GIS bus electrical contact defect diagnosis method fusing magnetic field-current characteristics and related device

Abstract

The invention provides a GIS bus electrical contact defect diagnosis method fusing magnetic field-current characteristics and a related device. The GIS bus electrical contact defect diagnosis method comprises the steps of obtaining GIS bus conductor current, shell ring current waveforms and shell space magnetic field distribution under different electrical contact defects; carrying out fault characteristic current extraction on the conductor current and the shell circulation waveform by adopting an inverse phase difference algorithm, and carrying out time embedding processing on the shell space magnetic field distribution through map coding to respectively obtain a characteristic current signal and magnetic field time sequence data; and taking the characteristic current signal and the magnetic field time sequence data as a comprehensive characteristic set, carrying out classification training on the comprehensive characteristic set by adopting a deep learning neural network, constructing a GIS bus electrical contact defect diagnosis model, and carrying out electrical contact defect diagnosis by utilizing the model. According to the invention, by obtaining the related current and magnetic field data of the GIS bus, multi-dimensional detection can be realized, technical support is provided for state maintenance, the intelligent operation and maintenance level is improved, and safe and stable operation of equipment is guaranteed.

Description

Technical Field

[0001] The present invention belongs to the technical field of power system equipment diagnosis, and specifically relates to a GIS (Gas Insulated Switchgear) busbar electrical contact defect diagnosis method and related devices that integrate magnetic field and current characteristics. Background Art

[0002] Gas-insulated metal-enclosed switchgear (GIS) is a critical component of power systems, with its busbars responsible for transmitting high voltages and high currents. However, over long-term operation, GIS busbars can develop contact defects, such as loose bolts and slack contact springs. This increases contact resistance, leading to temperature rise, equipment overheating, and even short-circuit failures, seriously compromising the safe operation of the power system.

[0003] Currently, methods for detecting electrical contact defects in GIS busbars include loop resistance, vibration, partial discharge, and infrared detection. While these methods have some applications, they have limitations, such as the inability to detect live faults, insensitivity to early-stage faults, and significant susceptibility to environmental interference. Furthermore, diagnostic methods based on magnetic field distribution also face challenges in feature extraction and susceptibility to background interference, making them difficult to meet the demands of high-precision detection.

[0004] Existing technologies for detecting electrical contact defects in GIS busbars suffer from limitations in single methods, incomplete feature extraction, and susceptibility to environmental interference, making early and accurate fault diagnosis difficult. Therefore, developing a diagnostic method that integrates multiple features and adapts to complex operating conditions is crucial for improving GIS busbar maintenance and ensuring the safe operation of power systems. Summary of the Invention

[0005] In view of this, the present invention aims to provide a GIS busbar electrical contact defect diagnosis method and related devices that integrate magnetic field-current characteristics to overcome the shortcomings of the existing technology and achieve accurate diagnosis of GIS busbar electrical contact defects.

[0006] In order to achieve the above object, the technical solution provided by the present invention is as follows:

[0007] In a first aspect, the present invention provides a method for diagnosing GIS busbar electrical contact defects by integrating magnetic field and current characteristics, comprising the following steps:

[0008] Obtain the waveforms of GIS busbar conductor current and casing circulating current as well as the magnetic field distribution in the casing space under different electrical contact defects;

[0009] The inverse difference algorithm is used to extract the fault characteristic current from the conductor current and the shell circulating current waveforms, and the spatial magnetic field distribution of the shell is time-embedded through spectrum coding to obtain the characteristic current signal and magnetic field time series data respectively.

[0010] The characteristic current signal and magnetic field time series data are used as a comprehensive feature set, and a deep learning neural network is used to classify and train the comprehensive feature set. A GIS busbar electrical contact defect diagnosis model is constructed and used to diagnose GIS busbar electrical contact defects.

[0011] Furthermore, the waveforms of the GIS busbar conductor current and casing circulating current as well as the magnetic field distribution in the casing space are obtained under different electrical contact defects, including:

[0012] Install current sensors on the GIS busbar conductors to monitor the conductor current waveform in real time.

[0013] Arrange a Hall sensor array on the GIS busbar housing to measure the housing circulating current waveform and spatial magnetic field distribution;

[0014] The current waveform and magnetic field data under different electrical contact defect states are recorded to obtain the conductor current and shell circulating current waveforms as well as the magnetic field distribution in the shell space.

