A method and system for monitoring the operating status of substation equipment based on digital twins

Abstract

A method and system for monitoring the operating status of substation equipment based on digital twins, the method comprising: obtaining substation detection data, analyzing the substation detection data, and screening out characteristic data; first, establishing a 3D digital model of the substation based on the substation's real-life physical objects and three-dimensional geometric data, and simultaneously constructing a substation characteristic database; then, performing feature matching on the 3D digital model based on the substation's operating status and real-time parameters to form a substation digital twin; then, analyzing the operating data in the substation digital twin and outputting fault characteristic data; and performing fault analysis on substation equipment based on the fault characteristic data. The present invention establishes a substation digital twin by modeling and simulating the entire substation data to simulate the substation's operating environment, enabling real-time monitoring of substation operating information and data, and greatly improving the reliability and real-time performance of substation fault handling.

Description

Technical Field

[0001] The present invention relates to the field of substation operation, maintenance and management, and in particular to a substation equipment operating status monitoring method and system based on digital twins. Background Art

[0002] With the continuous development of power systems, the scale and complexity of substations are also increasing, and the requirements for the safety and reliability of substation operations are becoming increasingly stringent. As the core of the power system, substations are directly related to the stability and reliability of the system power supply.

[0003] However, traditional substation monitoring and data collection systems typically rely on manual inspections, relying on manual patrols and testing of various substation equipment to detect and alert power equipment problems. This method lacks timeliness, accuracy, and reliability, and is prone to missed detections and misjudgments. Furthermore, while some common monitoring methods, such as jumper temperature measurement and ultrasonic testing, have been adopted during substation construction, these methods often only monitor single fault conditions and fail to fully cover all possible substation fault scenarios. This presents a significant challenge for substation fault monitoring. Summary of the Invention

[0004] The purpose of the present invention is to overcome the above-mentioned defects and problems existing in the prior art, and to provide a substation equipment operation status monitoring method and system based on digital twins. By modeling the entities and operation data of the entire substation, a substation digital twin is constructed to simulate the operating environment of the substation, and to realize real-time monitoring of the substation operation information and data, so as to improve the reliability and real-time performance of substation fault handling.

[0005] To achieve the above objectives, the technical solution of the present invention is: a method for monitoring the operating status of substation equipment based on digital twins, comprising:

[0006] Obtain substation detection data, analyze the substation detection data, and filter out characteristic data;

[0007] First, a 3D digital model of the substation is established based on the actual physical objects and 3D geometric data of the substation. At the same time, a feature database of the substation is constructed. Then, based on the operating status and real-time parameters of the substation, feature matching is performed on the 3D digital model to form a digital twin of the substation. The operating data in the digital twin of the substation is then analyzed to output fault feature data.

[0008] Conduct fault analysis on substation equipment based on fault characteristic data.

[0009] The analysis of substation detection data to screen out characteristic data includes:

[0010] Normalize the substation detection data to obtain the data matrix Y;

[0011] According to the data matrix Y, the following target loss function is established:

[0012]

[0013] Where h is the target loss function; u represents the mapping matrix of the data matrix Y in the feature space;

[0014] Calculate the covariance matrix C of the data matrix Y:

[0015]

[0016] Where m is the number of data matrices Y;

[0017] Minimize the objective loss function h, and establish the following Lagrangian function based on the Lagrangian multiplier method:

[0018] f(u,λ)=u T Cu-λ(u T u-1);

[0019] Where λ is the penalty factor;

[0020] The penalty factor λ is obtained by finding the extreme value of the Lagrangian function, and the mapping matrix u is obtained using the following formula:

[0021] Cu=λu;

[0022] Perform eigenvector principal component screening on the mapping matrix u to obtain the principal components of the mapping matrix u;

[0023] The principal components of multiple groups of mapping matrices u are subjected to convolution calculation, maximum pooling and full splicing operations to obtain feature data.

