Gas-insulated combined equipment state prediction model construction method and state prediction method

Abstract

The present invention provides a method for constructing a state prediction model of a gas-insulated combined device and a state prediction method. The method for constructing a state prediction model of a gas-insulated combined device includes: obtaining partial discharge history data, equipment characteristic parameter history data, and operation history data of the gas-insulated combined device, wherein the equipment characteristic parameter history data includes equipment characteristic parameter history data of electrical components whose failure rate exceeds a preset value; determining the historical state results of the gas-insulated combined device according to the partial discharge history data, the equipment characteristic parameter history data, and the operation history data; establishing a training set according to the partial discharge history data, the equipment characteristic parameter history data, the operation history data, and the corresponding historical state results; and training a long short-term memory network model through the training set to obtain a state prediction model of the gas-insulated combined device. Through the present invention, the state of the gas-insulated combined device is predicted in all aspects to ensure safe and stable operation.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of electric power, and in particular to a method for constructing a state prediction model of a gas-insulated combined equipment and a state prediction method. Background Art

[0002] As one of the core equipment of the power system, the health status of Gas Insulated Switchgear (GIS) is closely related to the safe operation of the power system. During the long-term operation of GIS, it is affected by many factors such as chemical stress, thermal stress, electrical stress and mechanical stress, and various failures are inevitable.

[0003] At present, the research on GIS status prediction mainly focuses on a certain equipment inside GIS. For example, an insulation electric field degradation calculation model is established for GIS busbar, and the electric field degradation characteristics of several typical latent faults such as metal tip, metal particles, and insulator air gap are analyzed. The central limit theorem is used to estimate the fault probability of different fault types and provide restriction measures; for the SF6 gas density, pressure and temperature data inside GIS, the Seq2Seq time series prediction model is used to predict the SF6 gas state; for the basin insulator inside GIS, an insulator state prediction method based on mass loss rate is proposed. However, there are multiple equipment combinations inside GIS, and it is necessary to combine the state quantities of multiple types of equipment to comprehensively predict the overall health status of GIS. Summary of the invention

[0004] In order to comprehensively predict the state of a gas-insulated combined device and ensure the safe and stable operation of the gas-insulated combined device, the present invention proposes a method for constructing a state prediction model for a gas-insulated combined device and a state prediction method.

[0005] In a first aspect, the present invention provides a method for constructing a state prediction model of a gas-insulated combined device, the method comprising:

[0006] Obtaining partial discharge historical data, equipment characteristic parameter historical data, and operation historical data of gas-insulated combined equipment, wherein the equipment characteristic parameter historical data includes equipment characteristic parameter historical data of electrical components in the gas-insulated combined equipment whose failure rate exceeds a preset value;

[0007] Determine the historical status results of the gas-insulated combined equipment based on the partial discharge historical data, equipment characteristic parameter historical data, and operation historical data;

[0008] A training set is established based on the partial discharge historical data, the equipment characteristic parameter historical data, the operation historical data, and the corresponding historical status results;

[0009] The long short-term memory network model is trained through the training set to obtain the gas-insulated combination equipment state prediction model.

[0010] Considering that the existing prediction method for gas-insulated combination equipment is aimed at predicting the state of a single electrical component inside the equipment, the equipment characteristic parameters of the single electrical component are used in the prediction process. However, the gas-insulated combination equipment contains multiple electrical components, and the equipment characteristic parameters of each electrical component are also different. Therefore, through the method provided in the embodiment of the present invention, from the perspective of gas-insulated combination equipment failure, the equipment characteristic parameters of electrical components with a higher failure rate are selected to construct a gas-insulated combination equipment state prediction model. Through this prediction model, the state of the gas-insulated combination equipment can be predicted in all aspects, thereby ensuring the safe and stable operation of the gas-insulated combination equipment and improving the level of smart operation and maintenance and intelligent scheduling of the power grid.

[0011] In combination with the first aspect, in a first embodiment of the first aspect, obtaining historical data of equipment characteristic parameters of a gas-insulated combined equipment includes:

[0012] Obtain the failure rate of each electrical component in the gas-insulated combined equipment;

[0013] According to the failure rate of each electrical component, select an electrical component whose failure rate is greater than a preset value;

[0014] The equipment characteristic parameter historical data corresponding to the electrical component having a failure rate greater than a preset value is determined as the equipment characteristic parameter historical data of the gas-insulated combination device.

