A GIS disconnector mechanical fault identification method and device

Abstract

The present application relates to a kind of GIS disconnecting switch mechanical fault identification method and device, its method includes: obtaining GIS disconnecting switch source side and load side bus structure parameter, and according to its calculation bus electrical parameter;According to the multiple movement states of GIS disconnecting switch moving contact, the stroke curve discrete time sequence is constructed;Based on stroke curve discrete time sequence, the whole process VFTO discrete time sequence is constructed, and the time sequence data in it is labeled;From the whole process VFTO discrete time sequence, multiple transient features are extracted, and according to each transient feature and its corresponding label, the labeled sample set of supervised model is constructed;Through the completed supervised model of training and real-time whole process VFTO discrete time sequence, the mechanical fault of target GIS disconnecting switch is identified.The present application trains supervised model based on the discrete time sequence of GIS disconnecting switch mechanical state, to improve the accuracy of fault detection.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of electrical fault identification, and particularly relates to a GIS disconnector mechanical fault identification method and device. BACKGROUND

[0002] Monitoring vibration signals. The GIS disconnector mechanical state monitoring based on vibration signals is to collect the shell vibration signals of the disconnector during the disconnector opening and closing operation by installing vibration sensors on the GIS shell, and to extract the characteristic quantities in the vibration signals associated with the disconnector mechanical structure action to realize the online monitoring of the disconnector mechanical state. However, the vibration is generated in the substation including the circuit breaker operation and the GIS bus through which the current flows, and the associated characteristic quantities in the collected signals are easily disturbed by noise, and the engineering applicability is not high.

[0003] Monitoring the driving motor current. The disconnector opening and closing operation is driven by the driving motor outside the GIS tank, and the driving motor current fluctuation is caused by the driving motor operation torque change due to the disconnector mechanical structure abnormality. For example, in an existing high-voltage disconnector fault determination method, the disconnector driving motor current signal is obtained, the motor current signal is compared with the related characteristics of the motor current signals in different fault states, and the fault state of the disconnector is determined according to the comparison result. However, the fault mapping relationship between the motor current and the contact movement is unstable due to the transmission mechanism failure, and the fault discrimination is not accurate. SUMMARY

[0004] In order to improve the accuracy of the disconnector fault state detection, a GIS disconnector mechanical fault identification method is provided in the first aspect of the application, comprising: acquiring the source side and load side bus structure parameters of the GIS disconnector, and calculating the bus electrical parameters according to the bus structure parameters; constructing a stroke curve discrete time sequence according to a plurality of movement states of the disconnector moving contact; based on the bus structure parameters, the bus electrical parameters and the stroke curve discrete time sequence, constructing a whole process VFTO discrete time sequence, and labeling the time sequence data in the VFTO discrete time sequence; extracting a plurality of features from the whole process VFTO discrete time sequence, and constructing a labeled sample set according to each feature and its corresponding label; training a supervised model based on the dataset constructed by the labeled sample set; and identifying the mechanical fault of the target GIS disconnector through the trained supervised model and the real-time whole process VFTO discrete time sequence.

[0005] In some embodiments of the present application, the step of constructing the discrete time sequence of the stroke curve according to the plurality of motion states of the GIS disconnector moving contact includes: establishing a discrete expression of the stroke curve of the moving contact of the disconnector in normal, rust and jammed mechanical states respectively according to the motion characteristics of the moving contact of the disconnector in the normal, rust and jammed states.

[0006] In some embodiments of the present application, the step of constructing the discrete time sequence of the whole-process VFTO based on the bus structure parameters, bus electrical parameters and the discrete time sequence of the stroke curve includes: establishing a differential equation of a GIS distributed parameter model based on the bus structure parameters and bus electrical parameters through a transmission line model; solving the differential equation through a finite element method according to a preset boundary condition and a GIS disconnector contact gap breakdown condition to obtain the GIS distributed parameter model of the discrete time sequence of the single breakdown VFTO; and substituting the GIS distributed parameter model of the discrete time sequence of the single breakdown VFTO into the discrete time sequence of the stroke curve to calculate the VFTO data corresponding to each stroke curve and obtain the discrete time sequence of the whole-process VFTO.

[0007] Further, the step of establishing the differential equation of the GIS distributed parameter model based on the bus structure parameters and bus electrical parameters through the transmission line model includes: establishing a GIS disconnector single breakdown distributed parameter model based on the bus structure parameters and bus electrical parameters; and establishing the differential equation of the GIS distributed parameter model through the transmission line model and the GIS disconnector single breakdown distributed parameter model.

