Power transmission and transformation model order reduction method, system and device and storage medium

Abstract

The invention discloses a power transmission and transformation model order reduction method, system and device and a storage medium, and belongs to the technical field of electric power, and the method comprises the steps: obtaining the original data of a power transmission and transformation device, carrying out the standardization processing of the original data, and constructing a power transmission and transformation device training data set; performing dimension reduction on the power transmission and transformation equipment training data set to obtain power transmission and transformation equipment dimension reduction data; training a multi-layer self-encoding model and a classification model according to the dimension reduction data of the power transmission and transformation equipment; constructing a power transmission and transformation equipment data classification model through the multi-layer self-encoding model and the classification model; building a digital twin reduced-order model of the power transmission and transformation equipment through the dimension reduction data of the power transmission and transformation equipment and the data classification model of the power transmission and transformation equipment; and obtaining high-dimensional data of the power transmission and transformation equipment, and performing order reduction on the high-dimensional data through the digital twin order reduction model of the power transmission and transformation equipment. The calculation efficiency of the digital twin model of the power transmission and transformation equipment is improved.

Description

Technical Field

[0001] The present invention relates to the field of electric power technology, and in particular to a method, system, device and storage medium for reducing the order of a power transmission and transformation model. Background Art

[0002] With the rapid development of smart grids, power transmission and transformation equipment, as a key component of the power system, has important significance for ensuring the safe and stable operation of the power grid through real-time monitoring and accurate prediction of its operating status. However, the data generated by power transmission and transformation equipment during operation often has high-dimensional and nonlinear characteristics, which brings great challenges to the modeling and analysis of the equipment. Traditional modeling methods have low computational efficiency when processing high-dimensional data, which limits the application effect of the model.

[0003] To overcome this problem, digital twin technology came into being. As an emerging modeling method, digital twin achieves comprehensive perception, dynamic monitoring and intelligent optimization of physical entities by building digital models that are highly consistent with physical entities. However, for power transmission and transformation equipment that can be modeled as high-dimensional digital twin models, how to improve the computational efficiency of digital twin models of power transmission and transformation equipment is a problem that still needs to be solved.

[0004] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0005] In view of the above-mentioned existing problems, the present invention aims to solve the technical problem of how to improve the computational efficiency of the digital twin model of power transmission and transformation equipment.

[0006] In order to solve the above technical problems, a power transmission and transformation model reduction method is proposed, including:

[0007] Obtain original data of power transmission and transformation equipment, and standardize the original data to construct a training data set for power transmission and transformation equipment; reduce the dimension of the training data set for power transmission and transformation equipment to obtain reduced-dimensional data of power transmission and transformation equipment; train a multi-layer autoencoder model and a classification model based on the reduced-dimensional data of power transmission and transformation equipment; construct a data classification model for power transmission and transformation equipment through the multi-layer autoencoder model and the classification model; build a digital twin reduced-order model for power transmission and transformation equipment through the reduced-dimensional data of power transmission and transformation equipment and the data classification model for power transmission and transformation equipment; obtain high-dimensional data of power transmission and transformation equipment, and reduce the high-dimensional data through the digital twin reduced-order model for power transmission and transformation equipment.

[0008] As a preferred solution of the power transmission and transformation model reduction method described in the present invention, wherein: the construction of the power transmission and transformation equipment training data set includes calculating the mean and standard deviation of the original data;

[0009] The mean is subtracted from each data point in the original data and the result is divided by the standard deviation to obtain a training data set for power transmission and transformation equipment.

[0010] As a preferred solution of the power transmission and transformation model reduction method described in the present invention, wherein: the power transmission and transformation equipment dimensionality reduction data includes constructing a power transmission and transformation equipment data matrix and a covariance matrix through the power transmission and transformation equipment training data set;

[0011] Performing eigenvalue decomposition on the covariance matrix to obtain eigenvalues ​​and corresponding eigenvectors;

[0012] Constructing a principal component matrix through the eigenvalues ​​and the eigenvectors;

[0013] The power transmission and transformation equipment data matrix is ​​multiplied by the principal component matrix to obtain the power transmission and transformation equipment dimensionality reduction data.

