A method, system and medium for diagnosing abnormal state of capacitor voltage transformer

Abstract

The present invention discloses a method, system and medium for diagnosing abnormal state of capacitor voltage transformer, which includes obtaining state data of target capacitor voltage transformer and capacitor voltage transformers of the same type thereof; calculating the horizontal fault detection index of the target capacitor voltage transformer, and determining whether the target capacitor voltage transformer has a fault according to the horizontal fault detection index, and if a fault occurs, performing a vertical comparison on the change of the state data of the target capacitor voltage transformer in the time dimension to determine the fault type corresponding to the target capacitor voltage transformer. The present invention can solve the problem of real-time evaluation of the healthy operation state of capacitor voltage transformer, can realize capacitor voltage transformer state diagnosis based on horizontal and vertical information fusion, effectively reduces the misdiagnosis probability of single target monitoring, and has the advantages of high diagnostic accuracy and easy acquisition of fault information.

Description

Technical Field

[0001] The invention relates to equipment status diagnosis technology, and in particular to a method, system and medium for diagnosing abnormal status of a capacitive voltage transformer. Background Art

[0002] Compared with electromagnetic voltage transformers, capacitive voltage transformers are gradually replacing electromagnetic voltage transformers due to their advantages such as high insulation strength, small size, light weight, and no ferromagnetic resonance. They are widely used in voltage measurement, power measurement, relay protection, and carrier communication in power systems. The measurement results of capacitive voltage transformers are an important basis for the normal operation of secondary metering, relay protection, and monitoring equipment, and are crucial for the safe and stable operation of power grids. However, due to the influence of factors such as raw materials, manufacturing experience, and system overvoltage, capacitive voltage transformers may experience capacitor divider failures, intermediate transformer failures, lightning arrester failures, and damper failures during operation. How to effectively monitor capacitive voltage transformers and promptly discover and eliminate operating failures of capacitive voltage transformers is of great significance to the safe and reliable operation of power grids.

[0003] Therefore, real-time monitoring of capacitor voltage transformers is particularly important in maintaining the temperature safety of the power grid. Real-time evaluation of the healthy operating status of capacitor voltage transformers can be carried out. When a capacitor voltage transformer fails, it can be immediately checked, the fault type can be accurately determined, and the fault can be alarmed, so that maintenance personnel can obtain fault information faster and solve it quickly. However, traditional capacitor voltage transformer monitoring and diagnosis methods have problems such as single judgment criteria, inappropriate operation monitoring times, and difficulty in obtaining fault information. Summary of the invention

[0004] Technical problem to be solved by the present invention: In view of the above-mentioned problems in the prior art, a method, system and medium for diagnosing abnormal status of a capacitor voltage transformer are provided. The present invention aims to solve the problem of real-time evaluation of the healthy operating status of a capacitor voltage transformer, and can realize capacitor voltage transformer status diagnosis based on horizontal and vertical information fusion, effectively reducing the misdiagnosis probability of single-target monitoring, and has the advantages of high diagnostic accuracy and easy acquisition of fault information.

[0005] In order to solve the above technical problems, the technical solution adopted by the present invention is:

[0006] A method for diagnosing abnormal state of a capacitive voltage transformer, comprising:

[0007] S101, obtaining status data of a target capacitor voltage transformer and capacitor voltage transformers of the same type as the target capacitor voltage transformer;

[0008] S102, calculating a transverse fault detection index of the target capacitor voltage transformer according to the state data of the target capacitor voltage transformer and the capacitor voltage transformer of the same type as the target capacitor voltage transformer, and determining whether the target capacitor voltage transformer fails according to the transverse fault detection index, and if the target capacitor voltage transformer fails, jumping to step S103;

[0009] S103, performing a longitudinal comparison on changes in the time dimension of the state data of the target capacitor voltage transformer to determine a fault type corresponding to the target capacitor voltage transformer.

[0010] Optionally, before step S101, the step of determining the same type of capacitor voltage transformer as the target capacitor voltage transformer is included: obtaining the number of capacitor voltage transformers of the same level in the single-phase line where the target capacitor voltage transformer is located; if the number exceeds a set value, the capacitor voltage transformers of the same level in the single-phase line where the target capacitor voltage transformer is located are used as capacitor voltage transformers of the same type as the target capacitor voltage transformer; otherwise, the capacitor voltage transformers of the same level in the three-phase line where the target capacitor voltage transformer is located are used as capacitor voltage transformers of the same type as the target capacitor voltage transformer.

[0011] Optionally, the state data in step S101 includes secondary voltage data of the capacitor voltage transformer collected at a set interval time t; and the calculation of the lateral fault detection index of the target capacitor voltage transformer in step S102 includes:

[0012] S201, for the target capacitor voltage transformer and the capacitor voltage transformer of the same type, respectively, according to the m secondary voltage data U1~U2 obtained by sampling in the current time window T m Calculate the centroid as the secondary voltage data U cen,i ;

[0013] S202, according to the secondary voltage data U of the target capacitor voltage transformer and the capacitor voltage transformer of the same type cen,i , calculate the voltage offset ΔU of the target capacitive voltage transformer cen,t ;

[0014] S203, according to the voltage offset ΔU cen,t Calculate the secondary voltage change rate ΔU of the target capacitor voltage transformer t %.

