Transient recording data-based prompting method and device and storage medium

Abstract

The invention discloses a prompting method and device based on transient recording data and a storage medium. The method comprises the steps that a first transient recording data set of the electric power system and a second transient recording data set of the electric power system are obtained, the first transient recording data set is used for representing data collected from a first protection device of the electric power system through first transient recording equipment of the electric power system, and the second transient recording data set is used for representing data collected from a second protection device of the electric power system through second transient recording equipment of the electric power system; the second transient recording data set is used for representing data acquired from a second protection device of the power system through second transient recording equipment of the power system; respectively inputting the first transient recording data set and the second transient recording data set into a multi-dimensional analysis model of the power system for analysis to obtain an analysis result of the power system; and determining prompt information of the power system based on the analysis result, the first transient recording data set and the second transient recording data set. The technical problem of low fault processing efficiency of the power system is solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power systems, in particular to a prompt method and device based on transient recording wave data and a storage medium. BACKGROUND

[0002] In the power system, in order to enhance the stability and reliability of the system, for the key lines and equipment, a double protection strategy is usually adopted to realize the protection operation, that is, two independent relay protection systems are deployed, although the above-mentioned redundant configuration can significantly improve the protection efficiency. However, in the actual operation process of the system, due to the implementation of the double protection strategy, there may be a situation that the sampling sources are not synchronized, which brings difficulties for subsequent data comparison and fault judgment, thereby causing the technical problem of low fault handling efficiency of the power system.

[0003] At present, there is no effective solution to the above technical problem of low fault handling efficiency of the power system. SUMMARY

[0004] The embodiments of the present application provide a prompt method and device based on transient recording wave data and a storage medium, which at least solve the technical problem of low fault handling efficiency of the power system.

[0005] According to one aspect of the embodiments of the present application, a prompt method based on transient recording wave data is provided, which can include: obtaining a first transient recording wave data set of a power system and a second transient recording wave data set of the power system, wherein the first transient recording wave data set is used to represent data collected from a first protection device of the power system by a first transient recording wave device of the power system, and the second transient recording wave data set is used to represent data collected from a second protection device of the power system by a second transient recording wave device of the power system; inputting the first transient recording wave data set and the second transient recording wave data set into a multi-dimensional analysis model of the power system for analysis respectively to obtain an analysis result of the power system, wherein the multi-dimensional analysis model is trained by a first historical transient recording wave data set of the power system and a second historical transient recording wave data set of the power system, the first historical transient recording wave data set is a historical data set corresponding to the first transient recording wave data set, the second historical transient recording wave data set is a historical data set corresponding to the second transient recording wave data set, and the analysis result is used to represent a working state of the power system; determining prompt information of the power system based on the analysis result, the first transient recording wave data set and the second transient recording wave data set, wherein the prompt information is used to prompt that there is a potential fault risk in the power system.

[0006] Optionally, the first transient record data set and the second transient record data set are respectively input into a multi-dimensional analysis model of the power system for analysis to obtain an analysis result of the power system, including: performing normalization processing on data in the first transient record data set respectively to obtain a normalized first transient record data set, and performing normalization processing on data in the second transient record data set respectively to obtain a normalized second transient record data set; constructing a first multi-dimensional analysis matrix based on the normalized first transient record data set, and constructing a second multi-dimensional analysis matrix based on the normalized second transient record data set; inputting the first multi-dimensional analysis matrix and the second multi-dimensional analysis matrix into the multi-dimensional analysis model for analysis to obtain the analysis result.

[0007] Optionally, the analysis result includes: a first analysis result and a second analysis result, wherein the first analysis result is an analysis result of the multi-dimensional analysis model on the first transient record data, and the second analysis result is an analysis result of the multi-dimensional analysis model on the second transient record data; based on the analysis result, the first transient record data set and the second transient record data set, the prompt information of the power system is determined, including: comparing the first analysis result and the second analysis result to obtain a first comparison result, wherein the first comparison result is used to represent whether the first analysis result and the second analysis result are the same; in response to the first comparison result representing that the first analysis result and the second analysis result are not the same, the prompt information is determined based on the first transient record data set and the second transient record data set.

[0008] Optionally, in response to the first comparison result representing that the first analysis result and the second analysis result are not the same, the prompt information is determined based on the first transient record data set and the second transient record data set, including: in response to the first comparison result representing that the first analysis result and the second analysis result are not the same, performing alignment processing on the first transient record data set and the second transient record data set respectively to obtain an alignment processing result, wherein the alignment processing result is used to adjust the first sampling frequency of the first transient record data set and the second sampling frequency of the second transient record data set to be the same; based on the alignment processing result, the first transient record data set, the second transient record data set and a target abnormal threshold of the power system, a second comparison result is determined, wherein the second comparison result is used to represent that there is a potential fault risk in the power system; based on the second comparison result, the first transient record data set and the second transient record data set, the prompt information is determined.

[0009] Optionally, the second comparison result comprises a voltage amplitude comparison result, a current amplitude comparison result and a time difference value comparison result, and the prompt information is determined based on the first transient record data set and the second transient record data set and the second comparison result, including: obtaining a first voltage amplitude, a first current amplitude and a first time difference value corresponding to the target record sampling point in the first transient record data set, and obtaining a second voltage amplitude, a second current amplitude and a second time difference value corresponding to the target record sampling point in the second transient record data set; determining the voltage amplitude comparison result based on the first voltage amplitude, the second voltage amplitude and a voltage amplitude abnormal threshold in the target abnormal threshold, wherein the voltage amplitude comparison result is used to represent the voltage abnormality of the power system; determining the current amplitude comparison result based on the first current amplitude, the second current amplitude and a current amplitude abnormal threshold in the target abnormal threshold, wherein the current amplitude comparison result is used to represent the current abnormality of the power system; determining the time difference value comparison result based on the first time difference value, the second time difference value and a time difference value abnormal threshold in the target abnormal threshold, wherein the time difference value comparison result is used to represent the abnormality of the power equipment in the power system; and determining the prompt information based on the voltage amplitude comparison result, the current amplitude comparison result and the time difference value comparison result.

[0010] Optionally, the prompt information is determined based on the voltage amplitude comparison result, the current amplitude comparison result and the time difference value comparison result, including: comparing the analysis result with a preset analysis result of the power system based on the voltage amplitude comparison result, the current amplitude comparison result and the time difference value comparison result to obtain a third comparison result; and determining the prompt information in response to the third comparison result representing that the analysis result is different from the preset analysis result.

[0011] Optionally, the working state of the power system at least includes a normal working state, a short-circuit fault state, an oscillation state and a frequency abnormal state, wherein the oscillation state is used to represent the disturbance condition of the power system, and the frequency abnormal state is used to represent the power imbalance condition of the power system.

