A method for extracting steep wave features of flexible DC transformer

Abstract

The present application relates to a method for extracting steep wave features of a flexible DC transformer. The method comprises: obtaining target identification parameters, wherein the target identification parameters include a target wavefront time and a target steep wave voltage peak value; inputting the target identification parameters into a recognition model of a steep wave voltage peak value, wherein the recognition model is constructed based on the correspondence between the real wavefront time and the real steep wave voltage; obtaining a recognition result output by the recognition model, wherein the recognition result represents the probability of the target steep wave voltage peak value appearing at the target wavefront time. The method for extracting steep wave features of a flexible DC transformer can improve the accuracy of identifying the steep wave voltage peak value.

Description

Technical Field

[0001] The present application relates to the technical field of flexible DC transformers, and in particular to a method for extracting steep wave features of flexible DC transformers. Background Art

[0002] The flexible DC connection transformer is the link for energy exchange between the AC system and the converter valve of the flexible DC substation. In order to ensure the safety of the flexible DC connection transformer, it is necessary to identify the steep wave voltage peak of the flexible DC transformer.

[0003] At present, the identification of steep wave voltage peak mainly involves simulating lightning waves and operation waves to identify the steep wave voltage peak of the flexible DC connection transformer.

[0004] However, the accuracy of identifying the steep wave voltage peak by simulating lightning waves and operating waves is not high. Summary of the invention

[0005] Based on this, it is necessary to provide a method for extracting steep wave features of a flexible DC transformer that can improve the accuracy of steep wave voltage peak recognition in response to the above technical problems.

[0006] A method for extracting steep wave features of a flexible DC transformer, comprising:

[0007] Acquire target identification parameters, wherein the target identification parameters include target wavefront time and target steep wave voltage peak value;

[0008] Inputting the target identification parameters into an identification model of a steep wave voltage peak, wherein the identification model is constructed based on a correspondence between a real wavefront time and a real steep wave voltage;

[0009] A recognition result output by the recognition model is obtained, wherein the recognition result represents a probability that the target steep wave voltage peak value appears at the target wavefront time.

[0010] In one embodiment, the recognition model includes a recognition function, and the recognition function is the product of a first objective function and a second objective function;

[0011] The first objective function is negatively correlated with the cube of the steep wave voltage peak value, positively correlated with the quadratic value of the steep wave voltage peak value, and positively correlated with the linear value of the steep wave voltage peak value;

[0012] The second objective function is linearly positively correlated with the qth power of the wavefront time difference, and the wavefront time difference is the difference between the wavefront time and a constant o.

[0013] In one embodiment, the recognition model is constructed in the following manner:

[0014] Acquire multiple groups of collected data, each group of collected data includes multiple corresponding relationships between real wavefront time and real steep wave voltage;

[0015] The recognition model is constructed according to the multiple sets of collected data.

[0016] In one embodiment, the step of constructing the recognition model based on the multiple sets of collected data includes:

[0017] Convert each group of the collected data into an initial matrix to obtain a plurality of initial matrices;

[0018] Determine a first probability matrix and a second probability matrix respectively according to the plurality of initial matrices, wherein the first probability matrix is ​​a probability matrix of a steep wave voltage peak value, and the second probability matrix is ​​a probability matrix of a steep wave voltage distribution within a rising time;

[0019] The first probability matrix and the second probability matrix are fitted respectively to obtain the recognition model.

[0020] In one embodiment, fitting the first probability matrix and the second probability matrix respectively includes:

[0021] Using the first formula as the fitting function of the first probability matrix, fitting the first probability matrix by Lagrange interpolation to obtain a first objective function;

[0022] The second formula is used as the fitting function of the second probability matrix, and the second probability matrix is ​​fitted by Lagrange interpolation to obtain a second objective function.