[0015] In combination with the first aspect, in a second embodiment of the first aspect, determining a historical status result of the gas-insulated combination device according to the partial discharge historical data, the device characteristic parameter historical data, and the operation historical data includes:

[0016] Determine the operation state membership vector of each historical data according to the partial discharge historical data, the equipment characteristic parameter historical data and the operation historical data;

[0017] According to the operation status membership vector of each data and the corresponding weight, the historical status result of the gas-insulated combination equipment is determined.

[0018] In combination with the first aspect, in a third embodiment of the first aspect, the historical data of equipment characteristic parameters include at least one of SF6 gas density, main circuit resistance, gas pressure of the pneumatic mechanism, number of operations, and temperature at the connection point of the outlet bushing.

[0019] In combination with the first aspect or the third embodiment of the first aspect, in a fourth embodiment of the first aspect, the operation history data includes at least one of equipment family defects, operating years and maintenance records.

[0020] In combination with the first aspect, in a fifth embodiment of the first aspect, obtaining partial discharge history data, equipment characteristic parameter history data, and operation history data of a gas-insulated combination device includes:

[0021] Obtain initial partial discharge history data, initial equipment characteristic parameter history data, and initial operation history data of gas-insulated combined equipment;

[0022] The initial partial discharge historical data, the initial equipment characteristic parameter historical data and the initial operation historical data are normalized to obtain the partial discharge historical data, the equipment characteristic parameter historical data and the operation historical data.

[0023] In a second aspect, the present invention further provides a method for predicting a state of a gas-insulated combined device, the method comprising:

[0024] Obtain current partial discharge data, current equipment characteristic parameter data, and current operation data;

[0025] The operating state of the gas-insulated combination equipment is predicted based on current partial discharge data, current equipment characteristic parameter data, current operating history data, and a gas-insulated combination equipment state prediction model, wherein the gas-insulated combination equipment state prediction model is obtained according to the gas-insulated combination equipment state prediction model construction method in the first aspect or any embodiment of the first aspect.

[0026] Considering that the existing prediction method for gas-insulated combination equipment is aimed at predicting the state of a single electrical component inside the equipment, the equipment characteristic parameters of the single electrical component are used in the prediction process. However, the gas-insulated combination equipment contains multiple electrical components, and the equipment characteristic parameters of each electrical component are also different. Therefore, through the method provided in the embodiment of the present invention, from the perspective of gas-insulated combination equipment failure, the equipment characteristic parameters of electrical components with a higher failure rate are selected to predict the state of the gas-insulated combination equipment, and the state of the gas-insulated combination equipment is predicted in all aspects, thereby ensuring the safe and stable operation of the gas-insulated combination equipment and improving the level of smart operation and maintenance and intelligent scheduling of the power grid.

[0027] In a third aspect, the present invention further provides a device for constructing a state prediction model of a gas-insulated combined equipment, the device comprising:

[0028] A first acquisition module is used to acquire partial discharge historical data, equipment characteristic parameter historical data, and operation historical data of the gas-insulated combined device, wherein the equipment characteristic parameter historical data includes equipment characteristic parameter historical data of electrical components in the gas-insulated combined device whose failure rate exceeds a preset value;

[0029] A determination module, used to determine the historical status result of the gas-insulated combination device according to the partial discharge historical data, the equipment characteristic parameter historical data, and the operation historical data;

[0030] Establishing a module for establishing a training set based on partial discharge historical data, equipment characteristic parameter historical data, operation historical data, and corresponding historical status results;

[0031] The training module is used to train the long short-term memory network model through a training set to obtain a gas-insulated combined equipment state prediction model.

[0032] In a fourth aspect, the present invention further provides a gas-insulated combined equipment state prediction device, the device comprising:

[0033] The second acquisition module is used to acquire current partial discharge data, current equipment characteristic parameter data, and current operation data;

[0034] A prediction module is used to predict the operating state of a gas-insulated combination device based on current partial discharge data, current device characteristic parameter data, current operating history data, and a gas-insulated combination device state prediction model, wherein the gas-insulated combination device state prediction model is obtained according to the gas-insulated combination device state prediction model construction method in the first aspect or any embodiment of the first aspect.

