GIS isolation switch mechanical fault identification method and device

Abstract

The invention relates to a GIS disconnecting switch mechanical fault identification method and device, and the method comprises the steps: obtaining bus structure parameters of a source side and a load side of a GIS disconnecting switch, and calculating bus electrical parameters according to the bus structure parameters; constructing a travel curve discrete time sequence according to the plurality of motion states of the moving contact of the GIS disconnecting switch; constructing a whole-process VFTO discrete time sequence based on the travel curve discrete time sequence, and tagging time sequence data in the whole-process VFTO discrete time sequence; extracting a plurality of transient characteristics from the whole-process VFTO discrete time sequence, and constructing a labeled sample set with a supervision model according to each transient characteristic and a corresponding label; and through the trained supervised model and the real-time whole-process VFTO discrete time sequence, identifying the mechanical fault of the target GIS isolation switch. According to the method, the supervised model is trained through the discrete time sequence based on the mechanical state of the GIS disconnecting switch, so that the accuracy of fault detection is improved.

Description

Technical Field

[0001] The invention belongs to the technical field of electrical fault identification, and in particular relates to a method and a device for identifying mechanical faults of GIS disconnect switches. Background Art

[0002] Monitoring vibration signals. The mechanical status monitoring of GIS disconnectors based on vibration signals is to install vibration sensors on the GIS housing to collect the housing vibration signals during the disconnector opening and closing operations, and extract the characteristic quantities associated with the mechanical structure of the disconnector in the vibration signals to achieve online monitoring of the mechanical status of the disconnector. However, the GIS busbars in the substation, including the circuit breaker operation and the current flowing through them, will generate vibrations, and the associated characteristic quantities in the collected signals are easily interfered by noise, so the engineering applicability is not high.

[0003] Monitor the current of the drive motor. The opening and closing operations of the isolating switch are driven by the drive motor outside the GIS tank body, and the drive is transmitted to the movable contact of the isolating switch through the transmission rod and the transmission shaft to complete the linear motion. Abnormalities in the mechanical structure of the isolating switch will cause changes in the operating torque of the drive motor and thus cause fluctuations in the current of the drive motor. For example, in a prior art method for determining faults of high-voltage isolating switches, the current signal of the isolating switch drive motor is obtained, and the relevant features of the motor current signal and the motor current signals of known different fault states are compared, and the fault state of the isolating switch is determined based on the comparison results. However, a fault in the transmission mechanism will make the fault mapping relationship between the motor current and the contact movement unstable, and the fault judgment will be inaccurate. Summary of the invention

[0004] In order to improve the detection accuracy of the fault state of the disconnector, a first aspect of the present invention provides a method for identifying mechanical faults of a GIS disconnector, comprising: obtaining the busbar structural parameters on the source side and the load side of the GIS disconnector, and calculating the busbar electrical parameters according to the busbar structural parameters; constructing a discrete time series of travel curves according to multiple motion states of the moving contact of the GIS disconnector; constructing a full-process VFTO discrete time series based on the busbar structural parameters, the busbar electrical parameters and the discrete time series of the travel curve, and labeling the time series data in the VFTO discrete time series; extracting multiple features from the full-process VFTO discrete time series, and constructing a labeled sample set according to each feature and its corresponding label; training a supervised model based on the data set constructed with the labeled sample set; identifying the mechanical fault of the target GIS disconnector through the trained supervised model and the real-time full-process VFTO discrete time series.

[0005] In some embodiments of the present invention, constructing a discrete time series of travel curves according to multiple motion states of the moving contacts of the GIS disconnector includes: establishing discrete expressions of the travel curves of the moving contacts of the disconnector in normal, corroded and stuck mechanical states according to the motion characteristics of the moving contacts of the GIS disconnector in normal, corroded and stuck mechanical states.

[0006] In some embodiments of the present invention, the construction of the whole process VFTO discrete time series based on the busbar structural parameters, busbar electrical parameters and travel curve discrete time series includes: based on the busbar structural parameters and busbar electrical parameters, establishing the differential equation of the GIS distributed parameter model through the transmission line model; according to the preset boundary conditions and the GIS disconnector contact gap breakdown conditions, solving the differential equation through the finite element method to obtain the GIS distributed parameter model of the single breakdown VFTO discrete time series; substituting the GIS distributed parameter model of the single breakdown VFTO discrete time series into the travel curve discrete time series, calculating the VFTO data corresponding to each travel curve, and obtaining the whole process VFTO discrete time series.

