Intelligent control system and method for vacuum circuit breaker

Abstract

The invention relates to the technical field of circuit breaker control, and particularly discloses an intelligent control system and method for a vacuum circuit breaker, and the system employs a neural network model based on deep learning to carry out the multi-scale time sequence correlation aggregation analysis of the power consumption proportionality coefficients of a contact resistor, an operation mechanism and a control circuit in the vacuum circuit breaker. According to the method, multi-scale time sequence dynamic correlation characteristics among power consumption proportionality coefficients of multiple components are captured, a power consumption influence rule among different components in the vacuum circuit breaker is revealed, and therefore accurate judgment of the abnormal power consumption state of the vacuum circuit breaker is achieved by considering the time sequence dynamic interaction relation among the power consumption of the different components. According to the method, the power consumption state of the vacuum circuit breaker can be analyzed more comprehensively by considering the time sequence power consumption change trend of each component and the dynamic association mode between the components, and the power consumption abnormality condition of the vacuum circuit breaker can be identified, so that the power consumption abnormality detection requirements under various complex working conditions can be better met.

Description

Technical Field

[0001] This application relates to the technical field of circuit breaker control, and more specifically, to an intelligent control system and method for a vacuum circuit breaker. Background Art

[0002] A vacuum circuit breaker is a switching device widely used in high-voltage power systems. It has high breaking capacity, fast switching speed, good insulation performance, and reliable operating characteristics. It is commonly used for the protection and control of high-voltage transmission lines, substations, and power equipment in power systems. It can quickly cut off the current when a fault occurs in the circuit to avoid further damage. With the development of power systems towards higher voltages and larger capacities, the requirements for the performance of circuit breakers are getting higher and higher. Maintaining and intelligently controlling vacuum circuit breakers helps ensure the safe and stable operation of power systems.

[0003] Traditionally, the monitoring and maintenance of vacuum circuit breakers mainly rely on regular inspections and manual detections. This method is not only inefficient but also difficult to detect potential problems in a timely manner. In this regard, the invention patent with the publication number CN116799965B proposes an intelligent control method for the power consumption of a vacuum circuit breaker. By obtaining the contact resistance of the contacts, the power of the operating mechanism, and the control circuit in the vacuum circuit breaker, analyzing the power consumption ratio coefficients of the three, and comparing the power consumption ratio coefficients of the contact resistance of the contacts, the operating mechanism, and the control circuit with their respective preset reference ranges, it is possible to determine the types of abnormal power consumption of the vacuum circuit breaker, such as abnormal power consumption of the contact resistance of the contacts, abnormal power consumption of the operating mechanism, and abnormal power consumption of the control circuit.

[0004] However, in actual operation, the power consumption of each component of the vacuum circuit breaker does not exist independently, but there are complex interactions in the time dimension. For example, when the contact resistance of the contacts increases due to poor contact, it may increase the resistance when the operating mechanism operates, thereby increasing the power consumption of the operating mechanism; at the same time, the control circuit may also need to consume more energy to maintain the stable operation of the entire system. In the existing technology, only the relationship between the power consumption ratio coefficients of each component and the preset range is analyzed in isolation, without fully considering the mutual influence of the power consumption between different components inside the vacuum circuit breaker and the dynamic correlation over time, which may lead to inaccurate judgment of abnormal power consumption.

[0005] Therefore, an optimized intelligent control system and method for a vacuum circuit breaker are expected. Summary of the Invention

[0006] To solve the above technical problems, this application is proposed. Embodiments of this application provide an intelligent control system and method for a vacuum circuit breaker, which uses a neural network model based on deep learning to perform multi-scale temporal correlation aggregation analysis on the power consumption proportionality coefficients of the contact resistance, operating mechanism, and control circuit in the vacuum circuit breaker, so as to capture the multi-scale temporal dynamic correlation characteristics between the power consumption proportionality coefficients of multiple components, reveal the power consumption influence law between different components inside the vacuum circuit breaker, and thus realize accurate judgment of the abnormal power consumption state of the vacuum circuit breaker by considering the temporal dynamic interaction relationship between the power consumptions of different components. By considering the temporal power consumption change trends of each component and the dynamic correlation patterns between them, this method can more comprehensively analyze the power consumption state of the vacuum circuit breaker, identify abnormal power consumption situations of the vacuum circuit breaker, and thus better meet the requirements for detecting abnormal power consumption under various complex working conditions.