[0008] Further, the step of extracting a plurality of features from the discrete time sequence of the whole-process VFTO and constructing a labeled sample set according to each feature and its corresponding label includes: decomposing the discrete time sequence of the whole-process VFTO into a plurality of discrete time sequences of single breakdown VFTO; extracting a breakdown time feature, a residual voltage feature, a peak value feature and an oscillation duration feature from each discrete time sequence of single breakdown VFTO, and normalizing each feature to obtain a three-dimensional feature sequence set; labeling each feature sequence based on the corresponding mechanical state of the feature sequence to obtain a plurality of unlabeled samples and form the labeled sample set.

[0009] In the above embodiments, the step of training the supervised model based on the data set constructed based on the labeled sample set includes:

[0010] The step of training the K-nearest neighbor classification model based on the data set constructed based on the labeled sample set.

[0011] In a second aspect, the application provides a GIS disconnector mechanical fault identification device, comprising: an acquisition module, configured to acquire source side and load side bus structure parameters of the GIS disconnector, and calculate bus electrical parameters according to the bus structure parameters; a construction module, configured to construct a stroke curve discrete time sequence according to a plurality of movement states of a moving contact of the GIS disconnector; construct a whole-process VFTO discrete time sequence based on the bus structure parameters, the bus electrical parameters and the stroke curve discrete time sequence, and label time sequence data in the VFTO discrete time sequence; an extraction module, configured to extract a plurality of features from the whole-process VFTO discrete time sequence, and construct a labeled sample set according to each feature and its corresponding label; and an identification module, configured to train a supervised model based on a data set constructed based on the labeled sample set, and identify a mechanical fault of a target GIS disconnector through the trained supervised model and a real-time whole-process VFTO discrete time sequence.

[0012] In a third aspect, the application provides an electronic device, comprising: one or more processors; and a storage device 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.

[0013] In a fourth aspect, the application provides a computer readable medium having a computer program stored thereon, wherein the computer program is executed by a processor to implement the GIS disconnector mechanical fault identification method provided in the first aspect.

[0014] The application has the following beneficial effects:

[0015] The application constructs a feature quantity directly and strongly associated with the contact stroke from the perspective of the disconnector opening and closing electromagnetic transient process, and realizes direct representation of the mechanical state of the disconnector; the application constructs a whole-process VFTO simulation model of the gap breakdown between the opening and closing contacts of the disconnector by using the GIS structure and electrical parameters, establishes a complete balanced VFTO waveform data set containing the normal and fault states of the disconnector and different degrees of faults, in combination with the movement characteristics of the contacts in each state of the disconnector. The mechanical state discrimination model established based on the data set can accurately identify a plurality of mechanical states of the disconnector. BRIEF DESCRIPTION OF DRAWINGS

[0016] Figure 1 FIG. 1 is a basic flowchart of the GIS disconnector mechanical fault identification method in some embodiments of the application;

[0017] Figure 2 FIG. 2 is a specific flowchart of the GIS disconnector mechanical fault identification method in some embodiments of the application;

[0018] Figure 3 Schematic diagram of contact gap single-break GIS distribution parameter model in some embodiments of the present application;

[0019] Figure 4 Schematic diagram of contact stroke curve of isolator in each mechanical state in some embodiments of the present application;

[0020] Figure 5 Flow chart of whole-process VFTO simulation calculation in some embodiments of the present application;

[0021] Figure 6 Schematic diagram of effect of optimal k value selection and accuracy of k-neighbor model in some embodiments of the present application;

[0022] Figure 7 Schematic diagram of structure of GIS isolator mechanical fault recognition device in some embodiments of the present application;

[0023] Figure 8 Schematic diagram of structure of electronic device in some embodiments of the present application. DETAILED DESCRIPTION

[0024] The principles and features of the present application are described below in combination with the drawings, and the examples are only used to explain the present application and are not used to limit the scope of the present application.

[0025] REFERENCE Figure 1 AND Figure 2 In the first aspect of the present application, a GIS isolator mechanical fault recognition method is provided, comprising: S1. acquiring source side and load side bus structure parameters of a GIS isolator, and calculating bus electrical parameters according to the bus structure parameters; S2. constructing a stroke curve discrete time sequence according to a plurality of motion states of a moving contact of the GIS isolator; based on the bus structure parameters, the bus electrical parameters and the stroke curve discrete time sequence, constructing a whole-process VFTO discrete time sequence, and labeling time sequence data in the VFTO discrete time sequence; S3. extracting a plurality of features from the whole-process VFTO discrete time sequence, and constructing a labeled sample set according to each feature and its corresponding label; S4. training a supervised model based on a data set constructed by the labeled sample set; and recognizing a mechanical fault of a target GIS isolator by using the trained supervised model and real-time whole-process VFTO discrete time sequence.

