GIS high-voltage switch secondary circuit intelligent control method and system

Abstract

The invention discloses an intelligent control method and system for a GIS high-voltage switch secondary circuit, and relates to the technical field of power system automation, and the method comprises the steps: configuring a control logic based on the state information of a GIS circuit breaker control switch and a GIS isolation grounding switch in the GIS high-voltage switch secondary circuit, and generating a response control signal; adjusting a control loop of the GIS circuit breaker according to the response control signal, and monitoring real-time feedback information through a signal loop; and based on the real-time feedback information, combining an equivalent circuit model to optimize a charging and discharging strategy of the energy storage loop. Compared with a traditional GIS high-voltage switch secondary circuit system which mainly depends on fixed electrical connection lines and manual configuration and often cannot flexibly adapt to a real-time changing system, due to the fact that an intelligent control strategy, an advanced communication technology and real-time data analysis are combined for use, the real-time change of the GIS high-voltage switch secondary circuit system is achieved, and the real-time change of the GIS high-voltage switch secondary circuit system is improved. Therefore, the expansibility of the system is effectively improved, and real-time and reliable information interaction is ensured.

Description

Technical Field

[0001] The invention relates to the technical field of power system automation, and in particular to an intelligent control method and system for a secondary circuit of a GIS high-voltage switch. Background Art

[0002] The existing high-voltage switch secondary circuit control system mainly relies on connecting a large number of discrete components through a large number of cables and manual configuration methods to achieve control, and lacks the application of combining advanced communication technology with intelligent control strategies and data analysis algorithms. Therefore, when the power system conditions are complex or dynamically changing, this control method that relies on traditional methods will lead to slow response speed and inaccurate control, or even be unusable due to system incompatibility, which in turn affects the safety and efficiency of the system. Therefore, there is an urgent need for an intelligent control method for the secondary circuit of a GIS high-voltage switch that can still achieve real-time precise control and good scalability when the power system conditions are complex or dynamically changing, so as to ensure the stable operation of the power system. Summary of the invention

[0003] In view of the problems existing in the existing high-voltage switch secondary circuit control system, the present invention is proposed.

[0004] Therefore, the problem to be solved by the present invention is how to use communication technology and intelligent control strategy to realize the secondary circuit control of the high voltage switch.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0006] In a first aspect, an embodiment of the present invention provides a GIS high-voltage switch secondary circuit intelligent control method, which includes configuring control logic based on status information of a GIS circuit breaker control switch and a GIS isolation grounding switch in the GIS high-voltage switch secondary circuit, and generating a response control signal;

[0007] adjusting a control loop of the GIS circuit breaker according to the response control signal, and monitoring real-time feedback information through a signal loop;

[0008] Based on the real-time feedback information, the charging and discharging strategy of the energy storage loop is optimized in combination with an equivalent circuit model.

[0009] As a preferred solution of the GIS high-voltage switch secondary circuit intelligent control method of the present invention, generating the response control signal includes the following steps:

[0010] Continuously monitoring current and voltage levels on the GIS circuit breaker;

[0011] Convert the monitored current and voltage data into digital signals and analyze the digital signals from the circuit breaker;

[0012] Evaluate data based on a predetermined algorithm to determine if there is an overload risk;

[0013] When an overload risk is determined, a corresponding control signal is automatically generated.

[0014] As a preferred solution of the GIS high-voltage switch secondary circuit intelligent control method of the present invention, the predetermined algorithm is as follows:

[0015] I EWMA (t) = αI(t) + (1-α)I EWMA (t-1)

[0016] Among them, I EWMA (t) is the smoothing result at time t, I(t) is the actual observation value at time t, and I EWMA (t-1) is the smoothing result at the previous time t-1, and a is the smoothing coefficient.

[0017] As a preferred solution of the intelligent control method for the secondary circuit of the GIS high-voltage switch of the present invention, the optimization of the charging and discharging strategy of the energy storage circuit includes the following steps:

[0018] Establish an equivalent circuit model and calibrate the model parameters;

[0019] Input data obtained from GIS circuit breakers in real time into the equivalent circuit model to predict voltage and available capacity in current and future states;

[0020] Optimize the charging and discharging strategy based on the model prediction results;

[0021] The battery charging and discharging model is shown as follows:

[0022]

[0023] Where E0 is the open circuit voltage, R is the internal resistance, I is the charge and discharge current, K is the polarization resistance, Q is the discharged or charged capacity, Q0 is the total capacity, A and B are constants describing the time-dependent behavior, and t is the time.

