GIS (Geographic Information System) metal foreign matter identification method and device based on photon-phase technology

Abstract

The invention relates to a GIS (Geographic Information System) metal foreign matter identification method and device based on a photon-phase technology. The photon counting detection system comprises a photon counting platform, a partial discharge sensor, a partial discharge-free alternating current excitation source, a data acquisition piece connected with the photon counting platform and the partial discharge sensor, and a data processing piece connected with the data acquisition piece which are sequentially connected in parallel. The method comprises the following steps: acquiring photon pulse data of the current metal foreign matter by using the photon counting detection system; performing phase analysis on the photon pulse data of the current metal foreign body to obtain a photon counting phase analysis spectrogram of the current metal foreign body; and extracting characteristic parameters of the current metal foreign matter based on the photon counting phase analysis spectrogram, and inputting the characteristic parameters of the current metal foreign matter into a pre-trained metal foreign matter identification model to obtain the type of the current metal foreign matter. Therefore, the problem that related technologies are greatly influenced by the environment is solved, and accurate recognition of unknown metal foreign bodies is achieved.

Description

Technical Field

[0001] The present application relates to the technical field of operation and maintenance of high-voltage AC power transmission equipment, and in particular to a method and device for identifying metal foreign bodies in a GIS (Gas Insulated Switchgear) based on photon-phase technology. Background Art

[0002] Gas-insulated switchgear has been widely used in power systems due to its advantages of small footprint, environmental friendliness, and high safety. It is a key device in today's power transmission and distribution network system. However, during the production, transportation, installation, and operation of GIS, due to mechanical vibration, collision, or thermal expansion and contraction friction, metal foreign matter will inevitably be generated. After being charged, free metal foreign matter moves freely in the cavity under the influence of electric field force, gravity, and other factors. Especially when metal foreign matter is adsorbed on the surface of the basin insulator, it is very easy to induce surface flashover of the insulator, which seriously threatens the stable operation of GIS.

[0003] Most of the existing metal foreign body detection methods, such as pulse current method, ultra-high frequency method, ultrasonic method, etc., detect the current, electromagnetic waves, and ultrasonic waves generated by the local discharge induced by the metal foreign body. However, these methods are greatly affected by environmental noise and it is difficult to detect stationary metal foreign bodies attached to the surface of the insulating basin. In addition, optical detection method, as a new detection method for detecting and analyzing optical signals caused by defects, has the advantages of strong anti-electromagnetic interference, strong insulation and high sensitivity, but its research on metal foreign body detection is still relatively small. In addition, most of the existing research focuses on defect feature analysis and less on state assessment.

[0004] Therefore, it is urgent to study a metal foreign body detection method based on optical methods and establish a diagnostic recognition model in combination with artificial intelligence algorithms to provide new ideas for future research on practical metal foreign body diagnostic technology. Summary of the invention

[0005] The present application provides a GIS metal foreign body identification method and device based on photon-phase technology to solve the problem that the related technology is greatly affected by the environment, and realizes the accurate identification of unknown metal foreign bodies.

[0006] The first aspect of the present application provides a GIS metal foreign body identification method based on photon-phase technology, the method uses a photon counting detection system, the photon counting detection system includes a photon counting platform, a partial discharge sensor, a non-partial discharge AC excitation source, a data acquisition component connected to the photon counting platform and the partial discharge sensor, and a data processing component connected to the data acquisition component, wherein the method includes:

[0007] Using the photon counting detection system to obtain photon pulse data of the current metal foreign matter;

[0008] Performing phase analysis on the photon pulse data of the current metal foreign matter to obtain a photon counting phase analysis spectrum of the current metal foreign matter;

[0009] The characteristic parameters of the current metal foreign object are extracted based on the photon counting phase analysis spectrum of the current metal foreign object, and the characteristic parameters of the current metal foreign object are input into a pre-trained metal foreign object recognition model to obtain the type of the current metal foreign object.

[0010] According to one embodiment of the present application, before the characteristic parameter is input into the pre-trained metal foreign body recognition model, it also includes:

[0011] Using the photon counting detection system to obtain photon pulse data of multiple metal foreign matter samples at multiple voltages;

[0012] Phase analysis is performed on the photon pulse data of the multiple metal foreign matter samples at multiple voltages to obtain a photon counting phase analysis spectrum of each metal foreign matter sample, and characteristic parameters of each metal foreign matter sample are obtained according to the photon counting phase analysis spectrum of each metal foreign matter sample, and the characteristic parameters of each metal foreign matter sample are fitted to obtain a characteristic parameter database;

[0013] The extreme learning machine network is optimized based on a preset improved particle swarm optimization algorithm, and the optimized extreme learning machine network is trained using the characteristic parameter database to obtain the pre-trained metal foreign body recognition model.

[0014] According to an embodiment of the present application, the optimized extreme learning machine network is trained using the characteristic parameter database to obtain the pre-trained metal foreign body recognition model, including:

[0015] The feature parameter data in the feature parameter database is input into the optimized extreme learning machine network for iterative training, and when the number of iterative training of the optimized extreme learning machine network reaches a preset number of iterations, a global optimal solution is determined to construct the pre-trained metal foreign body recognition model based on the global optimal solution.