[0026] 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 extra-high-voltage power systems. This phenomenon is usually generated by the operation of disconnectors, and is characterized by a very short wave front time, usually between 3 to 100 nanoseconds, hence the name "Very Fast". The frequency of VFTO can be as high as hundreds of megahertz, and it has unique waveform and spectral characteristics compared with lightning overvoltage and operating overvoltage.

[0027] Reference Figure 3 With Figure 4 In step S1 of some embodiments of the present application, the source side and load side bus structure parameters of the GIS disconnector are obtained, and the bus electrical parameters are calculated according to the bus structure parameters;

[0028] Specifically, the structure parameters of the GIS disconnector two-side bus and surrounding equipment are obtained according to the GIS substation design drawings or field measurement, including the GIS disconnector source side bus , load side bus length , bus outer diameter and GIS tank inner diameter structure parameters, the electrical parameters of the GIS disconnector two-side bus are calculated by using parameter calculation formula, and the calculation formula is as follows:

[0029] (1),

[0030] In formula (1), are the GIS bus outer diameter and the GIS shell inner diameter, respectively; are the vacuum permeability, the relative permeability of the GIS bus and the relative permeability of the SF6 gas filled in the GIS, respectively; are the vacuum dielectric constant and the relative dielectric constant of the SF6 gas, respectively; are the conductivities of the GIS bus and the SF6 gas, respectively.

[0031] In step S2 of some embodiments of the present application, the travel curve discrete time sequence is constructed according to the plurality of motion states of the moving contact of the GIS disconnector, including:

[0032] S21. According to the motion characteristics of the moving contact of the GIS disconnector under normal, rust and jam, the discrete expressions of the moving contact travel curve under the normal, rust and jam mechanical states of the disconnector are established respectively.

[0033] Specifically, according to the motion characteristics of the moving contact of the disconnector under normal, rust and jam, the discrete expressions of the moving contact travel curve under the normal, rust and jam mechanical states of the disconnector are established as shown in the following formulas (2), (3) and (4) respectively.

[0034] (2),

[0035] In formula (2), is the stroke of the i-th discrete point of the moving contact stroke curve of the isolator in the normal state; is the maximum distance between the moving and static contacts of the isolator; is the moving speed of the moving contact of the isolator in the normal state;

[0036] In formula (2), is the discrete time step, preferably ;

[0037] In formula (2), is related to the operation time of the isolator and the discrete time step , and is determined by formula (3) as follows.

[0038] (3),

[0039] When the metal elements in the operating mechanism of the isolator are corroded, the operating speed of the isolator will decrease. According to the corrosion degree, the speed of formula 2 is replaced by the moving speed under corrosion, and the expression of the moving contact stroke curve under the corrosion state is shown in formula (4).

[0040] (4),

[0041] In formula (4), is the moving speed of the moving contact of the isolator in the corrosion state.

[0042] The isolator is stuck and refuses to move due to corrosion and other reasons, which is reflected in the moving stroke of the isolator contact. Taking the case of a stuck and refused to move during closing as an example, the mathematical expression of the moving contact stroke curve of the isolator is as follows

[0043] (5),

[0044] In formula (5), are the moving speeds of the moving contact of the isolator before and after sticking, respectively; are the times when the isolator sticks and recovers, respectively; is the recovery action speed of the isolator.

[0045] Setting the key parameters in the stroke curve expression associated with the mechanical state , constructing a complete stroke curve set of each mechanical state of the isolator , is the total number of stroke curves.

[0046] In step S2 of some embodiments of the application, the constructing the whole-process VFTO discrete-time sequence based on the busbar structure parameters, busbar electrical parameters and the discrete-time sequence of the travel curve includes:

[0047] S22, based on the busbar structure parameters and busbar electrical parameters, establishing a differential equation of the GIS distributed parameter model through a transmission line model;

[0048] Further, in step S22, the establishing a differential equation of the GIS distributed parameter model through a transmission line model based on the busbar structure parameters and busbar electrical parameters includes:

[0049] S221, based on the busbar structure parameters and busbar electrical parameters, establishing a single-breakdown distributed parameter model of a GIS disconnector;

[0050] S222, establishing a differential equation of the GIS distributed parameter model through a transmission line model and the single-breakdown distributed parameter model of the GIS disconnector.

[0051] First, the GIS busbar length , the GIS distributed parameter , the single-breakdown distributed parameter model of the contact gap breakdown including the arc discharge process of the disconnector and the two-end busbars is established; the voltage and current at position x at time t in the GIS distributed parameter model are denoted as 、 The equation of the GIS distributed parameter model is expressed as:

[0052] (6),

[0053] The initial conditions of the source-side busbar and the load-side busbar of the GIS distributed parameter model are set according to the following formula:

[0054] (7),

[0055] wherein denote the two ends of the disconnector at the connection between the source-side busbar and the load-side busbar.

