Method and system for extracting hidden trouble traveling wave discharge characteristics of line

Abstract

The invention discloses a line hidden danger traveling wave discharge feature extraction method and system. The method comprises the steps of obtaining target hidden danger discharge data; performing first feature extraction and second feature extraction on the target hidden danger discharge data; and presetting a first judgment strategy, judging the first feature extraction and the second feature extraction in combination with the first judgment strategy, and outputting reasonably judged features. The accuracy and efficiency of line hidden danger detection are improved, and potential discharge fault points can be quickly identified and positioned, so that the occurrence of power failure accidents is reduced, and safe and stable operation of a power grid is guaranteed. Besides, the method and the system have good expansibility and adaptability, can adapt to different types of lines and environment conditions, and provide powerful technical support for maintenance and management of the power system.

Description

Technical Field

[0001] The present invention relates to the technical field of extracting traveling wave discharge characteristics of line hidden dangers, and in particular to a method and system for extracting traveling wave discharge characteristics of line hidden dangers. Background Art

[0002] Transmission and distribution lines are prone to insulator degradation, contamination, floating foreign objects, etc., which can lead to weakened insulation strength between the high-voltage side conductors and the ground wires and towers at the ground potential, causing hidden discharges. If not cleared in time, it will develop into a fault and eventually cause the line to trip and stop operating, resulting in significant economic losses and safety risks.

[0003] In order to accurately and timely identify and eliminate discharges on the line, it is necessary to first identify the existence and type of hidden discharges on the line. Currently, most transmission and distribution lines of various voltage levels have installed distributed traveling wave fault locating devices, which collect high-frequency discharge traveling waves generated and propagated from the discharge point at both ends of the line, calculate their characteristics, and compare and determine whether they have abnormal characteristics, so as to identify the existence and type of discharge, and notify the line operation and maintenance personnel to carry out maintenance work.

[0004] At present, similar technologies mainly extract high-frequency discharge waveform fragments, calculate specified features such as amplitude, phase, power frequency accompanying periodicity, etc., and use pattern classification algorithms such as decision trees, support vector machines, neural networks, etc. to finally output the existence or type label of hidden dangers when solving the problem of hidden danger discharge identification and classification. However, in reality, it is very difficult to extract the traveling wave characteristics of transmission line hidden dangers. Ineffective extraction leads to a decrease in positioning accuracy and recognition rate. Therefore, an effective and practical method for extracting the traveling wave discharge characteristics of line hidden dangers is needed to solve the subsequent location of hidden danger points. Summary of the invention

[0005] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0006] In view of the above existing problems, the present invention is proposed.

[0007] Therefore, the present invention provides a method and system for extracting traveling wave discharge characteristics of line hidden dangers, which can solve the problems mentioned in the background technology.

[0008] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0009] In a first aspect, the present invention provides a method for extracting traveling wave discharge characteristics of line hidden dangers, comprising:

[0010] Obtain target hidden danger discharge data;

[0011] Performing a first feature extraction and a second feature extraction on the target hidden danger discharge data;

[0012] A first judgment strategy is preset, and the first feature extraction and the second feature extraction are judged in combination with the first judgment strategy, and a reasonable feature is output.

[0013] As a preferred solution of the method for extracting the traveling wave discharge characteristics of line hidden dangers described in the present invention, the first feature extraction and the second feature extraction include:

[0014] The first feature extraction is a process of obtaining a plurality of target time domain features by analyzing the target hidden danger discharge data in the time domain;

[0015] The second feature extraction is a process of obtaining a plurality of target frequency domain features by frequency domain analysis of the target hidden danger discharge data.

[0016] As a preferred solution of the method for extracting the traveling wave discharge characteristics of line hidden dangers described in the present invention, the first judgment strategy includes:

[0017] Preset the first atlas;

[0018] Design a graph based on the first feature extraction and the second feature extraction results, which is recorded as a second graph;

[0019] The first spectrum is compared with the second spectrum.

[0020] As a preferred solution of the method for extracting the traveling wave discharge characteristics of line hidden dangers described in the present invention, the first judgment strategy also includes:

[0021] Presetting a first threshold;

[0022] Determining the relationship between the comparison result of the first spectrum and the second spectrum and the first threshold;

[0023] Whether the first feature extraction and the second feature extraction are reasonable is judged according to the relationship between the comparison result of the first map and the second map and the first threshold.