[0016] According to an embodiment of the present application, performing phase analysis on the photon pulse data of the current metal foreign matter to obtain the photon counting phase analysis spectrum of the current metal foreign matter includes:

[0017] The phase of the power frequency cycle is evenly divided into multiple phase windows;

[0018] Calculate the number of photon pulses in each phase window, and accumulate the number of photon pulses in each phase window to obtain a photon number-phase sequence;

[0019] The photon number-phase sequence is visualized to obtain the photon counting phase analysis spectrum.

[0020] According to one embodiment of the present application, the characteristic parameters include at least one of the total number of photons, mean phase asymmetry, skewness, steepness, and Pearson correlation coefficient.

[0021] According to the GIS metal foreign body identification method based on photon-phase technology in the embodiment of the present application, the photon counting detection system is used to obtain the photon pulse data of the current metal foreign body; the photon pulse data of the current metal foreign body is phase-analyzed to obtain the photon counting phase-analyzed spectrum of the current metal foreign body; the characteristic parameters of the current metal foreign body are extracted based on the photon counting phase-analyzed spectrum, and the characteristic parameters of the current metal foreign body are input into the pre-trained metal foreign body identification model to obtain the type of the current metal foreign body. In this way, the problem that the related technology is greatly affected by the environment is solved, and the accurate identification of unknown metal foreign bodies is achieved.

[0022] The second aspect of the present application provides a GIS metal foreign body identification device based on photon-phase technology, wherein the device uses a photon counting detection system, wherein the photon counting detection system includes a photon counting platform, a partial discharge sensor, a non-partial discharge AC excitation source, a data acquisition component connected to the photon counting platform and the partial discharge sensor, and a data processing component connected to the data acquisition component, wherein the device includes:

[0023] An acquisition module, used to acquire photon pulse data of the current metal foreign matter using the photon counting detection system;

[0024] A phase analysis module, used for performing phase analysis on the photon pulse data of the current metal foreign matter to obtain a photon counting phase analysis spectrum of the current metal foreign matter;

[0025] The identification module is used to extract the characteristic parameters of the current metal foreign matter based on the photon counting phase analysis spectrum of the current metal foreign matter, and input the characteristic parameters of the current metal foreign matter into a pre-trained metal foreign matter identification model to obtain the type of the current metal foreign matter.

[0026] According to one embodiment of the present application, before inputting the characteristic parameter into the pre-trained metal foreign body recognition model, the recognition module is further used to:

[0027] Using the photon counting detection system to obtain photon pulse data of multiple metal foreign matter samples at multiple voltages;

[0028] Phase analysis is performed on the photon pulse data of the multiple metal foreign matter samples at multiple voltages to obtain a photon counting phase analysis spectrum of each metal foreign matter sample, and characteristic parameters of each metal foreign matter sample are obtained according to the photon counting phase analysis spectrum of each metal foreign matter sample, and the characteristic parameters of each metal foreign matter sample are fitted to obtain a characteristic parameter database;

[0029] The extreme learning machine network is optimized based on a preset improved particle swarm optimization algorithm, and the optimized extreme learning machine network is trained using the characteristic parameter database to obtain the pre-trained metal foreign body recognition model.

[0030] According to one embodiment of the present application, the identification module is used to:

[0031] The feature parameter data in the feature parameter database is input into the optimized extreme learning machine network for iterative training, and when the number of iterative training of the optimized extreme learning machine network reaches a preset number of iterations, a global optimal solution is determined to construct the pre-trained metal foreign body recognition model based on the global optimal solution.

[0032] According to one embodiment of the present application, the phase resolution module is used to:

[0033] The phase of the power frequency cycle is evenly divided into multiple phase windows;

[0034] Calculate the number of photon pulses in each phase window, and accumulate the number of photon pulses in each phase window to obtain a photon number-phase sequence;

[0035] The photon number-phase sequence is visualized to obtain the photon counting phase analysis spectrum.

[0036] According to one embodiment of the present application, the characteristic parameters include at least one of the total number of photons, mean phase asymmetry, skewness, steepness, and Pearson correlation coefficient.

[0037] According to the GIS metal foreign body identification device based on photon-phase technology in the embodiment of the present application, the photon counting detection system is used to obtain the photon pulse data of the current metal foreign body; the photon pulse data of the current metal foreign body is phase analyzed to obtain the photon counting phase analysis spectrum of the current metal foreign body; the characteristic parameters of the current metal foreign body are extracted based on the photon counting phase analysis spectrum, and the characteristic parameters of the current metal foreign body are input into the pre-trained metal foreign body identification model to obtain the type of the current metal foreign body. In this way, the problem that the related technology is greatly affected by the environment is solved, and the accurate identification of unknown metal foreign bodies is achieved.

[0038] The third aspect of the present application provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the GIS metal foreign body identification method based on photon-phase technology as described in the above embodiment.

