A GIS busbar electric contact magnetic field-current fusion detection method and related device

Abstract

The present invention provides a GIS busbar electric contact magnetic field-current fusion detection method and related devices, including obtaining the magnetic field distribution data of the busbar shell and the difference between the busbar current and the conductor circulating current under the GIS busbar operation state; using super-resolution reconstruction technology to perform fine processing on the collected shell magnetic field distribution data and current difference data; using the shell magnetic field and differential current after super-resolution reconstruction as input, and using the deep learning architecture to train and construct a deep learning agent model; fitting and reconstructing the internal magnetic field of the GIS busbar based on the constructed deep learning agent model; using the reconstructed GIS busbar internal magnetic field to determine the degree of magnetic field distortion around the contact, and realizing the detection and analysis of the GIS busbar electrical contact state according to the degree of distortion. The present invention can realize effective detection and analysis of the GIS busbar electrical contact state through magnetic field-current fusion detection, and ensure the safe and stable operation of the equipment.

Description

Technical Field

[0001] The invention belongs to the technical field of high-voltage power transmission and transformation, and in particular relates to a GIS busbar electric contact magnetic field-current fusion detection method and related devices. Background Art

[0002] In modern power systems, gas insulated switchgear (GIS) is widely used in high-voltage power transmission and distribution networks due to its excellent insulation performance and compact structure. The electrical contact state of the GIS busbar is directly related to the reliability and safety of the equipment. Poor electrical contact may cause overheating, arcing, and even equipment failure, thus affecting the stability of the entire power system. Therefore, effective detection and monitoring of the electrical contact state of the GIS busbar is the key to ensuring the safe operation of the power system.

[0003] Traditional GIS busbar electrical contact status detection methods mainly include loop resistance test method, temperature-vibration monitoring method, partial discharge detection method and gas decomposition detection method, but these methods are often difficult to fully reflect the actual changes in the electrical contact status. With the development of magnetic field and current measurement technology, magnetic field-current fusion detection methods have attracted attention because they can provide more comprehensive electrical contact status information. Previous work at home and abroad focused on two aspects: diagnosing internal contact and bolt connection defects based on changes in the internal space tangential magnetic field; and locating breakdown faults based on changes in the axial magnetic field of the shell. The above two methods do not realize the influence of spatial magnetic field attenuation and external background interference noise, and the nonlinear characterization ability of internal defects is insufficient. Therefore, a method that introduces transient current and spatial magnetic field variables and adopts multimodal fusion deep learning method is invented, which is of great significance to improving the operating reliability and safety of GIS equipment. Summary of the invention

[0004] In view of this, the present invention aims to overcome the defects of the above-mentioned technology and provide a GIS busbar electrical contact magnetic field-current fusion detection method and related devices.

[0005] In order to achieve the above object, the technical solution provided by the present invention is as follows:

[0006] In a first aspect, the present invention provides a GIS busbar electric contact magnetic field-current fusion detection method, comprising the following steps:

[0007] Obtain the magnetic field distribution data of the busbar casing and the difference between the busbar current and the conductor circulating current when the GIS busbar is in operation;

[0008] Using super-resolution reconstruction technology, the collected magnetic field distribution data and differences are processed in a refined manner;

[0009] The super-resolution reconstructed magnetic field distribution data and difference values ​​are used as input, and a deep learning agent model is trained and constructed with the help of a deep learning architecture;

[0010] Based on the constructed deep learning agent model, the magnetic field inside the GIS busbar is fitted and reconstructed;

[0011] The reconstructed internal magnetic field of the GIS bus is used to determine the degree of magnetic field distortion around the contacts, and the electrical contact state of the GIS bus is detected and analyzed based on the degree of distortion.

[0012] Furthermore, the magnetic field distribution data of the busbar casing and the difference between the busbar current and the conductor circulating current are obtained when the GIS busbar is in operation, including:

[0013] A single-axis magnetic sensor array is evenly arranged circumferentially on the magnetic ring of the GIS busbar housing to obtain the magnetic field distribution of the GIS busbar housing, thereby obtaining magnetic field distribution data;

[0014] A three-axis magnetic sensor array is arranged at equal intervals between adjacent single-axis magnetic sensors on the same magnetic ring to measure and obtain the GIS bus current and conductor circulating current, thereby calculating the difference.