[0007] According to one aspect of this application, an intelligent control method for a vacuum circuit breaker is provided, which includes:

[0008] Step 1: Obtain the time queue of the power consumption proportionality coefficient of the contact resistance in the vacuum circuit breaker;

[0009] Step 2: Obtain the time queue of the power consumption proportionality coefficient of the operating structure in the vacuum circuit breaker;

[0010] Step 3: Obtain the time queue of the power consumption proportionality coefficient of the control circuit in the vacuum circuit breaker;

[0011] Step 4: Based on the time queue of the power consumption proportionality coefficient of the contact resistance, the time queue of the power consumption proportionality coefficient of the operating structure, and the time queue of the power consumption proportionality coefficient of the control circuit, determine whether the power consumption of the vacuum circuit breaker is abnormal, where determining whether the power consumption of the vacuum circuit breaker is abnormal includes: performing multi-scale temporal correlation aggregation analysis and cross-temporal scale core feature anchoring interaction based on the power consumption proportionality coefficient on the contact resistance, the operating structure, and the control circuit to obtain a judgment result;

[0012] Step 5: In response to the judgment result that the power consumption of the vacuum circuit breaker is abnormal, determine the type of abnormal power consumption of the vacuum circuit breaker to obtain a set of abnormal power consumption types;

[0013] Step 6: Feed back the set of abnormal power consumption types to the remote monitoring center of the vacuum circuit breaker.

[0014] According to another aspect of this application, an intelligent control system for a vacuum circuit breaker is provided, which includes:

[0015] A contact resistance power consumption proportionality coefficient acquisition module, configured to obtain the time queue of the power consumption proportionality coefficient of the contact resistance in the vacuum circuit breaker;

[0016] An operating structure power consumption ratio coefficient acquisition module, configured to acquire a time queue of the power consumption ratio coefficients of the operating structure in the vacuum circuit breaker;

[0017] A control circuit power consumption ratio coefficient acquisition module, configured to acquire a time queue of the power consumption ratio coefficients of the control circuit in the vacuum circuit breaker;

[0018] A power consumption anomaly judgment module, configured to judge whether the power consumption of the vacuum circuit breaker is abnormal based on the time queue of the power consumption ratio coefficients of the contact resistance, the time queue of the power consumption ratio coefficients of the operating structure, and the time queue of the power consumption ratio coefficients of the control circuit. Among them, judging whether the power consumption of the vacuum circuit breaker is abnormal includes: performing multi-scale time series correlation aggregation analysis and cross-time series scale core feature anchoring interaction based on the power consumption ratio coefficients on the contact resistance, the operating structure, and the control circuit to obtain a judgment result;

[0019] A power consumption anomaly type determination module, configured to, in response to the judgment result that the power consumption of the vacuum circuit breaker is abnormal, determine the power consumption anomaly type of the vacuum circuit breaker to obtain a set of power consumption anomaly types;

[0020] A power consumption anomaly feedback module, configured to feedback the set of power consumption anomaly types to the remote monitoring center of the vacuum circuit breaker.