[0056] The boundary conditions of the source-side busbar first end, the load-side busbar last end and the arc position of the disconnector of the GIS distributed parameter model are set according to the following formula:

[0057] (8),

[0058] In formula (8), the arc discharge process of the disconnector gap breakdown is equivalent to the lumped parameter inductance and the resistance . Preferably, the arc discharge resistance and inductance are 、 .

[0059] S23, according to the preset boundary condition and GIS isolating switch contact gap breakdown condition, the finite element method is used to solve the differential equation, and the GIS distribution parameter model of single breakdown VFTO discrete time sequence is obtained;

[0060] Specifically, the numerical solving method of formula (6)-(8) model adopts time domain finite element method.

[0061] According to the single breakdown distribution parameter model, combined with the gap breakdown condition, all single breakdown VFTO data of the isolating switch opening and closing are iterated to form the GIS distribution parameter model for simulating single breakdown VFTO discrete time sequence ;

[0062] S24, the GIS distribution parameter model of single breakdown VFTO discrete time sequence is substituted into the stroke curve discrete time sequence, the VFTO data corresponding to each stroke curve is calculated, and the whole process VFTO discrete time sequence is obtained.

[0063] Specifically, according to the following formula, the stroke curve discrete time sequence is substituted To calculate the critical breakdown voltage of the gap.

[0064] (9);

[0065] When the contact gap breakdown voltage Is greater than the critical breakdown voltage The single breakdown VFTO data is simulated and calculated, and the whole stroke curve discrete time sequence The whole process VFTO discrete time sequence Is obtained, the whole process VFTO data corresponding to three types of stroke curves is calculated, and the data set , wherein, Is the number of stroke curves.

[0066] S25, the whole process VFTO discrete time sequence is constructed, and the time sequence data in the VFTO discrete time sequence is labeled.

[0067] Specifically, according to the mechanical state, the three types of VFTO time sequence data are labeled with label value. The labels of the three types of whole process VFTO data three-dimensional feature sequence of the isolating switch are set to 0, 1 and 2 respectively.

[0068] In step S3 of some embodiments of the application, the multiple features are extracted from the whole process VFTO discrete time sequence, and the labeled sample set is constructed according to each feature and its corresponding label.

[0069] S31, decomposing the whole-process VFTO discrete-time sequence into a plurality of single-break VFTO discrete-time sequences;

[0070] Specifically, the voltage change rate of the VFTO is calculated, a suitable threshold is set, and the single-break time of the whole-process VFTO is screened out, wherein the voltage rise rate calculation formula is as follows:

[0071] (10),

[0072] In the formula, is the voltage change rate of the VFTO; is the sampling time of the acquisition device at the discrete time step under the on-site measured waveform; is the threshold for distinguishing the breakdown time.

[0073] According to formula (10), all single-break time points in the whole-process VFTO discrete-time sequence are located The sequence number corresponding to the single-break time point is The data between two breakdown time points is extracted as the single-break VFTO waveform data of the contact gap, and the whole-process VFTO waveform data is denoted as The whole-process VFTO waveform data can be decomposed into m single-break VFTO waveform data , and n is the number of single-break data points.

[0074] S32, extracting the breakdown time feature, residual voltage feature, peak value feature and oscillation duration feature from each single-break VFTO discrete-time sequence, and normalizing each feature to obtain a three-dimensional feature sequence set;

[0075] Specifically, the whole-process VFTO discrete-time sequence is decomposed into a plurality of single-break process discrete-time sequences, the breakdown time , residual voltage , peak value and oscillation duration of each sequence are extracted, and normalized to construct a feature sequence . The calculation formula of the corresponding feature of the kth single-break VFTO is as follows:

[0076] (11)

[0077] In formula (11), is the starting sequence number participating in the calculation of the residual voltage, which is usually taken as 100-500, and preferably 200.

[0078] In formula (11), is the time step of the discrete waveform data; is the waveform oscillation amplitude threshold; m is the number of single breakdown in the whole process VFTO waveform.

[0079] is the source side voltage fundamental effective value is normalized. Specifically, let be the normalized feature, according to the following formula is the fundamental effective value of the source side voltage, to , is normalized

[0080] (12),

[0081] Construct a three-dimensional feature sequence .

[0082] Let the time interval between the current absolute breakdown time and the first breakdown time be the relative breakdown time of this time ; Let the absolute value of the difference between the current residual voltage and the last residual voltage be the residual voltage first difference component of this time , as shown in the following formula:

[0083] (13),

[0084] (14),

[0085] According to the following formula (15), calculate the ratio of voltage peak value to oscillation duration .