[0015] Furthermore, when training and building the deep learning agent model, the input data is trained through the deep learning architecture, and the model parameters are adjusted during the training process to optimize the model performance, and finally the nonlinear relationship in the GIS busbar magnetic field and current is learned.

[0016] Furthermore, the magnetic field inside the GIS busbar is fitted and reconstructed based on the constructed deep learning agent model, including:

[0017] In the constructed deep learning agent model, the Pisa law of magnetic field distribution is introduced to calculate the magnetic field based on the current distribution of the GIS bus. At the same time, combined with the circuit topology constraints, it is ensured that the current distribution and path conform to the actual circuit connection method, thereby realizing the fitting reconstruction of the internal magnetic field of the GIS bus.

[0018] In a second aspect, the present invention provides a GIS busbar electric contact magnetic field-current fusion detection device, comprising:

[0019] The data acquisition module is used to obtain the magnetic field distribution data of the busbar casing and the difference between the busbar current and the conductor circulating current when the GIS busbar is in operation;

[0020] The data reconstruction module is used to refine the collected magnetic field distribution data and differences using super-resolution reconstruction technology;

[0021] A model building module is used to take the super-resolution reconstructed magnetic field distribution data and difference as input, and train and build a deep learning agent model with the help of a deep learning architecture;

[0022] The magnetic field reconstruction module is used to fit and reconstruct the magnetic field inside the GIS busbar based on the constructed deep learning agent model;

[0023] The contact detection module is used to determine the degree of magnetic field distortion around the contact using the reconstructed internal magnetic field of the GIS busbar, and to detect and analyze the electrical contact state of the GIS busbar based on the degree of distortion.

[0024] Furthermore, the magnetic field distribution data of the busbar casing and the difference between the busbar current and the conductor circulating current are obtained when the GIS busbar is in operation, including:

[0025] A single-axis magnetic sensor array is evenly arranged circumferentially on the magnetic ring of the GIS busbar housing to obtain the magnetic field distribution of the GIS busbar housing, thereby obtaining magnetic field distribution data;

[0026] A three-axis magnetic sensor array is arranged at equal intervals between adjacent single-axis magnetic sensors on the same magnetic ring to measure and obtain the GIS bus current and conductor circulating current, thereby calculating the difference.

[0027] Furthermore, when training and building the deep learning agent model, the input data is trained through the deep learning architecture, and the model parameters are adjusted during the training process to optimize the model performance, and finally the nonlinear relationship in the GIS busbar magnetic field and current is learned.

[0028] Furthermore, the magnetic field inside the GIS busbar is fitted and reconstructed based on the constructed deep learning agent model, including:

[0029] In the constructed deep learning agent model, the Pisa law of magnetic field distribution is introduced to calculate the magnetic field based on the current distribution of the GIS bus. At the same time, combined with the circuit topology constraints, it is ensured that the current distribution and path conform to the actual circuit connection method, thereby realizing the fitting reconstruction of the internal magnetic field of the GIS bus.

[0030] In a third aspect, the present invention provides a computer device, the device comprising a processor and a memory:

[0031] The memory is used to store a computer program and send instructions of the computer program to the processor;

[0032] The processor executes a GIS busbar electric contact magnetic field-current fusion detection method as described in the first aspect according to the instructions of the computer program.

[0033] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the computer program implements a GIS busbar electrical contact magnetic field-current fusion detection method as described in the first aspect.

[0034] In summary, the present invention provides a GIS busbar electrical contact magnetic field-current fusion detection method, including obtaining the magnetic field distribution data of the busbar shell and the difference between the busbar current and the conductor circulating current under the GIS busbar operation state; using super-resolution reconstruction technology to perform fine processing on the collected shell magnetic field distribution data and current difference data; using the shell magnetic field and differential current after super-resolution reconstruction as input, with the help of deep learning architecture, training and constructing a deep learning agent model; fitting and reconstructing the internal magnetic field of the GIS busbar based on the constructed deep learning agent model; using the reconstructed GIS busbar internal magnetic field to determine the degree of magnetic field distortion around the contact, and realizing the detection and analysis of the GIS busbar electrical contact state according to the degree of distortion. The present invention can realize effective detection and analysis of the GIS busbar electrical contact state through magnetic field-current fusion detection, and ensure the safe and stable operation of the equipment.