[0023] In one embodiment, the step of determining the first probability matrix according to the plurality of initial matrices comprises:

[0024] Determine a peak matrix based on a plurality of the initial matrices;

[0025] Determine the first probability matrix according to the peak matrix; and / or,

[0026] The step of determining a second probability matrix according to a plurality of the initial matrices comprises:

[0027] Determine a steep wave voltage distribution matrix during a rising time according to the plurality of initial matrices;

[0028] The second probability matrix is ​​determined according to the steep wave voltage distribution matrix within the rising time.

[0029] In one embodiment, the acquiring of multiple sets of collected data includes:

[0030] Sensing the operation data of the flexible DC transformer through an electro-optical sensor;

[0031] The operation data is decoded by a decoding industrial computer to obtain multiple groups of collected data.

[0032] A device for extracting steep wave characteristics of a flexible DC transformer, comprising:

[0033] A first acquisition module is used to acquire target identification parameters, wherein the target identification parameters include target wavefront time and target steep wave voltage peak value;

[0034] An identification module, used for inputting the target identification parameters into an identification model of a steep wave voltage peak value, wherein the identification model is constructed based on a correspondence between a real wavefront time and a real steep wave voltage;

[0035] The second acquisition module is used to acquire the recognition result output by the recognition model, wherein the recognition result represents the probability of the target steep wave voltage peak occurring at the target wavefront time.

[0036] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0037] A computer-readable storage medium stores a computer program, which implements the steps of the above method when executed by a processor.

[0038] The above-mentioned method for extracting steep wave features of a flexible DC transformer includes: obtaining target identification parameters, wherein the target identification parameters include a target wavefront time and a target steep wave voltage peak value; inputting the target identification parameters into an identification model of a steep wave voltage peak value, wherein the identification model is constructed based on the correspondence between a real wavefront time and a real steep wave voltage; obtaining an identification result output by the identification model, wherein the identification result characterizes the probability of the target steep wave voltage peak value appearing at the target wavefront time. Since the identification model is constructed based on the correspondence between the real wavefront time and the real steep wave voltage, the identification result obtained using the identification model also takes into account the steep wave effects caused by various electromagnetic transient characteristics, and is not limited to the steep wave effects caused by lightning waves and operating waves. Compared with identifying the steep wave voltage peak value by simulating lightning waves and operating waves, the accuracy of identifying the steep wave voltage peak value is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the conventional technology, the drawings required for use in the embodiments or the conventional technology descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0040] Figure 1 A schematic flow chart of a method for extracting steep wave features of a flexible DC transformer provided by an embodiment;

[0041] Figure 2 A schematic diagram of a flow chart of a method for constructing a recognition model provided by an embodiment;

[0042] Figure 3 An embodiment provides a Figure 2 A detailed flow chart of step 220;

[0043] Figure 4 An equivalent schematic diagram of a first probability matrix provided by an embodiment;

[0044] Figure 5 An equivalent schematic diagram of a second probability matrix provided by an embodiment;

[0045] Figure 6 An equivalent schematic diagram of a third probability matrix provided by an embodiment;

[0046] Figure 7 A schematic diagram of a set of collected data provided by an embodiment;

[0047] Figure 8 A schematic structural diagram of a device for extracting steep wave characteristics of a flexible DC transformer is provided in accordance with an embodiment. DETAILED DESCRIPTION

[0048] In order to facilitate understanding of the present application, the present application will be described more fully below with reference to the relevant drawings. Embodiments of the present application are provided in the drawings. However, the present application can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present application more thorough and comprehensive.

[0049] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application.

[0050] It can be understood that the terms "first", "second", etc. used in the present application can be used in this article to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from another element.

[0051] It should be noted that when an element is considered to be "connected" to another element, it can be directly connected to the other element, or connected to the other element through an intermediate element. In addition, the "connection" in the following embodiments should be understood as "electrical connection", "communication connection", etc. if there is transmission of electrical signals or data between the connected objects.

[0052] When used herein, the singular forms "a", "an", and "said / the" may also include plural forms, unless the context clearly indicates otherwise. It should also be understood that the terms "include / comprise" or "have" and the like specify the presence of stated features, wholes, steps, operations, components, parts, or combinations thereof, but do not exclude the possibility of the presence or addition of one or more other features, wholes, steps, operations, components, parts, or combinations thereof. At the same time, the term "and / or" used in this specification includes any and all combinations of the relevant listed items.

