A kind of box-type substation monitoring method and device, system, storage medium

Abstract

The application provides a kind of box-type substation monitoring method and device, system, storage medium, belong to substation monitoring technical field, this method includes: based on the discharge data of box-type substation that first ultrasonic wave data is corrected to the electromagnetic pulse data collected by electromagnetic sensor in box-type substation;Box-type substation discharge data is compared with preset threshold value, whether the fault of box-type substation occurs is judged;Wherein, first ultrasonic wave data is the data collected by ultrasonic sensor in different positions in box-type substation;In response to the fault of box-type substation, the fault position of box-type substation is determined based on discharge data using time difference positioning method;Based on fault position, the operation state data of box-type substation is analyzed to determine fault type, and the parameters of box-type substation are compensated based on the compensation mode corresponding to different fault types.The application adopts multi-modal compensation strategy based on fault type, to improve the power supply reliability of box-type substation.

Description

Technical Field

[0001] The present application belongs to the technical field of substation monitoring, and more specifically, relates to a box-type substation monitoring method and device, system, and storage medium. Background Art

[0002] In power systems, box-type substations are key equipment for power distribution and control, and their stable operation is crucial to the entire power network. Traditional box-type substation fault monitoring relies heavily on simple electrical parameter measurements. This lacks accuracy and cannot accurately locate the fault, making it difficult to meet the power supply reliability requirements of modern smart grids. Summary of the Invention

[0003] The purpose of this application is to provide a box-type substation monitoring method and device, system, and storage medium to improve the accuracy of box-type substation fault location, and then perform targeted processing based on the fault location to improve the power supply reliability of the box-type substation.

[0004] A first aspect of an embodiment of the present application provides a box-type substation monitoring method, comprising:

[0005] The first ultrasonic data is corrected based on the electromagnetic pulse data collected by the electromagnetic sensor in the box-type substation to obtain the discharge data of the box-type substation; wherein the first ultrasonic data is data collected by the ultrasonic sensors at different locations in the box-type substation;

[0006] Comparing the discharge data of the box-type substation with a preset threshold to determine whether the box-type substation has a fault;

[0007] In response to a fault in the box-type substation, the fault location of the box-type substation is determined using the time difference positioning method based on the discharge data; the operating status data of the box-type substation is analyzed based on the fault location to determine the fault type, and the parameters of the box-type substation are compensated based on the compensation methods corresponding to different fault types.

[0008] A second aspect of the embodiments of the present application provides a box-type substation monitoring device, comprising:

[0009] A data correction module, configured to correct the first ultrasonic data based on the electromagnetic pulse data collected by the electromagnetic sensor in the box-type substation to obtain the discharge data of the box-type substation; wherein the first ultrasonic data is data collected by ultrasonic sensors at different locations in the box-type substation;

[0010] A fault judgment module is used to compare the discharge data of the box-type substation with a preset threshold value to determine whether the box-type substation has a fault;

[0011] The compensation module is configured to, in response to a fault of the box-type substation, determine a fault position of the box-type substation based on the discharge data by using a time-difference positioning method; analyze operation state data of the box-type substation based on the fault position to determine a fault type, and compensate parameters of the box-type substation based on a compensation mode corresponding to the fault type.

[0012] In a third aspect, the embodiment of the present application provides a box-type substation monitoring system, including a memory, a processor, and a computer program stored in the memory and running on the processor, and the processor implements the steps of the box-type substation monitoring method.

[0013] In a fourth aspect, the embodiment of the present application provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the steps of the box-type substation monitoring method.

[0014] The box-type substation monitoring method and device, system, and storage medium provided by the embodiment of the present application have the following beneficial effects.

[0015] The embodiment of the present application effectively solves the key problems of low precision and difficult positioning of the traditional monitoring technology through multi-physical field data fusion and intelligent compensation mechanism. The embodiment of the present application overcomes the limitation of a single sensor by using electromagnetic-ultrasonic signal space-time correction technology, improves the sensitivity of discharge detection, and can more accurately locate the fault position. Secondly, for the fault position, the embodiment of the present application adopts a multi-modal compensation strategy based on the fault type, which can compensate the voltage or reactive power output by the box-type substation, significantly improve the service life of the equipment, improve the power supply reliability of the box-type substation, and meet the power supply demand of the load. BRIEF DESCRIPTION OF DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without any creative effort based on these drawings.

[0017] Figure 1 A flowchart of a box-type substation monitoring method provided by an embodiment of the present application is shown in the figure.

[0018] Figure 2 A structural block diagram of a box-type substation monitoring device provided by an embodiment of the present application is shown in the figure.

[0019] Figure 3 A schematic block diagram of a box-type substation monitoring system provided by an embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0020] In the following description, specific details such as specific system structures and techniques are provided for purposes of illustration rather than limitation to facilitate a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obscuring the description of the present application with unnecessary detail.

[0021] In order to make the purpose, technical solutions and advantages of this application clearer, specific embodiments will be described below with reference to the accompanying drawings.