[0035] The present invention also provides a GIS busbar electric contact magnetic field-current fusion detection device, computer equipment and computer-readable storage medium, which have similar effects to the above method when implemented and will not be described in detail here. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. 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 creative work.

[0037] Figure 1 A flow chart of a GIS busbar electric contact magnetic field-current fusion detection method provided by an embodiment of the present invention;

[0038] Figure 2 A wiring schematic diagram of a GIS busbar electric contact magnetic field-current fusion detection device provided in an embodiment of the present invention;

[0039] Figure 3 A block diagram of a computer device provided in an embodiment of the present invention.

[0040] In the attached figure: 1-GIS busbar to be tested, 2-single-axis magnetic sensor array, 3-three-axis magnetic sensor array, 4-super-resolution reconstruction module, 5-deep learning module, 6-magnetic field fitting and reconstruction module, 7-electrical contact state detection and analysis module. DETAILED DESCRIPTION

[0041] In order to make the purpose, 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 creative work are within the scope of protection of the present invention.

[0042] See also Figure 1 The embodiment of the present invention provides a GIS busbar electric contact magnetic field-current fusion detection method, comprising the following steps:

[0043] S1: Obtain the magnetic field distribution data of the busbar casing and the difference between the busbar current and the conductor circulating current when the GIS busbar is in operation.

[0044] It should be noted that the magnetic field distribution data is information describing the strength and direction of the magnetic field in the space around the GIS busbar housing. The busbar current is the current passing through the GIS busbar conductor. The conductor circulating current is the circulating current generated around the GIS busbar conductor due to electromagnetic induction and other reasons.

[0045] This step measures the magnetic field distribution around the busbar casing, and also measures the busbar current and conductor circulating current respectively, and then calculates the difference between the two. The magnetic field distribution data of the busbar casing contains important information about the electromagnetic state of the busbar during operation. Different operating conditions and fault conditions will cause changes in the magnetic field distribution. By obtaining the magnetic field distribution data, basic electromagnetic characteristic information can be provided for subsequent analysis. The difference between the busbar current and the conductor circulating current reflects the abnormality of the current distribution inside the busbar, and is of great reference value for judging the electrical contact state of the busbar. For example, when the electrical contact is poor, the current distribution may change, which in turn affects the difference between the busbar current and the conductor circulating current.

[0046] S2: Use super-resolution reconstruction technology to refine the collected magnetic field distribution data and differences.

[0047] It should be noted that super-resolution reconstruction technology is a signal processing technology that can recover high-resolution detail information from low-resolution images or data, thereby improving the resolution and quality of the data.

[0048] This step uses super-resolution reconstruction technology to interpolate, denoise, and enhance edges of low-resolution data to generate higher-resolution data.

[0049] S3: Use the super-resolution reconstructed magnetic field distribution data and differences as input, and use the deep learning architecture to train and build a deep learning agent model.

[0050] It should be noted that deep learning architecture is a series of complex model structures based on artificial neural networks, such as convolutional neural networks (CNN), recurrent neural networks (RNN), etc., which can automatically learn features and patterns from large amounts of data.

[0051] In this step, we first select a suitable deep learning architecture, such as a convolutional neural network (CNN). CNN is suitable for processing data with spatial structures, such as magnetic field distribution data. It extracts features and transforms input data through structures such as convolutional layers, pooling layers, and fully connected layers.

[0052] Then, the super-resolution reconstructed shell magnetic field data and differential current data are used as input samples, and corresponding label data (e.g., known and accurate busbar internal magnetic field distribution or electrical contact status information) are prepared.

[0053] The deep learning model is trained using the back-propagation algorithm and optimizers (such as stochastic gradient descent SGD, adaptive moment estimation Adam, etc.). During the training process, the model calculates the output results based on the input data and compares them with the label data. The error gradient is calculated through the back-propagation algorithm, and the model parameters (such as weights and biases) are updated so that the output of the model gradually approaches the real internal state of the busbar.

[0054] After multiple iterations of training, when the performance of the model (such as loss function value, accuracy, etc.) reaches certain requirements, the model training is considered complete, and a deep learning proxy model is constructed.

[0055] S4: Fit and reconstruct the internal magnetic field of the GIS bus based on the constructed deep learning agent model.

[0056] It should be noted that fitting reconstruction refers to obtaining the estimated value of the magnetic field inside the GIS busbar through calculation and reasoning based on the existing model and input data, making it as close as possible to the actual magnetic field distribution.