[0024] The performing eigenvector principal component screening on the mapping matrix u to obtain the principal component of the mapping matrix u includes:

[0025] The mapping matrix u is transformed as follows to obtain the new variable:

[0026]

[0027] Where, β=(q1,q2,...,q r ) T is a new variable, u=(u1,u2,...,u s ) T is the mapping matrix, r<s; a rs is an algebraic relation matrix;

[0028] Create the following new variable matrix:

[0029]

[0030] Diagonalize the matrix β and find the characteristic roots;

[0031] Calculate the eigenvectors according to the eigenroots, arrange the eigenvectors into a matrix by row from top to bottom according to the size of the corresponding eigenroots, take the first k rows to form a new matrix P, and use the new matrix P as the principal component of the mapping matrix u.

[0032] The feature matching of the 3D digital model to form a substation digital twin includes:

[0033] Calculate the expected target value:

[0034]

[0035] Where L(θ) is the expected target value; θ=[θ1,θ2,…,θ m ] is the collected substation electrical data; y is the substation electrical data number;

[0036] Calculate the difference characteristics of the twin output data:

[0037] F dif = abs(L(p)-L(θ));

[0038] Where, F dif is the data difference eigenvalue; L(p) represents the target value of the new matrix P;

[0039] Calculate the error function:

[0040]

[0041] Where M is the quantity;

[0042] The expected target value L(θ) and the difference characteristics of the output data are continuously iterated until the error function is within a reasonable range;

[0043] The expected target value after iteration is used as the data of the 3D digital model to form a digital twin of the substation.

[0044] The fault analysis of substation equipment according to the fault characteristic data includes:

[0045] The substation historical data is mapped to the fault type one by one. The mapping function used is as follows:

[0046] y i =f(x i1 , x i2 ,...x iN );

[0047] Where x i is the state parameter of the i-th device; N is the number of parameters; f is the mapping from substation status to fault type; y i is the fault type;

[0048] Use the following formula to classify fault information:

[0049]

[0050] Where, is the mapping from the original space to the N-dimensional feature space; x i and χ nn are input and weight vectors respectively; H is the regularization constant; is the slack variable; b nn is the hyperplane threshold;

[0051] Use group search method to update and iterate the classification;

[0052] When the error accuracy is reached, the iteration is stopped and the fault diagnosis type is output.

[0053] The method further includes fault diagnosis:

[0054] According to the fault diagnosis type, the fault information is classified and coded according to the voltage, current and temperature fault types;

[0055] Set failure criteria and thresholds for all failures;

[0056] Establish a fault tree based on fault standards and thresholds, fault characteristic information, and fault diagnosis type, and encode the fault tree address;

[0057] The substation equipment operation data is implanted into the fault tree, and query and analysis are performed to obtain fault diagnosis information.

[0058] The method further includes determining the cause of the fault:

[0059] The following formula is used to filter the fault information. When γ>0, it indicates that the fault information is valid. If γ<0, the fault information is considered to be noise and should be discarded.

[0060]

[0061] Where, γ is the fault information evaluation benchmark; H k (x p ) represents the discretization degree of the nearest k points; e k (x p ) is the local density of the sample; k is the fault information number; dist(x q ) represents x q Distance to the origin;

[0062] Encode and reduce the dimension of the filtered fault information;

[0063] Encode the processed fault information in the fault tree and traverse and compare;

[0064] The fault type is obtained through the optimization algorithm, and the fault cause is given through the fault tree.

[0065] A substation equipment operating status monitoring system based on digital twins, which is applied to the above-mentioned method, comprises:

[0066] The characteristic data acquisition module is used to obtain substation detection data, analyze the substation detection data, and filter out characteristic data;

[0067] The substation digital twin generation module is used to first establish a 3D digital model of the substation based on the substation's physical scene and 3D geometric data, and simultaneously build a substation feature database. It then performs feature matching on the 3D digital model based on the substation's operating status and real-time parameters to form the substation digital twin. It then analyzes the operating data in the substation digital twin and outputs fault feature data.

[0068] The substation fault analysis module is used to perform fault analysis on substation equipment based on fault characteristic data.