[0024] As a preferred solution of the intelligent control method for the secondary circuit of the GIS high-voltage switch of the present invention, wherein: the prediction of the voltage and available capacity in the current and future states adopts an improved convolutional neural network model;

[0025] The convolutional neural network model includes an input layer, a convolution layer, a spatial pyramid pooling layer, a fully connected layer and an output layer.

[0026] As a preferred solution of the GIS high-voltage switch secondary circuit intelligent control method of the present invention, the convolution layer is shown as follows:

[0027] F(i)=ReLU(W*xi+b)

[0028] Among them, W is the convolution kernel weight, x i is the input data, b is the bias, F (i) is the activated feature map, * represents the convolution operation;

[0029] The pooling layer is shown as follows:

[0030] P(j)=max(F j,k )

[0031] Among them, F j,k Represents the area in the feature map output by the convolutional layer, and P(j) is the output after the pooling operation;

[0032] The spatial pyramid pooling layer is shown as follows:

[0033] P SPP =[P1,P2,...Pn]

[0034] Among them, P n is the maximum pooling result of the corresponding area.

[0035] As a preferred solution of the GIS high-voltage switch secondary circuit intelligent control method described in the present invention, the response control signal includes an instruction to generate an opening or closing circuit breaker, a command to adjust the grounding switch state, and an emergency signal to trigger a safety protection program.

[0036] In a second aspect, an embodiment of the present invention provides a GIS high-voltage switch secondary circuit intelligent control system, which includes:

[0037] Status information collection module, used to collect status information of GIS circuit breaker control switch and GIS isolation grounding switch;

[0038] A logic control module, configured to configure control logic based on the received status information and generate a response control signal;

[0039] An execution control module, used for adjusting a control loop of the GIS circuit breaker and controlling the action of the motor according to the response control signal;

[0040] The optimization module optimizes the charging and discharging strategy of the energy storage circuit based on the real-time feedback information and in combination with an equivalent circuit model.

[0041] In a third aspect, an embodiment of the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, wherein: when the processor executes the computer program, it implements any step of the above-mentioned GIS high-voltage switch secondary circuit intelligent control method.

[0042] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the above-mentioned GIS high-voltage switch secondary circuit intelligent control method is implemented.

[0043] The beneficial effect of the present invention is that compared with the traditional GIS high-voltage switch secondary circuit system, which mainly relies on fixed electrical connections and manual configuration and is often unable to flexibly adapt to the technical problems of the real-time changing system, the present invention uses a combination of intelligent control strategies and advanced communication technologies, as well as real-time data analysis, thereby effectively improving the scalability of the system and ensuring real-time and reliable information interaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0045] Figure 1 The figure is a flow chart of the intelligent control method for the secondary circuit of GIS high-voltage switch. DETAILED DESCRIPTION

[0046] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0047] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0048] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0049] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0050] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0051] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0052] Example 1

[0053] Reference Figure 1 , which is the first embodiment of the present invention, and provides a GIS high-voltage switch secondary circuit intelligent control method, comprising:

[0054] S1: Configure control logic based on the status information of the GIS circuit breaker control switch and the GIS isolation grounding switch in the secondary circuit of the GIS high-voltage switch;

[0055] It should be noted that GIS circuit breaker refers to a switchgear used to control high-voltage circuits, which can be air-insulated, gas-insulated, or solid-insulated; GIS isolating earthing switch refers to a switchgear used to isolate parts of high-voltage circuits to ensure maintenance safety, which can be manually operated, electrically operated, or remotely operated;

[0056] Status information refers to the operating data collected from these devices, including switch position information, current value, voltage value, temperature, and pressure environmental data.

[0057] It should be understood that in order to better achieve accurate control of the power system and improve the safety of operation, the specific implementation steps of configuring the control logic based on the status information of the GIS circuit breaker control switch and the GIS isolation grounding switch may be:

[0058] First, the system administrator or automated script retrieves the latest control strategies and parameter settings from the central database, and then uses dedicated management software to download these control strategies and parameters to the intelligent control modules of each GIS circuit breaker and GIS isolation and earthing switch.

