A high and low voltage switch equipment control method and system

Abstract

The present invention discloses a control method and system for high and low voltage switchgear, which relates to the technical field of power equipment state control. It includes collecting the state data of high and low voltage switchgear, generating a state variable matrix, calculating the normalized time change rate, calculating the relative entropy variation between state variables using KL divergence, correcting the normalized time change rate, constructing a normalized state change rate matrix, calculating the geodesic distance between state variables using Fisher information metric, and constructing an embedding coordinate; calculating the generalized Laplacian operator of the embedding coordinate, combining with the gauge field theory, calculating the change rate of the embedding coordinate, monitoring the state of the switchgear and making adjustments; constructing the embedding coordinate through Fisher-Rao metric and multi-dimensional scaling analysis to improve the depth of state analysis and the comprehensiveness of state monitoring, combining with the gauge field theory, calculating the change rate of the embedding coordinate, and enhancing the sensitivity and noise resistance of anomaly detection.

Description

Technical Field

[0001] The present invention relates to the technical field of power equipment state control, and particularly to a control method and system for high and low voltage switchgear. Background Art

[0002] As an important part of the power system, the main function of high and low voltage switchgear is to control the on-off of current to ensure the safe and stable operation of the power system. With the development of power industry technology, especially the emergence of smart grid, the requirements for the intelligence, precision and automation of switchgear are gradually increasing. Modern high and low voltage switchgear not only needs to have the basic switch function, but also needs to monitor the equipment state in real time, and predict the health state and operation performance of the equipment through data analysis to ensure the efficient operation of the power system and reduce the probability of faults.

[0003] There are still some key deficiencies in the existing technologies. Most traditional equipment monitoring systems rely on regular manual inspections and experience judgments, which are difficult to achieve real-time dynamic monitoring and fault prediction, and have poor adaptability to the state changes of equipment and external environments. Most existing equipment state monitoring methods use simple threshold judgments or basic statistical analyses, lacking in-depth dynamic modeling and efficient intelligent decision-making capabilities, and often unable to accurately reflect the actual state and potential faults of equipment. Summary of the Invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a control method and system for high and low voltage switchgear, which solves the problems that most existing equipment state monitoring methods use simple threshold judgments or basic statistical analyses, lack in-depth dynamic modeling and efficient intelligent decision-making capabilities, and often cannot accurately reflect the actual state and potential faults of equipment.

[0006] To solve the above technical problems, the present invention provides the following technical solutions:

[0007] In the first aspect, the present invention provides a control method for high and low voltage switchgear, which includes

[0008] collecting the state data of high and low voltage switchgear, generating a state variable matrix, calculating the normalized time change rate, calculating the relative entropy variation between state variables using KL divergence, correcting the normalized time change rate, constructing a normalized state change rate matrix, calculating the geodesic distance between state variables using Fisher information metric, and constructing an embedding coordinate;

[0009] calculating the generalized Laplacian operator of the embedding coordinate, combining with the gauge field theory, calculating the change rate of the embedding coordinate, monitoring the state of the switchgear and making adjustments;

[0010] Build a visualization interface to display the monitoring results and store the status data generated by collection, analysis.

[0011] As a preferred solution of the high and low voltage switchgear control method described in the present invention, wherein: the collecting of the status data of the high and low voltage switchgear and constructing the embedded coordinates includes:

[0012] Collect the status data of the high and low voltage switchgear through intelligent sensors, and the intelligent sensors include current, voltage, power, temperature, electromagnetic field strength, laser displacement and contact resistance sensors;

[0013] The status data includes current, voltage, load power, temperature, electromagnetic interference intensity, switch contact gap, contact resistance and corresponding time interval data;

[0014] Use the maximum information entropy criterion to set the time window, use the time window as the number of rows of the state variable matrix, sort the preprocessed status data in chronological order to generate the state variable matrix;

[0015] Use the steady-state probability distribution method to set the reference state value and calculate the normalized time change rate;

[0016] Use the KL divergence to calculate the relative entropy variation between state variables, and use the exponential decay function to correct the normalized time change rate;

[0017] For the corrected normalized time change rate, use the matrix scaling transformation method to construct the normalized state change rate matrix;

