Load isolation switch control method and system

Abstract

The invention relates to the technical field of electric power safety control, in particular to a load isolation switch control method and system, and the method comprises the steps: collecting an environment feature group of power grid operation, a body state monitoring group of an isolation switch, and a load side operation feature group; calculating offsets between the environment feature group, the ontology state monitoring group and the load operation feature group and a preset environment feature reference group, an ontology state reference group and a load operation reference group, and generating a state offset feature matrix; inputting the state offset characteristic matrix into an isolation risk assessment engine, and outputting an isolation abnormal risk probability; when the isolation abnormal risk probability exceeds a preset safety threshold value, collecting at least two groups of environment feature groups, body state monitoring groups and load operation feature groups based on a predetermined collection frequency, and converting the collected data into a time sequence feature tensor;

Description

Technical Field

[0001] This invention relates to the technical field of power safety control, and in particular to a load disconnect switch control method and system. Background Technology

[0002] During the operation of a power system, load disconnect switches are key equipment for ensuring the safety and stability of the power grid, and their operating status directly affects the reliability of power supply. With the continuous expansion of the power grid and the large-scale integration of distributed energy resources and smart loads, the power grid operating environment is becoming increasingly complex, and the operating conditions faced by load disconnect switches are becoming more and more diverse.

[0003] Existing control methods for load disconnectors largely rely on the monitoring and judgment of a single or a few parameters, such as using isolated parameters like contact temperature or opening / closing time for status assessment and operational control. These methods fail to comprehensively consider environmental factors affecting power grid operation, the disconnector's own condition, and the load-side operating status. Consequently, under complex operating conditions, it is difficult to accurately predict potential anomalies in the disconnector, often resulting in reactive measures only after a fault occurs. This lack of early warning and adaptive control of the disconnector can lead to serious consequences such as the expansion of power grid faults and power outages. Summary of the Invention

[0004] To address the aforementioned technical problems, this invention provides a load disconnect switch control method and system that can improve the safety, stability, and reliability of the power grid.

[0005] In a first aspect, the present invention provides a load disconnect switch control method, the method comprising:

[0006] Collect environmental characteristics of power grid operation, status monitoring of disconnecting switches, and operating characteristics of load side;

[0007] Calculate the offsets between the environmental feature group, the body state monitoring group, and the load operation feature group and the preset environmental feature benchmark group, body state benchmark group, and load operation benchmark group, respectively, and generate a state offset feature matrix;

[0008] The state offset feature matrix is ​​input into the isolation risk assessment engine, which outputs the isolation anomaly risk probability.

[0009] When the probability of the isolation anomaly exceeds the preset safety threshold, at least two sets of the environmental feature group, the body status monitoring group, and the load operation feature group are collected based on a predetermined collection frequency, and the collected data are converted into time-series feature tensors.

[0010] The time-series feature tensor is input into the isolation control strategy optimization engine to generate an adaptive operation control instruction set containing the target device identifier, operation instructions, and execution parameters;

[0011] The adaptive operation control instruction set is executed to complete the load isolation operation.

[0012] Furthermore, the method for determining the sampling frequency includes:

[0013] Calculate the extent to which the probability of the isolated anomaly risk exceeds a preset safety threshold;

[0014] The sampling frequency is calculated by comprehensively evaluating the excess amplitude and the body status monitoring group.

[0015] Furthermore, the environmental characteristic group includes ambient temperature, humidity, dust content, electromagnetic interference intensity, and vibration amplitude.

[0016] Furthermore, the body status monitoring group includes contact force, opening and closing time, contact surface temperature, and insulation resistance value.

[0017] Furthermore, the load-side operating characteristic set includes feeder current phase, active power change rate, and instantaneous voltage sag depth.

[0018] Furthermore, the collected data is converted into a temporal feature tensor, including:

[0019] The time interval is determined based on the collection frequency, and the collected data is arranged in chronological order to form a time series.

[0020] The parameters of the environmental feature group, the body status monitoring group, and the load operation feature group are used as feature dimensions;

[0021] By combining time series data and feature dimensions, a time series feature tensor is constructed.

[0022] Furthermore, the adaptive operation control instruction set includes target device identification instructions, operation instructions, and execution parameter instructions.

[0023] On the other hand, this application also provides a load disconnect switch control system, the system comprising:

[0024] The data acquisition module collects environmental characteristics of the power grid operation, the status monitoring of the disconnecting switch, and the operating characteristics of the load side.

[0025] The offset calculation module calculates the offsets between the environmental feature group, the body state monitoring group, and the load operation feature group and the preset environmental feature benchmark group, body state benchmark group, and load operation benchmark group, respectively, and generates a state offset feature matrix.

[0026] The risk assessment module inputs the state offset feature matrix into the isolation risk assessment engine and outputs the isolation anomaly risk probability.

[0027] The time-series feature generation module, when the probability of the isolated anomaly risk exceeds a preset safety threshold, collects at least two sets of the environmental feature group, the body status monitoring group, and the load operation feature group based on a predetermined collection frequency, and converts the collected data into a time-series feature tensor.

[0028] The control instruction generation module inputs the timing feature tensor into the isolation control strategy optimization engine to generate an adaptive operation control instruction set containing the target device identifier, operation instructions, and execution parameters.

[0029] The operation execution module executes the adaptive operation control instruction set to complete the load isolation operation.

