Power transmission line visual multi-terminal collaborative inspection method and system based on electric red-ong system

Abstract

The invention relates to the technical field of power transmission line protection, and discloses a power transmission line visual multi-terminal cooperative inspection method and system based on an electric red-ong system, and the method comprises the steps: obtaining a predicted current value according to a load type and a real-time current value, judging whether to carry out the open-circuit protection or not according to the predicted current value, and when the open-circuit protection needs to be carried out, carrying out the open-circuit protection according to the predicted current value. And if the predicted current value is greater than the preset current value, calling a corresponding circuit breaker flapping graph, performing simulation according to the predicted current value and the circuit breaker flapping graph to obtain an initial breaking time sequence, then calculating a fault influence coefficient according to the real-time monitoring data, and adjusting the initial breaking time sequence according to the fault influence coefficient to obtain a target breaking time sequence. And the extension structure of the circuit breaker is considered, so that a corresponding circuit breaking sequence is formed, and the reliability of a power grid system during operation is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power transmission line protection, more particularly, the present application relates to a power transmission line visualized multi-terminal cooperative inspection method and system based on an electric Hong system. BACKGROUND

[0002] The electric Hong system is widely used in various aspects of power production. Through the monitoring and data acquisition of power equipment terminals, data can be interacted on the network through a unified communication protocol, thereby improving data processing capacity and maintaining dynamic balance of power consumption and power generation. The application of the electric Hong system can reduce the work burden of grass-roots operation and maintenance personnel, and greatly improve the efficiency and safety through centralized, remote and batch equipment control and maintenance.

[0003] The electric Hong system has the advantages of high efficiency, safety and reliability, and has completely changed the operation mode of traditional power grids, providing an innovative solution for the rational allocation and utilization of energy. In the process of ensuring the stable operation of smart grids, various new devices and technologies are introduced into power transmission lines, among which the intelligent circuit breaker plays a crucial role as a key technology. The intelligent circuit breaker not only can automatically monitor, control and protect the power transmission line, but also realizes remote control function, providing strong support for the intelligent management of power transmission lines. Although the existing technology has covered many related contents about circuit breakers, there are still some deficiencies.

[0004] For example, the Chinese patent with publication number CN116260119A provides a circuit data identification circuit breaker protection method and system, which matches the circuit breaker in the wake-up state based on the abnormal positioning result, and sends circuit control information to the matched circuit breaker, then receives circuit control response information, and completes the circuit protection processing of abnormal data based on the circuit control response information. The Chinese patent with publication number CN111371077A provides a protection control method for a flexible intelligent distribution network suitable for multiple fault types, which can effectively isolate the fault point when the distribution network occurs short circuit and broken line fault.

[0005] Although the existing technology can realize the basic protection of the circuit relying on the circuit breaker, in the actual power grid scene, multiple circuit breakers are often distributed at each node, which form a complex power grid topology structure. However, the current scheme does not effectively visualize the topology structure when the power transmission line fails, which cannot assist the operation and maintenance personnel to intuitively master the connection logic and topology association between the circuit breakers, and does not develop a scientific circuit priority order based on the topology characteristics, but directly synchronously disconnects multiple circuit breakers. This operation lacking of topology consideration and visualization support will cause sudden changes in the power grid operation state, destroy the stability of the system operation, and ultimately significantly reduce the operation reliability of the entire power grid.

[0006] In view of this, the application proposes a power transmission line visualized multi-terminal cooperative inspection method and system based on an electric Hong system to solve the above problems. SUMMARY

[0007] In order to overcome the above-mentioned defects of the prior art, the application provides a power transmission line visualized multi-terminal cooperative inspection method and system based on an electric Hong system.

