66kV distributed arc suppression coil intelligent centralized control method and system based on multi-source data fusion

Abstract

The invention discloses a 66kV distributed arc suppression coil intelligent centralized control method and system based on multi-source data fusion, and the method is characterized in that the method comprises the following steps: constructing a distributed arc suppression coil intelligent centralized control system, and collecting control data in real time; an improved vector superposition method is adopted to calculate the capacitance current of each feeder line, and a multi-objective optimization model is established by using control data; solving the multi-objective optimization model by adopting a genetic algorithm to obtain an optimal resistance value combination; and the optimal resistance value combination is issued to each arc suppression coil controller through the communication module, and intelligent centralized control of the distributed arc suppression coils is implemented.

Description

Technical Field

[0001] The present invention relates to a field, and more specifically, to a 66kV distributed arc suppression coil intelligent centralized control method and system based on multi-source data fusion. Background Art

[0002] According to the "Technical Specifications for Overvoltage Protection Design of Power Equipment," 66kV systems must be equipped with arc suppression coils when the capacitive current exceeds 10A due to a single-phase ground fault. With the continued renovation and development of 66kV systems in Northeast China and Inner Mongolia, the cabling rate has gradually increased, and the system's capacitive current levels have also gradually increased. The capacity of a single arc suppression coil is insufficient to meet the system's compensation requirements. Therefore, most systems use multiple arc suppression coils for distributed compensation, located within the 66kV substation. This compensation method has led to some control challenges.

[0003] First, the inappropriate damping resistor value configured for each arc suppression coil causes the displacement voltage to exceed operating requirements or affects the measurement of the system's capacitive current. If the resistance value is too small, the displacement voltage easily exceeds the allowable range, while if the resistance value is too large, it will affect the arc suppression coil assembly's ability to accurately measure the system's capacitive current.

[0004] Secondly, in systems with multiple arc suppression coils, the lack of communication between the coils results in inaccurate measurements of the system's ground capacitance current. This limitation restricts the system's automated operation, forcing engineers to manually set the coils to a higher detuning setting to suppress displacement voltage and prevent system resonance. However, this mode of operation results in excessive residual current in the system during a single-phase ground fault, preventing effective arc extinguishing and potentially causing widespread damage.

[0005] Furthermore, because distribution network systems operate in a controlled open-loop system, they often lack data acquisition systems. This means there's no early warning mechanism before a fault occurs, and afterward, fault cause analysis is difficult. By establishing a centralized control system, comprehensive data can be leveraged to provide fault warnings and analyze fault types, thereby increasing system operational safety.

[0006] Among the existing solutions, patent CN101453118B adopts a distributed one-control-multiple architecture, connecting the upper and lower computers through the CAN bus, but does not integrate the grid topology data. As a result, the damping resistor configuration relies only on local information and cannot globally optimize the resistance value.

[0007] Patent CN111817433A monitors multiple arc suppression coils and small resistors through the CAN bus, but data cannot be shared between subsystems (such as feeder parameters and tower models), resulting in a capacitance current calculation error of more than 20%, affecting tuning accuracy.

[0008] Patent CN102931651A uses fiber-optic communication to improve transmission speed, but it is still limited to the real-time status exchange of a single arc suppression coil and does not solve the problem of coordinated calculation of multiple arc suppression coils. For example, the parameters of arc suppression coils in different locations cannot be integrated, resulting in an overly conservative setting of the system detuning degree (>15%) and excessive residual current.

[0009] Existing systems separate the communication module from the computational module, resulting in a disconnect between data acquisition and decision execution. For example, damping resistor adjustments lag behind grid state changes. Existing systems fail to integrate grid topology, such as switch status and feeder length, with equipment parameters like grounding transformer capacity. This prevents the construction of an accurate system electrical model, leading to optimization results that deviate from actual operating conditions. Existing systems also lack centralized data analysis capabilities and rely solely on threshold alarms, failing to provide early warning and fault type identification.

[0010] In response to the above problems, there is an urgent need for an intelligent centralized control method and system for 66kV distributed arc suppression coils based on multi-source data fusion. Summary of the Invention

[0011] In order to solve the deficiencies in the prior art, the present invention provides a 66kV distributed arc suppression coil intelligent centralized control method and system based on multi-source data fusion.

[0012] The present invention adopts the following technical solutions.