[0022] Please refer to Figure 1 , Figure 1 This is a flow chart of a method for monitoring a box-type substation provided in one embodiment of the present application, the method comprising:

[0023] S101: Correcting first ultrasonic data based on electromagnetic pulse data collected by electromagnetic sensors in the box-type substation to obtain discharge data of the box-type substation, wherein the first ultrasonic data is data collected by ultrasonic sensors at different locations in the box-type substation.

[0024] In this embodiment, a box-type substation is a low-voltage power distribution device that assembles switchgear, measuring instruments, protective devices, and auxiliary equipment in a closed or semi-enclosed metal cabinet. It is used to centrally distribute and control electricity and plays a key role in power distribution and circuit protection in the power system. Typically, when the insulation materials in the box-type substation become aged, damaged, or damp, it will cause uneven electric field distribution, thereby causing partial discharge. This discharge usually occurs at insulation defects, such as cable joints, insulator surfaces, switch contacts, etc. Therefore, the location of the fault can be determined by analyzing the discharge data within the box-type substation.

[0025] Existing fault location methods can be determined by analyzing the operating status data of the box-type substation, such as changes in parameters such as current, voltage, and power, but this method lacks accuracy. Another method is to determine the location of the fault through ultrasonic positioning, but this method is susceptible to interference from the external environment and can also cause inaccurate positioning. Based on this, the present application installs electromagnetic sensors and ultrasonic sensors in the box-type substation, and through the collaborative work of the two, accurately locates the fault location.

[0026] An electromagnetic sensor is a device that detects electromagnetic pulse signals. It converts these signals into electrical signals by sensing changes in the surrounding electromagnetic field. An ultrasonic sensor is a device that transmits and receives ultrasonic signals. In this embodiment, ultrasonic sensors are installed at various locations within the box-type substation to collect ultrasonic signal data generated by phenomena such as discharge within the substation. This data can reflect the characteristics of the sound signals within the substation.

[0027] In this embodiment, because electromagnetic pulse signals propagate at the speed of light, their time delay is negligible and they are not easily affected by environmental factors. Therefore, ultrasonic signals can be corrected based on the electromagnetic pulse signals. For example, a time-of-day positioning method is used for multi-physics field collaborative positioning. By synchronously collecting first ultrasonic data and ultra-high frequency electromagnetic pulse signals (UHF, in this field, refers to electromagnetic waves with a signal frequency range of 300 MHz to 3 GHz) generated by partial discharge, a joint acoustic-electric propagation model is constructed. The propagation speed difference between the electromagnetic pulse and the ultrasonic wave is then used to dynamically correct the ultrasonic time delay data using an adaptive Kalman filter. This embodiment utilizes this method to correct the first ultrasonic data, thereby improving the accuracy of fault location using discharge data from box-type substations.

[0028] S102: Compare the discharge data of the box-type substation with a preset threshold value to determine whether a fault occurs in the box-type substation.

[0029] In this embodiment, the discharge data of the box-type substation includes ultrasonic intensity, and the preset threshold includes a first preset threshold and a second preset threshold, where the first preset threshold is less than the second preset threshold. Comparing the discharge data of the box-type substation with the preset threshold to determine whether a fault has occurred in the box-type substation includes:

[0030] If the ultrasonic intensity of the box-type substation is greater than the second preset threshold, the box-type substation fails;

[0031] If the ultrasonic intensity of the box-type substation is greater than the first preset threshold and less than or equal to the second preset threshold, the box-type substation has not failed, and the discharge data of the box-type substation in this scenario is marked as "fault risk".

[0032] If the ultrasonic intensity of the box-type substation is less than or equal to the first preset threshold, the box-type substation has not failed, and the discharge data of the box-type substation in this scenario is marked as "no fault risk".

[0033] In the embodiment, the traditional "fault / normal" binary judgment mode is broken through, an intermediate risk state is introduced, and early warning of faults is realized through threshold interval division. In addition, the embodiment adds labels to data of different risk levels, and when a fault occurs in the box-type substation, data with high risk levels are associated to realize more accurate fault type judgment.

[0034] In the embodiment, the box-type substation monitoring method further includes:

[0035] In response to no fault occurring in the box-type substation, the historical data collection frequency is updated based on the discharge data to obtain a target data collection frequency, and the box-type substation is monitored at the target data collection frequency.

[0036] For example, the gradient boosting sampling formula can be used to calculate the change amount of the frequency adjustment, and the target data collection frequency is determined based on the change amount of the frequency adjustment. The gradient boosting sampling formula is:

[0037]

[0038] wherein, represents the change amount of the frequency adjustment, that is, the increment from the historical data collection frequency to the target data collection frequency, represents the maximum allowed data sampling frequency, represents the minimum allowed data sampling frequency, represents an adjustment factor, which controls the rate of frequency change, represents the current monitored ultrasonic intensity, represents a second preset threshold. In the embodiment, is a smooth transition function, which can ensure smooth transition of the sampling frequency and avoid system oscillation or data discontinuity caused by sudden change of the sampling frequency. The data output by the function is dimensionless data.