[0024] As a preferred solution of the method for extracting the traveling wave discharge characteristics of line hidden dangers described in the present invention, the first feature extraction and the second feature extraction also include:

[0025] The first feature extraction includes configuring a first calculation logic for any target time domain feature of the target hidden danger discharge data;

[0026] The second feature extraction includes configuring a second calculation logic for any target frequency domain feature of the target hidden danger discharge data.

[0027] As a preferred solution of the method for extracting the traveling wave discharge characteristics of the line hidden dangers described in the present invention, wherein: the target time domain characteristics at least include the rising edge time of the discharge data, the discharge pulse phase distribution, the discharge pulse energy and the discharge pulse frequency;

[0028] The target frequency domain features include at least the frequency center of gravity and the frequency range of the discharge data.

[0029] As a preferred solution of the method for extracting the traveling wave discharge characteristics of the line hidden danger described in the present invention, the step of obtaining the target hidden danger discharge data includes:

[0030] Determine the positioning tower of the target hidden danger discharge point;

[0031] Each group of hidden danger discharge data in the historical database of the positioning tower is obtained.

[0032] In a second aspect, the present invention provides a system for extracting traveling wave discharge characteristics of line hidden dangers, comprising:

[0033] A data acquisition module, used to acquire target hidden danger discharge data;

[0034] A feature extraction module, used for performing a first feature extraction and a second feature extraction on the target hidden danger discharge data;

[0035] The feature judgment module is used to preset a first judgment strategy, judge the first feature extraction and the second feature extraction in combination with the first judgment strategy, and output a reasonable feature.

[0036] In a third aspect, the present invention provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above-mentioned method when executing the computer program.

[0037] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps of the method described above when executed by a processor.

[0038] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention proposes a method and system for extracting the characteristics of traveling wave discharge of hidden dangers of a line, obtains target hidden danger discharge data; performs a first feature extraction and a second feature extraction on the target hidden danger discharge data; presets a first judgment strategy, judges the first feature extraction and the second feature extraction in combination with the first judgment strategy, and outputs reasonable judgment characteristics. The accuracy and efficiency of line hidden danger detection are improved, and potential discharge fault points can be quickly identified and located, thereby reducing the occurrence of power outages and ensuring the safe and stable operation of the power grid. In addition, the method and system also have good scalability and adaptability, can adapt to different types of lines and environmental conditions, and provide strong technical support for the maintenance and management of power systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0040] Figure 1 A method flow chart of a method and system for extracting traveling wave discharge characteristics of line hidden dangers provided by an embodiment of the present invention;

[0041] Figure 2 A schematic diagram of time domain division of a hidden danger discharge data of a method and system for extracting traveling wave discharge characteristics of a hidden danger of a line provided by an embodiment of the present invention;

[0042] Figure 3 A schematic diagram of a single discharge pulse waveform of a method and system for extracting traveling wave discharge characteristics of line hidden dangers provided by an embodiment of the present invention;

[0043] Figure 4 A schematic diagram of a method for extracting traveling wave discharge characteristics of a line hidden danger and a system for frequency domain analysis of hidden danger discharge data provided by an embodiment of the present invention;

[0044] Figure 5 A method for extracting traveling wave discharge characteristics of line hidden dangers and a flow chart of hidden danger discharge data feature extraction of a system provided in one embodiment of the present invention;

[0045] Figure 6 An internal structural diagram of a computer device of a method and system for extracting traveling wave discharge characteristics of line hidden dangers provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0046] 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.

[0047] Example 1

[0048] Reference Figure 1-Figure 6 , which is the first embodiment of the present invention, and provides a method and system for extracting traveling wave discharge characteristics of line hidden dangers, including:

[0049] There are some problems in the existing related technologies. For example, the traditional traveling wave discharge detection method relies on high-precision time synchronization, which is difficult to guarantee in practical applications, especially in large-scale power grids. In addition, due to factors such as environmental noise and equipment aging, accurate signal recognition and feature extraction become complicated and prone to errors. These problems limit the accuracy and reliability of traveling wave discharge detection technology, which in turn affects the timely discovery and handling of line hidden dangers.