[0015] Optionally, in step S201, the centroid is calculated as the secondary voltage data U cen,i The function expression is:

[0016]

[0017] In the above formula, U cen,iis the secondary voltage data of any i-th capacitive voltage transformer, U1~U m are respectively m secondary voltage data sampled by the i-th capacitive voltage transformer in the current time window T, where m is the number of secondary voltage data sampled in the current time window T; the voltage offset ΔU in step S202 cen,t The calculation function expression is:

[0018] ΔU cen,t =|U cen,t-1 -U cen,t |

[0019] In the above formula, U cen,t-1 is the secondary voltage data of the capacitor voltage transformer adjacent to the target capacitor voltage transformer, and when the value of the index t of the target capacitor voltage transformer is 0, the capacitor voltage transformer adjacent to the target capacitor voltage transformer refers to the nth capacitor voltage transformer, n is the total number of the target capacitor voltage transformer and capacitor voltage transformers of the same type, U cen,t is the secondary voltage data of the target capacitor voltage transformer; the secondary voltage change rate ΔU in step S203 t The calculation function expression of % is:

[0020]

[0021] In the above formula, ΔU cen,t is the voltage offset of the target capacitor voltage transformer, U cen,t is the secondary voltage data of the target capacitor voltage transformer.

[0022] Optionally, determining whether a target capacitor voltage transformer has a fault according to the lateral fault detection index in step S102 includes: determining a secondary voltage change rate ΔU of the target capacitor voltage transformer t % Whether it is established within the specified change rate interval, if it is established, it is determined that the target capacitor voltage transformer is not faulty, otherwise it is determined that the target capacitor voltage transformer is faulty, where the specified change rate interval is:

[0023]

[0024] In the above formula, k is the capacitance voltage division ratio of the target capacitor voltage transformer when it is normal, k1 is the capacitance voltage division ratio of the target capacitor voltage transformer when the upper capacitor breaks down by 2%, k2 is the capacitance voltage division ratio of the target capacitor voltage transformer when the lower capacitor breaks down by 2%, and there are:

[0025]

[0026] Wherein, C1 is the upper capacitor of the target capacitor voltage transformer, and C2 is the lower capacitor of the target capacitor voltage transformer. Optionally, the longitudinal comparison in step S103 to determine the fault type corresponding to the target capacitor voltage transformer includes:

[0027] S301, inputting the secondary voltage data sampled by the target capacitor voltage transformer within the specified time window into the trained machine learning model to obtain the predicted secondary voltage U at the current moment pd ;

[0028] S302, according to ΔU ps =|U pd -U ps |Calculate the predicted secondary voltage U at the current moment pd , Actual secondary voltage data U ps The voltage offset ΔU between ps , and shift the voltage by ΔU ps Divide by the actual secondary voltage data U ps Get the secondary voltage change rate ΔU of the target capacitor voltage transformer at the current moment p %;

[0029] S303, determine whether the target capacitor voltage transformer's current moment and multiple consecutive secondary voltage change rates before the current moment exceed the set threshold value. If so, determine that the fault type of the target capacitor voltage transformer is a capacitor breakdown fault; otherwise, determine that the fault type of the target capacitor voltage transformer is an aging or moisture fault.

[0030] Optionally, after determining in step S303 that the fault type of the target capacitive voltage transformer is a capacitor breakdown fault, the method further includes determining the number h of the broken-down capacitors: determining the type of the secondary voltage data input into the machine learning model in step S301, and if the secondary voltage data is phase voltage data, then determining the type of the secondary voltage data according to ΔU p % = (h-1) × 100% determines the number h of the target capacitor voltage transformer breakdown capacitance; if the secondary voltage data is line voltage data, the number h of the target capacitor voltage transformer breakdown capacitance is determined according to the following formula:

[0031]

[0032] Among them, ΔU p % is the secondary voltage change rate of the target capacitor voltage transformer at the current moment.

[0033] Optionally, the status data in step S101 includes temperature rise data of a target capacitor voltage transformer; and step S103 further includes determining that an electromagnetic unit of the target capacitor voltage transformer fails when the temperature rise data of the target capacitor voltage transformer exceeds a set value.

[0034] In addition, the present invention also provides a capacitor voltage transformer abnormal state diagnosis system, comprising a microprocessor and a memory connected to each other, wherein the microprocessor is programmed or configured to execute the capacitor voltage transformer abnormal state diagnosis method.

[0035] In addition, the present invention also provides a computer-readable storage medium, in which a computer program is stored. The computer program is used to be programmed or configured by a microprocessor to execute the method for diagnosing abnormal conditions of a capacitor voltage transformer.

[0036] Compared with the prior art, the present invention mainly has the following advantages: the present invention includes obtaining the status data of the target capacitor voltage transformer and the capacitor voltage transformer of the same type as that of the target capacitor voltage transformer; calculating the lateral fault detection index of the target capacitor voltage transformer, and determining whether the target capacitor voltage transformer has a fault according to the lateral fault detection index; if a fault occurs, a longitudinal comparison is made on the change of the status data of the target capacitor voltage transformer in the time dimension to determine the fault type corresponding to the target capacitor voltage transformer. The present invention can solve the problem of real-time evaluation of the healthy operating status of the capacitor voltage transformer, realize the status diagnosis of the capacitor voltage transformer based on the lateral and longitudinal information fusion, effectively reduce the misdiagnosis probability of single-target monitoring, and has the advantages of high diagnostic accuracy and easy acquisition of fault information. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 Schematic diagram of the basic flow of the method of the embodiment of the present invention.