[0021] Compared with the prior art, the intelligent control system and method for a vacuum circuit breaker provided in this application uses a neural network model based on deep learning to perform multi-scale time series correlation aggregation analysis on the power consumption ratio coefficients of the contact resistance, the operating mechanism, and the control circuit in the vacuum circuit breaker, to capture the multi-scale time series dynamic correlation characteristics between the power consumption ratio coefficients of multiple components, reveal the power consumption influence laws between different components inside the vacuum circuit breaker, and thus realize an accurate judgment of the abnormal power consumption state of the vacuum circuit breaker by considering the time series dynamic interaction relationship between the power consumption of different components. By considering the time series power consumption change trends of each component and the dynamic correlation patterns between them, this method can analyze the power consumption state of the vacuum circuit breaker more comprehensively, identify the abnormal power consumption situation of the vacuum circuit breaker, and thus better meet the power consumption anomaly detection requirements under various complex working conditions. Description of the Drawings

[0022] By describing the embodiments of the present application in more detail in conjunction with the drawings, the above and other objects, features, and advantages of the present application will become more obvious. The drawings are used to provide a further understanding of the embodiments of the present application, and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation to the present application. In the drawings, the same reference numerals generally represent the same components or steps.

[0023] Figure 1Flow chart of the intelligent control method for a vacuum circuit breaker according to an embodiment of the present application.

[0024] Figure 2 Flow chart of sub-step S4 of the intelligent control method for a vacuum circuit breaker according to an embodiment of the present application.

[0025] Figure 3 Schematic diagram of data flow of sub-step S4 of the intelligent control method for a vacuum circuit breaker according to an embodiment of the present application.

[0026] Figure 4 Flow chart of sub-step S43 of the intelligent control method for a vacuum circuit breaker according to an embodiment of the present application.

[0027] Figure 5 Flow chart of sub-step S432 of the intelligent control method for a vacuum circuit breaker according to an embodiment of the present application.

[0028] Figure 6 Block diagram of the intelligent control system for a vacuum circuit breaker according to an embodiment of the present application. Detailed implementation manners

[0029] As shown in the present application and the claims, unless the context clearly indicates otherwise, words such as "a", "an", "one", and / or "the" are not specifically singular and may also include the plural. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0030] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, however, any number of different modules can be used and run on the user terminal and / or the server. The modules are only illustrative, and different aspects of the system and method can use different modules.

[0031] In the present application, flow charts are used to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the operations before or below do not necessarily need to be executed precisely in sequence. On the contrary, according to needs, various steps can be executed in reverse order or simultaneously. At the same time, other operations can also be added to these processes, or one or several operations can be removed from these processes.

[0032] Next, example embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. It should be understood that the present application is not limited by the example embodiments described here.

[0033] It should be noted that in this application, all actions of obtaining data are carried out on the premise of complying with the corresponding data protection regulations and policies of the country where the device is located and obtaining the authorization given by the corresponding device owner.

[0034] As mentioned in the above background art, Patent CN116799965B proposes an intelligent control method for the power consumption of a vacuum circuit breaker. It obtains the contact resistance of the contacts, the power of the operating mechanism and the control circuit in the vacuum circuit breaker, analyzes the power consumption ratio coefficients of the three, and judges the abnormal power consumption type of the vacuum circuit breaker by comparing the power consumption ratio coefficients of the contact resistance of the contacts, the operating mechanism and the control circuit with their respective preset reference ranges, such as abnormal power consumption of the contact resistance of the contacts, abnormal power consumption of the operating mechanism, and abnormal power consumption of the control circuit.