[0053] refer to Figure 1 , Figure 1 A schematic diagram of a flow chart of a method for extracting steep wave features of a flexible DC transformer is provided in an embodiment. Figure 1 As shown, a method for extracting steep wave features of a flexible DC transformer is provided, including steps 110 to 130.

[0054] Step 110: Acquire target identification parameters, where the target identification parameters include target wavefront time and target steep wave voltage peak value.

[0055] Wherein, the target identification parameter refers to a parameter used to identify the steep wave peak value. Specifically, the target identification parameter includes a target wavefront time and a target steep wave voltage peak value. The target wavefront time refers to the wavefront time that needs to be predicted. The target steep wave voltage peak value refers to the steep wave voltage peak value that needs to be predicted. In the present embodiment, the target wavefront time and the target steep wave voltage peak value are both predicted values. Exemplarily, the target wavefront time can be 8ms (microseconds), and the target steep wave voltage peak value can be 1.8pu (per unit).

[0056] Step 120: input the target identification parameters into a recognition model of steep wave voltage peak value, wherein the recognition model is constructed based on the correspondence between the real wavefront time and the real steep wave voltage.

[0057] The identification model is used to predict the probability of the target steep wave voltage peak occurring at the target wavefront time. The greater the probability, the more likely it is to occur. Specifically, the identification model is constructed based on the correspondence between the real wavefront time and the real steep wave voltage. The real wavefront time refers to the real wavefront time. The real steep wave feature refers to the real steep wave feature.

[0058] Specifically, due to the particularity of the flexible DC transmission system, there are system resonant overvoltages and special overvoltage waveforms caused by DC system faults. The flexible DC transformer is subjected to steep wave effects caused by various electromagnetic transient characteristics during operation. Conventional lightning waves and operating waves can no longer accurately describe the steep wave characteristics of the flexible DC transformer during operation. The identification model in this step is constructed based on the correspondence between the real wavefront time and the real steep wave voltage, that is, the steep wave effects caused by various electromagnetic transient characteristics during operation of the flexible DC transformer are taken into account. Therefore, the results calculated using the identification model are more accurate.

[0059] Step 130 : Obtain a recognition result output by the recognition model, wherein the recognition result represents a probability of the target steep wave voltage peak occurring at the target wavefront time.

[0060] Among them, the recognition result refers to the result calculated by inputting the target recognition parameters into the recognition model. Specifically, the recognition result is used to characterize the probability of the target steep wave voltage peak appearing at the target wavefront time. It can be understood that the greater the probability, the greater the possibility of the target steep wave voltage peak appearing at the target wavefront time. If the probability is too large, protection needs to be taken before the target wavefront time arrives.

[0061] In this embodiment, since the recognition model is constructed by the correspondence between the real wavefront time and the real steep wave voltage, the recognition result obtained by using the recognition model also takes into account the steep wave effect caused by various electromagnetic transient characteristics, not only limited to the steep wave effect caused by lightning waves and operating waves, compared with the recognition of steep wave voltage peaks by simulating lightning waves and operating waves, the accuracy of steep wave voltage peak recognition is improved. In addition, since the probability of the target steep wave voltage peak occurring at the target wavefront time can be obtained by inputting the target recognition parameters into the recognition model, the recognition efficiency is also high.

[0062] In one embodiment, the recognition model includes a recognition function, wherein the recognition function is the product of the first objective function and the second objective function;

[0063] The first objective function is negatively correlated with the cube of the steep wave voltage peak value, positively correlated with the quadratic value of the steep wave voltage peak value, and positively correlated with the linear value of the steep wave voltage peak value;

[0064] The second objective function is linearly positively correlated with the qth power of the wavefront time difference, and the wavefront time difference is the difference between the wavefront time and a constant o.

