Transformer insulation status evaluation method, device, electronic equipment and storage medium

Abstract

The present invention provides a transformer insulation state assessment method, device, electronic device and storage medium, the transformer insulation state assessment method includes: determining the load factor of the target transformer according to wind and solar power output data and load data; using kernel principal component analysis to determine the insulation state characteristic quantity of the target transformer; determining the insulation state index of the target transformer according to abnormal state statistical data, and determining the threshold of the insulation state index of the target transformer according to historical data; obtaining real-time monitoring data of the target transformer, and then determining the insulation state of the target transformer. The beneficial effects of the present invention are: considering the transformer insulation state assessment affected by wind power, photovoltaics, load, and operating environment, improving the accuracy of the transformer insulation state assessment; using kernel principal component analysis to complete the redundancy analysis and correlation analysis of the transformer multi-dimensional operating data and monitoring data, and providing risk estimation for transformer failure.

Description

Technical Field

[0001] The present invention relates to the field of power equipment monitoring and computer technology, and in particular to a transformer insulation state evaluation method, device, electronic equipment and storage medium. Background Art

[0002] As the penetration rate of new energy in the power system increases, intermittent power generation from new energy sources such as wind power and photovoltaics and load changes will cause slight changes in the operating temperature of the transformer. Slight changes in the operating temperature of the transformer and changes in the meteorological parameters of the transformer operating environment (such as temperature, humidity, etc.) will cause changes in the dissolved gas in the insulating oil, resulting in inaccurate transformer insulation status assessment results based on dissolved gas in the oil.

[0003] Analysis of dissolved gases in transformer insulating oil is one of the most effective methods for determining the early potential faults of transformers. However, existing transformer operating status analysis methods based on dissolved gases in oil all use deterministic methods, and do not consider the impact of wind and solar power output, load uncertainty, and ambient temperature changes on transformer operation, resulting in inaccurate transformer operating status assessment. Using only experience and a single parameter will result in low accuracy in transformer insulation status assessment, and problems such as over-repair or disrepair of the transformer will occur. Summary of the invention

[0004] The main purpose of the embodiments of the present invention is to provide a transformer insulation status assessment method, device, electronic device and storage medium, which improves the accuracy of transformer insulation status assessment and provides risk prediction for transformer failure.

[0005] One aspect of the present invention provides a method for evaluating the insulation status of a transformer, comprising:

[0006] According to the transformer insulation status assessment request, obtain the wind and solar power output data and load data connected to the target transformer, and determine the load factor of the target transformer according to the wind and solar power output data and the load data;

[0007] Collecting environmental parameters and insulation monitoring data of the target transformer, and determining the insulation state characteristic quantity of the target transformer by using kernel principal component analysis according to the load factor, the environmental parameters and the insulation monitoring data;

[0008] Acquire historical data and abnormal state statistical data, determine the insulation state index of the target transformer according to the abnormal state statistical data, and determine the threshold value of the insulation state index of the target transformer according to the historical data;

[0009] Real-time monitoring data of the target transformer is acquired, and the insulation state of the target transformer is determined according to the real-time monitoring data, the insulation state index, and a threshold value of the insulation state index.

[0010] According to the transformer insulation status assessment method, according to the transformer insulation status assessment request, wind and solar power output data and load data connected to the target transformer are obtained, and according to the wind and solar power output data and the load data, the load factor of the target transformer is determined, including:

[0011] Taking the rated capacity of the target transformer as a reference value, performing normalization processing on the wind-solar output data and the load data to obtain a probability density function of wind power output, a probability density function of photovoltaic output, and a probability density function of load output, wherein the wind-solar output data includes wind power output data and photovoltaic output data;

[0012] According to the wind power output probability density function, the photovoltaic output probability density function and the load output probability density function, a normal Copula function is used to construct a wind-solar-load multi-dimensional joint probability density distribution function f(p w ,p p ,p l )for

[0013]

[0014] Where I is the identity matrix, ζ′=[Φ -1 (a),Φ -1 (b),Φ -1 (c)], a, b, c represent the cumulative distribution function of wind power, photovoltaic cumulative distribution function and load cumulative distribution function respectively, Φ -1 represents the inverse function of the cumulative distribution function of the standard normal distribution, R is the product-moment correlation coefficient matrix of the normal Copula function, wherein the product-moment correlation coefficient matrix of the normal Copula function is calculated using at least one of the maximum information coefficient, the Kendall rank correlation coefficient, and the Spearman correlation coefficient;

[0015] According to the multi-dimensional joint probability density distribution function of wind and solar load, the transformer load factor f(k) is determined as

[0016]

[0017] where p w 、p p 、p l They represent the per unit values ​​of wind power output, photovoltaic output and load respectively.