[0015] Furthermore, the steps of extracting fault characteristic current from the conductor current and casing circulating current waveforms using an inverse differential algorithm include:

[0016] Filter the collected conductor current and shell circulating current waveforms;

[0017] According to the determined differential step size, the pre-processed signal is subjected to inverse differential calculation;

[0018] The result of the differential calculation is compared with the set threshold. If the absolute value of the differential result is greater than the threshold, it is determined that the signal change at that point may be related to an electrical contact defect, and the point and its related information are recorded. If the differential result is less than the threshold, the signal change at that point is considered normal and is not included in the fault feature analysis range.

[0019] The recorded signal points that may be related to the fault are screened, the screened signals are integrated, and the characteristic current signals that can accurately reflect the electrical contact defects are extracted.

[0020] Furthermore, the spatial magnetic field distribution of the shell is subjected to time embedding processing through atlas coding, including:

[0021] Based on the shell space magnetic field distribution data measured by the Hall sensor array, a spatial magnetic field map is constructed with spatial position as coordinates and magnetic field strength and direction as attributes;

[0022] Convert the spatial magnetic field map into a time series code according to a preset coding rule;

[0023] The generated time series code is verified. If it meets the characteristics of spatial magnetic field distribution and time variation information, the magnetic field time series data is obtained.

[0024] In a second aspect, the present invention provides a GIS busbar electrical contact defect diagnosis device integrating magnetic field and current characteristics, comprising:

[0025] Data acquisition module, data processing module and model building and diagnosis module;

[0026] The data acquisition module is used to obtain the waveforms of GIS busbar conductor current and casing circulating current as well as the magnetic field distribution in the casing space under different electrical contact defects;

[0027] The data processing module is used to extract fault characteristic current from the conductor current and casing circulating current waveforms using an inverse differential algorithm, and to perform time embedding processing on the casing spatial magnetic field distribution through spectrum coding to obtain characteristic current signals and magnetic field time series data respectively;

[0028] The characteristic current signal and magnetic field time series data are used as a comprehensive feature set, and a deep learning neural network is used to classify and train the comprehensive feature set. A GIS busbar electrical contact defect diagnosis model is constructed and used to diagnose GIS busbar electrical contact defects.

[0029] Furthermore, the data acquisition module includes a current sensor and a Hall sensor array. The data acquisition module acquires the waveforms of the GIS busbar conductor current and the shell circulating current under different electrical contact defects, as well as the magnetic field distribution in the shell space, including:

[0030] Install current sensors on the GIS busbar conductors to monitor the conductor current waveform in real time.

[0031] Arrange a Hall sensor array on the GIS busbar housing to measure the housing circulating current waveform and spatial magnetic field distribution;

[0032] The current waveform and magnetic field data under different electrical contact defect states are recorded to obtain the conductor current and shell circulating current waveforms as well as the magnetic field distribution in the shell space.

[0033] Furthermore, the data processing module includes a reverse differential algorithm module, which extracts fault characteristic current from the conductor current and the shell circulating current waveform through the reverse differential algorithm module, including:

[0034] Filter the collected conductor current and shell circulating current waveforms;

[0035] According to the determined differential step size, the pre-processed signal is subjected to inverse differential calculation;

[0036] The result of the differential calculation is compared with the set threshold. If the absolute value of the differential result is greater than the threshold, it is determined that the signal change at that point may be related to an electrical contact defect, and the point and its related information are recorded. If the differential result is less than the threshold, the signal change at that point is considered normal and is not included in the fault feature analysis range.

[0037] The recorded signal points that may be related to the fault are screened, the screened signals are integrated, and the characteristic current signals that can accurately reflect the electrical contact defects are extracted.

[0038] Furthermore, the data processing module further includes a spectrum encoding module, and the data processing module performs time embedding processing on the magnetic field distribution in the shell space through the spectrum encoding module, including:

[0039] Based on the shell space magnetic field distribution data measured by the Hall sensor array, a spatial magnetic field map is constructed with spatial position as coordinates and magnetic field strength and direction as attributes;

[0040] Convert the spatial magnetic field map into a time series code according to a preset coding rule;

[0041] The generated time series code is verified. If it meets the characteristics of spatial magnetic field distribution and time variation information, the magnetic field time series data is obtained.