[0038] Figure 2 Schematic diagram of the structure of a capacitive voltage transformer involved in an embodiment of the present invention.

[0039] Figure 3 The figure is a schematic diagram of a process of determining a fault type in an embodiment of the present invention.

[0040] Figure 4 Schematic diagram of the basic structure of the system of the embodiment of the present invention. DETAILED DESCRIPTION

[0041] like Figure 1 As shown, the abnormal state diagnosis method of the capacitor voltage transformer in this embodiment includes:

[0042] S101, obtaining status data of a target capacitor voltage transformer and capacitor voltage transformers of the same type as the target capacitor voltage transformer;

[0043] S102, calculating a transverse fault detection index of the target capacitor voltage transformer according to the state data of the target capacitor voltage transformer and the capacitor voltage transformer of the same type as the target capacitor voltage transformer, and determining whether the target capacitor voltage transformer fails according to the transverse fault detection index, and if the target capacitor voltage transformer fails, jumping to step S103;

[0044] S103, performing a longitudinal comparison on changes in the time dimension of the state data of the target capacitor voltage transformer to determine a fault type corresponding to the target capacitor voltage transformer.

[0045] It should be noted that the present embodiment focuses on the processing of the target capacitor voltage transformer failure. Therefore, if the target capacitor voltage transformer does not fail in step S102, the required operation is selected as needed or no operation is performed. The required operation is generally selected to directly jump to step S101, delay the jump to step S101, or directly exit according to actual needs. For example, when the abnormal state diagnosis method of the capacitor voltage transformer of the present embodiment is applied to the monitoring of the capacitor voltage transformer, when the method of timing execution of steps S101 to S103 is adopted, when no fault occurs, it is generally selected to directly jump to step S101 or delay the jump to step S101. If the abnormal state diagnosis method of the capacitor voltage transformer of the present embodiment is applied to the one-time detection of the capacitor voltage transformer, it can be directly exited when no fault occurs. In addition, steps S101 to S103 in the present embodiment describe the abnormal state diagnosis method of the capacitor voltage transformer of the present embodiment from the perspective of a single target capacitor voltage transformer. Undoubtedly, based on the state data obtained in step S101, steps S102 and S103 can also be performed on the target capacitor voltage transformer and any one of its same type capacitor voltage transformers to determine whether a fault occurs and to determine the type of fault. The only difference is that it will additionally involve the traversal of multiple capacitor voltage transformers, but in the traversal processing link, steps S102 and S103 are still repeated.

[0046] The key to determining whether a target capacitor voltage transformer has a fault based on a lateral fault detection index in the abnormal state diagnosis method of a capacitor voltage transformer in the present embodiment is to determine capacitor voltage transformers of the same type. In order to improve the accuracy of determining whether a target capacitor voltage transformer has a fault based on a lateral fault detection index, the present embodiment includes a step of determining capacitor voltage transformers of the same type as the target capacitor voltage transformer before step S101: obtaining the number of capacitor voltage transformers of the same level in the single-phase line where the target capacitor voltage transformer is located; if the number exceeds a set value, the capacitor voltage transformers of the same level in the single-phase line where the target capacitor voltage transformer is located are used as capacitor voltage transformers of the same type as the target capacitor voltage transformer; otherwise, the capacitor voltage transformers of the same level in the three-phase line where the target capacitor voltage transformer is located are used as capacitor voltage transformers of the same type as the target capacitor voltage transformer.

[0047] Since both steps S102 and S103 require data from different time periods, when step S101 obtains the state data of the target capacitor voltage transformer and capacitor voltage transformers of the same type, it actually includes obtaining the state data of the target capacitor voltage transformer and capacitor voltage transformers of the same type at different time periods. By collecting the state data of multiple capacitor voltage transformer devices in the same power grid structure single-phase circuit at different time periods; by comparing each state data with the abnormal state indicator range of the abnormal state model and the abnormal state indicator range at different time points of the abnormal model, it can be used to determine whether to perform fault diagnosis; by comparing each monitoring indicator with the corresponding fault indicator combination and indicator range under different fault types of the fault model, it can be used to diagnose different fault types; by comparing each state data with each parameter indicator and indicator range in the fault parameter model, it can be used to evaluate the degree of the fault.

[0048] The state data of the capacitor voltage transformer can be selected according to actual needs. For example, as an optional implementation, the state data in step S101 of this embodiment includes the secondary voltage data of the capacitor voltage transformer collected at a set interval time t; the lateral fault detection index of the target capacitor voltage transformer calculated in step S102 includes:

[0049] S201, for the target capacitor voltage transformer and the capacitor voltage transformer of the same type, respectively, according to the m secondary voltage data U1~U2 obtained by sampling in the current time window T m Calculate the centroid as the secondary voltage data U cen,i ;

[0050] S202, according to the secondary voltage data U of the target capacitor voltage transformer and the capacitor voltage transformer of the same type cen,i , calculate the voltage offset ΔU of the target capacitive voltage transformercen,t ;

[0051] S203, according to the voltage offset ΔU cen,t Calculate the secondary voltage change rate ΔU of the target capacitor voltage transformer t %.