[0039] The fourth aspect of the present application provides a computer-readable storage medium on which a computer program is stored. The program is executed by a processor to implement the GIS metal foreign body identification method based on photon-phase technology as described in the above embodiment.

[0040] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0042] Figure 1 is a schematic structural diagram of a photon counting detection system according to an embodiment of the present application;

[0043] Figure 2 A flowchart of a GIS metal foreign body identification method based on photon-phase technology provided according to an embodiment of the present application;

[0044] Figure 3 A schematic diagram of the structure of a GIS linear particle defect model according to an embodiment of the present application;

[0045] Figure 4 It is a schematic diagram of the structure of the traditional ELM network;

[0046] Figure 5 The present invention is a schematic diagram of a construction process of a metal foreign body recognition model based on an improved PSO (Particle Swarm Optimization)-ELM (Extreme Learning Machine) according to an embodiment of the present application;

[0047] Figure 6 This is a schematic diagram of PRPC spectra of aluminum wires of different lengths at 10 kV according to one embodiment of the present application;

[0048] Figure 7 It is a schematic diagram of a characteristic parameter fitting curve according to an embodiment of the present application;

[0049] Figure 8 A schematic diagram of a classification confusion matrix of an improved PSO-ELM model according to an embodiment of the present application;

[0050] Fig. 9 It is a block diagram of a GIS metal foreign body identification device based on photon-phase technology according to an embodiment of the present application;

[0051] Fig.10 Schematic diagram of the structure of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0052] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0053] The following describes a GIS metal foreign body identification method and device based on photon-phase technology according to an embodiment of the present application with reference to the accompanying drawings.

[0054] Before introducing the GIS metal foreign body identification method based on photon-phase technology of the embodiment of the present application, the photon counting detection system used in the GIS metal foreign body identification method based on photon-phase technology of the present application is first introduced.

[0055] Specifically, the photon counting detection system of the present application includes a photon counting platform, a partial discharge sensor, a non-partial discharge AC excitation source, a data acquisition component connected to the photon counting platform and the partial discharge sensor, and a data processing component connected to the data acquisition component.

[0056] The photon counting platform includes a photomultiplier tube (PMT), a GIS model and an airtight device (test chamber), the data acquisition component can be a data acquisition card, and the data processing component can be a computer.

[0057] For example, Figure 1As shown, the photon counting detection system can be composed of a personal computer, a non-partial discharge AC excitation source, a PMT, a GIS model, an airtight device (test chamber), a data acquisition card, a partial discharge sensor and a darkroom. The embodiment of the present application uses a non-partial discharge AC voltage source as a test power source and pressurizes the defective sample placed in the sealed chamber. In order to simulate the normal working environment of GIS, the influence of air pressure on photon release and the pressure resistance of the test chamber are comprehensively considered, and 0.3MPa SF6 gas is filled in the chamber. In order to obtain reliable experimental data, the MPD 800 partial discharge sensor is used to detect the partial discharge starting voltage and monitor the occurrence of PD (Partial Discharge) during the pressurization process. In the experiment, the photon pulse data of a certain metal foreign body, a certain voltage, and a certain time length are measured by PMT.

[0058] The following is an introduction to the GIS metal foreign body identification method based on photon-phase technology using the above-mentioned photon counting detection system proposed in this application.

[0059] Specifically, Figure 2 A schematic flow chart of a GIS metal foreign body identification method based on photon-phase technology provided in an embodiment of the present application.

[0060] like Figure 2 As shown, the GIS metal foreign body identification method based on photon-phase technology includes the following steps:

[0061] In step S201, a photon counting detection system is used to obtain photon pulse data of the current metal foreign matter.

[0062] Optionally, the embodiment of the present application can use aluminum wires of different degrees as the current metal foreign matter, and the defect samples formed are as follows: Figure 3 As shown, the cross-sectional diameter D of the aluminum wire used is 0.4 mm, and the length H can be 2.0 mm, 4.0 mm, 6.0 mm, 8.0 mm, or 10.0 mm.

[0063] Specifically, the embodiment of the present application can place a defective sample containing the current metal foreign matter on a photon counting platform of a photon counting detection system, pressurize the defective sample through the photon counting detection system, and obtain the photon pulse data of the current metal foreign matter through the PMT in the photon counting platform.

[0064] In step S202, phase analysis is performed on the photon pulse data of the current metal foreign matter to obtain a photon counting phase analysis spectrum of the current metal foreign matter.

[0065] Furthermore, in some embodiments, the photon pulse data of the current metal foreign matter is phase-analyzed to obtain a photon counting phase-analyzed spectrum of the current metal foreign matter, including: evenly dividing the phase of the power frequency cycle into multiple phase windows; calculating the number of photon pulses in each phase window, and accumulating the number of photon pulses in each phase window to obtain a photon number-phase sequence; visually displaying the photon number-phase sequence to obtain a photon counting phase-analyzed spectrum.