[0035] However, in actual operation, the power consumption of each component of the vacuum circuit breaker does not exist independently, but there are complex interactions in the time dimension. For example, when the contact resistance of the contacts increases due to poor contact, it may increase the resistance when the operating mechanism operates, thereby increasing the power consumption of the operating mechanism; at the same time, the control circuit may also need to consume more energy to maintain the stable operation of the entire system. In the prior art, only the relationship between the power consumption ratio coefficients of each component and the preset range is analyzed in isolation, without fully considering the mutual influence of the power consumption between different components inside the vacuum circuit breaker and the dynamic correlation over time, which may lead to inaccurate judgment of abnormal power consumption. To solve the above technical problems, this application proposes an optimized intelligent control method for vacuum circuit breakers. It uses a neural network model based on deep learning to perform multi-scale time-series correlation aggregation analysis on the power consumption ratio coefficients of the contact resistance of the contacts, the operating mechanism and the control circuit in the vacuum circuit breaker, to capture the multi-scale time-series dynamic correlation characteristics between the power consumption ratio coefficients of multiple components, and reveal the law of power consumption influence between different components inside the vacuum circuit breaker, so as to accurately judge the abnormal power consumption state of the vacuum circuit breaker by considering the time-series dynamic interaction relationship between the power consumption of different components. By considering the time-series power consumption change trend of each component and the dynamic correlation mode between them, this method can analyze the power consumption state of the vacuum circuit breaker more comprehensively, identify the abnormal power consumption situation of the vacuum circuit breaker, and thus better meet the requirements of abnormal power consumption detection under various complex working conditions.

[0036] Figure 1 It is a flowchart of the intelligent control method for a vacuum circuit breaker according to an embodiment of this application. As Figure 1As shown, the intelligent control method for the vacuum circuit breaker includes the following steps: S1, obtaining the time queue of the power consumption proportion coefficient of the contact resistance in the vacuum circuit breaker; S2, obtaining the time queue of the power consumption proportion coefficient of the operating structure in the vacuum circuit breaker; S3, obtaining the time queue of the power consumption proportion coefficient of the control circuit in the vacuum circuit breaker; S4, based on the time queue of the power consumption proportion coefficient of the contact resistance, the time queue of the power consumption proportion coefficient of the operating structure, and the time queue of the power consumption proportion coefficient of the control circuit, determining whether the power consumption of the vacuum circuit breaker is abnormal. Among them, determining whether the power consumption of the vacuum circuit breaker is abnormal includes: performing multi-scale time-series correlation aggregation analysis and cross-time-scale core feature anchoring interaction based on the power consumption proportion coefficient for the contact resistance, the operating structure, and the control circuit to obtain a judgment result; S5, in response to the judgment result indicating that the power consumption of the vacuum circuit breaker is abnormal, determining the type of power consumption abnormality of the vacuum circuit breaker to obtain a set of power consumption abnormality types; S6, feeding back the set of power consumption abnormality types to the remote monitoring center of the vacuum circuit breaker.

[0037] In the above intelligent control method for the vacuum circuit breaker, in step S1, the time queue of the power consumption proportion coefficient of the contact resistance in the vacuum circuit breaker is obtained. It should be understood that the power consumption of the contact resistance is an important part of the power consumption of the vacuum circuit breaker, and its magnitude directly affects the performance and operation stability of the circuit breaker. If the contact resistance of the contacts is too large, a large amount of electrical energy will be lost at the contact part and converted into heat energy, which not only reduces the power transmission efficiency of the system but may also cause the contacts to overheat. In severe cases, it may even cause the contact material to melt and deform, thereby affecting the normal opening and closing operations of the vacuum circuit breaker and threatening the safe and stable operation of the power system. Therefore, by obtaining the time queue of the power consumption proportion coefficient of the contact resistance, the power consumption proportion at different times can be completely recorded, revealing any abnormal fluctuations in the power consumption of the contact resistance. For example, when problems such as oxidation, corrosion, or poor contact occur on the contact surface, the power consumption proportion coefficient of the contact resistance will show an obvious upward trend, providing a key basis for subsequent power consumption abnormality diagnosis. In practical applications, high-precision current sensors and voltage sensors can be used to respectively measure the current value flowing through the contact resistance and the voltage value across the contacts in real time, calculate the power value of the contact resistance at each moment. At the same time, a power sensor installed in the main circuit of the vacuum circuit breaker is used to monitor the total power consumption of the entire vacuum circuit breaker in real time. Then, by calculating the proportion of the power consumption of the contact resistance in the total power consumption, the power consumption proportion coefficient of the contact resistance at each moment can be obtained, and further arranging them in chronological order to form the time queue of the power consumption proportion coefficient of the contact resistance.