[0039] S103: In response to the box-type substation occurring a fault, the time difference positioning method is used to determine the fault position of the box-type substation based on the discharge data. The operation state data of the box-type substation is analyzed based on the fault position to determine the fault type, and the parameters of the box-type substation are compensated based on the compensation mode corresponding to different fault types.

[0040] In this embodiment, the time-difference location method is a positioning technique that uses the arrival time differences of signals received by multiple sensors, the coordinates of each sensor, and the ultrasonic velocity to construct a hyperbolic equation system. The spatial coordinates of the fault point are determined by solving the hyperbolic equation system. The operating status data of the box-type substation contains various parameters and information during the substation's operation, such as voltage, current, switch status, and power factor. This data reflects the substation's operating status, and the fault type can be determined based on the previously determined fault location and the substation's operating status. For example, if a fault is determined on an incoming circuit breaker, the fault type can be determined to be "overload" based on the substation's operating status data (e.g., an increase in the incoming circuit breaker temperature or current exceeding the rated value). This is because the incoming circuit breaker is being subjected to current exceeding its rated capacity due to excessive loads or abnormal startup of high-current equipment. Another example: if a fault is determined on a capacitor compensation device, the fault type can be determined to be a capacitor failure based on the substation's operating status data (e.g., a decrease in the capacitor compensation device's power factor or large system voltage fluctuations). Because capacitors may operate in overvoltage, overcurrent or high temperature environments for a long time, their internal components may be damaged, resulting in dielectric breakdown, leakage and other problems, which will affect the capacitor compensation effect.

[0041] The formula for the hyperbolic equation system can be:

[0042]

[0043] Among them, (x, y, z) is the coordinate of the fault location to be solved, (x i ,y i ,z i ) and (x j ,y j ,z j ) are the position coordinates of different ultrasonic sensors, and v is the velocity of the ultrasonic wave in the discharge data.

[0044] is the time difference between each pair of ultrasonic sensors.

[0045] In this embodiment, the operating status data of the box-type substation is analyzed based on the fault location to determine the fault type. The analysis method may be a threshold comparison method, a model analysis method, a wavelet transform analysis method, or the like. The threshold comparison method may compare the operating status data (such as voltage, current, and temperature) with a preset normal threshold range, and determine a fault if the threshold is exceeded. The model analysis method may input historical operating status data and the fault location into a neural network model for training to obtain a trained fault classification model, and then input the current collected data into the trained fault classification model to determine the fault type. The wavelet transform analysis method may perform time-frequency analysis on non-stationary signals to extract fault features, and then determine the fault type based on the fault features.

[0046] In this embodiment, after determining the fault type of the box-type substation, the parameters of the box-type substation can be compensated based on the compensation mode corresponding to different fault types. The compensation mode corresponding to different fault types is a compensation mode determined according to historical experience. For example, if the fault type is an overload of a certain line, the corresponding compensation mode can be to adjust the load distribution of the line and transfer part of the load to other lines. If the fault type is an insulation deterioration fault, the corresponding compensation mode is to increase the reactive power, which is suitable for short-term fault resolution. If a serious insulation deterioration fault occurs, the insulation device can be replaced.

[0047] From the above, it can be concluded that the application effectively solves the key problems of low precision and difficult positioning of traditional monitoring technology through multi-physical field data fusion and intelligent compensation mechanism. The application overcomes the limitations of a single sensor through electromagnetic-ultrasonic signal space-time correction technology, improves the sensitivity of discharge detection, and can more accurately locate the fault position. Secondly, for the fault position, the application adopts a multi-modal compensation strategy based on fault type, which can compensate the voltage or reactive power output of the box-type substation, significantly improve the service life of the equipment, improve the power supply reliability of the box-type substation, and meet the power supply demand of the load.

[0048] In an embodiment of the application, the discharge data of the box-type substation is obtained by correcting the first ultrasonic wave data based on the electromagnetic pulse data collected by the electromagnetic sensor in the box-type substation, comprising:

[0049] The time delay difference between the electromagnetic pulse data and the first ultrasonic wave data is calculated, and an association model of the electromagnetic pulse data and the first ultrasonic wave data is established based on the time delay difference;

[0050] The abnormal values in the first ultrasonic wave data are identified and removed based on the association model, and the discharge data of the box-type substation is obtained.

[0051] The abnormal values in the first ultrasonic wave data are identified and removed based on the association model, and the discharge data of the box-type substation is obtained.

[0052] The first ultrasonic wave data is compensated based on the temperature data and humidity data in the box-type substation, and the abnormal values in the compensated first ultrasonic wave data are identified and removed based on the association model.

[0053] In this embodiment, because the electromagnetic wave signal propagates fast in the medium and is not easy to cause signal delay, the ultrasonic wave signal attenuates greatly in the air and is easily affected by environmental characteristics such as temperature and humidity, so the first ultrasonic wave data can be corrected based on the electromagnetic pulse data collected by the electromagnetic sensor to obtain the discharge data of the box-type substation.

