A Substation Real-Time Diagnosis Method, Device, Electronic Equipment and Storage Medium

Abstract

The present invention provides a real-time diagnosis method, device, electronic device and storage medium for a substation, and relates to the technical field of substations. The method comprises: first preprocessing pre-collected historical data of substation parameters to generate preprocessed historical data of corresponding parameters; then performing polynomial weighted fitting on the preprocessed historical data of corresponding parameters to generate polynomial fitting results; then collecting current data of the substation parameters in real time, and updating the polynomial fitting results using a weighted sequential least squares method. The updated polynomial fitting results can be used for substation diagnosis, thereby solving the technical problems of low accuracy and untimely response in substation fault diagnosis in the prior art, and achieving the technical effect of more accurate and timely substation diagnosis.

Description

Technical Field

[0001] The present invention relates to the technical field of substations, and in particular to a real-time diagnosis method, device, electronic equipment and storage medium for substations. Background Art

[0002] Digital substations are constructed in layers of intelligent primary and networked secondary equipment, enabling information sharing and interoperability among intelligent electrical devices within the substation. By introducing advanced power system monitoring, control, and fault diagnosis technologies, and utilizing digital communication networks and intelligent devices to transmit data, digital substations enable real-time monitoring and control of power system components, revolutionizing the traditional power industry.

[0003] As power networks continue to expand in size and complexity, the demand for accurate and timely fault diagnosis systems is growing to ensure the reliable operation of digital substations. Because power system failures can have serious consequences, including power outages, equipment damage, and even safety hazards, timely fault detection and diagnosis are essential to minimize their impact on the grid. Furthermore, critical parameters collected by substations often contain random noise, which negatively impacts data processing and, consequently, affects the accuracy of substation fault diagnosis. Summary of the Invention

[0004] The object of the present invention is to provide a real-time diagnosis method, device, electronic device and storage medium for a substation to alleviate the technical problems of low accuracy and untimely response in the prior art of substation fault diagnosis.

[0005] In a first aspect, an embodiment of the present invention provides a real-time diagnosis method for a substation, the method comprising: preprocessing pre-collected historical data of substation parameters to generate preprocessed historical data of corresponding substation parameters; performing polynomial weighted fitting on the preprocessed historical data of corresponding substation parameters to generate polynomial fitting results; collecting current data of the substation parameters in real time, and updating the polynomial fitting results using a weighted sequential least squares method; and using the updated polynomial fitting results for diagnosis of the substation.

[0006] In some optional implementations, the above-mentioned substation parameters include: voltage, current, temperature and load capacity; preprocessing the historical data of the pre-collected substation parameters to generate preprocessed historical data of the substation parameters, including: discretizing the pre-collected historical data of the substation parameters to generate discrete historical data; using different sliding windows to smooth the above-mentioned discrete historical data, determining the smoothed historical data results corresponding to the above-mentioned different sliding windows, and the corresponding smoothness; determining the preprocessed historical data corresponding to the substation parameters based on the above-mentioned smoothed historical data results corresponding to the sliding window with the smallest smoothness.

[0007] In some optional implementations, the discrete historical data is smoothed using different sliding windows to determine the smoothed historical data results and corresponding smoothness corresponding to the different sliding windows, including: determining the average value of M data points in the sliding window as the smoothing value of the midpoint of the M data points; the sliding window includes M data points, M is an odd number greater than 1; starting from the first data point, the sliding window is shifted point by point to determine the smoothing value corresponding to each sliding window as the corresponding smoothed historical data result; and the smoothness corresponding to the sliding window with a window size of M is calculated based on the smoothing value.

[0008] In some optional implementations, polynomial weighted fitting is performed on the preprocessed historical data of the corresponding strain power station parameters, including: determining the weight of each data point in the preprocessed historical data of the corresponding strain power station parameters based on a weight calculation formula; the weight calculation formula is: ; Where i is the serial number of the data point, i≥1, Based on the weight of each data point, generate the weighted matrix of the above pre-processed historical data of the corresponding power station parameters .

[0009] In some optional implementations, the polynomial weighted fitting is performed on the above pre-processed historical data of the corresponding power station parameters, and further includes: a weighted matrix based on the above pre-processed historical data of the corresponding power station parameters , a vector of smoothed values for each data point , the first Vandermonde matrix As well as the fitting performance index, determine the vector consisting of the polynomial coefficients obtained for historical data .