[0030] Thirdly, this application provides an electronic device including a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor. The transceiver, the memory, and the processor are connected via the bus, and the computer program, when executed by the processor, implements the steps of any of the methods described above.

[0031] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the methods described above.

[0032] Compared with existing technologies, the advantages of this invention are as follows: This method comprehensively collects the environmental characteristics of the power grid operation, the physical state of the disconnector switch, and the operating status of the load side through data acquisition, enabling a comprehensive evaluation of multiple key factors, thereby making control decisions more comprehensive and reducing the risk of ignoring key parameters; through offset calculation and risk assessment, the method can monitor the offset of various features in real time and calculate the abnormal risk probability of the disconnector switch based on the offset; this allows the method to promptly detect potential risks during power grid operation, improving the safety and reliability of the power grid; traditional methods often rely on preset control logic, making it difficult to cope with complex and ever-changing power grid operating conditions; this method adopts an adaptive control method based on time-series features. When the risk probability exceeds a threshold, the method generates a time-series feature tensor based on the real-time collected data, inputs it into the control strategy optimization engine for adaptive adjustment, and generates... Personalized and targeted operating instructions; flexible response to different operating conditions, improving control accuracy; the method has early warning capabilities, and once a potential abnormal risk is identified, the method can proactively generate control instructions and execute load isolation operations; the proactive intervention mechanism can effectively prevent the expansion of the power grid fault range and prevent serious consequences such as power outages, thereby improving the stability and safety of the power method; by real-time monitoring and evaluation of various key parameters of the power grid and adjusting the operation control according to real-time data, the method can dynamically adjust under different environments and operating conditions, avoiding the limitations of static control strategies that cannot adapt to complex operating conditions, and improving the reliability of the power grid under complex operating conditions; this control method can detect anomalies in advance in complex power grid environments and proactively intervene, significantly improving the safety, stability and reliability of the power grid, avoiding the passivity and limitations of existing methods when dealing with complex operating conditions. Attached Figure Description

[0033] Figure 1 This is a flowchart of the present invention;

[0034] Figure 2 This is a structural diagram of the load disconnect switch control system in this invention. Detailed Implementation

[0035] This application will now be described with reference to the accompanying drawings.

[0036] like Figure 1 As shown, a load disconnect switch control method of the present invention specifically includes the following steps:

[0037] S1. Collect environmental characteristics of power grid operation, status monitoring of disconnecting switches, and operating characteristics of load side;

[0038] S2. Calculate the offsets between the environmental feature group, the body status monitoring group and the load operation feature group and the preset environmental feature benchmark group, body status benchmark group and load operation benchmark group, respectively, and generate a state offset feature matrix.

[0039] S3. Input the state offset feature matrix into the isolation risk assessment engine and output the isolation anomaly risk probability.

[0040] S4. When the probability of the isolation anomaly exceeds the preset safety threshold, at least two sets of the environmental feature group, the body status monitoring group and the load operation feature group are collected based on the predetermined collection frequency, and the collected data are converted into time-series feature tensors.

[0041] S5. Input the time-series feature tensor into the isolation control strategy optimization engine to generate an adaptive operation control instruction set containing the target device identifier, operation instructions and execution parameters;

[0042] S6. Execute the adaptive operation control instruction set to complete the load isolation operation.

[0043] In this embodiment, the method comprehensively collects environmental characteristics of the power grid operation, the physical state of the disconnector switch, and the operating status of the load side through data acquisition. This enables a comprehensive evaluation of multiple key factors, resulting in more comprehensive control decisions and reducing the risk of neglecting key parameters. Through offset calculation and risk assessment, the method can monitor the offset of various features in real time and calculate the probability of abnormal risks of the disconnector switch based on the offset. This allows the method to promptly detect potential risks during power grid operation, improving the safety and reliability of the power grid. Traditional methods often rely on preset control logic, which is difficult to cope with complex and ever-changing power grid operating conditions. This method adopts an adaptive control method based on time-series features. When the risk probability exceeds a threshold, the method generates a time-series feature tensor based on the real-time collected data, inputs it into the control strategy optimization engine for adaptive adjustment, and generates personalized, targeted control strategies. This method offers targeted operational instructions; it can flexibly respond to different operating conditions, improving control accuracy; it possesses early warning capabilities, and once a potential abnormal risk is identified, the method can proactively generate control instructions and execute load isolation operations; the proactive intervention mechanism can effectively prevent the expansion of the power grid fault range and prevent serious consequences such as power outages, thereby improving the stability and safety of the power grid; by real-time monitoring and evaluation of various key parameters of the power grid and adjusting operational control based on real-time data, the method can dynamically adjust under different environments and operating conditions, avoiding the limitations of static control strategies in adapting to complex operating conditions and improving the reliability of the power grid under complex operating conditions; this control method can detect anomalies in advance in complex power grid environments and proactively intervene, significantly improving the safety, stability, and reliability of the power grid, avoiding the passivity and limitations of existing methods in handling complex operating conditions.

[0044] In some embodiments of the present invention, for step S1, the environmental characteristic group of the power grid operation, the physical status monitoring group of the disconnecting switch, and the load-side operation characteristic group are collected.

