A GIS disconnector mechanical state online evaluation method based on VFTC

Abstract

The present application relates to a kind of GIS disconnecting switch mechanical state on-line evaluation method based on VFTC, comprising: obtaining the VFTC full process waveform generated in the process of switching on and off of GIS disconnecting switch when no fault, VFTC full process waveform is composed of multiple single breakdown oscillation waveform;The expectation and variance of the peak value of each single breakdown oscillation waveform when no fault are calculated based on Gaussian process regression model;The upper and lower threshold of the peak value of each single breakdown oscillation waveform is set based on the value of expectation and variance, the proportion of the number of the peak value of each single breakdown oscillation waveform of the equipment to be diagnosed in the corresponding upper and lower threshold range is counted, whether the equipment to be diagnosed produces fault is evaluated based on the proportion;It can realize the on-line monitoring of GIS disconnecting switch mechanical state without power, without periodic power-off disassembly calibration, save a lot of manpower and material resources, while various potential mechanical faults can be found in time, avoid its further development deterioration, guarantee the stable operation of GIS disconnecting switch and power system.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of electrical equipment state evaluation, and in particular to a GIS disconnector mechanical state online evaluation method based on VFTC. BACKGROUND

[0002] GIS (Gas Insulated Switchgear) equipment is favored in the power industry due to its small size, high insulation level and other advantages, and the number of GIS equipment delivered in the power grid has been increasing in recent years. As one of the key components of GIS equipment, correct evaluation of the mechanical state of the disconnector is crucial to ensuring the normal operation of the power grid.

[0003] The current GIS disconnector mechanical state evaluation method in the power grid is an invasive offline evaluation, that is, the section where the equipment to be evaluated is powered off first, and then the equipment is disassembled for evaluation. This method is time-consuming and labor-intensive, and the efficiency is low. Moreover, since the power needs to be turned off first and then evaluated, it seriously affects the efficiency of the power grid.

[0004] Due to the two great advantages of continuous evaluation and no need to disassemble the equipment, the GIS disconnector mechanical state online evaluation method has attracted widespread attention in the industry. The existing online evaluation methods can be mainly divided into two categories: 1. Monitor the electrical parameters of the drive motor, such as collecting the motor output power, then estimate the probability density estimation curve and calculate the similarity to determine whether the opening and closing is in place, but this method cannot identify the opening and closing that is not in place due to subsequent transmission link failure of the motor; 2. Monitor the vibration signal during the opening and closing of the disconnector, collect the vibration signal generated during the operation of the GIS disconnector, and realize online monitoring of the mechanical state by combining a neural network, but the vibration signal is not sensitive to some mechanical faults.

[0005] In summary, the existing online evaluation methods cannot fully reflect the mechanical state of the disconnector. SUMMARY

[0006] The present application provides a GIS disconnector mechanical state online evaluation method based on VFTC, which uses the maximum value of single breakdown of VFTC generated during the opening and closing of the GIS disconnector to evaluate the mechanical state of the disconnector, directly monitors the final working link of the mechanical structure of the GIS disconnector - the moving and static contacts, and realizes comprehensive evaluation of the entire mechanical system.

[0007] According to a first aspect of the present application, a GIS disconnector mechanical state online evaluation method based on VFTC is provided, comprising:

[0008] Step 1, obtaining VFTC full process waveforms generated in the on-off process of GIS disconnectors in the non-fault state, wherein the VFTC full process waveforms are composed of a plurality of single breakdown oscillation waveforms;

[0009] Step 2, calculating the expectation and variance of the peak values of each single breakdown oscillation waveform in the non-fault state based on a Gaussian process regression model;

[0010] Step 3, setting upper and lower threshold values of the peak values of each single breakdown oscillation waveform based on the values of the expectation and variance, counting the proportion of the number of the peak values of each single breakdown oscillation waveform of the equipment to be diagnosed within the corresponding upper and lower threshold value range, and evaluating whether the equipment to be diagnosed generates a fault based on the proportion.

[0011] On the basis of the above technical solutions, the application can also be improved as follows.

[0012] Optionally, the obtaining process of the first single breakdown oscillation waveform in step 1 comprises:

[0013] Step 101, setting the sampling period of current data as ;

[0014] Step 102, calculating the current difference value between adjacent two sampling time points , wherein I n represents the current value at the nth sampling time point;

[0015] Step 103, when , judging that the first arc breakdown occurs, and recording the current time as the breakdown time ; after the breakdown time , judging that the arc extinguishment occurs when , and defining the current time as the arc extinguishment time ; and are set parameters;

[0016] Step 104, recording the current waveform between the breakdown time and the arc extinguishment time as the first single breakdown oscillation waveform : .