[0012] According to an aspect of an embodiment of the present application, there is provided a prompt device based on transient recording data, which can include: an acquisition unit configured to acquire a first transient recording data set of a power system and a second transient recording data set of the power system, wherein the first transient recording data set is used to represent data collected from a first protection device of the power system by a first transient recording device of the power system, and the second transient recording data set is used to represent data collected from a second protection device of the power system by a second transient recording device of the power system; an analysis unit configured to input the first transient recording data set and the second transient recording data set into a multi-dimensional analysis model of the power system respectively for analysis, to obtain an analysis result of the power system, wherein the multi-dimensional analysis model is trained by a first historical transient recording data set of the power system and a second historical transient recording data set of the power system, the first historical transient recording data set is a historical data set corresponding to the first transient recording data set, the second historical transient recording data set is a historical data set corresponding to the second transient recording data set, and the analysis result is used to represent a working state of the power system; and a determination unit configured to determine prompt information of the power system based on the analysis result, the first transient recording data set and the second transient recording data set, wherein the prompt information is used to prompt that there is a potential fault risk in the power system.

[0013] According to another aspect of an embodiment of the present application, there is also provided a computer-readable storage medium including a stored program, wherein the program, when executed by a processor, controls a device where the storage medium is located to perform the prompt method based on transient recording data according to an embodiment of the present application.

[0014] According to another aspect of an embodiment of the present application, there is also provided an electronic device including one or more processors and a memory, the memory being configured to store one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the prompt method based on transient recording data according to an embodiment of the present application.

[0015] According to another aspect of an embodiment of the present application, there is also provided a computer program product including a computer program, the computer program, when executed by a processor, implementing the prompt method based on transient recording data according to an embodiment of the present application.

[0016] In the embodiment of the present application, the first transient recording wave data set is collected from the first protection device of the power system by the first transient recording wave device of the power system, and the second transient recording wave data set is collected from the second protection device of the power system by the second transient recording wave device of the power system, the first transient recording wave data set and the second transient recording wave data set are respectively input into the multi-dimensional analysis model for analysis, so as to achieve the purpose of obtaining the analysis result of the power system, and then according to the above obtained analysis result, the first transient recording wave data set and the second transient recording wave data set, the prompt information of the power system can be determined. Since the first transient recording wave data set and the second transient recording wave data set are collected from different protection devices by different transient recording wave devices, the above obtained first transient recording wave data set and second transient recording wave data set are input into the multi-dimensional analysis model for analysis to obtain the analysis result, according to the analysis result at this time, the first transient recording wave data set and the second transient recording wave data set, the prompt information of the power system can be determined, so that when the power system has a potential fault risk, the relevant staff can be prompted in time to solve the technical problem of low fault handling efficiency of the power system, and the technical effect of improving the fault handling efficiency of the power system is realized. BRIEF DESCRIPTION OF DRAWINGS

[0017] The accompanying drawings, which are included to provide a further understanding of the present application and are incorporated in and constitute a part of this application, illustrate embodiments of the present application and together with the description serve to explain the present application. In the drawings:

[0018] Figure 1 is a flow chart of a prompt method based on transient recording wave data according to an embodiment of the present application;

[0019] Figure 2 is a flow chart of a dual transient recording wave data fast comparison and alarm method according to an embodiment of the present application;

[0020] Fig. 3(a) is a schematic diagram of two kinds of transient recording wave data before alignment according to an embodiment of the present application;

[0021] Fig. 3(b) is a schematic diagram of two kinds of transient recording wave data after alignment according to an embodiment of the present application;

[0022] Figure 4 is a schematic diagram of another alignment processing of transient recording wave data according to an embodiment of the present application;

[0023] Figure 5 is a schematic diagram of a prompt device based on transient recording wave data according to an embodiment of the present application. DETAILED DESCRIPTION

[0024] In the following, the technical solutions in the embodiments of the present application will be described clearly and completely with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all the other embodiments obtained by a person of ordinary skill in the art without creative effort should belong to the protection scope of the present application.

[0025] It should be noted that the terms "first", "second" and the like in the description and claims of the present application and the above drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in other than the order illustrated or described herein. In addition, the terms "comprise" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device that includes a list of steps or units does not necessarily limit to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0026] According to the embodiments of the present application, a prompt method based on transient recording data is provided. It should be noted that the steps shown in the flowchart of the drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described herein can be executed in an order different from that shown herein.

[0027] Figure 1 is a flowchart of a prompt method based on transient recording data according to the embodiments of the present application, as shown in Figure 1 The method can include the following steps:

[0028] Step S101, acquiring a first transient recording data set of the power system and a second transient recording data set of the power system.

[0029] In the technical solution provided in the above step S101 of the present application, the first transient recording data set of the power system and the second transient recording data set of the power system can be acquired, wherein the first transient recording data set is used to represent the data collected from the first protection device of the power system by the first transient recording device of the power system, and the second transient recording data set is used to represent the data collected from the second protection device of the power system by the second transient recording device of the power system.

[0030] Optionally, the first transient recording device can be referred to as a first transient recording apparatus, and the second transient recording device can be referred to as a second transient recording apparatus. The first transient recording data set can be referred to as a first transient data set, and can also be referred to as first sampling data, and is represented by S1. The second transient recording data set can be referred to as a second transient data set, and can also be referred to as second sampling data, and is represented by S2. The first transient recording data set and the second transient recording data set each include voltage or current transient recording data.

[0031] For example, transient recording data of two sets of protection devices within 6 cycles is collected by transient recording apparatuses installed on the devices, and the sampling data of the two sets of protection devices are defined as sampling data S1 and S2, which each include voltage, current, and other transient recording data.

[0032] It should be noted that the above is only one preferred embodiment of obtaining the first transient recording data set of the power system and the second transient recording data set of the power system, and the process and method of obtaining the first transient recording data set of the power system and the second transient recording data set of the power system are not specifically limited.

[0033] In step S102, the first transient recording data set and the second transient recording data set are respectively input into a multi-dimensional analysis model of the power system for analysis, and an analysis result of the power system is obtained.

[0034] In the technical solution provided in step S102 of the present application, after the first transient recording data set and the second transient recording data set are obtained, the first transient recording data set and the second transient recording data set are respectively input into a multi-dimensional analysis model of the power system for analysis, so as to obtain an analysis result of the power system.

[0035] Optionally, the following step needs to be performed twice: the first transient recording data set and the second transient recording data set are respectively input into a multi-dimensional analysis model of the power system for analysis, and an analysis result of the power system is obtained. After the step is performed, two analysis results can be obtained, and if the two analysis results are different, the next step can be performed.

[0036] Optionally, the multi-dimensional analysis model is trained by a first historical transient recording data set of the power system and a second historical transient recording data set of the power system, the first historical transient recording data set is a historical data set corresponding to the first transient recording data set, the second historical transient recording data set is a historical data set corresponding to the second transient recording data set, and the analysis result is used to represent a working state of the power system.

[0037] Optionally, the multi-dimensional analysis model can be constructed by a convolutional neural network (CNN). The convolutional neural network is a deep learning model suitable for processing data with grid structure (such as images, signal waveforms, etc.), which can automatically extract features in the data and classify or predict through convolutional layers, pooling layers, and fully connected layers.