[0059] In the specific settings of the control strategy, when multiple input signals are involved, the processing priority of each signal is set, and the threshold of the key operation is configured, where the threshold setting can be manually preset, such as automatically switching to the isolation state when the current exceeds a predetermined value, and setting the delay and duration of the operation, such as performing the isolation operation within 5 seconds after the circuit breaker is actuated. In addition, the logical relationship between devices can be set to define how the corresponding isolation switch should respond when a circuit breaker is actuated, and configure the interlocking logic between devices to ensure the operation sequence and safety. In terms of feedback and monitoring settings, the system will configure the real-time monitoring logic of status information, such as regularly checking and reporting the status of the equipment, and set the automatic feedback mechanism when abnormal operation or status is detected, including the generation of error logs and the triggering of alarms. After the configuration is completed, the control logic will be field tested in the actual power system environment to verify its execution accuracy and response time, and the control parameters and logic will be adjusted and optimized according to the test results to improve the overall efficiency and safety of the system.

[0060] S2: receiving the state information through optical fiber network transmission; configuring control logic according to the state information; generating a response control signal according to the received state information;

[0061] Specifically, a response control signal is generated according to the received status information, and the response control signal includes an instruction to open or close the circuit breaker, a command to adjust the state of the grounding switch, and an emergency signal to trigger a safety protection program; the response control signal generated according to the received status information can specifically be:

[0062] First, sensors installed on GIS circuit breakers continuously monitor current and voltage levels. These sensors can detect current values ​​that are beyond the normal operating range, that is, identify overload conditions. After that, the monitored current and voltage data are converted into digital signals by the sensors and sent to the control center in real time through the fiber optic network. The fiber optic network ensures high speed and low latency of data transmission, allowing the control center to receive almost real-time equipment status data. Furthermore, in the control center, a dedicated data processing system receives and analyzes the digital signals from the circuit breakers.

[0063] The system uses predetermined algorithms to evaluate data, such as threshold judgment, where the system determines whether the current state is overloaded based on the set safety current threshold; trend analysis, where the system also analyzes the current change trend to determine whether the overload is instantaneous or continuously increasing. Finally, once the system determines that there is an overload risk, it automatically generates a corresponding control signal.

[0064] In this process, threshold detection algorithms are involved. The most direct application is to monitor whether the current of GIS circuit breakers exceeds the safe operating range in power systems. Set a maximum current threshold Imax, such as 120% of the rated current; for example, if the rated current of the GIS circuit breaker is 1000A, Imax may be set to 1200A. If the current exceeds 1200A at any time, the system automatically cuts off the power supply to prevent further damage.

[0065] An exponentially weighted moving average algorithm is also involved in this process to quickly reflect actual changes in current readings, especially when system conditions change rapidly (such as a sudden load increase). The formula is:

[0066] I EWMA (t) = αI(t) + (1-α)I EWMA (t-1)

[0067] Among them, I EWMA (t) is the smoothing result at time t, I(t) is the actual observation value at time t, and I EWMA (t-1) is the smoothing result at the previous time t-1, and a is the smoothing coefficient.

[0068] Setting α = 0.2 can respond faster to the actual current increase without delaying the execution of alarms and protection measures, especially when the current rises rapidly.

[0069] S3: Using the generated response control signal to adjust the control loop of the GIS circuit breaker, and monitoring the real-time feedback information through the signal loop;

[0070] Among them, the signal loop involves the transmission and processing of control signals to ensure that the circuit breaker can receive and execute commands from the control system;

[0071] Real-time recording of operating status refers to the use of sensors and data acquisition systems to continuously monitor and record equipment operating parameters and environmental conditions, such as current, voltage, temperature, mechanical position and other key variables, for immediate analysis and response.

[0072] It should be noted that the control loop refers to the electrical and logical path used to manage and execute the operation of GIS circuit breakers and GIS isolating earthing switches. It can be a traditional hard-wired circuit, a control system based on PLC (programmable logic controller), or a remote control system implemented through a network interface.

[0073] It is understandable that the optimization of the control loop is to improve the response speed and operation accuracy of the system, and to ensure that necessary operations can be performed quickly and accurately when the power system state changes. The GIS intelligent high-voltage switch adopts an intelligent control unit for knife switches, and implements the relay circuit with soft logic, such as the mutual interlocking of the closing and opening disconnectors. At the same time, the power supply is operated through voltage monitoring, the motor working current is monitored through current sensors, and the motor is protected against overcurrent, undervoltage, and phase failure. For the three-position knife switch, the mechanical interlocking logic is realized through intelligent means.

