Reclosing locking dynamic adjustment method and system based on voltage mutual inductance

Abstract

The invention discloses a reclosing locking dynamic adjustment method and system based on voltage mutual inductance, and relates to the technical field of reclosing locking dynamic adjustment, and the method comprises the following steps: collecting the voltage waveform of a power system, and carrying out the power failure prediction if the system does not recover the power supply; acquiring cable equipment data and power grid load data when the power system breaks down; constructing a power system anomaly evaluation model based on machine learning according to the cable equipment data and the power grid load data; obtaining a node area power system abnormity evaluation coefficient with the voltage waveform higher than the stable voltage, and carrying out fault positioning on the node area based on a preset power system safety and stability coefficient; and judging whether locking operation is carried out or not, if the locking operation is carried out, acquiring the voltage waveform after maintenance and the abnormal evaluation coefficient of the power system to judge whether the fault is eliminated or not, and closing the locking of the reclosing. According to the invention, through reclosing locking dynamic adjustment, the problems that the locking time is too long and the fault type cannot be accurately identified are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of dynamic adjustment of reclosing lockout, and more specifically, to a method and system for dynamic adjustment of reclosing lockout based on voltage mutual inductance. Background Art

[0002] A recloser is a device used in power systems to restore power to a line that has been disconnected due to a short circuit or other fault. The working principle is that when a fault occurs, the circuit breaker first disconnects the circuit, but after a short period of time, the recloser automatically recloses and attempts to restore power supply. The main purpose of the recloser is to respond to short-term, transient faults and reduce the duration of power outages caused by short-term faults. Lockout is a safety protection mechanism for the recloser in certain fault conditions. After the recloser attempts to restore power, if the fault still exists, the recloser will enter a lockout state to prevent damage to the equipment or other safety issues caused by repeated reclosing. Lockout usually requires manual operation or remote operation to reset.

[0003] For example, the invention patent with announcement number: CN117080000A discloses a high-voltage circuit breaker and its reclosing lockout logic function device, which includes the following steps: when the switch device performs a closing action, timing and counting are performed. If the preset number of operations is reached within the set time, a reclosing lockout is required, so that the main closing circuit is disconnected and the closing action cannot be performed. The circuit breaker is restarted after the internal temperature of the resistor drops, thereby solving the problem of overheating of the closing resistor caused by frequent closing operations of the circuit breaker and protecting the circuit breaker. At the same time, compared with the existing reclosing lockout logic function circuit, the redundancy of components is reduced and the reliability of the circuit breaker reclosing is improved.

[0004] For example, the invention patent with announcement number CN107681633B announces an intelligent protection device for the secondary voltage of a voltage transformer, and includes the following steps: the device is arranged after the voltage transformer to perform intelligent overcurrent protection on the secondary voltage generated by the voltage transformer and can automatically reclose after the fault disappears. The present invention combines a tripping device, a fault discrimination device and a CPU control device to perform intelligent protection on the circuit. When the circuit operates normally, the sampling device continuously collects the real-time current value in the circuit, and transmits the collected real-time current value to the CPU control device, so as to control the action of the tripping device through the CPU control device. When the real-time current value is too large, the CPU control device controls the tripping device to trip to protect the voltage transformer. After the tripping device trips, the CPU control device collects the voltage of the fault discrimination device to analyze what kind of fault is generated at the secondary voltage output end. After waiting for the fault to disappear, the CPU control device controls the tripping device to reclose and restore the secondary voltage output of the voltage transformer.

[0005] The above disclosed technical solutions have at least the following technical problems: The traditional reclosing lockout state is generally activated according to a set time or a specified number of reclosing times. If the power does not return to normal, the reclosing will enter the lockout state. However, these methods will lead to problems such as long lockout time and inability to accurately identify the fault type, affecting the recovery efficiency and flexibility of the power system.

[0006] In view of the above problems, the present invention proposes a solution. Summary of the invention

[0007] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a method and system for dynamic adjustment of reclosing lockout based on voltage mutual inductance, which solves the problems of too long lockout time and inability to accurately identify fault type through dynamic adjustment of reclosing lockout.