[0018] According to the transformer insulation status assessment method, the method further includes:

[0019] The environmental parameters are collected by a first sensor, wherein the environmental data collected by the first sensor includes at least one of environmental temperature, rainfall, humidity and wind speed;

[0020] The insulation monitoring data is collected by a second sensor, and the insulation monitoring data collected by the second sensor includes at least one of oil temperature, trace water, carbon monoxide, carbon dioxide, methane, ethane, ethylene, acetylene and hydrogen, wherein the collected insulation monitoring data can be customized.

[0021] According to the transformer insulation state assessment method, the environmental parameters and insulation monitoring data of the target transformer are collected, and according to the load factor, the environmental parameters and the insulation monitoring data, the insulation state characteristic quantity of the target transformer is determined by using kernel principal component analysis, including:

[0022] According to the transformer load factor f(k), environmental parameters and insulation monitoring data of the target transformer, the sample data matrix S is obtained as follows:

[0023] S={X1,X2...X i ,...X n}

[0024] Where i is the transformer quantity identifier, X i represents the characteristic quantity of the i-th transformer, and X i represents an m-dimensional vector, n is the total number of samples, and;

[0025] The sample data matrix is ​​passed through a nonlinear mapping function Mapped to a high-dimensional feature space, the dimension of the high-dimensional feature space is d, and then the d×n nonlinear mapping matrix φ(X) is obtained as

[0026] {φ(X1),φ(X2),…,φ(X i )…,φ(X n )}

[0027] Among them, the nonlinear mapping function The mapping is φ(X)::R m →R d , d>>m, where the nonlinear mapping function One of the radial basis kernel function, Gaussian kernel function and polynomial kernel function may also be used;

[0028] According to the nonlinear mapping matrix, the kernel matrix K is determined as

[0029] [φ(X) T φ(X)]

[0030] Where K is a symmetric semi-positive matrix of n×n, and the kernel matrix is ​​centered for

[0031]

[0032] Among them I n Indicates that each element is n×n matrix;

[0033] Determine the matrix eigenvector α and eigenvalue λ according to the kernel matrix, where Kα=λα, and perform eigenvector normalization for

[0034]

[0035] Determine the retained principal components based on the eigenvalues ​​exceeding the preset cumulative contribution, and select the normalized eigenvectors exceeding the preset cumulative contribution for reconstruction for

[0036]

[0037] According to the transformer insulation state evaluation method, historical data and abnormal state statistical data are obtained, the insulation state index of the target transformer is determined according to the abnormal state statistical data, and the threshold of the insulation state index of the target transformer is determined according to the historical data, including:

[0038] According to the historical data and the abnormal state statistical data, Hotelling-T 2 Calculate T 2 Statistics, and, using the squared prediction error Q statistic, according to T 2 Statistics and Q statistics determine the insulation status index as

[0039]

[0040] in, is the nonlinear mapping matrix, is the principal component eigenvector, is the sample mapping mean, I is the identity matrix, and λ is the eigenvalue matrix;

[0041] According to the normal state T in the historical data 2 and Q statistics, calculate T 2 Thresholds for the Q statistic and Q statistic and Q m for

[0042]

[0043]

[0044] Among them, l represents the number of principal components retained, a is the confidence level; F a (l,nl) is the critical value of the F distribution under the condition of l and nl degrees of freedom, μ is the mean of the sample Q statistic, ρ is the standard deviation of the sample Q statistic The degree of freedom is h = 2μ 2 / ρ and chi-square distribution with confidence level a.

[0045] According to the transformer insulation state evaluation method, real-time monitoring data of the target transformer is obtained, and the insulation state of the target transformer is determined according to the real-time monitoring data, the insulation state index and the threshold value of the insulation state index, including:

[0046] The transformer is calculated by the real-time monitoring data Statistics and Q r Statistics, based on threshold and Q m , calculate the outlier index Ψ as

[0047] The insulation state of the target transformer is determined according to the value of the abnormal value indicator Ψ.

[0048] According to the transformer insulation status assessment method, the method further includes:

[0049] According to the alarm interval range of the value of the abnormal value indicator Ψ and the insulation state, an alarm prompt of a corresponding level is executed.