[0008] To achieve the above object, the application provides the following technical scheme:

[0009] In the first aspect, the power transmission line visualized multi-terminal cooperative inspection method based on the electric Hong system comprises:

[0010] Obtaining real-time current information and real-time current value, determining the corresponding load type based on the real-time current information, and obtaining the predicted current value according to the load type and the real-time current value;

[0011] According to the predicted current value, it is judged whether to perform circuit breaking protection, when the circuit breaking protection is needed, the corresponding circuit breaker topology diagram is called, simulation is performed according to the predicted current value and the circuit breaker topology diagram, and the initial breaking time sequence is obtained;

[0012] Obtaining real-time monitoring data of Q circuit breakers in the circuit breaker topology diagram, calculating the fault influence coefficient according to the real-time monitoring data, adjusting the initial breaking time sequence according to the fault influence coefficient to obtain the target breaking time sequence, and outputting the target breaking time sequence diagram for visual display, so as to facilitate the operation and maintenance personnel to intuitively master the breaking time sequence between the circuit breakers and ensure the stability of the power system.

[0013] Further, the method of simulating according to the predicted current value and the circuit breaker topology diagram to obtain the initial breaking time sequence comprises:

[0014] Obtaining the short-circuit impedance value corresponding to each line in the circuit breaker topology diagram and the circuit breaker specification corresponding to the Q circuit breakers, constructing a corresponding digital twin model according to the circuit breaker topology diagram, taking the maximum time current value in the predicted current value and the short-circuit impedance value as the input of the digital twin model, obtaining the instantaneous current value corresponding to each circuit breaker, and determining the initial breaking time sequence according to the instantaneous current value and the circuit breaker specification.

[0015] Further, the circuit breaker specification includes rated current value and withstand time, and the method of determining the initial breaking time sequence according to the instantaneous current value and the circuit breaker specification comprises:

[0016] Determine the absolute value of the difference between the instantaneous current value corresponding to the Q circuit breakers and the rated current value, divide the Q circuit breakers according to the withstand time to generate a first initial sequence and a second initial sequence, adjust the first initial sequence and the second initial sequence according to the absolute value of the difference, obtain the first target sequence and the second target sequence, and splice the first target sequence and the second target sequence to obtain the initial opening sequence.

[0017] Further, the real-time monitoring data includes the total use time, the real-time temperature value and the opening response time, and the fault influence coefficient is obtained by analyzing the total use time, the real-time temperature value and the opening response time.

[0018] Further, the initial opening sequence includes the first target sequence and the second target sequence, and the method for adjusting the initial opening sequence according to the fault influence coefficient to obtain the target opening sequence includes:

[0019] According to the numerical value of the fault influence coefficient, each element in the second target sequence is arranged in descending order to obtain a second adjustment sequence, and the first target sequence and the second adjustment sequence are spliced to obtain the target opening sequence.

[0020] Further, the method for constructing the load classification model includes:

[0021] M groups of training data are obtained, M is a positive integer greater than 1, the training data includes historical current information and historical load type, the historical current information and the historical load type are used as a sample set, the sample set is divided into a training set and a test set, a classifier is constructed, the historical current information in the training set is used as input data, and the historical load type in the training set is used as output data. The classifier is trained to obtain an initial classifier, and the initial classifier is tested using the test set to output a classifier meeting a predetermined accuracy as a load classification model.

[0022] Further, the method for constructing the current prediction model includes:

[0023] A preset historical data set, a sliding step and a sliding window length are set, the historical data set includes G groups of historical transaction data, the historical transaction data includes historical load type and historical current value; the historical data set is converted into a plurality of training samples using a sliding window method, the training samples are used as input of the load prediction model, the historical current value after the sliding step is predicted as output, and the subsequent historical current value of each training sample is predicted as a prediction target. The prediction accuracy is used as a training target to train the current prediction model; and a current prediction model for predicting the current value at a future time according to the real-time current value is generated.

[0024] Further, the method for determining whether to perform circuit protection according to the predicted current value includes:

[0025] Judge whether there is a moment current value greater than a preset first current threshold in the predicted current value, or W moment current values greater than a preset second current threshold exist continuously, if so, circuit protection is performed, the predicted current value includes S moment current values, S> W, the first current threshold is greater than the second current threshold.