[0038] For example, after obtaining the transient recording data sets from two sets of protection devices collected by different transient recording devices, the transient recording data sets of the two sets are analyzed by using the convolutional neural network to obtain the working state of the power system.

[0039] It should be noted that this is only one preferred embodiment of obtaining the analysis result of the power system, and the process and method of obtaining the analysis result of the power system are not specifically limited. As long as the first transient recording data set and the second transient recording data set are input into the multi-dimensional analysis model of the power system for analysis to obtain the analysis result of the power system, the process and method are within the protection scope of the present application, and will not be listed here.

[0040] In step S103, based on the analysis result, the first transient recording data set and the second transient recording data set, the prompt information of the power system is determined, wherein the prompt information is used to prompt that the power system has a potential fault risk.

[0041] In the technical solution provided by the above step S103 of the present application, the analysis result, the first transient recording data set and the second transient recording data set obtained according to the above steps can be used to determine the prompt information of the power system, so as to prompt the staff responsible for the power system that the power system has a potential fault risk. The prompt information can be called fault information or abnormal alarm information.

[0042] It can be understood that this is only one preferred embodiment of determining the prompt information of the power system, and the process and method of determining the prompt information of the power system are not specifically limited. As long as the process and method of determining the prompt information of the power system based on the analysis result, the first transient recording data set and the second transient recording data set are within the protection scope of the present application, and will not be listed here.

[0043] The first transient recording wave data set is collected from the first protection device of the power system by the first transient recording wave device of the power system, and the second transient recording wave data set is collected from the second protection device of the power system by the second transient recording wave device of the power system, the first transient recording wave data set and the second transient recording wave data set are respectively input into the multi-dimensional analysis model for analysis, so as to achieve the purpose of obtaining the analysis result of the power system, and then the prompt information of the power system can be determined according to the above obtained analysis result, the first transient recording wave data set and the second transient recording wave data set. Since the first transient recording wave data set and the second transient recording wave data set are collected from different protection devices by different transient recording wave devices, the first transient recording wave data set and the second transient recording wave data set are input into the multi-dimensional analysis model for analysis to obtain the analysis result, and the prompt information of the power system can be determined according to the analysis result, the first transient recording wave data set and the second transient recording wave data set at this time, so that when the power system has a potential fault risk, the relevant staff can be prompted in time to solve the technical problem of low fault handling efficiency of the power system, and the technical effect of improving the fault handling efficiency of the power system is realized.

[0044] The above method of the embodiment will be further introduced below.

[0045] As an optional embodiment, in step S102, the first transient recording wave data set and the second transient recording wave data set are respectively input into the multi-dimensional analysis model of the power system for analysis to obtain the analysis result of the power system, including: respectively performing normalization processing on the data in the first transient recording wave data set to obtain the normalized first transient recording wave data set, and respectively performing normalization processing on the data in the second transient recording wave data set to obtain the normalized second transient recording wave data set; constructing a first multi-dimensional analysis matrix based on the normalized first transient recording wave data set, and constructing a second multi-dimensional analysis matrix based on the normalized second transient recording wave data set; respectively inputting the first multi-dimensional analysis matrix and the second multi-dimensional analysis matrix into the multi-dimensional analysis model for analysis to obtain the analysis result.

[0046] In this embodiment, after obtaining the first transient recording data set and the second transient recording data set, the data in the first transient recording data set is normalized respectively to obtain a normalized first transient recording data set, and the data in the second transient recording data set is normalized respectively to obtain a normalized second transient recording data set. The normalized first transient recording data set is used to construct a first multi-dimensional analysis matrix, and the normalized second transient recording data set is used to construct a second multi-dimensional analysis matrix. Then, the first multi-dimensional analysis matrix and the second multi-dimensional analysis matrix can be input into a multi-dimensional analysis model for analysis to obtain an analysis result and determine the working state of the power system at this time.

[0047] Alternatively, the first multi-dimensional analysis matrix can be represented by S1'. The second multi-dimensional analysis matrix can be represented by S2'. The first multi-dimensional analysis matrix and the second multi-dimensional analysis matrix are both matrices in which each type of data is a dimension. The rows of the matrix represent each cycle, and the columns of the matrix represent each sampling point, as shown in Table 1 and Table 2. Table 1 is a first multi-dimensional analysis matrix table, and Table 2 is a second multi-dimensional analysis matrix table.

[0048] Alternatively, as shown in Table 1, in cycle 1, n sampling points can be obtained, i.e., X 1-1 , X 1-2 ,..., X 1-n ; in cycle 2, n sampling points can be obtained, i.e., X 2-1 , X 2-2 ,..., X 2-n ; and in cycle 6, n sampling points can be obtained, i.e., X 6-1 , X 6-2 ,..., X 6-n . The first multi-dimensional analysis matrix can be constructed according to the above obtained sampling points. As shown in Table 2, the second multi-dimensional analysis matrix is constructed in the same way as the first multi-dimensional analysis matrix, and details are not repeated here.

[0049] Table 1 First multi-dimensional analysis matrix table

[0050]

[0051] Table 2 Second multi-dimensional analysis matrix table

[0052]

[0053] Optionally, the normalization processing is used to represent the conversion of the original data into standardized data within a certain range, usually scaling the data to between 0 and 1, or between -1 and 1, in order to facilitate algorithm processing and comparison. The purpose of normalization processing is to eliminate the influence of data dimension and magnitude, so that different types of features can be compared and analyzed on the same scale.

[0054] For example, after obtaining the sampling data collected from different transient recorders, normalization processing is required for each type of data in the sampling data S1 and S2, and a multi-dimensional analysis matrix is constructed for each type of data, respectively S1' and S2', and then the obtained multi-dimensional analysis matrix is sequentially input into the trained neural network CNN, so as to determine the results of the two sets of sampling data respectively, and thus the analysis results can be obtained.

[0055] For another example, the above-mentioned normalization processing refers to separately normalizing each type of data, that is, as shown in the following formula:

[0056]

[0057] wherein, Xi represents the i-th sampling data in each type of data, minX represents the minimum sampling data value in each type of data, and maxX represents the maximum sampling data value in each type of data. i wherein, Xi represents the i-th sampling data in each type of data, minX represents the minimum sampling data value in each type of data, and maxX represents the maximum sampling data value in each type of data.

[0058] As an optional embodiment, the analysis result includes a first analysis result and a second analysis result, wherein the first analysis result is an analysis result of the multi-dimensional analysis model on the first transient record data, and the second analysis result is an analysis result of the multi-dimensional analysis model on the second transient record data. Based on the analysis result, the first transient record data set and the second transient record data set, the prompt information of the power system is determined, including: comparing the first analysis result and the second analysis result to obtain a first comparison result, wherein the first comparison result is used to represent whether the first analysis result and the second analysis result are the same; in response to the first comparison result representing that the first analysis result and the second analysis result are not the same, determining the prompt information based on the first transient record data set and the second transient record data set.