[0069] A substation equipment operating status monitoring device based on digital twins, comprising a memory and a processor;

[0070] The memory is configured to store computer program code and transmit the computer program code to the processor;

[0071] The processor is configured to execute the method according to the instructions in the computer program code.

[0072] A computer-readable storage medium stores a computer program, which implements the above-mentioned method when executed by a processor.

[0073] Compared with the prior art, the present invention has the following beneficial effects:

[0074] The present invention provides a method and system for monitoring the operating status of substation equipment based on digital twins. The method constructs a digital twin of the substation by modeling the entities and operating data of the entire substation to simulate the operating environment of the substation, thereby realizing real-time monitoring of the substation operating information and data, and greatly improving the reliability and real-time performance of substation fault handling. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] Figure 1 This is a flow chart of a method for monitoring the operating status of substation equipment based on digital twins of the present invention.

[0076] Figure 2 This is a structural block diagram of a substation equipment operation status monitoring system based on digital twins of the present invention.

[0077] Figure 3 It is an architectural diagram of a substation equipment operation status monitoring system based on digital twins in an embodiment of the present invention.

[0078] Figure 4 This is a structural block diagram of a substation equipment operation status monitoring device based on digital twins in the present invention. DETAILED DESCRIPTION

[0079] The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0080] See also Figure 1 , a substation equipment operating status monitoring method based on digital twin, comprising:

[0081] S1. Obtain substation detection data, analyze the substation detection data, and filter out characteristic data;

[0082] S2. First, build a 3D digital model of the substation based on the actual physical scene and 3D geometric data of the substation, and simultaneously construct a feature database of the substation. Then, perform feature matching on the 3D digital model based on the substation's operating status and real-time parameters to form a digital twin of the substation. Then, analyze the operating data in the digital twin of the substation and output fault feature data.

[0083] S3. Perform fault analysis on substation equipment based on fault characteristic data.

[0084] Furthermore, the substation detection data is analyzed to screen out characteristic data, including:

[0085] Normalize the substation detection data to obtain the data matrix Y;

[0086] According to the data matrix Y, the following target loss function is established:

[0087]

[0088] Where h is the target loss function; u represents the mapping matrix of the data matrix Y in the feature space;

[0089] Calculate the covariance matrix C of the data matrix Y:

[0090]

[0091] Where m is the number of data matrices Y;

[0092] Minimize the objective loss function h, and establish the following Lagrangian function based on the Lagrangian multiplier method:

[0093] f(u,λ)=u T Cu-λ(u T u-1);

[0094] Where λ is the penalty factor;

[0095] The penalty factor λ is obtained by finding the extreme value of the Lagrangian function, and the mapping matrix u is obtained using the following formula:

[0096] Cu=λu;

[0097] Perform eigenvector principal component screening on the mapping matrix u to obtain the principal components of the mapping matrix u;

[0098] The principal components of multiple groups of mapping matrices u are subjected to convolution calculation, maximum pooling and full splicing operations to obtain feature data.

[0099] Furthermore, the eigenvector principal component screening of the mapping matrix u to obtain the principal component of the mapping matrix u includes:

[0100] The mapping matrix u is transformed as follows to obtain the new variable:

[0101]

[0102] Where, β=(q1,q2,...,q r ) T is a new variable, u=(u1,u2,...,u s ) T is the mapping matrix, r<s; a rs is an algebraic relation matrix;

[0103] Create the following new variable matrix:

[0104]

[0105] Diagonalize the matrix β and find the characteristic roots;

[0106] Calculate the eigenvectors according to the eigenroots, arrange the eigenvectors into a matrix by row from top to bottom according to the size of the corresponding eigenroots, take the first k rows to form a new matrix P, and use the new matrix P as the principal component of the mapping matrix u.