[0035] In a fifth aspect, the present invention further provides a computer device, comprising a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to execute any embodiment of the method for constructing a state prediction model of a gas-insulated combination device in the content of the invention, or the steps corresponding to any embodiment of the method for predicting the state of a gas-insulated combination device. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0037] Figure 1 is a flow chart of a method for constructing a state prediction model of a gas-insulated combined equipment according to an exemplary embodiment;

[0038] Figure 2 is a graph of the overall temporal relationship of the long short-term memory network in one example;

[0039] Figure 3 is a diagram of the gated unit structure of a long short-term memory network in an example;

[0040] Figure 4is a flow chart of a method for predicting a state of a gas-insulated combined device according to an exemplary embodiment;

[0041] Figure 5 A schematic diagram of the structure of a device for constructing a state prediction model of a gas-insulated combined equipment proposed according to an exemplary embodiment;

[0042] Figure 6 It is a structural schematic diagram of a gas-insulated combined equipment state prediction device proposed according to an exemplary embodiment;

[0043] Figure 7 It is a schematic diagram of the hardware structure of a computer device proposed according to an exemplary embodiment. DETAILED DESCRIPTION

[0044] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0045] In addition, the technical features involved in the different embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0046] In order to comprehensively predict the state of a gas-insulated combined device and ensure the safe and stable operation of the gas-insulated combined device, the present invention proposes a method for constructing a state prediction model for a gas-insulated combined device and a state prediction method.

[0047] Figure 1 1 is a flow chart of a method for constructing a state prediction model for a gas-insulated combined equipment according to an exemplary embodiment. Figure 1 As shown, the method for constructing a gas-insulated combined equipment state prediction model includes the following steps S101 to S104.

[0048] Step S101: acquiring partial discharge history data, equipment characteristic parameter history data, and operation history data of a gas-insulated combination device, wherein the equipment characteristic parameter history data includes equipment characteristic parameter history data of electrical components in the gas-insulated combination device whose failure rate exceeds a preset value.

[0049] In an optional embodiment, the gas-insulated combined device includes electronic components such as circuit breakers, disconnectors, grounding switches, mutual inductors, lightning arresters, busbars, connectors, and outgoing terminals. These electronic components are all enclosed in a metal grounded housing, and sulfur hexafluoride (SF6) gas with excellent insulation and arc extinguishing properties is filled in the housing as an insulation and arc extinguishing medium. Therefore, the gas-insulated combined device is also called SF6 fully enclosed combined electrical appliances.

[0050] In an optional embodiment, when partial discharge exists in the gas-insulated combined equipment, it indicates that insulation degradation exists in the gas-insulated combined equipment, that is, partial discharge can directly reflect the insulation state of the gas-insulated combined equipment, and partial discharge data will be measured during live detection and preventive testing of the gas-insulated combined equipment, and it is also relatively easy to obtain partial discharge data. Therefore, when predicting the state of the gas-insulated combined equipment, partial discharge is selected as one of the observation data.

[0051] In an optional embodiment, the partial discharge history data includes but is not limited to the apparent partial discharge value, the energy of the partial discharge pulse, the external frequency voltage amplitude, the number of partial discharge pulses, the actual voltage during partial discharge, etc.

[0052] In an optional embodiment, the historical data of the characteristic parameters of the equipment include at least one of SF6 gas density, main circuit resistance, gas pressure of the pneumatic mechanism, number of operations, and temperature at the connection point of the outlet bushing.

[0053] In one example, the SF6 gas density in the equipment characteristic parameters determines the insulation strength and arc extinguishing capability of the gas-insulated combined equipment.

[0054] In an optional embodiment, the main circuit resistance in the equipment characteristic parameters reflects the technical status of the circuit breaker itself.

[0055] In an optional embodiment, the pneumatic mechanism circuit breaker relies on compressed air when performing opening / closing operations. The air pressure of the pneumatic mechanism is the only power for the normal operation of the circuit breaker. Therefore, the air pressure of the pneumatic mechanism is selected as the equipment characteristic parameter when predicting the status of the gas-insulated combination device.

[0056] In an optional embodiment, the number of operations in the equipment characteristic parameter refers to the number of load switching operations of the gas-insulated combined equipment. The number of operations reflects the relationship between the operating years and the rated life. Under the same rated life, the longer the operating years, the greater the number of operations.

[0057] In an optional embodiment, the temperature at the connection point of the outlet bushing in the equipment characteristic parameters can reflect the heating defect. When the temperature is abnormal, it will affect the stable operation of the gas-insulated combination equipment.