[0008] To achieve the above object, the present invention provides the following technical solutions: The method for dynamic adjustment of reclosing lockout based on voltage mutual inductance comprises the following steps: after the reclosing is started once, the voltage waveform of the power system is collected, and if the power supply of the system is not restored, a power fault prediction is performed; cable equipment data and power grid load data when the power system fails are obtained; a power system abnormality assessment model is constructed based on machine learning according to the cable equipment data and the power grid load data, and a power system abnormality assessment coefficient is generated; according to the collected voltage waveform of the power system, a node area where the voltage waveform is higher than the stable voltage is obtained, and a power system abnormality assessment coefficient of the node area where the voltage waveform is higher than the stable voltage is obtained; fault location of the node area is performed based on a preset power system safety and stability coefficient; according to the fault location of the node, it is determined whether a locking operation is performed on the reclosing of the power system, and if a locking operation is performed, it is determined whether the fault is eliminated by collecting the voltage waveform after maintenance and the power system abnormality assessment coefficient, and the locking operation of the reclosing is automatically turned off.

[0009] In a preferred embodiment, the cable equipment data is specifically obtained by the following method: obtaining basic cable insulation data of the cable equipment data, the basic cable insulation data including the length of the cable, the resistivity of the insulating material, and the cross-sectional area of ​​the cable; calculating the insulation resistance by measuring the leakage current and leakage voltage of the cable, and obtaining the insulation loss factor based on the dielectric loss tangent detection method according to the insulation resistance; calculating the cable insulation performance coefficient based on the cable insulation performance formula according to the insulation loss factor combined with the cable insulation basic data; obtaining the aging rate of the cable based on the life cycle analysis method by obtaining environmental data, historical operating frequency, and historical aging rate; and obtaining the cable equipment data based on the preset cable equipment calculation formula according to the cable insulation performance coefficient combined with the aging rate of the cable.

[0010] In a preferred embodiment, the grid load data is specifically acquired by the following method: the load data of each node is acquired and current load data and power load data are obtained based on a load flow calculation method; the grid frequency data of each node is acquired and grid frequency deviation value is obtained based on the grid frequency data according to a preset grid frequency stability value; the grid frequency deviation value is subjected to a standard deviation calculation method to obtain a grid frequency fluctuation coefficient; the grid load data is calculated based on the current load data and the power load data in combination with the grid frequency load coefficient based on a preset grid load calculation formula.

[0011] In a preferred embodiment, the power system abnormality assessment model is constructed based on machine learning according to the cable equipment data and the power grid load data to generate the power system abnormality assessment coefficient. The specific steps are as follows: historical cable equipment data and historical power grid load data are obtained, and the historical cable equipment data and historical power grid load data are preprocessed and normalized; the processed historical cable equipment data and historical power grid load data are divided into a training set and a test set; the model is trained based on the training set based on the machine learning algorithm and the weights of the historical cable equipment data and the historical power grid load data are automatically adjusted, and the power system abnormality assessment model is constructed by capturing the abnormal relationship between the historical cable equipment data and the historical power grid load data and the operation of the power system, and the model is verified and evaluated by the test set to obtain a trained model; the newly acquired cable equipment data and power grid load data are input into the trained power system abnormality assessment model to generate the power system abnormality assessment coefficient.

[0012] In a preferred embodiment, the power system abnormality assessment coefficient of the node area where the voltage waveform is higher than the stable voltage is obtained, and the fault location of the node area is performed based on the preset power system safety and stability coefficient. The specific steps are as follows: the collected voltage waveform of the power system is analyzed based on the voltage under stable operation of the power system, and the node area where the voltage is higher than the stable voltage is marked; the power system abnormality assessment coefficient of the marked node area is obtained, and the fault location of the node area is performed based on the preset power system safety and stability coefficient; if the power system abnormality assessment coefficient is greater than the power system safety and stability coefficient, the node area is a power system fault area; if the power system abnormality assessment coefficient is less than or equal to the power system safety and stability coefficient, the node area is an instantaneous fault area.