[0065] In this embodiment, q and o are both constants, which need to be calculated using the corresponding relationship between the real wavefront time and the real steep wave voltage. For example, the first objective function f(p)=jp 3 +kp 2+lp+m, the second objective function f(t)=n(to) q , then the identification function is f(p,t)=f(p)*f(t). Among them, p is the peak value of steep wave voltage, t is the wavefront time, j, k, l, m, n, o and q are all constants, which can be calculated by Lagrange interpolation method using the corresponding relationship between the real wavefront time and the real steep wave voltage.

[0066] It should be noted that j, k, l, and m in the first objective function are already known, and n, o, and q in the second objective function are also already known.

[0067] Exemplarily, in an actual calculation, the first objective function is:

[0068] f(p)=-236.38p 3 +815.19p 2 +-728.43p+162.62.

[0069] Exemplarily, in an actual calculation, the second objective function is:

[0070] f(t)=76.4(t-0.4) 0.14 .

[0071] The following is an explanation of how to construct a recognition model.

[0072] refer to Figure 2 , Figure 2 A schematic diagram of a process for constructing a recognition model provided in an embodiment. Figure 2 As shown, a method for constructing a recognition model is provided, including step 210 to step 220.

[0073] Step 210: Acquire multiple groups of collected data, each group of collected data includes multiple corresponding relationships between real wavefront time and real steep wave voltage.

[0074] In this step, the number of corresponding relationships of each group of collected data is the same. Specifically, each collected data includes a plurality of real wavefront times and a plurality of real steep wave voltages in one-to-one correspondence, that is, the collected data includes the instantaneous values ​​of steep wave voltages corresponding to the plurality of real wavefront times.

[0075] Step 220: construct the recognition model based on the multiple groups of collected data.

[0076] In this embodiment, the recognition model is constructed based on multiple sets of collected data. Specifically, the actual steep wave voltage peak value of each actual wavefront time can be extracted from the collected data.

[0077] In this embodiment, since the wavefront time and the steep wave voltage are both real, they represent the steep wave effects caused by various electromagnetic transient characteristics, so the obtained identification model is more accurate.

[0078] refer to Figure 3 , Figure 3 An embodiment provides a Figure 2 In one embodiment, as Figure 3 As shown, step 220, constructing the recognition model according to the multiple groups of collected data, includes steps 310 to 330.

[0079] Step 310: Convert each group of the collected data into an initial matrix to obtain multiple initial matrices.

[0080] Among them, the initial matrix refers to the data converted from the collected data, and the collected data is represented in the form of a matrix. Specifically, the initial matrix is ​​an N*H matrix. Among them, N represents the number of real steep wave voltages, H=2h, h is the number of phases of the transformer, that is, h=1, 2 or 3. It should be noted that the value of h can be set as needed and is not limited here. When h=3, the real steep wave voltages of the three phases of the transformer are collected. Exemplarily, when h=3, the initial matrix can be expressed as:

[0081]

[0082] Among them, the first column, the third column and the fifth column all represent the number of real steep wave voltages, and the number N of real steep wave voltages of the initial matrix A is 172. The second column, the fourth column and the fifth column respectively represent the instantaneous values ​​of the real steep wave voltages corresponding to the three phases of the transformer. Exemplarily, the number B of the initial matrix can be 1523 times, which is not limited here.

[0083] Step 320: Determine a first probability matrix and a second probability matrix according to the multiple initial matrices, wherein the first probability matrix is ​​a probability matrix of steep wave voltage peak value, and the second probability matrix is ​​a probability matrix of steep wave voltage distribution within the rising time.

[0084] In this step, a first probability matrix is ​​determined according to a plurality of initial matrices, and a second probability matrix is ​​determined according to a plurality of initial matrices.

[0085] The first probability matrix is ​​a probability matrix of steep wave voltage peaks. Specifically, the size of the first probability matrix is ​​the number of peaks*h. For example, the number of peaks can be 10, and the number of peaks 10 represents 10 values ​​such as 1.0pu-1.9pu. Figure 4 , Figure 4 An equivalent schematic diagram of a first probability matrix provided for an embodiment.