[0058] In an optional embodiment, the operation history data includes at least one of equipment family defects, operating years and maintenance records.

[0059] In an optional embodiment, a device family defect refers to a device defect that is confirmed to be caused by common factors of design, and / or material, and / or process. If such a defect occurs, other devices with the same design, and / or material, and / or process, regardless of whether the same defect can be detected at present, are called family defective devices until the hidden danger of such defect is eliminated. Device family defects may cause serious power grid accidents and equipment accidents.

[0060] In an optional embodiment, the operating years are an important factor in determining the condition and the remaining life of the gas-insulated assembly equipment.

[0061] In one example, maintenance records are an important basis for judging the status of gas-insulated combined equipment.

[0062] Step S102: Determine the historical status result of the gas-insulated combination equipment according to the partial discharge historical data, the equipment characteristic parameter historical data, and the operation historical data.

[0063] In an optional embodiment, the historical status results include normal status, attention status, abnormal status, and serious status.

[0064] Step S103: Establish a training set based on partial discharge historical data, equipment characteristic parameter historical data, operation historical data, and corresponding historical status results.

[0065] Step S104: training the long short-term memory network model using the training set to obtain a gas-insulated combined equipment state prediction model.

[0066] Considering that the existing prediction methods for gas-insulated combination equipment are aimed at predicting the state of a single electrical component inside the equipment, the equipment characteristic parameters of the single electrical component are used in the prediction process. However, the gas-insulated combination equipment contains multiple electrical components, and the equipment characteristic parameters of each electrical component are also different. Therefore, through the method for constructing a gas-insulated combination equipment state prediction model provided by an embodiment of the present invention, from the perspective of gas-insulated combination equipment failure, the equipment characteristic parameters of electrical components with a higher failure rate are selected to construct a gas-insulated combination equipment state prediction model. Through this prediction model, the state of the gas-insulated combination equipment can be predicted in all aspects, thereby ensuring the safe and stable operation of the gas-insulated combination equipment and improving the level of smart operation and maintenance and intelligent scheduling of the power grid.

[0067] The gas-insulated combined equipment contains many electrical components, each of which has a corresponding device characteristic parameter, but the degree of influence of each device characteristic parameter on the state prediction result of the gas-insulated combined equipment is different. If too many device characteristic parameters are selected, the amount of calculation data will increase and the prediction efficiency will be reduced; if too few device characteristic parameters are selected, it will not be enough to accurately reflect the state of the gas-insulated combined equipment. Therefore, the device characteristic parameters select the device characteristic parameters of the electrical components whose failure rate exceeds the preset value.

[0068] In one example, the device characteristic parameter historical data in step S101 above is obtained by the following steps:

[0069] First, the failure rate of each electrical component in the gas-insulated assembly equipment is obtained.

[0070] Then, according to the failure rate of each electrical component, an electrical component with a failure rate greater than a preset value is selected. The preset value can be set according to actual conditions and is not specifically limited here.

[0071] Finally, the equipment characteristic parameter historical data corresponding to the electrical components whose failure rate is greater than a preset value is determined as the equipment characteristic parameter historical data of the gas-insulated combination device.

[0072] Electrical components are screened by failure rate, and equipment characteristic parameters corresponding to electrical components with failure rates greater than preset values ​​are selected as prediction data. This can accurately predict the status of gas-insulated combination equipment while reducing the number of equipment characteristic parameters, reducing the amount of calculated data, and improving prediction efficiency.

[0073] In one example, the above step S101 obtains the partial discharge history data, the equipment characteristic parameter history data, and the operation history data of the gas-insulated combination equipment through the following steps:

[0074] First, the initial partial discharge history data, initial equipment characteristic parameter history data, and initial operation history data of the gas-insulated combination equipment are obtained.

[0075] Then, the initial partial discharge history data, the initial equipment characteristic parameter history data and the initial operation history data are normalized to obtain the partial discharge history data, the equipment characteristic parameter history data and the operation history data.

[0076] In an optional embodiment, the initial partial discharge history data, the SF6 gas density and the number of operations in the initial equipment characteristic parameter history data, and the operating years in the initial operation history data are all quantitative data, and the above quantitative data are normalized in combination with their respective threshold ranges.

[0077] Exemplarily, when the value of the above quantitative data is larger, the corresponding electrical component state is worse, and this type of data adopts the following normalization formula:

[0078]

[0079] Among them, x is the data value size, x m is the minimum value of the corresponding data, x M is the maximum value of the corresponding data, x n is the normalized result.