[0013] In a preferred embodiment, the reclosing switch of the power system is judged whether to perform a locking operation based on the fault location of the node. If a locking operation is performed, it is judged whether the fault is eliminated by collecting the voltage waveform after maintenance and the power system abnormality assessment coefficient, and the locking operation of the reclosing switch is automatically closed. The specific steps are as follows: If the fault location of the node area is an instantaneous fault area, there is no need to perform a locking operation on the reclosing switch, and the reclosing switch is allowed to automatically reclose after a period of time to restore the power supply of the power system; if the fault location of the node area is a power system fault area, the locking operation of the reclosing switch is required; after the locking operation of the reclosing switch is performed, the relevant maintenance personnel are notified to check and repair the power system; the voltage waveform after maintenance and the power system abnormality assessment coefficient are collected; if the voltage waveform is within the stable voltage, and the power system abnormality assessment coefficient is lower than the power system safety stability coefficient, the fault is eliminated, and the system automatically closes the locking operation of the reclosing switch.

[0014] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. By dynamically adjusting the locking of the reclosing switch, the stability of the power system can be effectively improved, unnecessary power outages can be reduced, while misoperation and equipment damage can be avoided, and the self-healing ability and reliability of the system can be improved.

[0015] 2. Building models through machine learning can automatically identify patterns and regularities from data, improve prediction accuracy, optimize decision-making processes, and provide efficient and intelligent solutions to complex problems. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A schematic structural diagram of a method for dynamic adjustment of reclosing lockout based on voltage mutual inductance provided in an embodiment of the present application.

[0017] Figure 2 A schematic diagram of the structure of a reclosing lockout dynamic adjustment system based on voltage mutual inductance provided in an embodiment of the present application. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] Embodiment 1, Figure 1 The structural schematic diagram of the dynamic adjustment method of reclosing lockout based on voltage mutual inductance provided in the embodiment of the present application includes the following steps: S1, when the reclosing switch is activated once, the voltage waveform of the power system is collected. If the power supply of the system is not restored, the power failure prediction is carried out.

[0020] In this example, a voltage transformer is installed at each node of the power system, and the voltage waveform of the power system is collected through the voltage transformer. When a fault occurs in the power system, the circuit breaker will trip, disconnect the circuit of the power system, and stop supplying power. Then the reclosing switch will reclose the circuit breaker for the first time to restore the power supply to the power system. If the power supply of the power system is not restored, it is necessary to predict the fault of the power system and locate the fault of the power system. Fault location can quickly identify the location of the fault and reduce the time for operation and maintenance personnel to find the fault point. This is crucial for restoring power supply, especially in the power system. Reducing power outage time can minimize the impact on industry, commerce and residents' lives. Rapid fault location helps to improve the recovery speed of the system and reduce the economic losses caused by the fault. Through accurate fault location, the power company can isolate only the fault area when a fault occurs, instead of shutting down the entire power network or shutting down part of a large area. This can minimize large-scale power outages caused by faults, ensure normal power supply in other areas, and improve the continuity and stability of power supply.

[0021] S2, obtains the cable equipment data and grid load data when a power system failure occurs.

[0022] In this example, the cable equipment data and grid load data are obtained when the power system fails. The cable equipment data refers to the relevant data of the cable equipment when the power system fails, which plays a vital role in fault diagnosis, protection operation and restoration of normal operation. Cable equipment data usually refers to various monitoring data of the cable itself during the operation of the power system, including the insulation performance, aging rate, fault location information, etc. of the cable. When a fault occurs, the cable equipment data can help engineers analyze the cause of the fault, determine the fault location, evaluate the status of the cable, and take corresponding repair measures.

[0023] Acquiring cable equipment data has the following advantages for analyzing power system abnormalities: Real-time monitoring and fault prediction: Acquiring data from cable equipment can enable real-time monitoring of the power system. By real-time monitoring of key parameters such as cable temperature, current, vibration, insulation resistance, etc., potential fault signs can be discovered in time before potential abnormalities occur in the system. This real-time data analysis helps to predict possible faults in cable equipment in advance, avoid sudden shutdowns or damage, and reduce the risk of power outages.

[0024] Early fault detection and location: Cables in power systems are often buried or difficult to observe directly, and traditional detection methods may require shutdown inspections or periodic maintenance. Early fault detection can be achieved by obtaining real-time cable health data combined with artificial intelligence or machine learning technology. By monitoring current, voltage fluctuations, temperature anomalies, etc., the problematic areas in the cable can be quickly located, allowing more accurate repair or replacement measures to be taken.