[0017] Optionally, the step 2 comprises:

[0018] Step 201, recording the breakdown time sequence , and p is the breakdown number; generating the breakdown time sequence to be estimated, wherein , , is the sampling period of the estimated breakdown time sequence;

[0019] Step 202, calculating the breakdown time sequence and the breakdown time sequence ; , , and ;

[0020] Step 203, using the single breakdown oscillation peak formation sequence and the breakdown time sequence to train a Gaussian process regression model to obtain hyperparameters, and using a conjugate gradient method to obtain the maximum value of the log-likelihood function of the training sample to obtain optimal hyperparameters based on the covariance matrix; the single breakdown oscillation peak formation sequence , ;

[0021] Step 204, obtaining a trained Gaussian process regression model based on the optimal hyperparameters, and using the trained Gaussian process regression model to obtain the expectation and variance of the peak value of each single breakdown oscillation waveform under fault-free conditions based on the covariance matrix.

[0022] Optionally, the formula of each covariance matrix in the step 202 is:

[0023] ;

[0024] , is the hyperparameter of the Gaussian process regression model, is the value corresponding to the two breakdown time sequences.

[0025] Optionally, the formula for calculating the optimal hyperparameters in the step 203 is:

[0026] ;

[0027] ; is the hyperparameter of the Gaussian process regression model.

[0028] Optionally, the formula for calculating the expectation and variance of the peak value of each single breakdown oscillation waveform under fault-free conditions in the step 204 is:

[0029] ;

[0030] N represents a normal distribution, represents the peak value prior mean of the single breakdown oscillation waveform.

[0031] Optionally, the upper and lower thresholds of the peak value of each single-breakdown oscillation waveform in step 3 are respectively: and ;

[0032] wherein n represents the serial number of the single-breakdown oscillation waveform, represents the expectation of the peak value of each single-breakdown oscillation waveform, represents the standard deviation of the peak value of each single-breakdown oscillation waveform.

[0033] Optionally, after step 3 judges that the device to be diagnosed is a faulty device, it further includes:

[0034] Step 4, calculating the VFTC oscillation peak expectation of the faulty device , based on the oscillation peak expectation and the expectation of the peak value of each single-breakdown oscillation waveform when there is no fault calculating the stroke relative error ;

[0035] Step 5, traversing the stroke relative error corresponding to the moment when the stroke relative error is maximum , according to the relative moment judging the fault type of the faulty device.

[0036] Optionally, the stroke relative error in step 4 is: ;

[0037] The calculation formula of the moment when the relative error is maximum is:

[0038] .

[0039] Optionally, step 5 includes:

[0040] If t is greater than 0, it means that the faulty device has a misalignment of opening and closing; otherwise, it means that the faulty device has a transmission jam.

[0041] The application provides a GIS disconnector mechanical state online evaluation method based on VFTC. BRIEF DESCRIPTION OF DRAWINGS

[0042] Figure 1 A flowchart of an embodiment of the GIS disconnector mechanical state online evaluation method based on VFTC provided by the application is shown in the figure.

[0043] Figure 2 A VFTC full-process waveform and single breakdown waveform schematic diagram provided by the embodiment of the application is shown in the figure.

[0044] Figure 3 A VFTC oscillation peak value expectation and variance distribution schematic diagram under normal conditions provided by the embodiment of the application is shown in the figure.

[0045] Figure 4 A fault abnormal point distribution schematic diagram provided by the embodiment of the application is shown in the figure.

[0046] Figure 5 A relative error maximum moment schematic diagram under different states provided by the embodiment of the application is shown in the figure. DETAILED DESCRIPTION

[0047] The principles and characteristics of the application are described below in combination with the drawings, and the examples are only used to explain the application and not to limit the scope of the application.

[0048] Figure 1 A flowchart of an embodiment of the GIS disconnector mechanical state online evaluation method based on VFTC provided by the application is shown in the figure. Figure 1 The online evaluation method comprises:

[0049] Step 1, obtaining a VFTC full-process waveform generated in the GIS disconnector opening and closing process under no fault, wherein the VFTC full-process waveform is composed of multiple single breakdown oscillation waveforms.

[0050] Step 2, calculating the expectation and variance of the peak value of each single breakdown oscillation waveform under no fault based on a Gaussian process regression model.