[0054] In the embodiment, the electromagnetic pulse data is electromagnetic signal data generated by a discharge phenomenon and collected by electromagnetic sensors in the box-type substation, which can reflect the discharge intensity, frequency and other characteristics. The first ultrasonic data is ultrasonic signal data generated by the discharge and collected by ultrasonic sensors at different positions in the box-type substation, which is used to locate the discharge position. The time delay difference represents the time difference of electromagnetic pulses and ultrasonic signals generated by the same discharge event and arriving at different sensors, which is a key parameter for correlating the two kinds of data. The electromagnetic sensors and ultrasonic sensors in the embodiment have the same clock, and the electromagnetic pulse data and the first ultrasonic data generated by the same discharge event are matched by time stamp, and then the time difference of the two to different sensors is calculated to construct a time delay matrix. Based on the time delay matrix and the position information of the sensors, an electromagnetic-ultrasonic correlation model (such as a hyperbolic positioning equation) is established, and based on the above correlation model, the abnormal values in the first ultrasonic data are identified and removed, so that the discharge data of the box-type substation can be obtained.

[0055] In the embodiment, the abnormal values are noise or interference data deviating from the true discharge signal in the first ultrasonic data, which is caused by environmental noise, sensor failure and other factors. These data will affect the judgment of the fault position, so it is necessary to identify and remove these abnormal values. Before removing the abnormal values, it needs to be considered that the temperature, humidity and other environments of the box-type substation will affect the first ultrasonic data, so the first ultrasonic data can be compensated based on the temperature data and humidity data, and then the abnormal values in the compensated first ultrasonic data are identified and removed based on the correlation model.

[0056] Compensating the first ultrasonic data based on the temperature data and the humidity data includes:

[0057] Compensating the ultrasonic speed in the first ultrasonic data based on the temperature data and the speed correction formula to obtain a target ultrasonic speed, and compensating the ultrasonic signal attenuation coefficient in the first ultrasonic data based on the humidity data and the signal attenuation correction formula to obtain a target ultrasonic attenuation coefficient.

[0058] The speed correction formula is: , is the standard sound speed, is the real-time temperature, is the standard temperature (20℃).

[0059] The signal attenuation correction formula is: , is the reference attenuation coefficient, is the reference humidity, is the real-time humidity, is the attenuation index (usually 0.5-1).

[0060] From the above, the embodiment can accurately grasp the internal relationship between the electromagnetic pulse and the first ultrasonic data by calculating the time delay difference and establishing a correlation model, and provides a basis for the correction of the first ultrasonic data. In addition, before the correlation model is used to identify and eliminate the abnormal values of the first ultrasonic data, the first ultrasonic data is compensated in combination with the temperature data and the humidity data, the interference of environmental factors is fully considered, the error is effectively reduced, the final discharge data is more accurate, a reliable basis is provided for subsequent fault judgment and positioning, and the accuracy and reliability of the box-type substation monitoring are improved.

[0061] In an embodiment of the present application, the discharge data includes ultrasonic intensity.

[0062] Based on the discharge data, a time difference positioning method is used to determine the fault position of the box-type substation, comprising:

[0063] The spatial coordinates of each ultrasonic sensor are determined, and the time difference corresponding to each pair of ultrasonic sensors is calculated. The time difference corresponding to a pair of ultrasonic sensors is the difference between the time points at which each sensor in the pair receives ultrasonic waves. A pair of ultrasonic sensors refers to any two ultrasonic sensors.

[0064] A nonlinear equation set of the fault position is constructed using geometric relationships.

[0065] Based on the spatial coordinates of each ultrasonic sensor and the multiple time differences, the nonlinear equation set is solved to obtain the coordinates of the fault position.

[0066] In the embodiment, at least three ultrasonic sensors can be arranged in the box-type substation, and the three sensors are not on the same plane. The position of the sensor installation avoids metal obstacles, which can reduce ultrasonic reflection interference. The position coordinates of each ultrasonic sensor in the three-dimensional space of the box-type substation are usually established in a coordinate system with the geometric center of the box-type substation as the origin. In this way, the spatial coordinates of each ultrasonic sensor can be determined.

[0067] In the embodiment, after determining the spatial coordinates of each ultrasonic sensor, the time difference corresponding to each pair of ultrasonic sensors is calculated. The time difference corresponding to a pair of ultrasonic sensors is the difference between the time points at which each sensor in the pair receives ultrasonic waves. A pair of ultrasonic sensors includes two ultrasonic sensors. Based on the spatial coordinates of each ultrasonic sensor and the multiple time differences, the nonlinear equation set (i.e., the hyperbolic equation set in the above embodiment) is solved. For example, the Levenberg-Marquardt algorithm is used for iterative solution, and the initial value is set by the geometric center of the sensor. When the convergence condition (residual sum of squares ) is reached, the three-dimensional coordinates (x, y, z) of the fault position are output.