[0025] Data-driven intelligent diagnosis: Cable equipment data can provide support for intelligent diagnosis based on big data and artificial intelligence. Through long-term accumulated historical data combined with machine learning models, trend prediction and failure mode analysis of cable equipment can be performed. This data-based diagnosis can not only discover potential problems with equipment, but also analyze equipment aging trends and predict the remaining service life of equipment, thereby optimizing the maintenance plan of the power system.

[0026] Optimize maintenance and resource allocation: Comprehensive analysis of cable equipment data can help power companies better manage equipment and allocate resources. For example, by using data to predict the possibility of equipment failure, it is possible to arrange maintenance and replacement plans reasonably to avoid frequent equipment failures. Accurate fault assessment can also reduce unnecessary maintenance work, save operation and maintenance costs, and improve resource utilization efficiency.

[0027] Improve the stability of the power system: The stability and safety of the power system are closely related to the operating status of the equipment. As an important transmission line, the status of the cable has a huge impact on the stability of the system. Through data acquisition and analysis, cable faults or anomalies can be identified and eliminated earlier, avoiding the instability or collapse of the power system caused by cable faults, and ensuring the smooth operation of the power system.

[0028] Help formulate reasonable backup power supply strategies: By analyzing the status data of cable equipment, power companies can accurately assess which parts have potential risks and formulate more reasonable backup power supply and emergency response strategies. For example, if the health of cable equipment is poor, alternative lines or backup equipment can be arranged in advance to ensure that the power system is not affected.

[0029] Improve the intelligence level of power systems: With the development of smart grid technology, more and more power systems are beginning to achieve intelligent management with the help of data collection and analysis technology. The acquisition and analysis of cable equipment data can further improve the intelligence level of the power grid, enabling power companies to manage power facilities in a more efficient and accurate way, reduce manual intervention, and enhance the system's self-repair and self-optimization capabilities.

[0030] Improve equipment life and efficiency: By continuously monitoring the working status of cable equipment, abnormal operating conditions such as overload and overheating can be detected in time, and corresponding measures can be taken to avoid premature aging or damage of equipment, thereby extending the service life of the cable. In addition, monitoring data can also help optimize power transmission efficiency and reduce energy consumption.

[0031] The specific method for obtaining the cable equipment data is as follows: Acquire basic cable insulation data of the cable equipment data, wherein the basic cable insulation data includes the length of the cable, the resistivity of the insulation material, and the cross-sectional area of ​​the cable; The insulation resistance is calculated by measuring the leakage current and leakage voltage of the cable, and the insulation loss factor is obtained based on the insulation resistance and the dielectric loss tangent detection method; The cable insulation performance coefficient is calculated based on the cable insulation performance formula according to the insulation loss factor combined with the basic data of cable insulation; Obtain environmental data, historical operating frequency and historical aging rate to calculate the aging rate of the cable based on the life cycle analysis method; The cable equipment data is calculated based on the cable insulation performance coefficient and the cable aging rate based on the preset cable equipment calculation formula.

[0032] The specific calculation formula of the cable insulation performance coefficient is as follows:

[0033] The specific calculation formula of the aging rate of the cable is as follows:

[0034] The specific calculation formula for the cable equipment data is as follows:

[0035] In the formula, For cable equipment data, is the aging rate of the cable, is the cable insulation performance coefficient, is the cable utilization rate, is the resistivity of the insulating material, is the length of the cable, is the cross-sectional area of ​​the cable, is the insulation loss factor, is the insulation resistance, is the cable insulation utilization rate, is the historical aging rate of the cable, is the temperature of the cable, is the humidity of the cable, is the historical operating frequency.

[0036] It should be noted that the aging rate of cables is usually used to evaluate the performance degradation of cables during long-term use. The aging rate of cables can also be predicted through life cycle analysis. This method usually takes into account multiple factors such as material aging, use environment, and operating frequency to conduct long-term life prediction and aging evaluation. The insulation performance of cable equipment is one of the key factors to ensure its safe and reliable operation. Obtaining these data plays an important role in obtaining cable equipment data.

[0037] Grid load data refers to the power demand and consumption of each part of the power system. These load data are crucial for the safe and stable operation of the power system, especially in the event of a fault, as they can help analyze and evaluate the system's response and provide a basis for restoring power supply.