[0086] (15)

[0087] The same group of features is rearranged in ascending order of residual voltage first difference absolute value , and a three-dimensional feature sequence is constructed .

[0088] S33, based on the mechanical state corresponding to the feature sequence, mark each feature sequence to obtain a plurality of to-be-labeled samples and form a labeled sample set.

[0089] According to the mechanical state corresponding to the feature sequence, mark the feature sequence as , and form a labeled sample data set . According to formulas (9)-(13), separate single breakdown waveforms from the whole process VFTO data set , extract features and normalize to form a three-dimensional feature sequence set , according to the mechanical state corresponding to the feature sequence, mark the feature sequence as , and form a labeled sample data set .

[0090] According to formula (11)-(15) to the whole process VFTO data set Each whole process VFTO waveform data is separated, feature extraction and normalized to form a three-dimensional feature sequence, combined with data labels to form a labeled sample data set .

[0091] In step S4 of the above embodiment, the data set constructed based on the labeled sample set, training the supervised model comprises: based on the data set constructed by the labeled sample set, training the K nearest neighbor classification model.

[0092] S41. Calculate the similarity between sample sequences.

[0093] The similarity between sample sequences is usually selected to calculate the distance between samples, commonly including Euclidean distance, Manhattan distance, cosine similarity, dynamic time warping (DTW) optimal matching distance, etc., preferably using the optimal matching distance of DTW.

[0094] Specifically, first calculate the Euclidean distance matrix of two three-dimensional sample sequences 、 According to the following formula:

[0095] (16),

[0096] In formula (16), are the lengths of three-dimensional sample sequences ; The optimal matching path between two samples is the path with the shortest cumulative distance from the beginning to the end, that is:

[0097] (17),

[0098] In the formula, denotes the optimal matching path of the distance matrix in the ith row and the jth column.

[0099] The minimum cumulative distance between two sequences is calculated by dynamic programming method , then the similarity between two time series is expressed by the following formula:

[0100] (18),

[0101] In the formula, is the optimal matching path of two time series; is the number of points of the optimal matching path. The smaller the value of

[0102] ​Then the mechanical state discrimination model is a supervised classification model, preferably a K-neighbor classification model; the sample data set is divided into 10 groups of training set and test set by 10-fold cross-validation, the similarity between the test set samples and the training set samples is calculated, K training samples with the highest similarity are selected, and the mechanical state of the test set samples is discriminated by the "majority voting method". The average accuracy of the 10 groups of test set samples is the generalization performance indicator of the current K value. In a suitable range, the K value at the inflection point of the accuracy drop is selected as the optimal K value of the model, and the preferred K value traversal range is [1-50].

[0103] Finally, in step S4, the mechanical fault of the target GIS disconnector is identified by the trained supervised model and the real-time full-process VFTO discrete-time sequence, which is the reverse of the training process,

[0104] Specifically, the full-process VFTO data to be evaluated is obtained:

[0105] The low-voltage signal output of the GIS switch load-side VFTO sensor is collected , and the primary-side VFTO waveform discrete data is obtained according to the sensor transformation ratio . .

[0106] (19),

[0107] To ensure the integrity of the collected data and preserve the original VFTO information, the sampling rate of the collection device should not be lower than 500MS / s, and preferably 625MS / s.

[0108] The features of the full-process VFTO waveform data to be evaluated are extracted and normalized. Let the full-process VFTO waveform data to be evaluated be , the features are extracted and normalized according to step S400 to form the three-dimensional feature sequence to be evaluated , is the length of the feature sequence to be evaluated, i.e. the number of single breakdown times of the full-process VFTO waveform to be evaluated.

[0109] The feature sequence of the full-process VFTO waveform to be evaluated is calculated and the similarity between the sample feature sequence in the labeled sample data set is calculated, and the mechanical state of the sample to be evaluated is discriminated by the K-neighbor model with the optimal K value . .

[0110] In one specific embodiment of the present application, the structural parameters of the busbars on both sides of the GIS disconnector are obtained according to the GIS substation design drawings or field measurement, and in this embodiment, for the GIS loop topology shown in Figure 2 , the structural parameters of the busbars are shown in the following table.

[0111] Table 1 GIS bus structure parameters of the example

[0112]

[0113] The distribution parameters of the bus are calculated according to formula 1 .

[0114] 2) A set of stroke curves of the isolator in the normal, rust and jammed states is constructed.