[0018] Extract the elements in the normalized state change rate matrix, use the Shannon entropy formula to calculate the Shannon entropy, and use the law of conservation of energy to calculate the equivalent temperature;

[0019] Use the reciprocal of the Boltzmann constant to calculate the reciprocal temperature parameter;

[0020] Use the Boltzmann factor to calculate the generalized partition function ;

[0021] Use the maximum entropy probability distribution to calculate the normalized probability, use the Fisher-Rao metric to calculate the diagonal elements of the Fisher information metric matrix, and construct the Fisher information metric matrix;

[0022] Use the Fisher information metric to calculate the geodesic distance between state variables, construct the geodesic distance matrix, and use the multi-dimensional scaling analysis method to construct the embedded coordinates.

[0023] As a preferred embodiment of the control method for high and low voltage switchgear of the present invention, wherein: calculating the generalized Laplace operator of the embedding coordinates, and combining with the gauge field theory to calculate the change rate of the embedding coordinates, including:

[0024] Using the central difference method to calculate the time derivative of the embedding coordinates;

[0025] Constructing the gauge field connection of the state variables based on the diagonal elements of the Fisher information metric matrix and performing normalization processing;

[0026] Using the covariant derivative to calculate the curvature tensor of the gauge field and performing normalization processing;

[0027] Using LU decomposition to calculate the determinant of the Fisher information metric matrix, using Cholesky decomposition to calculate the inverse matrix of the Fisher information metric matrix, and using the finite difference method to calculate the partial derivative of the embedding coordinates;

[0028] Using the Laplace - Beltrami operator to calculate the generalized Laplace operator of the embedding coordinates;

[0029] Combining with the gauge field theory to calculate the change rate of the embedding coordinates.

[0030] As a preferred embodiment of the control method for high and low voltage switchgear of the present invention, wherein: monitoring the state of the switchgear and making adjustments, including:

[0031] Using statistical analysis method to set the state threshold, comparing the change rate with the state threshold, when the change rate is less than the state threshold, it is judged as the normal state and continue to monitor;

[0032] When the change rate is greater than or equal to the state threshold, it is judged as the abnormal state;

[0033] Using the variational method to calculate the gradient of the normalized gauge field connection and making adjustments in combination with the diagonal elements of the Fisher information metric matrix;

[0034] Calculating the difference between the change rate and the state threshold, which is defined as the control error term;

[0035] Using the empirical rule to set the adjustment coefficient and calculate the control offset;

[0036] Using the forward update method to calculate the optimal control input and execute it;

[0037] Calculating the change rate of the optimal control input embedding coordinates and monitoring, and stopping the adjustment when the change rate is less than the state threshold.

[0038] As a preferred embodiment of the control method for high and low voltage switchgear of the present invention, wherein: after collecting the state data, first perform pre - processing operations.

[0039] As a preferred solution of the control method for high - and low - voltage switchgear according to the present invention, wherein: constructing a visual interface to display the monitoring results includes:

[0040] Using the front - end framework React.js to construct a visual interface, including a main chart area and a top information bar;

[0041] Displaying the monitoring results in the main chart area and displaying the change rate of the embedded coordinates in the top information bar;

[0042] Allowing users who have passed real - name verification to view.

[0043] As a preferred solution of the control method for high - and low - voltage switchgear according to the present invention, wherein: storing the status data generated by collection and analysis includes:

[0044] Storing the collected status data and the generated monitoring results in a central database, and setting security access measures. The central database backs up the stored data to the cloud, and regularly performs integrity detection on the stored data and the backup data. After the detection is completed, an integrity detection record is generated and synchronously stored in the central database.

[0045] In a second aspect, the present invention provides a control method for high - and low - voltage switchgear, including,

[0046] A collection module, configured to collect the status data of the high - and low - voltage switchgear, generate a status variable matrix, calculate the normalized time change rate, calculate the relative entropy variation between the status variables using KL divergence, correct the normalized time change rate, construct a normalized status change rate matrix, calculate the geodesic distance between the status variables using Fisher information metric, and construct embedded coordinates;

[0047] A calculation and monitoring module, configured to calculate the generalized Laplacian operator of the embedded coordinates, combine the gauge field theory, calculate the change rate of the embedded coordinates, monitor the status of the switchgear and make adjustments;

[0048] A visualization and storage module, configured to construct a visual interface to display the monitoring results and store the status data generated by collection and analysis.