[0026] The power transmission line visual multi-terminal cooperative inspection system based on the electric pole system is used for realizing the power transmission line visual multi-terminal cooperative inspection method based on the electric pole system, and includes the following steps:

[0027] The prediction module is used for acquiring real-time current information and real-time current values, determining corresponding load types based on the real-time current information, and acquiring predicted current values according to the load types and the real-time current values.

[0028] The timing generation module is used for judging whether to perform circuit protection according to the predicted current values, and when circuit protection is needed, corresponding circuit breaker topology is called, simulation is performed according to the predicted current values and the circuit breaker topology, and initial opening timing is obtained.

[0029] The timing adjustment module is used for acquiring real-time monitoring data of Q circuit breakers in the circuit breaker topology, calculating a fault influence coefficient according to the real-time monitoring data, adjusting the initial opening timing according to the fault influence coefficient, obtaining target opening timing, and outputting a target opening timing diagram.

[0030] Compared with the prior art, the power transmission line visual multi-terminal cooperative inspection method based on the electric pole system has the following beneficial effects:

[0031] The power transmission line visual multi-terminal cooperative inspection method based on the electric pole system first acquires predicted current values according to load types and real-time current values, judges whether to perform circuit protection according to the predicted current values, when circuit protection is needed, corresponding circuit breaker topology is called, simulation is performed according to the predicted current values and the circuit breaker topology, and initial opening timing is obtained, then a fault influence coefficient is calculated according to real-time monitoring data, the initial opening timing is adjusted according to the fault influence coefficient, and target opening timing is obtained. BRIEF DESCRIPTION OF DRAWINGS

[0032] Figure 1 The flowchart of the power transmission line visual multi-terminal cooperative inspection method based on the electric pole system in the present application;

[0033] Figure 2 The structural schematic diagram of the power transmission line visual multi-terminal cooperative inspection system based on the electric pole system in the present application;

[0034] Figure 3 One of the circuit breaker topology diagrams in the present application;

[0035] Figure 4 Another schematic diagram of the circuit breaker topology in the present application. DETAILED DESCRIPTION

[0036] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative effort belong to the scope of protection of the present application.

[0037] Embodiment 1

[0038] Please refer to Figure 1 The embodiment discloses a power transmission line visual multi-terminal cooperative inspection method based on an electric power system, and includes the following steps.

[0039] S10: acquiring real-time current information and a real-time current value, determining a corresponding load type based on the real-time current information, and acquiring a predicted current value according to the load type and the real-time current value;

[0040] In the embodiment, the real-time current information includes but is not limited to a current phase angle, an instantaneous change value, and a current waveform diagram, etc. The current phase angle refers to a phase difference between a current waveform and a voltage waveform, and is usually represented by an angle. The phase angle reflects a time difference between a current and a voltage in the same period to reach a maximum value (or a zero value). The instantaneous change value represents an instantaneous change of a current value, and the current waveform diagram displays an amplitude change of a current in a period.

[0041] It should be noted that the load type at least includes an inductive load, a capacitive load, and a mixed load. The inductive load refers to a load mainly composed of inductors (such as motors, inductors, transformers, etc.) in a circuit. In the inductive load, the current lags behind the voltage. This lag is due to the electromotive force generated by the inductive element when the current changes, which resists the change of the current. On the contrary, the capacitive load refers to a load mainly composed of capacitors (such as capacitors, some types of circuits) in a circuit. In the capacitive load, the current leads the voltage. The capacitive element stores charges when the voltage changes, and releases the charges when the voltage decreases. The mixed load refers to a load containing inductive and capacitive elements, and thus has comprehensive characteristics. The phase relationship between the current and the voltage in the mixed load is between the inductive and capacitive.

[0042] It can be understood that, taking the current phase angle and the instantaneous change value as an example, when the load type is an inductive load, the peak of the current appears later than the peak of the voltage, in this case, the current phase angle is a positive angle, when the load type is a capacitive load, the peak of the current appears earlier than the peak of the voltage, the current phase angle is a negative angle, when the load type is a mixed load, the current phase angle can be a negative angle or a positive angle, but the absolute value of the current phase angle is smaller, in terms of the instantaneous change value, the inductive load will generate a high starting current (impact current) when starting, so that the instantaneous change value is larger, while the current change of the capacitive load is relatively stable. The instantaneous change value is smaller, and the corresponding mixed load is between the two when starting.