[0007] Furthermore, the differential equation of the GIS distributed parameter model is established through the transmission line model based on the busbar structural parameters and the busbar electrical parameters, including: establishing a single breakdown distributed parameter model of the GIS disconnector based on the busbar structural parameters and the busbar electrical parameters; establishing the differential equation of the GIS distributed parameter model through the transmission line model and the single breakdown distributed parameter model of the GIS disconnector.

[0008] Furthermore, the method of extracting multiple features from the full-process VFTO discrete time series and constructing a labeled sample set based on each feature and its corresponding label includes: decomposing the full-process VFTO discrete time series into multiple single-breakdown VFTO discrete time series; extracting breakdown moment features, residual voltage features, peak features and oscillation duration features from each single-breakdown VFTO discrete time series, and normalizing each feature to obtain a three-dimensional feature sequence set; based on the mechanical state corresponding to the feature sequence, labeling each feature sequence to obtain multiple samples to be labeled and form a labeled sample set.

[0009] In the above embodiment, the training of the supervised model based on the data set constructed with the labeled sample set includes: Based on the dataset constructed with labeled sample sets, the K-nearest neighbor classification model is trained.

[0010] According to a second aspect of the present invention, a GIS disconnector mechanical fault identification device is provided, comprising: an acquisition module for acquiring busbar structural parameters on the source side and the load side of the GIS disconnector, and calculating busbar electrical parameters based on the busbar structural parameters; a construction module for constructing a travel curve discrete time series according to multiple motion states of the moving contact of the GIS disconnector; constructing a full-process VFTO discrete time series based on the busbar structural parameters, busbar electrical parameters and travel curve discrete time series, and labeling the time series data in the VFTO discrete time series; an extraction module for extracting multiple features from the full-process VFTO discrete time series, and constructing a labeled sample set based on each feature and its corresponding label; an identification module for training a supervised model based on the data set constructed with the labeled sample set; and identifying the mechanical fault of the target GIS disconnector through the trained supervised model and the real-time full-process VFTO discrete time series.

[0011] The third aspect of the present invention provides an electronic device, comprising: one or more processors; a storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the GIS disconnector mechanical fault identification method provided in the first aspect of the present invention.

[0012] A fourth aspect of the present invention provides a computer-readable medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the GIS disconnector mechanical fault identification method provided in the first aspect of the present invention.

[0013] The beneficial effects of the present invention are: The present invention constructs a characteristic quantity that is directly and strongly associated with the contact stroke from the perspective of the electromagnetic transient process of the disconnector opening and closing, and realizes the direct characterization of the mechanical state of the disconnector; the present invention uses the GIS structure and electrical parameters to construct a full-process VFTO simulation model of the disconnector opening and closing contact gap breakdown, and combines the contact motion characteristics of each state of the disconnector to establish a complete balanced VFTO waveform data set containing normal and faulty disconnectors and different degrees of faults. The mechanical state discrimination model established based on this data set can accurately identify multiple mechanical states of the disconnector. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 It is a basic flow chart of a method for identifying mechanical faults of GIS disconnect switches in some embodiments of the present invention; Figure 2 It is a schematic diagram of a specific process of a method for identifying a mechanical fault of a GIS disconnector in some embodiments of the present invention; Figure 3A schematic diagram of a GIS distribution parameter model for a single breakdown of a contact gap in some embodiments of the present invention; Figure 4 Schematic diagram of contact travel curves of disconnectors in various mechanical states in some embodiments of the present invention; Figure 5 It is a full process VFTO simulation calculation flow chart in some embodiments of the present invention; Figure 6 A schematic diagram showing the effect of selecting the optimal k value and accuracy of the k-nearest neighbor model in some embodiments of the present invention; Figure 7 It is a structural schematic diagram of a GIS disconnector mechanical fault identification device in some embodiments of the present invention; Figure 8 It is a schematic diagram of the structure of an electronic device in some embodiments of the present invention. DETAILED DESCRIPTION

[0015] The principles and features of the present invention are described below in conjunction with the accompanying drawings. The examples given are only used to explain the present invention and are not used to limit the scope of the present invention.

