Substation transient electromagnetic disturbance micro-pulse waveform automatic analysis method and system

Abstract

The invention discloses a transformer substation transient electromagnetic disturbance micro-pulse waveform automatic analysis method and system, and the method comprises the steps: collecting transformer substation transient electromagnetic waveform data, extracting waveform data features, carrying out the analysis of the features to obtain a port type and a background noise amplitude, and obtaining a first amplitude threshold; searching a global maximum value of the sequence, taking the global maximum value as a maximum micro-pulse peak point, extracting the position of the maximum micro-pulse peak point and a waveform data sequence of adjacent symmetrical points with a distance threshold value according to a predetermined distance threshold value, and extracting the waveform data sequence into a two-dimensional array as one micro-pulse; zero setting is carried out on the extracted waveform data sequence in the original sequence, and the steps of extraction and zero setting are repeated until all micropulses with amplitudes larger than a first amplitude threshold value are found out; and analyzing the micro-pulse sequence to obtain a micro-pulse waveform parameter corresponding to the waveform data. According to the invention, the collected transient electromagnetic disturbance waveform data of the transformer substation can be automatically analyzed to obtain the waveform parameters of the micro-pulse sequence.

Description

Technical Field

[0001] The present invention relates to the technical field of micro-pulse waveform analysis, and in particular to an automatic analysis method and system for transient electromagnetic disturbance micro-pulse waveforms of a substation. Background Art

[0002] Damped oscillation is usually used to equate the electromagnetic interference on the ports of substation secondary equipment caused by switch operation, and it is used to evaluate the electromagnetic compatibility immunity of secondary equipment during electromagnetic compatibility testing. In the IEC61000-4-18 damped oscillation wave immunity test standard, the waveform parameters of the damped oscillation wave of secondary equipment caused by GIS switches are clearly defined, and the immunity requirements and test methods for secondary equipment are given. The standard only lists the test level of common-mode voltage, assuming that the differential-mode voltage is half of the common-mode voltage, that is, level 1: 0.25kV; level 2: 0.5kV; level 3: 1kV; level 4: 2kV. In the above definition, repetition rate = number of micropulses / macropulse duration: according to Pk 10 Attenuation to less than 50% of the Pk1 value, assuming that Pk 20 When it decays to 0, 10 oscillation cycles are considered to be the duration of the oscillation wave.

[0003] The existing technology mainly counts the peak voltage and main frequency characteristics, and has a general understanding of the port disturbance level and frequency range under the UHV level. In practical applications, the specific characteristics of the disturbance waveform need to be further analyzed and studied. Therefore, an automatic analysis method for the disturbance micro-pulse waveform is urgently needed. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a method and system for automatic analysis of substation transient electromagnetic disturbance micro-pulse waveforms, the purpose of which is to automatically analyze the collected substation transient electromagnetic disturbance waveform data, generate corresponding amplitude thresholds, combine the generated amplitude thresholds, use global search to generate micro-pulse sequences, and automatically analyze the micro-pulse sequences to obtain corresponding waveform parameters.

[0006] In order to achieve the above technical objectives, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides a method for automatically analyzing the micropulse waveform of transient electromagnetic disturbance in a substation, comprising: collecting transient electromagnetic waveform data of the substation and extracting waveform data features, analyzing the waveform data features to obtain the port type and background noise amplitude, and obtaining a first amplitude threshold; searching for a global maximum value of a sequence, taking the global maximum value of the sequence as the maximum micropulse peak point, extracting a waveform data sequence of the position of the maximum micropulse peak point and nearby symmetrical distance threshold points according to a predetermined distance threshold, and extracting the waveform data sequence as one of the micropulses into a two-dimensional array; setting the extracted waveform data sequence to zero in the original sequence, and repeating the extraction and zeroing steps until all micropulses with amplitudes greater than the first amplitude threshold are found; analyzing the micropulse sequence in the two-dimensional array to obtain micropulse waveform parameters corresponding to the transient electromagnetic waveform data of the substation.