[0052] In this embodiment, the centroid is calculated in step S201 as the secondary voltage data U cen,i The function expression is:

[0053]

[0054] In the above formula, U cen,i is the secondary voltage data of any i-th capacitive voltage transformer, U1~U m They are respectively m secondary voltage data sampled by the i-th capacitive voltage transformer in the current time window T, and m is the number of secondary voltage data sampled in the current time window T.

[0055] In this embodiment, the voltage offset ΔU in step S202 cen,t The calculation function expression is:

[0056] ΔU cen,t =|U cen,t-1 -U cen,t |

[0057] In the above formula, U cen,t-1 is the secondary voltage data of the capacitor voltage transformer adjacent to the target capacitor voltage transformer, and when the value of the index t of the target capacitor voltage transformer is 0, the capacitor voltage transformer adjacent to the target capacitor voltage transformer refers to the nth capacitor voltage transformer, n is the total number of the target capacitor voltage transformer and capacitor voltage transformers of the same type, U cen,t is the secondary voltage data of the target capacitor voltage transformer. The total number of the target capacitor voltage transformer and its same type capacitor voltage transformer is n, so the voltage offset of n capacitor voltage transformers is:

[0058] ΔU cen,1 =|U cen,2 -U cen,1 |

[0059] ΔU cen,2 =|U cen,3 -U cen,2 |

[0060] ΔU cen,3 =|U cen,4 -U cen,3 | ...

[0061] ΔU cen,n =|U cen,1 -U cen,n |

[0062] In the above formula, ΔU cen,1 ~ΔU cen,n are the voltage offsets of the 1st to nth capacitive voltage transformers, U cen,1 ~U cen,n They are the secondary voltage data of the 1st to nth capacitive voltage transformers respectively.

[0063] In this embodiment, the secondary voltage change rate ΔU in step S203 t The calculation function expression of % is:

[0064]

[0065] In the above formula, ΔU cen,t is the voltage offset of the target capacitor voltage transformer, U cen,t is the secondary voltage data of the target capacitor voltage transformer, and the secondary voltage change rate of n capacitor voltage transformers is:

[0066]

[0067]

[0068] ...

[0069]

[0070] In the above formula, ΔU1%~ΔU n % are the secondary voltage change rates of the 1st to nth capacitive voltage transformers, ΔU cen,1 ~ΔU cen,n are the voltage offsets of the 1st to nth capacitive voltage transformers, U cen,1 ~U cen,n They are the secondary voltage data of the 1st to nth capacitive voltage transformers respectively.

[0071] In this embodiment, determining whether a target capacitor voltage transformer has a fault according to the lateral fault detection index in step S102 includes: determining the secondary voltage change rate ΔU of the target capacitor voltage transformer t % Whether it is established within the specified change rate interval, if so, it is determined that the target capacitor voltage transformer is not faulty, otherwise it is determined that the target capacitor voltage transformer is faulty, wherein the specified change rate interval can be specified according to an empirical value.

[0072] like Figure 2As shown, one end of the capacitor voltage transformer is connected to the secondary voltage side, and the other end is grounded through a carrier device. The capacitor voltage transformer is composed of an upper capacitor and a lower capacitor connected in series. Figure 2 The capacitor C1 close to the secondary voltage side is the upper capacitor, and the capacitor C2 close to the carrier device side is the lower capacitor. The intermediate node UC1 between the upper capacitor and the lower capacitor is grounded to a terminal AT on the secondary side of the transformer T. The other terminal XT on the secondary side of the transformer T is grounded through a fuse F, and the fuse F is connected in parallel with an inductor L. U1 is the total voltage of the upper capacitor and the lower capacitor in series. As an optional implementation, in this embodiment, referring to the requirement of the initial value difference of capacitance ≤±2% (warning value) in the "Test Procedure for Status Inspection of Power Transmission and Transformation Equipment", let the upper capacitor be C1 and the lower capacitor be C2, then it can be known that the capacitance divider ratio of the target capacitive voltage transformer when it is normal is:

[0073]

[0074] When the upper capacitor breaks down by 2%, the capacitor voltage divider ratio is:

[0075]

[0076] Therefore, the upper threshold of the secondary voltage change rate ΔU a % (this is the threshold of the voltage imbalance rate calculated based on the CVT capacitor, divided into an upper limit and a lower limit, and the measured voltage data is compared with the threshold):

[0077]

[0078] When the lower capacitor breaks down by 2%, the capacitor voltage divider ratio is:

[0079]

[0080] Therefore, the lower threshold of the secondary voltage change rate ΔU b %for:

[0081]

[0082] Similarly, when the upper power-saving capacity and the lower power-saving capacity decrease by 2%, the change rates of their secondary voltages are shown in the following formulas:

[0083]

[0084]

[0085] When the equipment is operating normally, the voltage fluctuation range of the secondary side of the capacitor voltage transformer should be within the upper and lower limits of the set threshold. Because C2 is much larger than C1, the sequence relationship ΔU a '%<ΔU b%<0<ΔU a %<ΔU b '% is obvious, the phase voltage range is:

[0086]

[0087] The corresponding line voltage is expressed by the voltage division ratio, and its change rate range can be:

[0088]

[0089] In the above formula, k is the capacitance voltage division ratio of the target capacitor voltage transformer when it is normal, k1 is the capacitance voltage division ratio of the target capacitor voltage transformer when the upper capacitor breaks down by 2%, k2 is the capacitance voltage division ratio of the target capacitor voltage transformer when the lower capacitor breaks down by 2%, and there are:

[0090]

[0091] Wherein, C1 is the upper capacitance of the target capacitor voltage transformer, and C2 is the lower capacitance of the target capacitor voltage transformer.