[0038] In the above intelligent control method for vacuum circuit breakers, in step S2, a time queue of the power consumption proportionality coefficient of the operating structure in the vacuum circuit breaker is obtained. It should be understood that the operating mechanism is the core component for the vacuum circuit breaker to perform opening and closing operations, and its working state directly determines whether the vacuum circuit breaker can normally perform the tasks of opening and closing the circuit. During actual operation, the operating mechanism operates frequently, and its power consumption situation can reflect important information such as the mechanical performance, lubrication state, and wear degree of components of the mechanism. By obtaining the time queue of the power consumption proportionality coefficient of the operating structure, it helps to comprehensively and deeply analyze the power consumption changes of the operating mechanism at different times, and then accurately judge whether it is in a normal operating state, helps to timely discover potential fault hazards of the operating mechanism, and arrange maintenance and repair work in advance to ensure that the vacuum circuit breaker can operate reliably when needed. Similarly, in practical applications, high-precision current sensors and voltage sensors can be installed in the motor drive circuit of the operating mechanism to collect the current value and voltage value during motor operation in real time, so as to calculate the power value of the operating mechanism at each moment, and then combine with the total power consumption of the vacuum circuit breaker to calculate the time queue of the power consumption proportionality coefficient of the operating mechanism.

[0039] In the above intelligent control method for vacuum circuit breakers, in step S3, a time queue of the power consumption proportionality coefficient of the control circuit in the vacuum circuit breaker is obtained. Specifically, the control circuit, as the "brain" of the vacuum circuit breaker, is responsible for receiving, processing, and transmitting various operation instructions, as well as real-time monitoring and control of the operating state of the circuit breaker. The stability of its power consumption is directly related to the reliability and accuracy of the entire vacuum circuit breaker control. In a complex power system operation environment, the control circuit may be affected by various factors such as electromagnetic interference, component aging, and power supply fluctuations, resulting in changes in power consumption. By obtaining the time queue of the power consumption proportionality coefficient of the control circuit, it can provide key data support for analyzing the working stability and power consumption change law of the control circuit, helps to timely discover potential fault hazards in the control circuit, and ensures the normal operation of the control function of the vacuum circuit breaker. Here, in actual operation, the time queue of the power consumption proportionality coefficient of the control circuit can be calculated by installing high-precision current sensors and voltage sensors at the power input port of the control circuit to monitor the input current value and input voltage value of the control circuit in real time.

[0040] In the above intelligent control method for a vacuum circuit breaker, in step S4, based on the time queue of the power consumption proportionality coefficient of the contact resistance, the time queue of the power consumption proportionality coefficient of the operating structure, and the time queue of the power consumption proportionality coefficient of the control circuit, it is determined whether the power consumption of the vacuum circuit breaker is abnormal. Among them, determining whether the power consumption of the vacuum circuit breaker is abnormal includes: performing multi-scale time-series correlation aggregation analysis and cross-time-scale core feature anchoring interaction based on the power consumption proportionality coefficient for the contact resistance, the operating structure, and the control circuit to obtain a judgment result. Specifically, in actual operation, there are complex physical connections and energy interactions among the components of a vacuum circuit breaker. Its power consumption does not exist in isolation but is interrelated and dynamically changes over time. The traditional method of only analyzing the relationship between the power consumption proportionality coefficient of each component and a preset range in isolation completely ignores the internal connection between the power consumption of different components and its dynamic characteristics over time. This leads to great limitations in judging power consumption abnormalities and is prone to misjudgment and missed judgment. For example, due to slight oxidation and wear during long-term operation, the contact resistance of the contacts of a vacuum circuit breaker increases, resulting in an increase in the power consumption proportionality coefficient of the contact resistance. According to the traditional analysis method, this proportionality coefficient is still within the preset normal range and is not determined to be abnormal. As the power consumption of the contact resistance increases, the heat generated gradually affects the surrounding operating mechanism, causing a change in the viscosity of the lubricating oil of the operating mechanism, thereby increasing the friction during the operation of the operating mechanism and also increasing the power consumption. However, since this change in power consumption does not exceed the preset normal range of the power consumption proportionality coefficient of the operating mechanism, it is also not determined to be abnormal by the traditional analysis method. However, when there are slight changes in the power consumption proportionality coefficients of the contact resistance and the operating mechanism at the same time, and these changes show a certain correlation in time, it actually indicates potential fault hazards inside the vacuum circuit breaker. Therefore, in order to accurately judge the power consumption abnormality of the vacuum circuit breaker, the present application further performs time-series correlation aggregation analysis on the power consumption proportionality coefficients of the contact resistance, the operating structure, and the control circuit, and comprehensively determines whether the overall power consumption of the vacuum circuit breaker is abnormal according to the time-series dynamic correlation pattern among the power consumption proportionality coefficients of the contact resistance, the operating mechanism, and the control circuit.