[0045] The environmental characteristic group includes ambient temperature, humidity, dust content, electromagnetic interference intensity, and vibration amplitude;

[0046] Ambient temperature is collected in real time by temperature sensors arranged around the disconnector cabinet. Excessive temperature will accelerate the aging of insulation materials and reduce the conductivity of contacts, while excessively low temperature may cause mechanical parts to jam. It is a basic environmental parameter that affects the lifespan and operational reliability of the equipment.

[0047] Humidity is monitored by a humidity sensor. High humidity environments can easily cause condensation on the equipment surface, increasing the risk of insulation flashover. Humidity data can affect insulation failure.

[0048] Dust content is measured by using a dust sensor to capture the concentration of particulate matter in the air. Dust adhering to the contact surface increases the contact resistance, and long-term accumulation may lead to overheating of the contacts. In power grid equipment in industrial plants or windy and sandy areas, this parameter is used to assess the rate of contact degradation.

[0049] Electromagnetic interference intensity is measured by collecting the surrounding electromagnetic field intensity, electromagnetic radiation from equipment such as transformers and reactors in the power grid, and external radio signal interference. These factors can affect the normal operation of electronic components in the control circuit of the disconnecting switch. This data is used to determine whether the control signal is interfered with.

[0050] Vibration amplitude is monitored by vibration sensors to detect the vibration of the disconnect switch body and the mounting foundation. Vibration may come from the electrodynamic force during a short circuit in the power grid, the impact of equipment operation, or the vibration of surrounding machinery. Excessive vibration can cause fasteners to loosen and contacts to become poor, which can help predict mechanical failures.

[0051] The body status monitoring group includes contact force, opening and closing time, contact surface temperature and insulation resistance value;

[0052] The contact force of the contact is measured by a pressure sensor installed on the contact transmission mechanism. Insufficient contact force will lead to increased contact resistance and aggravated heat generation, while excessive contact force will increase mechanical wear. This parameter directly reflects the reliability of the contact connection and is a core indicator to ensure the safety of the conductive circuit.

[0053] The opening and closing time is recorded by a travel sensor. The time from the issuance of the operation command to the opening or closing of the disconnecting switch is recorded. If the time is too long, it means mechanical jamming or drive motor failure. If it is too short, there may be a problem of excessive operation impact. It is used to evaluate the mechanical operation performance.

[0054] The surface temperature of the contacts is collected non-contactly using an infrared temperature sensor or a fiber optic temperature measuring device. The contacts are the core conductive components of the disconnector switch, and their temperature directly reflects the current carrying capacity and contact status. An abnormal rise in temperature is often an early signal of a fault and needs to be analyzed in conjunction with the ambient temperature to eliminate environmental influences.

[0055] The insulation resistance value is measured periodically or in real time by an insulation resistance tester to measure the insulation resistance between the disconnecting switches and to ground. A decrease in insulation resistance indicates that the insulation material is aging or damp.

[0056] The load-side operating characteristic group includes feeder current phase, active power change rate, and instantaneous voltage sag depth;

[0057] The feeder current phase is obtained by combining a current transformer with a phase measurement device. The current phase relationship reflects the power consumption characteristics of the load. Abnormal phase offset may mean that a short circuit, harmonic pollution or grid instability of distributed power supply has occurred on the load side, affecting the timing of opening and closing of the disconnecting switch.

[0058] The rate of change of active power is based on the real-time monitoring of the rate of change of active power on the load side by a power sensor. Rapid power fluctuations can cause the disconnector contacts to be subjected to large current surges. This is used to judge the load stability during operation and to avoid opening and closing the switch under extreme conditions.

[0059] The instantaneous voltage sag depth is acquired by a voltage sensor to measure the instantaneous voltage drop on the load side. Voltage sags may be caused by grid faults, the start-up of large-capacity equipment, etc., which can affect the power supply stability of the disconnector control circuit and even lead to malfunctions in operating commands. This data is used to assess the reliability of the control power supply.

[0060] In this embodiment, the collected environmental features, device status, and load-side features cover the external environmental conditions, physical state, and electrical characteristics of the load side of the equipment, forming a multi-dimensional, full-scenario feature data system that can systematically reflect the actual operating conditions of the disconnector in a complex power grid environment. From the perspective of the correlation between data and device status, all collected parameters are directly related to the safe operation of the disconnector: the environmental feature group can provide early warnings of environmentally induced faults such as insulation aging and mechanical jamming; the device status monitoring group can capture potential equipment hazards such as poor contact and abnormal mechanical operation in real time; the load-side operating feature group can promptly detect external electrical shocks such as load fluctuations and short-circuit risks. Through the collection of these parameters, the potential risks, immediate status, and influencing factors of the equipment can be comprehensively mapped into quantifiable data. The collected real-time and continuous data can accurately reflect the dynamic changing trends of each feature, avoiding judgment bias caused by incomplete or delayed data, making subsequent analysis and decision-making based on this data more reliable, and helping to improve the safety and stability of power grid operation from the source.

[0061] In some embodiments of the present invention, for step S2, the offsets between the environmental feature group, the body state monitoring group and the load operation feature group and the preset environmental feature reference group, the body state reference group and the load operation reference group are calculated respectively, and a state offset feature matrix is ​​generated.

[0062] The preset environmental characteristic benchmark group, the body status benchmark group, and the load operation benchmark group are ideal state reference standards for the load disconnect switch under normal operating conditions. These benchmark groups provide a measurement scale for judging whether the current operating state of the equipment deviates from the normal range, so that the potential abnormal risks of the equipment can be accurately assessed by calculating the offset.