[0008] As a preferred solution of the method for automatically analyzing transient electromagnetic disturbance micro-pulse waveforms in substations according to the present invention, the acquisition of the port type and the background noise amplitude includes:

[0009] A waveform recognition model is constructed based on a convolutional neural network, and historical substation transient electromagnetic waveform data is collected. The port type and background noise amplitude are marked for each substation transient electromagnetic waveform data, sample data is generated, and the waveform recognition model is trained using the sample data;

[0010] Importing the substation transient electromagnetic waveform data collected in real time into the trained waveform recognition model, extracting waveform data features, and analyzing the waveform data features to obtain the port type and background noise amplitude;

[0011] A first amplitude threshold is set according to the port type and the background noise amplitude.

[0012] As a preferred solution of the method for automatically analyzing the transient electromagnetic disturbance micro-pulse waveform of a substation according to the present invention, the acquisition of micro-pulses greater than the first amplitude threshold value includes:

[0013] The duration of the micropulse is at the level of us, the duration of the entire macropulse is at the level of ms, and the interval between two adjacent pulses is much longer than the duration of the micropulse itself. Based on this feature, the global maximum value of the sequence is searched, and the global maximum value of the sequence is taken as the maximum micropulse peak point;

[0014] Extracting the position of the maximum micropulse peak point and the waveform data sequence of the symmetrical distance threshold points nearby according to the predetermined distance threshold, saving the waveform data sequence as a new sequence, i.e., the first peak micropulse, and extracting the first peak micropulse as one of the micropulses into a two-dimensional array;

[0015] After all the values ​​at the position of the first peak micropulse extracted from the original sequence are set to zero, a global search is performed again to find the maximum value, and the waveform data sequence is extracted according to the above steps and saved as a new sequence, i.e., the second peak micropulse, and the second peak micropulse is extracted as one of the micropulses into a two-dimensional array;

[0016] The steps of zeroing and extracting are repeated until all micropulses with amplitudes greater than the first amplitude threshold are found.

[0017] As a preferred solution of the automatic analysis method of substation transient electromagnetic disturbance micropulse waveform described in the present invention, all micropulses with amplitudes greater than the first amplitude threshold are extracted into a two-dimensional array, and each row of the two-dimensional array is one-dimensional micropulse waveform data.

[0018] As a preferred solution of the method for automatically analyzing the transient electromagnetic disturbance micro-pulse waveform of a substation according to the present invention, the acquisition of the micro-pulse waveform parameters includes:

[0019] Performing noise reduction processing on each row of data in the two-dimensional array by wavelet transform to obtain a new two-dimensional array Pulse1, and calculating the change rate of each row of data in the new two-dimensional array Pulse1;

[0020] Compare the change rate of each row of data with a predetermined change rate threshold, record the absolute time when the change rate of each row of data is first greater than the change rate threshold as Pstart, record the absolute time when the change rate of each row of data is last greater than the change rate threshold as Pend, and use the difference between Pstart and Pend as the micropulse duration;

[0021] The time corresponding to the position of the maximum peak micropulse in the two-dimensional array is recorded as Tmax, and then a search is performed from the position corresponding to the maximum peak micropulse toward time zero until the first point with a sign opposite to that of the maximum peak micropulse is found, and the time corresponding to the first point with a sign opposite to that of the maximum peak micropulse is recorded as Tmin, and then the difference between Tmax and Tmin is multiplied by 0.8 to obtain the micropulse rise time.

[0022] As a preferred solution of the method for automatically analyzing transient electromagnetic disturbance micro-pulse waveforms in substations described in the present invention, the acquisition of micro-pulse waveform parameters further includes:

[0023] All negative values ​​in the two-dimensional array are set to zero to obtain a new two-dimensional array PulseP, and points that meet the conditions are searched according to time as zero-crossing points in the waveform, and the positions of the zero-crossing points in the waveform are recorded as Zp. According to the positions of the zero-crossing points in the waveform, the maximum value or minimum value between the zero-crossing points is searched in the original waveform data, and the value of the maximum value or minimum value whose absolute value is greater than the second amplitude threshold is taken as the pulse peak value Pk, and a pulse peak value sequence is generated;

[0024] The pulse peak sequence is sorted according to time to form a positive and negative alternating pulse peak sequence, and the time difference between the peaks Pk1 and Pk3 is taken as the pulse oscillation period. The micropulse attenuation is Pk5 / Pk1, Pk 10 / Pk1.

