocessed vibration signal from time domain to frequency domain based on fast Fourier transform, and obtain a vibration signal spectrum diagram; The vibration signal spectrum is divided into several spectrum segments, and the average amplitude value corresponding to the frequency point in each spectrum segment and the sum of the amplitudes of all frequency points in the spectrum are calculated; The ratio of the amplitude average value to the amplitude sum is calculated, the frequency corresponding to the spectrum segment with the largest ratio of the amplitude average value to the amplitude sum is determined as the vibration characteristic value, and the maintenance threshold is determined according to the vibration characteristic value.

6. The intelligent box-type transformer maintenance management system according to claim 5 is characterized in that: Determining the maintenance threshold according to the vibration characteristic value includes: The maintenance threshold is calculated using the following formula: Among them, M is the maintenance threshold, M α is the preset standard maintenance threshold, V is the vibration characteristic value, V α is the preset standard vibration characteristic value, R is the preset range coefficient, and exp is the natural exponential function.

7. The intelligent box-type transformer maintenance management system according to claim 1 is characterized in that: The cycle setting module determines the maintenance cycle according to the maintenance index and the maintenance threshold, including: Calculate the difference between the maintenance index and the maintenance threshold of the box-type transformer, determine whether the difference between the maintenance index and the maintenance threshold is greater than a second preset threshold, and if the difference between the maintenance index and the maintenance threshold is greater than the second preset threshold, set the first preset period as the maintenance period of the box-type transformer; If the difference between the maintenance index and the maintenance threshold is less than or equal to the second preset threshold, determining whether the difference between the maintenance index and the maintenance threshold is greater than a third preset threshold; If the difference between the maintenance index and the maintenance threshold is greater than the third preset threshold, the second preset period is set as the maintenance period of the box transformer; If the difference between the maintenance index and the maintenance threshold is less than or equal to the third preset threshold, the third preset period is set as the maintenance period of the box transformer.

8. The intelligent box-type transformer maintenance management system according to claim 1 is characterized in that: The strategy setting module determines the maintenance strategy of the box-type transformer to be maintained according to the internal component parameters, including: Obtain the temperature value of the internal components of the box-type transformer to be repaired, and calculate the difference between the temperature value of the internal components of the box-type transformer to be repaired and a preset standard temperature threshold; The faulty components are located according to the difference between the temperature value of the internal components of the box-type transformer to be repaired and the preset standard temperature threshold, a maintenance strategy model is established, and the temperature value of each faulty component is input into the maintenance strategy model to obtain the maintenance strategy of the box-type transformer to be repaired.

9. The intelligent box-type transformer maintenance management system according to claim 8 is characterized in that: The specific steps of establishing the maintenance strategy model are as follows: Obtain historical maintenance data of the box-type transformer, and determine historical temperature values ​​of faulty components and corresponding historical maintenance strategies based on the historical maintenance data of the box-type transformer; Preprocessing the historical temperature values ​​of the faulty components and the corresponding historical maintenance strategies, and establishing a training sample set according to the preprocessed historical temperature values ​​of the faulty components and the corresponding historical maintenance strategies; An initial maintenance strategy model is established and trained according to the training sample set, and the trained initial maintenance strategy model is determined as the maintenance strategy model.

10. An intelligent box-type transformer maintenance management method, characterized in that: include: Obtain the power supply voltage of the box-type transformer, and determine the maintenance index according to the power supply voltage of the box-type transformer; Acquire a vibration signal of the box-type transformer, and determine a maintenance threshold value according to the vibration signal of the box-type transformer; Determine the maintenance cycle based on the maintenance index and maintenance threshold; The internal component parameters of the box-type transformer to be repaired are obtained, and the maintenance strategy of the box-type transformer to be repaired is determined according to the internal component parameters.

Images