[0074] More specifically, in order to improve the flexibility and maintainability of the system, soft logic is used to replace the traditional relay circuit. In actual implementation, a state machine-based logic control system is used to continuously monitor various input signals, such as voltage, current, temperature sensor readings, and switch position information. Based on these inputs, the system will decide the next operation according to the preset logic rules.

[0075] S4: Based on the real-time feedback information from the monitoring, the charging and discharging strategy of the energy storage loop is optimized by performing data analysis on the real-time operating status of the control loop feedback and combining the Thevenin model;

[0076] It should be noted that the energy storage circuit refers to the system in the GIS circuit breaker that is responsible for providing the necessary energy for the operating mechanism, which usually includes capacitors, batteries or other energy storage devices;

[0077] Specifically, taking the charge and discharge kinetics model of batteries or supercapacitors as an example, this model uses electrochemical reactions and physical properties to describe the behavior of energy storage devices, thereby accurately predicting the changes in key parameters during the charge and discharge process. The specific process can be:

[0078] Step 1: Establish a battery charge and discharge kinetic model

[0079] Based on the charging and discharging characteristics of the battery, an equivalent circuit model (Thevenin model) can be used to simulate its behavior. The formula is:

[0080]

[0081] E0 is the open circuit voltage, R is the internal resistance, I is the charge and discharge current, K is the polarization resistance, Q is the discharged or charged capacity, Q0 is the total capacity, A and B are constants describing the time-dependent behavior, and t is the time;

[0082] Step 2: Parameter calibration

[0083] The model parameters are calibrated using experimental data. The voltage and current under different charge and discharge conditions are measured experimentally, and the model parameters are fitted using mathematical methods such as the least squares method.

[0084] Step 3: Real-time status monitoring and model prediction

[0085] The data obtained from the GIS circuit breaker energy storage system in real time is input into the dynamic model to predict the voltage and available capacity under current and future conditions.

[0086] Real-time predictive execution: predict the future battery state based on the current charge / discharge rate I(t) and known model parameters.

[0087] Step 4: Strategy Optimization and Execution

[0088] Based on the results predicted by the model, the charging and discharging strategies are optimized to maximize energy efficiency and extend the life of the energy storage system.

[0089] Optimization strategy: Use the prediction model results to determine the optimal charging time and discharge depth to prevent overcharging or over-discharging while ensuring sufficient energy supply.

[0090] Step 5: Performance Evaluation and Feedback

[0091] Regularly evaluate the performance of the energy storage system and the accuracy of the prediction model, and adjust the model parameters based on actual operating data.

[0092] Adjustment and feedback: If the actual running data shows that the prediction deviates from the actual situation, adjust the model parameters to improve the prediction accuracy.

[0093] Furthermore, the future operation requirements are predicted based on the real-time operation status fed back in combination with the neural network model analysis; the configuration of the control loop is adjusted based on the predicted future operation requirements; the neural network model is a complex data processing algorithm that can learn and identify complex patterns from a large amount of data. In this embodiment, the model is trained to analyze the operation data of the power system and predict future operation requirements, such as when the circuit breaker needs to be turned on or off, when the load needs to be adjusted, etc.; the real-time operation status fed back refers to the data collected by the system in real time through sensors and monitoring equipment, such as current, voltage, temperature, and switch status. These data are fed back to the control system in real time for continuous monitoring and evaluation of system performance.

[0094] Specifically, the neural network model can use a convolutional neural network (CNN) model to analyze and predict the future operation requirements of the secondary circuit of the GIS high-voltage switch. The traditional CNN model can be described as:

[0095] (1) Input layer:

[0096] The input data include multi-dimensional time series data collected from GIS high-voltage switches, such as current, voltage, load fluctuation, etc.

[0097] (2) Convolutional layer:

[0098] The key features in the time series data are extracted through multiple convolutional filters. Each filter is responsible for detecting a specific pattern in the data, such as a sudden increase in current or a drop in voltage.

[0099] formula:

[0100] F(i)=ReLU(W*xi+b)

[0101] Where W is the convolution kernel weight, xi is the input data, b is the bias, F(i) is the activated feature map, and * represents the convolution operation.

[0102] (3) Pooling layer:

[0103] The maximum pooling method is used to simplify the feature map, retaining the most significant features while reducing the data dimension to improve the computational efficiency of the model.