[0066] Specifically, the embodiment of the present application can divide the phase 360° of a power frequency cycle into N phase windows, wherein the more phase windows there are, the higher the phase time accuracy is, and the more accurate the calculated statistical characteristic parameters are. However, due to the limited data storage and processing capabilities of the hardware system, the number of phase windows cannot be too large. N in the embodiment of the present application can be taken as 360, that is, each 1° is a phase window. Since a single photon pulse signal is a fixed square wave, photon counting can be performed, that is, the photon pulse data collected by the photon counting detection system is accumulated in number on the corresponding phase window to obtain the photon number-phase sequence, and the photon number-phase sequence is visualized to obtain a photon counting phase resolution (PRPC, Phase Resolved Photon Counting) spectrum.

[0067] In step S203, characteristic parameters of the current metal foreign object are extracted based on the photon counting phase analysis spectrum of the current metal foreign object, and the characteristic parameters of the current metal foreign object are input into a pre-trained metal foreign object recognition model to obtain the type of the current metal foreign object.

[0068] It is understandable that in order to establish a mapping relationship between photon pulse data and defect parameters, it is necessary to quantify the change law. Considering the differences in PRPC spectrum in terms of phase distribution, photon value, positive and negative half-cycle differences, etc., the embodiment of the present application extracts 7 statistical parameters of the photon number-phase sequence, as follows:

[0069] 1) The total number of photons Q, that is, the sum of the photon number sequence, reflects the overall characteristics of the PRPC spectrum.

[0070] 2) Mean phase asymmetry ψ, which reflects the difference between the peak phases of the positive and negative half cycles, is calculated as follows:

[0071] ψ=μ + / μ - (1)

[0072] Among them, μ + , μ - Respectively represent the mean phase of the PRPC spectrum in the positive and negative half-cycles of the phase. The general calculation formula is:

[0073]

[0074] Where, ω is the number of phase windows; is the phase of the i-th phase window, indicating the phase window width; p i is the number of photons in the ith phase window of the PRPC spectrum.

[0075] 3) Skewness S k Skewness S k It is used to describe the skew direction and degree of the PRPC spectrum distribution shape. If the skewness is greater than or less than 0, it corresponds to skew to the left or right, and the absolute value of the skewness is positively correlated with the skewness of the spectrum. The specific calculation formula is:

[0076]

[0077] Among them, σ is the standard deviation, and the calculation formula is

[0078]

[0079] 4) Steepness K u The steepness can reflect the protrusion of the graph shape. When the steepness is 0, the PRPC graph profile is consistent with the normal distribution curve; when the steepness is greater than 0, it means that the PRPC graph shape distribution is sharper and steeper than the normal distribution; and when the steepness is less than 0, it means that the PRPC graph shape is flatter than the normal distribution. u The definition is:

[0080]

[0081] 5) Pearson correlation coefficient ρ. The Pearson correlation coefficient can measure the similarity of the positive and negative half-cycle shape contours of the PRPC spectrum. The Pearson correlation coefficient value is between 0 and 1. The closer the Pearson correlation coefficient is to 0, the greater the difference between the positive and negative half-cycle shape contours of the PRPC spectrum; the closer the Pearson correlation coefficient is to 1, the more similar the positive and negative half-cycle shape contours of the PRPC spectrum. Among them, the Pearson correlation coefficient ρ is defined as:

[0082]

[0083] Furthermore, the extracted characteristic parameters of the current metal foreign body are input into a pre-trained metal foreign body recognition model, and the pre-trained metal foreign body recognition model performs calculation and reasoning based on the input characteristic parameters to output the type of the current metal foreign body.

[0084] Furthermore, in some embodiments, before inputting the characteristic parameters into the pre-trained metal foreign body recognition model, it also includes: using a photon counting detection system to obtain photon pulse data of multiple metal foreign body samples at multiple voltages; performing phase analysis on the photon pulse data of multiple metal foreign body samples at multiple voltages to obtain a photon counting phase analysis spectrum of each metal foreign body sample, and obtaining characteristic parameters of each metal foreign body sample based on the photon counting phase analysis spectrum of each metal foreign body sample, and fitting the characteristic parameters of each metal foreign body sample to obtain a characteristic parameter database; optimizing the extreme learning machine network based on a preset improved particle swarm optimization algorithm, and training the optimized extreme learning machine network using the characteristic parameter database to obtain a pre-trained metal foreign body recognition model.

[0085] The plurality of metal foreign body samples may be aluminum wires of different lengths. For example, the plurality of metal foreign body samples may be aluminum wires with lengths of 2.0 mm, 4.0 mm, 6.0 mm, 8.0 mm, and 10.0 mm, respectively.

[0086] Specifically, before inputting the characteristic parameters into the pre-trained metal foreign body recognition model, the embodiment of the present application needs to construct a metal foreign body recognition model. First, similar to the above-mentioned step of using the photon counting detection system to obtain the photon pulse data of the current metal foreign body, the photon counting detection system is used to test multiple metal foreign body samples at different voltages, thereby obtaining the photon pulse data of multiple metal foreign body samples at multiple voltages.