[0050] Another aspect of an embodiment of the present invention provides a transformer insulation status assessment device, comprising:

[0051] The first module is used to obtain the wind and solar power output data and load data connected to the target transformer according to the transformer insulation status assessment request, and determine the load factor of the target transformer according to the wind and solar power output data and the load data;

[0052] The second module is used to collect the environmental parameters and insulation monitoring data of the target transformer, and determine the insulation state characteristic quantity of the target transformer by using kernel principal component analysis according to the load factor, the environmental parameters and the insulation monitoring data;

[0053] The third module is used to obtain historical data and abnormal state statistical data, determine the insulation state index of the target transformer according to the abnormal state statistical data, and determine the threshold value of the insulation state index of the target transformer according to the historical data;

[0054] The fourth module is used to obtain the real-time monitoring data of the target transformer, and determine the insulation state of the target transformer according to the real-time monitoring data, the insulation state index and the threshold value of the insulation state index.

[0055] Another aspect of an embodiment of the present invention provides an electronic device, including a processor and a memory;

[0056] The memory is used to store programs;

[0057] The processor executes the program to implement the method described above.

[0058] The embodiment of the present invention also discloses a computer program product or a computer program, which includes a computer instruction stored in a computer-readable storage medium. A processor of a computer device can read the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the computer device executes the method described above.

[0059] The beneficial effects of the present invention are as follows: the transformer insulation state assessment taking into account the influence of wind power, photovoltaic power, load and operating environment improves the accuracy of the transformer insulation state assessment; the kernel principal component analysis is used to complete the redundancy analysis and correlation analysis of the transformer multi-dimensional operating data and monitoring data, and the transformer insulation state can be quickly identified according to the Hotelling-T2 and Squared Prediction Error (squared prediction error) statistics, and the abnormal state can be quantified. According to the severity of the abnormal state, different preventive measures are collected, thereby providing technical support for the reliable operation of the transformer and providing risk estimation for transformer failure. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] The above and / or additional aspects and advantages of the present invention will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which:

[0061] Figure 1 4 is a schematic diagram of a system for evaluating the insulation status of a transformer according to an embodiment of the present invention.

[0062] Figure 2 It is a schematic diagram of a transformer insulation status assessment process according to an embodiment of the present invention.

[0063] Figure 3 It is a schematic diagram of the transformer load factor calculation process according to an embodiment of the present invention.

[0064] Figure 4 It is a schematic diagram of the transformer feature extraction process according to an embodiment of the present invention.

[0065] Figure 5The invention discloses a flow chart of transformer insulation status index and limit value calculation.

[0066] Figure 6 Schematic diagram of a device for evaluating the insulation status of a transformer according to an embodiment of the present invention. DETAILED DESCRIPTION

[0067] The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention.

[0068] Reference Figure 1 , Figure 1 : is a schematic diagram of a system for evaluating the insulation status of a transformer. It includes a transformer 300, a server 400 and a client 500, wherein the transformer 300 is used to receive the power generated by the wind and solar power generation device 100 through the power grid 200, wherein the wind and solar power generation device includes a wind power generation device and a photovoltaic power generation device. Among them, the transformer 300 is also provided with a first sensor (not shown) and a second sensor (not shown), wherein the first sensor is used to collect environmental data of the transformer, and the environmental data collected by the first sensor include environmental temperature, rainfall, humidity, wind speed, etc., and the second sensor is used to collect insulation monitoring data, and the environmental data collected by the second sensor includes oil temperature, trace water, carbon monoxide, carbon dioxide, methane, ethane, ethylene, acetylene, hydrogen, etc.), wherein the type and quantity of the first sensor and the second sensor can be customized according to requirements. The server 400 also stores historical data and abnormal status data of the transformer 300, wherein the historical data indicates that the transformer includes environmental data, insulation detection data, wind power output, photovoltaic output, load output data, etc. under normal conditions, and the abnormal status data indicates environmental data, insulation detection data, wind power output, photovoltaic output, load output data, etc. when the transformer fails or is abnormal.

[0069] Among them, the server 400 is used to obtain the wind and solar power output data and load data connected to the transformer 300 according to the insulation status assessment request of the transformer 300, and determine the load factor of the transformer 300 according to the wind and solar power output data and load data; collect the environmental parameters and insulation monitoring data of the transformer 300, and determine the insulation status characteristic quantity of the transformer 300 by kernel principal component analysis according to the load factor, environmental parameters and insulation monitoring data; obtain historical data and abnormal status statistical data, determine the insulation status index of the transformer 300 according to the abnormal status statistical data, and determine the threshold of the insulation status index of the transformer 300 according to the historical data; obtain the real-time monitoring data of the transformer 300, and determine the insulation status of the transformer 300 according to the real-time monitoring data, the insulation status index and the threshold of the insulation status index, and the server 400 sends the status assessment result of the transformer 300 to the client 500.