[0013] The first aspect of the present invention relates to a 66kV distributed arc suppression coil intelligent centralized control method based on multi-source data fusion, the method comprising the following steps: constructing a distributed arc suppression coil intelligent centralized control system to collect control data in real time; using an improved vector superposition method to calculate the capacitance current of each feeder, and using the control data to establish a multi-objective optimization model; using a genetic algorithm to solve the multi-objective optimization model to obtain an optimal resistance combination; and sending the optimal resistance combination to each arc suppression coil controller through a communication module to implement intelligent centralized control of the distributed arc suppression coil.

[0014] Construct a distributed arc suppression coil intelligent centralized control system to collect control data in real time, including: integrated CAN bus, fiber optic Ethernet and wireless transmission interface, and communication connection between the arc suppression coil controller and the substation SCADA system.

[0015] Construct a distributed arc suppression coil intelligent centralized control system to collect control data in real time, including:

[0016] The control data includes grid topology parameters, equipment operating parameters and environmental parameters; the grid topology parameters include system grid structure, switch position status, feeder length and specifications, and distributed arc suppression coil specifications; the equipment operating parameters include the access position of each arc suppression coil, gear information, grounding transformer capacity, and current damping resistance value; the environmental parameters include tower height and grounding resistance measurement value.

[0017] An improved vector superposition method is used to calculate the capacitive current of each feeder, and a multi-objective optimization model is established using control data, including:

[0018] The sum of the capacitive currents of the feeders is:

[0019]

[0020] Where i is the number of the distributed arc suppression coil, n is the number of distributed arc suppression coils,

[0021] k i is the distribution coefficient of the arc suppression coil, L i is the feeder length of the feeder where the arc suppression coil is located,

[0022] U ph is the phase voltage, and are the equivalent capacitive reactance and inductive reactance of the feeder where the arc suppression coil is located.

[0023] An improved vector superposition method is used to calculate the capacitive current of each feeder, and a multi-objective optimization model is established using control data, including:

[0024] The objective function of the multi-objective optimization model is:

[0025]

[0026] Where R is the damping resistance of the arc suppression coil,

[0027] F(·,·) is the displacement voltage of the arc suppression coil.

[0028] The optimal resistance combination is sent to each arc suppression coil controller through the communication module to implement intelligent centralized control of the distributed arc suppression coils, including: calculating the minimum safe detuning degree based on the real-time capacitance and current values ​​and the critical resonance conditions; dynamically adjusting the arc suppression coil gear to control the detuning degree within the minimum safe detuning degree range.

[0029] Capture the 3rd to 7th harmonic components of the zero-sequence current, extract the waveform distortion rate and mutation amount; use the pre-built convolutional neural network model to output the fault probability and classification results.

[0030] The second aspect of the present invention relates to a 66kV distributed arc suppression coil intelligent centralized control system based on multi-source data fusion, which is implemented using the method of the first aspect of the present invention; the system includes a construction module, an optimization module, a solution module, and a control module; the construction module is used to construct a distributed arc suppression coil intelligent centralized control system and collect control data in real time; the optimization module is used to calculate the capacitive current of each feeder using an improved vector superposition method, and establish a multi-objective optimization model using control data; the solution module is used to solve the multi-objective optimization model using a genetic algorithm to obtain an optimal resistance combination; the control module is used to send the optimal resistance combination to each arc suppression coil controller through a communication module to implement intelligent centralized control of the distributed arc suppression coils.

[0031] A third aspect of the present invention relates to a terminal, comprising a processor and a storage medium; the storage medium is used to store instructions; and the processor is used to operate according to the instructions to execute the steps of the method described in the first aspect of the present invention.

[0032] A fourth aspect of the present invention relates to a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in the first aspect of the present invention.

[0033] The beneficial effect of the present invention is that, compared with the prior art, the present invention provides a method and system for intelligent centralized control of 66kV distributed arc suppression coils based on multi-source data fusion. By enabling distributed compensation arc suppression coil systems to communicate with each other, unified management of each arc suppression coil is achieved, allowing the resistance value of the damping resistor to be reasonably adjusted, thereby improving the measurement accuracy of the ground capacitance current. The centralized control system for 66kV distributed compensation arc suppression coils proposed by the present invention solves a series of problems existing in the prior art, improves the operational stability and safety of the power system, and has high practical value and promotion prospects.