[0042] In a third aspect, the present invention provides a computer device, comprising a processor and a memory:

[0043] The memory is used to store computer programs and send instructions of the computer programs to the processor;

[0044] The processor executes the GIS busbar electrical contact defect diagnosis method integrating magnetic field and current characteristics as described in the first aspect according to the instructions of the computer program.

[0045] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, a GIS busbar electrical contact defect diagnosis method integrating magnetic field-current characteristics as in the first aspect is implemented.

[0046] In summary, the present invention provides a GIS busbar electrical contact defect diagnosis method that integrates magnetic field and current characteristics, including obtaining the GIS busbar conductor current and casing circulating current waveforms and the casing spatial magnetic field distribution under different electrical contact defects; using an inverse differential algorithm to extract fault characteristic current from the conductor current and casing circulating current waveforms, and performing time embedding processing on the casing spatial magnetic field distribution through graph coding to obtain characteristic current signals and magnetic field time series data respectively; using the characteristic current signals and magnetic field time series data as a comprehensive feature set, and using a deep learning neural network to classify and train the comprehensive feature set, constructing a GIS busbar electrical contact defect diagnosis model, and using the GIS busbar electrical contact defect diagnosis model to perform GIS busbar electrical contact defect diagnosis. By obtaining GIS busbar-related current and magnetic field data, the present invention can realize multi-dimensional detection of GIS operating status, provide technical support for status inspection and maintenance, improve the level of intelligent operation and maintenance, and ensure safe and stable operation of equipment.

[0047] The present invention also provides a GIS busbar electrical contact defect diagnosis device, computer equipment and computer-readable storage medium that integrate magnetic field-current characteristics. When implemented, they have similar effects to the above method and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. 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 paying any creative work.

[0049] Figure 1 A flowchart of a GIS busbar electrical contact defect diagnosis method integrating magnetic field and current characteristics provided by an embodiment of the present invention;

[0050] Figure 2 A wiring schematic diagram of a GIS busbar electrical contact defect diagnosis device integrating magnetic field and current characteristics provided by an embodiment of the present invention;

[0051] Figure 3 A block diagram of a computer device provided in an embodiment of the present invention.

[0052] In the attached figure: 1-Hall sensor array, 2-current sensor, 3-reverse differential algorithm module, 4-atlas encoding module, 5-data fusion module, 6-neural network training module, 7-real-time analysis module, 8-GIS module to be tested. DETAILED DESCRIPTION

[0053] In order to make the purposes, features, and advantages of the present invention more obvious and easy to understand, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described below are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0054] See also Figure 1 The embodiment of the present invention provides a method for diagnosing GIS busbar electrical contact defects by integrating magnetic field and current characteristics, including the following steps:

[0055] S1: Obtain the waveforms of GIS busbar conductor current and casing circulating current as well as the magnetic field distribution in the casing space under different electrical contact defects.

[0056] It's important to note that conductor current refers to the current flowing in the GIS busbar conductor and reflects the power transmission performance of the busbar. Enclosure circulating current refers to the current generated within the GIS busbar enclosure, and its magnitude and distribution are related to the busbar's operating status. Enclosure space magnetic field distribution refers to the intensity and direction of the magnetic field in the space surrounding the GIS busbar and is closely related to current distribution.

[0057] This step obtains the above-mentioned basic data. Different electrical contact defects will cause specific changes in the conductor current, the shell circulating current waveform, and the magnetic field distribution in the shell space. By obtaining this data, information related to the defect can be captured.

[0058] S2: The inverse difference algorithm is used to extract the fault characteristic current from the conductor current and casing circulating current waveforms, and the spatial magnetic field distribution of the casing is time-embedded through spectrum coding to obtain the characteristic current signal and magnetic field time series data respectively.

[0059] It should be noted that the inverse differential algorithm is a signal processing algorithm that highlights signal variations by performing inversion and differential operations on the signal, and can be used for fault feature extraction. The fault characteristic current is a characteristic current signal associated with electrical contact defects extracted from the conductor current and casing circulating current waveforms. Spectral encoding is a method for encoding spatial magnetic field distribution data, converting spatial information into time series data. Time embedding converts original spatial information (such as magnetic field distribution) into time series data for subsequent time series analysis.

[0060] This step uses an inverse difference algorithm to invert the conductor current and casing current waveforms, then performs a differential operation, calculating the difference between the signals at adjacent moments. This emphasizes sudden changes in the signal, which are often caused by electrical contact defects, thereby extracting the characteristic fault current. Spectral encoding is also used to encode the magnetic field strength and direction information at different locations in the casing according to specific rules. This information is then converted into a time series, allowing analysis of the magnetic field distribution information over time.