[0068] From the above, in this embodiment, the ultrasonic intensity in the discharge data is taken as the key information, the spatial coordinates of the ultrasonic sensors are determined, the time difference corresponding to the ultrasonic intensity between adjacent ultrasonic sensors is calculated, and a nonlinear equation set is constructed by using the geometric relationship, thereby skillfully converting the physical phenomenon into a mathematical model. Subsequently, the equation set is solved based on the spatial coordinates and the time difference, so that the fault position can be accurately determined, the accuracy of fault positioning is improved, and the stable operation of the box-type substation is ensured.

[0069] In an embodiment of the present application, the operation state data of the box-type substation is analyzed based on the fault position to determine the fault type, including:

[0070] In response to the data amount of the operation state data being greater than or equal to the first data amount, the fault position and the operation state data of the box-type substation are input into a convolutional neural network model to determine the fault type of the box-type substation.

[0071] In response to the data amount of the operation state data being less than the first data amount, the fault position and the operation state data of the box-type substation are input into a K-nearest neighbor model to determine the fault type of the box-type substation.

[0072] In this embodiment, a convolutional neural network (CNN) model usually needs a large amount of data for training to fully learn the features and patterns in the data. When the data amount of the operation state data is greater than or equal to the first data amount, it means that there is enough data for the CNN model to learn and optimize. The CNN model has strong feature extraction capability and can automatically extract deep features related to the fault type from the data. In the case of sufficient data, the CNN model can more accurately capture the features of the fault type, thereby improving the accuracy of fault type determination.

[0073] The K-nearest neighbor (KNN) model is an instance-based learning method that does not require a complex model training process, but directly uses existing data for classification. Therefore, when the data amount of the operation state data is less than the first data amount, the KNN model can serve as an effective alternative to avoid performance degradation due to insufficient data. The KNN model has relatively low computational complexity and fast processing speed. In the case of small data amount, the KNN model can quickly find the most similar historical cases based on the fault position and the operation state data, thereby quickly determining the fault type.

[0074] From the above, different algorithm models are used under different data amounts in the embodiment, so as to fully utilize the advantages of the two models and ensure accurate and efficient fault type determination under various data conditions. The method considers the influence of data amount on model performance and also takes into account the applicability and calculation efficiency of the model.

[0075] In an embodiment of the present application, the fault type includes insulation deterioration fault and arc fault.

[0076] The parameters of the box-type substation are compensated based on the compensation mode corresponding to the different fault types, including at least one of the following:

[0077] In response to the fault type being an insulation deterioration fault, a reactive compensation amount is calculated based on a first dielectric loss factor of the insulation material corresponding to the fault position and a reference dielectric loss factor; and the reactive power of the box-type substation is compensated based on the reactive compensation amount.

[0078] In response to the fault type being an arc fault, a power supply branch corresponding to the fault position is determined, a compensation voltage value is determined based on a voltage change value, a current change value and a line equivalent impedance of the power supply branch within a first time length, and the output voltage of the box-type substation is compensated based on the compensation voltage value.

[0079] In the embodiment, the insulation deterioration fault refers to a fault that the insulation performance of the insulation material (such as cable insulation layer, switch cabinet insulator, etc.) in the box-type substation is degraded due to long-term electric field, thermal stress, mechanical vibration or environmental factors. Typical manifestations are increased dielectric loss factor, enhanced partial discharge signal and reduced insulation resistance. Therefore, when the fault type of the box-type substation is an insulation deterioration fault, the deviation between the current dielectric loss factor (first dielectric loss factor) of the insulation material and the reference dielectric loss factor is calculated to quantify the degree of insulation performance degradation, and then the reactive power to be compensated is determined to reduce the reactive loss and heating caused by insulation deterioration.

[0080] In the embodiment, the arc fault refers to an ionization discharge phenomenon between conductors in the box-type substation caused by insulation failure, poor contact or overvoltage, which may be accompanied by high temperature, electromagnetic interference and equipment burning risk. Typical manifestations are voltage drop, current surge, high-frequency noise, arc phenomenon, etc. Therefore, when the fault type of the box-type substation is an arc fault, the voltage and current change values of the fault branch within a first time length after the fault occurs are monitored, and the line equivalent impedance is combined to calculate the voltage value to be compensated, which can restore the power supply stability and avoid the negative impact of voltage sag on industrial production.

[0081] From the above, the embodiment is aimed at insulation deterioration fault, quantifies the deterioration degree by the dielectric loss factor deviation and dynamically compensates the reactive power, reduces the energy consumption and heating caused by insulation degradation, and prolongs the service life of the equipment; for arc fault, the compensation voltage is calculated in real time based on the transient voltage / current change and the line impedance, the power supply stability is quickly restored, and the sensitive equipment shutdown caused by voltage sag is avoided. The differentiated compensation strategy of the embodiment significantly reduces the impact of the fault on the power distribution system, ensures the power supply quality and continuity, and reduces the operation and maintenance cost.

[0082] In an embodiment of the present application, the reactive compensation amount is calculated based on the first dielectric loss factor of the insulation material corresponding to the fault position and the reference dielectric loss factor, comprising:

[0083] The reactive compensation amount is calculated based on the first formula, and the first formula is:

[0084]

[0085] wherein, represents the reactive compensation amount, represents the rated reactive capacity, represents the adjustment coefficient, which is a positive number, represents the first dielectric loss factor, represents the reference dielectric loss factor.