[0115] The movement speed of the moving contact of the isolator in the rust state, the jamming and recovery time and the recovery speed in the jammed state in formulas (2), (4) and (5) can realize the simulation of the movement characteristics of the moving contact of the isolator in different fault degrees in the fault state. The specific settings of the case are shown in the following table:

[0116] Table 2 Key parameter settings of stroke curves of each mechanical state

[0117]

[0118] In the table, Each value is subject to a normal distribution with a mean of and a standard deviation of In the jammed state, the jamming time is set to the time when the distance is equal to 20 mm; the jamming duration is 10 ms. According to the parameter settings in the above table, 100 groups of stroke curves of the normal, rust and jammed categories are generated, and the stroke curve set of the mechanical state of the isolator is ;

[0119] 3) A GIS distribution parameter model for the whole process of isolator opening and closing is established, and the whole process VFTO data corresponding to all stroke curves in the stroke curve data set are calculated and generated by means of numerical simulation method;

[0120] First, a GIS distribution parameter model for the whole process of isolator opening and closing is established

[0121] According to the GIS structure parameters and the distribution parameters, the GIS bus part is uniformly dispersed and the GIS distribution parameter model of single breakdown arc is established. Combined with formulas (6)-(8), the single breakdown VFTO discrete time sequence is solved by using the finite element method in time domain.

[0122] Secondly, the solving process of the whole process VFTO discrete time sequence is established.

[0123] The critical breakdown voltage of SF6 gas between the moving and static contacts of the GIS isolator and the contact opening distance are approximately proportional, that is,

[0124] (20),

[0125] wherein, is the critical breakdown voltage of the gap at time t; is the opening distance of the moving contact at time t; is the critical breakdown voltage per unit length of the gap, which is a constant for a given GIS tank.

[0126] The voltage difference between the contacts is determined by the voltage across the disconnector contacts, i.e.

[0127] (21),

[0128] wherein, represents the voltage at the end of the source bus at time t; represents the voltage at the beginning of the load bus at time t;

[0129] The VFTO simulation process generated by the opening and closing of the primary disconnector is shown in Figure 5 . When , the gap breakdown performs a single breakdown simulation of VFTO; when , the voltage of the source side bus varies at power frequency, and the voltage of the load side bus remains unchanged.

[0130] The following relationship exists between the contact spacing and the moving contact stroke curve when the disconnector is closed:

[0131] (22),

[0132] Substitute the discrete time sequence of the stroke curve into equations (20)-(22). According to the whole process simulation calculation process, calculate the discrete time sequence of the whole process VFTO .

[0133] Simulate the whole process VFTO corresponding to each stroke curve in the disconnector stroke curve set to form the disconnector whole process VFTO data set ;

[0134] 4) Extract the breakdown time, residual voltage, VFTO waveform peak value, and oscillation duration characteristics of all single breakdown waveforms in multiple sets of whole process VFTO . Take one of the whole process VFTO waveforms as an example, and the characteristics of the single breakdown waveform are shown in Table 3:

[0135] Table 3 Characteristics of each single breakdown waveform of the primary whole process VFTO

[0136] ​​

[0137] The data in Table 3 is constructed into a three-dimensional feature sequence according to steps S403 and S404 and normalized as shown in Table 4 below.

[0138] Table 4 Three-dimensional feature sequence of a full-process VFTO waveform Data

[0139]

[0140] Extracting features of various mechanical states of the full-process VFTO generated by simulation and constructing a labeled three-dimensional feature sequence to form a sample data set .

[0141] Referring to Figure 6 , 5) Calculate the similarity between the sample feature sequences of the sample data set according to equations (11)-(13) , divide the sample data set into 10 groups of training sets and test sets using 10-fold cross-validation, calculate the similarity between the test set samples and the training set samples, and import it into the K nearest neighbor model for discrimination, and calculate the average accuracy of the 10 groups of test set samples as the generalization performance indicator of the current K value. In this embodiment, the average accuracy and K value curve is shown in Figure 6 , and the optimal K value of the model is 19 according to the above K value selection standard.

[0142] 6) Synchronously collect the VFTO sensor output signals of the load side bus during the opening and closing operations of the disconnecting switch, restore the low-voltage collected data to the original full-process VFTO waveform data according to the transformation ratio of the VFTO sensor . Extract features according to step S400 and normalize to form a sample sequence to be evaluated. Calculate the similarity between the sample to be evaluated and the training sample , input the discrimination model to obtain the label with the highest frequency as the discrimination result.

[0143] It should be understood that since both the opening and closing processes can cause voltage breakdown, and the specific collected VFTO full-process discrete digital waveform can be used for GIS disconnecting switch mechanical fault online diagnosis by the above method, therefore, the method process of using the VFTO full-process discrete digital waveform generated during the opening process for GIS disconnecting switch mechanical fault online diagnosis is not described here.