[0061] Current changes caused by electrical contact defects are often relatively small, hidden within normal current signals and difficult to detect directly. Inverse differential processing can amplify these subtle changes, highlighting defect-related features from the complex background signal, enhancing the recognition of fault characteristics and facilitating subsequent analysis and processing.

[0062] In the process of atlas encoding and time embedding the magnetic field distribution, the spatial characteristic information of the magnetic field distribution can be retained in the time series data, so that the model can not only utilize the dynamic characteristics of the time series but also consider the spatial characteristics of the magnetic field distribution during analysis, and more comprehensively mine the information related to electrical contact defects in the magnetic field data, thereby improving the accuracy of diagnosis.

[0063] S3: The characteristic current signal and magnetic field time series data are used as a comprehensive feature set, and a deep learning neural network is used to classify and train the comprehensive feature set. A GIS busbar electrical contact defect diagnosis model is constructed and used to diagnose GIS busbar electrical contact defects.

[0064] It should be noted that this step combines the characteristic current signal and magnetic field time series data into a comprehensive feature set, which is then fed into a deep learning neural network. The neural network continuously adjusts its internal weights and biases to learn the mapping between the comprehensive feature set and the types of electrical contact defects. During training, the model's diagnostic accuracy is continuously improved by using a large amount of sample data with known defect types, calculating the error between the predicted results and the actual labels, and updating the neural network parameters using a backpropagation algorithm.

[0065] The diagnostic method provided in this embodiment is based on the physical phenomenon that GIS busbar electrical contact defects can cause changes in conductor current, casing circulating current waveform, and the magnetic field distribution within the casing. By acquiring data on these changes and processing them using techniques such as the inverse differential algorithm and graph coding, characteristic information related to the defect is extracted. This characteristic information is then used as input for training and classification using a deep learning neural network, thereby enabling the diagnosis of electrical contact defects. This method integrates multiple data types, such as conductor current, casing circulating current waveform, and the magnetic field distribution within the casing, comprehensively utilizing information related to electrical contact defects contained in these different data types. Compared to diagnostic methods based on a single data source, this method can more comprehensively reflect the defect situation and improve diagnostic accuracy and reliability. Furthermore, unique data processing methods, such as the inverse differential algorithm and graph coding, are used to perform targeted processing and feature extraction on the raw data, highlighting features related to the defect and enabling subsequent deep learning neural networks to better learn and classify.

[0066] In one embodiment, obtaining the waveforms of the GIS busbar conductor current and the casing circulating current as well as the magnetic field distribution in the casing space under different electrical contact defects includes:

[0067] S11: Install current sensors on the GIS bus conductors and monitor the conductor current waveform in real time through the current sensors.

[0068] It should be noted that the current sensor is based on the principle of electromagnetic induction. When current passes through a conductor, a magnetic field is generated around it. The current sensor detects the changes in the magnetic field and converts it into a corresponding electrical signal, thereby measuring the current in the conductor.

[0069] S12: Arrange a Hall sensor array on the GIS busbar housing to measure the housing circulating current waveform and spatial magnetic field distribution.

[0070] It should be noted that Hall effect sensors utilize the Hall effect. When a magnetic field exists around the GIS busbar casing, the sensor generates a voltage signal proportional to the magnetic field strength. By arranging multiple Hall effect sensors in an array, the magnetic field distribution at different locations can be measured. Furthermore, the current circulating around the casing also generates a magnetic field, and the waveform of this current can be indirectly measured using the Hall effect sensor array.

[0071] S13: Record the current waveform and magnetic field data under different electrical contact defect states, thereby obtaining the conductor current and shell circulating current waveforms and the shell space magnetic field distribution.

[0072] It should be noted that the GIS busbar is controlled to be in different electrical contact defect states, and the current sensor and Hall sensor array are used to record the current waveform and magnetic field data in the corresponding state in real time.

[0073] This embodiment installs current sensors on the GIS busbar conductors and arranges a Hall effect sensor array on the GIS busbar casing. This allows for simultaneous acquisition of multi-dimensional data: conductor current waveforms, casing circulating current waveforms, and the magnetic field distribution within the casing. Compared to single data sources, this multi-dimensional data provides a more comprehensive picture of the GIS busbar's operating status, providing a rich foundation for accurate subsequent diagnosis of electrical contact defects.