[0016] refer to Figure 1 and Figure 2 In the first aspect of the present invention, a method for identifying mechanical faults of GIS disconnectors is provided, comprising: S1. acquiring busbar structural parameters on the source side and the load side of the GIS disconnector, and calculating busbar electrical parameters according to the busbar structural parameters; S2. constructing a travel curve discrete time series according to multiple motion states of the moving contact of the GIS disconnector; constructing a full-process VFTO discrete time series based on the busbar structural parameters, busbar electrical parameters and travel curve discrete time series, and labeling the time series data in the VFTO discrete time series; S3. extracting multiple features from the full-process VFTO discrete time series, and constructing a labeled sample set according to each feature and its corresponding label; S4. training a supervised model based on the data set constructed with the labeled sample set; identifying the mechanical fault of the target GIS disconnector through the trained supervised model and the real-time full-process VFTO discrete time series.

[0017] It can be understood that VFTO (Very Fast Transient Overvoltage) refers to a very fast transient overvoltage phenomenon that may occur in high-voltage and ultra-high-voltage power systems. This phenomenon is usually caused by the operation of disconnectors and is characterized by a very short wavefront time, usually between 3 and 100 nanoseconds, hence the name "Very Fast". The frequency of VFTO may be as high as hundreds of megahertz, and compared with lightning overvoltage and switching overvoltage, it has unique waveform and spectrum characteristics.

[0018] refer to Figure 3 and Figure 4 , in step S1 of some embodiments of the present invention, the busbar structure parameters of the source side and the load side of the GIS disconnector are obtained, and the busbar electrical parameters are calculated according to the busbar structure parameters; Specifically, the structural parameters of the busbars on both sides of the GIS disconnector and the surrounding equipment are obtained according to the GIS substation design drawings or field measurements, including the busbars on the source side of the GIS disconnector. , Load side bus length , Busbar outer diameter With GIS tank inner diameter Structural parameters, use parameter calculation formula to calculate the electrical parameters of the busbars on both sides of the GIS disconnector. The calculation formula is as follows: (1), In formula (1), They are the outer diameter of GIS busbar and the inner diameter of GIS shell respectively; They are the vacuum magnetic permeability, the relative magnetic permeability of the GIS busbar and the relative magnetic permeability of the SF6 gas filled in the GIS; are the dielectric constant of vacuum and the relative dielectric constant of SF6 gas respectively; are the electrical conductivities of GIS busbar and SF6 gas respectively.

[0019] In step S2 of some embodiments of the present invention, constructing a discrete time series of travel curves according to multiple motion states of the moving contact of the GIS disconnector includes: S21. According to the movement characteristics of the moving contact of the GIS disconnector in normal, corroded and stuck conditions, discrete expressions of the moving contact travel curves in the normal, corroded and stuck mechanical states of the disconnector are established respectively.

[0020] Specifically, based on the motion characteristics of the moving contact of the disconnector under normal, corroded and stuck conditions, the discrete expressions of the moving contact travel curves under normal, corroded and stuck mechanical conditions of the disconnector are established as shown in the following equations (2), (3) and (4).

[0021] (2), In formula (2), is the stroke of the ith discrete point of the moving contact stroke curve of the disconnector in normal state; It is the maximum distance between the moving and static contacts of the isolating switch; It is the movement speed of the moving contact of the isolating switch in the normal state; In formula (2), is the discrete time step, preferably ; In formula (2), Operation time of isolating switch and discrete time steps It is determined by the following formula (3).

[0022] (3), When the metal components in the operating mechanism of the disconnector are corroded, the operating speed of the disconnector will decrease. According to the degree of corrosion, the speed in formula 2 is replaced by the movement speed under corrosion, which is the expression of the moving contact stroke curve under corrosion, as shown in formula (4).

[0023] (4), In formula (4), It is the movement speed of the moving contact of the isolating switch in the rusted state.

[0024] The disconnector is stuck and refuses to move due to corrosion and other reasons. The movement of the disconnector contact is divided into normal section, refusal section and recovery section. Taking the case of a stuck and refusal section during the closing process as an example, the mathematical expression of the travel curve of the disconnector moving contact is as follows (5), In formula (5), They are the moving speed of the disconnector moving contact before and after it gets stuck; They are the time when the isolating switch is stuck and when it is restored respectively; Restore the operating speed for the disconnector.

[0025] Set the key parameters associated with the mechanical state in the travel curve expression , construct a complete set of travel curves for each mechanical state of the disconnector , is the total number of travel curves.