[0063] The environmental characteristic benchmark group comprehensively considers the climatic conditions of different regions, seasons and time periods, and combines a large amount of historical operation data and experimental research to determine the reasonable range of ambient temperature, humidity, dust content, electromagnetic interference intensity and vibration amplitude of the environment where the load disconnect switch is located during normal operation, and uses this as the environmental characteristic benchmark group.

[0064] The body status reference group determines the standard values ​​or reasonable ranges of body status parameters such as contact force, opening and closing time, contact surface temperature and insulation resistance value under normal operation, based on the design parameters, manufacturing process and long-term operating experience of the disconnecting switch.

[0065] The load operation benchmark group analyzes the operating characteristics of the power grid under different load levels and power consumption modes. Combining load forecasting and actual operating data, it determines the normal range of load-side operating characteristic parameters such as feeder current phase, active power change rate, and instantaneous voltage sag depth.

[0066] For each parameter in the environmental characteristic group, calculate its difference or relative deviation from the parameter in the corresponding environmental characteristic benchmark group. The difference calculation is simple and intuitive, and is suitable for parameters with clear limits on the range of numerical variation. The relative deviation calculation can better reflect the relative degree of parameter change, and facilitates comparison and comprehensive analysis between different parameters.

[0067] The contact force offset is the actual contact force minus the contact force reference value. If the contact force is too small, it may lead to increased contact resistance and aggravated heat generation; if it is too large, it will increase mechanical wear. By calculating the offset, these potential problems can be detected in time.

[0068] The offset of opening and closing time is the actual opening and closing time minus the baseline value of opening and closing time. Too long a time means mechanical jamming or drive motor failure; too short a time means excessive operational impact. Offset calculation helps to evaluate mechanical operation performance.

[0069] The temperature deviation of the contact surface can reflect the heating status of the contact itself;

[0070] The insulation resistance value offset is the actual insulation resistance value minus the reference insulation resistance value; a decrease in insulation resistance indicates that the insulation material is aging or damp, and offset calculation can detect changes in insulation performance in a timely manner.

[0071] For parameters such as feeder current phase, active power change rate, and instantaneous voltage sag depth in the load-side operating characteristic group, the offset is calculated based on their characteristics and influence mechanisms.

[0072] Feeder current phase offset: This is calculated by comparing the actual collected feeder current phase with the reference phase, taking into account the balance between the three phases. Abnormal phase offset indicates problems such as short circuits, harmonic pollution, or unstable grid connection of distributed power sources on the load side.

[0073] Active power change rate offset: Rapid power fluctuations can cause the disconnector contacts to be subjected to large current surges. By calculating the offset, the load stability during operation can be judged, and the switching on and off under extreme conditions can be avoided.

[0074] Instantaneous voltage sag depth offset: Voltage sags may be caused by grid faults, large-capacity equipment startup, etc., which can affect the power supply stability of the disconnector control circuit and even lead to malfunction of operating commands. Offset calculation helps to assess the reliability of the control power supply.

[0075] The calculated offsets of each parameter in the environmental feature group, the body status monitoring group, and the load-side operation feature group are combined into a matrix in a certain order and format, namely the state offset feature matrix.

[0076] In this embodiment, by calculating the offsets between the environmental characteristic group, the physical status monitoring group, and the load operation characteristic group and their corresponding benchmark groups, multiple dimensions of factors such as the power grid operating environment, the physical status of the disconnector switch itself, and the operating conditions of the load side are comprehensively considered. This overcomes the limitations of existing methods that rely on only a single or a few parameters for status assessment, and can more accurately reflect the actual operating status of the load disconnector switch under complex operating conditions, thereby accurately predicting potential abnormal risks. The offset is calculated using difference or relative deviation, quantifying the degree of deviation between the equipment operating status and the normal benchmark status. This makes the assessment of abnormal risks more objective and accurate, avoiding errors caused by subjective judgment. The preset benchmark group fully considers the impact of different regions, seasons, time periods, and load levels on the operating status of the load disconnector switch, improving the adaptability and reliability of the control method. By continuously monitoring and calculating the offsets of each parameter, it is possible to... Before a significant equipment failure occurs, subtle changes in operating status are detected, providing a basis for preventative maintenance measures to prevent further development of the failure, thereby reducing the probability of failure and improving equipment reliability and lifespan. The calculation of offsets in load-side operating characteristic parameters, such as feeder current phase offset, active power change rate offset, and instantaneous voltage sag depth offset, enables timely detection of load-side anomalies. Early warnings allow for timely intervention to prevent the spread of faults and ensure the safe and stable operation of the power grid. The calculated parameter offsets are combined in a specific order and format into a state offset feature matrix, providing comprehensive and accurate data input for subsequent isolation risk assessment and isolation control strategy optimization engines. The state offset feature matrix reflects the deviation between the current operating state and the normal state of the equipment, enabling the control engine to generate reasonable risk assessment results and adaptive operation control command sets based on actual conditions.

[0077] In some embodiments of the present invention, for step S3, the state offset feature matrix is ​​input into the isolation risk assessment engine and the isolation anomaly risk probability is output.