[0010] In some optional implementations, the current data of the above substation parameters are collected in real time, and the weighted sequential least squares method is used to update the above polynomial fitting results, including: Collect the above substation parameters as the N+1th discrete data point in the above discrete historical data to generate current data; N is the number of data points in the above discrete historical data; based on the above current data, determine the second Vandermonde matrix , the smoothed value of the above current data , and the weight of each data point in the current data .

[0011] In some optional implementations, the current data of the substation parameters are collected in real time, and the polynomial fitting result is updated using the weighted sequential least squares method, which also includes: updating the polynomial fitting result using the weighted sequential least squares method, and the updated polynomial fitting coefficient is: ;in, are the updated polynomial coefficients; , ;

[0012] .

[0013] In a second aspect, an embodiment of the present invention provides a real-time diagnosis device for a substation, which includes: a preprocessing module for preprocessing the historical data of the substation parameters collected in advance to generate preprocessed historical data of the corresponding substation parameters; a weighted fitting module for performing polynomial weighted fitting on the above-mentioned preprocessed historical data of the corresponding substation parameters to generate polynomial fitting results; an updating module for real-time collection of current data of the above-mentioned substation parameters, and updating the above-mentioned polynomial fitting results using the weighted sequential least squares method; the updated above-mentioned polynomial fitting results are used for diagnosis of the above-mentioned substation.

[0014] In a third aspect, an embodiment of the present invention provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the computer program, the steps of the method described in any one of the first aspects are implemented.

[0015] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores machine-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to execute any method described in the first aspect above.

[0016] The present invention provides a real-time diagnosis method, device, electronic device and storage medium for a substation. The method first pre-processes historical data of pre-collected substation parameters to generate pre-processed historical data of the corresponding substation parameters; then, polynomial weighted fitting is performed on the pre-processed historical data of the corresponding substation parameters to generate polynomial fitting results; then, current data of the substation parameters are collected in real time, and the polynomial fitting results are updated using a weighted sequential least squares method. The updated polynomial fitting results can be used for substation diagnosis, thereby solving the technical problems of low accuracy and untimely response in substation fault diagnosis in the prior art, and achieving the technical effect of more accurate and timely substation diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0018] Figure 1 A flowchart of a real-time diagnosis method for a substation provided by an embodiment of the present invention;

[0019] Figure 2 A discrete historical data graph generated by discretizing historical data provided by an embodiment of the present invention;

[0020] Figure 3 A result graph after smoothing discrete historical data provided by an embodiment of the present invention;

[0021] Figure 4 A fitting result graph generated by performing polynomial weighted fitting on temperature history data provided by an embodiment of the present invention;

[0022] Figure 5 A fitting result update diagram provided by an embodiment of the present invention;

[0023] Figure 6 A schematic structural diagram of a real-time diagnostic device for a substation provided by an embodiment of the present invention;

[0024] Figure 7 A schematic structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0025] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions of the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings herein can be arranged and designed in various different configurations.

[0026] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention as claimed, but rather merely represents selected embodiments of the present invention. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without creative effort shall fall within the scope of protection of the present invention.

[0027] It should be noted that similar reference numerals and letters represent similar items in the following figures. Therefore, once an item is defined in one figure, it does not need to be further defined or explained in subsequent figures. Some embodiments of the present invention are described in detail below with reference to the accompanying figures. The following embodiments and features of the embodiments may be combined with each other unless there is a conflict.

[0028] Digital substations are constructed in layers of intelligent primary and networked secondary equipment, enabling information sharing and interoperability among intelligent electrical devices within the substation. By introducing advanced power system monitoring, control, and fault diagnosis technologies, and utilizing digital communication networks and intelligent devices to transmit data, digital substations have revolutionized the traditional power industry. As power networks continue to expand in size and complexity, the demand for accurate and timely fault diagnosis systems is also growing to ensure the reliable operation of digital substations. Because power system failures can have serious consequences, including power outages, equipment damage, and even safety hazards, timely fault detection and diagnosis are essential to minimize their impact on the power grid. Furthermore, critical parameters collected by substations often contain random noise, which negatively impacts data processing and, consequently, the accuracy of substation fault diagnosis.