[0092] Therefore, in order to improve the accuracy of fault judgment, in this embodiment, the specified change rate interval for judging whether the target capacitor voltage transformer has a fault is:

[0093]

[0094] In step S103, a longitudinal comparison is performed, i.e., a strategy for finding information differences in the historical data of a single device. Specifically, the secondary voltage historical data of a CVT device in a busbar of a power station is compared with the current data to obtain the secondary voltage change information of the CVT device. Figure 3 As shown, in step S103 of this embodiment, the longitudinal comparison is performed to determine the fault type corresponding to the target capacitor voltage transformer, including:

[0095] S301, inputting the secondary voltage data sampled by the target capacitor voltage transformer within the specified time window into the trained machine learning model to obtain the predicted secondary voltage U at the current moment pd ;

[0096] S302, according to ΔU ps =|U pd -U ps |Calculate the predicted secondary voltage U at the current moment pd , Actual secondary voltage data U ps The voltage offset ΔU between ps , and shift the voltage by ΔU ps Divide by the actual secondary voltage data U psGet the secondary voltage change rate ΔU of the target capacitor voltage transformer at the current moment p %;

[0097] S303, determine whether the target capacitor voltage transformer's current moment and multiple consecutive secondary voltage change rates before the current moment exceed the set threshold value. If so, determine that the fault type of the target capacitor voltage transformer is a capacitor breakdown fault; otherwise, determine that the fault type of the target capacitor voltage transformer is an aging or moisture fault.

[0098] Because the CVT equipment in the circuit is more or less affected by factors such as the system and the environment, a certain secondary voltage fluctuation occurs, which inevitably interferes with fault identification and easily causes misjudgment. Therefore, in step S301 of this embodiment, the secondary voltage data sampled by the target capacitive voltage transformer within the specified time window is input into the trained machine learning model to obtain the predicted secondary voltage U at the current moment. pd To improve the accuracy of predicting the secondary voltage (ideal value). Among them, the machine learning model can adopt an existing machine learning model as needed. For example, in this embodiment, a long short-term memory neural network (Long Short Term Memory, LSTM) prediction method is specifically used for voltage prediction. The prediction model is used to predict the sample to be tested. The voltage data of a certain period of time is input into the model to obtain the predicted voltage data. The secondary side voltage change rate is calculated through the actual voltage data and the predicted voltage data, and compared with the threshold value to perform fault diagnosis.

[0099] Taking into account that the secondary voltage of the equipment fluctuates due to uncertain factors such as the environment and power load, step S303 determines whether the secondary voltage change rate of the target capacitor voltage transformer at the current moment and multiple consecutive (specific selection can be made according to actual needs) moments before the current moment exceeds the set threshold. If so, the fault type of the target capacitor voltage transformer is determined to be a capacitor breakdown fault; otherwise, the fault type of the target capacitor voltage transformer is determined to be an aging or moisture fault.

[0100] See also Figure 3 In this embodiment, after determining that the fault type of the target capacitor voltage transformer is a capacitor breakdown fault in step S303, the number of broken-down capacitors h is further determined. According to the rate of change of the phase voltage and the line voltage, the number of capacitor breakdowns of the capacitor voltage transformer equipment can be determined (it means that if a faulty capacitor voltage transformer is detected on a bus, the number of broken-down capacitors in the capacitor voltage transformer can be determined according to this formula). For example, the number of broken-down capacitors of the capacitor voltage transformer h is:

[0101]

[0102] Where n2 is the number of cells in the initial lower capacitor, n'2 is the number of cells in the lower capacitor after breakdown (if the lower capacitor is not broken down, it remains unchanged), N is the total number of initial capacitor cells, and N' is the total number of capacitor cells after breakdown. Therefore, according to the rate of change of phase voltage and line voltage, the number of broken-down capacitors h can be inferred. Specifically, in this embodiment, determining the number of broken-down capacitors h includes: judging the type of secondary voltage data input into the machine learning model in step S301, if the secondary voltage data is phase voltage data, then according to ΔU p % = (h-1) × 100% determines the number h of the target capacitor voltage transformer breakdown capacitance; if the secondary voltage data is line voltage data, the number h of the target capacitor voltage transformer breakdown capacitance is determined according to the following formula:

[0103]

[0104] Among them, ΔU p % is the secondary voltage change rate of the target capacitor voltage transformer at the current moment.

[0105] See also Figure 3 As an optional implementation, the state data in step S101 of this embodiment includes the temperature rise data of the target capacitor voltage transformer; step S103 also includes determining that the electromagnetic unit of the target capacitor voltage transformer fails when the temperature rise data of the target capacitor voltage transformer exceeds the set value. Further, other abnormal state monitoring can be performed as needed, including monitoring indicators such as capacitance value, equipment temperature, equipment dielectric loss, operating environment humidity and vibration intensity, which can be coordinated with the secondary side voltage change rate indicator to reduce the misjudgment rate. The abnormal state indicator range is the numerical interval of each comprehensive indicator when the equipment is in an abnormal state. The relevant interval threshold setting can refer to parameter indicators or experimental data. When the monitoring indicator exceeds or is lower than the abnormal state indicator, the fault is judged. The fault indicator combination and indicator range are the characteristics of different indicators when different faults occur, or the characteristic interval in which they are located. When the monitoring indicator meets its fault characteristics and a certain indicator or several indicators are in the fault characteristic interval, the fault is diagnosed. Based on the combination of fault indicators and indicator range, the degree of occurrence of abnormal status indicators and different fault types are distinguished, the fault level is divided, the monitoring indicators are compared with the fault level indicators, the fault level is judged, and the priority of fault handling is divided accordingly.