[0074] In one embodiment, the steps of extracting fault characteristic current from the conductor current and casing circulating current waveforms using an inverse differential algorithm include:

[0075] S21: Filter the collected conductor current and casing circulating current waveforms.

[0076] It should be noted that based on the characteristics of the collected conductor current and casing circulating current waveforms, the appropriate filter type is selected. For example, a low-pass filter can remove high-frequency noise and make the signal smoother. The filter performs frequency analysis on the signal and filters out unnecessary frequency components.

[0077] S22: Performing inverse differential calculation on the preprocessed signal according to the determined differential step size.

[0078] It should be noted that, according to the determined differential step size, the pre-processed conductor current and casing circulating current waveform signals are inverted, that is, the amplitude of the signal is inverted, and then the difference between adjacent sampling points is calculated to obtain the inverted differential signal.

[0079] S23: Compare the result obtained by differential calculation with the set threshold. If the absolute value of the differential result is greater than the threshold, it is determined that the signal change at this point may be related to an electrical contact defect, and the point and its related information are recorded. When the differential result is less than the threshold, it is considered that the signal change at this point is normal and is not included in the fault feature analysis range.

[0080] It should be noted that the result obtained by the inverse differential calculation is compared with the set threshold. When the absolute value of the differential result is greater than the threshold, it means that the signal change at this point is large, which may be caused by an electrical contact defect. Therefore, the position, amplitude and other related information of this point are recorded; when the differential result is less than the threshold, it means that the signal change at this point is within the normal range and is not considered to be a fault feature.

[0081] S24: Screening the recorded signal points that may be related to the fault, integrating the screened signals, and extracting characteristic current signals that can accurately reflect the electrical contact defect.

[0082] It should be noted that the recorded signal points that may be related to the fault are further screened to remove possible misjudgment points, and then the screened signals are integrated, such as through statistical analysis, signal reconstruction and other methods, to extract characteristic current signals that can accurately reflect electrical contact defects.

[0083] This embodiment uses an inverse differential algorithm to process the preprocessed signal, highlighting signal variations, particularly those associated with electrical contact defects. This differential calculation amplifies fault-related mutations in the signal, making the fault characteristics more pronounced and facilitating subsequent analysis and judgment.

[0084] In one embodiment, time embedding processing is performed on the shell space magnetic field distribution by using atlas coding, including:

[0085] S25: Based on the shell spatial magnetic field distribution data measured by the Hall sensor array, a spatial magnetic field map is constructed with spatial position as coordinates and magnetic field strength and direction as attributes.

[0086] It should be noted that, based on the magnetic field strength and direction data at different positions measured by the Hall sensor array, a two-dimensional or three-dimensional spatial magnetic field map is constructed using the spatial position as the coordinate and the magnetic field strength and direction as the attributes.

[0087] S26: Convert the spatial magnetic field map into a time series code according to a preset coding rule.

[0088] It should be noted that, according to the preset coding rules, each spatial position in the spatial magnetic field map is encoded, and its magnetic field strength and direction information is converted into time series coding, that is, spatial information is converted into information in the time dimension.

[0089] S27: Verify the generated time series code. If it meets the characteristics of the spatial magnetic field distribution and the time variation information, the magnetic field time series data is obtained.

[0090] It should be noted that the generated time series code is verified to check whether it meets the characteristics of the spatial magnetic field distribution (such as the magnitude and direction of the magnetic field intensity) and the temporal variation information (such as the trend of the magnetic field over time). If it meets the requirements, the time series code is considered valid and the magnetic field time series data is obtained. If it does not meet the requirements, the coding rules need to be readjusted or the data needs to be processed.

[0091] This embodiment converts spatial magnetic field maps into time series encoding according to preset encoding rules, achieving the conversion from spatial information to time series information. Time series encoding is more convenient for computer processing and analysis. It can use time series analysis methods to mine potential information in magnetic field data, such as the trend of magnetic field changes over time, providing a more suitable data format for subsequent deep learning models.

[0092] Based on the same inventive concept, the present application also provides a device for diagnosing GIS busbar electrical contact defects that integrates magnetic field and current characteristics, for implementing the aforementioned method for diagnosing GIS busbar electrical contact defects that integrates magnetic field and current characteristics. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations of the embodiment of the device for diagnosing GIS busbar electrical contact defects that integrates magnetic field and current characteristics provided below can be found in the above-mentioned limitations of the method for diagnosing GIS busbar electrical contact defects that integrates magnetic field and current characteristics, and will not be repeated here.