[0080] Exemplarily, when the value of the above quantitative data is smaller, the corresponding electrical component state is worse, and this type of data adopts the following normalization formula:

[0081]

[0082] In one example, the above step S102 determines the historical status result of the gas-insulated assembly device through the following steps:

[0083] Firstly, the operation state membership vector of each historical data is determined according to the partial discharge historical data, the equipment characteristic parameter historical data and the operation historical data.

[0084] In an optional embodiment, the respective operating state membership vectors are obtained according to the normalization results of the quantitative data and the respective distribution functions. The distribution function may be a piecewise linear distribution function. The obtained normalization results are processed using the piecewise linear distribution function to obtain the operating state membership vectors corresponding to the data.

[0085] In an optional embodiment, the equipment family defects and maintenance records in the operation history data, and the air pressure of the pneumatic mechanism in the equipment characteristic parameter history data, are all qualitative data, and the measurement values ​​cannot be accurately obtained or are obtained only based on qualitative judgment. The qualitative data is directly converted into the corresponding membership vector based on expert experience. For example, if it is determined according to expert experience that the electrical component is in a "normal" state, the membership vector is determined to be [1,0,0,0]; if it is determined according to expert experience that the electrical component is in a "caution" state, the membership vector is determined to be [0,1,0,0]; if it is determined according to expert experience that the electrical component is in an "abnormal" state, the membership vector is determined to be [0,0,1,0]; if it is determined according to expert experience that the electrical component is in a "serious" state, the membership vector is determined to be [0,0,0,1].

[0086] Then, the historical status result of the gas-insulated combined device is determined according to the operation status membership vector of each data and the corresponding weight. Exemplarily, the weight corresponding to each data can be determined by expert experience.

[0087] The traditional recurrent neural network (RNN) has the problem of gradient dissipation in the information feedback process, and the input information will disappear quickly, and then the entire neural network is difficult to maintain long-term memory function. In order to enable the neural network structure to update information, it is necessary to add a forgetting and saving mechanism to the entire structure, forming a long short-term memory network (LSTM). In an embodiment of the present invention, LSTM is used to train the established training set to make up for the short-term memory deficiency of RNN.

[0088] At time t, the input of LSTM is: the sequence input value x at time t t , the output value h of LSTM at time t-1 t-1 And the gated unit state c at time t-1 t-1 ; The output of LSTM is: LSTM output value h at time t t And the state of the gate control unit c at time t t The overall timing relationship is as follows Figure 2 shown.

[0089] In LSTM, the forget gate determines c t-1 C t The input gate determines the influence of x t C t The influence degree of the output gate control c t For h t The calculation of forget gate, input gate and output gate are shown in the following formulas:

[0090] f t =σ(W f ·h t-1 +W f ·x t +b f )

[0091] i t =σ(W i ·h t-1 +W i ·x t +b i )

[0092] o t =σ(W o ·h t-1 +W o ·x t +b o )

[0093] Among them, f t 、i t , o tare the state settlement results of the forget gate, input gate, and output gate respectively; W f , W i , W o are the weight matrices of the forget gate, input gate, and output gate respectively; b f , b i , b o are the forget gate, input gate, and output gate bias respectively; σ represents the sigmoid function. The final output of LSTM is determined by the output gate and the unit state:

[0094]

[0095]

[0096]

[0097] in, is the unit state input at time t; W c is the input unit state weight matrix; b c is the input unit state bias term; tanh represents the activation function; Indicates element-wise multiplication. The structure of LSTM gated unit is as follows Figure 3 shown.

[0098] The historical status results obtained in the training set are used as data labels, and the data in the training set are calculated according to the following process to train the LSTM model:

[0099] First, the output value of each neuron in the LSTM model is forward calculated.

[0100] Secondly, the error term of each neuron is calculated in reverse. The back propagation of error terms in the LSTM model includes: back propagation along time; propagation of error terms to the upper layer.

[0101] Again, the gradient of each weight matrix is ​​calculated based on the error term of each neuron.

[0102] Finally, the trained LSTM model is obtained, that is, the gas-insulated combined equipment state prediction model. The parameters in the model reflect the relationship between partial discharge data, equipment characteristic parameter data, operation data and the state of the gas-insulated combined equipment. The trained model is used to calculate the current data obtained to predict the state of the gas-insulated combined equipment in the future.