[0026] In step S2 of some embodiments of the present invention, constructing the whole process VFTO discrete time series based on the busbar structural parameters, busbar electrical parameters and travel curve discrete time series includes: S22, based on the busbar structural parameters and busbar electrical parameters, establish a differential equation of a GIS distributed parameter model through a transmission line model; Furthermore, in step S22, the differential equation of the GIS distributed parameter model is established through the transmission line model based on the busbar structural parameters and busbar electrical parameters, including: S221. Based on the busbar structural parameters and busbar electrical parameters, a single breakdown distribution parameter model of the GIS disconnector is established; S222. Establish a differential equation of a GIS distributed parameter model through a transmission line model and the single breakdown distributed parameter model of the GIS disconnector.

[0027] First use the GIS bus length , GIS distribution parameters , establish a distributed parameter model including the arcing process of the disconnector and the single breakdown of the busbars at both ends when the contact gap is broken down; the voltage and current at position x at time t in the GIS distributed parameter model are recorded as , The GIS distribution parameter model equation is expressed as: (6), The initial conditions of the source side bus and the load measurement bus of the GIS distributed parameter model are set according to the following formula: (7), in, They respectively represent the two ends of the disconnector at the connection between the source side bus and the load side bus.

[0028] The boundary conditions of the source side bus head end, load measurement bus end, and disconnector arc position of the GIS distributed parameter model are set according to the following formula: (8), In formula (8), the arc burning process when the disconnector gap breaks down is represented by the lumped parameter inductor With resistance Preferably, the arcing resistance and inductance are , .

[0029] S23, according to the preset boundary conditions and the GIS disconnector contact gap breakdown conditions, the differential equation is solved by the finite element method to obtain the GIS distributed parameter model of the single breakdown VFTO discrete time series; Specifically, the numerical solution method of the model (6)-(8) adopts the time domain finite element method.

[0030] According to the single breakdown distribution parameter model, combined with the gap breakdown condition, all single breakdown VFTO data of the disconnector opening and closing are iterated cyclically to form a discrete time series for simulating single breakdown VFTO. GIS distributed parameter model; S24, substituting the GIS distribution parameter model of the single breakdown VFTO discrete time series into the travel curve discrete time series, calculating the VFTO data corresponding to each travel curve, and obtaining the whole process VFTO discrete time series.

[0031] Specifically, according to the following formula, substitute the discrete time series of the travel curve: Calculate the critical breakdown voltage of the gap.

[0032] (9); Breakdown voltage across contact gap Greater than critical breakdown voltage Simulate and calculate single breakdown VFTO data, iterate the entire travel curve discrete time series Get the whole process VFTO discrete time series , calculate the full process VFTO data corresponding to the three types of travel curves, and obtain the data set ,in, is the number of travel curves.

[0033] S25. Construct the whole process VFTO discrete time series and assign labels to the time series data in the VFTO discrete time series.

[0034] Specifically, according to the mechanical state, the three types of VFTO time series data are assigned label values. The labels of the three-dimensional feature sequences of the three types of VFTO data of the disconnector in the whole process, namely, normal, rusted and stuck, are set to 0, 1 and 2 respectively.

[0035] In step S3 of some embodiments of the present invention, extracting multiple features from the whole process VFTO discrete time series and constructing a labeled sample set according to each feature and its corresponding label includes: S31, decomposing the whole process VFTO discrete time series into multiple single breakdown VFTO discrete time series; Specifically, the voltage change rate of VFTO is calculated, a suitable threshold is set, and the single breakdown moment of VFTO in the whole process is screened out. The voltage rise rate calculation formula is as follows: (10), In the formula, is the voltage change rate of VFTO; In discrete time steps, it is the sampling time of the acquisition device under the waveform measured in the field; is the threshold for determining the breakdown moment.

[0036] According to formula (10), the VFTO discrete time series of the whole process is located The serial numbers corresponding to all single breakdown moments in are , extract the data between the two breakdown moments as the contact gap single breakdown VFTO waveform data, and record the whole process VFTO waveform data once Can be decomposed into m single breakdown VFTO waveform data , n is the number of single breakdown data points.

[0037] S32, extracting breakdown moment features, residual voltage features, peak features, and oscillation duration features from each single breakdown VFTO discrete time series, and normalizing each feature to obtain a three-dimensional feature sequence set; Specifically, the whole VFTO discrete time series is decomposed into multiple discrete time series of single breakdown processes, and the breakdown time of each series is extracted. , residual voltage , Peak The duration of oscillation , and normalize to construct feature sequence The calculation formula for the kth single breakdown VFTO corresponding characteristics is as follows: (11) In formula (11), The starting number for calculating the residual voltage is usually within the range of 100-500, preferably 200.

[0038] In formula (11), is the time step of discrete waveform data; is the waveform oscillation amplitude threshold; m is the number of single breakdowns in the whole VFTO waveform.