[0025] As a preferred solution of the automatic analysis method of transient electromagnetic disturbance micro-pulse waveform of substation described in the present invention, wherein: the point that satisfies the conditions according to time is used as the zero-crossing point Zeros in the waveform, wherein the conditions specifically include:

[0026] The searched point itself is equal to zero, and at the same time the point at the previous position is equal to zero, and the point at the next position is greater than zero; or the searched point itself is equal to zero, and at the same time the point at the previous position is greater than zero, and the point at the next position is equal to zero.

[0027] In a second aspect, the present invention provides a substation transient electromagnetic disturbance micro-pulse waveform automatic analysis system, comprising:

[0028] Waveform acquisition module, used to collect transient electromagnetic waveform data of substation;

[0029] A threshold setting module, used to extract the characteristics of the transient electromagnetic waveform data of the substation, analyze the characteristics of the waveform data to obtain the port type and the background noise amplitude, and obtain the first amplitude threshold;

[0030] A global search module is used to search for the global maximum value of the sequence, take the global maximum value of the sequence as the maximum micropulse peak point, extract the position of the maximum micropulse peak point and the waveform data sequence of the symmetrical distance threshold points nearby according to a predetermined distance threshold, and extract them as one of the micropulses into a two-dimensional array;

[0031] a zeroing search unit, configured to zero the extracted waveform data sequence in the original sequence, and repeat the steps of extracting and zeroing until all micropulses with amplitudes greater than the first amplitude threshold are found;

[0032] The parameter analysis module is used to analyze the micro-pulse sequence in the two-dimensional array to obtain the micro-pulse waveform parameters corresponding to the transient electromagnetic waveform data of the substation.

[0033] In a third aspect, the present invention provides a computing device, comprising:

[0034] Memory and processor;

[0035] The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the method are implemented.

[0036] In a fourth aspect, the present invention provides a computer-readable storage medium storing computer-executable instructions, which implement the steps of the method when executed by a processor.

[0037] Compared with the prior art, the beneficial effects of the present invention are as follows: the method and system for automatic analysis of substation transient electromagnetic disturbance micro-pulse waveforms of the present invention can automatically analyze the collected substation transient electromagnetic disturbance waveform data, generate corresponding amplitude thresholds, combine the generated amplitude thresholds, use global search to generate micro-pulse sequences, and automatically analyze the micro-pulse sequences to obtain corresponding waveform parameters. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0039] Figure 1 This is an overall flow chart of a method for automatically analyzing transient electromagnetic disturbance micro-pulse waveforms in a substation according to an embodiment of the present invention;

[0040] Figure 2 This is a structural framework diagram of a substation transient electromagnetic disturbance micro-pulse waveform automatic analysis system according to an embodiment of the present invention;

[0041] Figure 3 The present invention is a schematic diagram of the software interface of the method for automatically analyzing transient electromagnetic disturbance micro-pulse waveforms in a substation according to an embodiment of the present invention. DETAILED DESCRIPTION

[0042] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0043] Example 1

[0044] Reference Figure 1 , Figure 3 As one embodiment of the present invention, a method for automatically analyzing transient electromagnetic disturbance micro-pulse waveforms in a substation is provided, which specifically includes the following steps:

[0045] S100: collecting transient electromagnetic waveform data of the substation and extracting waveform data features, analyzing the waveform data features to obtain port types and background noise amplitudes, and obtaining a first amplitude threshold;

[0046] In the embodiment of the present application, obtaining the port type and the background noise amplitude includes:

[0047] A waveform recognition model is built based on a convolutional neural network. The transient electromagnetic waveform data of historical substations are collected. The port type and background noise amplitude are annotated for each substation transient electromagnetic waveform data. Sample data is generated and used to train the waveform recognition model.

[0048] The substation transient electromagnetic waveform data collected in real time is imported into the trained waveform recognition model to extract the waveform data features, and the waveform data features are analyzed to obtain the port type and background noise amplitude;

[0049] Setting a first amplitude threshold according to the port type and the background noise amplitude;

[0050] It should be noted that the first amplitude threshold is set to a minimum value. A value greater than this level is considered port interference. At the same time, the influence of measurement background noise can also be excluded. The first amplitude threshold should not be too large, and generally it only needs to be significantly greater than the background noise.