[0103] In one example, the present invention also provides a method for predicting the state of a gas-insulated combined device, such as Figure 4 As shown, the method comprises the following steps:

[0104] Step S401: Acquire current partial discharge data, current equipment characteristic parameter data, and current operation data.

[0105] Step S402: predict the operating state of the gas-insulated combination equipment based on current partial discharge data, current equipment characteristic parameter data, current operating history data, and a gas-insulated combination equipment state prediction model, wherein the gas-insulated combination equipment state prediction model is obtained according to the gas-insulated combination equipment state prediction model construction method in the above-mentioned embodiment.

[0106] Considering that the existing gas-insulated combination equipment prediction method is aimed at the state prediction of a single electrical component inside the equipment, the equipment characteristic parameters of the single electrical component are used in the prediction process. However, the gas-insulated combination equipment contains multiple electrical components, and the equipment characteristic parameters of each electrical component are also different. Therefore, through the gas-insulated combination equipment state prediction method provided by the embodiment of the present invention, from the perspective of gas-insulated combination equipment failure, the equipment characteristic parameters of electrical components with a higher failure rate are selected to predict the state of the gas-insulated combination equipment, and the state of the gas-insulated combination equipment is predicted in all aspects to ensure the safe and stable operation of the gas-insulated combination equipment and improve the level of smart operation and maintenance and intelligent scheduling of the power grid.

[0107] Based on the same inventive concept, the embodiment of the present invention also provides a device for constructing a state prediction model of a gas-insulated combined equipment, such as Figure 5 As shown, the device comprises:

[0108] The first acquisition module 501 is used to obtain local discharge history data, equipment characteristic parameter history data, and operation history data of the gas-insulated combination device. The equipment characteristic parameter history data includes equipment characteristic parameter history data of electrical components in the gas-insulated combination device whose failure rate exceeds a preset value. For details, please refer to the description of step S101 in the above embodiment, which will not be repeated here.

[0109] The determination module 502 is used to determine the historical status result of the gas-insulated combination device according to the partial discharge historical data, the equipment characteristic parameter historical data, and the operation historical data; for details, please refer to the description of step S102 in the above embodiment, which will not be repeated here.

[0110] Establishing module 503 is used to establish a training set according to partial discharge historical data, equipment characteristic parameter historical data, operation historical data, and corresponding historical status results; for details, please refer to the description of step S103 in the above embodiment, which will not be repeated here.

[0111] The training module 504 is used to train the long short-term memory network model through the training set to obtain the gas-insulated combined equipment state prediction model. For details, please refer to the description of step S104 in the above embodiment, which will not be repeated here.

[0112] In one example, the first acquisition module 501 includes:

[0113] The first acquisition submodule is used to acquire the failure rate of each electrical component in the gas-insulated assembly device; for details, please refer to the description in the above embodiment, which will not be repeated here.

[0114] The selection submodule is used to select electrical components with a failure rate greater than a preset value according to the failure rate of each electrical component; the details are described in the above embodiment and will not be repeated here.

[0115] The first determination submodule is used to determine the device characteristic parameter history data corresponding to the electrical component whose failure rate is greater than a preset value as the device characteristic parameter history data of the gas-insulated combination device. For details, please refer to the description in the above embodiment, which will not be repeated here.

[0116] In one example, the first acquisition module 501 further includes:

[0117] The second acquisition submodule is used to obtain initial partial discharge history data, initial equipment characteristic parameter history data, and initial operation history data of the gas-insulated combination device; for details, please refer to the description in the above embodiment and will not be repeated here.

[0118] The second determination submodule is used to normalize the initial partial discharge history data, the initial equipment characteristic parameter history data and the initial operation history data to obtain partial discharge history data, equipment characteristic parameter history data and operation history data. For details, please refer to the description in the above embodiment and will not be repeated here.

[0119] In one example, the determination module 502 includes:

[0120] The third determination submodule is used to determine the operation state membership vector of each historical data according to the partial discharge historical data, the equipment characteristic parameter historical data and the operation historical data; for details, please refer to the description in the above embodiment and will not be repeated here.

[0121] The fourth determination submodule is used to determine the historical status result of the gas-insulated assembly device according to the operation status membership vector of each data and the corresponding weight. For details, please refer to the description in the above embodiment, which will not be repeated here.