[0059] In this embodiment, the analysis result obtained in the above steps can include a first analysis result and a second analysis result, and the first analysis result and the second analysis result can be compared to obtain a first comparison result. When the first comparison result represents that the first analysis result and the second analysis result are not the same, the prompt information can be determined according to the first transient record data set and the second transient record data set.

[0060] Optionally, when two analysis results are obtained, i.e., two first analysis results and second analysis results, the two first analysis results and second analysis results are compared respectively, if the two first analysis results and second analysis results are not the same, the prompt information can be determined according to the first transient recording data set and the second transient recording data set; if the two first analysis results and second analysis results are the same, the process can be directly ended.

[0061] For example, after the multi-dimensional analysis matrix is sequentially transmitted into the trained CNN neural network to realize the result determination of the two sets of sampling data, if the determination results of the two sets of data are consistent for two times in succession, the comparison is ended, otherwise, the comparison is performed in order to realize the purpose of determining the prompt information.

[0062] As an optional embodiment, in response to the first comparison result representing that the first analysis result and the second analysis result are not the same, the prompt information is determined based on the first transient recording data set and the second transient recording data set, including: in response to the first comparison result representing that the first analysis result and the second analysis result are not the same, the first transient recording data set and the second transient recording data set are respectively aligned to obtain an alignment result, wherein the alignment result is used to adjust the first sampling frequency of the first transient recording data set and the second sampling frequency of the second transient recording data set to be the same; based on the alignment result, the first transient recording data set, the second transient recording data set and a target abnormal threshold of the power system, a second comparison result is determined, wherein the second comparison result is used to represent that the power system has a potential fault risk; based on the second comparison result, the first transient recording data set and the second transient recording data set, the prompt information is determined.

[0063] In this embodiment, if the first comparison result represents that the first analysis result and the second analysis result are not the same, the first transient recording data set and the second transient recording data set can be respectively aligned to obtain an alignment result, and then based on the obtained alignment result, the first transient recording data set, the second transient recording data set and a target abnormal threshold of the power system, a second comparison result is determined, and finally the second comparison result, the first transient recording data set and the second transient recording data set are used to determine the prompt information.

[0064] Optionally, the target abnormal threshold can include a voltage amplitude abnormal threshold, a current amplitude abnormal threshold and a time difference abnormal threshold, wherein the target abnormal threshold can be a preset abnormal threshold.

[0065] Optionally, the alignment processing is used to ensure the consistency of the two sets of transient recording data in the time axis in the dual protection system. For example, the transient recording data of the two sets of protection devices are aligned, and the sampling frequencies of the transient recording data of the two sets of protection devices are processed to be consistent through the way of point extraction or interpolation. It should be noted that the alignment of the recording data of the two sets of protection devices refers to the alignment of the first positive peak or negative peak in S1 and S2, and the time interval is not more than half a cycle.

[0066] As an optional embodiment, the second comparison result includes: a voltage amplitude comparison result, a current amplitude comparison result and a time difference comparison result. Based on the second comparison result, the first transient recording data set and the second transient recording data set, the prompt information is determined, including: obtaining the first voltage amplitude, the first current amplitude and the first time difference corresponding to the target recording sampling point in the first transient recording data set, and obtaining the second voltage amplitude, the second current amplitude and the second time difference corresponding to the target recording sampling point in the second transient recording data set; based on the first voltage amplitude, the second voltage amplitude and the voltage amplitude abnormal threshold in the target abnormal threshold, the voltage amplitude comparison result is determined, wherein the voltage amplitude comparison result is used to represent the voltage abnormality of the power system; based on the first current amplitude, the second current amplitude and the current amplitude abnormal threshold in the target abnormal threshold, the current amplitude comparison result is determined, wherein the current amplitude comparison result is used to represent the current abnormality of the power system; based on the first time difference, the second time difference and the time difference abnormal threshold in the target abnormal threshold, the time difference comparison result is determined, wherein the time difference comparison result is used to represent the abnormality of the power equipment in the power system; based on the voltage amplitude comparison result, the current amplitude comparison result and the time difference comparison result, the prompt information is determined.

[0067] In this embodiment, the first voltage amplitude, the first current amplitude and the first time difference corresponding to the target recording sampling point in the first transient recording data set are obtained, and the second voltage amplitude, the second current amplitude and the second time difference corresponding to the target recording sampling point in the second transient recording data set are obtained, and then the voltage amplitude comparison result is determined according to the first voltage amplitude, the second voltage amplitude and the voltage amplitude abnormal threshold in the target abnormal threshold; the current amplitude comparison result is determined according to the first current amplitude, the second current amplitude and the current amplitude abnormal threshold in the target abnormal threshold; the time difference comparison result is determined according to the first time difference, the second time difference and the time difference abnormal threshold in the target abnormal threshold, and finally the prompt information is determined according to the voltage amplitude comparison result, the current amplitude comparison result and the time difference comparison result.

[0068] Optionally, the first voltage amplitude can be represented by The first current amplitude can be represented by is represented. The first time difference value can be referred to as the first time difference, which can be determined by is represented. The second voltage amplitude value can be determined by is represented. The second current amplitude value can be determined by is represented. The second time difference value can be referred to as the second time difference, which can be determined by is represented. The voltage amplitude abnormal threshold value can be determined by a voltage amplitude abnormal threshold value coefficient and a voltage rated value, wherein the voltage amplitude abnormal threshold value coefficient can be determined by U is represented. The voltage rated value can be determined by n is represented. The current amplitude abnormal threshold value can be determined by a current amplitude abnormal threshold value coefficient and a current rated value, wherein the current amplitude abnormal threshold value coefficient can be determined by I is represented. The current rated value can be determined by n is represented. The time difference abnormal threshold value can be determined by a time difference abnormal threshold value coefficient, wherein the time difference abnormal threshold value coefficient can be determined by T is represented.

[0069] Optionally, based on the first voltage amplitude, the second voltage amplitude, and the voltage amplitude abnormal threshold value in the target abnormal threshold value, the voltage amplitude comparison result is determined, including: performing subtraction operation on the first voltage amplitude and the second voltage amplitude to obtain a first difference value; obtaining a first voltage amplitude absolute value of the first voltage amplitude, and obtaining a second voltage amplitude absolute value of the second voltage amplitude; determining a target voltage amplitude based on the first voltage amplitude absolute value and the second voltage amplitude absolute value; determining a voltage ratio value as a ratio of the first difference value and the target voltage amplitude, and obtaining a voltage ratio absolute value of the voltage ratio value; in response to the voltage ratio absolute value being greater than the voltage amplitude abnormal threshold value, determining the voltage amplitude comparison result. Wherein, the target voltage amplitude is a maximum value between the first voltage amplitude absolute value and the second voltage amplitude absolute value.