[0086] like Figure 4 As shown, the abscissa of the first probability matrix is ​​the peak value, and the ordinates are the probability of the peak value and the cumulative probability of the peak value.

[0087] In one embodiment, the step of determining the first probability matrix according to the plurality of initial matrices comprises:

[0088] Determine a peak matrix based on a plurality of the initial matrices;

[0089] The first probability matrix is ​​determined according to the peak matrix.

[0090] The peak matrix refers to a matrix obtained based on multiple initial matrices and used to characterize the peak value of the steep wave voltage. Exemplarily, the size of the peak matrix is ​​B*(h+1). Specifically, one column of the peak matrix is ​​the number N of real steep wave voltages, and the remaining columns are the peak values ​​of the real steep wave voltages corresponding to each phase.

[0091] In one embodiment, the method of determining the peak matrix C according to the multiple initial matrices B*(h+1) can be referred to as follows:

[0092]

[0093] In one embodiment, the method of determining the first probability matrix D according to the peak matrix C can be referred to as follows:

[0094]

[0095]

[0096] The second probability matrix is ​​a probability matrix of steep wave voltage distribution in the rising time. The steep wave voltage distribution can be obtained by the number of steep wave voltages in each group of collected data / the total number of steep wave voltages in each group of collected data. Specifically, the size of the second probability matrix can also be 10*h. Figure 5 , Figure 5 An equivalent schematic diagram of a second probability matrix provided for an embodiment.

[0097] like Figure 5 As shown, the abscissa of the second probability matrix is ​​the wavefront time (ms), and the ordinate is the probability of the steep wave voltage distribution of the wavefront time and the cumulative probability of the steep wave voltage distribution.

[0098] In one embodiment, the step of determining the second probability matrix according to the plurality of initial matrices comprises:

[0099] Determine a steep wave voltage distribution matrix during a rising time according to the plurality of initial matrices;

[0100] The second probability matrix is ​​determined according to the steep wave voltage distribution matrix within the rising time.

[0101] Among them, the steep wave voltage distribution matrix during the rise time refers to a matrix obtained according to multiple initial matrices and used to characterize the steep wave voltage distribution during the rise time. Exemplarily, the size of the steep wave voltage distribution matrix during the rise time is B*(h+1). Specifically, one column of the steep wave voltage distribution matrix during the rise time is the number N of real steep wave voltages, and the remaining columns are the distribution of real steep wave voltages corresponding to each phase.

[0102] In one embodiment, the method of determining the steep wave voltage distribution matrix E during the rise time according to multiple initial matrices B*(h+1) can be referred to as follows:

[0103]

[0104] In one embodiment, the method for determining the second probability moment F according to the steep wave voltage distribution matrix E during the rise time can be referred to as follows:

[0105]

[0106]

[0107] Step 330: Fit the first probability matrix and the second probability matrix respectively to obtain the recognition model.

[0108] In this step, the first probability matrix and the second probability matrix are fitted respectively to obtain the recognition model.

[0109] In one embodiment, step 330, fitting the first probability matrix and the second probability matrix respectively, includes:

[0110] Using the first formula as the fitting function of the first probability matrix, fitting the first probability matrix by Lagrange interpolation to obtain a first objective function;

[0111] The second formula is used as the fitting function of the second probability matrix, and the second probability matrix is ​​fitted by Lagrange interpolation to obtain a second objective function.

[0112] In this embodiment, the first formula is exemplarily f(p)=jp 3 +kp 2 +lp+m, the second formula is f(t)=n(to) qIt should be noted that determining the first objective function according to the first formula is a process of using the first probability matrix to solve the constant in the first formula through Lagrange interpolation. Similarly, determining the second objective function according to the second formula is a process of using the second probability matrix to solve the constant in the second formula through Lagrange interpolation.

[0113] In one embodiment, optionally, a third probability matrix may be determined according to the initial matrix, and the first probability model, the second probability model and the third probability model may be fitted respectively, so as to obtain the recognition model.