[0122] In one example, the equipment characteristic parameter history data in the first acquisition module 501 includes at least one of SF6 gas density, main circuit resistance, gas pressure of the pneumatic mechanism, number of operations, and temperature at the connection point of the outlet bushing. For details, please refer to the description in the above embodiment, which will not be repeated here.

[0123] In one example, the operation history data in the first acquisition module 501 includes at least one of equipment family defects, operation years, and maintenance records. For details, please refer to the description in the above embodiment, which will not be repeated here.

[0124] like Figure 6 As shown, the present invention also provides a gas-insulated combined equipment state prediction device, the device comprising:

[0125] The second acquisition module 601 is used to acquire current partial discharge data, current equipment characteristic parameter data, and current operation data; for details, please refer to the description of step S401 in the above embodiment, which will not be repeated here.

[0126] The prediction module 602 is used to predict the operating state of the gas-insulated combined device according to the current partial discharge data, the current device characteristic parameter data, the current operating history data, and the gas-insulated combined device state prediction model, and the gas-insulated combined device state prediction model is obtained according to the gas-insulated combined device state prediction model construction method in the above embodiment. For details, please refer to the description of step S402 in the above embodiment, which will not be repeated here.

[0127] The specific limitations and beneficial effects of the above-mentioned device can be found in the above-mentioned limitations on the method for constructing a gas-insulated combination device state prediction model or the method for predicting the state of a gas-insulated combination device, which will not be repeated here. The above-mentioned modules can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0128] Figure 7 FIG. 1 is a schematic diagram of a hardware structure of a computer device according to an exemplary embodiment. Figure 7 As shown, the device includes one or more processors 710 and a memory 720, and the memory 720 includes a persistent memory, a volatile memory, and a hard disk. Figure 7 A processor 710 is taken as an example. The device may also include: an input device 730 and an output device 740.

[0129] The processor 710, the memory 720, the input device 730 and the output device 740 may be connected via a bus or other means. Figure 7The example of connecting through bus is taken in the following.

[0130] The processor 710 may be a central processing unit (CPU). The processor 710 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or a combination of the above chips. A general-purpose processor may be a microprocessor or the processor may be any conventional processor.

[0131] The memory 720, as a non-transient computer-readable storage medium, includes a persistent memory, a volatile memory, and a hard disk, and can be used to store non-transient software programs, non-transient computer executable programs, and modules, such as the program instructions / modules corresponding to the method for constructing a state prediction model of a gas-insulated combined device and the state prediction method in the embodiment of the present application. The processor 710 executes various functional applications and data processing of the server by running the non-transient software programs, instructions, and modules stored in the memory 720, that is, implementing any of the above-mentioned methods for constructing a state prediction model of a gas-insulated combined device and the state prediction method.

[0132] The memory 720 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required by at least one function; the data storage area may store data required for use, etc. In addition, the memory 720 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 720 may optionally include a memory remotely arranged relative to the processor 710, and these remote memories may be connected to the data processing device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0133] The input device 730 can receive input digital or character information and generate signal input related to user settings and function control. The output device 740 can include display devices such as display screens.

[0134] One or more modules are stored in the memory 720, and when executed by one or more processors 710, the execution is as follows: Figure 1 or Figure 4 The method shown.

[0135] The above-mentioned product can execute the method provided by the embodiment of the present invention, and has the functional modules and beneficial effects corresponding to the execution method. For technical details not described in detail in this embodiment, please refer to Figure 1 Related description of the illustrated embodiment.

[0136] The embodiment of the present invention further provides a non-transitory computer storage medium, which stores computer executable instructions, and the computer executable instructions can execute the construction and prediction methods in any of the above method embodiments. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory (Flash Memory), a hard disk (HDD) or a solid-state drive (SSD), etc.; the storage medium can also include a combination of the above types of memory.

[0137] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0138] The above is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features applied herein.