[0070] Optionally, based on the first current amplitude, the second current amplitude, and the current amplitude abnormal threshold value in the target abnormal threshold value, the current amplitude comparison result is determined, including: performing subtraction operation on the first current amplitude and the second current amplitude to obtain a second difference value; obtaining a first current amplitude absolute value of the first current amplitude, and obtaining a second current amplitude absolute value of the second current amplitude; determining a target current amplitude based on the first current amplitude absolute value and the second current amplitude absolute value; determining a current ratio value as a ratio of the second difference value and the target current amplitude, and obtaining a current ratio absolute value of the current ratio value; in response to the current ratio absolute value being greater than the current amplitude abnormal threshold value, determining the current amplitude comparison result. Wherein, the target current amplitude is a maximum value between the first current amplitude absolute value and the second current amplitude absolute value.

[0071] Optionally, based on the first time difference value, the second time difference value and the time difference value abnormal threshold in the target abnormal threshold, the time difference value comparison result is determined, including: performing subtraction operation on the first time difference value and the second time difference value to obtain a third difference value; based on the first time difference value and the second time difference value, a target time difference value is determined; a ratio of the third difference value to the target time difference value is determined as a time ratio, and a time ratio absolute value of the time ratio is obtained; in response to the time ratio absolute value being greater than the time difference value abnormal threshold, the time difference value comparison result is determined. The target time difference value is the maximum value between the first time difference value and the second time difference value.

[0072] For example, after the sampling frequencies of the recording wave data from the two sets of protection devices are processed to be consistent, the two sets of data processed to be consistent can be subjected to amplitude comparison and time difference value comparison, and if the characteristic value comparison of three consecutive points is abnormal, an abnormal alarm is formed. The manner of comparing the two sets of data processed to be consistent in amplitude and time difference value is as follows:

[0073]

[0074] Among them, respectively represent the corresponding voltage amplitudes in the data sets S1 and S2, δ U represents a voltage amplitude abnormal threshold coefficient, U n represents a voltage rated value, respectively represent the corresponding current amplitudes in the data sets S1 and S2, δ I represents a current amplitude abnormal threshold coefficient, I n represents a current rated value, represents the time difference between the current amplitude and the previous amplitude in the data set S1, represents the time difference between the current amplitude and the previous amplitude in the data set S2, δ T represents a time difference abnormal threshold coefficient.

[0075] As an optional embodiment, based on the voltage amplitude comparison result, the current amplitude comparison result and the time difference value comparison result, the prompt information is determined, including: based on the voltage amplitude comparison result, the current amplitude comparison result and the time difference value comparison result, the analysis result is compared with a preset analysis result of the power system to obtain a third comparison result; in response to the third comparison result representing that the analysis result is different from the preset analysis result, the prompt information is determined.

[0076] In this embodiment, after obtaining the voltage amplitude comparison result, the current amplitude comparison result and the time difference comparison result, the analysis result can be compared with a preset analysis result of the power system according to the voltage amplitude comparison result, the current amplitude comparison result and the time difference comparison result, so as to obtain a third comparison result, and if the third comparison result indicates that the analysis result is different from the preset analysis result, the prompt information can be determined, wherein the analysis result can be referred to as a judgment result, and the preset analysis result can be referred to as a true result. For example, the judgment result can be compared with the true result in the field, and if the judgment result is inconsistent with the true result, it indicates that the sampling loop has hidden faults.

[0077] As an optional embodiment, the working state of the power system at least includes: a normal working state, a short-circuit fault state, an oscillation state, and a frequency abnormal state, wherein the oscillation state is used to represent that the power system is in a disturbance state, and the frequency abnormal state is used to represent that the power system is in a power imbalance state.

[0078] In this embodiment, the working state of the power system at least includes: a normal working state, a short-circuit fault state, an oscillation state, and a frequency abnormal state, wherein the oscillation state can be referred to as a system oscillation state, the frequency abnormal state can be referred to as a frequency collapse state, and the normal working state can be referred to as a normal state.

[0079] For example, the judgment result of the power system can include: a normal state, a short-circuit fault state, a system oscillation state, a frequency collapse state, and other fault states, and it should be noted that the fault types of the power system are only exemplified herein, and are not specifically limited.

[0080] In this embodiment, the first transient recording wave data set is collected from the first protection device of the power system by the first transient recording wave device of the power system, and the second transient recording wave data set is collected from the second protection device of the power system by the second transient recording wave device of the power system, and the first transient recording wave data set and the second transient recording wave data set are respectively input into the multi-dimensional analysis model for analysis to achieve the purpose of obtaining the analysis result of the power system, and then according to the above obtained analysis result, the first transient recording wave data set and the second transient recording wave data set, the prompt information of the power system can be determined. Since the first transient recording wave data set and the second transient recording wave data set are collected from different protection devices by different transient recording wave devices, the first transient recording wave data set and the second transient recording wave data set obtained above are input into the multi-dimensional analysis model for analysis to obtain the analysis result, and according to the analysis result at this time, the first transient recording wave data set and the second transient recording wave data set, the prompt information of the power system can be determined, so that when the power system has a potential fault risk, the relevant staff can be prompted in time to solve the technical problem of low fault handling efficiency of the power system, and the technical effect of improving the fault handling efficiency of the power system is realized.

[0081] The technical solutions of the embodiments of the application will be illustrated below in combination with preferred embodiments.

[0082] In the power system, the relay protection device plays a crucial role, which is the key equipment to ensure the stable operation of the entire power grid. In order to further improve the reliability of the relay protection, for those important lines and equipment, the double principle is usually used for configuration, that is, two sets of independent protection devices are set. This configuration method can significantly improve the safety and reliability of the system, and ensure that another set of protection devices can take over the protection task in time when one set of protection devices fails, avoiding large-scale power failure accidents. However, in the actual operation process of the system, due to the implementation of the double protection strategy, there may be a situation that the sampling sources are not synchronized, which brings difficulties to the subsequent data comparison and fault judgment, thereby causing the technical problem of low fault handling efficiency of the power system.

[0083] Therefore, in order to solve the above problems, the application provides a prompt method based on transient recording data, which comprises the following steps: collecting a first transient recording data set from a first protection device of a power system through a first transient recording device of the power system, collecting a second transient recording data set from a second protection device of the power system through a second transient recording device of the power system, inputting the first transient recording data set and the second transient recording data set into a multi-dimensional analysis model for analysis, and obtaining an analysis result of the power system, and determining prompt information of the power system according to the analysis result, the first transient recording data set and the second transient recording data set. Since the first transient recording data set and the second transient recording data set are collected from different protection devices through different transient recording devices, the first transient recording data set and the second transient recording data set are input into the multi-dimensional analysis model for analysis to obtain the analysis result, and the prompt information of the power system can be determined according to the analysis result, the first transient recording data set and the second transient recording data set, so that when the power system has a potential fault risk, the relevant staff can be prompted in time to solve the technical problem of low fault processing efficiency of the power system, and the technical effect of improving the fault processing efficiency of the power system is achieved.