[0049] In a third aspect, the present invention provides a computer device, including a memory and a processor, where the memory stores a computer program, and wherein: when the computer program is executed by the processor, any step of the control method for high - and low - voltage switchgear as described in the first aspect of the present invention is implemented.

[0050] Fourthly, the present invention provides a computer-readable storage medium, on which a computer program is stored, wherein: when the computer program is executed by a processor, any step of the high- and low-voltage switchgear control method described in the first aspect of the present invention is implemented.

[0051] The beneficial effects of the present invention are as follows: By collecting the state data of high- and low-voltage switchgear, generating a state variable matrix, calculating the normalized time change rate, using the KL divergence to calculate the relative entropy variation between state variables, correcting the normalized time change rate, constructing a normalized state change rate matrix, using the Fisher information metric to calculate the geodesic distance between state variables, and constructing the embedding coordinates; calculating the generalized Laplacian operator of the embedding coordinates, combining with the gauge field theory, calculating the change rate of the embedding coordinates, monitoring the state of the switchgear and making adjustments; solving the problems of low sensitivity in anomaly detection, weak ability to capture non-linear features, and insufficient characterization of the state evolution mechanism in the traditional technology, improving the depth of state analysis and the comprehensiveness of state monitoring, and enhancing the sensitivity and anti-noise ability of anomaly detection. Description of the Drawings

[0052] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0053] Figure 1 It is a flowchart of the high- and low-voltage switchgear control method in Embodiment 1.

[0054] Figure 2 It is a structural diagram of the high- and low-voltage switchgear control system in Embodiment 1.

[0055] Figure 3 It is a flowchart of constructing the embedding coordinates in Embodiment 1.

[0056] Figure 4 It is a flowchart of monitoring the state of the switchgear and making adjustments in Embodiment 1. Detailed Embodiments

[0057] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following detailed description of the specific embodiments of the present invention will be made in conjunction with the drawings in the specification.

[0058] Many specific details are set forth in the following description to facilitate a thorough understanding of the present invention. However, the present invention can also be implemented in other ways different from those described herein. Those skilled in the art can make similar extensions without departing from the spirit of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0059] Secondly, the so-called "one embodiment" or "embodiment" herein refers to a specific feature, structure or characteristic that may be included in at least one implementation manner of the present invention. The appearances of "in one embodiment" in different places in this specification do not all refer to the same embodiment, nor are they separate or alternative embodiments that exclude each other with other embodiments.

[0060] Embodiment 1, referring to Figures 1 to 4 , is the first embodiment of the present invention. This embodiment provides a control method for high and low voltage switchgear, including the following steps:

[0061] S1. Collect the status data of the high and low voltage switchgear, generate a status variable matrix, calculate the normalized time change rate, calculate the relative entropy variation between the status variables using KL divergence, correct the normalized time change rate, construct a normalized status change rate matrix, calculate the geodesic distance between the status variables using Fisher information metric, and construct the embedding coordinates;

[0062] Specifically, collecting the status data of the high and low voltage switchgear and constructing the embedding coordinates includes:

[0063] Collect the status data of the high and low voltage switchgear through intelligent sensors. The intelligent sensors include current, voltage, power, temperature, electromagnetic field strength, laser displacement, and contact resistance sensors;

[0064] The status data includes current, voltage, load power, temperature, electromagnetic interference intensity, switch contact gap, contact resistance, and corresponding time interval data;

[0065] Preprocess the status data, including time synchronization, smoothing the status data using the Kalman filter algorithm, removing the noise introduced by sensor errors or external factors, identifying and deleting abnormal data using the Z-Score method, supplementing missing data using the spline interpolation algorithm, and normalizing the status data;

[0066] Set the time window using the maximum information entropy criterion. Take the time window as the number of rows of the status variable matrix, sort the preprocessed status data in chronological order, and generate the status variable matrix;