[0050] The present application provides a method that can effectively solve the above-mentioned problems. Next, a method for extracting the characteristics of traveling wave discharge of hidden dangers of the line will be described in detail in combination with multiple embodiments.

[0051] Figure 1 A method flow chart of a method and system for extracting traveling wave discharge characteristics of line hidden dangers is shown, including:

[0052] S101, obtaining target hidden danger discharge data;

[0053] In an optional embodiment, the target hidden danger discharge data may include at least one characteristic parameter of the traveling wave signal, such as the traveling wave arrival time, the traveling wave amplitude, the traveling wave frequency, etc. By analyzing these parameters, the target hidden danger discharge event can be preliminarily located and classified. Furthermore, the system can use advanced signal processing techniques, such as wavelet transform, Fourier transform, etc., to reduce noise and extract features from the acquired traveling wave signal to improve the accuracy and reliability of detection.

[0054] In an optional embodiment, a machine learning algorithm can be combined to perform intelligent recognition of traveling wave signals through a trained model, thereby achieving automatic detection and early warning of line hazards.

[0055] In an optional embodiment, the target hidden danger discharge data can be acquired in different ways, for example, by real-time monitoring through sensors installed at key locations of the transmission line, or by analyzing existing inspection data. These sensors can be traveling wave sensors based on the principle of electromagnetic induction, or fiber optic sensors based on optical principles. Real-time monitoring can provide a continuous data stream, which helps to capture instantaneous discharge events, while inspection data can provide support for the analysis of historical data. Through these different data acquisition methods, a comprehensive hidden danger detection network can be built, thereby improving the safety and reliability of the entire transmission system.

[0056] In the embodiment of the present application, obtaining target hidden danger discharge data includes:

[0057] Determine the positioning tower of the target hidden danger discharge point;

[0058] Each group of hidden danger discharge data in the historical database of the positioning tower is obtained.

[0059] In the embodiment of the present application, specifically, the characteristics of each group of hidden danger discharge data can be analyzed, including parameters such as the intensity, frequency and duration of the discharge. Advanced data analysis techniques, such as cluster analysis and principal component analysis, are used to process the data to identify potential abnormal patterns. Combining real-time monitoring data and historical data, a dynamic hidden danger discharge database is established for subsequent hidden danger identification and early warning. By comparing real-time monitoring data with data in the historical database, real-time tracking and analysis of line hidden dangers can be achieved, thereby timely discovering and warning of potential line faults.

[0060] It should be noted that obtaining target hidden danger discharge data can provide accurate hidden danger discharge characteristics and provide strong data support for early identification and early warning of hidden dangers. Through these data, hidden danger points can be located more accurately, so as to formulate targeted maintenance and repair plans, reduce the occurrence of sudden failures, and ensure the stable operation of the transmission system. In addition, the real-time updated hidden danger discharge database can also provide reference for similar hidden dangers that may occur in the future, enhancing the system's prediction ability and the flexibility of response strategies.

[0061] S102, performing first feature extraction and second feature extraction on the target hidden danger discharge data;

[0062] In an embodiment of the present application, the first feature extraction and the second feature extraction include:

[0063] The first feature extraction is a process of obtaining a plurality of target time domain features by analyzing the target hidden danger discharge data in the time domain;

[0064] The second feature extraction is a process of obtaining a plurality of target frequency domain features by frequency domain analysis of the target hidden danger discharge data.

[0065] In an optional embodiment, the first feature extraction can be implemented by Fourier transform, converting the time domain signal into a frequency domain signal, thereby extracting the frequency domain features reflecting the discharge characteristics of the hidden danger. In this way, the frequency components of the discharge signal can be analyzed, and the frequency patterns related to specific hidden dangers can be further identified.

[0066] In an optional embodiment, the first feature extraction can also use wavelet transform to capture the changes of signals at different scales to reveal the time-frequency characteristics of hidden danger discharge. Wavelet transform can provide time-frequency localization information, which helps to more accurately locate the specific time and frequency range of the discharge event. By combining time domain and frequency domain analysis, the characteristics of hidden danger discharge can be fully obtained, providing a richer data basis for subsequent analysis and processing.