[0043] The method for determining the corresponding load type based on the real-time current information comprises:

[0044] inputting the real-time current information into a pre-constructed load classification model to obtain the load type.

[0045] The construction method of the load classification model comprises:

[0046] obtaining M groups of training data, M being a positive integer greater than 1, the training data comprising historical current information and historical load types, taking the historical current information and the historical load types as a sample set, dividing the sample set into a training set and a test set, constructing a classifier, taking the historical current information in the training set as input data and taking the historical load types in the training set as output data, training the classifier to obtain an initial classifier, testing the initial classifier by using the test set, and outputting a classifier meeting a preset accuracy as the load classification model, the classifier being preferably one of a Naive Bayes model or a support vector machine model.

[0047] The method for obtaining predicted current information according to the load type and the real-time current information comprises:

[0048] inputting the load type and the real-time current information into a pre-constructed current prediction model to obtain the predicted current information.

[0049] The construction method of the current prediction model comprises:

[0050] presetting a historical data set, a sliding step and a sliding window length, the historical data set comprising G groups of historical transaction data, the historical transaction data comprising historical load types and historical current values; converting the historical data set into a plurality of training samples by using a sliding window method, taking the training samples as the input of a load prediction model, taking the historical current values after the sliding step as the output, taking the subsequent historical current values of each training sample as the prediction target, taking the prediction accuracy as the training target, and training the current prediction model; generating a current prediction model for predicting the current value at a future time according to the real-time current value, the current prediction model being an LSTM model.

[0051] It should be noted that the sliding window method is a conventional technical means of the LSTM model, and the present application will not be further explained in principle; but in order to facilitate the implementation of the present application, the present application provides the following examples of the sliding window method:

[0052] Suppose we want to train an LSTM model with historical data [1, 2, 3, 4, 5, 6], in this embodiment, the prediction time step is set to 1, the sliding step is set to 1, and the sliding window length is set to 3; then generate 3 groups of training samples and corresponding prediction target data: [1, 2, 3], [2, 3, 4] and [3, 4, 5] as training samples, and [4], [5] and [6] as prediction targets.

[0053] The prediction accuracy can be measured using mean square error or mean absolute error as the loss function, and the weights and biases of the model are updated by the back propagation algorithm to generate the current prediction model.

[0054] It should be noted that the power factor is different for different load types, the power factor is a parameter that describes the power conversion efficiency in the power system, and represents the ratio of active power to total input power, the value of the power factor ranges from 0 to 1, inductive load usually has a low power factor, which means that the current amplitude required to provide the same active power will be larger, capacitive load usually helps to improve the power factor, for the same active power, the current amplitude will be smaller, and the power factor corresponding to the mixed load is between the two, therefore, the load type affects the prediction of the subsequent current value, for example, when the load type is inductive load, the subsequent predicted current value is usually higher, because inductive load (such as motor, transformer, etc.) consumes more reactive power, which causes the phase angle between current and voltage to deviate, increasing the total input power, accordingly, when the load type is capacitive load, the subsequent predicted current value is usually lower, this embodiment considers the load type as an influencing factor, so that the subsequent predicted current is more accurate.

[0055] S20: determining whether to perform circuit protection according to the predicted current value, when circuit protection is needed, the corresponding circuit breaker topology is called, simulation is performed according to the predicted current value and the circuit breaker topology, and the initial opening timing is obtained;

[0056] In this embodiment, the method for determining whether to perform circuit protection according to the predicted current value comprises:

[0057] Judge whether there is a moment current value greater than a preset first current threshold value in the predicted current value, or W moment current values greater than a preset second current threshold value exist continuously, if so, circuit protection is performed, the predicted current value includes S moment current values, S> W, the first current threshold value is greater than the second current threshold value.