Claims

1. A method for constructing a state prediction model for a gas-insulated combined equipment, characterized in that: The method comprises: Acquire partial discharge history data, equipment characteristic parameter history data, and operation history data of a gas-insulated combined device, wherein the equipment characteristic parameter history data includes equipment characteristic parameter history data of electrical components in the gas-insulated combined device whose failure rate exceeds a preset value; Determine the historical status result of the gas-insulated combination device according to the partial discharge historical data, the device characteristic parameter historical data, and the operation historical data; Establishing a training set according to the partial discharge historical data, the equipment characteristic parameter historical data, the operation historical data, and the corresponding historical status results; The long short-term memory network model is trained by using the training set to obtain a gas-insulated combined equipment state prediction model; Obtain historical data on equipment characteristic parameters of gas-insulated combined equipment, including: Obtain the failure rate of each electrical component in the gas-insulated combined equipment; According to the failure rate of each electrical component, select an electrical component whose failure rate is greater than a preset value; Determine the equipment characteristic parameter history data corresponding to the electrical component whose failure rate is greater than a preset value as the equipment characteristic parameter history data of the gas-insulated combination device; The equipment characteristic parameter historical data includes at least one of SF6 gas density, main circuit resistance, gas pressure of the pneumatic mechanism, number of operations and temperature at the connection point of the outlet bushing; The operation history data includes at least one of equipment family defects, operating years and maintenance records.

2. The method according to claim 1, characterized in that Determining the historical status result of the gas-insulated combination device according to the partial discharge historical data, the device characteristic parameter historical data, and the operation historical data, including: Determine the operation state membership vector of each historical data according to the partial discharge historical data, the equipment characteristic parameter historical data, and the operation historical data; The historical status result of the gas-insulated combination device is determined according to the operation status membership vector of each data and the corresponding weight.

3. The method according to claim 1, characterized in that: Obtain the partial discharge historical data, equipment characteristic parameter historical data, and operation historical data of gas-insulated combined equipment, including: Obtain initial partial discharge history data, initial equipment characteristic parameter history data, and initial operation history data of gas-insulated combined equipment; The initial partial discharge history data, the initial equipment characteristic parameter history data and the initial operation history data are normalized to obtain the partial discharge history data, the equipment characteristic parameter history data and the operation history data.

4. A method for predicting the state of a gas-insulated combined equipment, characterized in that: The method comprises: Obtain current partial discharge data, current equipment characteristic parameter data, and current operation data; The operating state of the gas-insulated combination device is predicted based on the current partial discharge data, the current device characteristic parameter data, the current operating data, and a gas-insulated combination device state prediction model, wherein the gas-insulated combination device state prediction model is obtained according to the gas-insulated combination device state prediction model construction method described in any one of claims 1-3.

5. A device for constructing a state prediction model of a gas-insulated combined equipment, characterized in that: The device comprises: A first acquisition module is used to acquire partial discharge history data, equipment characteristic parameter history data, and operation history data of a gas-insulated combined device, wherein the equipment characteristic parameter history data includes equipment characteristic parameter history data of electrical components in the gas-insulated combined device whose failure rate exceeds a preset value; A determination module, used to determine the historical status result of the gas-insulated combination device according to the partial discharge historical data, the device characteristic parameter historical data, and the operation historical data; An establishment module, used to establish a training set according to the partial discharge historical data, the equipment characteristic parameter historical data, the operation historical data, and the corresponding historical status results; A training module, used for training the long short-term memory network model through the training set to obtain a gas-insulated combined equipment state prediction model; Obtain historical data of equipment characteristic parameters of gas-insulated combined equipment, including: Obtain the failure rate of each electrical component in the gas-insulated combined equipment; According to the failure rate of each electrical component, select an electrical component whose failure rate is greater than a preset value; Determine the equipment characteristic parameter history data corresponding to the electrical component whose failure rate is greater than a preset value as the equipment characteristic parameter history data of the gas-insulated combination device; The equipment characteristic parameter historical data includes at least one of SF6 gas density, main circuit resistance, gas pressure of the pneumatic mechanism, number of operations and temperature at the connection point of the outlet bushing; The operation history data includes at least one of equipment family defects, operating years and maintenance records.

6. A gas-insulated combined equipment state prediction device, characterized in that: The device comprises: The second acquisition module is used to acquire current partial discharge data, current equipment characteristic parameter data, and current operation data; A prediction module is used to predict the operating state of the gas-insulated combination device based on the current partial discharge data, the current device characteristic parameter data, the current operating data, and a gas-insulated combination device state prediction model, wherein the gas-insulated combination device state prediction model is obtained according to the gas-insulated combination device state prediction model construction method described in any one of claims 1 to 3.

7. A computer device, characterized in that: It comprises a memory and a processor, the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method for constructing a gas-insulated combination device state prediction model according to any one of claims 1 to 3, or the steps of the gas-insulated combination device state prediction method according to claim 4 by executing the computer instructions.

Images