[0051] Step 3, setting upper and lower thresholds of the peak value of each single breakdown oscillation waveform based on the expected value and variance, calculating the proportion of the number of the peak values of each single breakdown oscillation waveform of the device to be diagnosed within the corresponding upper and lower threshold range, and evaluating whether the device to be diagnosed fails based on the proportion.

[0052] The VFTC-based GIS disconnector mechanical state online evaluation method provided by the application can realize online monitoring of the mechanical state of the GIS disconnector without periodic power-off disassembly and calibration, saves a large amount of manpower and material resources, can timely find various potential mechanical faults, avoids further development and deterioration of the faults, and guarantees stable operation of the GIS disconnector and the power system.

[0053] Embodiment 1

[0054] The embodiment 1 provided by the application is an embodiment of the VFTC-based GIS disconnector mechanical state online evaluation method provided by the application, which combines Figure 1 It can be known that the embodiment of the online evaluation method comprises:

[0055] Step 1, acquiring a VFTC full-process waveform generated in the process of opening and closing of the GIS disconnector when there is no fault, wherein the VFTC full-process waveform is composed of a plurality of single breakdown oscillation waveforms.

[0056] As Figure 2 shown is a schematic diagram of a VFTC full-process waveform and a single breakdown waveform provided by the embodiment of the application, in a possible embodiment manner, the VFTC full-process waveform in step 1 is decomposed into a plurality of single breakdown waveforms , wherein the acquisition process of the first single breakdown oscillation waveform comprises:

[0057] Step 101, setting the sampling period of the current data as .

[0058] Step 102, calculating the current difference value , between adjacent two sampling time points, wherein I n represents the current value at the n th sampling time point.

[0059] Step 103, when , it is judged that the first arc breakdown occurs, and the current time is recorded as the breakdown time ; after the breakdown time , it is judged that the arc extinguishment occurs when , and the current time is defined as the arc extinguishment time . and are set parameters.

[0060] In the specific implementation, and may be 100 and 28, respectively.

[0061] Step 104, record the current waveform between the breakdown time and the arc extinguishing time as the first single-breakdown oscillation waveform and the arc extinguishing time . .

[0062] record the current waveform between the breakdown time and the arc extinguishing time and the arc extinguishing time . , The expression is as follows:

[0063] .

[0064] Traverse the whole process waveform of the VFTC, if there are p breakdowns in the whole process, then the following set can be obtained according to the above formula:

[0065]

[0066] Step 2, calculate the expectation and variance of the peak value of each single-breakdown oscillation waveform in the fault-free state based on the Gaussian process regression model.

[0067] In a possible implementation manner, step 2 includes:

[0068] Step 201, record the breakdown time sequence , p is the number of breakdowns; generate the breakdown time sequence that needs to be estimated , wherein, , , is the sampling period of the estimated breakdown time sequence, which can be specified by a user.

[0069] Step 202, calculate each covariance matrix between the breakdown time sequence and the breakdown time sequence , , , and .

[0070] In a possible implementation manner, the formula of each covariance matrix in step 202 is as follows:

[0071] .

[0072] , is a hyperparameter of the Gaussian process regression model, is the value corresponding to the two breakdown time sequences. ​

[0073] Step 203, forming a sequence of single-break oscillation peak values and breakdown time sequence Training the Gaussian process regression model to obtain hyperparameters, based on the covariance matrix, using the conjugate gradient method to obtain the maximum value of the log-likelihood function of the training sample to obtain the optimal hyperparameters; forming a sequence of single-break oscillation peak values , .

[0074] In one possible implementation manner, the formula for calculating the optimal hyperparameters in step 203 is:

[0075] .

[0076] ; is the hyperparameter of the Gaussian process regression model.

[0077] Step 204, obtaining a trained Gaussian process regression model based on the optimal hyperparameters, using the trained Gaussian process regression model, based on the covariance matrix, to obtain the expectation and variance of the peak value of each single-break oscillation waveform under fault-free condition.

[0078] In one possible implementation manner, the formula for calculating the expectation and variance of the peak value of each single-break oscillation waveform under fault-free condition in step 204 is:

[0079] ;

[0080] N represents a normal distribution, represents the prior mean of the peak value of the single-break oscillation waveform, and generally takes a value of 0.