[0039] The source side voltage fundamental effective value Normalization. Specifically, remember is the normalized feature, according to the following formula is the fundamental effective value of the voltage on the source side. , Normalization (12), Constructing 3D feature sequences .

[0040] The time interval between the current absolute breakdown time and the first breakdown time is recorded as the relative breakdown time of this time. ; The absolute value of the difference between the current residual voltage and the previous residual voltage is recorded as the first-order difference of the residual voltage , as shown in the following formula: (13), (14), The ratio of the voltage peak value to the oscillation duration is calculated according to the following formula (15): .

[0041] (15) Group features together According to the absolute value of the first-order difference of the residual voltage Rearrange in ascending order to construct a three-dimensional feature sequence .

[0042] S33. Based on the mechanical state corresponding to the feature sequence, each feature sequence is labeled to obtain a plurality of samples to be labeled and form a labeled sample set.

[0043] According to the mechanical state corresponding to the feature sequence, the feature sequence is marked as , forming a labeled sample dataset According to equations (9)-(13), the whole process VFTO data set The VFTO waveform data of each whole process is separated into single breakdown waveform, feature extraction and normalization to form a three-dimensional feature sequence set ,According to the mechanical state corresponding to the feature sequence, the feature sequence is marked as , forming a labeled sample dataset .

[0044] According to equations (11)-(15), the whole process VFTO data set The VFTO waveform data of each whole process is separated into single breakdown waveforms, features are extracted and normalized to form a three-dimensional feature sequence, and combined with data labels to form a labeled sample data set .

[0045] In step S4 of the above embodiment, the training of a supervised model based on a data set constructed with a labeled sample set includes: training a K-nearest neighbor classification model based on a data set constructed with a labeled sample set.

[0046] S41. Calculate the similarity between sample sequences.

[0047] The similarity between sample sequences is usually calculated by calculating the distance between samples. Commonly used distances include Euclidean distance, Manhattan distance, cosine similarity, and the optimal matching distance of dynamic time warping (DTW). The optimal matching distance of DTW is preferably used.

[0048] Specifically, first calculate two three-dimensional sample sequences according to the following formula , The Euclidean distance matrix : (16), In formula (16), The three-dimensional sample sequence The optimal matching path between two samples is the path with the shortest cumulative distance from the beginning to the end, that is: (17), In the formula, Represents the optimal matching path in the i-th row and j-th column of the distance matrix.

[0049] Use dynamic programming to calculate the minimum cumulative distance between two sequences , then the similarity between two time series is expressed by the following formula: (18), In the formula, is the optimal matching path of two time series; is the number of points in the optimal matching path. The smaller the value, the higher the similarity between samples.

[0050] Then the mechanical state discrimination model is a supervised classification model, and the K-nearest neighbor classification model is preferably used; the sample data set is divided into 10 training sets and test sets by 10-fold cross validation, the similarity between the test set samples and the training set samples is calculated, and the K training samples with the highest similarity are selected, and the "majority voting method" is used to discriminate the mechanical state of the test set samples. The average accuracy of the 10 groups of test set samples is calculated as the generalization performance index of the current K value. The k value is traversed in a suitable range, and the K value at the inflection point of the accuracy decrease is selected as the optimal K value of the model. The preferred K value traversal range is [1-50].

[0051] Finally, in step S4, the mechanical fault of the target GIS disconnector is identified by using the trained supervised model and the real-time full-process VFTO discrete time series, which is the opposite of the training process. Specifically, obtain the full process VFTO data to be evaluated: Collect the low voltage signal output of the VFTO sensor on the load side of the GIS switch , according to the sensor ratio , get the primary side VFTO waveform discrete data .

[0052] (19), To ensure that the collected data completely retains the original VFTO information, the sampling rate of the acquisition device should not be lower than 500MS / s, preferably 625MS / s.

[0053] Extract features and normalize the VFTO waveform data of the entire process to be evaluated. The VFTO waveform data of the entire process to be evaluated is recorded as , extract features according to step S400 and normalize to form a three-dimensional feature sequence to be evaluated , is the length of the characteristic sequence to be evaluated, that is, the number of single breakdowns of the VFTO waveform in the entire process to be evaluated.

[0054] Calculate the characteristic sequence of the VFTO waveform of the whole process to be evaluated With labeled sample dataset The K-nearest neighbor model with the optimal K value is used to identify the samples to be evaluated. Mechanical state .