[0029] Based on this, the embodiments of the present invention provide a substation real-time diagnosis method, device, electronic device and storage medium to solve the technical problems of low accuracy and untimely response in substation fault diagnosis in the prior art.

[0030] To facilitate understanding of this embodiment, a real-time diagnosis method for a substation disclosed in an embodiment of the present invention is first described in detail. Figure 1 The flowchart of a real-time diagnosis method for a substation is shown. The method can be executed by an electronic device and mainly includes the following steps S110 to S130:

[0031] S110: Preprocessing the pre-collected historical data of substation parameters to generate preprocessed historical data of corresponding substation parameters;

[0032] Substation parameters can include important parameters such as voltage, current, temperature, and load capacity. During parameter collection, random noise is often unavoidable. This noise negatively impacts subsequent data fitting and other processing, further impacting the accuracy of substation diagnostics. Furthermore, because the collection of important substation parameters such as voltage, current, temperature, and load capacity is a continuous process, fitting results must be updated based on the latest collected data.

[0033] In one embodiment, the preprocessing may include discretization processing and smoothing processing, that is, the step of preprocessing the pre-collected historical data of substation parameters may include:

[0034] (S11) discretizing the historical data of the substation parameters collected in advance to generate discrete historical data;

[0035] Discretize historical data of important parameters such as voltage, current, temperature and load capacity, and set fixed time intervals , every Discretization of historical data of important parameters such as voltage, current, temperature and load capacity , where i is the serial number of the historical data. Assume that there are N data points in the discretized historical data.

[0036] (S12) Smoothing the discrete historical data using different sliding windows, and determining the smoothing results of the historical data corresponding to the different sliding windows, as well as the corresponding smoothness; that is, smoothing the discrete historical data using sliding windows of different sizes, and calculating the smoothness of the discrete historical data of different windows.

[0037] This step specifically includes: first, determining the average value of M data points within a sliding window as the smoothing value of the midpoint of the M data points; the sliding window includes M data points, where M is an odd number greater than 1. Then, starting from the first data point, the sliding window is translated point by point, and the smoothing value corresponding to each sliding window is determined as the corresponding result of smoothing the historical data; then, based on the smoothing value, the smoothness corresponding to the sliding window of window size M is calculated.

[0038] As a specific example, when the number of data points included in the sliding window is M, M is an odd number greater than 1, calculate the M data points in any sliding window ,..., The average value of , as the smoothed value of the midpoint of M data points:

[0039]

[0040] in, For the Smoothed value of data points;

[0041] Starting from the first data point, the sliding window is shifted point by point to obtain the corresponding discrete historical data of the smoothed signal:

[0042] 、 、 ...;

[0043] Calculate the smoothness r for a window size of M:

[0044]

[0045] When M takes the values of 3, 5, 7, and 9, four smoothness levels and four sets of discrete historical data of the smoothed signal are calculated.

[0046] (S13) Determining the pre-processed historical data corresponding to the strain station parameter based on the smoothing processing result corresponding to the sliding window with the minimum smoothness; that is, using the smoothed discrete historical data obtained by the sliding window with the minimum smoothness as the final smoothed discrete historical data.

[0047] S120: performing polynomial weighted fitting on the pre-processed historical data of the corresponding power station parameters to generate a polynomial fitting result;

[0048] In one embodiment, polynomial weighted fitting is performed on the pre-processed historical data of the corresponding power station parameters, including:

[0049] (S21) determining the weight of each data point in the pre-processed historical data corresponding to the strain power station parameter based on a weight calculation formula;

[0050] The weight calculation formula is: ; Where i is the serial number of the data point, i≥1, ;

[0051] There is no strict quantitative standard for the value of α, but there are qualitative standards: 1) The data points that are closer in time (that is, the data points with larger i) should be more important, and thus their weight should be larger, so α must be greater than or equal to 1; 2) The larger the value of α, the more attention is paid to the data points that are closer in time during fitting, and the more distant data points are ignored.

[0052] (S22) Based on the weight of each data point, a weighted matrix of the historical data of the corresponding power station parameters after preprocessing is generated ; That is, the weights of all data points constitute the weighted matrix of historical data .