[0057] In this step, the shell magnetic field data and differential current data collected in real time and reconstructed with super resolution are input into the constructed deep learning agent model.

[0058] The model processes and analyzes the input data according to the features and patterns it has learned, and calculates the corresponding output results through the internal neural network structure. The output results are the fitting and reconstruction results of the magnetic field distribution inside the GIS busbar.

[0059] S5: The reconstructed internal magnetic field of the GIS bus is used to determine the degree of magnetic field distortion around the contact, and the electrical contact state of the GIS bus is detected and analyzed based on the degree of distortion.

[0060] It should be noted that in GIS busbars, contacts are key components for achieving electrical connection. When the electrical contact state of the contacts changes (such as increased contact resistance, poor contact, etc.), the magnetic field distribution around the contacts will deviate from the normal state. This deviation is called magnetic field distortion around the contacts. The degree of magnetic field distortion can be measured by some characteristic parameters (such as the change in magnetic field intensity, the change in magnetic field direction, etc.).

[0061] This step first determines the position of the contact inside the GIS busbar, and extracts the magnetic field information of the area around the contact based on the reconstructed magnetic field distribution data inside the GIS busbar.

[0062] Then, the magnetic field information around the contact is compared with the magnetic field information under normal operation. The degree of magnetic field distortion can be quantitatively determined by calculating the difference in magnetic field strength, the angle between magnetic field directions, etc.

[0063] Finally, the electrical contact state of the GIS busbar is determined based on the pre-established relationship between the degree of magnetic field distortion and the electrical contact state (which can be obtained through experimental data or theoretical analysis). For example, when the degree of magnetic field distortion exceeds a certain threshold, it is considered that the contact has problems such as poor electrical contact.

[0064] This embodiment provides a GIS busbar electrical contact magnetic field-current fusion detection method, which fuses the magnetic field distribution data of the GIS busbar shell with the difference data of the busbar current and the conductor circulating current, making full use of the information contained in the two different types of data. The magnetic field data reflects the electromagnetic state of the busbar, while the current difference data reflects the abnormality of the current distribution. The combination of the two can more comprehensively and accurately describe the operating state of the GIS busbar, and has higher reliability than the single data analysis method. At the same time, the deep learning architecture is used to build an agent model to realize the automatic learning and prediction of the complex electromagnetic state inside the GIS busbar. Traditional GIS busbar electrical contact state detection methods usually rely on empirical formulas or simple mathematical models, which are difficult to accurately capture the nonlinear relationships and complex changes inside the busbar. The deep learning model has a strong nonlinear mapping capability, which can automatically learn the features and patterns in the data, improve the accuracy and adaptability of the detection, and provide a new and more effective method for GIS busbar state monitoring.

[0065] In one embodiment, obtaining the magnetic field distribution data of the busbar housing and the difference between the busbar current and the conductor circulating current when the GIS busbar is in operation includes:

[0066] Uniaxial magnetic sensor arrays are evenly arranged circumferentially on the magnetic ring of the GIS busbar housing to obtain the magnetic field distribution of the GIS busbar housing, thereby obtaining the magnetic field distribution data;

[0067] A three-axis magnetic sensor array is arranged at equal intervals between adjacent single-axis magnetic sensors on the same magnetic ring to measure and obtain the GIS bus current and conductor circulating current, thereby calculating the difference.

[0068] In this embodiment, to obtain the magnetic field distribution of the busbar housing, the characteristic of the uniaxial magnetic sensor array being evenly arranged circumferentially on the magnetic ring is utilized, and each uniaxial magnetic sensor measures the magnetic field component in a certain direction at its location. By processing and analyzing the magnetic field component data at these different locations, combined with the position information of the sensor, the magnetic field distribution around the busbar housing can be inferred.

[0069] For measuring bus current and conductor circulating current, a three-axis magnetic sensor array is arranged at equal intervals next to the single-axis magnetic sensor on the same magnetic ring. The three-axis magnetic sensor can measure the spatial magnetic field vector, and the magnetic field generated by the bus current and conductor circulating current will show specific vector characteristics at this position. By analyzing and processing the magnetic field vector data measured by the three-axis magnetic sensor, combined with relevant electromagnetic principles (such as Ampere's loop theorem, etc.), the magnitude of the bus current and conductor circulating current can be calculated.

