A high-voltage switch cabinet load dynamic analysis method, device, medium and product

Abstract

The application relates to a high-voltage switch cabinet load dynamic analysis method, equipment, medium and product, the method comprises the following steps: acquiring basic configuration parameters and historical operation data of a high-voltage switch cabinet; calculating a load theoretical value through the basic configuration parameters and the historical operation data of the high-voltage switch cabinet; constructing a load analysis model according to the type of the high-voltage switch cabinet and the load theoretical value; acquiring real-time operation data of the high-voltage switch cabinet; predicting the real-time operation data through the load analysis model to obtain a predicted load; and formulating a control strategy of the high-voltage switch cabinet through the predicted load. The application can understand the load state of the high-voltage switch cabinet, reduce premature or unnecessary power-off tests and maintenance, and achieve maintenance when necessary, thereby significantly improving the reliability and economy of a power system, reducing the calculation complexity, avoiding the time delay effect, and improving the load monitoring precision.

Description

Technical Field

[0001] This invention relates to the field of high-voltage switchgear monitoring technology, and in particular to a method, equipment, medium, and product for dynamic load analysis of high-voltage switchgear. Background Technology

[0002] In the processes of power generation, transmission, distribution, and energy conversion in a power supply system, high-voltage switchgear plays a crucial role in the switching, control, and protection of power lines. Existing switchgear load index prediction devices can monitor switchgear loads, but they require monitoring multiple operational data points such as current, voltage, power, and temperature as prior knowledge. A load state prediction model is then established based on this prior knowledge. Because the switchgear itself, the controlled objects within the switchgear, and the power grid comprising the switchgear all possess complex, uncertain, and fuzzy physical processes, multiple operational data points change in real time. This necessitates real-time operation of the prediction model to meet prediction requirements. Furthermore, the large number of control nodes in the switchgear necessitates real-time cyclic prediction of all control nodes, which would generate enormous computational pressure. Additionally, cyclic prediction introduces delays in control node prediction, resulting in low prediction accuracy. Summary of the Invention

[0003] To achieve the above-mentioned objectives and other advantages of the present invention, a first objective of the present invention is to provide a method for dynamic load analysis of high-voltage switchgear, comprising the following steps:

[0004] Obtain the basic configuration parameters and historical operating data of the high-voltage switchgear;

[0005] The theoretical load value is calculated based on the basic configuration parameters and historical operating data of the high-voltage switchgear.

[0006] A load analysis model is constructed based on the type of high-voltage switchgear and theoretical load values.

[0007] Obtain real-time operating data of the high-voltage switchgear;

[0008] The predicted load is obtained by using a load analysis model to predict real-time operating data.

[0009] Control strategies for high-voltage switchgear are developed by predicting load.

[0010] Furthermore, the basic configuration parameters of the high-voltage switchgear include rated voltage, rated insulation level, rated frequency, rated current, rated short-circuit breaking current, 4S thermal stability current, rated dynamic stability current, and protection level.

[0011] Furthermore, the historical operating data of the high-voltage switchgear includes the voltage value, load current value, operating time, temperature value, humidity value, and wind speed value during the operation of the high-voltage switchgear.

[0012] Furthermore, the calculation of the theoretical load value using the basic configuration parameters and historical operating data of the high-voltage switchgear includes the following steps:

[0013] The load calculation formula is selected based on the type of high-voltage switchgear; wherein, the types of high-voltage switchgear include metal-enclosed bay switchgear, metal-enclosed armored switchgear, and metal-enclosed box switchgear.

[0014] The theoretical load value is calculated by using the selected load theory calculation formula, combined with the basic configuration parameters and historical operating data; wherein the theoretical load value includes normal load component, meteorological sensitive load component, special event load component, and random load component.

[0015] Furthermore, the construction of the load analysis model based on the type of high-voltage switchgear and the theoretical load value includes the following steps:

[0016] The factors influencing the load of high-voltage switchgear are extracted from the types of high-voltage switchgear, normal load components, weather-sensitive load components, special event load components, and random load components.