[0051] S200: searching for the global maximum value of the sequence, taking the global maximum value of the sequence as the maximum micropulse peak point, extracting the position of the maximum micropulse peak point and the waveform data sequence of the symmetrical distance threshold points nearby according to the predetermined distance threshold, and extracting them as one of the micropulses into a two-dimensional array;

[0052] In the embodiment of the present application, the global maximum value of the sequence is searched, and the global maximum value of the sequence is taken as the maximum micropulse peak point; the position of the maximum micropulse peak point and the waveform data sequence of the symmetrical distance threshold points nearby are extracted according to the predetermined distance threshold, the waveform data sequence is saved as a new sequence, i.e., the first peak micropulse, and the first peak micropulse is extracted as one of the micropulses into the two-dimensional array.

[0053] It should be noted that the port disturbance macro pulse waveform generated by a switch operation contains multiple micro pulse waveforms. First, all eligible micro pulse sequences should be found. The duration of the micro pulse is at the us level, while the duration of the entire macro pulse is at the ms level. The interval between two adjacent pulses is much longer than the duration of the micro pulse itself. This feature is used to search for the global maximum value of the sequence, and the global maximum value of the sequence is used as the maximum micro pulse peak point. With the maximum micro pulse peak point as the center, a value that can contain the entire micro pulse and avoid the next micro pulse can be appropriately selected within a certain range;

[0054] It should be noted that if the duration of micropulses is not taken into account, the time between the first micropulse sequence and the last micropulse sequence can be considered as the macropulse time;

[0055] It should be noted that the distance threshold is set at a distance from the peak point so that the micropulse can be included in the distance threshold range centered on the peak point. Considering that a general micropulse lasts for several microseconds, the distance represented by the distance threshold should be set at about several microseconds.

[0056] S300: setting the extracted waveform data sequence to zero in the original sequence;

[0057] In the embodiment of the present application, all the values ​​at the position of the first peak micropulse extracted from the original sequence are set to zero and then a global search is performed again to find the maximum value.

[0058] S400: Repeat the steps of extracting and zeroing until all micropulses with amplitudes greater than a first amplitude threshold are found;

[0059] In the embodiments of the present application, Figure 1 As shown, after all the values ​​at the position of the first peak micropulse extracted from the original sequence are set to zero, a global search is performed again to find the maximum value, and the waveform data sequence is extracted according to the above steps and saved as a new sequence, namely, the second peak micropulse, and the second peak micropulse is extracted as one of the micropulses into a two-dimensional array;

[0060] Furthermore, the steps of zeroing and extracting are repeated until all micropulses with amplitudes greater than the first amplitude threshold are found, and all micropulses with amplitudes greater than the first amplitude threshold are extracted into a two-dimensional array, wherein each row of the two-dimensional array is one-dimensional micropulse waveform data.

[0061] S500: Analyze the micro-pulse sequence in the two-dimensional array to obtain micro-pulse waveform parameters corresponding to the transient electromagnetic waveform data of the substation;

[0062] In the embodiment of the present application, each row of data in the two-dimensional array is subjected to noise reduction processing by wavelet transform to obtain a new two-dimensional array Pulse1, and the rate of change of each row of data in the new two-dimensional array Pulse1 is calculated;

[0063] In the embodiment of the present application, the change rate of each row of data is compared with a predetermined change rate threshold, the absolute time when the change rate of each row of data is first greater than the change rate threshold is recorded as Pstart, the absolute time when the change rate of each row of data is last greater than the change rate threshold is recorded as Pend, and the difference between Pstart and Pend is taken as the duration of the micropulse;

[0064] It should be noted that the change rate threshold represents the change rate of a certain point, and is calculated according to the following formula for the i-th point:

[0065]

[0066] Where n represents the distance from i, which can be taken as 1 / 4 cycle, and the change rate threshold value can be less than Max / n*10%;

[0067] In the embodiment of the present application, the time corresponding to the position of the maximum peak micropulse in the two-dimensional array is recorded as Tmax, and then a search is performed from the position corresponding to the maximum peak micropulse to time zero until the first point with a different sign from the maximum peak micropulse is found, and the time corresponding to the first point with a different sign from the maximum peak micropulse is recorded as Tmin, and then the difference between Tmax and Tmin is multiplied by 0.8 to obtain the micropulse rise time;

[0068] In the embodiment of the present application, all negative values ​​in the two-dimensional array are set to zero to obtain a new two-dimensional array PulseP, and points that meet the conditions are searched according to time as zero-crossing points in the waveform, and the positions of the zero-crossing points in the waveform are recorded as Zp. According to the positions of the zero-crossing points in the waveform, the maximum or minimum value between the zero-crossing points is searched in the original waveform data, and the value of the maximum or minimum value whose absolute value is greater than the second amplitude threshold is taken as the pulse peak value Pk, and a pulse peak sequence is generated;