[0067] Set the reference status value using the steady-state probability distribution method, and calculate the normalized time change rate. The formula is:

[0068] ,

[0069] where is the normalized time change rate of the jth status variable at the ith time point, is the value of the j-th state variable at the i-th time point, representing the state data at the preprocessed time point, is the reference state value, is the time interval between adjacent state variables, calculating the average change rate of all normalized time change rates;

[0070] Using the KL divergence to calculate the relative entropy variation between state variables, and using the exponential decay function to correct the normalized time change rate, the formula is:

[0071] ,

[0072] where is the normalized time change rate of the j-th state variable at the i-th time point after correction, is the relative entropy variation between the j-th state variable and the average change rate, is the normalized time change rate of the j-th state variable, is the average change rate of the j-th state variable;

[0073] For the corrected normalized time change rate, use the matrix scaling transformation method to construct the normalized state change rate matrix;

[0074] Extract the elements in the normalized state change rate matrix, use the Shannon entropy formula to calculate the Shannon entropy, and use the law of conservation of energy to calculate the equivalent temperature, the formula is:

[0075] ,

[0076] where is the equivalent temperature, T is the temperature, P is the load power, and C is the specific heat capacity of the device;

[0077] Use the reciprocal of the Boltzmann constant to calculate the reciprocal temperature parameter, the formula is:

[0078] ,

[0079] where is the reciprocal temperature parameter, is the Boltzmann constant;

[0080] Use the Boltzmann factor to calculate the generalized partition function , the formula is:

[0081] ,

[0082] where N is the number of state variables, is the reciprocal temperature parameter of the i-th device, is the Shannon entropy of the i-th state variable;

[0083] The normalized probability is calculated using the maximum entropy probability distribution, and the diagonal elements of the Fisher information metric matrix are calculated using the Fisher-Rao metric. The Fisher information metric matrix is constructed with the formula:

[0084] ,

[0085] where is the diagonal element of the Fisher information metric matrix, corresponding to the local information metric of the k-th state variable, is the normalized probability of the k-th state variable, is the change increment of the k-th state variable in the normalized state change rate matrix, is the logarithm of the generalized partition function, used to calculate the second-order change rate of the state variable, is the change increment of the logarithm of the generalized partition function with respect to the k-th state variable and is the second-order partial derivative;

[0086] The geodesic distance between state variables is calculated using the Fisher information metric, the geodesic distance matrix is constructed, and the embedding coordinates are constructed using the multidimensional scaling analysis method.

[0087] Traditional rate-of-change analysis directly uses raw values or simple filtering without dynamically correcting for distribution differences. It quantifies the deviation between the state variable and the average rate of change through KL divergence and then adjusts it in an exponentially decaying form so that the rate of change reflects the balance between local anomalies and global trends. The corrected rate of change not only retains the temporal dynamics but also eliminates the influence of noise through entropy variation, improving the sensitivity of anomaly detection in multi-variable complex scenarios (such as a sharp increase in electromagnetic interference). The combination of KL divergence and exponential decay cross-domain integrates information theory and signal processing and has not been widely applied to the rate-of-change correction in equipment condition monitoring. Traditional condition monitoring only uses physical temperature and does not combine load power and entropy as an equivalent index. By introducing load power and Shannon entropy into equivalent temperature through energy conservation, a thermodynamic analogy is constructed to reflect the "information thermal state" of equipment operation. The equivalent temperature combines physical parameters (temperature, power) and information parameters (entropy), providing a multi-dimensional characterization of the equipment state. Compared with single-temperature monitoring, it can provide earlier warnings of anomalies (such as potential faults with increased contact resistance). Traditional equipment monitoring does not use the generalized partition function for state distribution modeling, and Fisher information is mostly used for parameter optimization rather than state space analysis. By transforming Shannon entropy into probability weights through the Boltzmann factor and combining Fisher information metric calculations of the local information sensitivity of state variables, a geometric representation of the multi-dimensional state space is constructed. The Fisher information metric matrix reveals the non-linear dependencies between state variables (such as the coupling effect between current and contact resistance). Compared with traditional correlation analysis, it can capture complex fault patterns more accurately. Traditional state analysis mostly uses Euclidean distance or correlation coefficient and does not introduce the geodesic distance of information geometry. By calculating the geodesic distance between state variables through the Fisher information metric matrix and combining MDS embedding coordinates, the non-linear geometric relationship between variables is revealed. The geodesic distance reflects the intrinsic distribution curvature of state variables (such as the non-linear impact of voltage mutations on contact resistance), and it can capture the dynamic associations between multi-dimensional states more accurately than Euclidean distance;