[0014] As a preferred solution of the power transmission and transformation model reduction method described in the present invention, wherein: the training of the multi-layer autoencoder model and the classification model includes setting a multi-layer autoencoder model with a decreasing number of hidden layer variables and constructing a separate input layer and output layer for each layer of the encoding network in the multi-layer autoencoder model;

[0015] Training the multi-layer autoencoder model layer by layer according to the dimension reduction data of the power transmission and transformation equipment;

[0016] Set up a classification model with fully connected layers;

[0017] The dimension-reduced data of the power transmission and transformation equipment is used as the input of the fully connected layer to train the classification model.

[0018] As a preferred solution of the power transmission and transformation model reduction method described in the present invention, wherein: the training of the multi-layer autoencoder model includes using the power transmission and transformation equipment dimension reduction data as the input of the first layer autoencoder of the multi-layer autoencoder model to obtain the first layer output result;

[0019] The output result of the first layer is used as the input of the second layer autoencoder to obtain the output result of the second layer, and so on, until the multi-layer autoencoder model is trained.

[0020] As a preferred solution of the power transmission and transformation model reduction method described in the present invention, wherein: the training of the classification model includes inputting the power transmission and transformation equipment dimension reduction data into the fully connected layer of the classification model to obtain the power transmission and transformation equipment output data;

[0021] According to the output data of the power transmission and transformation equipment, the parameters of the classification model are optimized to complete the training of the classification model.

[0022] As a preferred solution of the power transmission and transformation model reduction method described in the present invention, wherein: the construction of the power transmission and transformation equipment data classification model includes combining the multi-layer autoencoder network with the classification network to obtain an initial power transmission and transformation equipment data classification model;

[0023] The initial data classification model is optimized through the dimension reduction data to obtain a power transmission and transformation equipment data classification model.

[0024] Another object of the present invention is to provide a power transmission and transformation model reduction system, which aims to solve technical problems such as low data processing efficiency, high model training complexity, insufficient model accuracy and generalization ability, and difficulty in processing high-dimensional data. It improves data processing efficiency through standardized processing and dimensionality reduction, simplifies the model training process, reduces computing resource consumption, and combines multi-layer autoencoder models with classification models to improve model accuracy and generalization ability. Finally, the digital twin reduction model is used to realize the reduction of high-dimensional data, making it suitable for accurate analysis and prediction.

[0025] As a preferred solution of the power transmission and transformation model order reduction system described in the present invention, it is characterized by comprising a processing module, a dimensionality reduction module, a training module, a construction module, a building module and an order reduction module;

[0026] The processing module is used to obtain the original data of the power transmission and transformation equipment, and perform standardization processing on the original data to construct a training data set for the power transmission and transformation equipment;

[0027] The dimension reduction module is used to reduce the dimension of the power transmission and transformation equipment training data set to obtain the power transmission and transformation equipment dimension reduction data;

[0028] The training module is used to train the multi-layer autoencoder model and the classification model according to the dimension reduction data of the power transmission and transformation equipment;

[0029] The construction module is used to construct a power transmission and transformation equipment data classification model through the multi-layer autoencoder model and the classification model;

[0030] The building module is used to build a digital twin reduced-order model of power transmission and transformation equipment through the dimensionality reduction data of the power transmission and transformation equipment and the data classification model of the power transmission and transformation equipment;

[0031] The order reduction module is used to obtain high-dimensional data of power transmission and transformation equipment, and reduce the order of the high-dimensional data through the digital twin order reduction model of the power transmission and transformation equipment.

[0032] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and is characterized in that when the processor executes the computer program, the steps of the power transmission and transformation model reduction method are implemented.

[0033] A computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps of the power transmission and transformation model reduction method are implemented.

[0034] The beneficial effects of the present invention are as follows: the present application realizes dimensionality reduction processing of model data by constructing a reduced-order model of high-dimensional data, thereby improving the computational efficiency of the digital twin model of power transmission and transformation equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work, among which:

[0036] Figure 1 The overall process of a power transmission and transformation model reduction method provided by an embodiment of the present invention is Figure 1 .