[0078] The isolation risk assessment engine includes:

[0079] Data preprocessing module: The state offset feature matrix contains the offset information between each parameter in the environmental feature group, the body state monitoring group, and the load operation feature group and the corresponding benchmark group. However, these data may have problems such as different dimensions and large differences in numerical range. Directly inputting them into the risk assessment model may affect the accuracy of the assessment results. The data preprocessing module is used to standardize and normalize the state offset feature matrix to eliminate the differences in dimensions and numerical ranges between the data, making the data more suitable for subsequent risk assessment model processing.

[0080] Risk assessment model: built on machine learning and deep learning; the machine learning model can learn the complex nonlinear relationship between state shift features and isolated anomaly risks by training on a large amount of historical data; the deep learning model has powerful feature extraction and learning capabilities, and can automatically extract deeper feature information from the state shift feature matrix to better capture its state change trend and improve the accuracy of risk assessment.

[0081] Decision logic module: Based on the output of the risk assessment model, combined with the preset risk level classification standards and decision rules, the final probability of isolating abnormal risks is determined; the risk level is divided into three levels: low, medium and high, each corresponding to a different risk probability range; when the output of the risk assessment model falls within a certain risk level range, the decision logic module converts it into a specific probability value of isolating abnormal risks and outputs it to the subsequent control links.

[0082] When the state offset feature matrix is ​​input into the isolation risk assessment engine, it first enters the data preprocessing module for data standardization, normalization, and other processing. The processed data is then transmitted to the risk assessment model, which calculates and analyzes the input data based on pre-trained parameters or rules to obtain a preliminary assessment result of the isolation anomaly risk of the current load disconnect switch. Then, the decision logic module determines the final isolation anomaly risk probability based on the preliminary assessment result and preset decision rules, and outputs it.

[0083] In this embodiment, the data preprocessing module eliminates the differences in dimensions and numerical ranges between different parameters in the state offset feature matrix through standardization and normalization operations, avoiding interference with the evaluation results caused by inconsistent data formats. The risk assessment model, built based on machine learning and deep learning, can accurately capture the complex nonlinear relationship between state offset features and isolated anomaly risks by learning from a large amount of historical data. It can uncover deeper state change trends from the matrix, improving the accuracy of risk assessment. The decision logic module, combined with preset risk level classification standards and decision rules, transforms the output of the risk assessment model into specific isolated anomaly risk probabilities, and clarifies the probability ranges corresponding to low, medium, and high risk levels, making the abstract risk assessment results more intuitive and quantifiable. This facilitates accurate understanding of the current risk situation in subsequent control stages. This provides maintenance personnel with clear judgment criteria, avoiding biases caused by subjective judgments and ensuring the operability of risk assessment results in practical applications. The isolation anomaly risk probability output by the isolation risk assessment engine can objectively reflect the current operational risk status of the load disconnect switch. When the risk probability is at different levels, corresponding countermeasures can be triggered, enabling early prediction of disconnect switch anomaly risks and effectively reducing the possibility of serious consequences such as the expansion of the power grid fault range and power outages. The risk assessment model can adapt to the diversified operating conditions brought about by the expansion of the power grid scale and the access of distributed energy and smart loads. At the same time, the preset rules of the decision logic module can be adjusted according to actual operating needs, so that the risk assessment results can dynamically adapt to the power grid operating characteristics under different scenarios, further enhancing the applicability and effectiveness of the method in complex environments.

[0084] In some embodiments of the present invention, for step S4, when the probability of the isolation anomaly risk exceeds a preset safety threshold, at least two sets of the environmental feature group, the body status monitoring group and the load operation feature group are collected based on a predetermined collection frequency, and the collected data are converted into time-series feature tensors.

[0085] The method for determining the sampling frequency includes:

[0086] The calculation determines the extent to which the probability of the isolated anomaly risk exceeds a preset safety threshold. This extent reflects the urgency of the equipment facing an anomaly or malfunction. Generally, a larger extent indicates a more dangerous state, requiring more frequent data collection to promptly grasp changes in the equipment's status and provide the latest information for subsequent control decisions. A smaller extent may indicate only a minor anomaly, allowing for a reduction in the data collection frequency to decrease the system's data processing burden and resource consumption. Conversely, a larger extent suggests an imminent serious malfunction, necessitating an immediate increase in the data collection frequency to monitor various equipment parameters in real time and ensure timely and effective control measures.

[0087] A comprehensive evaluation is conducted on the exceedance range and the main body status monitoring group to calculate the sampling frequency. Based on the degree of influence of each parameter on the operating status of the load disconnect switch, corresponding weights are assigned. Then, based on the magnitude of the exceedance range and the measured values ​​of each parameter, scores are assigned according to a pre-set scoring standard. Finally, the scores of each parameter are multiplied by their respective weights and summed to obtain a comprehensive evaluation score. The sampling frequency is determined based on the comprehensive evaluation score; a higher comprehensive evaluation score indicates a higher level of risk for the equipment, and the sampling frequency should be increased accordingly.

[0088] Once the sampling frequency is determined, at least two sets of data—environmental characteristic group, physical condition monitoring group, and load operation characteristic group—need to be collected at that frequency. The environmental characteristic group includes parameters such as ambient temperature, humidity, dust content, electromagnetic interference intensity, and vibration amplitude. These parameters affect the performance and lifespan of the load disconnect switch. The physical condition monitoring group data directly reflects the operating status of the equipment itself. The load operation characteristic group includes parameters such as feeder current phase, active power change rate, and instantaneous voltage sag depth. These parameters reflect the operating conditions on the load side. Abnormal changes on the load side may cause excessive current or voltage surges to the load disconnect switch, leading to equipment damage.