[0070] In some embodiments, the wind and solar power generation devices may also be other non-steady-state power generation devices, such as tidal power generation devices, waste heat recovery power generation devices, etc.

[0071] refer to Figure 2 ,in Figure 2 1 is a schematic diagram of a transformer insulation status assessment process, which includes but is not limited to steps S100 to S400:

[0072] S100, according to the transformer insulation status assessment request, obtain the wind and solar power output data and load data connected to the target transformer, and determine the load factor of the target transformer according to the wind and solar power output data and load data.

[0073] In some embodiments, reference Figure 3 The transformer load factor calculation process diagram shown in FIG. 1 includes but is not limited to steps S110 to S130:

[0074] S110, using the rated capacity of the target transformer as a reference value, performing normalization processing on the wind and solar power output data and the load data to obtain a probability density function of wind power output, a probability density function of photovoltaic output, and a probability density function of load output, wherein the wind and solar power output data includes wind power output data and photovoltaic power output data;

[0075] S120, based on the probability density function of wind power output, the probability density function of photovoltaic output and the probability density function of load output, a normal Copula function is used to construct a multi-dimensional joint probability density distribution function of wind, photovoltaic and load f(p w ,p p ,p l )for

[0076]

[0077] Where I is the identity matrix, ζ′=[Φ -1 (a),Φ -1 (b),Φ -1 (c)], a, b, c represent the cumulative distribution function of wind power, photovoltaic cumulative distribution function and load cumulative distribution function respectively, Φ -1 represents the inverse function of the cumulative distribution function of the standard normal distribution, R is the product-moment correlation coefficient matrix of the normal Copula function, wherein the product-moment correlation coefficient matrix of the normal Copula function is calculated using at least one of the maximum information coefficient, the Kendall rank correlation coefficient, and the Spearman correlation coefficient;

[0078] S130, according to the multi-dimensional joint probability density distribution function of wind and solar load, determine the transformer load factor f(k) as

[0079]

[0080] where p w 、p p 、p l They represent the per unit values ​​of wind power output, photovoltaic output and load respectively.

[0081] S200, collecting environmental parameters and insulation monitoring data of the target transformer, and determining the insulation state characteristic quantity of the target transformer by using kernel principal component analysis according to the load factor, environmental parameters and insulation monitoring data.

[0082] In some embodiments, reference Figure 4 The transformer feature extraction process diagram shown in FIG. 1 includes but is not limited to the following steps:

[0083] S210, according to the transformer load factor f(k), environmental parameters and insulation monitoring data of the target transformer, the sample data matrix S is obtained as

[0084] S={X1,X2...X i ,...X n}

[0085] Where i is the transformer quantity identifier, X i represents the characteristic quantity of the i-th transformer, and X i represents an m-dimensional vector, n is the total number of samples, and;

[0086] S220, the sample data matrix is ​​transformed through a nonlinear mapping function Mapped to a high-dimensional feature space, the dimension of the high-dimensional feature space is d, and then the d×n nonlinear mapping matrix φ(X) is obtained as

[0087] {φ(X1),φ(X2),…,φ(X i )…,φ(X n )}

[0088] Among them, the nonlinear mapping function The mapping is φ(X)::R m →R d , d>>m, where the nonlinear mapping function One of the radial basis kernel function, Gaussian kernel function and polynomial kernel function may also be used;

[0089] S230, determining the kernel matrix K according to the nonlinear mapping matrix:

[0090] [φ(X) T φ(X)]

[0091] Where K is a symmetric semi-positive matrix of n×n, and the kernel matrix is ​​centered for

[0092]

[0093] Among them I n Indicates that each element is n×n matrix;

[0094] S240, determining the matrix eigenvector α and eigenvalue λ according to the kernel matrix, where Kα=λα, and performing eigenvector normalization for

[0095]

[0096] S250, determining the retained principal components according to the eigenvalues ​​exceeding the preset cumulative contribution amount, and selecting the normalized eigenvectors exceeding the preset cumulative contribution amount for reconstruction for

[0097]

[0098] S300, acquiring historical data and abnormal state statistical data, determining an insulation state index of a target transformer according to the abnormal state statistical data, and determining a threshold value of the insulation state index of the target transformer according to the historical data.