[0037] Figure 2 A process of a power transmission and transformation model reduction method provided by an embodiment of the present invention Figure 2 .

[0038] Figure 3 A schematic diagram of the module structure of a power transmission and transformation model reduction system provided by an embodiment of the present invention.

[0039] Figure 4 A schematic diagram of the device structure of a hardware operating environment involved in a power transmission and transformation model reduction system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0040] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0041] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0042] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it an embodiment that is mutually exclusive with other embodiments, either individually or selectively.

[0043] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0044] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0045] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0046] Example 1, reference Figure 1-Figure 2 , which is the first embodiment of the present invention, and provides a method for reducing the order of a power transmission and transformation model, comprising:

[0047] At present, digital twins, as an emerging modeling method, realize comprehensive perception, dynamic monitoring and intelligent optimization of physical entities by building digital models that are highly consistent with physical entities. However, for power transmission and transformation equipment that can be modeled as high-dimensional digital twin models, how to improve the computational efficiency of digital twin models of power transmission and transformation equipment is a problem that still needs to be solved.

[0048] This application achieves dimensionality reduction processing of model data by constructing a reduced-order model of high-dimensional data, thereby improving the computational efficiency of the digital twin model of power transmission and transformation equipment.

[0049] S1: Acquire original data of power transmission and transformation equipment, and perform standardization on the original data to construct a training data set for power transmission and transformation equipment.

[0050] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a device for building a digital twin reduced-order model of power transmission and transformation equipment based on data optimization, etc. The following takes the device for building a digital twin reduced-order model of power transmission and transformation equipment based on data optimization as an example to illustrate this embodiment and the following embodiments.

[0051] It should be noted that power transmission and transformation equipment includes incoming power lines, transformers, disconnectors, circuit breakers, current transformers, voltage transformers, lightning arresters, outgoing power lines, transmission lines, etc. The original data includes power transmission and transformation equipment status data, such as current, voltage, power, temperature, etc.; power transmission and transformation equipment environmental monitoring data, such as ambient temperature, humidity, air quality, etc.

[0052] It is understandable that standardizing the raw data can eliminate the dimensional differences between different features of the raw data, allowing the data to be compared and calculated on the same scale, which can improve the training efficiency and performance of subsequent models.

[0053] Specifically, the steps of standardizing the original data and constructing a training data set for power transmission and transformation equipment include:

[0054] Calculate the mean and standard deviation of the original data;

[0055] The mean is subtracted from each data point in the original data and the result is divided by the standard deviation to obtain a training data set for power transmission and transformation equipment.

[0056] Data standardization is to convert the original data into standardized data with a mean of 0 and a variance of 1. By subtracting the mean from each data point in the original data and dividing it by the standard deviation, the new data point obtained is standardized data, which can be used as a training data set for power transmission and transformation equipment.

[0057] S2: Performing dimension reduction on the power transmission and transformation equipment training data set to obtain dimension reduction data of the power transmission and transformation equipment.

[0058] It should be noted that data dimensionality reduction is to reduce the dimension of the data while retaining the main information of the original data, reduce the complexity of the data, and reduce the computational complexity of subsequent model training.

[0059] The step of reducing the dimension of the power transmission and transformation equipment training data set to obtain the reduced-dimensional data of the power transmission and transformation equipment comprises:

[0060] Constructing a power transmission and transformation equipment data matrix and a covariance matrix through the power transmission and transformation equipment training data set;

[0061] Performing eigenvalue decomposition on the covariance matrix to obtain eigenvalues ​​and corresponding eigenvectors;

[0062] Constructing a principal component matrix through the eigenvalues ​​and the eigenvectors;

[0063] The power transmission and transformation equipment data matrix is ​​multiplied by the principal component matrix to obtain the power transmission and transformation equipment dimensionality reduction data.