[0089] In power systems, the data acquisition process may be affected by various interference factors. Acquiring multiple sets of data can perform redundant processing, and noise and outliers can be removed through data fusion, filtering and other technical means to improve the accuracy and reliability of the data.

[0090] The collected data is converted into a temporal feature tensor, including:

[0091] The time interval is determined based on the collection frequency, and the collected data is arranged in chronological order to form a time series.

[0092] The parameters of the environmental feature group, the body status monitoring group, and the load operation feature group are used as feature dimensions;

[0093] By combining time series data and feature dimensions, a time series feature tensor is constructed; each element of the time series feature tensor represents a data value at a specific time and under a specific feature.

[0094] In this embodiment, the data collection frequency can be dynamically adjusted using an evaluation method based on the exceedance magnitude. This ensures timely data collection when the equipment is in an emergency, enabling rapid response to potential risks. When a large exceedance magnitude indicates a risk of serious equipment failure, the data collection frequency will be increased accordingly to ensure real-time monitoring of equipment status and reduce the likelihood of failure. The data collection frequency is dynamically adjusted based on the urgency of the equipment status. When the exceedance magnitude is small, the collection frequency can be appropriately reduced to decrease unnecessary system burden and resource consumption, thereby optimizing the overall system operating efficiency. The comprehensive evaluation score calculation method integrates multi-dimensional information on equipment operating status and environmental parameters, ensuring that decision-makers can effectively manage the equipment. The system monitors the real-time status of equipment and takes timely control measures to prevent equipment failure. Through multiple data acquisitions and redundant processing, noise and outliers during data acquisition are effectively reduced, improving data accuracy and reliability. The time-series feature tensor-based data organization method allows the data processing system to better adapt to different equipment and operating environments. By constructing time-series feature tensors, the system can capture the changing state of equipment over time, thereby dynamically adjusting the acquisition strategy and further enhancing the system's adaptability and flexibility. This step effectively improves the stability and responsiveness of the equipment monitoring system by dynamically adjusting the data acquisition frequency, optimizing the data acquisition process, improving data quality, and providing accurate decision-making basis.

[0095] In some embodiments of the present invention, for step S5, the time-series feature tensor is input into the isolation control strategy optimization engine to generate an adaptive operation control instruction set containing the target device identifier, operation instructions and execution parameters.

[0096] The isolation control strategy optimization engine consists of:

[0097] Power Operation Rules Knowledge Base: Based on power industry standards and safe operating procedures, it stores rigid constraints and prohibitions for disconnecting switch operation; including five-prevention operation rules, equipment rated parameter limits, and operation sequence requirements; it provides an insurmountable safety boundary for control strategy optimization, ensuring that the generated operation instructions comply with the basic principles of safe operation of the power system, and avoiding equipment damage or power grid accidents caused by strategy violations;

[0098] Digital twin model of equipment characteristics: including mechanical characteristic model, electrical characteristic model, and life loss model; maps the dynamic parameters in the time-series feature tensor to the real-time state of the equipment, provides a quantitative adjustment basis for the execution parameters of operation commands, and ensures that the control strategy matches the individual characteristics of the equipment;

[0099] Multi-objective optimization decision module: Prioritizes the rapid elimination of isolated anomaly risks as the safety objective; selects the operation timing with the least impact on user power supply based on load-side characteristics as the power supply impact objective; adjusts the operation intensity according to the device's status to reduce mechanical wear as the equipment loss objective; balances multiple objective requirements while meeting safety rules to avoid suboptimal decisions caused by a single objective.

[0100] Dynamic verification and correction unit: performs real-time verification and adjustment of the initially generated control strategy to ensure its adaptability to dynamic changes in power grid operating conditions; verifies the consistency with the current time-series feature tensor, compatibility with power grid dispatch instructions, and execution feasibility; and compensates for the deviation between model predictions and actual operating conditions through a closed-loop verification mechanism.

[0101] Command formatting output interface: converts the optimized control strategy into an adaptive operation control command set that conforms to the power system communication protocol;

[0102] The adaptive operation control instruction set includes target device identification instructions, operation instructions, and execution parameter instructions;

[0103] The target equipment identification instruction is used to accurately locate the load disconnect switch to be operated, avoiding misoperation due to equipment confusion; the operation instruction is determined according to the type of isolation anomaly risk, equipment status and power grid conditions, covering basic operations and emergency operations; the execution parameter instruction is used to standardize the technical indicators during the operation process, ensuring accurate and safe operation and reducing the impact on equipment and power grid.

[0104] In this embodiment, supported by a power operation rule knowledge base, the generated operation instructions are ensured to strictly comply with the safety standards and regulations of the power industry, avoiding equipment damage or grid accidents caused by policy violations and ensuring the safe operation of the power system. The application of a digital twin model of equipment characteristics enables the control strategy to be quantitatively adjusted according to the real-time status of the equipment, ensuring that the operation instructions match the individual characteristics of the equipment and improving the service life and performance of the equipment. Through a multi-objective optimization decision-making module, multiple factors such as safety, power supply stability, and equipment loss are considered, and reasonable decision-making balance is made under the premise of meeting the safety of power system operation, effectively avoiding suboptimal results driven by a single objective. The generated control strategy is verified and corrected in real time to ensure that it adapts to the dynamic changes of grid operating conditions, increases the reliability and flexibility of operation, compensates for the deviation between prediction and actual operating conditions, and improves the accuracy of control decisions. Finally, an adaptive operation control instruction set that conforms to the power system communication protocol is generated, which can be accurately executed in actual operation, ensuring the efficient and safe operation of the power system. The beneficial effect of this step is to improve the intelligence, precision, and security of the power system control strategy, ensure the efficient operation of the grid under complex operating conditions, and reduce equipment loss and failure risks.