[0053] In one embodiment, performing polynomial weighted fitting on the pre-processed historical data of the corresponding power station parameters further includes:

[0054] (S23) Weighted matrix based on pre-processed historical data of the corresponding power station parameters , a vector of smoothed values for each data point , the first Vandermonde matrix As well as the fitting performance index, determine the vector consisting of the polynomial coefficients obtained for historical data .

[0055] As a specific example, a polynomial of power n is fitted, that is, ;in, is the fitted value of the data point with sequence number i, is the coefficient to be solved;

[0056] The vector of smoothed values of all data points is ;

[0057] The vector of polynomial coefficients obtained for historical data is ;

[0058] Define the first Vandermonde matrix as ;

[0059] Solving the fitting performance index The minimum value of .

[0060] Among them, J is about The quadratic index function is an N-dimensional parabolic surface with a unique minimum point. Its minimum point should make the Jacobian matrix equal to 0, that is:

[0061] ;

[0062] According to this formula, we can get .

[0063] S130: collecting current data of substation parameters in real time, and using weighted sequential least squares method to update the polynomial fitting result; the updated polynomial fitting result is used for substation diagnosis.

[0064] In one embodiment, the step of collecting current data of substation parameters in real time in S130 and updating the polynomial fitting result using the weighted sequential least squares method may include:

[0065] (S31) at time intervals Collect substation parameters as the N+1th discrete data point in the discrete historical data to generate current data; N is the number of data points in the discrete historical data;

[0066] (S32) Based on the current data, determine the second Vandermonde matrix , smoothed value of current data , and the weight of each data point in the current data .

[0067] That is, at time intervals Get the latest data, which constitutes the N+1th discrete data point; data points are re-smoothed, and the smoothing value of the latest data is ;The weight of the latest data point is .

[0068] Traditional least squares methods have two problems: 1) they treat all data points equally, but in reality (for example, in substation diagnosis), the more recent data points are more important; 2) all data are processed at once after collection, but in reality (for example, in substation diagnosis), data arrives one after another and is updated in real time. In this case, if traditional least squares methods are still used, a global fit must be performed on all data, including the latest data. For large-scale data, this approach is not conducive to storage and timely processing. Therefore, in the embodiments of this application, weighted sequential least squares methods are used as the fitting method.

[0069] In one embodiment, the above S130 may further include: (S33) updating the polynomial fitting result using a weighted sequential least squares method;

[0070] The updated polynomial fitting coefficients are: ;in, are the updated polynomial coefficients;

[0071] , ;

[0072] .

[0073] Assume that N old data points have been preprocessed and fitted, where the smoothed value vector is , the first Vandermonde matrix is , the weight matrix is For these N old data points, the least squares estimate is:

[0074] (Formula 1);

[0075] At this time, the latest N+1 data point comes, and its corresponding smoothing value is , the Vandermonde vector is , the weight is .

[0076] The smoothed value vector of all N+1 data points is , the Vandermonde matrix is , the weight matrix is If the traditional least squares method is used for the N+1 data points, the least squares estimate can be obtained as:

[0077] (Formula 2);

[0078] Arrange (Formula 2) and substitute (Formula 1) into it to get:

[0079] (Formula 3);

[0080] in, , .

[0081] Note that, compared to (Formula 2), in (Formula 3), The calculation uses , that is, the sequential least squares method can continuously correct the existing estimation results based on the latest data points without the need for overall fitting.

[0082] An embodiment of the present invention provides a real-time diagnosis method for a substation. The method preprocesses pre-collected historical data of substation parameters to generate pre-processed historical data of the corresponding substation parameters. Then, polynomial weighted fitting is performed on the pre-processed historical data of the corresponding substation parameters to generate polynomial fitting results. Then, current data of the substation parameters is collected in real time, and the polynomial fitting results are updated using a weighted sequential least squares method. The updated polynomial fitting results can be used for substation diagnosis, reducing the influence of random noise of the substation historical data on the fitting results. The fitting results can be updated in real time and quickly according to the latest collected data, thereby achieving more accurate estimation and prediction of substation fault conditions.