[0058] It can be understood that the embodiment is to predict the current value in the future for a period of time, which can be one hour or half an hour, so there will be S moment current values in the predicted current value, and the moment current value represents the current value at a certain moment in the future, therefore, when there is a moment current value greater than a preset first current threshold value in the predicted current value, or W moment current values greater than a preset second current threshold value exist continuously, circuit protection is needed, which has the advantage of effectively predicting and detecting current abnormal conditions in the future for a period of time, and timely performing circuit protection to prevent circuit or equipment from being damaged due to overload or other abnormal current, and by setting two different current threshold values, different protection measures can be taken flexibly according to the severity of the current abnormality, thereby enhancing the safety and reliability of the system.

[0059] The above circuit breaker topology diagram represents the circuit structure between a plurality of circuit breakers, for example, as shown in Figure 3 and Figure 4 , as shown in Figure 3 , the power supply 10, short-circuit impedance 20, circuit breaker 30, main line 40 and branch line 50 are shown, it can be understood that the above-mentioned power supply 10 generally represents a circuit, for example, a micro-grid circuit, which is generated by a plurality of distributed energy sources, as known from Figure 3 and Figure 4 , it can be understood that a plurality of circuit breakers 30 have different circuit structures.

[0060] It should be noted that the circuit breaker topology diagram is pre-constructed according to expert knowledge or prior knowledge of a person skilled in the art during the construction of a smart grid, and is stored in the database of the system, when a node fails, the corresponding circuit breaker topology diagram is directly retrieved according to the position information of the node.

[0061] The method for simulating according to the predicted current value and the circuit breaker topology diagram to obtain an initial opening sequence includes:

[0062] Obtain the short-circuit impedance value corresponding to each line in the circuit breaker topology diagram, and the circuit breaker specification corresponding to the Q circuit breakers, construct a corresponding digital twin model according to the circuit breaker topology diagram, take the maximum moment current value in the predicted current value and the short-circuit impedance value as the input of the digital twin model, obtain the instantaneous current value corresponding to each circuit breaker, and determine the initial opening sequence according to the instantaneous current value and the circuit breaker specification.

[0063] It should be noted that, still taking Figure 3 and Figure 4 for example, the impedance value corresponding to each line in the above represents that it contains both the short-circuit impedance 20 of the main line 40 and the short-circuit impedance 20 of the branch line 50. The breaker specification includes but is not limited to rated current value and withstand time. The rated current value refers to the current value specified by the manufacturer that the device can safely operate for a long time under the specified environment. The withstand time refers to the time range that the circuit breaker can withstand overcurrent or short-circuit current.

[0064] It should be added that the method of constructing a corresponding digital twin model according to the breaker topology diagram can be to simulate the dynamic behavior of the power system by using simulation software or platforms such as MATLAB / Simulink, PowerFactory, etc. In the simulation, the target to be simulated is to be clearly defined. In this embodiment, the target to be simulated is a short-circuit fault. According to the breaker topology diagram, define the nodes (such as load nodes, etc.) and edges (such as line connections, breaker connections, etc.) in the system. The node represents the connection point in the power system, and the edge represents the electrical element connecting these nodes.

[0065] It can be understood that the instantaneous current value corresponding to each breaker can be the instantaneous current value of the branch line where the breaker is located. For example, as shown in Figure 3 and Figure 4 , Figure 3 In the first breaker 301, the second breaker 302 and the third breaker 303 are in parallel, so Figure 3 the instantaneous current value corresponding to each breaker is approximately equal, while Figure 4 In the first breaker 301, the second breaker 302 and the third breaker 303 are in parallel, so

[0066] The breaker specification includes but is not limited to rated current value and withstand time. The method of determining the initial breaking sequence according to the instantaneous current value and the breaker specification includes:

[0067] Determine the absolute value of the difference between the instantaneous current value corresponding to the Q breakers and the rated current value. According to the withstand time, divide the Q breakers to generate a first initial sequence and a second initial sequence. According to the absolute value of the difference, adjust the first initial sequence and the second initial sequence to obtain a first target sequence and a second target sequence. The first target sequence and the second target sequence are spliced head to tail to obtain the initial breaking sequence.