[0084] In the embodiment of the application, a dual transient recording data fast comparison and alarm method is provided. The method can compare the transient recording data of dual protection through synchronous sampling, and realize fast consistency check by using advanced algorithms. When inconsistent data is detected, an alarm signal can be automatically triggered to timely notify the operation and maintenance personnel. The method can not only effectively solve the problem of asynchronous sampling source between dual protection, but also improve the accuracy of transient recording data comparison, thereby enhancing the reliability and fault processing efficiency of the power system.

[0085] Figure 2 A flow chart of a dual transient recording data fast comparison and alarm method according to the embodiment of the application is shown in FIG. 1. Figure 2 The method comprises the following steps:

[0086] In step S201, the transient recording data sets of two sets of protection devices within 6 cycles are collected.

[0087] In this embodiment, the transient recording data of two sets of protection devices within 6 cycles are collected by the transient recording devices installed on the devices, and the sampling data of the two sets of protection devices are defined as sampling data S1 and S2. S1 and S2 both include voltage, current and other recording data.

[0088] In step S202, two multi-dimensional analysis matrices are constructed.

[0089] In this embodiment, after obtaining the sampling data collected from different transient recorders, the various types of data of the sampling data S1 and S2 need to be normalized, and multi-dimensional analysis matrices S1' and S2' are constructed respectively.

[0090] Optionally, the multi-dimensional analysis matrix mentioned above takes each type of data as a one-dimensional matrix, the rows of the matrix represent each cycle, and the columns of the matrix represent each sampling point, as shown in Table 1 and Table 2, which will not be repeated here.

[0091] Optionally, the normalization mentioned above means that each type of data is normalized separately, as shown in the following formula:

[0092]

[0093] wherein, X i represents the i-th sampling data in each type of data, minX represents the minimum sampling data value in each type of data, and maxX represents the maximum sampling data value in each type of data.

[0094] Step S203: inputting the two multi-dimensional analysis matrices into the neural network to obtain a determination result.

[0095] In this embodiment, the multi-dimensional analysis matrices obtained in the above steps are sequentially input into the trained neural network CNN, so as to determine the results of the two sets of sampling data respectively, and thus the determination result can be obtained.

[0096] Optionally, the determination result of the power system can include: a normal state, a short-circuit fault state, a system oscillation state, a frequency collapse state, and other fault states.

[0097] Step S204: determining whether the determination result appears twice continuously and is consistent.

[0098] In this embodiment, according to the two determination results obtained in the above steps, if the two determination results are the same, the process ends directly, and if the two determination results are different, step S205 is performed.

[0099] Optionally, if the determination results of the two sets of data appear twice continuously and are consistent, the comparison ends, otherwise the comparison is performed.

[0100] Step S205: performing alignment processing on the two sets of transient record data sets, so that the sampling frequencies of the two sets of transient record data sets are consistent.

[0101] In this embodiment, the transient recording wave data of the two sets of protection devices are aligned, and the sampling frequencies of the transient recording wave data of the two sets of protection devices are processed to be consistent by means of point extraction or interpolation. It should be noted that the alignment of the recording wave data of the two sets of protection devices refers to the alignment of the first positive peak or negative peak in S1 and S2, and the time interval is not more than half a cycle. That is, as shown in FIG. 3(a) and FIG. 3(b), FIG. 3(a) is a schematic diagram of two sets of transient recording wave data before alignment according to an embodiment of the present application, and FIG. 3(b) is a schematic diagram of two sets of transient recording wave data after alignment according to an embodiment of the present application.

[0102] Optionally, Figure 4 FIG. 4 is a schematic diagram of another alignment processing of transient recording wave data according to an embodiment of the present application, as shown in the figure, if the time difference between point a and point d is within half a cycle, then a and d are aligned, otherwise, whether the time difference between point b and point c is within half a cycle can be compared, if it is within half a cycle, then b and c are aligned, and so on, the positive peak or negative peak with a time interval of not more than half a cycle in the two sets of transient recording wave data are aligned. Figure 4

[0103] Step S206, amplitude comparison and time difference comparison of the two sets of transient recording wave data.

[0104] In this embodiment, the two sets of data processed consistently need to be compared in amplitude and time difference, and if the characteristic values of three consecutive points are compared abnormally, an abnormal alarm is formed. The way of comparing the two sets of data processed consistently in amplitude and time difference is as follows:

[0105]

[0106] Among them, respectively represent the corresponding voltage amplitudes in data sets S1 and S2, δ U represents the voltage amplitude abnormal threshold coefficient, U n represents the voltage rated value, respectively represent the corresponding current amplitudes in data sets S1 and S2, δ I represents the current amplitude abnormal threshold coefficient, I n represents the current rated value, represents the time difference between the current amplitude and the previous amplitude in data set S1, represents the time difference between the current amplitude and the previous amplitude in data set S2, δ T represents the time difference abnormal threshold coefficient.

[0107] Step S207, judging whether the two sets of transient recording wave data of three consecutive points have abnormal characteristic values. ​

[0108] In this embodiment, it is needed to judge whether two sets of transient recording data sets of three continuous point feature values exist abnormality, if the abnormality exists, step S208 is executed, if the abnormality does not exist, it is directly ended.

[0109] Step S208, it is determined that the sampling circuit exists fault hidden danger.

[0110] In this embodiment, the determination result can be compared with the real result on site, if the determination result is inconsistent with the real result, the sampling circuit exists fault hidden danger.

[0111] In this embodiment, through the first transient recording equipment of the power system, the first transient recording data set is collected from the first protection device of the power system, and through the second transient recording equipment of the power system, the second transient recording data set is collected from the second protection device of the power system, the first transient recording data set and the second transient recording data set are respectively input into the multi-dimensional analysis model for analysis, so as to achieve the purpose of obtaining the analysis result of the power system, and then according to the above obtained analysis result, the first transient recording data set and the second transient recording data set, the prompt information of the power system can be determined. Since the first transient recording data set and the second transient recording data set are collected from different protection devices through different transient recording equipment, the first transient recording data set and the second transient recording data set obtained above are input into the multi-dimensional analysis model for analysis to obtain the analysis result, according to the analysis result at this time, the first transient recording data set and the second transient recording data set, the prompt information of the power system can be determined, so that when the power system exists potential fault risk, the relevant staff can be prompted in time, so as to solve the technical problem of low fault handling efficiency of the power system, and realize the technical effect of improving the fault handling efficiency of the power system.

[0112] According to the embodiment of the application, a prompt device based on transient recording data is provided. It should be noted that the prompt device based on transient recording data can be used to execute the prompt method based on transient recording data in the embodiment.

[0113] Figure 5 is a schematic diagram of a prompt device based on transient recording data according to an embodiment of the application. As shown in Figure 5 the prompt device based on transient recording data 500 can include an acquisition unit 501, an analysis unit 502 and a determination unit 503.

[0114] The acquisition unit 501 is configured to acquire a first transient recording wave data set of the power system and a second transient recording wave data set of the power system, wherein the first transient recording wave data set is used to represent data collected from a first protection device of the power system by a first transient recording wave device of the power system, and the second transient recording wave data set is used to represent data collected from a second protection device of the power system by a second transient recording wave device of the power system.