[0064] It can be understood that the data matrix of power transmission and transformation equipment is a matrix of n rows and p columns constructed from the original data, where n is the number of samples and p is the number of features. The covariance matrix is ​​used to measure the linear correlation between two variables. By calculating the covariance of each pair of variables, the covariance matrix can be obtained. The covariance calculation formula is:

[0065]

[0066] Where Cov(X, Y) is the covariance of X and Y, x i and i is the ith observation of X and Y, μ x and μ y is the mean of X and Y, and n is the number of observations.

[0067] Eigenvalue decomposition is a method of decomposing a matrix into the product of matrices represented by its eigenvalues ​​and eigenvectors. For a real symmetric matrix A, the formula for eigenvalue decomposition is:

[0068] A=QΛQ T

[0069] Among them, Q is an orthogonal matrix composed of the eigenvectors of the real symmetric matrix A, whose column vector is the unit eigenvector of A, Λ is a diagonal matrix, whose diagonal elements are the corresponding eigenvalues ​​of A, and QT is the transposed matrix of Q. According to actual needs or preset thresholds, the eigenvectors corresponding to the first k largest eigenvalues ​​are selected as principal components, where k is the dimension after dimensionality reduction, and the selected k eigenvectors are used as columns to construct the principal component matrix. Multiply the power transmission and transformation equipment data matrix by the principal component matrix to obtain a matrix with n rows and k columns, which is the dimensionality reduction data of the power transmission and transformation equipment.

[0070] S3: Training a multi-layer autoencoder model and a classification model according to the dimension reduction data of the power transmission and transformation equipment.

[0071] like Figure 2 As shown, it should be noted that the multi-layer autoencoder consists of multiple hidden layers, which are located between the input layer and the output layer. The input layer receives the original data, while the output layer attempts to reconstruct the input data. The classification model contains the structure of a fully connected layer network, and the number of neurons in the output layer matches the number of categories of the classification task.

[0072] Step S301: setting a multi-layer autoencoder model with a decreasing number of hidden layer variables and constructing a separate input layer and output layer for each layer of the encoding network in the multi-layer autoencoder model;

[0073] It should be noted that by designing a multi-layer autoencoder, the number of hidden variables decreases layer by layer, and the deep features of the data can be gradually extracted.

[0074] Step S302: training the multi-layer autoencoder model layer by layer according to the dimension reduction data of the power transmission and transformation equipment;

[0075] The dimensionality reduction data of power transmission and transformation equipment is used to train network parameters layer by layer and learn the characteristic information of the data.

[0076] In a feasible manner, the step of training the multi-layer autoencoder model layer by layer according to the dimension reduction data of the power transmission and transformation equipment includes:

[0077] Using the dimension reduction data of the power transmission and transformation equipment as the input of the first layer autoencoder of the multi-layer autoencoder model to obtain the first layer output result;

[0078] The output result of the first layer is used as the input of the second layer autoencoder to obtain the output result of the second layer, and so on, until the multi-layer autoencoder model is trained.

[0079] Step S303: Set up a classification model including a fully connected layer; the characteristic of the fully connected layer is that each node of the layer is connected to all nodes of the previous layer, and there is a certain connection weight between each input feature and each neuron. These weights are used to adjust the influence of the input data. The fully connected layer is usually used for classification, and the classification effect can be achieved by adjusting the number of nodes and weights of the output layer.

[0080] Step S304: using the dimension-reduced data of the power transmission and transformation equipment as input of the fully connected layer to train the classification model.

[0081] The dimension-reduced data of power transmission and transformation equipment is used as the input of the fully connected layer network, and the output is the classification result of the data.

[0082] In a feasible manner, the step of using the dimension reduction data of the power transmission and transformation equipment as the input of the fully connected layer to train the classification model includes:

[0083] Inputting the dimension reduction data of the power transmission and transformation equipment into the fully connected layer of the classification model to obtain the output data of the power transmission and transformation equipment;

[0084] According to the output data of the power transmission and transformation equipment, the parameters of the classification model are optimized to complete the training of the classification model.