[0081] As shown in FIG. 3, the distribution of the expectation and variance of the VFTC oscillation peak value under normal condition is provided in the embodiment of the present application, and the expectation Figure 3 and variance are obtained in the embodiment. As shown in FIG. 3. Figure 3

[0082] Step 3, setting the upper and lower threshold values of the peak value of each single-break oscillation waveform based on the values of the expectation and variance, counting the proportion of the number of the peak values of each single-break oscillation waveform of the device to be diagnosed within the corresponding upper and lower threshold value range, and evaluating whether the device to be diagnosed has a fault based on the proportion.

[0083] In one possible implementation manner, the upper and lower threshold values of the peak value of each single-break oscillation waveform set in step 3 are respectively: and ; ​

[0084] wherein n represents the serial number of single breakdown oscillation waveform, represents the expectation of the peak value of each single breakdown oscillation waveform, represents the standard deviation of the peak value of each single breakdown oscillation waveform.

[0085] In the implementation, step 3 obtains the single breakdown oscillation peak value sequence of the equipment to be diagnosed and the breakdown time sequence , and the proportion of abnormal points is counted to determine whether the equipment is faulty, including:

[0086] Step 301, obtaining the VFTC full-process waveform of the equipment to be diagnosed, and extracting features to obtain the single breakdown oscillation peak value sequence and the breakdown time sequence . The label of each breakdown point is determined , and the formula is as follows:

[0087] .

[0088] If , it is considered that the point is a normal point, and if , it is considered that the point is an abnormal point.

[0089] Step 302, counting the proportion of abnormal points, and the specific formula is as follows:

[0090] .

[0091] Compare it with the significance level , if , it is considered that the equipment is normal, otherwise it is considered that the equipment is faulty, and in the embodiment 0.3 is taken, , so it is determined that the equipment has a fault, and as shown in Figure 4 , it is a fault abnormal point distribution diagram provided by the embodiment of the application, and the fault abnormal point in the embodiment is as shown in Figure 4 .

[0092] In one possible embodiment, after step 3 determines that the equipment to be diagnosed is a faulty equipment, it further includes:

[0093] Step 4, calculating the VFTC oscillation peak value expectation of the faulty equipment, and calculating the stroke relative error based on the oscillation peak value expectation and the expectation of the peak value of each single breakdown oscillation waveform when there is no fault .

[0094] In one possible embodiment, the stroke relative error : ;

[0095] the moment when the relative error is maximum The calculation formula is:

[0096] .

[0097] Step 5, traversing the travel relative error The moment when the relative error is maximum According to the relative moment Judge the fault type of the fault equipment.

[0098] In a possible embodiment, step 5 includes:

[0099] , indicates that the maximum value of the relative error appears at the end of the travel, indicating that the fault equipment fails to reach the position during closing and opening; otherwise, indicating that the fault equipment has transmission jam.

[0100] In the embodiments provided by the present application , it is judged that the transmission jam fault occurs in the equipment. As Figure 5 shown is a relative error maximum moment diagram in different states provided by the embodiments of the present application.

[0101] The embodiment of the present application provides a GIS disconnector mechanical state online evaluation method based on VFTC, directly monitors the final working link of the mechanical structure of the GIS disconnector, that is, the moving and static contacts, uses the VFTC generated during the closing and opening of the GIS disconnector to perform online evaluation on the mechanical state of the disconnector, and realizes comprehensive evaluation on the entire mechanical system; can realize non-stop online monitoring of the mechanical state of the GIS disconnector, without the need for periodic power-off disassembly and calibration, saving a lot of manpower and material resources, and at the same time, various potential mechanical faults can be found in time, avoiding further development and deterioration, and ensuring the stable operation of the GIS disconnector and the power system.

[0102] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0103] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can adopt a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) containing computer usable program code.

[0104] The present application is described in reference to the flowchart and / or block diagrams of the methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each block of the flowchart and / or block diagrams, and combinations of blocks in the flowchart and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart and / or block diagram block or blocks. Figure 1 The flowchart and / or block diagrams can also be implemented by the Figure 1 means for carrying out any one or more of the functionality described with respect to any one or more of the flowchart and / or block diagrams blocks.

[0105] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the flowchart and / or block diagram block or blocks. Figure 1 The flowchart and / or block diagrams can also be implemented by the Figure 1 means for carrying out any one or more of the functionality described with respect to any one or more of the flowchart and / or block diagrams blocks.

[0106] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the flowchart and / or block diagram block or blocks. Figure 1 The flowchart and / or block diagrams can also be implemented by the Figure 1 means for carrying out any one or more of the functionality described with respect to any one or more of the flowchart and / or block diagrams blocks.