[0087] Furthermore, similar to the above-mentioned step of performing phase analysis on the photon pulse data of the current metal foreign object to obtain the photon counting phase analysis spectrum of the current metal foreign object, phase analysis is performed on the photon pulse data of multiple metal foreign object samples at multiple voltages to obtain the photon counting phase analysis spectrum of each metal foreign object sample, and based on the photon counting phase analysis spectrum of each metal foreign object sample, the characteristic parameters of each metal foreign object sample, namely, the total number of photons, mean phase asymmetry, skewness, steepness and Pearson correlation coefficient, are obtained.

[0088] It is understandable that effective metal foreign body diagnosis requires a huge database for training. If the characteristic parameter data corresponding to metal foreign bodies of different types and sizes are obtained only through experiments, the workload associated with developing the database will be very huge. Therefore, for quantities with functional relationships, such as metal foreign body size and PRPC characteristic parameters, after obtaining a limited number of data points through experiments, the relationship between the metal foreign body size and the PRPC characteristic parameters can be curve-fitted to obtain the corresponding functional relationship, thereby generating a characteristic parameter database of infinite size in theory.

[0089] Furthermore, the embodiment of the present application can classify metal foreign bodies according to the obtained photon information, for example, classify the size of metal foreign bodies according to the total number of photons. Furthermore, the intelligent algorithm used in the embodiment of the present application is an improved PSO-ELM. The traditional ELM network is as follows: Figure 4 As shown in FIG. 1 , the ELM model is composed of an input layer, a hidden layer, and an output layer, and only the number of hidden layer nodes l and the activation function g(x) need to be set to obtain a unique optimal solution. However, if the parameters l and the function g(x) are selected manually, the ELM model effect is often not guaranteed to be optimal. Therefore, the embodiment of the present application introduces an improved particle swarm optimization algorithm (PSO) to optimize the parameters of the ELM. In the particle swarm optimization algorithm, particles represent possible solutions to the optimization problem, and speed is used to represent the optimal solution. Location and fitness It represents the state of the i-th particle in the solution space after the k-th iteration, and is updated for the k+1th iteration through equations (8) and (9) until the stopping condition is met and the global optimal solution is reached.

[0090]

[0091] in, is the velocity of the ith particle in the solution space after the k+1th iteration, ω is the inertia weight, c1 and c2 are non-negative acceleration factors, r1 and r2 are random numbers between 0 and 1, Represents the global optimal value of particle fitness.

[0092] Furthermore, in order to take into account the convergence ability and optimization efficiency of the algorithm and avoid falling into the local optimum during the iteration process, the embodiment of the present application makes two improvements to the conventional PSO algorithm:

[0093] 1) The fixed inertia weight ω is changed to a linear decrease. That is:

[0094] w k =w start -(w start -w end )*k / k max (5)

[0095] Among them, w k is the inertia weight after the kth iteration, w start 、w end are the initial inertia weight and the final inertia weight in the iteration process, k max is the maximum number of iterations. Therefore, the inertia weight is larger in the early stage, which maintains the global search ability of the algorithm, while the reduction of the inertia weight in the later stage is conducive to improving the optimization accuracy.

[0096] 2) Introduce particle mutation. In each iteration of the particle, the particle state is reinitialized with a certain probability, and the spatial range of the particle group is expanded, thereby increasing the probability of finding a better value. Specifically, for particle i after the kth iteration, a random number q between [0,1] is generated. If q is not greater than the mutation probability p, then:

[0097]

[0098] in, is the inertia weight value, X random is the random position in the solution space. Therefore, the ever-shrinking particle population can be expanded through mutation operations, which is conducive to the algorithm achieving global optimization.

[0099] Furthermore, after finding the optimal solution through the improved particle swarm optimization algorithm, the number of hidden layer nodes and activation function of the ELM network are optimized, and the optimized ELM network is trained through the feature parameter database to construct a pre-trained metal foreign body recognition model.

[0100] Furthermore, in some embodiments, the optimized extreme learning machine network is trained using a feature parameter database to obtain a pre-trained metal foreign body recognition model, including: inputting the feature parameter data in the feature parameter database into the optimized extreme learning machine network for iterative training, and when the number of iterative training of the optimized extreme learning machine network reaches a preset number of iterations, determining the global optimal solution, so as to construct a pre-trained metal foreign body recognition model based on the global optimal solution.

[0101] Specifically, the embodiment of the present application optimizes the network parameters of the extreme learning machine based on the constructed feature parameter database and the preset improved particle swarm optimization algorithm, and obtains a solution close to the global optimal solution after a preset number of iterations, that is, the optimal number of hidden layer nodes and the optimal activation function, and constructs a pre-trained metal foreign body recognition model based on the optimized parameters.

[0102] Among them, the construction process of the metal foreign body recognition model based on the improved PSO-ELM is as follows: Figure 5 As shown in the figure, firstly, the photon counting measurement of the defective samples is carried out through the photon counting detection system, the PRPC spectrum is drawn according to the photon pulse data, and the characteristic parameters are extracted based on the PRPC spectrum. The characteristic parameters are fitted to build a database, and the ELM network optimized by the improved PSO algorithm is used to construct an effective metal foreign body recognition model, so as to classify and identify metal foreign bodies in GIS.