[0114] In this embodiment, the third probability matrix is ​​a probability matrix of the rising change rate distribution. Specifically, the rising change rate can be obtained by dividing the difference between two adjacent instantaneous values ​​by the time difference corresponding to the two adjacent instantaneous values. Specifically, the size of the third probability matrix can also be 10*h. Figure 6 , Figure 6 An equivalent schematic diagram of a third probability matrix provided for an embodiment.

[0115] like Figure 6 As shown, the abscissa of the third probability matrix is ​​the steepness (KV / ms), and the ordinate is the probability of the steepness and the cumulative probability of the steepness.

[0116] In this embodiment, the step of determining the third probability matrix according to the initial matrix includes:

[0117] Determine a rising change rate distribution matrix according to a plurality of said initial matrices;

[0118] The third probability matrix is ​​determined according to the rise change rate distribution matrix.

[0119] The rise rate distribution matrix refers to a matrix obtained based on multiple initial matrices and used to characterize the rise rate of steep wave voltage. Exemplarily, the size of the rise rate distribution matrix is ​​B*(h+1). Specifically, one column of the rise rate distribution matrix is ​​the number N of real steep wave voltages, and the remaining columns are the distribution of the rise rate of each phase.

[0120] In one embodiment, the method of determining the rising change rate distribution matrix G according to the multiple initial matrices B*(h+1) can be referred to as follows:

[0121]

[0122]

[0123] In one embodiment, the method of determining the third probability matrix H according to the rising change rate distribution matrix G can be referred to as follows:

[0124]

[0125] It is understandable that the recognition model can be constructed using the first probability matrix and the second probability matrix, or the first probability matrix, the second probability matrix and the third probability matrix. In the research findings, only using the first probability matrix and the second probability matrix to construct the recognition model can also achieve the recognition effect, but due to the reduction in the amount of calculation, the calculation efficiency is also improved, saving computing resources.

[0126] It should be noted that, in this embodiment, if h=3, the identification result represents the probability of the target steep wave voltage peak occurring in any one of the three phases of the transformer at the target wavefront time.

[0127] In one embodiment, step 210, obtaining multiple sets of collected data, may include:

[0128] Sensing the operation data of the flexible DC transformer through an electro-optical sensor;

[0129] The operation data is decoded by a decoding industrial computer to obtain multiple groups of collected data.

[0130] Among them, the electro-optical sensor is placed near the transformer, with one end pointing to the transformer bushing grading ring and the other end connected to the transmission optical fiber. The other end of the transmission optical fiber is connected to the decoding industrial computer. The electro-optical sensor transmits the operating data obtained by the sensing transformer to the decoding industrial computer through the transmission optical fiber. The decoding industrial computer decodes the operating data to obtain multiple sets of collected data.

[0131] refer to Figure 7 , Figure 7 A schematic diagram of a set of collected data provided by an embodiment. Figure 7 As shown in FIG. 1 , the horizontal axis of the collected data is time, and the vertical axis is the instantaneous value of the steep wave voltage. Each phase of the transformer corresponds to a waveform curve.

[0132] It should be understood that although Figure 1-Figure 3 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 1-Figure 3 At least part of the steps may include multiple steps or multiple stages. These steps or stages are not necessarily performed at the same time, but can be performed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed in turn or alternately with other steps or at least part of the steps or stages in other steps.

[0133] refer to Figure 8 , Figure 8 A schematic diagram of a structure of a device for extracting steep wave characteristics of a flexible DC transformer is provided in an embodiment. Figure 8 As shown, a device for extracting steep wave features of a flexible DC transformer is provided, comprising: a first acquisition module 810, an identification module 820 and a second acquisition module 830, wherein:

[0134] The first acquisition module 810 is used to acquire target identification parameters, wherein the target identification parameters include target wavefront time and target steep wave voltage peak value;

[0135] The identification module 820 is used to input the target identification parameters into the identification model of the steep wave voltage peak value, wherein the identification model is constructed based on the corresponding relationship between the real wavefront time and the real steep wave voltage;

[0136] The second acquisition module 830 is used to acquire the recognition result output by the recognition model, where the recognition result represents the probability of the target steep wave voltage peak occurring at the target wavefront time.