[0038] Obtaining grid load data has the following advantages for analyzing power system abnormalities: Real-time monitoring and early warning: By acquiring grid load data in real time, the operation status of the grid can be dynamically monitored, and the load conditions of each node can be understood in real time. This data can help system operators find overload, load imbalance or other abnormal conditions. Load data can help predict possible system overload or other abnormalities, provide early warning, and take effective measures to reduce the occurrence of failures.

[0039] Load fluctuation analysis: Analyze load fluctuations. Grid load is usually affected by many factors such as weather, season, time period, etc. By acquiring long-term load data, these fluctuation patterns can be analyzed to help determine whether there are abnormalities or potential faults. If the load data changes suddenly, it may be due to a sudden increase in certain loads or a fault in the grid (such as line failure, equipment failure, etc.). Load data can quickly help identify these sudden changes and facilitate timely response.

[0040] Optimize load distribution: Load balancing. By analyzing the load data of each region and each line, the power system can optimize load distribution to avoid overloading or inefficient operation of certain lines, thereby reducing power loss and improving power supply efficiency. Identify potential bottlenecks. Certain regions or lines in the power grid may become bottlenecks due to excessive load. Through load data analysis, these potential bottlenecks can be discovered and improvements or upgrades can be made in advance.

[0041] Fault diagnosis and location: Detect abnormal loads. When the load data changes are not as expected, there may be a fault in a part of the power system. By monitoring the changes in the load, engineers can quickly locate the fault point. Combined with other data sources: Combining load data with other monitoring data (such as voltage, current, frequency, etc.) can provide more accurate fault diagnosis and help improve the speed and accuracy of fault location.

[0042] Improve grid dispatching efficiency: Assist dispatching decisions. Load data helps grid dispatchers understand power demand and load conditions at each node in real time. By comprehensively analyzing load data, dispatchers can make more appropriate dispatching decisions to ensure a smooth and efficient power supply. Load forecasting and planning: Based on the historical trend of load data and combined with external factors such as weather and holidays, the power system can predict future loads and prepare sufficient spare capacity in advance to avoid power shortages or oversupply.

[0043] Supporting power grid investment and planning: Planning decision support, power grid load data is crucial for long-term planning of the power grid. By analyzing historical load data, it can help planners understand the load demand in different regions and time periods, and optimize the expansion and upgrade plan of the power grid. For equipment upgrades and replacements, load data can also help evaluate the load capacity of existing equipment, guide equipment updates and replacement decisions, and thus improve the overall reliability and efficiency of the power grid.

[0044] Support system stability assessment: Stability analysis, through load data, can be used to analyze the stability of the power system, evaluate the operational stability of the power grid under different load conditions, and predict possible instability risks (such as voltage collapse, frequency fluctuations, etc.). Optimize system configuration, power grid load data can also help evaluate the system's ability to cope with high or extreme loads, and then guide the configuration and investment decisions of power grid facilities.

[0045] The specific method for obtaining the power grid load data is as follows: Obtaining load data of each node and obtaining current load data and power load data based on a load flow calculation method; Obtaining grid frequency data of each node, and obtaining a grid frequency deviation value based on the grid frequency data and a preset grid frequency stability value; The grid frequency fluctuation coefficient is obtained by using the standard deviation calculation method to calculate the grid frequency deviation value; The grid load data is calculated based on the current load data and the power load data in combination with the grid frequency load factor based on a preset grid load calculation formula.

[0046] The specific calculation method of the power grid load data is as follows:

[0047] In the formula, is the grid load data of the i-th node, where i=1,2,3,...,R, R is an integer, N is the number of nodes, is the grid frequency data of the i-th node, is the preset grid frequency stability value, is the current load data of the i-th node, is the power load data of the i-th node.

[0048] It should be noted that the frequency change of the power grid reflects the balance between power supply and demand. If the load demand suddenly increases or decreases, the frequency of the power grid will fluctuate. When the current load data and power load data are getting larger and larger, the power grid load data will become larger and larger, increasing the probability of failure of the power system. Therefore, obtaining the frequency data, current load data and power load data of the power grid plays an important role in calculating the power grid load data.