[0088] In addition to traditional parameters such as the collected current, voltage, load power, and temperature, new parameters "electromagnetic interference intensity" and "switch contact gap" are added, significantly improving the comprehensiveness of condition monitoring. Compared with a fixed time window, the self-adaptability of the maximum information entropy criterion can dynamically capture key change points in the data, avoiding information loss or redundancy. KL divergence quantifies the relative entropy variation between state variables and combines with an exponential decay function to correct the rate of change, effectively filtering out noise interference and highlighting the significance of abnormal states. The combination of Fisher-Rao metric and geodesic distance captures the non-linear geometric characteristics between state variables, and through MDS mapping, the embedding coordinates are generated, significantly improving the accuracy and visualization effect of state representation.

[0089] S2. Calculate the generalized Laplacian operator of the embedding coordinates, combine with gauge field theory, calculate the change rate of the embedding coordinates, monitor the state of the switching equipment and make adjustments;

[0090] Specifically, calculate the generalized Laplacian of the embedding coordinates, and combine with the gauge field theory to calculate the change rate of the embedding coordinates, including:

[0091] Use the central difference method to calculate the time derivative of the embedding coordinates;

[0092] Construct the gauge field connection of the state variables based on the diagonal elements of the Fisher information metric matrix and perform normalization. The formula is:

[0093] ,

[0094] where is the gauge field connection of the k-th embedding coordinate, is the time derivative of the k-th embedding coordinate at time t, where is the diagonal element of the Fisher information metric matrix, corresponding to the local information metric of the k-th state variable;

[0095] Use the covariant derivative to calculate the curvature tensor of the gauge field and perform normalization;

[0096] Use LU decomposition to calculate the determinant of the Fisher information metric matrix, use Cholesky decomposition to calculate the inverse matrix of the Fisher information metric matrix, and use the finite difference method to calculate the partial derivative of the embedding coordinates;

[0097] Use the Laplace - Beltrami operator to calculate the generalized Laplacian of the embedding coordinates. The formula is:

[0098] ,

[0099] where is the generalized Laplacian of the k-th embedding coordinate, is the determinant of the Fisher information metric matrix, is the inverse matrix of the Fisher information metric matrix, characterizing the information metric relationship between different state variables, is the partial derivative of the k-th embedding coordinate with respect to the j-th embedding coordinate;

[0100] Combine with the gauge field theory to calculate the change rate of the embedding coordinates. The formula is:

[0101] ,

[0102] where is the change rate of the k-th embedding coordinate, is the normalized gauge field connection of the k-th embedding coordinate, is the curvature tensor of the normalized k-th and j-th gauge fields.

[0103] Traditional information geometry uses the Fisher metric to calculate geodesic distances or parameter sensitivities, and does not directly construct a gauge field connection. Gauge field theory is mostly applied to physical fields (such as electromagnetic fields) and is not widely used in embedded coordinate analysis. By taking the diagonal elements of the information metric as a normalization factor and combining it with the time derivative, a gauge field connection is constructed to achieve the geometric representation of the dynamic evolution of state variables. Traditional embedded coordinate analysis (such as MDS) only generates static coordinates and does not calculate dynamic rates; gauge field theory is not widely used for rate prediction in information geometry. By adding the normalized gauge field connection and the curvature tensor, a rate of change is constructed, which combines local dynamics (connection) and global geometry (curvature). The rate of change reflects both time evolution and coupling between variables, and can more accurately predict the dynamic evolution of the state space (such as the sudden change trend of device states) compared to simple derivatives;

[0104] The central difference method has higher accuracy compared to the one-sided difference, can effectively reduce truncation errors, and provides an accurate estimate of the embedded coordinates changing with time. LU decomposition efficiently calculates the determinant, and Cholesky decomposition ensures the numerical stability of the inverse matrix. The combination of the two significantly reduces the computational complexity of complex matrix operations.