[0086] The compensation voltage is calculated based on the second formula, and the second formula is:

[0087]

[0088] wherein, represents the compensation voltage, represents the safety adjustment coefficient, represents the voltage drop amplitude, represents the current mutation amount, represents the line equivalent impedance.

[0089] In the embodiment, when insulation deterioration leads to > , the reactive compensation amount is proportionally increased to offset the additional reactive demand caused by the increase of dielectric loss, thereby improving the service life of the box-type substation.

[0090] In the embodiment, by comprehensively considering the voltage drop amplitude ( ) and the impedance pressure drop caused by the current mutation ( ), the compensation voltage is calculated in real time, which can significantly shorten the response time, and the total voltage after compensation meets the demand of the load, which can meet the normal power supply demand of the load.

[0091] The box-type substation monitoring method corresponding to the above embodiment, Figure 2A structural block diagram of the box-type substation monitoring device provided by an embodiment of the present application is shown. For ease of illustration, only parts related to the embodiments of the present application are shown. For reference Figure 2 The box-type substation monitoring device 20 includes a data correction module 21, a fault judgment module 22, and a compensation module 23.

[0092] The data correction module 21 is configured to correct first ultrasonic wave data based on electromagnetic pulse data collected by electromagnetic sensors in the box-type substation to obtain discharge data of the box-type substation. The first ultrasonic wave data is data collected by ultrasonic wave sensors at different positions in the box-type substation.

[0093] The fault judgment module 22 is configured to compare the discharge data of the box-type substation with a preset threshold value to determine whether a fault occurs in the box-type substation.

[0094] The compensation module 23 is configured to, in response to a fault occurring in the box-type substation, determine a fault position of the box-type substation based on the discharge data using a time-difference positioning method, analyze operation state data of the box-type substation based on the fault position to determine a fault type, and compensate parameters of the box-type substation based on a compensation mode corresponding to the fault type.

[0095] In an embodiment of the present application, the data correction module 21 is specifically configured to:

[0096] calculate a time delay difference between the electromagnetic pulse data and the first ultrasonic wave data, and establish an association model of the electromagnetic pulse data and the first ultrasonic wave data based on the time delay difference;

[0097] identify and remove abnormal values in the first ultrasonic wave data based on the association model to obtain the discharge data of the box-type substation.

[0098] In an embodiment of the present application, the data correction module 21 is specifically configured to:

[0099] perform data compensation on the first ultrasonic wave data based on temperature data and humidity data in the box-type substation, and identify and remove abnormal values in the first ultrasonic wave data after compensation based on the association model.

[0100] In an embodiment of the present application, the discharge data includes ultrasonic wave intensity.

[0101] The fault judgment module 22 is specifically configured to:

[0102] determine spatial coordinates of each ultrasonic wave sensor, calculate time differences respectively corresponding to each pair of ultrasonic wave sensors, and the time difference corresponding to a pair of ultrasonic wave sensors is a difference between time points at which each sensor in the pair of sensors receives ultrasonic waves; a pair of ultrasonic wave sensors are any two ultrasonic wave sensors.

[0103] The nonlinear equation set for the fault location is constructed by using geometric relations.

[0104] The nonlinear equation set is solved based on the spatial coordinates of each ultrasonic sensor and the plurality of time differences to obtain the coordinates of the fault location.

[0105] In an embodiment of the present application, the fault judgment module 22 is specifically configured to:

[0106] in response to the data amount of the operation state data being greater than or equal to the first data amount, inputting the fault location and the operation state data of the box-type substation into a convolutional neural network model to determine the fault type of the box-type substation;

[0107] in response to the data amount of the operation state data being less than the first data amount, inputting the fault location and the operation state data of the box-type substation into a K-nearest neighbor model to determine the fault type of the box-type substation.

[0108] In an embodiment of the present application, the fault type includes an insulation deterioration fault and an arc fault.

[0109] The compensation module 23 is specifically configured to:

[0110] in response to the fault type being the insulation deterioration fault, calculating a reactive power compensation amount based on a first dielectric loss factor of the insulation material corresponding to the fault location and a reference dielectric loss factor, and compensating the reactive power of the box-type substation based on the reactive power compensation amount;

[0111] in response to the fault type being the arc fault, determining a power supply branch corresponding to the fault location, determining a compensation voltage value based on a voltage change value, a current change value and a line equivalent impedance of the power supply branch within a first time length, and compensating the output voltage of the box-type substation based on the compensation voltage value.

[0112] In an embodiment of the present application, the compensation module 23 is specifically configured to:

[0113] calculating the reactive power compensation amount based on a first formula, the first formula being:

[0114]

[0115] wherein, the reactive power compensation amount is represented by Qcomp, a rated reactive power capacity is represented by Qrated, an adjustment coefficient is represented by k, and k is a positive number, the first dielectric loss factor is represented by tanδ1, the reference dielectric loss factor is represented by tanδ0.