[0049] S3, construct a power system abnormality assessment model based on machine learning according to the cable equipment data and power grid load data, and generate a power system abnormality assessment coefficient. The specific steps are as follows: Acquire historical cable equipment data and historical power grid load data, and perform preprocessing and normalization operations on the historical cable equipment data and historical power grid load data; Dividing the processed historical cable equipment data and historical power grid load data into a training set and a test set; The model is trained based on the machine learning algorithm using the training set and the weights of the historical cable equipment data and the historical power grid load data are automatically adjusted. By capturing the abnormal relationship between the historical cable equipment data and the historical power grid load data and the power system operation, a power system abnormality assessment model is constructed. The model is then verified and evaluated using the test set to obtain a trained model. The newly acquired cable equipment data and grid load data are input into the trained power system anomaly assessment model to generate the power system anomaly assessment coefficient.

[0050] The specific calculation method of the power system abnormality assessment model is as follows:

[0051] In the formula, is the power system abnormality assessment coefficient, For cable equipment data, is the grid load data, is the cable equipment data weight coefficient, is the weight coefficient of power grid load data.

[0052] It should be noted that the data is preprocessed, normalized, and other operations are performed to ensure its quality and consistency. As the cable equipment data and grid load data become larger and larger, the power system abnormality assessment coefficient also becomes larger and larger.

[0053] S4, according to the collected voltage waveform of the power system, obtain the node area where the voltage waveform is higher than the stable voltage, and obtain the power system abnormality assessment coefficient of the node area where the voltage waveform is higher than the stable voltage. Based on the preset power system safety and stability coefficient, the fault location of the node area is performed. The specific steps are as follows: The collected voltage waveform of the power system is analyzed based on the voltage under stable operation of the power system, and the node areas where the voltage is higher than the stable voltage are marked; Obtain the power system abnormality assessment coefficient of the marked node area, and locate the fault in the node area based on the preset power system safety and stability coefficient; If the power system abnormality assessment coefficient is greater than the power system safety and stability coefficient, the node area is the power system fault area, indicating that the problem causing the power short circuit is on the power system equipment, for example, the insulation performance of the cable fails or the cable ages, or the load of the power grid is too high, causing the equipment to be affected and causing power outage; If the power system abnormality assessment coefficient is less than or equal to the power system safety and stability coefficient, the node area is a transient fault area, and the circuit breaker tripping is not caused by problems within the power system. The occurrence time of transient faults is usually very short, lasting from a few milliseconds to a few seconds. After the fault, the system or equipment will quickly return to normal.

[0054] S5, based on the fault location of the node, determines whether to perform a locking operation on the reclosing switch of the power system. If a locking operation is performed, determines whether the fault has been eliminated by collecting the voltage waveform after maintenance and the power system abnormality assessment coefficient, and automatically turns off the locking operation of the reclosing switch.

[0055] If the fault location of the node area is an instantaneous fault area, there is no need to lock the reclosing switch, and the reclosing switch will automatically reclose after a period of time to restore the power supply of the power system; If the fault location of the node area is the power system fault area, the reclosing switch needs to be locked and the reclosing switch cannot be operated to prevent the reclosing switch from being locked, resulting in frequent automatic reclosing of the faulty line. If the fault is not effectively cleared, the equipment will frequently try to close, which may cause serious damage to the distribution line or electrical equipment (such as circuit breakers, transformers, cables, etc.), and even cause safety hazards such as fire; After the reclosing lock operation is performed, notify the relevant maintenance personnel to check and repair the power system; Collect voltage waveforms after maintenance and power system abnormality assessment coefficients; If the voltage waveform is within the stable voltage and the power system abnormality assessment coefficient is lower than the power system safety stability coefficient, the fault is eliminated and the system automatically turns off the locking operation of the reclosing switch.

[0056] Embodiment 2, Figure 2 The schematic diagram of the structure of the dynamic adjustment system of the reclosing lock based on voltage mutual inductance provided in the embodiment of the present application includes a fault prediction initial module, a data acquisition module, a model building module, a fault location module, and a lock operation module, and there are connections between the modules: The initial fault prediction module is used to collect the voltage waveform of the power system after the reclosing switch is started once, and to predict the power fault if the power supply of the system is not restored; A data acquisition module is used to acquire cable equipment data and grid load data when a power system failure occurs; A model building module is used to build a power system abnormality assessment model based on machine learning according to cable equipment data and power grid load data, and generate a power system abnormality assessment coefficient; A fault location module is used to obtain a node area where the voltage waveform is higher than the stable voltage according to the collected voltage waveform of the power system, obtain a power system abnormality assessment coefficient of the node area where the voltage waveform is higher than the stable voltage, and determine the fault location of the node based on a preset power system safety and stability coefficient; The interlocking control module is used to determine whether to perform an interlocking operation on the power system's reclosing switch according to the fault location of the node. If an interlocking operation is performed, it is used to determine whether the fault has been eliminated by collecting the voltage waveform after maintenance and the power system abnormality assessment coefficient, and automatically close the interlocking operation of the reclosing switch.