[0085] In this embodiment, a multi-layer autoencoder model with a decreasing number of hidden layer variables is set up, and a separate input layer and output layer are constructed for each layer of the encoding network in the multi-layer autoencoder model; the multi-layer autoencoder model is trained layer by layer according to the reduced-dimensional data of the power transmission and transformation equipment; a classification model including a fully connected layer is set up; and the reduced-dimensional data of the power transmission and transformation equipment is used as the input of the fully connected layer to train the classification model.

[0086] In summary, this embodiment solves the technical problem of how to improve the computational efficiency of the digital twin model of power transmission and transformation equipment by training a multi-layer autoencoder model and a classification model.

[0087] S4: Constructing a data classification model for power transmission and transformation equipment through the multi-layer autoencoding model and the classification model.

[0088] It is understandable that the multi-layer autoencoder model and the classification model are combined to construct an efficient data classification network for power transmission and transformation equipment, and the network is optimized by fine-tuning. This step is to further improve the classification performance of the model by integrating the feature extraction ability of the autoencoder and the classification ability of the classification network to achieve better data classification results.

[0089] The steps of constructing a data classification model for power transmission and transformation equipment by using the multi-layer autoencoder model and the classification model include:

[0090] The multi-layer autoencoder network is combined with the classification network to obtain an initial power transmission and transformation equipment data classification model; the initial data classification model is optimized through the dimension reduction data to obtain a power transmission and transformation equipment data classification model.

[0091] It should be noted that the specific step of combining the multi-layer autoencoder network with the classification network is to use the output of the multi-layer autoencoder as the input of the classification network and construct a fully connected layer network for classification, so that the initial power transmission and transformation equipment data classification model can directly use the feature information extracted by the autoencoder, thereby improving the accuracy of classification. The step of optimizing the initial power transmission and transformation equipment data classification model through the reduced dimension data is to make small-scale adjustments to the initial power transmission and transformation equipment data classification model to further optimize the performance of the model. The back-propagation gradient descent algorithm can be used to update the parameters so that the classification performance of the initial power transmission and transformation equipment data classification model is optimized, and the power transmission and transformation equipment data classification model is obtained. The gradient descent formula is:

[0092]

[0093]

[0094] Among them, θ represents the model parameters, which can be weights or biases, and α is the learning rate, which is used to control the size of each update step. is the loss function and J(θ) is the gradient with respect to the parameter θ.

[0095] S5: Building a digital twin reduced-order model of power transmission and transformation equipment through the dimensionality reduction data of the power transmission and transformation equipment and the data classification model of the power transmission and transformation equipment.

[0096] It is understood that the principal component extraction process of the dimensionality reduction data of the power transmission and transformation equipment and the data classification network of the power transmission and transformation equipment are combined to build a reduced-order model for high-dimensional data, forming a complete reduced-order model for dimensionality reduction and feature extraction of the high-dimensional digital twin model.

[0097] S6: Acquire high-dimensional data of the power transmission and transformation equipment, and reduce the order of the high-dimensional data through the digital twin reduction model of the power transmission and transformation equipment.

[0098] It is understandable that the digital twin reduced-order model of the power transmission and transformation equipment can reduce the order of high-dimensional data of the power transmission and transformation equipment and reduce data complexity.

[0099] When using the digital twin reduced-order model of power transmission and transformation equipment, first input the high-dimensional data of the power transmission and transformation equipment, perform coarse dimensionality reduction on the data through principal component analysis, then use a multi-layer autoencoder to extract the high-level feature information of the data, and finally classify the high-level feature information of the data according to the classification network to obtain the data classification result. It should be noted that the new data is first standardized using the mean and variance of the offline data set, and then the new data is added to the offline data set, and the mean and variance of the offline data set are updated.

[0100] Example 2, reference Figure 4 The second embodiment of the present invention is different from the previous embodiment in that:

[0101] like Figure 4 As shown, Figure 4 The power transmission and transformation model reduction device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0102] The power transmission and transformation model reduction device may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the power transmission and transformation model reduction device are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the power transmission and transformation model reduction device to communicate with other devices wirelessly or by wire to exchange data. Although the power transmission and transformation model reduction device with various systems is shown in the figure, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.