[0017] The SVM model was trained under supervision by extracting influencing factors, and the SVM model with the highest prediction accuracy was selected.

[0018] The trained SVM model is used to make preliminary predictions on the test data, and the predicted loads are output respectively.

[0019] Furthermore, the construction of the load analysis model based on the type of high-voltage switchgear and the theoretical load value also includes the following steps:

[0020] Constructing the state transition and emission probability representation of a Hidden Markov Model using supervised learning classification methods;

[0021] The initial state probability, state transition matrix, and emission probability matrix of the Hidden Markov Model are calculated based on the load prediction results.

[0022] By fitting a Gaussian mixture model with predicted probabilities, the conversion between multidimensional continuous probability vectors and emission probabilities is realized, and the state transition matrix is ​​obtained through the Baum-Welch algorithm.

[0023] The state transition parameters of the Hidden Markov Model are corrected.

[0024] Furthermore, the process of formulating a control strategy for the high-voltage switchgear by predicting the load includes the following steps:

[0025] When the predicted load exceeds the preset load value, reduce the voltage drop of the transmission and distribution lines;

[0026] Connect a series compensation capacitor in the circuit to reduce inductive reactance;

[0027] When the compensation capacitor is connected to the power transmission system, the synchronous motor generates negative braking.

[0028] A second objective of the present invention is to provide an electronic device comprising: a memory having program code stored thereon; and a processor connected to the memory, wherein when the program code is executed by the processor, a method for dynamic load analysis of a high-voltage switchgear is implemented.

[0029] A third objective of this invention is to provide a computer-readable storage medium having program instructions stored thereon, which, when executed, implement a method for dynamic load analysis of a high-voltage switchgear.

[0030] The fourth objective of this invention is to provide a computer program product, including a computer program / instruction, which, when executed by a processor, implements a method for dynamic load analysis of high-voltage switchgear.

[0031] Compared with the prior art, the beneficial effects of the present invention are:

[0032] This invention provides a method, equipment, medium, and product for dynamic load analysis of high-voltage switchgear, which can understand the load status of high-voltage switchgear, reduce premature or unnecessary power outages for testing and maintenance, ensure that maintenance is carried out only when necessary, significantly improve the reliability and economy of the power system, reduce computational complexity while avoiding delay effects, and improve load monitoring accuracy.

[0033] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it according to the contents of the specification, the preferred embodiments of the present invention are described in detail below with reference to the accompanying drawings. Specific embodiments of the present invention are given in detail below with reference to the accompanying drawings. Attached Figure Description

[0034] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0035] Figure 1 Here is a flowchart of a dynamic load analysis method for high-voltage switchgear, as described in Example 1.

[0036] Figure 2 This is a schematic diagram of the electronic device in Example 2;

[0037] Figure 3 This is a schematic diagram of a computer-readable storage medium according to Example 3. Detailed Implementation

[0038] The present invention will now be further described in conjunction with the accompanying drawings and specific embodiments. It should be noted that, without conflict, the various embodiments or technical features described below can be arbitrarily combined to form new embodiments.

[0039] Example 1

[0040] A method for dynamic load analysis of high-voltage switchgear, such as Figure 1 As shown, it includes the following steps:

[0041] Obtain the basic configuration parameters and historical operating data of the high-voltage switchgear; among which, the basic configuration parameters of the high-voltage switchgear include rated voltage, rated insulation level, rated frequency, rated current, rated short-circuit breaking current, 4S thermal stability current, rated dynamic stability current and protection level.

[0042] Historical operating data of high-voltage switchgear includes voltage, load current, operating time, temperature, humidity, and wind speed during operation.

[0043] The theoretical load value is calculated using the basic configuration parameters and historical operating data of the high-voltage switchgear; this specifically includes the following steps:

[0044] The load calculation formula is selected based on the type of high-voltage switchgear; the types of high-voltage switchgear include metal-enclosed bay switchgear, metal-enclosed armored switchgear, and metal-enclosed box switchgear.