[0093] The embodiment of the present invention further provides a GIS busbar electrical contact defect diagnosis device integrating magnetic field and current characteristics, comprising:

[0094] Data acquisition module, data processing module and model building and diagnosis module;

[0095] The data acquisition module is used to obtain the waveforms of GIS busbar conductor current and casing circulating current as well as the magnetic field distribution in the casing space under different electrical contact defects;

[0096] The data processing module is used to extract fault characteristic current from the conductor current and casing circulating current waveforms using an inverse differential algorithm, and to perform time embedding processing on the casing spatial magnetic field distribution through spectrum coding to obtain characteristic current signals and magnetic field time series data respectively;

[0097] The characteristic current signal and magnetic field time series data are used as a comprehensive feature set, and a deep learning neural network is used to classify and train the comprehensive feature set. A GIS busbar electrical contact defect diagnosis model is constructed and used to diagnose GIS busbar electrical contact defects.

[0098] See also Figure 2Among them, the Hall sensor array 1 is used to measure the magnetic field distribution of the GIS busbar casing, and is connected to the GIS module to be tested 8 and the spectrum encoding module 4: the current sensor 2 is used to monitor the current waveform in the GIS busbar conductor in real time, and is connected to the GIS module to be tested 8 and the reverse differential algorithm module 3; the reverse differential algorithm 3 processes the current signal collected by the current sensor 2, and is connected to the data fusion module 5 and the current sensor 2; the spectrum encoding module 4 is used to convert the spatial magnetic field distribution data measured by the Hall sensor array 1 into time series data, and is connected to the data fusion module 5 and the Hall sensor array 1; the data fusion module 5 fuses the characteristic current signal extracted by the reverse differential algorithm module 3 with the GIS busbar spatial magnetic field spectrum encoded by the spectrum encoding module 4, and is connected to the reverse differential algorithm module 3 and the spectrum encoding module 4; the neural network training module 6 is used to construct a GIS busbar electrical contact defect diagnosis model, and is connected to the data fusion module 5 and the real-time analysis module 7; the real-time analysis module 7 identifies the electrical contact state and is connected to the neural network training module 6.

[0099] Furthermore, the data acquisition module includes a current sensor and a Hall sensor array. The data acquisition module acquires the waveforms of the GIS busbar conductor current and the shell circulating current under different electrical contact defects, as well as the magnetic field distribution in the shell space, including:

[0100] Install current sensors on the GIS busbar conductors to monitor the conductor current waveform in real time.

[0101] Arrange a Hall sensor array on the GIS busbar housing to measure the housing circulating current waveform and spatial magnetic field distribution;

[0102] The current waveform and magnetic field data under different electrical contact defect states are recorded to obtain the conductor current and shell circulating current waveforms as well as the magnetic field distribution in the shell space.

[0103] Furthermore, the data processing module includes a reverse differential algorithm module, which extracts fault characteristic current from the conductor current and the shell circulating current waveform through the reverse differential algorithm module, including:

[0104] Filter the collected conductor current and shell circulating current waveforms;

[0105] According to the determined differential step size, the pre-processed signal is subjected to inverse differential calculation;

[0106] The result of the differential calculation is compared with the set threshold. If the absolute value of the differential result is greater than the threshold, it is determined that the signal change at that point may be related to an electrical contact defect, and the point and its related information are recorded. If the differential result is less than the threshold, the signal change at that point is considered normal and is not included in the fault feature analysis range.

[0107] The recorded signal points that may be related to the fault are screened, the screened signals are integrated, and the characteristic current signals that can accurately reflect the electrical contact defects are extracted.

[0108] Furthermore, the data processing module further includes a spectrum encoding module, and the data processing module performs time embedding processing on the magnetic field distribution in the shell space through the spectrum encoding module, including:

[0109] Based on the shell space magnetic field distribution data measured by the Hall sensor array, a spatial magnetic field map is constructed with spatial position as coordinates and magnetic field strength and direction as attributes;

[0110] Convert the spatial magnetic field map into a time series code according to a preset coding rule;

[0111] The generated time series code is verified. If it meets the characteristics of spatial magnetic field distribution and time variation information, the magnetic field time series data is obtained.