[0057] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0058] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product.

[0059] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0060] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0061] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0062] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A dynamic adjustment method for reclosing lockout based on voltage mutual inductance, characterized in that: The steps include: When the reclosing switch is activated once, the voltage waveform of the power system is collected. If the power supply of the system is not restored, the power failure prediction is carried out; Obtain cable equipment data and grid load data when a power system failure occurs; According to the cable equipment data and grid load data, a power system abnormality assessment model is constructed based on machine learning to generate a power system abnormality assessment coefficient; According to the collected voltage waveform of the power system, a node area where the voltage waveform is higher than the stable voltage is obtained, and a power system abnormality assessment coefficient of the node area where the voltage waveform is higher than the stable voltage is obtained; and fault location of the node area is performed based on a preset power system safety and stability coefficient; According to the fault location of the node, the reclosing operation of the power system is judged whether to perform the locking operation. If the locking operation is performed, the voltage waveform after maintenance and the power system abnormality assessment coefficient are collected to determine whether the fault has been eliminated, and the locking operation of the reclosing operation is automatically turned off.

2. The method for dynamic adjustment of reclosing lockout based on voltage mutual inductance according to claim 1 is characterized in that: The specific method for obtaining the cable equipment data is as follows: Acquire basic cable insulation data of the cable equipment data, wherein the basic cable insulation data includes the length of the cable, the resistivity of the insulation material, and the cross-sectional area of ​​the cable; The insulation resistance is calculated by measuring the leakage current and leakage voltage of the cable, and the insulation loss factor is obtained based on the insulation resistance and the dielectric loss tangent detection method; The cable insulation performance coefficient is calculated based on the cable insulation performance formula according to the insulation loss factor combined with the basic data of cable insulation; Obtain environmental data, historical operating frequency and historical aging rate to calculate the aging rate of the cable based on the life cycle analysis method; The cable equipment data is calculated based on the cable insulation performance coefficient and the cable aging rate based on the preset cable equipment calculation formula.

3. The method for dynamic adjustment of reclosing lockout based on voltage mutual inductance according to claim 1, characterized in that: The specific method for obtaining the power grid load data is as follows: Obtaining load data of each node and obtaining current load data and power load data based on a load flow calculation method; Obtaining grid frequency data of each node, and obtaining a grid frequency deviation value based on the grid frequency data and a preset grid frequency stability value; The grid frequency fluctuation coefficient is obtained by using the standard deviation calculation method to calculate the grid frequency deviation value; The grid load data is calculated based on the current load data and the power load data in combination with the grid frequency load factor based on a preset grid load calculation formula.

4. The method for dynamic adjustment of reclosing lockout based on voltage mutual inductance according to claim 1, characterized in that: The specific steps of constructing a power system abnormality assessment model based on machine learning according to the cable equipment data and the power grid load data and generating a power system abnormality assessment coefficient are as follows: Acquire historical cable equipment data and historical power grid load data, and perform preprocessing and normalization operations on the historical cable equipment data and historical power grid load data; Dividing the processed historical cable equipment data and historical power grid load data into a training set and a test set; The model is trained based on the machine learning algorithm using the training set and the weights of the historical cable equipment data and the historical power grid load data are automatically adjusted. By capturing the abnormal relationship between the historical cable equipment data and the historical power grid load data and the power system operation, a power system abnormality assessment model is constructed. The model is then verified and evaluated using the test set to obtain a trained model. The newly acquired cable equipment data and grid load data are input into the trained power system anomaly assessment model to generate the power system anomaly assessment coefficient.