[0105] In some embodiments of the present invention, for step S6, the adaptive operation control instruction set is executed to complete the load isolation operation;

[0106] After the control center transmits the generated adaptive operation control instruction set to the field operation terminal, the field operators need to analyze the instruction set in detail. The operators need to verify the target equipment identification through the power grid equipment management system to ensure that the operation object is accurate. For operation instructions, it is necessary to clarify whether it is a circuit breaker opening or closing operation, as well as the time requirements for the operation. The execution parameters cover various key settings in the operation process, and the operators need to fully understand the meaning and impact of these parameters.

[0107] After the analysis is completed, the operator needs to confirm with the control center a second time through voice communication or the command verification system to ensure that the understanding of the command set is consistent with that of the control center, so as to avoid misoperation due to misunderstanding of the command.

[0108] During operation, relevant data from the environmental characteristic group, the physical status monitoring group, and the load-side operating characteristic group are monitored in real time. These real-time data are transmitted to the field operation terminal and the control center so that operators and monitoring personnel can understand the operating status of the equipment and the power grid in a timely manner.

[0109] If any abnormal situation is discovered during operation, the operator should immediately stop the operation and handle it according to the pre-established emergency plan; at the same time, the abnormal situation should be reported to the control center in a timely manner so that the control center can coordinate relevant resources for handling.

[0110] After the operation is completed, the operator needs to conduct a comprehensive inspection of the load disconnect switch and related equipment to confirm that the equipment is in normal condition. The inspection includes the contact condition of the contacts, insulation performance, and flexibility of the operating mechanism. The contact temperature should be measured again using an infrared thermometer to ensure that the temperature is within the normal range. The insulation resistance value should be measured using an insulation resistance tester to verify whether the insulation performance has been restored well.

[0111] In addition to inspecting the equipment itself, it is also necessary to confirm the relevant parameters of the power grid to ensure that the load isolation operation has not adversely affected the operation of the power grid; check whether the voltage, current, power factor and other parameters near the operation point are within the normal range, and whether there are any fluctuations or abnormalities.

[0112] All aspects of the operation process, including operation time, operators, execution of operation instructions, equipment status monitoring results, power grid parameter monitoring results, and handling of abnormal situations, should be recorded in detail and promptly reported back to the control center.

[0113] In this embodiment, operators verify the target equipment identification through the power grid equipment management system to strictly confirm the operation object and avoid misoperation from the source. Simultaneously, a second confirmation is made with the control center, using voice communication or a command verification system to eliminate misunderstandings of commands and ensure consistency in understanding of operation direction, time requirements, and execution parameters. During operation, relevant data from the environment, equipment itself, and load side are monitored in real time and transmitted synchronously to the field terminal and control center, enabling operators and monitoring personnel to promptly grasp the equipment and power grid status. In the event of an anomaly, operators can immediately stop operation and activate the emergency plan, while simultaneously coordinating resources with the control center to effectively prevent the anomaly from escalating into a fault, significantly improving the operational efficiency. The safety and controllability of the process are ensured. After the operation is completed, a comprehensive inspection of the disconnecting switch and related equipment is carried out. The contact, insulation performance and operating mechanism status are verified by means of infrared thermometry, insulation resistance test and other means. At the same time, it is confirmed that the grid voltage, current, power factor and other parameters are normal to ensure that the load isolation operation has no adverse impact on the grid. Reliable isolation is achieved and the stable operation of the grid is maintained. The operation time, personnel, instruction execution, monitoring results and abnormal handling information are recorded in detail and fed back to the control center to form a complete operation file. This not only provides a detailed basis for subsequent operation and maintenance and fault analysis, but also facilitates the review and optimization of the operation process and continuously improves the standardization of load isolation operation.

[0114] like Figure 2 As shown, a load disconnect switch control system of the present invention specifically includes the following modules;

[0115] The data acquisition module collects environmental characteristics of the power grid operation, the status monitoring of the disconnecting switch, and the operating characteristics of the load side.

[0116] The offset calculation module calculates the offsets between the environmental feature group, the body state monitoring group, and the load operation feature group and the preset environmental feature benchmark group, body state benchmark group, and load operation benchmark group, respectively, and generates a state offset feature matrix.

[0117] The risk assessment module inputs the state offset feature matrix into the isolation risk assessment engine and outputs the isolation anomaly risk probability.

[0118] The time-series feature generation module, when the probability of the isolated anomaly risk exceeds a preset safety threshold, collects at least two sets of the environmental feature group, the body status monitoring group, and the load operation feature group based on a predetermined collection frequency, and converts the collected data into a time-series feature tensor.

[0119] The control instruction generation module inputs the timing feature tensor into the isolation control strategy optimization engine to generate an adaptive operation control instruction set containing the target device identifier, operation instructions, and execution parameters.