[0067] In an optional embodiment, the first feature extraction can also be implemented by short-time Fourier transform (STFT), which can provide spectral information of the signal in different time windows. By selecting an appropriate window length, STFT can strike a balance between time resolution and frequency resolution, thereby effectively analyzing the frequency characteristics of the discharge signal changing over time. In addition, the use of STFT can assist in determining the dynamic change process of the discharge event, providing a more detailed perspective for the monitoring and analysis of hidden danger discharges.

[0068] In the embodiment of the present application, the first feature extraction and the second feature extraction further include:

[0069] The first feature extraction includes configuring a first calculation logic for any target time domain feature of the target hidden danger discharge data;

[0070] In an optional embodiment, the second feature extraction can further optimize the feature extraction algorithm by analyzing the waveform characteristics of the discharge pulse, including but not limited to the rising edge time Trise and the pulse discharge energy P. By comparing the similarities and differences of different discharge pulse waveforms, line hidden dangers can be more accurately identified.

[0071] In an optional embodiment, by using advanced signal processing techniques, such as wavelet transform or Fourier transform, more characteristic parameters helpful for diagnosis can be extracted, thereby improving the detection accuracy and reliability of the entire system.

[0072] In an optional embodiment, the second feature extraction can further refine the feature extraction process by analyzing the waveform characteristics of the discharge pulse, such as pulse width, peak voltage, pulse interval, etc. The comprehensive analysis of these parameters helps to distinguish different types of discharge events, thereby providing more accurate data support for the location of line hidden dangers.

[0073] In an optional embodiment, by establishing a database containing these characteristic parameters, a retrospective analysis of historical data can be achieved, providing a scientific basis for predicting and preventing potential line failures. In addition, in combination with a machine learning algorithm, pattern recognition can be performed on the waveform characteristics of the discharge pulse, thereby achieving automatic detection and early warning of line hidden dangers.

[0074] In an embodiment of the present application, the second feature extraction includes configuring a second calculation logic for any target frequency domain feature of the target hidden danger discharge data.

[0075] In the embodiment of the present application, the target time domain features include at least the rising edge time of the discharge data, the discharge pulse phase distribution, the discharge pulse energy and the discharge pulse frequency;

[0076] The target frequency domain features include at least the frequency center of gravity and the frequency range of the discharge data.

[0077] In the embodiment of the present application, Figure 2 Taking the definition and calculation method of time domain discharge characteristic quantity as an example, since there is a close relationship between hidden danger discharge and power frequency voltage value, and considering the symmetry of power frequency waveform, half power frequency cycle (1 / 2 cycle) is selected as the unit of hidden danger discharge data analysis, so as to analyze the phase characteristics of discharge pulse. As shown in the figure, the waveform of 40ms (2 cycles) is divided into 4 waveforms with a length of 10ms for separate analysis, and the discharge characteristic quantity is calculated for each waveform. Finally, the discharge characteristic quantities of all waveforms are summarized and statistically analyzed to obtain the complete discharge characteristics.

[0078] ① Discharge pulse phase ψ: The power frequency voltage phase at the moment corresponding to the peak of each discharge pulse. Through statistical analysis, the relationship between different types of hidden danger discharges and power frequency voltage phases can be studied. For example, the phase distribution of 5 discharge pulses is [101.4065, 121.4549, 140.0003, 155.4029, 176.0219].

[0079] ② Pulse extreme value IM: The maximum amplitude of the traveling current waveform recorded by the measuring device, which can directly reflect the instantaneous intensity of the discharge pulse. In the figure, IM = 0.83A.

[0080] ③ Number of discharge pulses N: The total number of discharge pulses with an amplitude exceeding 50% IM, representing the frequency of discharge per unit time. In the figure, N = 5.

[0081] ④ Pulse polarity distribution: The number of discharge pulses with positive polarity Np and the number of discharge pulses with negative polarity Nn in the discharge pulse. In the figure, all the discharge pulses are negative polarity, so Np=0, Nn=5.

[0082] Amplify the waveform and calculate the rising edge time and energy parameters of each discharge pulse. Take the first discharge pulse as an example. Figure 3 As shown:

[0083] ⑤ Rise time Trise: The time it takes for the discharge pulse to rise from zero to the peak value, which symbolizes the steepness and waveform frequency of the discharge pulse. According to the amplitude I0 of the discharge pulse, the moments corresponding to 10% I0 and 90% I0 in the pulse rise process are taken as t1 and t2, and 1.25 times the time difference Δt between the two is the pulse rise time Trise.