[0105] Furthermore, monitoring and adjusting the state of the switching device includes:

[0106] Using statistical analysis methods to set state thresholds, comparing the rate of change with the state thresholds. When the rate of change is less than the state threshold, it is judged as the normal state and monitoring continues;

[0107] When the rate of change is greater than or equal to the state threshold, it is judged as the abnormal state;

[0108] Using the variational method to calculate the gradient of the normalized gauge field connection and making adjustments in combination with the diagonal elements of the Fisher information metric matrix. The formula is:

[0109] ,

[0110] where is the gradient of the k-th gauge field connection after adjustment, is the gradient of the k-th normalized gauge field connection;

[0111] Calculating the difference between the rate of change and the state threshold, which is defined as the control error term;

[0112] Using empirical rules to set the adjustment coefficient and calculating the control offset. The formula is:

[0113] ,

[0114] where is the k-th control offset, is the adjustment coefficient, is the k-th control error term;

[0115] Use the forward update method to calculate the optimal control input and execute it;

[0116] Calculate the change rate of the embedded coordinates of the optimal control input and monitor it. Stop adjusting when the change rate is less than the state threshold.

[0117] The statistical analysis method sets the state threshold in a data-driven manner, which is more adaptable than the fixed threshold and can dynamically reflect the changes in the device operating conditions. The anomaly judgment method based on the change rate makes full use of the dynamic trend information and goes beyond the limitations of traditional static parameter monitoring. The variational method combines the diagonal elements of the Fisher information metric matrix to accurately calculate the gradient of the gauge field connection, providing a dual basis of geometry and information theory for state adjustment. The control error term quantifies the degree of anomaly and provides a specific target for adjustment. The empirical rule introduces domain knowledge to balance the computational complexity and practicality. The forward update method ensures the dynamic adjustment of the control input with the change of the state through iterative optimization, which is more forward-looking than the traditional feedback control. By recalculating the change rate of the embedded coordinates, the adjustment effect is verified and the stop condition is set to form a closed-loop control mechanism.

[0118] S3. Build a visualization interface to display the monitoring results and store the state data generated by collection and analysis;

[0119] Specifically, build a visualization interface to display the monitoring results, including:

[0120] Use the front-end framework React.js to build a visualization interface, including the main chart area and the top information bar;

[0121] Display the monitoring results in the main chart area and display the change rate of the embedded coordinates in the top information bar;

[0122] Allow users who have passed real-name verification to view.

[0123] The component-based design and virtual DOM technology of React.js significantly improve the rendering efficiency and maintainability of the interface. Compared with traditional static HTML or basic JavaScript development, it can update complex monitoring data in real time without page reload. The main chart area converts complex multi-dimensional state data into intuitive visual information through graphical display (such as showing current changes with a line chart and reflecting temperature distribution with a scatter plot). Placing the change rate of the embedded coordinates in the top information bar provides a real-time dynamic key indicator, facilitating users to quickly grasp the evolution speed of the device state. The real-name verification mechanism ensures that only authorized users can access the monitoring data, significantly enhancing the security and data privacy protection capabilities of the system.

[0124] Further, store the status data generated by collection and analysis, including:

[0125] Store the collected status data and the monitoring results generated by analysis in a central database, and set security access measures. The central database will perform cloud backup on the stored data, and regularly perform integrity detection on the stored data and the backup data. After the detection is completed, an integrity detection record will be generated and synchronously stored in the central database.

[0126] Centralized storage of status data and monitoring results facilitates the efficient management and unified analysis of data. Security access measures effectively prevent unauthorized access or data leakage, ensuring the confidentiality and integrity of the switchgear status data. Cloud backup significantly improves the disaster resistance of data through off-site redundant storage. Regular integrity detection ensures that the data has not been tampered with or damaged, promptly discovers potential problems, generates and stores integrity detection records, forming a traceable audit chain, and enhancing the transparency and verifiability of data management.