[0045] The main electrical components of a metal-enclosed switchgear are housed in separate compartments, but it has one or more non-metallic partitions that meet a certain protection level. For example, the JYN2-12 type high-voltage switchgear.

[0046] Metal-enclosed armored switchgear mainly consists of circuit breakers, instrument transformers, busbars, etc., which are installed in metal-enclosed switchgear in grounded compartments separated by metal partitions. An example is the KYN28A-12 type high-voltage switchgear.

[0047] Metal-enclosed box-type switchgear is a switchgear whose enclosure is metal-enclosed. For example, the XGN2-12 type high-voltage switchgear.

[0048] The theoretical load value is calculated by using the selected load theory calculation formula, combined with basic configuration parameters and historical operating data; the theoretical load value includes normal load component, meteorological sensitive load component, special event load component, and random load component.

[0049] The normal load component is independent of weather and temperature, and exhibits different patterns of variation for different forecast periods;

[0050] Meteorologically sensitive load components are closely related to meteorological factors such as temperature, humidity, wind force, and sunshine / cloudiness.

[0051] The load component of special events is affected by special times, and the load forecast can be corrected according to different time periods based on historical experience;

[0052] Random load components are affected by location uncertainties; different system structures and loads result in different random load components.

[0053] A load analysis model is constructed based on the type of high-voltage switchgear and theoretical load values; specifically, the following steps are included:

[0054] The factors influencing the load of high-voltage switchgear are extracted from the types of high-voltage switchgear, normal load components, weather-sensitive load components, special event load components, and random load components.

[0055] The SVM model was trained under supervision by extracting influencing factors, and the SVM model with the highest prediction accuracy was selected.

[0056] The trained SVM model is used to make preliminary predictions on the test data, and the predicted loads are output respectively.

[0057] Because of its excellent nonlinear data processing capabilities, the SVM algorithm can be used for load forecasting. The SVM model converges quickly and does not suffer from issues related to network layer count or local optima.

[0058] To improve the global search capability of the SVM model, a Hidden Markov Model (HMM) is employed. This involves the following steps:

[0059] Constructing the state transition and emission probability representation of a Hidden Markov Model using supervised learning classification methods;

[0060] The initial state probability, state transition matrix, and emission probability matrix of the Hidden Markov Model are calculated based on the load prediction results.

[0061] By fitting a Gaussian mixture model with predicted probabilities, the conversion between multidimensional continuous probability vectors and emission probabilities is realized, and the state transition matrix is ​​obtained through the Baum-Welch algorithm.

[0062] The state transition parameters of the Hidden Markov Model are corrected.

[0063] Obtain real-time operating data of the high-voltage switchgear;

[0064] The predicted load is obtained by using a load analysis model to predict real-time operating data.

[0065] Control strategies for high-voltage switchgear are developed based on load forecasting. Specifically, the following steps are included:

[0066] When the predicted load exceeds the preset load value, reduce the voltage drop of the transmission and distribution lines;

[0067] Connect a series compensation capacitor in the circuit to reduce inductive reactance;

[0068] When the compensation capacitor is connected to the power transmission system, the synchronous motor generates negative braking.

[0069] Example 2

[0070] An electronic device, such as Figure 2 As shown, it includes: a memory storing program code; and a processor connected to the memory, which, when the program code is executed by the processor, implements a method for dynamic load analysis of a high-voltage switchgear.

[0071] Example 3

[0072] A computer-readable storage medium, such as Figure 3 As shown, it stores program instructions, which, when executed, implement a method for dynamic load analysis of high-voltage switchgear. For a detailed description of the method, please refer to the corresponding description in the above method embodiments; it will not be repeated here.

[0073] Example 4

[0074] A computer program product includes a computer program / instructions that, when executed by a processor, implement a method for dynamic load analysis of a high-voltage switchgear. A detailed description of the method can be found in the corresponding description in the above method embodiments, and will not be repeated here.