[0070] The arrangement of the single-axis magnetic sensor array can obtain the magnetic field information of a certain direction around the busbar shell in a relatively comprehensive manner, providing basic data for analyzing the magnetic field state during busbar operation. By analyzing the magnetic field distribution, the changes in the magnetic field around the busbar can be understood, which is of great significance for judging the operating state of the busbar and possible problems (such as magnetic field anomalies caused by partial discharge, etc.).

[0071] The three-axis magnetic sensor array can accurately measure the magnetic field vector generated by the bus current and the conductor circulating current, and then calculate the bus current and the conductor circulating current. The bus current reflects the load condition of the bus, while the change of the conductor circulating current can reflect the operating status and shielding condition of the conductor inside the bus. By obtaining the difference between these two parameters, the abnormal current distribution inside the bus can be further analyzed, providing key information for subsequent fault diagnosis.

[0072] In one embodiment, when training and building a deep learning agent model, the input data is trained through the deep learning architecture, and the model parameters are adjusted during the training process to optimize the model performance, and finally the complex nonlinear relationship between the GIS busbar magnetic field and current is learned.

[0073] In this embodiment, the input data is input into the selected deep learning architecture, and the model calculates and processes the input data according to the current parameters to obtain the corresponding output results. The output results of the model are compared with the pre-set label data (i.e., the known accurate magnetic field distribution inside the GIS bus, electrical contact status and other information), and the loss function value is calculated to measure the difference between the model output and the true value. Using an optimization algorithm (such as stochastic gradient descent SGD, adaptive moment estimation Adam, etc.), the gradient of the parameters is calculated according to the loss function value, and then the model parameters are adjusted in the direction of the gradient so that the loss function value gradually decreases. Repeat the above process, that is, perform multiple iterative training until the performance of the model reaches a satisfactory level, at which time the model has learned the complex nonlinear relationship between the magnetic field and current of the GIS bus.

[0074] In one embodiment, the magnetic field inside the GIS bus is fitted and reconstructed based on the constructed deep learning proxy model, including: introducing the Pisa law of magnetic field distribution in the constructed deep learning proxy model, and calculating the magnetic field according to the current distribution of the GIS bus; and combining the circuit topology constraints to ensure that the current distribution and path conform to the actual circuit connection method, thereby achieving fitting reconstruction of the magnetic field inside the GIS bus.

[0075] In this embodiment, in the deep learning proxy model, the conductor of the GIS bus is decomposed into multiple tiny current elements. According to the Biot-Savart law (i.e., Pisa's law), the magnetic induction intensity generated by each current element at a certain point in space is calculated, and then the total magnetic induction intensity of the point is obtained by vector superposition, thereby calculating the magnetic field distribution inside the entire GIS bus. At the same time, the circuit topology constraints are considered to ensure that the current distribution and path calculated by the model are consistent with the actual circuit connection. For example, the inflow and outflow of current at the node must satisfy Kirchhoff's current law, and the voltage drop in the loop must satisfy Kirchhoff's voltage law. Through such constraints, the calculated current distribution is reasonable, thereby ensuring that the magnetic field distribution calculated based on the current distribution is more in line with reality. Finally, the fitting reconstruction of the magnetic field inside the GIS bus is achieved through the above method, and an estimation result that can reflect the real magnetic field distribution inside the bus is obtained.

[0076] Based on the same inventive concept, the embodiment of the present application also provides a GIS busbar electric contact magnetic field-current fusion detection device for implementing the above-mentioned GIS busbar electric contact magnetic field-current fusion detection method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above-mentioned method, so the specific limitations in the embodiment of a GIS busbar electric contact magnetic field-current fusion detection device provided below can be referred to the above limitations on a GIS busbar electric contact magnetic field-current fusion detection method, and will not be repeated here.

[0077] The embodiment of the present invention further provides a GIS busbar electric contact magnetic field-current fusion detection device, comprising:

[0078] The data acquisition module is used to obtain the magnetic field distribution data of the busbar casing and the difference between the busbar current and the conductor circulating current when the GIS busbar is in operation;

[0079] The data reconstruction module is used to refine the collected magnetic field distribution data and differences using super-resolution reconstruction technology;

[0080] A model building module is used to take the super-resolution reconstructed magnetic field distribution data and difference as input, and train and build a deep learning agent model with the help of a deep learning architecture;

[0081] A magnetic field reconstruction module, used for fitting and reconstructing the magnetic field inside the GIS busbar based on the constructed deep learning agent model;

[0082] The contact detection module is used to determine the degree of magnetic field distortion around the contact using the reconstructed internal magnetic field of the GIS busbar, and to detect and analyze the electrical contact state of the GIS busbar based on the degree of distortion.