[0099] In some embodiments, reference Figure 5 The transformer insulation status index and limit value calculation flow chart shown in FIG. 1 includes but is not limited to steps S310 to S320:

[0100] S310, based on historical data and abnormal status statistics, uses Hotelling-T 2 Calculate T 2 Statistics, and, using the squared prediction error Q statistic, according to T 2 Statistics and Q statistics determine the insulation status index as

[0101]

[0102] in, is the nonlinear mapping matrix, is the principal component eigenvector, is the sample mapping mean, I is the identity matrix, and λ is the eigenvalue matrix;

[0103] S320, according to the normal state T in the historical data 2 and Q statistics, calculate T 2 Threshold of statistic And, the threshold for calculating the Q statistic is Q m for

[0104]

[0105]

[0106] Among them, l represents the number of principal components retained, a is the confidence level; F a (l,nl) is the critical value of the F distribution under the condition of l and nl degrees of freedom, μ is the mean of the sample Q statistic, ρ is the standard deviation of the sample Q statistic The degree of freedom is h = 2μ 2 / ρ and chi-square distribution with confidence level a.

[0107] S400, acquiring real-time monitoring data of a target transformer, and determining the insulation state of the target transformer according to the real-time monitoring data, an insulation state index, and a threshold value of the insulation state index.

[0108] In some embodiments, the transformer T2r and Q are calculated based on the transformer real-time monitoring data. r Statistics;

[0109] Calculate the outlier index Ψ, which can be expressed as When Ψ<0, the transformer insulation state is judged to be normal, otherwise, it is judged to be abnormal, and the larger the Ψ value, the more serious the abnormality.

[0110] In some embodiments, the abnormal value indicator Ψ is divided into multiple levels, and is divided into levels 1-4 from small to large according to verification, so as to identify the severity of the transformer insulation state when it is abnormal. The risk level is obtained by judging the real-time collection and analyzing it through the above embodiment to perform corresponding processing. For example, when the risk level of the transformer insulation state is detected to be 1, its abnormality level is low, and an early warning report is executed. When the risk level of the transformer insulation state is detected to be 3, the transformer has a corresponding fault, which may cause the risk of power distribution failure, and equipment replacement and maintenance are required.

[0111] Figure 6 It is a schematic diagram of the insulation status alarm process of a transformer according to an embodiment of the present invention.

[0112] In some embodiments, reference Figure 6 The schematic diagram of the transformer insulation status assessment device shown includes a first module 610 , a second module 620 , a third module 630 and a fourth module 640 .

[0113] Among them, the first module is used to obtain the wind and solar power output data and load data of the target transformer according to the transformer insulation status assessment request, and determine the load factor of the target transformer according to the wind and solar power output data and load data; the second module is used to collect the environmental parameters and insulation monitoring data of the target transformer, and determine the insulation state characteristic quantity of the target transformer by kernel principal component analysis according to the load factor, environmental parameters and insulation monitoring data; the third module is used to obtain historical data and abnormal state statistical data, determine the insulation state index of the target transformer according to the abnormal state statistical data, and determine the threshold of the insulation state index of the target transformer according to the historical data; the fourth module is used to obtain the real-time monitoring data of the target transformer, and determine the insulation state of the target transformer according to the real-time monitoring data, the insulation state index and the threshold of the insulation state index.

[0114] Exemplarily, with the cooperation of the first module, the second module, the third module and the fourth module in the device, the embodiment device can implement any of the aforementioned transformer insulation status assessment methods, that is, according to the transformer insulation status assessment request, obtain the wind and solar power output data and load data connected to the target transformer, and determine the load factor of the target transformer according to the wind and solar power output data and the load data; collect the environmental parameters and insulation monitoring data of the target transformer, and determine the insulation status characteristic quantity of the target transformer according to the load factor, environmental parameters and insulation monitoring data by kernel principal component analysis; obtain historical data and abnormal status statistical data, determine the insulation status index of the target transformer according to the abnormal status statistical data, and determine the threshold of the insulation status index of the target transformer according to the historical data; obtain real-time monitoring data of the target transformer, and determine the insulation status of the target transformer according to the real-time monitoring data, the insulation status index and the threshold of the insulation status index. The beneficial effects of the present invention are as follows: the transformer insulation state assessment taking into account the influence of wind power, photovoltaic power, load and operating environment improves the accuracy of the transformer insulation state assessment; the kernel principal component analysis is used to complete the redundancy analysis and correlation analysis of the transformer multi-dimensional operating data and monitoring data, and the transformer insulation state can be quickly identified according to the Hotelling-T2 and Squared Prediction Error (squared prediction error) statistics, and the abnormal state can be quantified. According to the severity of the abnormal state, different preventive measures are collected, thereby providing technical support for the reliable operation of the transformer and providing risk estimation for transformer failure.