[0075] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0076] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

[0077] The above are merely embodiments of this specification and are not intended to limit the scope of one or more embodiments of this specification. Various modifications and variations can be made to one or more embodiments of this specification by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of one or more embodiments of this specification should be included within the scope of the claims of one or more embodiments of this specification.

Claims

1. A method for dynamic load analysis of high-voltage switchgear, characterized in that, Includes the following steps: Obtain the basic configuration parameters and historical operating data of the high-voltage switchgear; The theoretical load value is calculated based on the basic configuration parameters and historical operating data of the high-voltage switchgear. A load analysis model is constructed based on the type of high-voltage switchgear and theoretical load values. Obtain real-time operating data of the high-voltage switchgear; The predicted load is obtained by using a load analysis model to predict real-time operating data. Develop control strategies for high-voltage switchgear by predicting load; The calculation of the theoretical load value based on the basic configuration parameters and historical operating data of the high-voltage switchgear includes the following steps: The load calculation formula is selected based on the type of high-voltage switchgear; wherein, the types of high-voltage switchgear include metal-enclosed bay switchgear, metal-enclosed armored switchgear, and metal-enclosed box switchgear. The theoretical load value is calculated by using the selected load theory calculation formula, combined with the basic configuration parameters and historical operating data; wherein, the theoretical load value includes normal load component, meteorological sensitive load component, special event load component, and random load component; The process of constructing a load analysis model based on the type of high-voltage switchgear and theoretical load values ​​includes the following steps: The factors influencing the load of high-voltage switchgear are extracted from the types of high-voltage switchgear, normal load components, weather-sensitive load components, special event load components, and random load components. The SVM model was trained under supervision by extracting influencing factors, and the SVM model with the highest prediction accuracy was selected. The trained SVM model is used to make preliminary predictions on the test data, and the predicted loads are output respectively. The process of constructing a load analysis model based on the type of high-voltage switchgear and theoretical load values ​​also includes the following steps: Constructing the state transition and emission probability representation of a Hidden Markov Model using supervised learning classification methods; The initial state probability, state transition matrix, and emission probability matrix of the Hidden Markov Model are calculated based on the load prediction results. By fitting a Gaussian mixture model with predicted probabilities, the conversion between multidimensional continuous probability vectors and emission probabilities is realized, and the state transition matrix is ​​obtained through the Baum-Welch algorithm. The state transition parameters of the Hidden Markov Model are corrected.

2. The method for dynamic load analysis of high-voltage switchgear according to claim 1, characterized in that: The basic configuration parameters of the high-voltage switchgear include rated voltage, rated insulation level, rated frequency, rated current, rated short-circuit breaking current, 4S thermal stability current, rated dynamic stability current, and protection level.

3. The method for dynamic load analysis of high-voltage switchgear according to claim 2, characterized in that: The historical operating data of the high-voltage switchgear includes voltage, load current, operating time, temperature, humidity, and wind speed during operation.

4. The method for dynamic load analysis of high-voltage switchgear according to claim 1, characterized in that, The process of developing a control strategy for high-voltage switchgear based on load prediction includes the following steps: When the predicted load exceeds the preset load value, reduce the voltage drop of the transmission and distribution lines; Connect a series compensation capacitor in the circuit to reduce inductive reactance; When the compensation capacitor is connected to the power transmission system, the synchronous motor generates negative braking.

5. An electronic device, characterized in that, include: A memory that stores program code; A processor, which is connected to the memory, and which, when the program code is executed by the processor, implements the method as described in any one of claims 1 to 4.

6. A computer-readable storage medium, characterized in that, It stores program instructions that, when executed, implement the method as described in any one of claims 1 to 4.

7. A computer program product comprising a computer program / instructions, characterized in that, When the computer program / instruction is executed by the processor, it implements the method as described in any one of claims 1 to 4.

Images