[0103] Therefore, in order to achieve high-sensitivity detection and effective identification of GIS metal foreign bodies, the present application firstly builds a photon counting detection system; then, the photon signals of different metal foreign bodies (such as scaled pot insulators with different lengths of aluminum wires attached to the surface) are obtained at different voltages, and characteristic parameters such as total number of photons, skewness, steepness, mean and phase asymmetry are extracted based on the phase-resolved photon counting (PRPC) spectrum, and a large number of characteristic parameter data sets are obtained through sample point fitting curves; finally, a recognition model is constructed based on the improved particle swarm optimization extreme learning machine algorithm and the training data set to intelligently identify metal foreign bodies. Thus, the characteristic parameters based on PRPC effectively reflect the defect-induced photon response characteristics, and the detection accuracy of the recognition model proposed in the present application for linear metal foreign bodies is higher than 90.00%.

[0104] In order to help those skilled in the art to more clearly and intuitively understand the technical effects achieved by the GIS metal foreign body identification method based on photon-phase technology proposed in this application, a detailed description is given below in conjunction with specific embodiments.

[0105] Specifically, the embodiments of the present application are first based on Figure 3 The photon test data of aluminum wire samples of different lengths at 10kV are shown in Figure 1. The PRPC spectra obtained are as follows: Figure 6 As shown, Figure 6 (a) is the PRPC spectrum of an aluminum wire sample with a length of 0 mm at 10 kV. Figure 6 (b) is the PRPC spectrum of an aluminum wire sample with a length of 2.0 mm at 10 kV. Figure 6 (c) is the PRPC spectrum of an aluminum wire sample with a length of 4.0 mm at 10 kV. Figure 6 (d) is the PRPC spectrum of an aluminum wire sample with a length of 6.0 mm at 10 kV. Figure 6 (e) is the PRPC spectrum of an aluminum wire sample with a length of 8.0 mm at 10 kV. Figure 6 (f) is the PRPC spectrum of an aluminum wire sample with a length of 10.0 mm at 10 kV.

[0106] Depend on Figure 6 It can be seen that the PRPC spectrum has a polarity effect similar to that of the PRPD spectrum. Based on the deep mining of the PRPC spectrum, characteristic parameters can be extracted to characterize the defect-induced photon response characteristics.

[0107] Furthermore, characteristic parameters are extracted from the obtained PRPC spectrum, namely the total number of photons Q, the skewness S k , steepness K u , mean phase asymmetry ψ and Pearson correlation coefficient ρ, and perform smoothing spline fitting, such as Figure 6 As shown, a characteristic parameter database related to the length of aluminum wire is constructed.

[0108] Furthermore, the total photon level can indirectly reflect the severity of the damage to insulation caused by aluminum wire particles. In order to more conveniently perform defect classification, the embodiment of the present application roughly divides the severity of aluminum wire particle defects into 4 levels based on the photon counting results. The corresponding relationship between the severity of aluminum wire particle defects and the length of the aluminum wire is shown in Table 1.

[0109] Table 1

[0110] level Length range Label 1 L<2.0mm S1 2 2.0mm≤L<4.0mm S2 3 4.0mm≤L<8.0mm S3 4 L≥8.0mm S4

[0111] Furthermore, using the improved PSO algorithm and Figure 7 The constructed feature parameter database optimizes the ELM network parameters and obtains a solution close to the global optimal solution after 100 iterations, that is, the optimal number of hidden layer nodes is 72 and the optimal activation function is the sin function. The ELM classification model constructed based on the optimized parameters has the following classification results for the test set: Figure 8 As shown, the results show that the characteristic parameters based on PRPC can effectively reflect the defect-induced photon response characteristics, and the detection accuracy of the proposed recognition model for linear metal foreign matter reaches 95%.

[0112] Those skilled in the art can understand that when a metal foreign body exists in the insulation system of a GIS, since the metal foreign body is a conductor, its presence will inevitably cause electric field distortion and induce ionization and luminescence of the insulating medium. The embodiment of the present application detects the optical signal of the metal foreign body, and combines the photon-phase technology to draw a photon counting phase analysis spectrum, extracts its characteristic parameters to reflect the characteristics of the metal foreign body, and uses the extreme learning machine network optimized by the improved particle swarm optimization algorithm and the collected characteristic data set for training to obtain a metal foreign body diagnosis model to identify unknown metal foreign bodies.

[0113] According to the GIS metal foreign body identification method based on photon-phase technology in the embodiment of the present application, the photon counting detection system is used to obtain the photon pulse data of the current metal foreign body; the photon pulse data of the current metal foreign body is phase-analyzed to obtain the photon counting phase-analyzed spectrum of the current metal foreign body; the characteristic parameters of the current metal foreign body are extracted based on the photon counting phase-analyzed spectrum, and the characteristic parameters of the current metal foreign body are input into the pre-trained metal foreign body identification model to obtain the type of the current metal foreign body. In this way, the problem that the related technology is greatly affected by the environment is solved, and the accurate identification of unknown metal foreign bodies is achieved.