[0112] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0113] Reference Figure 3 An embodiment of the present invention also provides a computer device, comprising: a memory and a processor and a computer program stored in the memory. When the computer program is executed on the processor, a GIS busbar electrical contact defect diagnosis method integrating magnetic field-current characteristics as described in any one of the above methods is implemented.

[0114] The computer device may be a desktop computer, notebook computer, PDA, cloud server or other computing device. The computer device may include, but is not limited to, a processor and a memory. It will be understood by those skilled in the art that Figure 3The computer device is merely an example and does not constitute a limitation on the computer device. The computer device may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the computer device may also include input and output devices, network access devices, etc.

[0115] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0116] In some embodiments, the memory may be an internal storage unit of the computer device, such as a hard drive or memory of the computer device. In other embodiments, the memory may also be an external storage device of the computer device, such as a plug-in hard drive, a Smart Media Card (SMC), a Secure Digital (SD) card, a flash memory card, etc. equipped with the computer device. Furthermore, the memory may include both an internal storage unit of the computer device and an external storage device. The memory is used to store an operating system, application programs, a boot loader, data, and other programs, such as the program code of the computer program. The memory may also be used to temporarily store data that has been output or is about to be output.

[0117] An embodiment of the present invention also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, it implements a GIS busbar electrical contact defect diagnosis method that integrates magnetic field-current characteristics as described in any one of the above methods.

[0118] In this embodiment, if the integrated unit is implemented as a software functional unit and sold or used as a standalone product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application can implement all or part of the process steps in the above-mentioned method embodiments by using a computer program to instruct the relevant hardware. The computer program can be stored in a computer-readable storage medium. When executed by a processor, the computer program can implement the steps of each of the above-mentioned method embodiments. The computer program includes computer program code, which can be in source code form, object code form, executable file, or some intermediate form. The computer-readable medium can include at least: any entity or device capable of carrying computer program code to a camera / terminal device, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signals, telecommunication signals, and software distribution media. Examples include USB flash drives, removable hard drives, magnetic disks, or optical disks. In some jurisdictions, based on legislation and patent practice, computer-readable media cannot be electric carrier signals or telecommunication signals.

[0119] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0120] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0121] In the embodiments disclosed in the present application, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are merely schematic. For example, the division of the modules or units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0122] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A GIS busbar electrical contact defect diagnosis method integrating magnetic field and current characteristics, characterized in that: The steps include: Obtain the GIS busbar conductor current and casing circulating current waveforms and the casing space magnetic field distribution under different electrical contact defects; The fault characteristic current is extracted from the conductor current and the shell circulating current waveform by using an inverse difference algorithm, and the spatial magnetic field distribution of the shell is time-embedded by using a spectrum coding to obtain characteristic current signals and magnetic field time series data respectively; The characteristic current signal and the magnetic field time series data are used as a comprehensive feature set, and a deep learning neural network is used to classify and train the comprehensive feature set, a GIS busbar electrical contact defect diagnosis model is constructed, and the GIS busbar electrical contact defect diagnosis model is used to perform GIS busbar electrical contact defect diagnosis.

2. The GIS busbar electrical contact defect diagnosis method integrating magnetic field and current characteristics according to claim 1 is characterized in that: Obtain the GIS busbar conductor current and shell circulating current waveforms and shell space magnetic field distribution under different electrical contact defects, including: A current sensor is installed on the GIS bus conductor to monitor the conductor current waveform in real time through the current sensor; Arrange a Hall sensor array on the GIS busbar housing to measure the housing circulating current waveform and spatial magnetic field distribution; The current waveform and magnetic field data under different electrical contact defect states are recorded to obtain the conductor current and shell circulating current waveforms and the shell space magnetic field distribution.

3. The GIS busbar electrical contact defect diagnosis method integrating magnetic field and current characteristics according to claim 1 is characterized in that: The steps of extracting fault characteristic current from the conductor current and the casing circulating current waveform using an inverse differential algorithm include: Filter the collected conductor current and shell circulating current waveforms; According to the determined differential step length, an inverse differential calculation is performed on the preprocessed signal; Compare the result obtained by differential calculation with the set threshold. If the absolute value of the differential result is greater than the threshold, it is determined that the signal change at this point may be related to an electrical contact defect, and the point and its related information are recorded. When the differential result is less than the threshold, it is considered that the signal change at this point is normal and is not included in the scope of fault feature analysis. The recorded signal points that may be related to the fault are screened, the screened signals are integrated, and the characteristic current signals that can accurately reflect the electrical contact defects are extracted.