[0116] Referring to Figure 3 , Figure 3 is a schematic block diagram of a box-type substation monitoring system provided by an embodiment of the present application. As shown in Figure 3 The box-type substation monitoring system 300 in the embodiment shown may include: one or more processors 301, one or more input devices 302, one or more output devices 303 and one or more memories 304. The processors 301, input devices 302, output devices 303 and memories 304 communicate with each other via a communication bus 305. The memory 304 is used to store computer programs, which include program instructions. The processor 301 is used to execute the program instructions stored in the memory 304. The processor 301 is configured to call the program instructions to execute the functions of each module in the above-mentioned device embodiments, such as Figure 2 The functions of the data correction module 21, the fault judgment module 22 and the compensation module 23 are shown.

[0117] It should be understood that in the embodiment of the present application, the processor 301 may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0118] The input device 302 may include a touchpad, a fingerprint collection sensor (for collecting user fingerprint information and fingerprint direction information), a microphone, etc. The output device 303 may include a display (LCD, etc.), a speaker, etc.

[0119] The memory 304 may include a read-only memory and a random access memory, and provides instructions and data to the processor 301. A portion of the memory 304 may also include a non-volatile random access memory. For example, the memory 304 may also store device type information.

[0120] In a specific implementation, the processor 301, input device 302, and output device 303 described in the embodiments of the present application can execute the implementation methods described in the first and second embodiments of the box-type substation monitoring method provided in the embodiments of the present application, and can also execute the implementation methods of the box-type substation monitoring system described in the embodiments of the present application, which will not be repeated here.

[0121] In another embodiment of the present application, a computer readable storage medium is provided, which stores a computer program. The computer program includes program instructions, which, when executed by a processor, implement all or part of the processes of the above-mentioned embodiments. The computer program can also instruct related hardware to complete the implementation. The computer program can be stored in a computer readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various method embodiments can be implemented. The computer program includes computer program code, which can be in the form of source code, object code, executable code, or some intermediate form. The computer readable medium can include any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc.

[0122] The computer readable storage medium can be an internal storage unit of the box-type substation monitoring system, such as a hard disk or a memory of the box-type substation monitoring system. The computer readable storage medium can also be an external storage device of the box-type substation monitoring system, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. Further, the computer readable storage medium can include both the internal storage unit and the external storage device of the box-type substation monitoring system. The computer readable storage medium is used to store the computer program and other programs and data required by the box-type substation monitoring system. The computer readable storage medium can also be used to temporarily store data that has been output or will be output.

[0123] Those skilled in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized in electronic hardware, computer software or a combination of both. In order to clearly illustrate the interchangeability of hardware and software, the components and steps of each example have been described in general terms in the above description. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. A skilled person can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0124] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the box-type substation monitoring system and unit described above can refer to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0125] In several embodiments provided in the present application, it should be understood that the disclosed box-type substation monitoring system and method can be implemented in other ways. For example, the above-described device embodiments are only schematic, for example, the division of units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed units can be indirect coupling or communication connection through some interfaces or units, and can also be electrical, mechanical or other forms of connection.

[0126] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiments of the present application.

[0127] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0128] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto, and any skilled person in the art can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A box-type substation monitoring method, characterized in that: include: The first ultrasonic data is corrected based on the electromagnetic pulse data collected by the electromagnetic sensor in the box-type substation to obtain the discharge data of the box-type substation; wherein the first ultrasonic data is data collected by the ultrasonic sensors at different locations in the box-type substation; Comparing the discharge data of the box-type substation with a preset threshold to determine whether the box-type substation has a fault; The discharge data of the box-type substation includes ultrasonic intensity, the preset threshold includes a first preset threshold and a second preset threshold, and the first preset threshold is less than the second preset threshold; comparing the discharge data of the box-type substation with the preset threshold to determine whether a fault occurs in the box-type substation, including: If the ultrasonic intensity of the box-type substation is greater than the second preset threshold, the box-type substation fails; If the ultrasonic intensity of the box-type substation is greater than the first preset threshold and less than or equal to the second preset threshold, the box-type substation has not failed, and the discharge data of the box-type substation in this scenario is marked as having a fault risk; If the ultrasonic intensity of the box-type substation is less than or equal to the first preset threshold, the box-type substation has not failed, and the discharge data of the box-type substation in this scenario is marked as having no fault risk; In response to a fault occurring in the box-type substation, the fault location of the box-type substation is determined using a time difference positioning method based on the discharge data; the operating status data of the box-type substation is analyzed based on the fault location to determine the fault type, and the parameters of the box-type substation are compensated based on compensation methods corresponding to different fault types; The fault types include insulation degradation faults and arc faults; The compensating the parameters of the box-type substation based on the compensation methods corresponding to different fault types includes at least one of the following: In response to the fault type being an insulation degradation fault, calculating a reactive compensation amount based on a first dielectric loss factor and a reference dielectric loss factor of an insulation material corresponding to the fault location; and compensating the reactive power of the box-type substation based on the reactive compensation amount; In response to the fault type being an arc fault, determining a power supply branch corresponding to the fault location, determining a compensation voltage value based on a voltage change value, a current change value, and a line equivalent impedance of the power supply branch within a first time period, and compensating the output voltage of the box-type substation based on the compensation voltage value; The compensation voltage is calculated based on the following formula: in, represents the compensation voltage, represents the safety adjustment factor, Indicates the voltage drop amplitude, Indicates the current mutation amount, Indicates the equivalent impedance of the line.