[0114] Next, the GIS metal foreign body identification device based on photon-phase technology proposed in an embodiment of the present application is described with reference to the accompanying drawings.

[0115] Fig. 9 It is a block diagram of a GIS metal foreign body identification device based on photon-phase technology according to an embodiment of the present application.

[0116] In this embodiment, the device utilizes a photon counting detection system, which includes a photon counting platform, a partial discharge sensor, a non-partial discharge AC excitation source, a data acquisition component connected to the photon counting platform and the partial discharge sensor, and a data processing component connected to the data acquisition component.

[0117] like Fig. 9 As shown, the GIS metal foreign body identification device 10 based on photon-phase technology includes: an acquisition module 100, a phase analysis module 200 and an identification module 300.

[0118] Among them, the acquisition module 100 is used to obtain the photon pulse data of the current metal foreign object using a photon counting detection system; the phase analysis module 200 is used to perform phase analysis on the photon pulse data of the current metal foreign object to obtain the photon counting phase analysis spectrum of the current metal foreign object; the identification module 300 is used to extract the characteristic parameters of the current metal foreign object based on the photon counting phase analysis spectrum of the current metal foreign object, and input the characteristic parameters of the current metal foreign object into a pre-trained metal foreign object identification model to obtain the type of the current metal foreign object.

[0119] Furthermore, in some embodiments, before inputting the characteristic parameters into the pre-trained metal foreign body recognition model, the recognition module 300 is also used to: obtain photon pulse data of multiple metal foreign body samples at multiple voltages using a photon counting detection system; perform phase analysis on the photon pulse data of multiple metal foreign body samples at multiple voltages to obtain a photon counting phase analysis spectrum of each metal foreign body sample, and obtain characteristic parameters of each metal foreign body sample based on the photon counting phase analysis spectrum of each metal foreign body sample, and fit the characteristic parameters of each metal foreign body sample to obtain a characteristic parameter database; optimize the extreme learning machine network based on a preset improved particle swarm optimization algorithm, train the optimized extreme learning machine network using the characteristic parameter database, and obtain a pre-trained metal foreign body recognition model.

[0120] Furthermore, in some embodiments, the identification module 300 is used to: input the feature parameter data in the feature parameter database into the optimized extreme learning machine network for iterative training, and when the number of iterative training of the optimized extreme learning machine network reaches a preset number of iterations, determine the global optimal solution, so as to construct a pre-trained metal foreign body identification model based on the global optimal solution.

[0121] Furthermore, in some embodiments, the phase resolution module 200 is used to: evenly divide the phase of the power frequency cycle into multiple phase windows; calculate the number of photon pulses in each phase window, and accumulate the number of photon pulses in each phase window to obtain a photon number-phase sequence; visualize the photon number-phase sequence to obtain a photon counting phase resolution spectrum.

[0122] Furthermore, in some embodiments, the characteristic parameters include at least one of the total number of photons, mean phase asymmetry, skewness, steepness, and Pearson correlation coefficient.

[0123] It should be noted that the aforementioned explanation of the embodiment of the GIS metal foreign body identification method based on photon-phase technology is also applicable to the GIS metal foreign body identification device based on photon-phase technology of this embodiment, and will not be repeated here.

[0124] According to the GIS metal foreign body identification device based on photon-phase technology in the embodiment of the present application, the photon counting detection system is used to obtain the photon pulse data of the current metal foreign body; the photon pulse data of the current metal foreign body is phase analyzed to obtain the photon counting phase analysis spectrum of the current metal foreign body; the characteristic parameters of the current metal foreign body are extracted based on the photon counting phase analysis spectrum, and the characteristic parameters of the current metal foreign body are input into the pre-trained metal foreign body identification model to obtain the type of the current metal foreign body. In this way, the problem that the related technology is greatly affected by the environment is solved, and the accurate identification of unknown metal foreign bodies is achieved.

[0125] Fig.10 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device may include:

[0126] A memory 901 , a processor 902 , and a computer program stored in the memory 901 and executable on the processor 902 .

[0127] When the processor 902 executes the program, the GIS metal foreign body identification method based on the photon-phase technology provided in the above embodiment is implemented.

[0128] Furthermore, the electronic device further comprises:

[0129] The communication interface 903 is used for communication between the memory 901 and the processor 902 .

[0130] The memory 901 is used to store computer programs that can be executed on the processor 902 .

[0131] The memory 901 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0132] If the memory 901, the processor 902 and the communication interface 903 are implemented independently, the communication interface 903, the memory 901 and the processor 902 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Fig. 9 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0133] Optionally, in a specific implementation, if the memory 901, the processor 902 and the communication interface 903 are integrated on a chip, the memory 901, the processor 902 and the communication interface 903 can communicate with each other through an internal interface.

[0134] The processor 902 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0135] An embodiment of the present application also provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the above-mentioned GIS metal foreign body identification method based on photon-phase technology is implemented.