[0115] The analysis unit 502 is configured to input the first transient recording wave data set and the second transient recording wave data set into a multi-dimensional analysis model of the power system respectively for analysis, to obtain an analysis result of the power system, wherein the multi-dimensional analysis model is trained by a first historical transient recording wave data set of the power system and a second historical transient recording wave data set of the power system, the first historical transient recording wave data set is a historical data set corresponding to the first transient recording wave data set, the second historical transient recording wave data set is a historical data set corresponding to the second transient recording wave data set, and the analysis result is used to represent a working state of the power system.

[0116] The determination unit 503 is configured to determine prompt information of the power system based on the analysis result, the first transient recording wave data set and the second transient recording wave data set, wherein the prompt information is used to prompt that there is a potential fault risk in the power system.

[0117] Optionally, the analysis unit 502 includes: a first acquisition module configured to perform normalization processing on data in the first transient recording wave data set respectively to obtain a first transient recording wave data set after normalization processing, and perform normalization processing on data in the second transient recording wave data set respectively to obtain a second transient recording wave data set after normalization processing; a construction module configured to construct a first multi-dimensional analysis matrix based on the first transient recording wave data set after normalization processing, and construct a second multi-dimensional analysis matrix based on the second transient recording wave data set after normalization processing; and a second acquisition module configured to input the first multi-dimensional analysis matrix and the second multi-dimensional analysis matrix into the multi-dimensional analysis model respectively for analysis to obtain the analysis result.

[0118] Optionally, the analysis result includes a first analysis result and a second analysis result, wherein the first analysis result is an analysis result of the multi-dimensional analysis model on the first transient recording wave data, and the second analysis result is an analysis result of the multi-dimensional analysis model on the second transient recording wave data, and the determination unit 503 can include: a comparison module configured to compare the first analysis result and the second analysis result to obtain a first comparison result, wherein the first comparison result is used to represent whether the first analysis result and the second analysis result are the same; and a determination module configured to, in response to the first comparison result representing that the first analysis result and the second analysis result are not the same, determine the prompt information based on the first transient recording wave data set and the second transient recording wave data set.

[0119] Optionally, the determining module can comprise: an obtaining submodule, configured to, in response to the first comparison result representing that the first analysis result and the second analysis result are different, perform alignment processing on the first transient recording wave data set and the second transient recording wave data set respectively to obtain an alignment processing result, wherein the alignment processing result is used to adjust the first sampling frequency of the first transient recording wave data set and the second sampling frequency of the second transient recording wave data set to be the same; a first determining submodule, configured to determine a second comparison result based on the alignment processing result, the first transient recording wave data set, the second transient recording wave data set and a target abnormal threshold of the power system, wherein the second comparison result is used to represent that there is a potential fault risk in the power system; and a second determining submodule, configured to determine the prompt information based on the second comparison result, the first transient recording wave data set and the second transient recording wave data set.

[0120] Optionally, the second comparison result comprises a voltage amplitude comparison result, a current amplitude comparison result and a time difference value comparison result, and the second determining submodule is further configured to: obtain a first voltage amplitude, a first current amplitude and a first time difference value corresponding to a target recording wave sampling point in the first transient recording wave data set, and obtain a second voltage amplitude, a second current amplitude and a second time difference value corresponding to the target recording wave sampling point in the second transient recording wave data set; determine the voltage amplitude comparison result based on the first voltage amplitude, the second voltage amplitude and a voltage amplitude abnormal threshold in the target abnormal threshold, wherein the voltage amplitude comparison result is used to represent that there is a voltage abnormality in the power system; determine the current amplitude comparison result based on the first current amplitude, the second current amplitude and a current amplitude abnormal threshold in the target abnormal threshold, wherein the current amplitude comparison result is used to represent that there is a current abnormality in the power system; and determine the time difference value comparison result based on the first time difference value, the second time difference value and a time difference value abnormal threshold in the target abnormal threshold, wherein the time difference value comparison result is used to represent that there is an abnormality in a power device in the power system; and determine the prompt information based on the voltage amplitude comparison result, the current amplitude comparison result and the time difference value comparison result.

[0121] Optionally, the second determining submodule is further configured to: compare the analysis result with a preset analysis result of the power system based on the voltage amplitude comparison result, the current amplitude comparison result and the time difference value comparison result to obtain a third comparison result; and in response to the third comparison result representing that the analysis result and the preset analysis result are different, determine the prompt information.

[0122] Optionally, the working state of the power system at least comprises a normal working state, a short-circuit fault state, an oscillation state and a frequency abnormality state, wherein the oscillation state is used to represent that the power system is in a disturbance condition, and the frequency abnormality state is used to represent that the power system is in a power imbalance condition.

[0123] In this embodiment, a first transient recording data set of the power system and a second transient recording data set of the power system are acquired by an acquisition unit, wherein the first transient recording data set is used to represent data collected from a first protection device of the power system by a first transient recording device of the power system, and the second transient recording data set is used to represent data collected from a second protection device of the power system by a second transient recording device of the power system; the first transient recording data set and the second transient recording data set are respectively input into a multidimensional analysis model of the power system by an analysis unit for analysis, to obtain an analysis result of the power system, wherein the multidimensional analysis model is trained by a first historical transient recording data set of the power system and a second historical transient recording data set of the power system, the first historical transient recording data set is a historical data set corresponding to the first transient recording data set, the second historical transient recording data set is a historical data set corresponding to the second transient recording data set, and the analysis result is used to represent a working state of the power system; and a determination unit determines prompt information of the power system based on the analysis result, the first transient recording data set and the second transient recording data set, wherein the prompt information is used to prompt that there is a potential fault risk in the power system, thereby solving the technical problem of low fault processing efficiency of the power system, and achieving the technical effect of improving the fault processing efficiency of the power system.

[0124] According to the embodiments of the present application, a computer readable storage medium is also provided, which includes a stored program, wherein when the program is executed by a processor, the device where the storage medium is located performs the prompt method based on transient recording data in the embodiments.

[0125] According to the embodiments of the present application, an electronic device is also provided, which includes one or more processors and a memory, and the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the prompt method based on transient recording data in the embodiments.

[0126] According to the embodiments of the present application, a computer program product is also provided, which includes a computer program, and when the computer program is executed by a processor, the prompt method based on transient recording data in the embodiments of the present application is implemented.

[0127] The above-mentioned serial numbers of the embodiments of the present application only serve for description, and do not represent the advantages and disadvantages of the embodiments.

[0128] In the above-mentioned embodiments of the present application, the description of each embodiment has its own emphasis, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0129] In several embodiments provided by the present application, it should be understood that the disclosed technology can be implemented in other ways. Among them, the above-mentioned device embodiments are only illustrative, for example, the division of units can be a logical function division, and actual implementation can have another division mode, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection between units or modules through some interfaces, and can be electrical or other forms.