[0120] The operation execution module executes the adaptive operation control instruction set to complete the load isolation operation.

[0121] In this embodiment, the system comprehensively collects environmental characteristics of the power grid operation, the physical state of the disconnector switch, and the operating status of the load side through the data acquisition module. This enables a comprehensive assessment of multiple key factors, resulting in more comprehensive control decisions and reducing the risk of overlooking critical parameters. Through the offset calculation module and risk assessment module, the system can monitor the offset of various characteristics in real time and calculate the probability of abnormal risks of the disconnector switch based on the offset. This allows the system to promptly detect potential risks during power grid operation, improving the safety and reliability of the power grid. Traditional methods often rely on preset control logic, which is difficult to cope with complex and ever-changing power grid operating conditions. The system adopts an adaptive control method based on time-series characteristics. When the risk probability exceeds a threshold, the system generates a time-series feature tensor based on the real-time acquired data, inputs it into the control strategy optimization engine for adaptive adjustment, and generates a personalized control system. The system provides targeted and specific operating instructions, enabling flexible responses to different operating conditions and improving control accuracy. It possesses early warning capabilities; once a potential anomaly is detected, the system proactively generates control instructions and executes load isolation operations. This proactive intervention mechanism effectively prevents the expansion of power grid faults and avoids serious consequences such as power outages, thereby improving the stability and security of the power system. By monitoring and evaluating various key parameters of the power grid in real time and adjusting operating controls based on real-time data, the system can dynamically adjust under different environments and operating conditions, avoiding the limitations of static control strategies in adapting to complex conditions and improving the reliability of the power grid under complex conditions. This control system can proactively intervene in complex power grid environments to detect anomalies in advance, significantly improving the safety, stability, and reliability of the power grid and avoiding the passivity and limitations of existing methods in handling complex conditions.

[0122] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the technical principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for controlling a load disconnect switch, characterized in that, The method includes: Collect environmental characteristics of power grid operation, status monitoring of disconnecting switches, and operating characteristics of load side; Calculate the offsets between the environmental feature group, the body state monitoring group, and the load operation feature group and the preset environmental feature benchmark group, body state benchmark group, and load operation benchmark group, respectively, and generate a state offset feature matrix; The state offset feature matrix is ​​input into the isolation risk assessment engine, which outputs the isolation anomaly risk probability. When the probability of the isolation anomaly exceeds the preset safety threshold, at least two sets of the environmental feature group, the body status monitoring group, and the load operation feature group are collected based on a predetermined collection frequency, and the collected data are converted into time-series feature tensors. The time-series feature tensor is input into the isolation control strategy optimization engine to generate an adaptive operation control instruction set containing the target device identifier, operation instructions, and execution parameters; The adaptive operation control instruction set is executed to complete the load isolation operation.

2. The load disconnect switch control method as described in claim 1, characterized in that, The method for determining the sampling frequency includes: Calculate the extent to which the probability of the isolated anomaly risk exceeds a preset safety threshold; The sampling frequency is calculated by comprehensively evaluating the excess amplitude and the body status monitoring group.

3. The load disconnect switch control method as described in claim 1, characterized in that, The environmental characteristic group includes ambient temperature, humidity, dust content, electromagnetic interference intensity, and vibration amplitude.

4. The load disconnect switch control method as described in claim 1, characterized in that, The body status monitoring group includes contact force, opening and closing time, contact surface temperature, and insulation resistance value.

5. The load disconnect switch control method as described in claim 1, characterized in that, The load-side operating characteristic group includes feeder current phase, active power change rate, and instantaneous voltage sag depth.

6. The load disconnect switch control method as described in claim 2, characterized in that, The collected data is converted into a temporal feature tensor, including: The time interval is determined based on the collection frequency, and the collected data is arranged in chronological order to form a time series. The parameters of the environmental feature group, the body status monitoring group, and the load operation feature group are used as feature dimensions; By combining time series data and feature dimensions, a time series feature tensor is constructed.

7. The load disconnect switch control method as described in claim 1, characterized in that, The adaptive operation control instruction set includes target device identification instructions, operation instructions, and execution parameter instructions.

8. A load disconnector control system, characterized in that, The system includes: The data acquisition module collects environmental characteristics of the power grid operation, the status monitoring of the disconnecting switch, and the operating characteristics of the load side. The offset calculation module calculates the offsets between the environmental feature group, the body state monitoring group, and the load operation feature group and the preset environmental feature benchmark group, body state benchmark group, and load operation benchmark group, respectively, and generates a state offset feature matrix. The risk assessment module inputs the state offset feature matrix into the isolation risk assessment engine and outputs the isolation anomaly risk probability. The time-series feature generation module, when the probability of the isolated anomaly risk exceeds a preset safety threshold, collects at least two sets of the environmental feature group, the body status monitoring group, and the load operation feature group based on a predetermined collection frequency, and converts the collected data into a time-series feature tensor. The control instruction generation module inputs the timing feature tensor into the isolation control strategy optimization engine to generate an adaptive operation control instruction set containing the target device identifier, operation instructions, and execution parameters. The operation execution module executes the adaptive operation control instruction set to complete the load isolation operation.

9. An electronic device comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, characterized in that, When the computer program is executed by the processor, it implements the steps of the method as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1-7.

Images