[0083] As a specific example, combining Figures 2 to 5 As shown, a real-time diagnosis method for a substation provided by an embodiment of the present application includes the following steps:

[0084] (1) Discretize historical data of important parameters such as voltage, current, temperature and load capacity, including:

[0085] Set a fixed time interval In this example, ;

[0086] Every Discretization of historical data of important parameters such as voltage, current, temperature and load capacity , where i is the serial number of the historical data. Assume that the discretized historical data has N data points. In this example, the historical data of temperature is recorded. , after discretization, we get Figure 2 30 data points shown;

[0087] (2) Based on the discretized historical data, smoothing is performed on the data, including:

[0088] Use sliding windows of different sizes to smooth discrete historical data and calculate the smoothness of discrete historical data of different windows;

[0089] The discrete historical data after smoothing obtained by the sliding window with the minimum smoothness is used as the final discrete historical data after smoothing. In this example, when the sliding window is 5, the smoothness is the minimum, and the following can be obtained: Figure 3 Smoothed graph of historical data shown.

[0090] The following steps can be used to smooth discrete historical data using sliding windows of different sizes and calculate the smoothness of discrete historical data of different windows:

[0091] Step 1), when the number of data points included in the sliding window is M, M is an odd number greater than 1, calculate the M data points in any sliding window ,..., The average value of , as the smoothed value of the midpoint of M data points:

[0092] ;

[0093] in, For the Smoothed value of data points;

[0094] Step 2) Starting from the first data point, the sliding window is shifted point by point to obtain the corresponding discrete historical data of the smoothed signal:

[0095] 、 、 ...;

[0096] Step 3), calculate the smoothness r with a window size of M:

[0097]

[0098] In step 4), when M takes the values of 3, 5, 7, and 9, four smoothness levels and four sets of discrete historical data of the smoothed signal are calculated.

[0099] (3) Perform polynomial weighted fitting on the discrete historical data, including:

[0100] Determine the weight of each data point in the discretized historical data;

[0101] Based on the weights, a polynomial weighted fitting is performed. In this example, the following can be obtained: Figure 4 The temperature history data fitting graph is shown.

[0102] The weight of each data point in the discretized historical data can be determined by the following steps, including:

[0103] Step 1) Calculate the weight of the data point with sequence number i using the following formula: .in, In this example, ;

[0104] Step 2), the weights of all data points constitute the weighted matrix of historical data .

[0105] The following steps may be used to implement polynomial weighted fitting based on the weights, including:

[0106] Step 1) Fitting is performed with a polynomial of power n, that is, .in, is the fitted value of the data point with sequence number i, are the coefficients to be solved. In this example, ;

[0107] Step 2), the vector composed of the smoothed values of all data points is ;

[0108] Step 3), the vector of polynomial coefficients obtained for historical data is ;

[0109] Step 4), define the first Vandermonde matrix as ;

[0110] Step 5), solve the fitting performance index The minimum value of .

[0111] (4) Collect the latest data and use the weighted sequential least squares method to update the polynomial fitting results, including:

[0112] At time intervals Get the latest data, which constitutes the 31st discrete data point;

[0113] Re-smooth the three data points at the end of the discrete data, and the smoothing value of the latest data is ;

[0114] The weight of the latest data point is ;

[0115] The weighted sequential least squares method is used to update the polynomial fitting results. The updated polynomial coefficients are: .in, are the updated polynomial coefficients, , , In this embodiment, the following can be obtained: Figure 5 The fitted results shown in the figure are updated.

[0116] Through the above-mentioned substation real-time diagnosis method provided by this embodiment, historical data of important parameters such as voltage, current, temperature and load capacity are discretized; based on the discretized historical data, they are smoothed; polynomial weighted fitting is performed on the discretized historical data; the latest data is collected, and the polynomial fitting results are updated using the weighted sequential least squares method, which reduces the impact of random noise in the substation historical data on the fitting results, and can quickly update the fitting results in real time based on the latest collected data, thereby obtaining a more accurate estimation and prediction of the substation fault condition.