[0041] Figure 2 FIG. is a flowchart of sub-step S4 of the intelligent control method for a vacuum circuit breaker according to an embodiment of the present application. Figure 3 FIG. is a schematic diagram of data flow of sub-step S4 of the intelligent control method for a vacuum circuit breaker according to an embodiment of the present application. As Figure 2 and Figure 3As shown, step S4 includes steps: S41, performing data structuring processing on the time queue of the power consumption proportion coefficient of the contact resistance of the contact, the time queue of the power consumption proportion coefficient of the operating structure, and the time queue of the power consumption proportion coefficient of the control circuit to obtain a multi-component power consumption proportion coefficient time series aggregation matrix; S42, performing multi-scale time series correlation analysis between the power consumption proportion coefficients on the multi-component power consumption proportion coefficient time series aggregation matrix to obtain a first-scale time series correlation coding feature vector between the power consumption proportion coefficients and a second-scale time series correlation coding feature vector between the power consumption proportion coefficients; S43, performing cross-time-scale feature interaction coding based on core information anchoring on the first-scale time series correlation coding feature vector between the power consumption proportion coefficients and the second-scale time series correlation coding feature vector between the power consumption proportion coefficients to obtain a time series multi-scale correlation coding feature vector between the power consumption proportion coefficients; S44, determining the judgment result based on the time series multi-scale correlation coding feature vector between the power consumption proportion coefficients.

[0042] Specifically, in step S41, data structuring processing is performed on the time queue of the power consumption proportion coefficient of the contact resistance of the contact, the time queue of the power consumption proportion coefficient of the operating structure, and the time queue of the power consumption proportion coefficient of the control circuit to obtain a multi-component power consumption proportion coefficient time series aggregation matrix. It should be understood that considering that the time queue data of the power consumption proportion coefficients of each component exist in a discrete form and the information is relatively scattered, in order to better mine and utilize the information hidden in the data, the present application further performs structuring processing on it. By arranging the time queue of the power consumption proportion coefficient of the contact resistance of the contact, the time queue of the power consumption proportion coefficient of the operating structure, and the time queue of the power consumption proportion coefficient of the control circuit in chronological order and classifying them according to the corresponding components, a two-dimensional multi-component power consumption proportion coefficient time series aggregation matrix is constructed. In the multi-component power consumption proportion coefficient time series aggregation matrix, each row represents the power consumption proportion coefficient of a component at different time points, and each column represents the power consumption proportion coefficients of different components at the same time point. Through such data structuring processing, not only can the change situation of the power consumption proportion coefficients of each component of the vacuum circuit breaker over time be presented more intuitively and clearly, but also an effective data analysis framework is provided for the analysis of the time series correlation pattern between the power consumption proportion coefficients of each component.