[0083] See also Figure 2 Among them, the single-axis magnetic sensor array 2 is responsible for obtaining the magnetic field distribution of the GIS busbar shell; the three-axis magnetic sensor array 3 is responsible for obtaining the difference between the GIS busbar current and the conductor circulating current. The super-resolution reconstruction module 4 is connected to the single-axis magnetic sensor array 2 and is responsible for processing the collected shell magnetic field data to improve the data resolution; the deep learning module 5 is connected to the super-resolution reconstruction module 4 and the three-axis magnetic sensor array 3 and is responsible for constructing a deep learning agent model; the deep learning module 5 is connected to the magnetic field fitting and reconstruction module 6 to realize the fitting reconstruction of the internal magnetic field of the GIS busbar. The magnetic field fitting and reconstruction module 6 is connected to the electrical contact state detection and analysis module 7 and is responsible for the detection and defect diagnosis of the electrical contact state of the GIS busbar.

[0084] Furthermore, the magnetic field distribution data of the busbar casing and the difference between the busbar current and the conductor circulating current are obtained when the GIS busbar is in operation, including:

[0085] A single-axis magnetic sensor array is evenly arranged circumferentially on the magnetic ring of the GIS busbar housing to obtain the magnetic field distribution of the GIS busbar housing, thereby obtaining magnetic field distribution data;

[0086] A three-axis magnetic sensor array is arranged at equal intervals between adjacent single-axis magnetic sensors on the same magnetic ring to measure and obtain the GIS bus current and conductor circulating current, thereby calculating the difference.

[0087] Furthermore, when training and building a deep learning agent model, the input data is trained through the deep learning architecture, and the model parameters are adjusted during the training process to optimize the model performance, and finally the complex nonlinear relationship between the GIS busbar magnetic field and current is learned.

[0088] Furthermore, the magnetic field inside the GIS busbar is fitted and reconstructed based on the constructed deep learning agent model, including:

[0089] In the constructed deep learning agent model, the Pisa law of magnetic field distribution is introduced to calculate the magnetic field based on the current distribution of the GIS bus. At the same time, the circuit topology constraints are combined to ensure that the current distribution and path conform to the actual circuit connection method, thereby realizing the fitting reconstruction of the internal magnetic field of the GIS bus.

[0090] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be 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 in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in 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, which will not be repeated here.

[0091] Reference Figure 3 An embodiment of the present invention further 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 electric contact magnetic field-current fusion detection method as described in any one of the above methods is implemented.

[0092] The computer device may be a desktop computer, a notebook, a PDA, a cloud server or other computing device. The computer device may include, but is not limited to, a processor and a memory. Those skilled in the art will understand that Figure 3 It is only an example of a computer device and does not constitute a limitation of the computer device. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, it may also include input and output devices, network access devices, etc.

[0093] 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) or 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, etc.

[0094] In some embodiments, the memory may be an internal storage unit of the computer device, such as a hard disk 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 disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the computer device. Further, the memory may include both an internal storage unit and an external storage device of the computer device. The memory is used to store an operating system, an application program, a boot loader (BootLoader), 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 to be output.

[0095] 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, a GIS busbar electrical contact magnetic field-current fusion detection method as described in any one of the above methods is implemented.

[0096] In this embodiment, if the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the camera / terminal device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. For example, USB flash drive, mobile hard disk, disk or optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0097] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0098] Those of ordinary skill 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 to be beyond the scope of this application.

[0099] 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 only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, 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.

[0100] 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 the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. 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 embodiments of the present invention.

Claims

1. A GIS busbar electric contact magnetic field-current fusion detection method, characterized in that: The steps include: Obtain the magnetic field distribution data of the busbar casing and the difference between the busbar current and the conductor circulating current when the GIS busbar is in operation; Using super-resolution reconstruction technology, the collected magnetic field distribution data and the difference are refined; Using the magnetic field distribution data reconstructed by super-resolution and the difference as input, training and constructing a deep learning agent model with the help of a deep learning architecture; Fitting and reconstructing the magnetic field inside the GIS busbar based on the constructed deep learning agent model; The reconstructed internal magnetic field of the GIS bus is used to determine the degree of magnetic field distortion around the contacts, and the electrical contact state of the GIS bus is detected and analyzed based on the degree of distortion.