[0068] It should be noted that the withstand time refers to the time range within which a circuit breaker can withstand overcurrent or short-circuit current. Therefore, in this embodiment, a corresponding withstand time threshold is set, and circuit breakers with withstand times less than the withstand time threshold are assigned to the first initial sequence, while the rest are assigned to the second initial sequence. Then, the first initial sequence and the second initial sequence are sorted in descending order according to the absolute value of the difference to obtain the first target sequence and the second target sequence.

[0069] The advantage of obtaining the initial interruption sequence in this way is that by prioritizing circuit breakers with larger absolute values ​​of the difference, it can be ensured that the fault current is quickly interrupted when the current exceeds the equipment's capacity, thus avoiding equipment damage. Prioritizing circuit breakers with shorter withstand times helps to prevent them from failing to interrupt the current in time when a short-circuit fault occurs, thereby protecting other important equipment in the system.

[0070] S30: Obtain real-time monitoring data of Q circuit breakers in the circuit breaker topology diagram, calculate the fault impact coefficient based on the real-time monitoring data, adjust the initial interruption sequence based on the fault impact coefficient, and obtain the target interruption sequence.

[0071] In this embodiment, the real-time monitoring data includes, but is not limited to, total usage time, real-time temperature value, and interruption response time. Interruption response time refers to the time required from the time the circuit breaker receives the fault signal until the interruption action is completed. Interruption response time can be the average of several historical interruption response times.

[0072] Methods for calculating the fault impact coefficient based on real-time monitoring data include:

[0073] After normalizing the total acquisition time, real-time temperature value, and interruption response time, the fault impact coefficient is obtained by weighted summation.

[0074] Optionally, the calculation formula is:

[0075] |FIT=w1·TUD n +w2·BRT n +w3·RTE n |;

[0076] In the formula, FIF is the fault influence coefficient, and TUD is the fault influence coefficient. n To use the normalized value of the total duration, BRT is the normalized value of the on / off response time, and RTE is the normalized value of the real-time temperature value.

[0077] w1, w2 and w3 are weight coefficients, and w1, w2 and w3 are all greater than 0, the size of the weight coefficient is a specific value obtained by quantifying each parameter, which is convenient for subsequent comparison, and the size of the weight coefficient depends on the number of sample data and the corresponding processing coefficient preliminarily set by the person skilled in the art for each group of sample data; as long as it does not affect the proportional relationship between the parameter and the quantized value.

[0078] It should be noted that the normalization method of the total duration, the real-time temperature value and the breaking response time is Min-Max normalization, and the expression is: In the formula, x n is the normalized value, x is the actual value of the original data, x min is the minimum value in the value range of this type of data, which can be the minimum value obtained by historical statistics or a reasonable lower limit set by artificial, x max is the maximum value in the value range of this type of data, which can also be the maximum value obtained by historical statistics or a reasonable upper limit set by artificial.

[0079] In this embodiment, the total duration is used as an example, when the total duration used is larger, the probability of failure of the circuit breaker is larger, therefore, according to the above content, the fault influence coefficient is positively correlated with the probability of failure of the circuit breaker.

[0080] The initial breaking time sequence includes a first target sequence and a second target sequence, the method for adjusting the initial breaking time sequence according to the fault influence coefficient to obtain the target breaking time sequence includes:

[0081] According to the value of the fault influence coefficient, each element in the second target sequence is arranged in descending order to obtain a second adjustment sequence, the first target sequence and the second adjustment sequence are spliced at the head and tail to obtain the target breaking time sequence, and the target breaking time sequence diagram is output for visual display, which is convenient for the operation and maintenance personnel to intuitively master the breaking time sequence between the circuit breakers and ensure the stability of the power system.