5. The method for dynamic adjustment of reclosing lockout based on voltage mutual inductance according to claim 1, characterized in that: The power system abnormality assessment coefficient of the node area where the voltage waveform is higher than the stable voltage is obtained, and the fault location of the node area is performed based on the preset power system safety and stability coefficient. The specific steps are as follows: The collected voltage waveform of the power system is analyzed based on the voltage under stable operation of the power system, and the node areas where the voltage is higher than the stable voltage are marked; Obtain the power system abnormality assessment coefficient of the marked node area, and locate the fault in the node area based on the preset power system safety and stability coefficient; If the power system abnormality assessment coefficient is greater than the power system safety and stability coefficient, the node area is the power system fault area; If the power system abnormality assessment coefficient is less than or equal to the power system safety and stability coefficient, the node area is an instantaneous fault area.

6. The method for dynamic adjustment of reclosing lockout based on voltage mutual inductance according to claim 1, characterized in that: The method of determining whether to perform a locking operation on the reclosing switch of the power system according to the fault location of the node, and if a locking operation is performed, determining whether the fault is eliminated by collecting the voltage waveform after maintenance and the abnormal evaluation coefficient of the power system, and automatically closing the locking operation of the reclosing switch, the specific steps are as follows: If the fault location of the node area is an instantaneous fault area, there is no need to lock the reclosing switch, and the reclosing switch will automatically reclose after a period of time to restore the power supply of the power system; If the fault location of the node area is the power system fault area, the reclosing operation needs to be performed; After the reclosing lock operation is performed, notify the relevant maintenance personnel to check and repair the power system; Collect voltage waveforms after maintenance and power system abnormality assessment coefficients; If the voltage waveform is within the stable voltage and the power system abnormality assessment coefficient is lower than the power system safety stability coefficient, the fault is eliminated and the system automatically turns off the locking operation of the reclosing switch.

7. The method for dynamic adjustment of reclosing lockout based on voltage mutual inductance according to claim 2, characterized in that: The specific calculation formula of the cable insulation performance coefficient is as follows: The specific calculation formula of the aging rate of the cable is as follows: The specific calculation formula for the cable equipment data is as follows: In the formula, For cable equipment data, is the aging rate of the cable, is the cable insulation performance coefficient, is the cable utilization rate, is the resistivity of the insulating material, is the length of the cable, is the cross-sectional area of ​​the cable, is the insulation loss factor, is the insulation resistance, is the cable insulation utilization rate, is the historical aging rate of the cable, is the temperature of the cable, is the humidity of the cable, is the historical operating frequency.

8. The method for dynamic adjustment of reclosing lockout based on voltage mutual inductance according to claim 3, characterized in that: The specific calculation method of the power grid load data is as follows: In the formula, is the grid load data of the i-th node, where i=1,2,3,...,R, R is an integer, N is the number of nodes, is the grid frequency data of the i-th node, is the preset grid frequency stability value, is the current load data of the i-th node, is the power load data of the i-th node.

9. The method for dynamic adjustment of reclosing lockout based on voltage mutual inductance according to claim 4, characterized in that: The specific calculation method of the power system abnormality assessment model is as follows: In the formula, is the power system abnormality assessment coefficient, For cable equipment data, is the grid load data, is the cable equipment data weight coefficient, is the weight coefficient of power grid load data.

10. A system using the voltage mutual inductance-based reclosing lockout dynamic adjustment method according to any one of claims 1 to 9, characterized in that: It includes the fault prediction initial module, data acquisition module, model building module, fault location module, and locking control module. There are connections between the modules: The initial fault prediction module is used to collect the voltage waveform of the power system after the reclosing switch is started once, and to predict the power fault if the power supply of the system is not restored; A data acquisition module is used to acquire cable equipment data and grid load data when a power system failure occurs; A model building module is used to build a power system abnormality assessment model based on machine learning according to cable equipment data and power grid load data, and generate a power system abnormality assessment coefficient; A fault location module is used to obtain a node area where the voltage waveform is higher than the stable voltage according to the collected voltage waveform of the power system, obtain a power system abnormality assessment coefficient of the node area where the voltage waveform is higher than the stable voltage, and determine the fault location of the node based on a preset power system safety and stability coefficient; The interlocking control module is used to determine whether to perform an interlocking operation on the power system's reclosing switch according to the fault location of the node. If an interlocking operation is performed, it is used to determine whether the fault has been eliminated by collecting the voltage waveform after maintenance and the power system abnormality assessment coefficient, and automatically close the interlocking operation of the reclosing switch.

Images