[0034] The beneficial effects of the present invention also include:

[0035] This invention proposes a centralized control system that deeply integrates communication and computing functions, breaking through the information barriers of distributed arc suppression coils and achieving global parameter optimization and active safety protection. Through automatic tuning, the system can more accurately control the detuning degree of the arc suppression coils, reducing residual current during single-phase grounding faults and improving arc extinguishing effectiveness.

[0036] 2. The centralized control system also has data collection and analysis capabilities, enabling real-time monitoring of the system's operating status, fault warnings, and fault type analysis. This will help improve the operational safety of the distribution network and reduce the risk of equipment damage and casualties caused by faults. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 Schematic diagram of the intelligent centralized control method for arc suppression coils of the present invention;

[0038] Figure 2 A schematic diagram of calculating capacitor current according to the present invention;

[0039] Figure 3 A schematic diagram of calculating the detuning degree according to the present invention;

[0040] Figure 4 A schematic diagram of fault detection according to the present invention;

[0041] Figure 5 This is the system overview interface diagram. DETAILED DESCRIPTION

[0042] In order to make the purpose, technical solutions and advantages of the present invention clearer and more accurate, the technical solutions of the present invention are described in detail below through multiple specific embodiments. The embodiments used in the present invention are only used to explain the present invention and are not intended to limit the content of the present invention.

[0043] The present invention proposes a centralized control system that deeply integrates communication and computing functions, breaks through the information barriers of distributed arc suppression coils, and realizes global parameter optimization and active safety protection. The system realizes unified management of each arc suppression coil by enabling the distributed compensation arc suppression coil systems to communicate with each other, so that the resistance value of the damping resistor can be reasonably adjusted, thereby improving the measurement accuracy of the ground capacitance current. At the same time, through the automatic tuning function, the system can more accurately control the detuning degree of the arc suppression coil, reduce the residual current during single-phase grounding faults, and improve the arc extinguishing effect. The centralized control system of the 66kV distributed compensation arc suppression coil proposed in the present invention solves a series of problems existing in the prior art, improves the operating stability and safety of the power system, and has high practical value and promotion prospects.

[0044] Figure 1 Schematic diagram of the arc suppression coil intelligent centralized control method of the present invention. Figure 1 The first aspect of the present invention relates to a 66kV distributed arc suppression coil intelligent centralized control method based on multi-source data fusion, the method comprising the following steps:

[0045] Step 1: Construct a distributed arc suppression coil intelligent centralized control system to collect control data in real time.

[0046] The multi-protocol communication unit integrates CAN bus, fiber-optic Ethernet, and wireless transmission interfaces, making it compatible with existing arc suppression coil controllers (sub-nodes) and substation SCADA systems. The data integration unit collects and stores the following data in real time: grid topology parameters (system grid structure diagram, switch position status, feeder length and specifications (cross-sectional area, insulation grade); equipment operating parameters (arc suppression coil connection location, gear information, grounding transformer capacity, current damping resistor value); and environmental parameters (pole tower height, grounding resistance measurement). A dynamic database builds a grid electrical model based on time-series data, supporting updates within seconds.

[0047] Step 2: Use the improved vector superposition method to calculate the capacitive current of each feeder and establish a multi-objective optimization model using the control data.

[0048] Figure 2 Schematic diagram of the present invention for calculating the capacitor current. Figure 2 , an improved vector superposition method is used to calculate the capacitive current of each feeder, and a multi-objective optimization model is established using control data, including:

[0049] The sum of the capacitive currents of the feeders is:

[0050]

[0051] Where i is the number of the distributed arc suppression coil, n is the number of distributed arc suppression coils,

[0052] k i is the distribution coefficient of the arc suppression coil, which is calculated from the grid topology parameters. i The feeder length of the arc suppression coil is calculated based on the feeder length and specifications, feeder location, voltage level, and feeder power transmission per unit time.

[0053] U ph is the phase voltage, and are the equivalent capacitive reactance and inductive reactance of the feeder where the arc suppression coil is located.

[0054] An improved vector superposition method is used to calculate the capacitive current of each feeder, and a multi-objective optimization model is established using control data, including:

[0055] The objective function of the multi-objective optimization model is:

[0056]

[0057] Where R is the damping resistance of the arc suppression coil,

[0058] F(·,·) is the displacement voltage of the arc suppression coil.

[0059] In one embodiment, It is calculated based on the asymmetric voltage at the neutral point of the power grid when the arc suppression coil stops operating, the detuning degree of the power grid or a single coil, and the power grid damping rate.

[0060] The constraints of the multi-objective optimization model include the resistance range of the damping resistor R min ≤R≤R max .