[0115] An embodiment of the present invention further provides an electronic device, the electronic device comprising a processor and a memory;

[0116] The memory stores a program;

[0117] The processor executes the program to execute the aforementioned transformer insulation state assessment method; the electronic device has the function of carrying and running the transformer insulation state assessment software system provided by the embodiment of the present invention.

[0118] An embodiment of the present invention further provides a computer-readable storage medium, wherein the storage medium stores a program, and the program is executed by a processor to implement the transformer insulation state assessment method as described above.

[0119] In some optional embodiments, the function / operation mentioned in the block diagram may not occur in the order mentioned in the operation diagram. For example, depending on the function / operation involved, the two boxes shown in succession can actually be executed substantially simultaneously or the boxes can sometimes be executed in reverse order. In addition, the embodiments presented and described in the flow chart of the present invention are provided by way of example, for the purpose of providing a more comprehensive understanding of technology. The disclosed method is not limited to the operations and logic flows presented by the embodiments of the present invention. Optional embodiments are expected, wherein the order of various operations is changed and wherein the sub-operations described as a part of a larger operation are performed independently.

[0120] The embodiment of the present invention also discloses a computer program product or a computer program, which includes a computer instruction stored in a computer-readable storage medium. A processor of a computer device can read the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the computer device executes the aforementioned transformer insulation state assessment method.

[0121] In addition, although the present invention is described in the context of functional modules, it should be understood that, unless otherwise specified, one or more of the functions and / or features described may be integrated into a single physical device and / or software module, or one or more functions and / or features may be implemented in separate physical devices or software modules. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding the present invention. More specifically, in view of the properties, functions, and internal relationships of various functional modules in the devices disclosed in the embodiments of the present invention, the actual implementation of the module will be understood within the conventional skills of engineers. Therefore, those skilled in the art can implement the present invention set forth in the claims without excessive experimentation using ordinary techniques. It is also understood that the specific concepts disclosed are merely illustrative and are not intended to limit the scope of the present invention, which is determined by the full scope of the appended claims and their equivalents.

[0122] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0123] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0124] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0125] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0126] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0127] Although the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the claims and their equivalents.

[0128] The above is a specific description of the preferred implementation of the present invention, but the present invention is not limited to the described embodiments. Those skilled in the art may make various equivalent modifications or substitutions without violating the spirit of the present invention. These equivalent modifications or substitutions are all included in the scope defined by the claims of this application.