[0069] It should be noted that the second amplitude threshold is mainly used to filter out very small peak jitter near the zero crossing point, and can generally be taken as Max*1%;

[0070] The conditions that should be specified include:

[0071] The searched point itself is equal to zero, and at the same time the point at the previous position is equal to zero, and the point at the next position is greater than zero; or the searched point itself is equal to zero, and at the same time the point at the previous position is greater than zero, and the point at the next position is equal to zero;

[0072] In the embodiment of the present application, the pulse peak sequence is sorted according to time to form a positive and negative staggered pulse peak sequence, and the time difference between the peaks Pk1 and Pk3 is used as the pulse oscillation period, then the micropulse attenuation is Pk5 / Pk1, Pk 10 / Pk1.

[0073] It should be noted that Table 1 shows the process parameters of all extracted parameters. Figure 3 The schematic diagram of the software interface of the automatic analysis method of transient electromagnetic disturbance micro-pulse waveform in substation;

[0074] Table 1: Computer extraction process parameter definitions;

[0075]

[0076]

[0077] It can be seen from the above embodiments that the method and system for automatic analysis of substation transient electromagnetic disturbance micropulse waveforms of the present invention can automatically analyze the collected substation transient electromagnetic disturbance waveform data, generate corresponding amplitude thresholds, combine the generated amplitude thresholds, use global search to generate micropulse sequences, and automatically analyze the micropulse sequences to obtain corresponding waveform parameters.

[0078] Example 2

[0079] Reference Figure 2 In this embodiment, a substation transient electromagnetic disturbance micro-pulse waveform automatic analysis system is provided, comprising:

[0080] Waveform acquisition module, used to collect transient electromagnetic waveform data of substation;

[0081] A threshold setting module is used to extract the characteristics of the transient electromagnetic waveform data of the substation, analyze the waveform data characteristics to obtain the port type and the background noise amplitude, and obtain the first amplitude threshold;

[0082] A global search module is used to search for the global maximum value of the sequence, and take the global maximum value of the sequence as the maximum micropulse peak point. According to a predetermined distance threshold, the position of the maximum micropulse peak point and the waveform data sequence of the symmetrical distance threshold points nearby are extracted and extracted as one of the micropulses into a two-dimensional array;

[0083] A zeroing search unit, used to zero the extracted waveform data sequence in the original sequence, and repeat the steps of extracting and zeroing until all micropulses with amplitudes greater than a first amplitude threshold are found;

[0084] The parameter analysis module is used to analyze the micro-pulse sequence in the two-dimensional array to obtain the micro-pulse waveform parameters corresponding to the transient electromagnetic waveform data of the substation.

[0085] Further, the parameter analysis module includes a noise reduction unit, a micropulse duration analysis unit, a micropulse rise time analysis unit, a zero-crossing point search unit, a pulse peak analysis unit, and a pulse oscillation period analysis unit;

[0086] Specifically, the noise reduction unit is used to perform noise reduction processing on each row of data in the two-dimensional array by using wavelet transform to obtain a new two-dimensional array Pulse1;

[0087] Specifically, the micropulse duration analysis unit is used to calculate the change rate of each row of data in the new two-dimensional array Pulse1, compare the change rate of each row of data with a predetermined change rate threshold, record the absolute time when the change rate of each row of data is first greater than the change rate threshold as Pstart, record the absolute time when the change rate of each row of data is last greater than the change rate threshold as Pend, and use the difference between Pstart and Pend as the micropulse duration;

[0088] Specifically, the micropulse rise time analysis unit is used to record the time of the position corresponding to the maximum peak micropulse in the two-dimensional array as Tmax, and then search from the position corresponding to the maximum peak micropulse to time zero until the first point with a different sign from the maximum peak micropulse is found, and record the time corresponding to the first point with a different sign from the maximum peak micropulse as Tmin, and then multiply the difference between Tmax and Tmin by 0.8 to obtain the micropulse rise time;