[0084] T rise =1.25*(t2-t1)

[0085] ⑥ Pulse discharge energy P: The energy released by a single discharge pulse reflects the energy intensity of the entire discharge pulse process. The calculation method is as follows:

[0086]

[0087] Wherein, u is the power frequency voltage value corresponding to the discharge pulse, qpulse is the discharge charge, that is, the integral of the discharge current, f is the sampling frequency, and t3 is the moment when the discharge pulse drops to 10% of the peak value.

[0088] In an optional embodiment, the second feature extraction can further optimize the feature extraction algorithm by analyzing the waveform characteristics of the discharge pulse, including but not limited to the rising edge time Trise and the pulse discharge energy P. By comparing the similarities and differences of different discharge pulse waveforms, line hidden dangers can be more accurately identified.

[0089] In an optional embodiment, by using advanced signal processing techniques, such as wavelet transform or Fourier transform, more characteristic parameters helpful for diagnosis can be extracted, thereby improving the detection accuracy and reliability of the entire system.

[0090] In an optional embodiment, the second feature extraction can further refine the feature extraction process by analyzing the waveform characteristics of the discharge pulse, such as pulse width, peak voltage, pulse interval, etc. The comprehensive analysis of these parameters helps to distinguish different types of discharge events, thereby providing more accurate data support for the location of line hidden dangers.

[0091] In an optional embodiment, by establishing a database containing these characteristic parameters, a retrospective analysis of historical data can be achieved, providing a scientific basis for predicting and preventing potential line failures. In addition, in combination with a machine learning algorithm, pattern recognition can be performed on the waveform characteristics of the discharge pulse, thereby achieving automatic detection and early warning of line hidden dangers.

[0092] In the embodiment of the present application, Figure 4 Take the definition and calculation method of frequency domain discharge characteristic quantity as an example.

[0093] The definition of characteristic parameters such as the frequency range of the discharge data is shown in the figure. Based on the spectrum obtained after fast Fourier transform (FFT) of the hidden danger discharge data, P50% is defined as drawing a P50% line on the graph, so that the ratio of the sum of the frequency components on the upper part to the sum of all frequency components is 30%; the frequency range fr is defined as the frequency components on the P50% line, which is the frequency range of the waveform.

[0094] It should be noted that the main idea of ​​the discharge data feature extraction process is to take each set of discharge data test samples as the research object, determine the starting and ending discrete data sets, build a continuous half-wave (1 / 2 cycle) data set within this range, and analyze and determine the sequence number of the half-wave. At the level of the half-wave time scale, carry out feature statistics and map drawing, and summarize and output the final feature statistics results.

[0095] It should be noted that the first feature extraction and the second feature extraction of the target hidden danger discharge data can more accurately identify the waveform characteristics of the discharge pulse, thereby improving the accuracy of hidden danger detection and the timeliness of early warning. The first feature extraction focuses on the time domain characteristics of the waveform, such as the rising edge, falling edge, peak value, etc. of the pulse, while the second feature extraction focuses on the frequency domain characteristics, such as the distribution of frequency components, energy concentration, etc. By combining these two feature extraction methods, a more comprehensive discharge feature model can be constructed to provide richer data support for subsequent pattern recognition and classification.

[0096] S103, presetting a first judgment strategy, judging the first feature extraction and the second feature extraction in combination with the first judgment strategy, and outputting a judged reasonable feature.

[0097] In the embodiment of the present application, the first judgment strategy includes:

[0098] Preset the first atlas;

[0099] Design a graph based on the first feature extraction and the second feature extraction results, which is recorded as a second graph;

[0100] The first spectrum is compared with the second spectrum.

[0101] In an optional embodiment, the first spectrum can be obtained through statistical analysis of historical discharge data, which reflects the discharge characteristics under normal operating conditions. By comparing with the second spectrum, abnormal changes in discharge characteristics can be intuitively identified, thereby providing a basis for early discovery of hidden dangers.