[0127] This embodiment also provides a high and low voltage switchgear control system, including:

[0128] A collection and embedding module, used to collect the status data of the high and low voltage switchgear, generate a status variable matrix, calculate the normalized time change rate, calculate the relative entropy variation between status variables using KL divergence, correct the normalized time change rate, construct a normalized state change rate matrix, calculate the geodesic distance between status variables using Fisher information metric, and construct embedding coordinates;

[0129] A calculation and monitoring module, used to calculate the generalized Laplacian operator of the embedding coordinates, combine with gauge field theory, calculate the change rate of the embedding coordinates, monitor the status of the switchgear and make adjustments;

[0130] A visualization and storage module, used to construct a visualization interface to display the monitoring results and store the status data generated by collection and analysis.

[0131] This embodiment also provides a computer device, applicable to the case of the high and low voltage switchgear control method, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the high and low voltage switchgear control method proposed in the above embodiment.

[0132] The computer device may be a terminal, which includes a processor, a memory, a communication interface, a display screen, and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a carrier network, NFC (Near Field Communication), or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or may also be a button, a trackball, or a touchpad provided on the housing of the computer device, or may also be an external keyboard, a touchpad, or a mouse, etc.

[0133] This embodiment also provides a storage medium, on which a computer program is stored, and when the program is executed by a processor, it implements the method for controlling high-voltage and low-voltage switchgear as proposed in the above embodiment; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM for short), Electrically Erasable Programmable Read-Only Memory (EEPROM for short), Erasable Programmable Read Only Memory (EPROM for short), Programmable Read-Only Memory (PROM for short), Read-Only Memory (ROM for short), magnetic memory, flash memory, a magnetic disk, or an optical disc.

[0134] In summary, the present invention collects the state data of high-voltage and low-voltage switchgear, generates a state variable matrix, calculates the normalized time change rate, calculates the relative entropy variation between state variables using KL divergence, corrects the normalized time change rate, constructs a normalized state change rate matrix, calculates the geodesic distance between state variables using Fisher information metric, and constructs an embedding coordinate; calculates the generalized Laplacian operator of the embedding coordinate, combines the gauge field theory, calculates the change rate of the embedding coordinate, monitors the state of the switchgear and makes adjustments; solves the problems of low sensitivity in anomaly detection, weak ability to capture non-linear characteristics, and insufficient representation of the state evolution mechanism in the traditional technology, improves the depth of state analysis and the comprehensiveness of state monitoring, and enhances the sensitivity and noise resistance of anomaly detection.

[0135] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered within the scope of the claims of the present invention.

Claims

1. A high and low voltage switchgear control method, characterized in that: include, Collect the state data of high and low voltage switchgear, generate the state variable matrix, calculate the normalized time change rate, use KL divergence to calculate the relative entropy variation between state variables, correct the normalized time change rate, construct the normalized state change rate matrix, use Fisher information metric to calculate the geodesic distance between state variables, and construct the embedded coordinates; Calculate the generalized Laplace operator of the embedded coordinates, combine it with gauge field theory, calculate the rate of change of the embedded coordinates, monitor the state of the switchgear and make adjustments; Build a visual interface to display monitoring results, store, collect and analyze the status data generated; The collecting of status data of high and low voltage switchgear and constructing embedded coordinates includes: Collecting status data of high and low voltage switchgear through intelligent sensors, including current, voltage, power, temperature, electromagnetic field strength, laser displacement and contact resistance sensors; The state data includes current, voltage, load power, temperature, electromagnetic interference intensity, switch contact gap, contact resistance and corresponding time interval data; The time window is set using the maximum information entropy criterion, and the time window is used as the number of rows of the state variable matrix. The preprocessed state data is sorted in chronological order to generate the state variable matrix. Use the steady-state probability distribution method to set the reference state value and calculate the normalized time rate of change; The relative entropy variation between state variables is calculated using KL divergence, and the normalized time rate of change is corrected using an exponential decay function; For the corrected normalized time rate of change, a normalized state rate of change matrix is ​​constructed using a matrix scaling method; Extract the elements in the normalized state change rate matrix, calculate the Shannon entropy using the Shannon entropy formula, and calculate the equivalent temperature using the law of conservation of energy; The reciprocal temperature parameter is calculated using the inverse of the Boltzmann constant; Computing the generalized partition function using the Boltzmann factor ; The normalized probability is calculated using the maximum entropy probability distribution, the diagonal elements of the Fisher information metric matrix are calculated using the Fisher-Rao metric, and the Fisher information metric matrix is ​​constructed; The geodesic distances between state variables are calculated using Fisher information metric, a geodesic distance matrix is ​​constructed, and the embedded coordinates are constructed using multidimensional scaling analysis methods.