[0107] While the preferred embodiments of the application have been described, additional variations and modifications can be made to the embodiments by those of skill in the art once they have the benefit of the present disclosure. Therefore, the appended claims are intended to cover all such modifications and variations as fall within the true spirit and scope of the application.

[0108] Obviously, numerous modifications and variations of the present application are possible in light of the above teachings. It is therefore to be understood that within the scope of the appended claims and their equivalents, the application can be practiced otherwise than as specifically described.

Claims

1. A GIS disconnector mechanical state online evaluation method based on VFTC, characterized in that, The online evaluation method comprises: Step 1, obtaining VFTC full-process waveforms generated in the on-off process of a GIS disconnector in a fault-free state, wherein the VFTC full-process waveforms are composed of multiple single breakdown oscillation waveforms; Step 2, calculating the expectation and variance of the peak value of each single breakdown oscillation waveform in the fault-free state based on a Gaussian process regression model; Step 3, setting upper and lower threshold values of the peak value of each single breakdown oscillation waveform based on the values of the expectation and variance, counting the proportion of the number of the peak values of each single breakdown oscillation waveform of a device to be diagnosed within the corresponding upper and lower threshold value range, and evaluating whether the device to be diagnosed generates a fault based on the proportion; The step 2 comprises: Step 201, record the breakdown time sequence , p is the breakdown times; generate the breakdown time sequence that needs to be estimated , wherein, , , is the sampling period of estimating the breakdown time sequence; Step 202, calculating between each covariance matrix between each covariance matrix , , and ; Step 203, forming a sequence of single-break oscillation peaks and the sequence of breakdown moments training a Gaussian process regression model to obtain hyperparameters, and using a conjugate gradient method to obtain optimal hyperparameters by maximizing a log-likelihood function of the training samples based on the covariance matrix; the sequence of single-break oscillation peaks , ; Step 204, obtaining a trained Gaussian process regression model based on the optimal hyperparameters, and using the trained Gaussian process regression model to obtain the expectation and variance of the peak value of each single breakdown oscillation waveform in the fault-free state based on the covariance matrix.

2. The online evaluation method according to claim 1, characterized in that, The obtaining process of the first single breakdown oscillation waveform in the step 1 comprises: Step 101, set the sampling period of the current data as ; Step 102, calculating the current difference value between two adjacent sampling time points , denotes the current value at the nth sampling time point; Step 103, when the first arc breakdown occurs, record the current time as the breakdown time ; after the breakdown time , determine when the arc extinguishes, define the current time as the arc extinguishing time ; and are set parameters; Step 104, recording the breakdown time The current waveform between the arc extinguishing time is the first single-breakdown oscillation waveform : .

3. The online evaluation method of claim 1, wherein, The formula of each covariance matrix in the step 202 is: ； , are hyperparameters of a Gaussian process regression model, are values corresponding to the two sequences of breakdown times.

4. The online evaluation method of claim 1, wherein, The formula for calculating the optimal hyperparameters in the step 203 is: ； ; are hyperparameters of the Gaussian process regression model.

5. The online evaluation method of claim 1, wherein, the step 204 of calculating the expectation of the peak value of each of the single-breakdown oscillation waveforms when there is no failure and the variance is given by the formula: ； N denotes a normal distribution, denotes the peak prior mean of the single-shot breakdown oscillation waveform.

6. The online evaluation method of claim 1, wherein, The upper and lower threshold values of the peak value of each single-breakdown oscillation waveform set in step 3 are respectively: and ; wherein n represents the number of the sequence of single breakdown oscillation waveforms, denotes the expectation of the peak value of each of the single breakdown oscillation waveforms, denotes the standard deviation of the peak value of each of the single breakdown oscillation waveforms.

7. The online evaluation method of claim 1, wherein, After the step 3 judges that the device to be diagnosed is a fault device, the method further comprises: Step 4, calculating a VFTC oscillation peak expectation for the faulty device based on the oscillation peak expectation and an expectation of the peak of each of the single-shot breakdown oscillation waveforms without fault to obtain a travel relative error ; Step 5, traversing to obtain the trip relative error The time corresponding to the maximum According to the time Determine the fault type of the faulty device.

8. The online evaluation method according to claim 7, characterized in that, The step 4 run relative error : ; The moment of maximum relative error The calculation formula is: 。 9. The online evaluation method of claim 7, wherein, The step 5 comprises: When the value of the parameter is 1, it indicates that the opening and closing of the fault device is not in place; otherwise, it indicates that the transmission of the fault device is stuck.

Images