[0136] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0137] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0138] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A GIS metal foreign body identification method based on photon-phase technology, characterized in that: The method utilizes a photon counting detection system, which includes a photon counting platform, a partial discharge sensor, a non-partial discharge AC excitation source, a data acquisition component connected to the photon counting platform and the partial discharge sensor, and a data processing component connected to the data acquisition component, which are sequentially connected in parallel. The method includes: Using the photon counting detection system to obtain photon pulse data of the current metal foreign matter; Performing phase analysis on the photon pulse data of the current metal foreign matter to obtain a photon counting phase analysis spectrum of the current metal foreign matter; The characteristic parameters of the current metal foreign object are extracted based on the photon counting phase analysis spectrum of the current metal foreign object, and the characteristic parameters of the current metal foreign object are input into a pre-trained metal foreign object recognition model to obtain the type of the current metal foreign object.

2. The method according to claim 1, characterized in that Before inputting the characteristic parameter into the pre-trained metal foreign body recognition model, the method further includes: Using the photon counting detection system to obtain photon pulse data of multiple metal foreign matter samples at multiple voltages; Phase analysis is performed on the photon pulse data of the multiple metal foreign matter samples at multiple voltages to obtain a photon counting phase analysis spectrum of each metal foreign matter sample, and characteristic parameters of each metal foreign matter sample are obtained according to the photon counting phase analysis spectrum of each metal foreign matter sample, and the characteristic parameters of each metal foreign matter sample are fitted to obtain a characteristic parameter database; The extreme learning machine network is optimized based on a preset improved particle swarm optimization algorithm, and the optimized extreme learning machine network is trained using the characteristic parameter database to obtain the pre-trained metal foreign body recognition model.

3. The method according to claim 2, characterized in that The method of using the characteristic parameter database to train the optimized extreme learning machine network to obtain the pre-trained metal foreign body recognition model includes: The feature parameter data in the feature parameter database is input into the optimized extreme learning machine network for iterative training, and when the number of iterative training of the optimized extreme learning machine network reaches a preset number of iterations, a global optimal solution is determined to construct the pre-trained metal foreign body recognition model based on the global optimal solution.

4. The method according to claim 1, characterized in that: The performing phase analysis on the photon pulse data of the current metal foreign matter to obtain the photon counting phase analysis spectrum of the current metal foreign matter includes: The phase of the power frequency cycle is evenly divided into multiple phase windows; Calculate the number of photon pulses in each phase window, and accumulate the number of photon pulses in each phase window to obtain a photon number-phase sequence; The photon number-phase sequence is visualized to obtain the photon counting phase analysis spectrum.

5. The method according to any one of claims 1 to 4, characterized in that The characteristic parameters include at least one of the total number of photons, mean phase asymmetry, skewness, steepness, and Pearson correlation coefficient.

6. A GIS metal foreign body identification device based on photon-phase technology, characterized in that: The device utilizes a photon counting detection system, which includes a photon counting platform, a partial discharge sensor, a non-partial discharge AC excitation source, a data acquisition component connected to the photon counting platform and the partial discharge sensor, and a data processing component connected to the data acquisition component, wherein the device includes: An acquisition module, used to acquire photon pulse data of the current metal foreign matter using the photon counting detection system; A phase analysis module, used for performing phase analysis on the photon pulse data of the current metal foreign matter to obtain a photon counting phase analysis spectrum of the current metal foreign matter; The identification module is used to extract the characteristic parameters of the current metal foreign matter based on the photon counting phase analysis spectrum of the current metal foreign matter, and input the characteristic parameters of the current metal foreign matter into a pre-trained metal foreign matter identification model to obtain the type of the current metal foreign matter.

7. The device according to claim 6, characterized in that Before inputting the characteristic parameter into the pre-trained metal foreign body recognition model, the recognition module is further used to: Using the photon counting detection system to obtain photon pulse data of multiple metal foreign matter samples at multiple voltages; Phase analysis is performed on the photon pulse data of the multiple metal foreign matter samples at multiple voltages to obtain a photon counting phase analysis spectrum of each metal foreign matter sample, and characteristic parameters of each metal foreign matter sample are obtained according to the photon counting phase analysis spectrum of each metal foreign matter sample, and the characteristic parameters of each metal foreign matter sample are fitted to obtain a characteristic parameter database; The extreme learning machine network is optimized based on a preset improved particle swarm optimization algorithm, and the optimized extreme learning machine network is trained using the characteristic parameter database to obtain the pre-trained metal foreign body recognition model.

8. The device according to claim 7, characterized in that The identification module is used to: The feature parameter data in the feature parameter database is input into the optimized extreme learning machine network for iterative training, and when the number of iterative training of the optimized extreme learning machine network reaches a preset number of iterations, a global optimal solution is determined to construct the pre-trained metal foreign body recognition model based on the global optimal solution.

9. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the GIS metal foreign body identification method based on photon-phase technology as described in any one of claims 1 to 5.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement the GIS metal foreign body identification method based on photon-phase technology as described in any one of claims 1 to 5.

Images