2. The box-type substation monitoring method according to claim 1, characterized in that: The method of correcting the first ultrasonic data based on the electromagnetic pulse data collected by the electromagnetic sensor in the box-type substation to obtain the discharge data of the box-type substation includes: calculating a time delay difference between the electromagnetic pulse data and the first ultrasonic data, and establishing a correlation model between the electromagnetic pulse data and the first ultrasonic data based on the time delay difference; Based on the association model, outliers in the first ultrasonic data are identified and eliminated to obtain discharge data of the box-type substation.

3. The box-type substation monitoring method according to claim 2, characterized in that: The identifying and eliminating abnormal values ​​in the first ultrasonic data based on the association model includes: The first ultrasonic data is compensated based on the temperature data and humidity data in the box-type substation, and abnormal values ​​in the compensated first ultrasonic data are identified and eliminated based on the association model.

4. The box-type substation monitoring method according to claim 1, characterized in that: The discharge data includes ultrasonic intensity; Determining the fault location of the box-type substation using the time difference positioning method based on the discharge data includes: Determine the spatial coordinates of each ultrasonic sensor; Calculate the time difference corresponding to each pair of ultrasonic sensors, where the time difference corresponding to a pair of ultrasonic sensors is the difference between the time points at which each sensor in the pair receives the ultrasonic wave; a pair of ultrasonic sensors is any two ultrasonic sensors; Use geometric relationships to construct a nonlinear system of equations for fault location; The nonlinear equation group is solved based on the spatial coordinates of each ultrasonic sensor and a plurality of time differences to obtain the coordinates of the fault location.

5. The box-type substation monitoring method according to claim 1, characterized in that: The analyzing the operating status data of the box-type substation based on the fault location to determine the fault type includes: In response to the data amount of the operating status data being greater than or equal to the first data amount, inputting the fault location and the operating status data of the box-type substation into a convolutional neural network model to determine the fault type of the box-type substation; In response to the data volume of the operating status data being less than the first data volume, the fault location and the operating status data of the box-type substation are input into a K-nearest neighbor model to determine the fault type of the box-type substation.

6. The box-type substation monitoring method according to claim 1, characterized in that: The calculating of the reactive compensation amount based on the first dielectric loss factor and the reference dielectric loss factor of the insulating material corresponding to the fault location includes: The reactive compensation amount is calculated based on the first formula, which is: in, Indicates the reactive compensation amount, Indicates the rated reactive capacity, Represents the adjustment coefficient, which is a positive number. represents the first dielectric loss factor, Indicates the base dielectric loss factor.

7. A box-type substation monitoring device, characterized in that: include: A data correction module, configured to correct the first ultrasonic data based on the electromagnetic pulse data collected by the electromagnetic sensor in the box-type substation to obtain the discharge data of the box-type substation; wherein the first ultrasonic data is data collected by ultrasonic sensors at different locations in the box-type substation; A fault judgment module is used to compare the discharge data of the box-type substation with a preset threshold value to determine whether the box-type substation has a fault; The fault judgment module is specifically configured to: if the ultrasonic intensity of the box-type substation is greater than a second preset threshold, the box-type substation fails; If the ultrasonic intensity of the box-type substation is greater than the first preset threshold and less than or equal to the second preset threshold, the box-type substation has not failed, and the discharge data of the box-type substation in this scenario is marked as having a fault risk; If the ultrasonic intensity of the box-type substation is less than or equal to the first preset threshold, the box-type substation has not failed, and the discharge data of the box-type substation in this scenario is marked as having no fault risk; a compensation module, configured to, in response to a fault occurring in the box-type substation, determine the fault location of the box-type substation using a time difference positioning method based on the discharge data; analyze the operating status data of the box-type substation based on the fault location to determine the fault type, and compensate the parameters of the box-type substation based on compensation methods corresponding to different fault types; The compensation module is specifically configured to: in response to the fault type being an insulation degradation fault, calculate a reactive compensation amount based on a first dielectric loss factor and a reference dielectric loss factor of the insulation material corresponding to the fault location; and compensate for the reactive power of the box-type substation based on the reactive compensation amount; In response to the fault type being an arc fault, determining a power supply branch corresponding to the fault location, determining a compensation voltage value based on a voltage change value, a current change value, and a line equivalent impedance of the power supply branch within a first time period, and compensating the output voltage of the box-type substation based on the compensation voltage value; The compensation voltage is calculated based on the following formula: in, represents the compensation voltage, represents the safety adjustment factor, Indicates the voltage drop amplitude, Indicates the current mutation amount, Indicates the equivalent impedance of the line.

8. A box-type substation monitoring system, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images