[0055] In a specific implementation of the present invention, the structural parameters of the busbars on both sides of the GIS disconnector are obtained according to the GIS substation design drawings or field measurements. Figure 2 The GIS circuit topology shown and the structural parameters of the bus are shown in the following table.

[0056] Table 1 GIS busbar structural parameters of the embodiment

[0057] The distribution parameters of the busbar are calculated according to formula 1: .

[0058] 2) Construct a set of travel curves including the isolating switch in three states: normal, corroded and stuck.

[0059] The movement speed of the isolating switch moving contact in the rusted state, the jamming and recovery time, and the recovery speed in the jammed state in formulas (2), (4), and (5) can simulate the movement characteristics of the isolating switch moving contact in different fault degrees under the fault state. The specific settings of this case are shown in the following table: Table 2 Key parameter settings of travel curves for each mechanical state

[0060] In the table, The respective values ​​are subject to the mean , standard deviation is Normal distribution; under the jam condition, the jam time is set to the time when the spacing is equal to 20mm; the jam duration is 10ms. According to the parameter settings in the above table, 100 groups of normal, rusted and jammed travel curves are generated, and the mechanical state travel curve set of the travel isolating switch is ; 3) Establish a GIS distributed parameter model for the entire process of disconnector opening and closing, and use numerical simulation methods to calculate and generate the full-process VFTO data corresponding to all travel curves in the travel curve data set; First, a GIS distributed parameter model for the entire process of disconnector opening and closing is established. According to the GIS structural parameters and distribution parameters, the GIS busbar part is evenly discretized and the GIS distribution parameter model of contact gap single breakdown arcing is established. Combining equations (6)-(8), the time domain finite element method is used to solve the single breakdown VFTO discrete time series.

[0061] Secondly, the whole VFTO discrete time series solution process is established.

[0062] The critical breakdown voltage of SF6 gas between the moving and static contacts of the GIS disconnector is approximately proportional to the contact opening distance, that is, (20), In the formula, is the critical breakdown voltage of the gap at time t; is the opening distance between the moving and static contacts at time t; is the critical breakdown voltage per unit length of gap, which is a constant for a given GIS tank.

[0063] Voltage difference between contacts Determined by the voltage across the disconnector contacts, that is (twenty one), In the formula, Indicates the source-measured bus terminal voltage at time t; Indicates the voltage at the first end of the busbar on the load side at time t; The VFTO simulation process generated by the opening and closing of a disconnector is as follows: Figure 5 As shown. , gap breakdown performs VFTO single breakdown simulation; when ,The bus voltage on the source side changes according to the power frequency, and the bus voltage on the load side remains unchanged.

[0064] When the disconnector is closed, the contact spacing and the moving contact travel curve have the following relationship: (twenty two), Discretize the travel curve into a time series Substitute into equations (20)-(22). Calculate the VFTO discrete time series of the whole process according to the whole process simulation calculation process .

[0065] Simulate and calculate the full-process VFTO corresponding to each stroke curve in the isolating switch stroke curve set to form a VFTO data set for the entire isolating switch process ; 4) Extract the breakdown time of all single breakdown waveforms in multiple groups of full-process VFTO , residual voltage , VFTO waveform peak The duration of oscillation Characteristics, taking one of the full-process VFTO waveforms as an example, the single breakdown waveform characteristics are shown in Table 3 below: Table 3 Characteristic data of each single breakdown waveform of VFTO in the whole process

[0066] Construct a three-dimensional feature sequence from the data in Table 3 according to steps S403 and S404 After normalization, the data are shown in Table 4.

[0067] Table 4 Three-dimensional characteristic sequence of a full-process VFTO waveform data

[0068] Extract the features of VFTO in the whole process of various mechanical states generated by simulation and construct a labeled three-dimensional feature sequence , forming a sample data set .

[0069] refer to Figure 6 , 5) Calculate the similarity between the sample feature sequences of the sample data set according to equations (11)-(13) , the sample data set is divided into 10 training sets and test sets by 10-fold cross validation, the similarity between the test set samples and the training set samples is calculated and imported into the K-nearest neighbor model for discrimination, and the average accuracy of the 10 test set samples is calculated as the generalization performance index of the current K value. The average accuracy and K value curve in this embodiment are shown in Figure 6 As shown, the optimal K value of the model is 19 according to the above K value selection standard.