[0061] Step 3: Use genetic algorithm to solve the multi-objective optimization model and obtain the optimal resistance value combination.

[0062] Figure 4 FIG. 1 is a schematic diagram of fault detection of the present invention. Figure 4 , a genetic algorithm is used to solve the optimal resistance combination, and it is sent to each arc suppression coil controller through the communication module.

[0063] Genetic Algorithm (GA) is a computational model of biological evolution that simulates the natural selection and genetic mechanisms of Darwin's theory of biological evolution. It is a method of searching for the optimal solution by simulating the natural evolution process.

[0064] Its main features are that it operates directly on structural objects without any restrictions on derivatives and function continuity; it has inherent implicit parallelism and better global optimization capabilities; it adopts a probabilistic optimization method, which can automatically obtain and guide the optimized search space without the need for definite rules, and adaptively adjust the search direction.

[0065] Genetic algorithms use all individuals in a population as their target and utilize randomization techniques to guide efficient searches within an encoded parameter space. Selection, crossover, and mutation constitute the genetic operations of a genetic algorithm; while parameter encoding, initial population setting, fitness function design, genetic operation design, and control parameter setting comprise the core of the genetic algorithm.

[0066] Genetic algorithms start with a population that represents a set of potential solutions to a problem, and a population consists of a certain number of individuals encoded by genes. Each individual is actually an entity with characteristics on its chromosome.

[0067] After the initial population is generated, it evolves generation by generation, following the principles of survival of the fittest, producing increasingly better approximate solutions. In each generation, individuals are selected based on their fitness within the problem domain, and crossover and mutation are performed using genetic operators from natural genetics to produce a population representing a new set of solutions. This process results in subsequent generations of populations becoming more adaptable to the environment than their predecessors, much like natural evolution. The best individuals in the final generation, after decoding, can be used as approximate optimal solutions to the problem.

[0068] The basic operation process of genetic algorithm is as follows:

[0069] (1) Initialization: Set the evolutionary generation counter t = 0, set the maximum evolutionary generation T, and randomly generate M individuals as the initial population P(0).

[0070] (2) Individual evaluation: Calculate the fitness of each individual in the population P(t).

[0071] (3) Selection operation: The selection operator is applied to the population. The purpose of selection is to directly pass on the optimized individuals to the next generation or to generate new individuals through pairing and crossover and then pass them on to the next generation. The selection operation is based on the fitness evaluation of individuals in the population.

[0072] (4) Crossover operation: Apply the crossover operator to the population. The crossover operator plays a core role in the genetic algorithm.

[0073] (5) Mutation operation: Apply the mutation operator to the population. This means changing the gene values ​​at certain loci of the individual strings in the population. After the population P(t) undergoes selection, crossover, and mutation operations, the next generation population P(t+1) is obtained.

[0074] (6) Termination condition judgment: If t = T, the individual with the maximum fitness obtained in the evolution process is output as the optimal solution and the calculation is terminated.

[0075] Genetic operations include the following three basic genetic operators: selection; crossover; and mutation.

[0076] Genetic algorithm is used to adjust the control parameters of each arc suppression coil and calculate the optimal resistance combination.

[0077] Step 4: Send the optimal resistance combination to each arc suppression coil controller through the communication module to implement intelligent centralized control of the distributed arc suppression coils.

[0078] Figure 3 Schematic diagram of calculating detuning degree in the present invention. Figure 3 , calculate the minimum safe detuning degree according to the real-time capacitance current value and the resonance critical condition:

[0079]

[0080] Dynamically adjust the arc suppression coil gear to control the detuning degree within v min Within ±2%.

[0081] Fault warning and type identification uses high-frequency transient signal analysis to capture the 3rd to 7th harmonic components of the zero-sequence current, extracting features such as waveform distortion rate and mutation rate. A convolutional neural network (CNN) model is used to output fault probability and classification results. The CNN training samples include fault types such as arc grounding and metal grounding.

[0082] Figure 5 This is the system overview interface diagram. Figure 5 The second aspect of the present invention relates to a 66kV distributed arc suppression coil intelligent centralized control system based on multi-source data fusion, which is implemented using the method of the first aspect of the present invention; the system includes a construction module, an optimization module, a solution module, and a control module; the construction module is used to construct a distributed arc suppression coil intelligent centralized control system and collect control data in real time; the optimization module is used to calculate the capacitive current of each feeder using an improved vector superposition method, and establish a multi-objective optimization model using control data; the solution module is used to solve the multi-objective optimization model using a genetic algorithm to obtain an optimal resistance combination; the control module is used to send the optimal resistance combination to each arc suppression coil controller through the communication module to implement intelligent centralized control of the distributed arc suppression coil.