[0103] 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, and other media that can store program codes.

[0104] 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.

[0105] 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.

[0106] 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.

[0107] Example 3, reference Figure 3 , which is the third embodiment of the present invention, and provides a power transmission and transformation model order reduction system, including a processing module 10, a dimension reduction module 20, a training module 30, a construction module 40, a building module 50 and an order reduction module 60;

[0108] The processing module 10 is used to obtain the original data of the power transmission and transformation equipment, and perform standardization processing on the original data to construct a training data set for the power transmission and transformation equipment;

[0109] The processing module 10 is further used to calculate the mean and standard deviation of the original data; and to subtract the mean from each data point in the original data and divide the result by the standard deviation to obtain a training data set for power transmission and transformation equipment.

[0110] A dimension reduction module 20 is used to reduce the dimension of the power transmission and transformation equipment training data set to obtain the power transmission and transformation equipment dimension reduction data;

[0111] The dimension reduction module 20 is also used to construct a power transmission and transformation equipment data matrix and a covariance matrix through the power transmission and transformation equipment training data set; perform eigenvalue decomposition on the covariance matrix to obtain eigenvalues ​​and corresponding eigenvectors; construct a principal component matrix through the eigenvalues ​​and the eigenvectors; multiply the power transmission and transformation equipment data matrix by the principal component matrix to obtain the power transmission and transformation equipment dimensionality reduction data.

[0112] A training module 30, for training a multi-layer autoencoder model and a classification model according to the dimension reduction data of the power transmission and transformation equipment;

[0113] The training module 30 is also used to set a multi-layer 20 encoding model with a decreasing number of hidden layer variables and construct a separate input layer and output layer for each layer of the encoding network in the multi-layer autoencoder model; train the multi-layer autoencoder model layer by layer according to the reduced dimensionality data of the power transmission and transformation equipment; set a classification model including a fully connected layer; use the reduced dimensionality data of the power transmission and transformation equipment as the input of the fully connected layer to train the classification model.

[0114] The training module 30 is also used to use the reduced-dimensional data of the power transmission and transformation equipment as the input of the first-layer autoencoder of the multi-layer autoencoder model to obtain the first-layer output result; use the first-layer output result as the input of the second-layer autoencoder to obtain the second-layer output result, and so on, until the training of the multi-layer autoencoder model is completed.

[0115] The training module 30 is also used to input the reduced-dimensional data of the power transmission and transformation equipment into the fully connected layer of the classification model to obtain the output data of the power transmission and transformation equipment; optimize the parameters of the classification model according to the output data of the power transmission and transformation equipment to complete the training of the classification model.

[0116] The construction module 40 is used to construct a power transmission and transformation equipment data classification model through the multi-layer autoencoder model and the classification model.

[0117] A building module 50 is used to build a digital twin reduced-order model of power transmission and transformation equipment through the dimensionality reduction data of the power transmission and transformation equipment and the data classification model of the power transmission and transformation equipment;

[0118] The building module 50 is also used to combine the multi-layer autoencoder network with the classification network to obtain an initial power transmission and transformation equipment data classification model; optimize the initial data classification model through the dimensionality reduction data to obtain a power transmission and transformation equipment data classification model.

[0119] The order reduction module 60 is used to obtain high-dimensional data of the power transmission and transformation equipment, and reduce the order of the high-dimensional data through the digital twin order reduction model of the power transmission and transformation equipment.

[0120] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A power transmission and transformation model reduction method, characterized by: include, Acquire the original data of the power transmission and transformation equipment, and perform standardization on the original data to construct a training data set for the power transmission and transformation equipment; Performing dimensionality reduction on the power transmission and transformation equipment training data set to obtain dimensionality reduction data of the power transmission and transformation equipment; Training a multi-layer autoencoder model and a classification model according to the dimension reduction data of the power transmission and transformation equipment; Constructing a data classification model for power transmission and transformation equipment through the multi-layer autoencoder model and the classification model; Building a digital twin reduced-order model of power transmission and transformation equipment through the dimensionality reduction data of the power transmission and transformation equipment and the data classification model of the power transmission and transformation equipment; High-dimensional data of power transmission and transformation equipment is obtained, and the high-dimensional data is reduced in order through a digital twin reduction model of the power transmission and transformation equipment.