[0106] In summary, the method of this embodiment can solve the technical problem of how to evaluate the healthy operating status of a capacitor voltage transformer in real time. The method of this embodiment adopts capacitor voltage transformer status monitoring based on horizontal and vertical information fusion, which effectively reduces the misdiagnosis probability of single-target monitoring.

[0107] In addition, the present invention also provides a capacitor voltage transformer abnormal state diagnosis system, comprising a microprocessor and a memory connected to each other, and the microprocessor is programmed or configured to execute the capacitor voltage transformer abnormal state diagnosis method.

[0108] like Figure 4 As shown, the abnormal state diagnosis system (monitoring diagnosis system) of the capacitor voltage transformer in this embodiment includes:

[0109] Index parameter collection layer: used to collect monitoring indicators of different monitoring points of multiple different capacitor voltage transformer devices in the same power grid structure, mainly including CVT (capacitor voltage transformer) secondary voltage data and CVT electromagnetic unit temperature data, and upload the monitoring indicators to the cloud;

[0110] Indicator parameter analysis layer: Use the cloud platform to compare and analyze the monitoring indicators collected by the acquisition layer, and analyze and determine whether the CVT secondary voltage data and CVT electromagnetic unit temperature data are within the normal threshold range. Its analysis model includes abnormal state model, fault model, and parameter model;

[0111] Fault status assessment layer: assess whether the CVT equipment has a capacitor unit fault or an electromagnetic unit fault (if the CVT secondary voltage change exceeds the threshold range, it is judged as a capacitor unit fault; if the infrared temperature measurement shows that the electromagnetic unit temperature is abnormal, it is an electromagnetic unit fault), and then conduct detailed diagnosis of different fault locations (capacitor unit faults generally include capacitor breakdown, capacitor aging, etc.; electromagnetic unit faults generally include core short circuit, abnormal partial discharge, turn-to-turn short circuit, etc.), and then display the fault indicators and fault types to the maintenance personnel's mobile communication equipment for real-time acquisition of equipment information.

[0112] Furthermore, the abnormal state diagnosis system (monitoring diagnosis system) of the capacitive voltage transformer in this embodiment is also connected to a terminal device, which can be divided into five modules according to its function: a data signal acquisition module, a DSP data processing module, an MCU system control module, a data storage module, and a human-computer interaction module. Its main functions include:

[0113] Data signal acquisition module: used to receive processed monitoring data indicators transmitted from the cloud.

[0114] DSP data processing module: used to receive the monitoring data transmitted by the data signal acquisition module, and form an instant visual fault view according to the set criteria.

[0115] MCU system control module: responsible for data control and management.

[0116] Data storage module: used to store monitoring data.

[0117] Human-computer interaction module: used to interact with maintenance workers, including keyboard control, display screen, etc.

[0118] The abnormal state diagnosis system of the capacitor voltage transformer in this embodiment can collect detection indicators of various monitoring points through intelligent sensors, and judge whether the equipment is abnormal by comparing the abnormal state model, fault model, parameter model and various monitoring indicators. If there is an abnormality, the fault type and fault size are judged, thereby realizing real-time monitoring of the capacitor voltage transformer, and transmitting the real-time fault information of the equipment to the cloud, and then transmitting it from the cloud to the mobile communication device of the maintenance personnel, so that the maintenance personnel can quickly, accurately and timely obtain various fault indicator information, and take corresponding maintenance measures for the fault. The monitoring indicators of multiple different capacitor voltage transformers of the same level in a single-phase bus structure of a power station at different time periods, especially the secondary voltage data, can be collected to identify capacitor breakdown faults; by comparing each monitoring indicator with the abnormal state indicator range of the abnormal state model and setting the number of monitoring times, it is used to determine whether to perform fault diagnosis; by comparing each monitoring indicator with the corresponding fault indicator combination and indicator range under different fault types of the fault model, it is used to diagnose different fault types; by comparing each monitoring indicator with each parameter indicator and indicator range in the fault parameter model, it is used to determine the fault level and evaluate the degree of the fault; the monitoring indicators mainly refer to the difference in the secondary voltage change rate between different target models, and the fluctuation of the secondary voltage change rate of a single model in different time periods. This horizontal and vertical method is used to identify capacitor breakdown faults. The relevant parameter indicator settings of capacitor voltage transformer equipment can be obtained by consulting relevant information or through historical experience.