[0070] 6) Synchronously collect the output signal of the load-side busbar VFTO sensor during the disconnector opening and closing operations, and restore the low-voltage collected data to the original full-process VFTO waveform data based on the transformation ratio of the VFTO sensor . Extract features and normalize them according to step S400 to form a sequence of samples to be evaluated. Calculate the similarity between the samples to be evaluated and the training samples , input the discriminant model to obtain the label with the highest frequency as the discriminant result.

[0071] It should be understood that since both the opening and closing processes will produce voltage breakdown, and the specific collected VFTO full-process discrete digital waveforms can be used for online diagnosis of GIS disconnector mechanical faults through the above method, the method flow of online diagnosis of GIS disconnector mechanical faults using the VFTO full-process discrete digital waveforms generated by the opening process will not be repeated here.

[0072] Example 2 refer to Figure 7In a second aspect of the present invention, a GIS disconnector mechanical fault identification device 1 is provided, comprising: an acquisition module 11, used to acquire the busbar structural parameters on the source side and the load side of the GIS disconnector, and calculate the busbar electrical parameters according to the busbar structural parameters; a construction module 12, used to construct a travel curve discrete time series according to multiple motion states of the moving contact of the GIS disconnector; based on the busbar structural parameters, busbar electrical parameters and travel curve discrete time series, a full-process VFTO discrete time series is constructed, and the time series data in the VFTO discrete time series is labeled; an extraction module 13, used to extract multiple features from the full-process VFTO discrete time series, and construct a labeled sample set according to each feature and its corresponding label; an identification module 14, used to train a supervised model based on the data set constructed with the labeled sample set; the mechanical fault of the target GIS disconnector is identified through the trained supervised model and the real-time full-process VFTO discrete time series.

[0073] Furthermore, the construction module 12 includes: an establishment unit, which is used to establish the differential equation of the GIS distributed parameter model through the transmission line model based on the busbar structural parameters and the busbar electrical parameters; a solving unit, which is used to solve the differential equation through the finite element method according to the preset boundary conditions and the GIS disconnector contact gap breakdown conditions to obtain the GIS distributed parameter model of the single breakdown VFTO discrete time series; a calculation unit, which is used to substitute the GIS distributed parameter model of the single breakdown VFTO discrete time series into the travel curve discrete time series, calculate the VFTO data corresponding to each travel curve, and obtain the whole process VFTO discrete time series.

[0074] Example 3 refer to Figure 8 According to a third aspect of the present invention, an electronic device is provided, comprising: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the GIS disconnector mechanical fault identification method according to the first aspect of the present invention.

[0075] The electronic device 500 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage device 508 into a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the electronic device 500 are also stored. The processing device 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0076] Typically, the following devices may be connected to the I / O interface 505: an input device 506 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 507 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 508 including, for example, a hard disk, etc.; and a communication device 509. The communication device 509 may allow the electronic device 500 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 8 The electronic device 500 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead. Figure 8 Each block shown in the figure may represent one device, or may represent multiple devices as required.

[0077] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through a communication device 509, or installed from a storage device 508, or installed from a ROM 502. When the computer program is executed by the processing device 501, the above functions defined in the method of the embodiment of the present disclosure are executed. It should be noted that the computer-readable medium described in the embodiment of the present disclosure can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection with one or more conductors, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In an embodiment of the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, an apparatus, or a device. In an embodiment of the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in combination with an instruction execution system, an apparatus, or a device. The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to: wire, optical cable, RF (radio frequency), etc., or any suitable combination of the foregoing.

[0078] The computer-readable medium may be included in the electronic device, or may exist independently without being installed in the electronic device. The computer-readable medium carries one or more computer programs. When the one or more programs are executed by the electronic device, the electronic device: Computer program code for performing the operations of embodiments of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, Python, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on a user's computer, partially on a user's computer, as a separate software package, partially on a user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0079] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0080] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for identifying mechanical faults of GIS disconnectors, characterized in that: include: Obtain busbar structural parameters on the source side and the load side of the GIS disconnector, and calculate busbar electrical parameters based on the busbar structural parameters; A discrete time series of travel curves is constructed according to multiple motion states of the moving contact of the GIS disconnector; a full-process VFTO discrete time series is constructed based on the busbar structural parameters, busbar electrical parameters and the discrete time series of travel curves, and labels are assigned to the time series data in the VFTO discrete time series; Extracting multiple features from the VFTO discrete time series of the whole process, and constructing a labeled sample set according to each feature and its corresponding label; A supervised model is trained based on a dataset constructed with labeled sample sets. The mechanical faults of the target GIS disconnector are identified through the trained supervised model and the real-time full-process VFTO discrete time series.