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

[0131] In addition, the functional units in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0132] If the integrated unit is realized in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the embodiments of the present application. The aforementioned storage medium includes: a U disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a mobile hard disk, a magnetic disk or an optical disk, and various media that can store program codes.

[0133] The above is only the preferred embodiment of the present application. It should be pointed out that for ordinary skilled in the art, without departing from the principles of the present application, a number of improvements and refinements can be made, and these improvements and refinements should be considered as the protection scope of the present application.

Claims

1. A prompting method based on transient recording data, characterized in that, The method comprises the following steps: acquiring a first transient recording data set of a power system and a second transient recording data set of the power system, wherein the first transient recording data set is used to represent data collected from a first protection device of the power system by a first transient recording device of the power system, and the second transient recording data set is used to represent data collected from a second protection device of the power system by a second transient recording device of the power system; inputting the first transient recording data set and the second transient recording data set into a multi-dimensional analysis model of the power system for analysis to obtain an analysis result of the power system, wherein the multi-dimensional analysis model is trained by a first historical transient recording data set of the power system and a second historical transient recording data set of the power system, the first historical transient recording data set is a historical data set corresponding to the first transient recording data set, the second historical transient recording data set is a historical data set corresponding to the second transient recording data set, and the analysis result is used to represent a working state of the power system; determining prompt information of the power system based on the analysis result, the first transient recording data set and the second transient recording data set, wherein the prompt information is used to prompt that the power system has a potential fault risk.

2. The method of claim 1, wherein, The method of inputting the first transient recording data set and the second transient recording data set into the multi-dimensional analysis model for analysis to obtain the analysis result of the power system comprises the following steps: respectively performing normalization processing on data in the first transient recording data set to obtain the first transient recording data set after normalization processing, and respectively performing normalization processing on data in the second transient recording data set to obtain the second transient recording data set after normalization processing; constructing a first multi-dimensional analysis matrix based on the first transient recording data set after normalization processing, and constructing a second multi-dimensional analysis matrix based on the second transient recording data set after normalization processing; respectively inputting the first multi-dimensional analysis matrix and the second multi-dimensional analysis matrix into the multi-dimensional analysis model for analysis to obtain the analysis result.

3. The method of claim 1, wherein, The analysis result comprises a first analysis result and a second analysis result, wherein the first analysis result is an analysis result of the multi-dimensional analysis model on the first transient recording data, the second analysis result is an analysis result of the multi-dimensional analysis model on the second transient recording data, and the prompt information of the power system is determined based on the analysis result, the first transient recording data set and the second transient recording data set, which comprises the following steps: comparing the first analysis result and the second analysis result to obtain a first comparison result, wherein the first comparison result is used to represent whether the first analysis result and the second analysis result are the same; in response to the first comparison result representing that the first analysis result and the second analysis result are not the same, determining the prompt information based on the first transient recording data set and the second transient recording data set.

4. The method of claim 3, wherein, In response to the first comparison result representing that the first analysis result and the second analysis result are different, the prompt information is determined based on the first transient recorded wave data set and the second transient recorded wave data set, including: In response to the first comparison result representing that the first analysis result and the second analysis result are different, the first transient recorded wave data set and the second transient recorded wave data set are respectively subjected to alignment processing to obtain an alignment processing result, wherein the alignment processing result is used to adjust the first sampling frequency of the first transient recorded wave data set and the second sampling frequency of the second transient recorded wave data set to be the same; Based on the alignment processing result, the first transient recorded wave data set, the second transient recorded wave data set and a target abnormal threshold of the power system, a second comparison result is determined, wherein the second comparison result is used to represent that the power system has a potential fault risk; Based on the second comparison result, the first transient recorded wave data set and the second transient recorded wave data set, the prompt information is determined.

5. The method of claim 4, wherein, The second comparison result includes a voltage amplitude comparison result, a current amplitude comparison result and a time difference value comparison result, based on the second comparison result, the first transient recorded wave data set and the second transient recorded wave data set, the prompt information is determined, including: First voltage amplitude, first current amplitude and first time difference value corresponding to a target recorded wave sampling point in the first transient recorded wave data set are obtained, and second voltage amplitude, second current amplitude and second time difference value corresponding to the target recorded wave sampling point in the second transient recorded wave data set are obtained; Based on the first voltage amplitude, the second voltage amplitude and a voltage amplitude abnormal threshold in the target abnormal threshold, the voltage amplitude comparison result is determined, wherein the voltage amplitude comparison result is used to represent that the power system has a voltage abnormality; Based on the first current amplitude, the second current amplitude and a current amplitude abnormal threshold in the target abnormal threshold, the current amplitude comparison result is determined, wherein the current amplitude comparison result is used to represent that the power system has a current abnormality; Based on the first time difference value, the second time difference value and a time difference value abnormal threshold in the target abnormal threshold, the time difference value comparison result is determined, wherein the time difference value comparison result is used to represent that a power equipment in the power system has an abnormality; Based on the voltage amplitude comparison result, the current amplitude comparison result and the time difference value comparison result, the prompt information is determined.

6. The method of claim 5, wherein, Based on the voltage amplitude comparison result, the current amplitude comparison result and the time difference value comparison result, the prompt information is determined, including: Based on the voltage amplitude comparison result, the current amplitude comparison result and the time difference value comparison result, the analysis result is compared with a preset analysis result of the power system to obtain a third comparison result; In response to the third comparison result representing that the analysis result and the preset analysis result are different, the prompt information is determined.

7. The method of claim 1, wherein, The working state of the power system at least includes: a normal working state, a short-circuit fault state, an oscillation state, and a frequency abnormal state, wherein the oscillation state is used to represent a disturbance condition of the power system, and the frequency abnormal state is used to represent a power imbalance condition of the power system.

8. A prompting device based on transient recording data, characterized in that, Comprise: An acquisition unit is configured to acquire a first transient recording data set of a power system and a second transient recording data set of the power system, wherein the first transient recording data set is used to represent data collected from a first protection device of the power system by a first transient recording device of the power system, and the second transient recording data set is used to represent data collected from a second protection device of the power system by a second transient recording device of the power system; An analysis unit is configured to input the first transient recording data set and the second transient recording data set into a multi-dimensional analysis model of the power system for analysis, respectively, to obtain an analysis result of the power system, wherein the multi-dimensional analysis model is trained by a first historical transient recording data set of the power system and a second historical transient recording data set of the power system, the first historical transient recording data set is a historical data set corresponding to the first transient recording data set, the second historical transient recording data set is a historical data set corresponding to the second transient recording data set, and the analysis result is used to represent a working state of the power system; A determination unit is configured to determine prompt information of the power system based on the analysis result, the first transient recording data set and the second transient recording data set, wherein the prompt information is used to prompt a potential fault risk of the power system.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium comprises a stored program, wherein when the program is run by a processor, it controls the device where the storage medium is located to execute the method of any one of claims 1-7.

10. An electronic device, comprising: Comprise one or more processors and a memory, the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method of any one of claims 1-7.

Images