[0102] In an optional embodiment, the construction of the first map may also be combined with expert experience to conduct a more in-depth analysis and interpretation of the discharge characteristics through an expert system to further improve the accuracy of hidden danger detection.

[0103] In an optional embodiment, the updating and optimization of the first map is a continuous process, which needs to be continuously adjusted and improved according to new discharge data to adapt to changes in the line operation status.

[0104] In the embodiment of the present application, the first judgment strategy also includes:

[0105] Presetting a first threshold;

[0106] Determining the relationship between the comparison result of the first spectrum and the second spectrum and the first threshold;

[0107] Whether the first feature extraction and the second feature extraction are reasonable is judged according to the relationship between the comparison result of the first map and the second map and the first threshold.

[0108] In an optional embodiment, the first threshold value can be set according to the statistical distribution of the discharge characteristics and expert experience to ensure that normal and abnormal discharge states can be effectively distinguished. The setting of the threshold value takes into account the operating environment of the line, historical fault data, and the fluctuation range of the discharge characteristics, aiming to reduce false positives and false negatives and improve the reliability of hidden danger detection.

[0109] In an optional embodiment, if the first feature extraction and the second feature extraction are unreasonable, the system will automatically trigger a procedure for re-extracting features and re-analyze the original data through an algorithm to ensure the accuracy of feature extraction.

[0110] In an optional embodiment, the parameters of the feature extraction algorithm can also be adjusted based on historical data and real-time feedback to adapt to the specific conditions of different lines. In this way, the system can continuously optimize the feature extraction process to ensure the efficiency and accuracy of hidden danger detection.

[0111] In summary, the present invention proposes a method for extracting the characteristics of traveling wave discharge of line hidden dangers, obtaining target hidden danger discharge data; performing a first feature extraction and a second feature extraction on the target hidden danger discharge data; presetting a first judgment strategy, combining the first judgment strategy to judge the first feature extraction and the second feature extraction, and outputting reasonable judgment characteristics. The accuracy and efficiency of line hidden danger detection are improved, and potential discharge fault points can be quickly identified and located, thereby reducing the occurrence of power outages and ensuring the safe and stable operation of the power grid. In addition, the method and system also have good scalability and adaptability, can adapt to different types of lines and environmental conditions, and provide strong technical support for the maintenance and management of power systems.

[0112] Example 2

[0113] In a preferred embodiment, Figure 5 As shown in the figure, this figure shows a flowchart of half-wave analysis, which is divided into two parts: Python implementation and Matlab implementation. The following is a detailed step-by-step description:

[0114] Python implementation part: Select the experimental analysis object and conduct hidden danger data analysis: determine the experimental object to be analyzed and conduct preliminary analysis of hidden danger data. Perform half-wave splitting of the source discharge data file and preliminary statistics of characteristic values ​​(such as the maximum value and upper quartile in the half-wave data): process the source data file, split the half-wave data, and count the characteristic values ​​in the half-wave data, such as the maximum value and upper quartile.

[0115] According to the statistical value, each half wave is assigned an I M Threshold:

[0116] According to the statistically obtained characteristic value, a threshold I is assigned to each half wave. M .

[0117] Matlab implementation part:

[0118] According to the half-wave analysis results, read the half-wave data from the source file:

[0119] According to the half-wave analysis results of the Python part, read the half-wave data from the source file.

[0120] Analyze the characteristics of half-wave data:

[0121] Perform feature analysis on the read half-wave data.

[0122] For every n(100) half-waves, draw a graph containing source data and statistical results:

[0123] A spectrum is drawn every 100 half waves, and the spectrum contains source data and statistical results.

[0124] Summarize the feature extraction results of each half-wave and output the statistical table:

[0125] Summarize the feature extraction results of all half-waves and output a statistical table.

[0126] Observe the spectrum and judge whether the extraction result is reasonable:

[0127] Observe the drawn graph and judge whether the feature extraction results are reasonable.

[0128] If it is unreasonable, return to manual adjustment, the IMIM threshold of the corresponding half-wave, and update the half-wave analysis result table.

[0129] If it makes sense, the process ends.

[0130] Manual adjustment part:

[0131] If the extraction result is found to be unreasonable in the spectrum observation of the Matlab implementation part, it is necessary to manually adjust the I of the corresponding half-wave M Threshold, update the half-wave analysis result table, and then redo the steps of the Matlab implementation part.