Claims

1. A method for evaluating the insulation status of a transformer, characterized in that: include: According to the transformer insulation status assessment request, obtain the wind and solar power output data and load data connected to the target transformer, and determine the load factor of the target transformer according to the wind and solar power output data and the load data; Collecting environmental parameters and insulation monitoring data of the target transformer, and determining the insulation state characteristic quantity of the target transformer by using kernel principal component analysis according to the load factor, the environmental parameters and the insulation monitoring data; Acquire historical data and abnormal state statistical data, determine the insulation state index of the target transformer according to the abnormal state statistical data, and determine the threshold value of the insulation state index of the target transformer according to the historical data; Acquire real-time monitoring data of the target transformer, and determine the insulation state of the target transformer according to the real-time monitoring data, the insulation state index and a threshold value of the insulation state index; The wind and solar power generation device may also be other non-steady-state power generation devices; The method further includes: collecting the environmental parameters through a first sensor, wherein the environmental data collected by the first sensor includes at least one of environmental temperature, rainfall, humidity and wind speed; collecting the insulation monitoring data through a second sensor, wherein the insulation monitoring data collected by the second sensor includes at least one of oil temperature, trace water, carbon monoxide, carbon dioxide, methane, ethane, ethylene, acetylene and hydrogen, wherein the collected insulation monitoring data can be customized and adjusted; The step of obtaining wind and solar power output data and load data connected to a target transformer according to a transformer insulation status assessment request, and determining a load factor of the target transformer according to the wind and solar power output data and the load data, comprises: Taking the rated capacity of the target transformer as a reference value, performing normalization processing on the wind-solar output data and the load data to obtain a probability density function of wind power output, a probability density function of photovoltaic output, and a probability density function of load output, wherein the wind-solar output data includes wind power output data and photovoltaic output data; According to the wind power output probability density function, the photovoltaic output probability density function and the load output probability density function, a normal Copula function is used to construct a wind-solar-load multi-dimensional joint probability density distribution function f(p w ,p p ,p l )for Where I is the identity matrix, ζ′=[Φ -1 (a),Φ -1 (b),Φ -1 (c)], a, b, c represent the cumulative distribution function of wind power, photovoltaic cumulative distribution function and load cumulative distribution function respectively, Φ -1 represents the inverse function of the cumulative distribution function of the standard normal distribution, R is the product-moment correlation coefficient matrix of the normal Copula function, wherein the product-moment correlation coefficient matrix of the normal Copula function is calculated using at least one of the maximum information coefficient, the Kendall rank correlation coefficient, and the Spearman correlation coefficient; According to the multi-dimensional joint probability density distribution function of wind and solar load, the transformer load factor f(k) is determined as where p w 、p p 、p l Respectively represent the per unit value of wind power output, photovoltaic output and load; The collecting of the environmental parameters and insulation monitoring data of the target transformer, and determining the insulation state characteristic quantity of the target transformer by using kernel principal component analysis according to the load factor, the environmental parameters and the insulation monitoring data, comprises: According to the transformer load factor f(k), environmental parameters and insulation monitoring data of the target transformer, the sample data matrix S is obtained as follows: S={X1,X2…X i ,…X n } Where i is the transformer quantity identifier, X i represents the characteristic quantity of the i-th transformer, and X i represents an m-dimensional vector, and n is the total number of samples; The sample data matrix is ​​passed through a nonlinear mapping function Mapped to a high-dimensional feature space, the dimension of the high-dimensional feature space is d, and then the d×n nonlinear mapping matrix φ(X) is obtained as {φ(X1),φ(X2),…,φ(X i )…,φ(X n )} Among them, the nonlinear mapping function The mapping method is φ(X):R m →R d , d>>m, where the nonlinear mapping function One of the radial basis kernel function, Gaussian kernel function and polynomial kernel function may also be used; According to the nonlinear mapping matrix, the kernel matrix K is determined as [φ(X) T φ(X)] Where K is a symmetric semi-positive matrix of n×n, and the kernel matrix is ​​centered for Among them I n Indicates that each element is n×n matrix; Determine the matrix eigenvector α and eigenvalue λ according to the kernel matrix, where Kα=λα, and perform eigenvector normalization for Determine the retained principal components based on the eigenvalues ​​exceeding the preset cumulative contribution, and select the normalized eigenvectors exceeding the preset cumulative contribution for reconstruction for The acquiring of historical data and abnormal state statistical data, determining the insulation state index of the target transformer according to the abnormal state statistical data, and determining the threshold of the insulation state index of the target transformer according to the historical data include: According to the historical data and the abnormal state statistical data, Hotelling-T 2 Calculate T 2 Statistics, and, using the squared prediction error Q statistic, according to T 2 Statistics and Q statistics determine the insulation status index as in, is the nonlinear mapping matrix, is the principal component eigenvector, is the sample mapping mean, I is the identity matrix, and λ is the eigenvalue matrix; According to the normal state T in the historical data 2 and Q statistics, calculate T 2 Thresholds for the Q statistic and Q statistic and Q m for Among them, l represents the number of principal components retained, a is the confidence level; F a (l,nl) is the critical value of the F distribution under the condition of l and nl degrees of freedom, μ is the mean of the sample Q statistic, ρ is the standard deviation of the sample Q statistic The degree of freedom is h = 2μ 2 / ρ and chi-square distribution with confidence level a.

2. The transformer insulation status evaluation method according to claim 1, characterized in that: The step of acquiring the real-time monitoring data of the target transformer and determining the insulation state of the target transformer according to the real-time monitoring data, the insulation state index and the threshold value of the insulation state index includes: The transformer is calculated by the real-time monitoring data Statistics and Q r Statistics, based on threshold and Q m , calculate the outlier index Ψ as The insulation state of the target transformer is determined according to the value of the abnormal value indicator Ψ.

3. The transformer insulation status evaluation method according to claim 1, characterized in that: The method further comprises: According to the alarm interval range of the value of the abnormal value indicator Ψ and the insulation state, an alarm prompt of a corresponding level is executed.