[0082] In this embodiment, the reason for rearranging only the second target sequence is that the elements in the first target sequence correspond to smaller withstand times, so these circuit breakers are more likely to fail when facing current overload, have been prioritized in the initial breaking sequence, and do not need to be adjusted according to the fault impact coefficient, while the elements in the second target sequence correspond to larger withstand times, so these circuit breakers can withstand longer overcurrent or short-circuit current in fault conditions. In order to further optimize the protection strategy of the system, the order between the elements in the second target sequence can be further adjusted according to the fault impact coefficient to ensure that these circuit breakers can be reasonably arranged according to their potential fault risk and response ability under different fault scenarios, thereby improving the safety and reliability of the system.

[0083] In this embodiment, the predicted current value is obtained according to the load type and the real-time current value, and it is determined whether to perform circuit breaking protection according to the predicted current value. When circuit breaking protection is needed, the corresponding circuit breaker topology is called, simulation is performed according to the predicted current value and the circuit breaker topology, and the initial breaking sequence is obtained. Then, the fault impact coefficient is calculated according to the real-time monitoring data, and the initial breaking sequence is adjusted according to the fault impact coefficient to obtain the target breaking sequence. In this embodiment, the topology structure of the circuit breaker is considered in the case of circuit failure, thereby forming the corresponding breaking sequence and improving the reliability of the power grid system during operation.

[0084] Embodiment 2

[0085] As shown in Figure 2 Based on embodiment 1, this embodiment provides a power transmission line visual multi-terminal cooperative inspection system based on a power grid system, which includes:

[0086] A prediction module is configured to obtain real-time current information and a real-time current value, determine a corresponding load type based on the real-time current information, and obtain a predicted current value according to the load type and the real-time current value.

[0087] A sequence generation module is configured to determine whether to perform circuit breaking protection according to the predicted current value, call a corresponding circuit breaker topology when circuit breaking protection is needed, and obtain an initial breaking sequence by simulating according to the predicted current value and the circuit breaker topology.

[0088] A sequence adjustment module is configured to obtain real-time monitoring data of Q circuit breakers in the circuit breaker topology, calculate a fault impact coefficient according to the real-time monitoring data, and adjust the initial breaking sequence according to the fault impact coefficient to obtain a target breaking sequence.

[0089] The initial breaking sequence includes a first target sequence and a second target sequence. The method for adjusting the initial breaking sequence according to the fault impact coefficient to obtain the target breaking sequence includes:

[0090] According to the numerical size of the fault influence coefficient, each element in the second target sequence is arranged in descending order to obtain a second adjustment sequence, the first target sequence and the second adjustment sequence are spliced at the head and tail to obtain a target opening timing sequence, and a target opening timing sequence diagram is output.

[0091] The above formulas are dimensionless values calculated, the formulas are obtained by collecting a large amount of data to simulate a formula of the most recent real situation, and the preset parameters, weights and threshold values in the formula are set by a person skilled in the art according to actual conditions.

[0092] The above is only a specific embodiment of the present application, but the protection scope of the present application is not limited thereto, any person skilled in the art can easily think of changes or replacements within the technical range disclosed by 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 subject to the protection scope of the claims.

[0093] Finally: the above is only a preferred embodiment of the present application and is not used to limit the present application, any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. A method for visualizing multi-terminal cooperative inspection of a power transmission line based on an electric field system, characterized in that, The method comprises the following steps: obtaining real-time current information and a real-time current value, determining a corresponding load type based on the real-time current information, and obtaining a predicted current value according to the load type and the real-time current value; determining whether to perform circuit breaking protection according to the predicted current value, and when the circuit breaking protection needs to be performed, calling a corresponding circuit breaker topology map, simulating according to the predicted current value and the circuit breaker topology map to obtain an initial breaking time sequence; obtaining real-time monitoring data of Q circuit breakers in the circuit breaker topology map, calculating a fault influence coefficient according to the real-time monitoring data, adjusting the initial breaking time sequence according to the fault influence coefficient to obtain a target breaking time sequence, and outputting a target breaking time sequence diagram.