[0083] The display interface module supports human-computer interaction, visually displaying the real-time grid topology, arc suppression coil operating status (gear position, damping resistance value), and early warning information. Interactive functions include parameter threshold modification, manual gear adjustment command issuance, and historical fault data review.

[0084] Through multi-source data fusion and dynamic database construction, this invention improves capacitor current calculation accuracy by 40%, supporting precise tuning. Globally optimized damping resistor configuration ensures that the displacement voltage does not exceed the 2% limit. Dynamic detuning adjustment controls the residual current of single-phase grounding faults to less than 5A, shortening the arc extinguishing time to 0.3 seconds. Fault warning accuracy is ≥90%, and type identification accuracy is ≥95%, significantly enhancing the grid's active defense capabilities.

[0085] The algorithm design of the functional calculation module depends on the specific data structure of the data summary module (such as the association mapping between feeder parameters and arc suppression coil positions). If it is separated from the communication architecture of this system (such as only using the CAN bus or optical fiber communication in the comparison document), the same precision optimization cannot be achieved.

[0086] The hardware configuration of the embodiment includes: a data aggregation module deployed in the substation control room, using an industrial-grade multi-protocol gateway (model: MOXA IG902); a functional computing module based on an ARM Cortex-A72 processor and equipped with a Linux real-time operating system; and a display interface module connected to a monitoring terminal (resolution: 1920×1080) via an HDMI interface.

[0087] The arc suppression coil controller (sub-node) uploads gear position and current data every 100ms via the CAN bus; the SCADA system transmits switch status and grid topology change information via the Modbus TCP protocol; the data aggregation module updates the dynamic database every 1 second, triggering the functional calculation module to optimize the process.

[0088] During the damping resistance optimization process, the data aggregation module obtains the current grid topology (total feeder length 25km, grounding transformer capacity 500kVA); the function calculation module calculates the capacitance current; and the genetic algorithm solves the optimal damping resistance to meet U0 = 1.8% U ph ; The command is sent to each arc suppression coil through optical fiber, the resistance is adjusted to the target value, and the execution result is fed back.

[0089] The zero-sequence current sensor detected a sudden change signal (peak amplitude 120A, duration 0.1s); the CNN model extracted the harmonic components (5th harmonic accounted for 15%, waveform distortion rate 8%); the output fault type was "intermittent arc grounding" (probability 92%), triggering an early warning and recording it in the database.

[0090] The system completes the analysis of the current power grid topology by real-time analysis of the remote signaling and telemetry signals of the power grid equipment, the action signals of the security and control system, the operating conditions of the equipment, and the specific changes in the power grid model. When the power grid topology changes, it can control the action of the arc suppression coil in the power grid, collect current data at different gears, and then calculate the capacitance current value of the power grid, and control the gear adjustment of the arc suppression coil to accurately compensate for the capacitance current of the system.

[0091] Figure 5The interface provides a system overview, organized around a prefecture-level power supply company. Each small box represents an independent 66kV system (note: the system, not the substation). Clicking on each system brings you to the corresponding secondary interface. Three alarm lights are located under each system, allowing operators to easily understand the system's operating status. These lights indicate equipment alarms, system alarms, and operational alarms. All alarms flash when triggered by an abnormality. Hovering the mouse over an alarm displays the alarm message, which can be reset by clicking it.

[0092] The warning lights are as follows: abnormal arc suppression coil status, mainly refers to abnormalities in the arc suppression coil body or its control unit, such as controller power failure, mechanism refusal to operate, gas alarm, etc. The arc suppression coil manufacturer can provide abnormal information. System abnormality, mainly refers to system capacitor current exceeding the starting threshold, system capacitor current capacity exceeding the compensation capacity, displacement voltage out of range, grounding alarm, etc. Operation abnormality alarm: When the intelligent centralized control system fails to operate, the system should be locked and the arc suppression coil should be switched to manual operation.

[0093] A third aspect of the present invention relates to a terminal, comprising a processor and a storage medium; the storage medium is used to store instructions; and the processor is used to operate according to the instructions to execute the steps of the method described in the first aspect of the present invention.