[0144] Example 2

[0145] Referring to Figure 7In a second aspect, the application provides a GIS disconnector mechanical fault identification device 1, comprising: an acquisition module 11, configured to acquire source side and load side bus structure parameters of the GIS disconnector, and calculate bus electrical parameters according to the bus structure parameters; a construction module 12, configured to construct a stroke curve discrete time sequence according to a plurality of motion states of a moving contact of the GIS disconnector; construct a whole-process VFTO discrete time sequence based on the bus structure parameters, the bus electrical parameters and the stroke curve discrete time sequence, and label time sequence data in the VFTO discrete time sequence; an extraction module 13, configured to extract a plurality of features from the whole-process VFTO discrete time sequence, and construct a labeled sample set according to each feature and its corresponding label; and an identification module 14, configured to train a supervised model based on a data set constructed by the labeled sample set, and identify a mechanical fault of a target GIS disconnector through the trained supervised model and a real-time whole-process VFTO discrete time sequence.

[0146] Further, the construction module 12 comprises: an establishment unit, configured to establish a differential equation of a GIS distribution parameter model based on the bus structure parameters and the bus electrical parameters through a transmission line model; a solving unit, configured to solve the differential equation through a finite element method according to a preset boundary condition and a GIS disconnector contact gap breakdown condition, to obtain a GIS distribution parameter model of a single breakdown VFTO discrete time sequence; and a calculation unit, configured to substitute the GIS distribution parameter model of the single breakdown VFTO discrete time sequence into the stroke curve discrete time sequence, to calculate VFTO data corresponding to each stroke curve, and to obtain the whole-process VFTO discrete time sequence.

[0147] Embodiment 3

[0148] Reference Figure 8 In a third aspect, the application provides an electronic device, comprising: one or more processors; and a storage device 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 in the first aspect.

[0149] The electronic device 500 can include a processing device (such as a central processor, a graphics processor, etc.) 501, which can perform various appropriate actions and processes according to programs stored in a read-only memory (ROM) 502 or programs 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 through a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0150] Generally, the following devices can be connected to the I / O interface 505: input devices 506, including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 507, including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 508, including, for example, a hard disk, etc.; and communication devices 509. The communication devices 509 can allow the electronic device 500 to communicate wirelessly or via a wire with other devices to exchange data. Although Figure 8 The electronic device 500 is shown with various devices, but it is understood that all of the shown devices are not required to be implemented or present. More or fewer devices can alternatively be implemented or present. Figure 8 Each block shown in the middle can represent one device or, as desired, multiple devices.

[0151] In particular, according to embodiments of the present disclosure, the processes described above with reference to the flowcharts can be implemented as a computer software program. For example, embodiments of the present disclosure include a computer program product comprising a computer program carried on a computer readable medium, the computer program containing program code for executing the methods illustrated by the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network by the communication device 509, or installed from the storage device 508, or installed from the ROM 502. When the computer program is executed by the processing device 501, the above-mentioned functions defined in the methods of embodiments of the present disclosure are executed. It should be noted that the computer readable medium described in embodiments of the present disclosure can be a computer readable signal medium or a computer readable storage medium or any combination of the two. The computer readable storage medium may, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any combination of the above. More specific examples of the computer readable storage medium can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In embodiments of the present disclosure, the computer readable storage medium can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus or device. In embodiments of the present disclosure, the computer readable signal medium can include a data signal carried in a baseband or as part of a carrier wave, in which the computer readable program code is carried. Such a propagated data signal can take a variety of forms, including but not limited to an electromagnetic signal, an optical signal or any suitable combination of the above. The computer readable signal medium can also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate or transport a program for use by or in connection with an instruction execution system, apparatus or device. The program code contained on the computer readable medium can be transmitted by any suitable medium, including but not limited to a wire, an optical fiber, an RF (radio frequency) or the like, or any suitable combination of the above.

[0152] The computer readable medium described above can be included in the electronic device described above; or can exist separately from the electronic device and be not assembled into the electronic device. The computer readable medium described above carries one or more computer programs, which, when executed by the electronic device, cause the electronic device to:

[0153] Computer program code for carrying out operations of embodiments of the present disclosure can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++, Python, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0154] The computer program instructions can also be loaded onto a computer or other programmable information processing apparatus to cause a series of operations to be performed on the computer or other programmable information processing apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable information processing apparatus implement the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0155] The above descriptions are only the preferred embodiment of the application, not intended to limit the application and any modification, equivalent replacement and improvement made within the spirit and principle of the application shall be included in the protection scope of the application.