4. A transformer insulation status assessment device, characterized in that: include: The first module is used to obtain the wind and solar power output data and load data connected to the target transformer according to the transformer insulation status assessment request, and determine the load factor of the target transformer according to the wind and solar power output data and the load data; The second module is used to collect the environmental parameters and insulation monitoring data of the target transformer, and determine the insulation state characteristic quantity of the target transformer by using kernel principal component analysis according to the load factor, the environmental parameters and the insulation monitoring data; The third module is used to obtain historical data and abnormal state statistical data, determine the insulation state index of the target transformer according to the abnormal state statistical data, and determine the threshold value of the insulation state index of the target transformer according to the historical data; A fourth module is used to obtain real-time monitoring data of the target transformer, and determine the insulation state of the target transformer according to the real-time monitoring data, the insulation state index and the threshold value of the insulation state index; The wind and solar power generation device may also be other non-steady-state power generation devices; It is also used for: collecting the environmental parameters through a first sensor, wherein the environmental data collected by the first sensor includes at least one of environmental temperature, rainfall, humidity and wind speed; collecting the insulation monitoring data through a second sensor, wherein the insulation monitoring data collected by the second sensor includes at least one of oil temperature, trace water, carbon monoxide, carbon dioxide, methane, ethane, ethylene, acetylene and hydrogen, wherein the collected insulation monitoring data can be customized; The first module is also used for: Taking the rated capacity of the target transformer as a reference value, performing normalization processing on the wind-solar output data and the load data to obtain a probability density function of wind power output, a probability density function of photovoltaic output, and a probability density function of load output, wherein the wind-solar output data includes wind power output data and photovoltaic output data; According to the wind power output probability density function, the photovoltaic output probability density function and the load output probability density function, a normal Copula function is used to construct a wind-solar-load multi-dimensional joint probability density distribution function f(p w ,p p ,p l )for Where I is the identity matrix, ζ′=[Φ -1 (a),Φ -1 (b),Φ -1 (c)], a, b, c represent the cumulative distribution function of wind power, photovoltaic cumulative distribution function and load cumulative distribution function respectively, Φ -1 represents the inverse function of the cumulative distribution function of the standard normal distribution, R is the product-moment correlation coefficient matrix of the normal Copula function, wherein the product-moment correlation coefficient matrix of the normal Copula function is calculated using at least one of the maximum information coefficient, the Kendall rank correlation coefficient, and the Spearman correlation coefficient; According to the multi-dimensional joint probability density distribution function of wind and solar load, the transformer load factor f(k) is determined as where p w 、p p 、p l Respectively represent the per unit value of wind power output, photovoltaic output and load; The third module is also used for: According to the transformer load factor f(k), environmental parameters and insulation monitoring data of the target transformer, the sample data matrix S is obtained as follows: S={X1,X2...X i ,...X n } Where i is the transformer quantity identifier, X i represents the characteristic quantity of the i-th transformer, and X i represents an m-dimensional vector, and n is the total number of samples; The sample data matrix is ​​passed through a nonlinear mapping function Mapped to a high-dimensional feature space, the dimension of the high-dimensional feature space is d, and then the d×n nonlinear mapping matrix φ(X) is obtained as {φ(X1),φ(X2),…,φ(X i )…,φ(X n )} Among them, the nonlinear mapping function The mapping method is φ(X):R m →R d , d>>m, where the nonlinear mapping function One of the radial basis kernel function, Gaussian kernel function and polynomial kernel function may also be used; According to the nonlinear mapping matrix, the kernel matrix K is determined as [φ(X) T φ(X)] Where K is a symmetric semi-positive matrix of n×n, and the kernel matrix is ​​centered for Among them I n Indicates that each element is n×n matrix; Determine the matrix eigenvector α and eigenvalue λ according to the kernel matrix, where Kα=λα, and perform eigenvector normalization for Determine the retained principal components based on the eigenvalues ​​exceeding the preset cumulative contribution, and select the normalized eigenvectors exceeding the preset cumulative contribution for reconstruction for The third module is also used for: According to the historical data and the abnormal state statistical data, Hotelling-T 2 Calculate T 2 Statistics, and, using the squared prediction error Q statistic, according to T 2 Statistics and Q statistics determine the insulation status index as in, is the nonlinear mapping matrix, is the principal component eigenvector, is the sample mapping mean, I is the identity matrix, and λ is the eigenvalue matrix; According to the normal state T in the historical data 2 and Q statistics, calculate T 2 Thresholds for the Q statistic and Q statistic and Q m for Among them, l represents the number of principal components retained, a is the confidence level; F a (l,nl) is the critical value of the F distribution under the condition of l and nl degrees of freedom, μ is the mean of the sample Q statistic, ρ is the standard deviation of the sample Q statistic The degree of freedom is h = 2μ 2 / ρ and chi-square distribution with confidence level a.

5. An electronic device, characterized in that: including a processor and a memory; The memory is used to store programs; The processor executes the program to implement the transformer insulation status evaluation method according to any one of claims 1 to 3.

6. A computer-readable storage medium, characterized in that: The storage medium stores a program, and the program is executed by a processor to implement the transformer insulation state evaluation method according to any one of claims 1 to 3.

Images