2. A power transmission and transformation model reduction method according to claim 1, characterized in that: The constructing of the power transmission and transformation equipment training data set includes calculating the mean and standard deviation of the original data; The mean is subtracted from each data point in the original data and the result is divided by the standard deviation to obtain a training data set for power transmission and transformation equipment.

3. A power transmission and transformation model reduction method as claimed in claim 2, characterized in that: The power transmission and transformation equipment dimensionality reduction data includes constructing a power transmission and transformation equipment data matrix and a covariance matrix through the power transmission and transformation equipment training data set; Performing eigenvalue decomposition on the covariance matrix to obtain eigenvalues ​​and corresponding eigenvectors; Constructing a principal component matrix through the eigenvalues ​​and the eigenvectors; The power transmission and transformation equipment data matrix is ​​multiplied by the principal component matrix to obtain the power transmission and transformation equipment dimensionality reduction data.

4. A power transmission and transformation model reduction method as claimed in claim 3, characterized in that: The training of the multi-layer autoencoder model and the classification model includes setting a multi-layer autoencoder model with a decreasing number of hidden layer variables and constructing a separate input layer and output layer for each layer of the encoding network in the multi-layer autoencoder model; Training the multi-layer autoencoder model layer by layer according to the dimension reduction data of the power transmission and transformation equipment; Set up a classification model with fully connected layers; The dimension-reduced data of the power transmission and transformation equipment is used as the input of the fully connected layer to train the classification model.

5. A power transmission and transformation model reduction method as claimed in claim 4, characterized in that: The training of the multi-layer autoencoder model includes using the dimension reduction data of the power transmission and transformation equipment as the input of the first layer autoencoder of the multi-layer autoencoder model to obtain the first layer output result; The output result of the first layer is used as the input of the second layer autoencoder to obtain the output result of the second layer, and so on, until the multi-layer autoencoder model is trained.

6. A power transmission and transformation model reduction method as claimed in claim 5, characterized in that: The training of the classification model includes inputting the dimension reduction data of the power transmission and transformation equipment into the fully connected layer of the classification model to obtain the output data of the power transmission and transformation equipment; According to the output data of the power transmission and transformation equipment, the parameters of the classification model are optimized to complete the training of the classification model.

7. A power transmission and transformation model reduction method according to claim 6, characterized in that: The constructing of the power transmission and transformation equipment data classification model includes combining the multi-layer autoencoder network with the classification network to obtain an initial power transmission and transformation equipment data classification model; The initial data classification model is optimized through the dimension reduction data to obtain a power transmission and transformation equipment data classification model.

8. A system using a power transmission and transformation model reduction method as claimed in any one of claims 1 to 7, characterized in that: It includes processing module, dimension reduction module, training module, construction module, building module and order reduction module; The processing module is used to obtain the original data of the power transmission and transformation equipment, and perform standardization processing on the original data to construct a training data set for the power transmission and transformation equipment; The dimension reduction module is used to reduce the dimension of the power transmission and transformation equipment training data set to obtain the power transmission and transformation equipment dimension reduction data; The training module is used to train the multi-layer autoencoder model and the classification model according to the dimension reduction data of the power transmission and transformation equipment; The construction module is used to construct a power transmission and transformation equipment data classification model through the multi-layer autoencoder model and the classification model; The building module is used to build a digital twin reduced-order model of power transmission and transformation equipment through the dimensionality reduction data of the power transmission and transformation equipment and the data classification model of the power transmission and transformation equipment; The order reduction module is used to obtain high-dimensional data of power transmission and transformation equipment, and reduce the order of the high-dimensional data through the digital twin order reduction model of the power transmission and transformation equipment.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of a method for reducing the order of a power transmission and transformation model described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of a power transmission and transformation model reduction method described in any one of claims 1 to 7 are implemented.

Images