[0104] formula:

[0105] P(j)=max(F j,k )

[0106] Where Fj,k represents the region P(j) in the feature map output by the convolutional layer, which is the output after the pooling operation.

[0107] (4) Fully connected layer:

[0108] The pooled feature map is flattened and passed through one or more fully connected layers to integrate and classify high-level features and output prediction results, such as whether the circuit breaker needs to be operated.

[0109] formula:

[0110] y=σ(W f ·P+b f )

[0111] Where Wf is the weight of the fully connected layer, P is the output of the pooling layer, bf is the bias, and σ is the activation function.

[0112] (5) Output layer:

[0113] Based on the output of the fully connected layer, predict future operational requirements, such as opening or closing of a circuit breaker.

[0114] Aiming at the application scenario of GIS high-voltage switch secondary circuit intelligent control system, the spatial pyramid pooling (SPP) layer is introduced. In the traditional convolutional network, the convolution layer is usually followed by a pooling layer to reduce the feature dimension and extract the main features. However, this method may ignore the position changes in the input data, which is disadvantageous in the dynamic monitoring of the power system. To solve this problem, the spatial pyramid pooling layer is introduced after the convolution layer. The spatial pyramid pooling layer can maintain the spatial hierarchy of the input features and output a fixed-size representation regardless of the size of the input image. This enables the network to process inputs of different sizes more flexibly while capturing multi-scale feature information.

[0115] (1) Improved convolutional layer: Continue to use standard convolution operations to extract basic features, but do not perform standard pooling directly after that. The formula remains the same.

[0116] (2) Introducing the SPP layer: Add the SPP layer after the convolution layer and apply pooling of different sizes (such as 1x1, 2x2, 4x4) to each convolution output. Formula example: P SPP =[P1,P2,...Pn], where Pn is the maximum pooling result of the corresponding area, which are flattened and concatenated into a single feature vector as the input of the subsequent layer.

[0117] (3) Subsequent processing: The output of SPP is passed to the fully connected layer for high-level feature integration and classification. The formulas of the fully connected layer and the output layer remain unchanged, and the prediction analysis continues.

[0118] Application Process:

[0119] (1) Data preprocessing: Collect and format input data from the GIS circuit breaker system in real time.

[0120] (2) Feature extraction: Use convolutional layers and pooling layers to automatically extract key features from time series data.

[0121] Among them, when extracting features, we choose to integrate data from different sensors (such as current, voltage, temperature, vibration, sound, etc.), and use their comprehensive information to perform more accurate state assessment and operation prediction to optimize the control strategy of GIS high-voltage switches.

[0122] First perform single modality feature extraction: F i =ReLU(W i *d i,norm +b i ), and then select the weighted feature fusion method to assign different weights to different features:

[0123] F=w1·F1+w2·F2+...+w k ·F k , where w k is the learned weight used to balance the impact of different sensor data.

[0124] Decision making: Analyze features through fully connected layers and output action recommendations.

[0125] Action execution: Automatically adjust the control logic of the circuit breaker based on the model prediction results.

[0126] In the monitoring data of GIS high-voltage switches, the use of SPP layers can more effectively capture abnormal fluctuations in voltage or current at different scales. The introduction of this structure can improve the model's sensitivity and response speed to sudden events in the power system (such as short circuits or equipment failures). With this improvement, the CNN model can not only more accurately identify and predict key operational requirements in high-voltage switches, but also enhance the model's adaptability to different input data scales, thereby improving the stability and reliability of the entire power monitoring system.

[0127] S5: Before configuring the control logic based on the status information of the GIS circuit breaker control switch and the GIS isolating earthing switch in the secondary circuit of the GIS high-voltage switch, including:

[0128] Real-time monitoring of the location information of GIS circuit breaker control switch and GIS isolation grounding switch based on the ring network monitoring system;

[0129] Evaluate the current state of the system based on the monitored position information and predict operational requirements according to preset rules;

[0130] Configure initial control logic in advance based on predicted operational needs;

[0131] After obtaining the position information of the GIS circuit breaker control switch and the GIS isolating earthing switch, the position of the cross-bay primary device is obtained through the process layer network, and the electrical interlock is set.

[0132] Implement electrical interlocking through software to ensure the coordinated operation of different devices and improve the overall reliability of the system;

[0133] It should be noted that the locking loop refers to a control system used to prevent erroneous operations and ensure equipment safety in order to better achieve the safety and efficiency of equipment operation.