Claims

1. A method for identifying mechanical faults in GIS disconnect switches, characterized in that, include: Obtain the structural parameters of the busbars on the source and load sides of the GIS disconnect switch, and calculate the busbar electrical parameters based on the busbar structural parameters; Based on the multiple motion states of the moving contact of the GIS disconnector, a discrete-time series of stroke curves is constructed: Based on the motion characteristics of the moving contact of the GIS disconnector under normal, corroded, and jammed conditions, discrete expressions for the stroke curves of the moving contact are established for the normal, corroded, and jammed mechanical states of the disconnector, respectively; based on the busbar structural parameters, busbar electrical parameters, and the discrete-time series of stroke curves, a full-process VFTO discrete-time series is constructed, and the time-series data in the VFTO discrete-time series are labeled; the full-process VFT is constructed based on the busbar structural parameters, busbar electrical parameters, and the discrete-time series of stroke curves. The discrete-time series includes: establishing a differential equation for the GIS distributed parameter model based on the busbar structural parameters and busbar electrical parameters using a transmission line model; solving the differential equation using the finite element method according to preset boundary conditions and GIS disconnector contact gap breakdown conditions to obtain the GIS distributed parameter model for a single breakdown VFTO discrete-time series; substituting the GIS distributed parameter model for the single breakdown VFTO discrete-time series into the travel curve discrete-time series to calculate the VFTO data corresponding to each travel curve, thus obtaining the full-process VFTO discrete-time series. Multiple features are extracted from the entire process VFTO discrete time series, and a labeled sample set is constructed based on each feature and its corresponding label: the entire process VFTO discrete time series is decomposed into multiple single-breakdown VFTO discrete time series; breakdown time features, residual voltage features, peak value features, and oscillation duration features 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; A supervised model is trained based on a dataset constructed from a labeled sample set. The mechanical faults of the target GIS disconnect switch are identified by using the trained supervised model and the real-time full-process VFTO discrete time series.

2. The method for identifying mechanical faults in GIS disconnect switches according to claim 1, characterized in that, The differential equations for establishing the GIS distributed parameter model based on the busbar structural parameters and busbar electrical parameters through the transmission line model include: Based on the busbar structural parameters and busbar electrical parameters, a single breakdown distribution parameter model for GIS disconnect switches is established. The differential equation of the GIS distributed parameter model is established using the transmission line model and the single breakdown distributed parameter model of the GIS disconnector.

3. The method for identifying mechanical faults in GIS disconnect switches according to claim 1, characterized in that, The dataset constructed based on the labeled sample set, and the supervised model trained thereon, include: A K-nearest neighbor classification model is trained on a dataset constructed from labeled sample sets.

4. A mechanical fault identification device for GIS disconnect switches, characterized in that, include: The acquisition module is used to acquire the bus structure parameters of the source side and load side of the GIS disconnect switch, and calculate the bus electrical parameters based on the bus structure parameters; The module is used to construct a discrete-time series of travel curves based on multiple motion states of the moving contact of the GIS disconnector: Based on the motion characteristics of the moving contact under normal, corroded, and jammed conditions, discrete expressions for the travel curves of the moving contact are established for the normal, corroded, and jammed mechanical states of the disconnector, respectively; 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 the time-series data in the VFTO discrete-time series are labeled; the construction of the full-process VFTO discrete-time series based on the busbar structural parameters, busbar electrical parameters, and the discrete-time series of travel curves... The VFTO discrete-time series includes: establishing a differential equation for a GIS distributed parameter model based on the busbar structural parameters and busbar electrical parameters using a transmission line model; solving the differential equation using the finite element method according to preset boundary conditions and GIS disconnector contact gap breakdown conditions to obtain a GIS distributed parameter model for a single breakdown VFTO discrete-time series; substituting the GIS distributed parameter model for the single breakdown VFTO discrete-time series into the travel curve discrete-time series to calculate the VFTO data corresponding to each travel curve, thus obtaining the full-process VFTO discrete-time series. The extraction module is used to extract multiple features from the entire process VFTO discrete time series and construct a labeled sample set based on each feature and its corresponding label: the entire process VFTO discrete time series is decomposed into multiple single-breakdown VFTO discrete time series; breakdown time features, residual voltage features, peak value features, and oscillation duration features 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; The identification module is used to train a supervised model based on a dataset constructed from a labeled sample set. The trained supervised model and the real-time full-process VFTO discrete time series are used to identify mechanical faults of the target GIS disconnect switch.

5. An electronic device, comprising: One or more processors; A storage device for storing one or more programs, which, when executed by one or more processors, cause the one or more processors to implement the GIS disconnector mechanical fault identification method as described in any one of claims 1 to 3.

6. A computer-readable medium having a computer program stored thereon, wherein, When the computer program is executed by the processor, it implements the mechanical fault identification method for GIS disconnect switches as described in any one of claims 1 to 3.

Images