[0117] In addition, the embodiment of the present invention also provides a real-time diagnosis device for a substation, see Figure 6 As shown, the device includes:

[0118] A preprocessing module 610 is used to preprocess the pre-collected historical data of substation parameters to generate preprocessed historical data of the corresponding substation parameters;

[0119] The weighted fitting module 620 is used to perform polynomial weighted fitting on the pre-processed historical data of the corresponding power station parameters to generate a polynomial fitting result;

[0120] The updating module 630 is used to collect the current data of the substation parameters in real time and update the polynomial fitting results using the weighted sequential least squares method; the updated polynomial fitting results are used for substation diagnosis.

[0121] The substation real-time diagnosis device provided in the embodiment of the present application can be specific hardware on the equipment or software or firmware installed on the equipment, etc. The implementation principle and technical effects of the device provided in the embodiment of the present application are the same as those of the aforementioned method embodiment. For the sake of brief description, for parts not mentioned in the device embodiment, reference can be made to the corresponding contents in the aforementioned method embodiment. Technical personnel in the relevant field can clearly understand that, for the convenience and simplicity of description, the specific working processes of the systems, devices and units described above can all refer to the corresponding processes in the aforementioned method embodiment, and will not be repeated here. The substation real-time diagnosis device provided in the embodiment of the present application has the same technical features as the substation real-time diagnosis method provided in the above embodiment, so it can also solve the same technical problems and achieve the same technical effects.

[0122] An embodiment of the present application further provides an electronic device. Specifically, the electronic device includes a processor and a storage device; the storage device stores a computer program, and when the computer program is run by the processor, it executes the method described in any one of the above-mentioned embodiments.

[0123] Figure 7 A structural diagram of an electronic device provided in an embodiment of the present application, the electronic device 400 includes: a processor 40, a memory 41, a bus 42 and a communication interface 43, wherein the processor 40, the communication interface 43 and the memory 41 are connected via the bus 42; the processor 40 is used to execute an executable module stored in the memory 41, such as a computer program.

[0124] Memory 41 may include high-speed random access memory (RAM) and may also include non-volatile memory, such as at least one disk storage device. Communication between the system network element and at least one other network element is achieved through at least one communication interface 43 (which may be wired or wireless), and may utilize the Internet, a wide area network, a local area network, a metropolitan area network, or the like.

[0125] The bus 42 may be an ISA bus, a PCI bus, or an EISA bus. The bus may be divided into an address bus, a data bus, a control bus, and the like. For ease of representation, Figure 7 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0126] Among them, the memory 41 is used to store programs, and the processor 40 executes the program after receiving the execution instruction. The method executed by the process definition device disclosed in any embodiment of the above-mentioned embodiment of the present invention can be applied to the processor 40 or implemented by the processor 40.

[0127] Processor 40 may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method may be completed by hardware integrated logic circuits or software instructions in processor 40. The above processor 40 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It may implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in conjunction with the embodiments of the present invention may be directly implemented and executed by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. The software module may be located in a storage medium well-known in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or the like. The storage medium is located in the memory 41 , and the processor 40 reads the information in the memory 41 and completes the steps of the above method in combination with its hardware.

[0128] Corresponding to the above method, an embodiment of the present application also provides a computer-readable storage medium, which stores machine-executable instructions. When the computer-executable instructions are called and executed by the processor, the computer-executable instructions prompt the processor to execute the steps of the above method.

[0129] In the embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interface, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0130] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0131] In addition, each functional unit in the embodiments provided in the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0132] If the functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or the portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, electronic device, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage media include various media that can store program code, such as USB flash drives, mobile hard drives, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks.