[0134] Furthermore, this embodiment also provides a GIS high-voltage switch secondary circuit intelligent control system, including:

[0135] Status information collection module, used to collect status information of GIS circuit breaker control switch and GIS isolation grounding switch;

[0136] A logic control module, configured to configure control logic based on the received status information and generate a response control signal;

[0137] An execution control module, used for adjusting a control loop of the GIS circuit breaker and controlling the action of the motor according to the response control signal;

[0138] The optimization module optimizes the charging and discharging strategy of the energy storage circuit based on the real-time feedback information and in combination with an equivalent circuit model.

[0139] This embodiment also provides a computer device, which is suitable for the case of a GIS high-voltage switch secondary circuit intelligent control method, including a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the GIS high-voltage switch secondary circuit intelligent control method proposed in the above embodiment.

[0140] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. 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 a computer program. The internal memory provides an environment for the operation of the operating system and the computer program 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 achieved through WIFI, an operator 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 a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0141] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for realizing the intelligent control of the secondary circuit of a GIS high-voltage switch as proposed in the above embodiment is implemented.

[0142] The storage medium proposed in this embodiment and the data storage method proposed in the above embodiment belong to the same inventive concept. The technical details not fully described in this embodiment can be found in the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0143] Example 2

[0144] This is the second embodiment of the present invention, which provides a GIS high-voltage switch secondary circuit intelligent control method. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0145] In order to verify the effectiveness and advantages of the intelligent control system based on the secondary circuit of GIS high-voltage switch, a six-month field test was conducted at a 500kV substation of a provincial power company. The test objects included 6 groups of GIS circuit breaker control switches and the corresponding GIS isolation and grounding switches, which were installed in different locations of the substation to control and protect the main transformer, transmission line and busbar.

[0146] During the test preparation phase, a comprehensive evaluation of the existing GIS high-voltage switch secondary circuit system was first conducted, including control logic, communication network and data acquisition system. Subsequently, the system was upgraded and modified as follows according to the requirements of the invention content:

[0147] A high-precision fiber optic sensor network is installed to monitor the status information of GIS circuit breakers and isolating earthing switches in real time, including switch position, current value, voltage value, temperature, pressure and other environmental data. These sensors use the latest fiber Bragg grating (FBG) technology and are characterized by high sensitivity, anti-electromagnetic interference and long-term stability.

[0148] The central control system was upgraded and an AI-based decision support module was introduced. This module uses an improved convolutional neural network (CNN) model and integrates a spatial pyramid pooling (SPP) layer to more effectively process multi-scale and multi-modal input data.

[0149] An energy storage optimization system based on the Thevenin model is introduced into the control loop. The system uses high-performance supercapacitors as energy storage devices and is equipped with an intelligent charge and discharge control unit that can dynamically adjust the charge and discharge strategy according to the real-time operating status and predicted operating requirements.

[0150] A dedicated software system was developed and deployed to achieve intelligent control of electrical interlocking and locking loops. The software system uses a distributed architecture that can process status information from different devices in real time and automatically configure control logic according to preset safety rules.

[0151] A ring network monitoring system based on industrial Ethernet was built to realize real-time monitoring of the position information of GIS circuit breaker control switches and GIS isolation grounding switches. The system adopts a redundant topology to ensure the reliability and real-time performance of communication.

[0152] After completing the hardware and software upgrades, a two-week system debugging and optimization process was conducted. During the debugging process, various possible operating scenarios and fault conditions were simulated, including load mutations, short circuit faults, equipment abnormalities, etc., to verify the system's responsiveness and control accuracy.

[0153] During the formal test phase, the system operates according to the following steps:

[0154] The ring network monitoring system continuously monitors the position information of GIS circuit breakers and isolating earthing switches, with a data acquisition frequency of 100 Hz to ensure that millisecond-level status changes can be captured.

[0155] The AI ​​module of the central control system analyzes the collected data in real time, evaluates the current status of the system and predicts future operational needs. The prediction time window is set to three scales of 5 minutes, 15 minutes and 30 minutes to adapt to changes in different time scales.

[0156] Based on the prediction results of the AI ​​module, the system automatically configures the initial control logic, including setting operation priorities, configuring thresholds for key operations, and defining logical relationships between devices.