[0107] Furthermore, the feature matching of the 3D digital model to form a substation digital twin includes:

[0108] Calculate the expected target value:

[0109]

[0110] Where L(θ) is the expected target value; θ=[θ1,θ2,…,θ m ] is the collected substation electrical data; y is the substation electrical data number;

[0111] Calculate the difference characteristics of the twin output data:

[0112] F dif = abs(L(p)-L(θ));

[0113] Where, F dif is the data difference eigenvalue; L(p) represents the target value of the new matrix P;

[0114] Calculate the error function:

[0115]

[0116] Where M is the quantity;

[0117] The expected target value L(θ) and the difference characteristics of the output data are continuously iterated until the error function is within a reasonable range;

[0118] The expected target value after iteration is used as the data of the 3D digital model to form a digital twin of the substation.

[0119] Using digital twin technology to model and simulate substations, and simulating the substation's operating environment based on digital twins, can better identify and analyze substation faults. The efficient data processing capabilities provided by digital twins enable high-quality predictions and decisions based on large amounts of data, ensuring the stability and reliability of substation operations.

[0120] Furthermore, the fault analysis of the substation equipment according to the fault characteristic data includes:

[0121] The substation historical data is mapped to the fault type one by one. The mapping function used is as follows:

[0122] y i =f(x i1 , x i2 ,...x iN );

[0123] Where x i is the state parameter of the i-th device; N is the number of parameters; f is the mapping from substation status to fault type; y i is the fault type;

[0124] Use the following formula to classify fault information:

[0125]

[0126] Where, is the mapping from the original space to the N-dimensional feature space; x i and χ nn are input and weight vectors respectively; H is the regularization constant; is the slack variable; b nn is the hyperplane threshold;

[0127] Use group search method to update and iterate the classification;

[0128] When the error accuracy is reached, the iteration is stopped and the fault diagnosis type is output.

[0129] In another embodiment of the present application, a method for monitoring the operating status of substation equipment based on digital twins further includes fault diagnosis:

[0130] According to the fault diagnosis type, the fault information is classified and coded according to voltage, current, temperature fault type, etc.

[0131] Set failure criteria and thresholds for all failures;

[0132] Establish a fault tree based on fault standards and thresholds, fault characteristic information, and fault diagnosis type, and encode the fault tree address;

[0133] The substation equipment operation data is implanted into the fault tree, and query and analysis are performed to obtain fault diagnosis information.

[0134] In another embodiment of the present application, a method for monitoring the operating status of substation equipment based on digital twins further includes determining the cause of the fault:

[0135] The following formula is used to filter the fault information. When γ>0, it indicates that the fault information is valid. If γ<0, the fault information is considered to be noise and should be discarded.

[0136]

[0137] Where, γ is the fault information evaluation benchmark; H k (x p ) represents the discretization degree of the nearest k points; e k (x p ) is the local density of the sample; k is the fault information number; dist(x q ) represents x q Distance from the origin, x q ∈N k (xp );

[0138] Encode and reduce the dimension of the filtered fault information;

[0139] Encode the processed fault information in the fault tree and traverse and compare;

[0140] The fault type is obtained through the optimization algorithm, and the fault cause is given through the fault tree. According to the fault cause, corresponding treatment methods can be formulated to improve the reliability and timeliness of fault handling.

[0141] See also Figure 2 The present invention also provides a substation equipment operating status monitoring system based on digital twins, which is applied to a substation equipment operating status monitoring method based on digital twins. The system includes:

[0142] The characteristic data acquisition module is used to obtain substation detection data, analyze the substation detection data, and filter out characteristic data;

[0143] The substation digital twin generation module is used to first establish a 3D digital model of the substation based on the substation's physical scene and 3D geometric data, and simultaneously build a substation feature database. It then performs feature matching on the 3D digital model based on the substation's operating status and real-time parameters to form the substation digital twin. It then analyzes the operating data in the substation digital twin and outputs fault feature data.

[0144] The substation fault analysis module is used to perform fault analysis on substation equipment based on fault characteristic data.