[0119] In the implementation of this scheme, when the monitoring index exceeds or falls below the abnormal state index, the fault is judged. The most important index is the voltage amplitude index on the secondary side of the capacitor voltage transformer, and different line voltages and phase voltage levels have different judgment thresholds, so there are also differences in the voltage amplitude non-alarm interval. For example, through calculation, the voltage amplitude non-alarm interval of the voltage level of 110kV and below is selected from -10% to +10% of the set value, while the voltage amplitude non-alarm interval of the 220kV voltage level is selected from -5% to +5% of the set value, and the voltage amplitude non-alarm interval of the 500kv voltage level is selected from -3% to +3% of the set value. When setting the alarm limit, it should be noted that there should be sufficient sensitivity, that is, the set limit should be smaller than the calculated value, and the sensitivity should be greater than 1; there will be no frequent alarms due to disturbances in the grid voltage, that is, the size of the set limit should be based on the stable level of the grid voltage, not too low, and can be gradually corrected according to the number of false alarms. When the monitoring index exceeds the non-alarm interval, it is determined to be an abnormal state. In the implementation of this solution, different intelligent sensors are used to collect and monitor the monitoring index data of different monitoring points of the capacitor voltage transformer equipment, such as secondary voltage, equipment temperature, capacitance value, equipment dielectric loss, operating environment humidity and vibration intensity. Among them, the intelligent sensor mainly monitors the change of the secondary voltage of the capacitor voltage transformer to determine the equipment capacitor breakdown fault, while other types of faults such as electromagnetic unit component failure and poor contact of the secondary terminal can be combined with infrared temperature measurement methods for joint judgment. In the implementation of this solution, by comparing the abnormal state model, fault model, parameter model with various monitoring indicators, the monitoring results and fault parameter results can be transmitted to the maintenance personnel or to the cloud platform through the cloud for the maintenance personnel to alarm. The cloud platform can also provide a basis for the function of providing a report of the monitoring data change curve, where the communication means are mobile communication, Internet of Things, wireless network and optical fiber communication. The intelligent sensor uploads the monitoring indicators to the cloud platform, uses the computing power of the cloud platform to process the parameters of various indicators, and compares the abnormal state model, fault model and parameter model to perform fault diagnosis. The system can be structured in a terminal storage medium for use by an instruction execution system, device or equipment (such as a system based on a mobile device, a system including a processing module, or other system that can fetch instructions from an instruction execution system, device or equipment and execute instructions), or in combination with these instruction execution systems, devices or equipment. For the purpose of this specification, "terminal readable medium" can be any device that can contain, store, communicate, propagate or transmit programs for use by an instruction execution system, device or equipment, or in combination with these instruction execution systems, devices or equipment. For example, when the system is structured on a mobile communication device, maintenance personnel can quickly obtain relevant monitoring indicator information of capacitor voltage transformers in the power grid through mobile devices. If a fault occurs, the cloud platform can also transmit the fault type and related fault indicators to the mobile device for maintenance personnel to accurately and quickly handle it.In summary, the horizontal and vertical information fusion monitoring and diagnosis system for the abnormal state of the capacitive voltage transformer adopted in this embodiment uploads the monitoring index information to the cloud through the intelligent sensor equipment, processes various indicators through the cloud platform, and transmits the fault information to the terminal device, that is, the mobile communication device of the maintenance personnel, thereby reducing the time of obtaining fault information and improving the maintenance efficiency.

[0120] In addition, the present invention also provides a computer-readable storage medium, in which a computer program is stored. The computer program is used to be programmed or configured by a microprocessor to execute the method for diagnosing abnormal conditions of a capacitor voltage transformer.

[0121] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may take the form of a computer program product implemented on one or more computer-readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes. The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, may be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the functions in the process. Figure 1 A process or multiple processes and / or boxes Figure 1 These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing device to work in a specific way, so that the instructions stored in the computer-readable memory produce a product including an instruction device, which implements the functions specified in the process. Figure 1 A process or multiple processes and / or boxes Figure 1 These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide for implementing the process in the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0122] The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technicians in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.

Claims

1. A method for diagnosing abnormal state of a capacitor voltage transformer, characterized in that: include: S101, obtaining status data of a target capacitor voltage transformer and capacitor voltage transformers of the same type as the target capacitor voltage transformer; S102, calculating a transverse fault detection index of the target capacitor voltage transformer according to the state data of the target capacitor voltage transformer and the capacitor voltage transformer of the same type as the target capacitor voltage transformer, and determining whether the target capacitor voltage transformer fails according to the transverse fault detection index, and if the target capacitor voltage transformer fails, jumping to step S103; S103, performing a longitudinal comparison on the change of the state data of the target capacitor voltage transformer in the time dimension to determine the fault type corresponding to the target capacitor voltage transformer; The longitudinal comparison in step S103 to determine the fault type corresponding to the target capacitor voltage transformer includes: S301, inputting the secondary voltage data sampled by the target capacitor voltage transformer within the specified time window into the trained machine learning model to obtain the predicted secondary voltage at the current moment U pd ; S302, according to Δ U ps =| U pd - U ps |Calculate the predicted secondary voltage at the current moment U pd , Actual secondary voltage data U ps The voltage offset between U ps , and shift the voltage by Δ U ps Divide by the actual secondary voltage data U ps Get the secondary voltage change rate Δ of the target capacitor voltage transformer at the current moment U p %; S303, determine whether the target capacitor voltage transformer's current moment and multiple consecutive secondary voltage change rates before the current moment exceed the set threshold value. If so, determine that the fault type of the target capacitor voltage transformer is a capacitor breakdown fault; otherwise, determine that the fault type of the target capacitor voltage transformer is an aging or moisture fault.