[0089] Specifically, the zero-crossing point search unit is used to set all negative values ​​in the two-dimensional array to zero to obtain a new two-dimensional array PulseP, and search for points that meet the conditions according to time as zero-crossing points Zeros in the waveform, and the conditions specifically include: the searched point itself is equal to zero, and at the same time the point at the previous position is equal to zero, and the point at the next position is greater than zero; or the searched point itself is equal to zero, and at the same time the point at the previous position is greater than zero, and the point at the next position is equal to zero;

[0090] Specifically, the pulse peak value analysis unit is used to record the position of the zero-crossing point in the waveform as Zp, search for the maximum value or minimum value between the zero-crossing points in the original waveform data according to the position of the zero-crossing point in the waveform, take the value of the maximum value or minimum value whose absolute value is greater than the second amplitude threshold as the pulse peak value Pk, and generate a pulse peak value sequence;

[0091] Specifically, the pulse oscillation period analysis unit is used to sort the pulse peak sequence according to time to form a positive and negative alternating pulse peak sequence, and the time difference between the peak values ​​Pk1 and Pk3 is used as the pulse oscillation period, then the micropulse attenuation is Pk5 / Pk1, Pk 10 / Pk1.

[0092] This embodiment also provides a computing device, including:

[0093] Memory and processor;

[0094] The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions to implement the method proposed in the above embodiment.

[0095] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method proposed in the above embodiment is implemented.

[0096] The storage medium proposed in this embodiment and the method proposed in the above embodiment belong to the same inventive concept. The technical details not fully described in this embodiment can be referred to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0097] Through the above description about the implementation mode, it can be clearly understood by those skilled in the art that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes. The scheme in the embodiments of the present application can be implemented in various computer languages, for example, object-oriented programming language Java and literal scripting language JavaScript, etc.

[0098] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0099] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0100] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0101] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for automatically analyzing transient electromagnetic disturbance micro-pulse waveforms in a substation, characterized in that: include: Collecting transient electromagnetic waveform data of the substation and extracting waveform data features, analyzing the waveform data features to obtain port types and background noise amplitudes, and obtaining a first amplitude threshold; Searching for the global maximum value of the sequence, taking the global maximum value of the sequence as the maximum micropulse peak point, extracting the position of the maximum micropulse peak point and a waveform data sequence of points symmetrically located at the distance threshold nearby according to a predetermined distance threshold, and extracting them as one of the micropulses into a two-dimensional array; Setting the extracted waveform data sequence to zero in the original sequence, and repeating the steps of extracting and setting to zero until all micropulses with amplitudes greater than the first amplitude threshold are found; The micro-pulse sequence in the two-dimensional array is analyzed to obtain micro-pulse waveform parameters corresponding to the transient electromagnetic waveform data of the substation.

2. The method for automatically analyzing transient electromagnetic disturbance micro-pulse waveforms in substations according to claim 1, characterized in that: The acquisition of the port type and the background noise amplitude includes: A waveform recognition model is constructed based on a convolutional neural network, and historical substation transient electromagnetic waveform data is collected. The port type and background noise amplitude are marked for each substation transient electromagnetic waveform data, sample data is generated, and the waveform recognition model is trained using the sample data; Importing the substation transient electromagnetic waveform data collected in real time into the trained waveform recognition model, extracting waveform data features, and analyzing the waveform data features to obtain the port type and background noise amplitude; A first amplitude threshold is set according to the port type and the background noise amplitude.

3. The method for automatically analyzing transient electromagnetic disturbance micro-pulse waveforms in substations according to claim 2, characterized in that: Acquiring a micropulse greater than the first amplitude threshold comprises: The duration of the micropulse is at the level of us, the duration of the entire macropulse is at the level of ms, and the interval between two adjacent pulses is much longer than the duration of the micropulse itself. Based on this feature, the global maximum value of the sequence is searched, and the global maximum value of the sequence is taken as the maximum micropulse peak point; Extracting the position of the maximum micropulse peak point and the waveform data sequence of the symmetrical distance threshold points nearby according to the predetermined distance threshold, saving the waveform data sequence as a new sequence, i.e., the first peak micropulse, and extracting the first peak micropulse as one of the micropulses into a two-dimensional array; After all the values ​​at the position of the first peak micropulse extracted from the original sequence are set to zero, a global search is performed again to find the maximum value, and the waveform data sequence is extracted according to the above steps and saved as a new sequence, i.e., the second peak micropulse, and the second peak micropulse is extracted as one of the micropulses into a two-dimensional array; The steps of zeroing and extracting are repeated until all micropulses with amplitudes greater than the first amplitude threshold are found.