[0133] It should be noted that similar numbers and letters represent similar items in the accompanying drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. In addition, the terms "first", "second", "third", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0134] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A real-time diagnosis method for a substation, characterized in that: include: Preprocessing the historical data of substation parameters collected in advance to generate preprocessed historical data of corresponding substation parameters; The substation parameters include: voltage, current, temperature and load capacity; Performing polynomial weighted fitting on the pre-processed historical data of the corresponding power station parameters to generate polynomial fitting results; The polynomial weighted fitting is performed on the pre-processed historical data of the corresponding strain station parameters, including: determining the weight of each data point in the pre-processed historical data of the corresponding strain station parameters based on a weight calculation formula; the weight calculation formula is: ; Where i is the serial number of the data point, i≥1, Based on the weight of each data point, generate the weighted matrix of the pre-processed historical data of the corresponding power station parameters ; Based on the weighted matrix of the historical data of the pre-processed corresponding strain station parameters , a vector of smoothed values for each data point , the first Vandermonde matrix As well as the fitting performance index, determine the vector consisting of the polynomial coefficients obtained for historical data ; collecting current data of the substation parameters in real time, and updating the polynomial fitting result using a weighted sequential least squares method; the updated polynomial fitting result is used for diagnosis of the substation; The current data of the substation parameters are collected in real time, and the polynomial fitting results are updated using the weighted sequential least squares method, including: Collect the substation parameters as the N+1th discrete data point in the discrete historical data to generate current data; N is the number of data points in the discrete historical data; based on the current data, determine the second Vandermonde matrix , the smoothed value of the current data , and the weight of each data point in the current data ; The polynomial fitting result is updated using the weighted sequential least squares method, and the updated polynomial fitting coefficient is: ; in, are the updated polynomial coefficients; ， ； ； is the first Vandermonde matrix, is the weighted matrix of historical data of substation parameters; A vector of coefficients of the polynomial obtained for the historical data.

2. The real-time diagnosis method for a substation according to claim 1, characterized in that: Preprocess the historical data of substation parameters collected in advance to generate preprocessed historical data of corresponding substation parameters, including: Discretize the historical data of substation parameters collected in advance to generate discrete historical data; Smoothing the discrete historical data using different sliding windows, and determining smoothing historical data results corresponding to the different sliding windows and corresponding smoothness; According to the smoothing processing historical data result corresponding to the sliding window with the minimum smoothness, the pre-processed historical data corresponding to the strain station parameter is determined.

3. The real-time diagnosis method for a substation according to claim 2, characterized in that: Smoothing the discrete historical data using different sliding windows, and determining smoothing historical data results corresponding to the different sliding windows and corresponding smoothness, including: Determine an average value of M data points in a sliding window as a smoothed value of a midpoint of the M data points; the sliding window includes M data points, M is an odd number greater than 1; each data point represents historical data at a moment; Starting from the first data point, the sliding window is translated point by point, and a smoothing value corresponding to each sliding window is determined to correspond to a result of smoothing the historical data; The smoothness corresponding to the sliding window with a window size of M is calculated based on the smoothness value.

4. A real-time diagnostic device for a substation, characterized in that: include: A preprocessing module is used to preprocess the historical data of substation parameters collected in advance and generate preprocessed historical data of corresponding substation parameters; A weighted fitting module is configured to perform polynomial weighted fitting on the pre-processed historical data of the corresponding strain station parameters to generate a polynomial fitting result; wherein the polynomial weighted fitting on the pre-processed historical data of the corresponding strain station parameters comprises: determining the weight of each data point in the pre-processed historical data of the corresponding strain station parameters based on a weight calculation formula; the weight calculation formula is: ; Where i is the serial number of the data point, i≥1, Based on the weight of each data point, generate the weighted matrix of the pre-processed historical data of the corresponding power station parameters ; Based on the weighted matrix of the historical data of the pre-processed corresponding strain station parameters , a vector of smoothed values for each data point , the first Vandermonde matrix As well as the fitting performance index, determine the vector consisting of the polynomial coefficients obtained for historical data ; An updating module, configured to collect current data of the substation parameters in real time and update the polynomial fitting result using a weighted sequential least squares method; the updated polynomial fitting result is used for diagnosis of the substation; The current data of the substation parameters are collected in real time, and the polynomial fitting results are updated using the weighted sequential least squares method, including: Collect the substation parameters as the N+1th discrete data point in the discrete historical data to generate current data; N is the number of data points in the discrete historical data; based on the current data, determine the second Vandermonde matrix , the smoothed value of the current data , and the weight of each data point in the current data ; The polynomial fitting result is updated using the weighted sequential least squares method, and the updated polynomial fitting coefficient is: ; in, are the updated polynomial coefficients; ， ； ； is the first Vandermonde matrix, is the weighted matrix of historical data of substation parameters; A vector of polynomial coefficients obtained for historical data.

5. An electronic device comprising a memory and a processor, wherein the memory stores a computer program that can be run 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 3 are implemented.

6. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to execute the method according to any one of claims 1 to 3.

Images