[0145] Specifically, such as Figure 3 As shown in the figure, the substation equipment operation status monitoring system based on digital twins consists of four parts: perception layer, data layer, platform layer and application layer. Among them, the perception layer is based on the physical network and sensors, including environmental perception network, equipment perception network, infrared video perception network, mobile monitoring equipment, etc., to collect data such as the substation environment and equipment operation, that is, to obtain substation detection data. The data layer uses big data and artificial intelligence technology to realize data collection, transmission, management and other functions, and archives and backs up the data for subsequent mining and analysis. The platform layer realizes data mapping, physical entity modeling, equipment simulation modeling, data processing, artificial intelligence analysis, collaborative computing and other functions based on digital twin technology, and provides business interfaces for specific application scenarios. The application layer uses digital twins to realize application functions such as substation performance analysis, fault diagnosis, trend prediction and data monitoring. When applied, the following steps are included:

[0146] Step 1: Obtain substation detection data through the perception layer;

[0147] Step 2: Analyze the detection data of the perception layer through the data layer to filter out the feature data;

[0148] Step 3: Use the platform layer to form a digital twin of the substation, perform collaborative calculations on the characteristic data of the data layer, and perform intelligent analysis and processing;

[0149] Step 4: Based on the platform layer data obtained in step 3, visual application processing is performed through the application layer to realize functions such as operation monitoring and fault analysis of substation equipment.

[0150] The implementation process of the substation digital twin is as follows:

[0151] 1) Based on the actual physical objects and 3D geometric data of the substation, a 3D digital model of the substation is established, and a feature database of the substation system is constructed;

[0152] 2) Based on the substation’s operating status data and real-time parameters, feature matching is performed on the 3D digital model to form a substation digital twin;

[0153] 3) Effectively integrate and intelligently analyze the operating data in the digital twin to provide a data interface for the application layer.

[0154] See also Figure 4 , the present invention also provides a substation equipment operating status monitoring device based on digital twin, including a memory and a processor;

[0155] The memory is configured to store computer program code and transmit the computer program code to the processor;

[0156] The processor is used to execute a method for monitoring the operating status of substation equipment based on digital twins according to instructions in the computer program code.

[0157] The present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, a method for monitoring the operating status of substation equipment based on digital twins is implemented.

[0158] Generally speaking, computer instructions for implementing the method of the present invention may be carried by any combination of one or more computer-readable storage media. Non-transitory computer-readable storage media may include any computer-readable media except for signals that are temporarily propagating.

[0159] Computer-readable storage media can be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or components, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EKROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device or device.

[0160] Computer program code for performing the operations of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages, in particular Python suitable for neural network computing and platform frameworks based on TensorFlow, PyTorch, etc. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or to an external computer (e.g., via the Internet using an Internet service provider).

[0161] The above-mentioned devices and non-temporary computer-readable storage media can be found in the detailed description of a method for monitoring the operating status of substation equipment based on digital twins and its beneficial effects, which will not be repeated here.

[0162] Although the embodiments of the present invention have been shown and described above, it should be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. A person skilled in the art may change, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. A method for monitoring the operating status of substation equipment based on digital twins, characterized in that: include: Obtain substation detection data, analyze the substation detection data, and filter out characteristic data; First, a 3D digital model of the substation is established based on the actual physical objects and 3D geometric data of the substation. At the same time, a feature database of the substation is constructed. Then, based on the operating status and real-time parameters of the substation, feature matching is performed on the 3D digital model to form a digital twin of the substation. The operating data in the digital twin of the substation is then analyzed to output fault feature data. Conduct fault analysis on substation equipment based on fault characteristic data; The analysis of substation detection data to screen out characteristic data includes: Normalize the substation detection data to obtain the data matrix ; According to the data matrix , establish the following objective loss function: ； Where, is the target loss function; Represents the data matrix The mapping matrix in the feature space; Calculate the data matrix The covariance matrix of : ； Where, is the data matrix the number of Minimize the objective loss function , and based on the Lagrange multiplier method, the following Lagrange function is established: ； Where, is the penalty factor; Find the extreme value of the Lagrangian function to obtain the penalty factor , and use the following formula to find the mapping matrix : ； Mapping Matrix Perform eigenvector principal component screening to obtain the mapping matrix The principal components of Multiple mapping matrices The principal components of the network are convolutionally calculated, and maximum pooling and full splicing operations are performed to obtain feature data.