2. The high and low voltage switchgear control method according to claim 1, characterized in that: The generalized Laplace operator of the embedded coordinates is calculated, combined with the gauge field theory, to calculate the rate of change of the embedded coordinates, including: The time derivatives of the embedded coordinates are calculated using the central difference method; The gauge field connection of the state variables is constructed based on the diagonal elements of the Fisher information metric matrix and normalized; The curvature tensor of the gauge field is calculated using covariant derivatives and normalized; The determinant of the Fisher information metric matrix is ​​calculated using LU decomposition, the inverse matrix of the Fisher information metric matrix is ​​calculated using Cholesky decomposition, and the partial derivatives of the embedded coordinates are calculated using the finite difference method; Compute the generalized Laplace operator of embedded coordinates using the Laplace-Beltrami operator; Combined with gauge field theory, the rate of change of the embedded coordinates is calculated.

3. The high and low voltage switchgear control method according to claim 2, characterized in that: The monitoring of the switchgear status and making adjustments include: Use statistical analysis to set the state threshold, compare the change rate with the state threshold, and when the change rate is less than the state threshold, it is judged as a normal state and monitoring continues; When the rate of change is greater than or equal to the state threshold, it is judged as an abnormal state; The gradient of the normalized gauge field connection is calculated using the variational method and adjusted in combination with the diagonal elements of the Fisher information metric matrix; Calculate the difference between the rate of change and the state threshold, which is defined as the control error term; Use empirical rules to set adjustment factors and calculate control offsets; Calculate the optimal control input using the forward update method and execute it; The change rate of the embedded coordinates of the optimized control input is calculated and monitored, and the adjustment is stopped when the change rate is less than the state threshold.

4. The high and low voltage switchgear control method according to claim 1, characterized in that: After the state data is collected, a pre-processing operation is first performed.

5. The high and low voltage switchgear control method according to claim 3, characterized in that: The construction of a visual interface to display monitoring results includes: Use the front-end framework React.js to build a visualization interface, including the main chart area and the top information bar; Display monitoring results in the main chart area and the rate of change of embedded coordinates in the top information bar; Users who have passed real-name verification are allowed to view the information.

6. The high and low voltage switchgear control method according to claim 3, characterized in that: The state data generated by the storage, collection and analysis includes: The collected status data and monitoring results generated by analysis are stored in the central database, and security access measures are set. The central database will back up the stored data to the cloud and regularly perform integrity checks on the stored data and backup data. After the test is completed, the integrity test record is generated and stored synchronously in the central database.

7. A high and low voltage switchgear control system, based on the high and low voltage switchgear control method according to any one of claims 1 to 6, characterized in that: include, The collection and embedding module is used to collect the state data of high and low voltage switchgear, generate the state variable matrix, calculate the normalized time change rate, use KL divergence to calculate the relative entropy variation between state variables, correct the normalized time change rate, construct the normalized state change rate matrix, use Fisher information metric to calculate the geodesic distance between state variables, and construct the embedding coordinates; The calculation monitoring module is used to calculate the generalized Laplace operator of the embedded coordinates, and calculate the rate of change of the embedded coordinates in combination with the gauge field theory, so as to monitor the state of the switchgear and make adjustments; The visualization storage module is used to build a visualization interface to display monitoring results and store the status data generated by collection and analysis.

8. 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 the high and low voltage switchgear control method according to any one of claims 1 to 6 are implemented.

9. 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 high and low voltage switchgear control method according to any one of claims 1 to 6 are implemented.

Images