2. The GIS busbar electric contact magnetic field-current fusion detection method according to claim 1 is characterized in that: Obtain the magnetic field distribution data of the busbar casing and the difference between the busbar current and the conductor circulating current when the GIS busbar is in operation, including: Uniaxial magnetic sensor arrays are evenly arranged circumferentially on the magnetic ring of the GIS busbar housing to obtain the magnetic field distribution of the GIS busbar housing, thereby obtaining the magnetic field distribution data; A three-axis magnetic sensor array is arranged at equal intervals between adjacent single-axis magnetic sensors on the same magnetic ring to measure and obtain the GIS bus current and conductor circulating current, thereby calculating the difference.

3. The GIS busbar electric contact magnetic field-current fusion detection method according to claim 1 is characterized in that: When training and building a deep learning agent model, the input data is trained through the deep learning architecture, and the model parameters are adjusted during the training process to optimize the model performance, and finally the nonlinear relationship between the GIS busbar magnetic field and current is learned.

4. The GIS busbar electric contact magnetic field-current fusion detection method according to claim 1 is characterized in that: Based on the constructed deep learning agent model, the magnetic field inside the GIS bus is fitted and reconstructed, including: In the constructed deep learning agent model, the Pisa law of magnetic field distribution is introduced to calculate the magnetic field based on the current distribution of the GIS bus. At the same time, the circuit topology constraints are combined to ensure that the current distribution and path conform to the actual circuit connection method, thereby realizing the fitting reconstruction of the internal magnetic field of the GIS bus.

5. A GIS busbar electric contact magnetic field-current fusion detection device, characterized in that: include: The data acquisition module is used to obtain the magnetic field distribution data of the busbar casing and the difference between the busbar current and the conductor circulating current when the GIS busbar is in operation; A data reconstruction module, used to perform fine processing on the collected magnetic field distribution data and the difference using super-resolution reconstruction technology; A model building module, used to take the magnetic field distribution data reconstructed by super resolution and the difference as input, and train and build a deep learning agent model with the help of a deep learning architecture; A magnetic field reconstruction module, used for fitting and reconstructing the magnetic field inside the GIS busbar based on the constructed deep learning agent model; The contact detection module is used to determine the degree of magnetic field distortion around the contact using the reconstructed internal magnetic field of the GIS busbar, and to detect and analyze the electrical contact state of the GIS busbar based on the degree of distortion.

6. The GIS busbar electric contact magnetic field-current fusion detection device according to claim 5 is characterized in that: Obtain the magnetic field distribution data of the busbar casing and the difference between the busbar current and the conductor circulating current when the GIS busbar is in operation, including: Uniaxial magnetic sensor arrays are evenly arranged circumferentially on the magnetic ring of the GIS busbar housing to obtain the magnetic field distribution of the GIS busbar housing, thereby obtaining the magnetic field distribution data; A three-axis magnetic sensor array is arranged at equal intervals between adjacent single-axis magnetic sensors on the same magnetic ring to measure and obtain the GIS bus current and conductor circulating current, thereby calculating the difference.

7. The GIS busbar electric contact magnetic field-current fusion detection device according to claim 5 is characterized in that: When training and building a deep learning agent model, the input data is trained through the deep learning architecture, and the model parameters are adjusted during the training process to optimize the model performance, and finally the nonlinear relationship between the GIS busbar magnetic field and current is learned.

8. The GIS busbar electric contact magnetic field-current fusion detection device according to claim 5 is characterized in that: Based on the constructed deep learning agent model, the magnetic field inside the GIS bus is fitted and reconstructed, including: In the constructed deep learning agent model, the Pisa law of magnetic field distribution is introduced to calculate the magnetic field based on the current distribution of the GIS bus. At the same time, the circuit topology constraints are combined to ensure that the current distribution and path conform to the actual circuit connection method, thereby realizing the fitting reconstruction of the internal magnetic field of the GIS bus.

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 electric contact magnetic field-current fusion detection method 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 a processor, a GIS busbar electric contact magnetic field-current fusion detection method as described in any one of claims 1-4 is implemented.

Images