[0094] A fourth aspect of the present invention relates to a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in the first aspect of the present invention.

[0095] Finally, it should be noted that the above embodiments are intended only to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art will appreciate that the technical solutions of the present invention still include modifications or equivalent substitutions that may be made to the specific embodiments of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention are intended to be covered by the claims of the present invention.

Claims

1. A 66kV distributed arc suppression coil intelligent centralized control method based on multi-source data fusion, characterized in that: The method comprises the following steps: Construct a distributed arc suppression coil intelligent centralized control system to collect control data in real time; An improved vector superposition method is used to calculate the capacitive current of each feeder, and a multi-objective optimization model is established using control data. Genetic algorithm is used to solve the multi-objective optimization model to obtain the optimal resistance value combination; The optimal resistance combination is sent to each arc suppression coil controller through the communication module to implement intelligent centralized control of the distributed arc suppression coils.

2. The intelligent centralized control method for 66kV distributed arc suppression coils based on multi-source data fusion according to claim 1 is characterized in that: The distributed arc suppression coil intelligent centralized control system is constructed to collect control data in real time, including: Integrates CAN bus, optical fiber Ethernet and wireless transmission interfaces to connect arc suppression coil controller and substation SCADA system.

3. The intelligent centralized control method for 66kV distributed arc suppression coils based on multi-source data fusion according to claim 2 is characterized in that: The structure of the distributed arc suppression coil intelligent centralized control system collects control data in real time, including: The control data includes power grid topology parameters, equipment operation parameters and environmental parameters; The grid topology parameters include system grid structure, switch position status, feeder length and specifications, and distributed arc suppression coil specifications; The equipment operating parameters include the connection position of each arc suppression coil, gear information, grounding transformer capacity, and current damping resistor value; The environmental parameters include tower height and ground resistance measurement value.

4. The intelligent centralized control method for 66kV distributed arc suppression coils based on multi-source data fusion according to claim 3 is characterized by: The improved vector superposition method is used to calculate the capacitance current of each feeder, and the control data is used to establish a multi-objective optimization model, including: The sum of the capacitive currents of the feeders is: Where i is the number of the distributed arc suppression coil, n is the number of distributed arc suppression coils, k i is the distribution coefficient of the arc suppression coil, L i is the feeder length of the feeder where the arc suppression coil is located, U ph is the phase voltage, and are the equivalent capacitive reactance and inductive reactance of the feeder where the arc suppression coil is located.

5. The intelligent centralized control method for 66kV distributed arc suppression coils based on multi-source data fusion according to claim 4 is characterized in that: The improved vector superposition method is used to calculate the capacitance current of each feeder, and the control data is used to establish a multi-objective optimization model, including: The objective function of the multi-objective optimization model is: Where R is the damping resistance of the arc suppression coil, F(·,·) is the displacement voltage of the arc suppression coil.

6. The intelligent centralized control method for 66kV distributed arc suppression coils based on multi-source data fusion according to claim 5 is characterized in that: The optimal resistance combination is sent to each arc suppression coil controller through the communication module to implement intelligent centralized control of the distributed arc suppression coils, including: Calculate the minimum safe detuning degree based on the real-time capacitance current value and the resonance critical condition; Dynamically adjust the arc suppression coil gear to control the detuning degree within the minimum safe detuning degree range.

7. The intelligent centralized control method for 66kV distributed arc suppression coils based on multi-source data fusion according to claim 6 is characterized in that: Capture the 3rd to 7th harmonic components of zero-sequence current and extract waveform distortion rate and mutation amount; Use the pre-built convolutional neural network model to output the fault probability and classification results.

8. A 66kV distributed arc suppression coil intelligent centralized control system based on multi-source data fusion, characterized by: Implemented by the method according to any one of claims 1 to 7; The system includes a construction module, an optimization module, a solution module, and a control module; The construction module is used to construct a distributed arc suppression coil intelligent centralized control system to collect control data in real time; The optimization module is used to calculate the capacitance current of each feeder using an improved vector superposition method and establish a multi-objective optimization model using control data; The solving module is used to solve the multi-objective optimization model using a genetic algorithm to obtain the optimal resistance value combination; The control module is used to send the optimal resistance combination to each arc suppression coil controller through the communication module, and implement intelligent centralized control of the distributed arc suppression coils.

9. A terminal comprising a processor and a storage medium; characterized in that: The storage medium is used to store instructions; The processor is configured to operate according to the instructions to execute the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images