[0132] Example 3

[0133] This embodiment also provides a system for extracting traveling wave discharge characteristics of line hidden dangers, including:

[0134] A data acquisition module, used to acquire target hidden danger discharge data;

[0135] A feature extraction module, used for performing a first feature extraction and a second feature extraction on the target hidden danger discharge data;

[0136] The feature judgment module is used to preset a first judgment strategy, judge the first feature extraction and the second feature extraction in combination with the first judgment strategy, and output a reasonable feature.

[0137] The above-mentioned unit modules may be embedded in or independent of the processor in the computer device in the form of hardware, or may be stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above-mentioned modules.

[0138] This embodiment also provides a computer device, which may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 6As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for extracting traveling wave discharge characteristics of line hazards is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a key, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse, etc.

[0139] This embodiment further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0140] Obtain target hidden danger discharge data;

[0141] Performing a first feature extraction and a second feature extraction on the target hidden danger discharge data;

[0142] A first judgment strategy is preset, and the first feature extraction and the second feature extraction are judged in combination with the first judgment strategy, and a reasonable feature is output.

[0143] 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.

[0144] Those skilled in the art will appreciate 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. 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.) that contain computer-usable program code. 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.

[0145] 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.

[0146] 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 including 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.

[0147] 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 The steps for the functions specified in one or more boxes.

[0148] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0149] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A method for extracting the characteristics of traveling wave discharge of line hidden dangers, characterized in that: include: Obtain target hidden danger discharge data; Performing a first feature extraction and a second feature extraction on the target hidden danger discharge data; A first judgment strategy is preset, and the first feature extraction and the second feature extraction are judged in combination with the first judgment strategy, and a reasonable feature is output.

2. The method for extracting the traveling wave discharge characteristics of line hidden dangers according to claim 1, characterized in that: The first feature extraction and the second feature extraction include: The first feature extraction is a process of obtaining a plurality of target time domain features by analyzing the target hidden danger discharge data in the time domain; The second feature extraction is a process of obtaining a plurality of target frequency domain features by frequency domain analysis of the target hidden danger discharge data.

3. The method for extracting the traveling wave discharge characteristics of line hidden dangers according to claim 2, characterized in that: The first judgment strategy includes: Preset the first atlas; Design a graph based on the first feature extraction and the second feature extraction results, which is recorded as a second graph; The first spectrum is compared with the second spectrum.

4. The method for extracting the traveling wave discharge characteristics of line hidden dangers according to claim 3 is characterized in that: The first judgment strategy also includes: Presetting a first threshold; Determining the relationship between the comparison result of the first spectrum and the second spectrum and the first threshold; Whether the first feature extraction and the second feature extraction are reasonable is judged according to the relationship between the comparison result of the first map and the second map and the first threshold.

5. The method for extracting the traveling wave discharge characteristics of line hidden dangers according to claim 4, characterized in that: The first feature extraction and the second feature extraction also include: The first feature extraction includes configuring a first calculation logic for any target time domain feature of the target hidden danger discharge data; The second feature extraction includes configuring a second calculation logic for any target frequency domain feature of the target hidden danger discharge data.

6. The method for extracting the traveling wave discharge characteristics of line hidden dangers according to claim 5, characterized in that: The target time domain features at least include the rising edge time of the discharge data, the discharge pulse phase distribution, the discharge pulse energy and the discharge pulse frequency; The target frequency domain features include at least the frequency center of gravity and the frequency range of the discharge data.

7. The method for extracting the traveling wave discharge characteristics of line hidden dangers according to claim 6, characterized in that: The obtaining of target hidden danger discharge data comprises: Determine the positioning tower of the target hidden danger discharge point; Each group of hidden danger discharge data in the historical database of the positioning tower is obtained.

8. A system for extracting the characteristics of traveling wave discharge of line hidden dangers, characterized in that: include: A data acquisition module, used to acquire target hidden danger discharge data; A feature extraction module, used for performing a first feature extraction and a second feature extraction on the target hidden danger discharge data; The feature judgment module is used to preset a first judgment strategy, judge the first feature extraction and the second feature extraction in combination with the first judgment strategy, and output a reasonable feature.

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

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images