[0157] Through the process layer network, the system obtains the location information of the primary equipment across the interval and sets the electrical interlock accordingly. This step ensures the coordinated operation between different devices and effectively prevents the occurrence of misoperation.

[0158] The energy storage optimization system dynamically adjusts the charging and discharging strategies of supercapacitors based on the Thevenin model and real-time operating data. The system will charge key equipment in advance based on predicted operating needs to ensure sufficient operating energy when needed.

[0159] When performing control operations, the system transmits control signals through the optical fiber network and monitors feedback information in real time. If an abnormal situation is detected, the system will immediately trigger the preset protection mechanism.

[0160] All operation records, state changes, and system responses are recorded in detail for subsequent performance analysis and system optimization.

[0161] During the entire test period, the researchers closely monitored the operation of the system and conducted regular data analysis and performance evaluation. By comparing the system performance before and after the transformation, the significant advantages of the invention in improving the reliability, response speed and energy efficiency of the power system were verified, as shown in the following table:

[0162] Table 1 Experimental data table

[0163]

[0164] Through in-depth analysis of the data in the above table, it can be clearly seen that the GIS high-voltage switch secondary circuit intelligent control system proposed in the present invention has significant advantages and innovations compared with the traditional system.

[0165] First, in terms of response time, the improved system showed excellent performance improvement. The response time of the traditional system is 150ms, while the improved system 5 can shorten the response time to 25ms, an increase of 83.3%. This significant improvement is attributed to the fiber optic network transmission and AI-based decision support module used in the present invention, which enables the system to complete state assessment and control decisions within milliseconds. Such a fast response capability is crucial to the safe and stable operation of the power system, especially in the face of sudden faults or drastic changes in load, the system can respond quickly and effectively prevent the expansion of faults or the occurrence of cascading faults.

[0166] The improved system also performed well in terms of misoperation rate. The misoperation rate of the traditional system was 0.5%, while the improved system 5 reduced this indicator to 0.02%, a reduction of 96%. This achievement is mainly due to the electrical interlocking and intelligent locking circuit implemented by the software introduced in the present invention. By real-time monitoring of the position information of the primary equipment across the interval, the system can dynamically set the electrical interlocking, effectively preventing misoperation caused by incorrect operation sequence or mismatch of equipment status. This not only improves the reliability of the system, but also greatly enhances the confidence of the operator.

[0167] The improvement of energy efficiency is also a highlight of the present invention. The energy efficiency of the traditional system is 85%, while the improved system 5 reaches 97%, an increase of 14.1%. This improvement is mainly attributed to the energy storage optimization system based on the Thevenin model. By accurately predicting future operating needs, the system is able to optimize the charging and discharging strategy of the supercapacitor, minimize energy losses, and ensure sufficient energy supply at critical operating moments. This not only reduces operating costs, but also conforms to the current development trend of energy conservation and emission reduction.

[0168] The improvement in system availability further demonstrates the advancement of the present invention. The availability of the conventional system is 99.9%, while that of the improved system 5 is increased to 99.995%. This means that the annual downtime of the system is reduced from 8.76 hours to 0.438 hours, greatly improving the continuity and reliability of power supply. This improvement is due to the distributed architecture and redundant design adopted in the present invention, which enables the system to quickly self-recover and reconstruct in the face of local failures.

[0169] Prediction accuracy is an innovative highlight of the present invention. By introducing an improved convolutional neural network model and a spatial pyramid pooling layer, the system is able to make high-precision predictions of future operational requirements. The prediction accuracy of the improved system 5 reached 97%, which provides strong support for the active prevention and control and optimized operation of the system. High-precision predictions enable the system to prepare in advance, such as adjusting energy storage strategies, presetting control logic, etc., so as to make faster and more accurate responses when actually needed.

[0170] Finally, the significant reduction in maintenance costs also highlights the economic value of the present invention. Compared with the traditional system, the maintenance cost of the improved system 5 is reduced by 25%. This is mainly due to the improvement of the intelligence and automation of the system, which reduces the need for manual inspection and maintenance. At the same time, the self-diagnosis and predictive maintenance functions of the system also make maintenance work more accurate and efficient, avoiding unnecessary downtime for maintenance.