2. A method for monitoring substation equipment operating status based on digital twins according to claim 1, characterized in that: The mapping matrix Perform eigenvector principal component screening to obtain the mapping matrix The main components include: The mapping matrix Perform the following transformation to obtain new variables: ； Where, is a new variable, is the mapping matrix, ; is an algebraic relation matrix; Create the following new variable matrix: ； The matrix Perform diagonalization and find the characteristic roots; According to the characteristic roots, the characteristic vectors are arranged into a matrix from top to bottom according to the size of the corresponding characteristic roots. Rows form a new matrix , the new matrix As a mapping matrix The main component of .

3. A method for monitoring substation equipment operating status based on digital twins according to claim 2, characterized in that: The feature matching of the 3D digital model to form a substation digital twin includes: Calculate the expected target value: ； Where, is the expected target value; The collected electrical data of the substation; Number the electrical data of the substation; Calculate the difference characteristics of the twin output data: ； Where, is the data difference characteristic value; Represents the new matrix Target value of Calculate the error function: ； Where, For quantity; The expected target value Continuously iterate the difference characteristics with the output data until the error function is within a reasonable range; The expected target value after iteration is used as the data of the 3D digital model to form a digital twin of the substation.

4. A method for monitoring substation equipment operating status based on digital twins according to claim 1, characterized in that: The fault analysis of substation equipment according to the fault characteristic data includes: The substation historical data is mapped to the fault type one by one. The mapping function used is as follows: ； Where, For the Device status parameters; is the number of parameters; Mapping of substation status to fault type; is the fault type; Use the following formula to classify fault information: ； Where, From the original space to dimensional feature space mapping; and are the input and weight vectors respectively; is the regularization constant; is the slack variable; is the hyperplane threshold; Use group search method to update and iterate the classification; When the error accuracy is reached, the iteration is stopped and the fault diagnosis type is output.

5. A method for monitoring substation equipment operating status based on digital twins according to claim 4, characterized in that: The method further includes fault diagnosis: According to the fault diagnosis type, the fault information is classified and coded according to the voltage, current and temperature fault types; Set failure criteria and thresholds for all failures; Establish a fault tree based on fault standards and thresholds, fault characteristic information, and fault diagnosis type, and encode the fault tree address; The substation equipment operation data is implanted into the fault tree, and query and analysis are performed to obtain fault diagnosis information.

6. A method for monitoring substation equipment operating status based on digital twins according to claim 4, characterized in that: The method further includes determining the cause of the fault: Use the following formula to filter the fault information. , it indicates that the fault information is valid. If , then the fault information is considered as noise and should be discarded; ； ； Where, It is the benchmark for fault information evaluation; Indicates recent The degree of discretization of points; is the local density of the sample; The fault information number; express Distance to the origin; Encode and reduce the dimension of the filtered fault information; Encode the processed fault information in the fault tree and traverse and compare; The fault type is obtained through the optimization algorithm, and the fault cause is given through the fault tree.

7. A substation equipment operation status monitoring system based on digital twins, characterized in that: The system is applied to the method according to any one of claims 1 to 6, and the system comprises: The characteristic data acquisition module is used to obtain substation detection data, analyze the substation detection data, and filter out characteristic data; The substation digital twin generation module is used to first establish a 3D digital model of the substation based on the substation's physical scene and 3D geometric data, and simultaneously build a substation feature database. It then performs feature matching on the 3D digital model based on the substation's operating status and real-time parameters to form the substation digital twin. It then analyzes the operating data in the substation digital twin and outputs fault feature data. The substation fault analysis module is used to perform fault analysis on substation equipment based on fault characteristic data.

8. A substation equipment operating status monitoring device based on digital twin, characterized in that: including memory and processor; The memory is configured to store computer program code and transmit the computer program code to the processor; The processor is configured to execute the method according to any one of claims 1 to 6 according to instructions in the computer program code.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images