[0137] In one embodiment, the recognition model includes a recognition function, and the recognition function is the product of the first objective function and the second objective function;

[0138] The first objective function is negatively correlated with the cube of the steep wave voltage peak value, positively correlated with the quadratic value of the steep wave voltage peak value, and positively correlated with the linear value of the steep wave voltage peak value;

[0139] The second objective function is linearly positively correlated with the qth power of the wavefront time difference, and the wavefront time difference is the difference between the wavefront time and a constant o.

[0140] In one embodiment, the apparatus further comprises:

[0141] A third acquisition module is used to acquire multiple groups of collected data, each group of collected data includes multiple corresponding relationships between real wavefront time and real steep wave voltage;

[0142] A construction module is used to construct the recognition model according to multiple groups of collected data.

[0143] In one embodiment, the building blocks include:

[0144] A conversion unit, used for converting each group of the collected data into an initial matrix to obtain a plurality of initial matrices;

[0145] A probability matrix determination unit, used to determine a first probability matrix and a second probability matrix respectively according to the plurality of initial matrices, wherein the first probability matrix is ​​a probability matrix of a steep wave voltage peak value, and the second probability matrix is ​​a probability matrix of a steep wave voltage distribution within a rising time;

[0146] A fitting unit is used to fit the first probability matrix and the second probability matrix respectively to obtain the recognition model.

[0147] In one embodiment, the fitting unit comprises:

[0148] A first fitting unit, configured to use the first formula as a fitting function of the first probability matrix, fit the first probability matrix through Lagrange interpolation, and obtain a first objective function;

[0149] The second fitting unit is used to use the second formula as the fitting function of the second probability matrix, fit the second probability matrix through Lagrange interpolation, and obtain a second objective function.

[0150] In one embodiment, the probability matrix determination unit includes:

[0151] A first determining subunit, configured to determine a peak matrix according to the plurality of initial matrices;

[0152] A second determining subunit is configured to determine the first probability matrix according to the peak matrix; and / or,

[0153] The probability matrix determination unit includes:

[0154] A third determining subunit is used to determine a steep wave voltage distribution matrix within a rising time according to the multiple initial matrices;

[0155] The fourth determining subunit is used to determine the second probability matrix according to the steep wave voltage distribution matrix within the rising time.

[0156] In one embodiment, the third acquisition module is specifically used to sense the operation data of the flexible DC transformer through an electro-optical sensor; and decode the operation data through a decoding industrial computer to obtain multiple groups of the collected data.

[0157] For the specific limitations of the device for extracting steep wave characteristics of flexible DC transformers, please refer to the limitations of the method for extracting steep wave characteristics of flexible DC transformers mentioned above, which will not be repeated here. Each module in the above-mentioned device for extracting steep wave characteristics of flexible DC transformers can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules. It should be noted that the division of modules in the embodiment of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation.

[0158] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0159] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0160] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0161] In the description of this specification, the description with reference to the terms "some embodiments", "other embodiments", "ideal embodiments", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic descriptions of the above terms do not necessarily refer to the same embodiment or example.

[0162] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0163] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A method for extracting steep wave features of a flexible DC transformer, characterized in that: include: Acquire target identification parameters, wherein the target identification parameters include target wavefront time and target steep wave voltage peak value; The target identification parameters are input into an identification model of a steep wave voltage peak value, wherein the identification model is constructed based on the correspondence between the real wavefront time and the real steep wave voltage, and the construction method of the identification model includes: obtaining multiple groups of collected data, each group of the collected data includes multiple correspondences between the real wavefront time and the real steep wave voltage; constructing the identification model according to the multiple groups of collected data, the identification model includes an identification function, the identification function is the product of a first objective function and a second objective function, the first objective function is negatively correlated with the cube of the steep wave voltage peak value, positively correlated with the square of the steep wave voltage peak value, and positively correlated with the first square of the steep wave voltage peak value; the second objective function is linearly positively correlated with the qth power of the wavefront time difference, the wavefront time difference is the difference between the wavefront time and a constant o, q and o are both constants, and are calculated using the correspondence between the real wavefront time and the real steep wave voltage; A recognition result output by the recognition model is obtained, wherein the recognition result represents a probability that the target steep wave voltage peak value appears at the target wavefront time.