2. The GIS disconnector mechanical fault identification method according to claim 1 is characterized in that: The method of constructing a discrete time series of travel curves according to multiple motion states of the moving contact of the GIS disconnector includes: According to the motion characteristics of the moving contact of the GIS disconnector in normal, corroded and stuck conditions, discrete expressions of the moving contact stroke curves of the disconnector in normal, corroded and stuck mechanical states are established respectively.

3. The GIS disconnector mechanical fault identification method according to claim 1 is characterized in that: The construction of the whole process VFTO discrete time series based on the busbar structural parameters, busbar electrical parameters and travel curve discrete time series includes: Based on the busbar structural parameters and busbar electrical parameters, a differential equation of a GIS distributed parameter model is established through a transmission line model; According to the preset boundary conditions and the breakdown conditions of the GIS disconnector contact gap, the differential equation is solved by the finite element method to obtain the GIS distributed parameter model of the single breakdown VFTO discrete time series; The GIS distributed parameter model of the single breakdown VFTO discrete time series is substituted into the travel curve discrete time series, and the VFTO data corresponding to each travel curve is calculated to obtain the whole process VFTO discrete time series.

4. The GIS disconnector mechanical fault identification method according to claim 3 is characterized in that: The differential equations for establishing the GIS distributed parameter model through the transmission line model based on the busbar structural parameters and busbar electrical parameters include: Based on the busbar structural parameters and busbar electrical parameters, a single breakdown distribution parameter model of the GIS disconnector is established; A differential equation of a GIS distributed parameter model is established through a transmission line model and the single breakdown distributed parameter model of the GIS disconnector.

5. The GIS disconnector mechanical fault identification method according to claim 14 is characterized in that: The step of extracting multiple features from the VFTO discrete time series of the whole process and constructing a labeled sample set according to each feature and its corresponding label includes: Decomposing the whole process VFTO discrete time series into multiple single breakdown VFTO discrete time series; The breakdown moment feature, residual voltage feature, peak feature and oscillation duration feature are extracted from each single breakdown VFTO discrete time series, and each feature is normalized to obtain a three-dimensional feature sequence set. Based on the mechanical state corresponding to the feature sequence, each feature sequence is labeled to obtain multiple samples to be labeled and form a labeled sample set.

6. The GIS disconnector mechanical fault identification method according to claim 1 is characterized in that: The data set constructed based on the labeled sample set and the supervised model trained include: Based on the dataset constructed with labeled sample sets, the K-nearest neighbor classification model is trained.

7. A GIS disconnector mechanical fault identification device, characterized in that: include: An acquisition module is used to acquire the busbar structural parameters on the source side and the load side of the GIS disconnector, and calculate the busbar electrical parameters according to the busbar structural parameters; A construction module is used to construct a discrete time series of travel curves according to multiple motion states of the moving contact of the GIS disconnector; based on the busbar structural parameters, busbar electrical parameters and the discrete time series of travel curves, a full-process VFTO discrete time series is constructed, and labels are assigned to the time series data in the VFTO discrete time series; An extraction module, used to extract multiple features from the whole process VFTO discrete time series, and construct a labeled sample set according to each feature and its corresponding label; The identification module is used to train a supervised model based on a data set constructed with a labeled sample set; the mechanical fault of the target GIS disconnector is identified through the trained supervised model and the real-time full-process VFTO discrete time series.

8. The GIS disconnector mechanical fault identification device according to claim 7 is characterized in that: The building blocks include: An establishing unit is used to establish a differential equation of a GIS distributed parameter model through a transmission line model based on the busbar structural parameters and the busbar electrical parameters; A solving unit is used to solve the differential equation by finite element method according to preset boundary conditions and GIS disconnector contact gap breakdown conditions to obtain a GIS distributed parameter model of a single breakdown VFTO discrete time series; The calculation unit is used to substitute the GIS distribution parameter model of the single breakdown VFTO discrete time series into the travel curve discrete time series, calculate the VFTO data corresponding to each travel curve, and obtain the whole process VFTO discrete time series.

9. An electronic device, comprising: one or more processors; A storage device for storing one or more programs, which, when executed by the one or more processors, enables the one or more processors to implement the GIS disconnector mechanical fault identification method as described in any one of claims 1 to 6.

10. A computer readable medium having a computer program stored thereon, wherein: When the computer program is executed by a processor, the method for identifying mechanical faults of a GIS disconnector switch as claimed in any one of claims 1 to 6 is implemented.

Images