4. The method for automatically analyzing transient electromagnetic disturbance micro-pulse waveforms in a substation according to claim 3, characterized in that: All micropulses with amplitudes greater than the first amplitude threshold are extracted into a two-dimensional array, and each row of the two-dimensional array is one-dimensional micropulse waveform data.

5. The method for automatically analyzing transient electromagnetic disturbance micro-pulse waveforms in a substation according to claim 4, characterized in that: The acquisition of the micropulse waveform parameters includes: Performing noise reduction processing on each row of data in the two-dimensional array by wavelet transform to obtain a new two-dimensional array Pulse1, and calculating the change rate of each row of data in the new two-dimensional array Pulse1; Compare the change rate of each row of data with a predetermined change rate threshold, record the absolute time when the change rate of each row of data is first greater than the change rate threshold as Pstart, record the absolute time when the change rate of each row of data is last greater than the change rate threshold as Pend, and use the difference between Pstart and Pend as the micropulse duration; The time corresponding to the position of the maximum peak micropulse in the two-dimensional array is recorded as Tmax, and then a search is performed from the position corresponding to the maximum peak micropulse toward time zero until the first point with a sign opposite to that of the maximum peak micropulse is found, and the time corresponding to the first point with a sign opposite to that of the maximum peak micropulse is recorded as Tmin, and then the difference between Tmax and Tmin is multiplied by 0.8 to obtain the micropulse rise time.

6. The method for automatically analyzing transient electromagnetic disturbance micro-pulse waveforms in a substation according to claim 4, characterized in that: The acquisition of the micropulse waveform parameters also includes: All negative values ​​in the two-dimensional array are set to zero to obtain a new two-dimensional array PulseP, and points that meet the conditions are searched according to time as zero-crossing points in the waveform, and the positions of the zero-crossing points in the waveform are recorded as Zp. According to the positions of the zero-crossing points in the waveform, the maximum value or minimum value between the zero-crossing points is searched in the original waveform data, and the value of the maximum value or minimum value whose absolute value is greater than the second amplitude threshold is taken as the pulse peak value Pk, and a pulse peak value sequence is generated; The pulse peak sequence is sorted according to time to form a positive and negative alternating pulse peak sequence, and the time difference between the peaks Pk1 and Pk3 is taken as the pulse oscillation period. The micropulse attenuation is Pk5 / Pk1, Pk 10 / Pk1.

7. The method for automatically analyzing transient electromagnetic disturbance micro-pulse waveforms in a substation according to claim 6, characterized in that: The point that satisfies the conditions according to time is used as the zero-crossing point Zeros in the waveform, wherein the conditions specifically include: The searched point itself is equal to zero, and at the same time the point at the previous position is equal to zero, and the point at the next position is greater than zero; or the searched point itself is equal to zero, and at the same time the point at the previous position is greater than zero, and the point at the next position is equal to zero.

8. A system using the method for automatically analyzing transient electromagnetic disturbance micro-pulse waveforms in substations as claimed in any one of claims 1 to 7, characterized in that: include: Waveform acquisition module, used to collect transient electromagnetic waveform data of substation; A threshold setting module, used to extract the characteristics of the transient electromagnetic waveform data of the substation, analyze the characteristics of the waveform data to obtain the port type and the background noise amplitude, and obtain the first amplitude threshold; A global search module is used to search for the global maximum value of the sequence, take the global maximum value of the sequence as the maximum micropulse peak point, extract the position of the maximum micropulse peak point and the waveform data sequence of the symmetrical distance threshold points nearby according to a predetermined distance threshold, and extract them as one of the micropulses into a two-dimensional array; a zeroing search unit, configured to zero the extracted waveform data sequence in the original sequence, and repeat the steps of extracting and zeroing until all micropulses with amplitudes greater than the first amplitude threshold are found; The parameter analysis module is used to analyze the micro-pulse sequence in the two-dimensional array to obtain the micro-pulse waveform parameters corresponding to the transient electromagnetic waveform data of the substation.

9. An electronic device, comprising: Memory and processor; The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions. When the computer executable instructions are executed by the processor, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having computer program instructions stored thereon, wherein the computer-executable instructions, when executed by a processor, implement the steps of the method according to any one of claims 1 to 7.

Images