2. The abnormal state diagnosis method of a capacitor voltage transformer according to claim 1, characterized in that: Before step S101, the step of determining the same type of capacitor voltage transformer as the target capacitor voltage transformer is included: obtaining the number of capacitor voltage transformers of the same level in the single-phase line where the target capacitor voltage transformer is located; if the number exceeds a set value, the capacitor voltage transformers of the same level in the single-phase line where the target capacitor voltage transformer is located are used as capacitor voltage transformers of the same type as the target capacitor voltage transformer; otherwise, the capacitor voltage transformers of the same level in the three-phase line where the target capacitor voltage transformer is located are used as capacitor voltage transformers of the same type as the target capacitor voltage transformer.

3. The abnormal state diagnosis method of a capacitor voltage transformer according to claim 1, characterized in that: The state data in step S101 includes the secondary voltage data of the capacitor voltage transformer collected at the set interval time t; the lateral fault detection index of the target capacitor voltage transformer calculated in step S102 includes: S201, for the target capacitor voltage transformer and the capacitor voltage transformer of the same type, respectively obtain the m Secondary voltage data U 1~ U m Calculate the centroid as secondary voltage data U cen,i ; S202, according to the secondary voltage data of the target capacitor voltage transformer and the capacitor voltage transformer of the same type U cen,i , calculate the voltage offset Δ of the target capacitive voltage transformer U cen,t ; S203, according to the voltage offset Δ U cen,t Calculate the secondary voltage change rate Δ of the target capacitor voltage transformer U t %.

4. The abnormal state diagnosis method of a capacitor voltage transformer according to claim 3, characterized in that: In step S201, the centroid is calculated as the secondary voltage data U cen,i The function expression is: In the above formula, U cen,i For any i Secondary voltage data of a capacitor voltage transformer, U 1~ U m Respectively i The capacitance voltage transformer is sampled in the current time window T. m Secondary voltage data, m is the number of secondary voltage data sampled within the current time window T; the voltage offset Δ in step S202 U cen,t The calculation function expression is: D U cen,t =| U cen,t-1 - U cen,t | In the above formula, U cen,t-1 is the secondary voltage data of the capacitor voltage transformer adjacent to the target capacitor voltage transformer, and the index of the target capacitor voltage transformer is t When the value of is 0, the capacitor voltage transformer adjacent to the target capacitor voltage transformer is the first n Capacitive voltage transformer, n is the total number of the target capacitor voltage transformer and its same type capacitor voltage transformers, U cen,t is the secondary voltage data of the target capacitor voltage transformer; the secondary voltage change rate Δ in step S203 U t The calculation function expression of % is: In the above formula, Δ U cen,t is the voltage offset of the target capacitor voltage transformer, U cen,t is the secondary voltage data of the target capacitor voltage transformer.

5. The abnormal state diagnosis method of a capacitor voltage transformer according to claim 3, characterized in that: In step S102, determining whether a target capacitor voltage transformer has a fault according to the lateral fault detection index includes: determining a secondary voltage change rate Δ of the target capacitor voltage transformer U t % Whether it is established within the specified change rate interval, if it is established, it is determined that the target capacitor voltage transformer is not faulty, otherwise it is determined that the target capacitor voltage transformer is faulty, where the specified change rate interval is: In the above formula, k is the capacitance voltage division ratio of the target capacitive voltage transformer when it is normal, k 1 is the capacitance voltage divider ratio of the target capacitor voltage transformer when the upper capacitor breaks down by 2%, k 2 is the capacitance voltage division ratio of the target capacitive voltage transformer when the lower capacitor breaks down by 2%, and: ， ， ， in, C 1 is the upper capacitance of the target capacitive voltage transformer, C 2 is the lower capacitance of the target capacitive voltage transformer.

6. The abnormal state diagnosis method of a capacitor voltage transformer according to claim 1, characterized in that: After determining in step S303 that the fault type of the target capacitor voltage transformer is a capacitor breakdown fault, the method further includes determining the number of capacitors that are broken down. h : Determine the type of secondary voltage data input into the machine learning model in step S301. If the secondary voltage data is phase voltage data, then Determine the amount of breakdown capacitance of the target capacitor voltage transformer h ; If the secondary voltage data is line voltage data, the number of capacitor breakdown capacitors of the target capacitor voltage transformer is determined according to the following formula: h : Among them, Δ U p % is the secondary voltage change rate of the target capacitor voltage transformer at the current moment.

7. The abnormal state diagnosis method of a capacitor voltage transformer according to claim 1, characterized in that: The state data in step S101 includes temperature rise data of the target capacitor voltage transformer; and step S103 also includes determining that the electromagnetic unit of the target capacitor voltage transformer fails when the temperature rise data of the target capacitor voltage transformer exceeds a set value.

8. A capacitive voltage transformer abnormal state diagnosis system, comprising a microprocessor and a memory connected to each other, characterized in that: The microprocessor is programmed or configured to execute the abnormal state diagnosis method of a capacitor voltage transformer as claimed in any one of claims 1 to 7.

9. A computer-readable storage medium having a computer program stored therein, characterized in that: The computer program is used to be programmed or configured by a microprocessor to execute the abnormal state diagnosis method of a capacitor voltage transformer as claimed in any one of claims 1 to 7.

Images