2. The method according to claim 1, characterized in that The first objective function f(p)=jp 3 +kp 2 +lp+m, the second objective function f(t)=n(to) q , then the identification function is f(p,t)=f(p)*f(t), where p is the peak value of the steep wave voltage, t is the wavefront time, j, k, l, m, n, o and q are all constants, and it is calculated by the Lagrange interpolation method using the correspondence between the real wavefront time and the real steep wave voltage.

3. The method according to claim 1, characterized in that Each piece of collected data includes a plurality of real wavefront times and a plurality of real steep wave voltages corresponding to each other.

4. The method according to claim 3, characterized in that: The step of constructing the recognition model according to the multiple sets of collected data includes: Convert each group of the collected data into an initial matrix to obtain a plurality of initial matrices; Determine a first probability matrix and a second probability matrix respectively according to the plurality of initial matrices, wherein the first probability matrix is ​​a probability matrix of a steep wave voltage peak value, and the second probability matrix is ​​a probability matrix of a steep wave voltage distribution within a rising time; The first probability matrix and the second probability matrix are fitted respectively to obtain the recognition model.

5. The method according to claim 4, characterized in that The fitting of the first probability matrix and the second probability matrix respectively comprises: Using the first formula as the fitting function of the first probability matrix, fitting the first probability matrix by Lagrange interpolation to obtain a first objective function; The second formula is used as the fitting function of the second probability matrix, and the second probability matrix is ​​fitted by Lagrange interpolation to obtain a second objective function.

6. The method according to claim 4, characterized in that The step of determining a first probability matrix according to a plurality of said initial matrices comprises: Determine a peak matrix based on a plurality of the initial matrices; Determine the first probability matrix according to the peak matrix; and / or, The step of determining a second probability matrix according to a plurality of the initial matrices comprises: Determine a steep wave voltage distribution matrix during a rising time according to the plurality of initial matrices; The second probability matrix is ​​determined according to the steep wave voltage distribution matrix within the rising time.

7. The method according to any one of claims 3 to 6, characterized in that: The obtaining of multiple sets of collected data includes: Sensing the operation data of the flexible DC transformer through an electro-optical sensor; The operation data is decoded by a decoding industrial computer to obtain multiple groups of collected data.

8. A device for extracting steep wave characteristics of a flexible DC transformer, characterized in that: include: A first acquisition module is used to acquire target identification parameters, wherein the target identification parameters include target wavefront time and target steep wave voltage peak value; An identification module is used to input the target identification parameters into an identification model of a steep wave voltage peak value, wherein the identification model is constructed based on the correspondence between the real wavefront time and the real steep wave voltage, and the construction method of the identification model includes: acquiring multiple groups of collected data, each group of the collected data includes multiple correspondences between the real wavefront time and the real steep wave voltage; constructing the identification model according to the multiple groups of collected data, and the identification model includes an identification function, which is the product of a first objective function and a second objective function, the first objective function is negatively correlated with the cube of the steep wave voltage peak value, positively correlated with the square of the steep wave voltage peak value, and positively correlated with the first square of the steep wave voltage peak value; the second objective function is linearly positively correlated with the qth power of the wavefront time difference, and the wavefront time difference is the difference between the wavefront time and a constant o, q and o are both constants, and are calculated using the correspondence between the real wavefront time and the real steep wave voltage; The second acquisition module is used to acquire the recognition result output by the recognition model, wherein the recognition result represents the probability of the target steep wave voltage peak occurring at the target wavefront time.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, 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 7 are implemented.

Images