2. The method of claim 1, wherein the method further comprises: The method of simulating according to the predicted current value and the circuit breaker topology map to obtain the initial breaking time sequence comprises the following steps: obtaining a short-circuit impedance value corresponding to each line in the circuit breaker topology map and a circuit breaker specification corresponding to the Q circuit breakers, constructing a corresponding digital twin model according to the circuit breaker topology map, taking the maximum time current value in the predicted current value and the short-circuit impedance value as inputs of the digital twin model, obtaining an instantaneous current value corresponding to each circuit breaker, and determining the initial breaking time sequence according to the instantaneous current value and the circuit breaker specification.

3. The method of claim 2, wherein the method further comprises: The circuit breaker specification comprises a rated current value and a withstand time, and the method of determining the initial breaking time sequence according to the instantaneous current value and the circuit breaker specification comprises the following steps: determining an absolute value of a difference between the instantaneous current value and the rated current value of the Q circuit breakers, dividing the Q circuit breakers according to the withstand time to generate a first initial sequence and a second initial sequence, adjusting the first initial sequence and the second initial sequence according to the absolute value of the difference, obtaining a first target sequence and a second target sequence, and splicing the first target sequence and the second target sequence at the head and tail to obtain the initial breaking time sequence.

4. The method of claim 3, wherein the method further comprises: The real-time monitoring data comprises a total use time, a real-time temperature value and a breaking response time, and the fault influence coefficient is obtained by analyzing the total use time, the real-time temperature value and the breaking response time.

5. The method of claim 4, wherein the method further comprises: The initial breaking time sequence comprises the first target sequence and the second target sequence, and the method of adjusting the initial breaking time sequence according to the fault influence coefficient to obtain the target breaking time sequence comprises the following steps: arranging each element in the second target sequence in descending order according to the numerical value of the fault influence coefficient to obtain a second adjustment sequence, and splicing the first target sequence and the second adjustment sequence at the head and tail to obtain the target breaking time sequence.

6. The method of claim 1, wherein the method further comprises: The method for constructing the load classification model comprises the following steps: obtaining M groups of training data, M being a positive integer greater than 1, the training data comprising historical current information and historical load types, taking the historical current information and the historical load types as a sample set, dividing the sample set into a training set and a test set, constructing a classifier, taking the historical current information in the training set as input data and the historical load types in the training set as output data, training the classifier to obtain an initial classifier, testing the initial classifier by using the test set, and outputting a classifier meeting a preset accuracy as the load classification model.

7. The method of claim 1, wherein the method further comprises: The method for constructing the current prediction model comprises the following steps: A preset historical data set, a sliding step, and a sliding window length are set, the historical data set includes G groups of historical transaction data, the historical transaction data includes a historical load type and a historical current value; the historical data set is converted into a plurality of training samples using a sliding window method, the training samples are used as an input of a load prediction model, a historical current value after the sliding step is predicted as an output, a subsequent historical current value of each training sample is used as a prediction target, a prediction accuracy is used as a training target, and the current prediction model is trained; and a current prediction model for predicting a future time current value according to a real-time current value is generated.

8. The method of claim 7, wherein the method further comprises: The method for determining whether to perform circuit protection according to the predicted current value includes: determining whether there is a time current value greater than a preset first current threshold in the predicted current value, or whether W continuous time current values are all greater than a preset second current threshold, and performing circuit protection if there is, the predicted current value including S time current values, S > W, and the first current threshold being greater than the second current threshold.

9. A power line visualized multi-terminal cooperative inspection system based on the electric bird system, which is used to realize the power line visualized multi-terminal cooperative inspection method based on the electric bird system in any one of claims 1-8, characterized in that, The method includes: a prediction module configured to obtain real-time current information and a real-time current value, determine a corresponding load type based on the real-time current information, and obtain a predicted current value according to the load type and the real-time current value; a time sequence generation module configured to determine whether to perform circuit protection according to the predicted current value, and obtain an initial opening time sequence by simulating the predicted current value and a circuit breaker topology when circuit protection is needed; a time sequence adjustment module configured to obtain real-time monitoring data of Q circuit breakers in the circuit breaker topology, calculate a fault influence coefficient according to the real-time monitoring data, adjust the initial opening time sequence according to the fault influence coefficient to obtain a target opening time sequence, and output a target opening time sequence diagram.

Images