[0171] In summary, the GIS high-voltage switch secondary circuit intelligent control system proposed in this invention has shown significant advantages in response speed, operational reliability, energy efficiency, system availability, predictive ability and economy. These improvements not only improve the overall performance and reliability of the power system, but also provide a new technical path for the intelligent and modern development of the power grid. Especially in the face of increasingly complex power demand and new energy grid connection challenges, the high flexibility and adaptability of this system will play an important role and make important contributions to building a safer, more efficient and more environmentally friendly smart grid.

[0172] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A GIS high-voltage switch secondary circuit intelligent control method, characterized in that: include, Configure control logic based on status information of the GIS circuit breaker control switch and the GIS isolating grounding switch in the secondary circuit of the GIS high-voltage switch, and generate a response control signal; adjusting a control loop of the GIS circuit breaker according to the response control signal, and monitoring real-time feedback information through a signal loop; Based on the real-time feedback information, the charging and discharging strategy of the energy storage loop is optimized in combination with an equivalent circuit model.

2. The GIS high-voltage switch secondary circuit intelligent control method according to claim 1 is characterized in that: Generating the response control signal comprises the following steps: Continuously monitoring current and voltage levels on the GIS circuit breaker; Convert the monitored current and voltage data into digital signals and analyze the digital signals from the circuit breaker; Evaluate data based on a predetermined algorithm to determine if there is an overload risk; When an overload risk is determined, a corresponding control signal is automatically generated.

3. The GIS high-voltage switch secondary circuit intelligent control method according to claim 2 is characterized in that: The predetermined algorithm is shown in the following formula: I EWMA (t)=αI(t)+(1-α)I EWMA (t-1) Among them, I EWMA (t) is the smoothing result at time t, I(t) is the actual observation value at time t, and I EWMA (t-1) is the smoothing result at the previous time t-1, and a is the smoothing coefficient.

4. The GIS high-voltage switch secondary circuit intelligent control method according to claim 3 is characterized in that: Optimizing the charging and discharging strategy of the energy storage circuit includes the following steps: Establish an equivalent circuit model and calibrate the model parameters; Input data obtained from GIS circuit breakers in real time into the equivalent circuit model to predict voltage and available capacity in current and future states; Optimize the charging and discharging strategy based on the model prediction results; The battery charging and discharging model is shown as follows: Where E0 is the open circuit voltage, R is the internal resistance, I is the charge and discharge current, K is the polarization resistance, Q is the discharged or charged capacity, Q0 is the total capacity, A and B are constants describing the time-dependent behavior, and t is the time.

5. The GIS high-voltage switch secondary circuit intelligent control method according to claim 4 is characterized in that: The prediction of voltage and available capacity in current and future states adopts an improved convolutional neural network model; The convolutional neural network model includes an input layer, a convolution layer, a spatial pyramid pooling layer, a fully connected layer and an output layer.

6. The GIS high-voltage switch secondary circuit intelligent control method according to claim 5, characterized in that: The convolutional layer is shown as follows: F(i)=ReLU(W*xi+b) Among them, W is the convolution kernel weight, x i is the input data, b is the bias, F (i) is the activated feature map, * represents the convolution operation; The pooling layer is shown as follows: P(j)=max(F j,k ) Among them, F j,k Represents the area in the feature map output by the convolutional layer, and P(j) is the output after the pooling operation; The spatial pyramid pooling layer is shown as follows: P SPP =[P1,P2,...Pn] Among them, P n is the maximum pooling result of the corresponding area.

7. The GIS high-voltage switch secondary circuit intelligent control method according to claim 6, characterized in that: The response control signal includes an instruction to generate an opening or closing circuit breaker, a command to adjust the state of a grounding switch, and an emergency signal to trigger a safety protection program.

8. A GIS high-voltage switch secondary circuit intelligent control system, based on the GIS high-voltage switch secondary circuit intelligent control method according to any one of claims 1 to 7, characterized in that: include, Status information collection module, used to collect status information of GIS circuit breaker control switch and GIS isolation grounding switch; A logic control module, configured to configure control logic based on the received status information and generate a response control signal; An execution control module, used for adjusting a control loop of the GIS circuit breaker and controlling the action of the motor according to the response control signal; The optimization module optimizes the charging and discharging strategy of the energy storage circuit based on the real-time feedback information and in combination with an equivalent circuit model.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the GIS high-voltage switch secondary circuit intelligent control method described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the GIS high-voltage switch secondary circuit intelligent control method described in any one of claims 1 to 7 are implemented.

Images