4. The GIS busbar electrical contact defect diagnosis method integrating magnetic field and current characteristics according to claim 2 is characterized in that: The time embedding process of the outer shell space magnetic field distribution is performed by atlas coding, including: According to the shell space magnetic field distribution data measured by the Hall sensor array, a spatial magnetic field map is constructed with spatial position as coordinates and magnetic field strength and direction as attributes; Converting the spatial magnetic field spectrum into a time series code according to a preset coding rule; The generated time series code is verified, and if it satisfies the characteristics of the spatial magnetic field distribution and the time variation information, the magnetic field time series data is obtained.

5. A GIS busbar electrical contact defect diagnosis device integrating magnetic field and current characteristics, characterized in that: include: Data acquisition module, data processing module and model building and diagnosis module; The data acquisition module is used to obtain the GIS busbar conductor current and shell circulating current waveforms and the shell space magnetic field distribution under different electrical contact defects; The data processing module is used to extract fault characteristic current from the conductor current and shell circulating current waveforms using an inverse difference algorithm, and to perform time embedding processing on the shell spatial magnetic field distribution through spectrum coding to obtain characteristic current signals and magnetic field time series data respectively; The characteristic current signal and the magnetic field time series data are used as a comprehensive feature set, and a deep learning neural network is used to classify and train the comprehensive feature set, a GIS busbar electrical contact defect diagnosis model is constructed, and the GIS busbar electrical contact defect diagnosis model is used to perform GIS busbar electrical contact defect diagnosis.

6. The GIS busbar electrical contact defect diagnosis device integrating magnetic field and current characteristics according to claim 5 is characterized in that: The data acquisition module includes a current sensor and a Hall sensor array. The data acquisition module acquires the GIS busbar conductor current and shell circulating current waveforms and the shell space magnetic field distribution under different electrical contact defects, including: The current sensor is installed on the GIS bus conductor, and the conductor current waveform is monitored in real time by the current sensor; Arranging the Hall sensor array on the GIS busbar housing to measure the housing circulating current waveform and spatial magnetic field distribution; The current waveform and magnetic field data under different electrical contact defect states are recorded to obtain the conductor current and shell circulating current waveforms and the shell space magnetic field distribution.

7. The GIS busbar electrical contact defect diagnosis device integrating magnetic field and current characteristics according to claim 5 is characterized in that: The data processing module includes a reverse differential algorithm module, and the data processing module extracts fault characteristic current from the conductor current and the shell circulating current waveform through the reverse differential algorithm module, including: Filter the collected conductor current and shell circulating current waveforms; According to the determined differential step length, an inverse differential calculation is performed on the preprocessed signal; Compare the result obtained by differential calculation with the set threshold. If the absolute value of the differential result is greater than the threshold, it is determined that the signal change at this point may be related to an electrical contact defect, and the point and its related information are recorded. When the differential result is less than the threshold, it is considered that the signal change at this point is normal and is not included in the scope of fault feature analysis. The recorded signal points that may be related to the fault are screened, the screened signals are integrated, and the characteristic current signals that can accurately reflect the electrical contact defects are extracted.

8. The GIS busbar electrical contact defect diagnosis device integrating magnetic field and current characteristics according to claim 6 is characterized in that: The data processing module further includes a spectrum encoding module, and the data processing module performs time embedding processing on the magnetic field distribution of the shell space through the spectrum encoding module, including: According to the shell space magnetic field distribution data measured by the Hall sensor array, a spatial magnetic field map is constructed with spatial position as coordinates and magnetic field strength and direction as attributes; Converting the spatial magnetic field spectrum into a time series code according to a preset coding rule; The generated time series code is verified, and if it satisfies the characteristics of the spatial magnetic field distribution and the time variation information, the magnetic field time series data is obtained.

9. A computer device, characterized in that: The device comprises a processor and a memory: The memory is used to store a computer program and send instructions of the computer program to the processor; The processor executes a GIS busbar electrical contact defect diagnosis method integrating magnetic field-current characteristics as described in any one of claims 1-4 according to the instructions of the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, it implements a GIS busbar electrical contact defect diagnosis method integrating magnetic field-current characteristics as described in any one of claims 1-4.

Images