[0043] Specifically, in step S42, multi-scale temporal correlation analysis is performed on the multi-component power consumption ratio coefficient temporal aggregation matrix to obtain the first-scale temporal correlation coding feature vector between power consumption ratio coefficients and the second-scale temporal correlation coding feature vector between power consumption ratio coefficients. Specifically, the present application takes into account that the temporal correlation between the power consumption ratio coefficients of each component may exhibit different characteristic patterns at different scales. For example, at a short time scale, the power consumption change of the contact resistance may be quickly transmitted to the operating mechanism, causing an immediate response in its power consumption; while at a long time scale, the power consumption fluctuation of the control circuit may gradually accumulate, leading to a slow decline in the overall performance of the vacuum circuit breaker. Therefore, in order to comprehensively capture the temporal correlation characteristics between the power consumption ratio coefficients at different scales, the present application uses multi-scale temporal correlation analysis technology to process the multi-component power consumption ratio coefficient temporal aggregation matrix, so as to reveal the internal laws and correlation characteristics of the data at different time scales. In a specific example of the present application, a first convolutional neural network is used to perform two-dimensional convolutional coding and feature activation on the multi-component power consumption ratio coefficient temporal aggregation matrix to obtain the first-scale temporal correlation coding feature vector between power consumption ratio coefficients; a second convolutional neural network is used to perform two-dimensional convolutional coding and feature activation on the multi-component power consumption ratio coefficient temporal aggregation matrix to obtain the second-scale temporal correlation coding feature vector between power consumption ratio coefficients, where the first convolutional neural network and the second convolutional neural network have different convolutional kernel sizes and strides. Specifically, the first convolutional neural network uses a smaller convolutional kernel size and stride, which can capture more detailed and short-term temporal correlation characteristics between power consumption ratio coefficients and is suitable for analyzing the power consumption change law at a short time scale; while the second convolutional neural network uses a larger convolutional kernel size and stride, which can capture more broad and long-term temporal correlation characteristics between power consumption ratio coefficients and is suitable for analyzing the power consumption accumulation effect at a long time scale. At the same time, the introduction of the activation function can enhance the non-linear expression ability of the network, enabling the model to better fit the complex temporal correlation pattern of the power consumption ratio coefficients. Through this multi-scale analysis method, the temporal dynamic correlation between the power consumptions of each component of the vacuum circuit breaker can be more comprehensively understood and analyzed, thereby improving the accuracy and reliability of the power consumption anomaly judgment.

[0044] Specifically, in step S43, a cross-temporal scale feature interaction encoding based on core information anchoring is performed on the temporal correlation encoding feature vector between the first-scale power consumption ratio coefficients and the temporal correlation encoding feature vector between the second-scale power consumption ratio coefficients to obtain a temporal multi-scale correlation encoding feature vector between the power consumption ratio coefficients. It should be understood that the temporal correlation encoding feature vector between the first-scale power consumption ratio coefficients and the temporal correlation encoding feature vector between the second-scale power consumption ratio coefficients respectively reflect the temporal correlation characteristics between the power consumption ratio coefficients of multiple components of the vacuum circuit breaker at different time scales. There is usually information redundancy or complementarity between the two. Traditional fusion methods such as feature addition and splicing often have difficulty effectively processing and utilizing cross-scale feature information, which may lead to information loss or poor fusion effect. In response to this, the present application proposes a cross-temporal scale feature interaction encoding method based on core information anchoring. By introducing a core information anchoring mechanism, it can automatically identify and focus on the core feature patterns of the temporal correlation between the power consumption ratio coefficients at the first scale and the second scale, suppress the interference of irrelevant or noise information, and through multi-level interaction analysis, promote the information exchange and fusion between features at different scales, thereby generating a temporal multi-scale correlation encoding feature vector between the power consumption ratio coefficients that synthesizes multi-scale correlation information, providing richer and more accurate information support for subsequent power consumption anomaly judgment. Among them, Figure 4 is a flowchart of sub-step S43 of the intelligent control method for a vacuum circuit breaker according to an embodiment of the present application. As Figure 4 shown, step S43 includes the steps of: S431, respectively extracting the temporal core information of the temporal correlation encoding feature vector between the first-scale power consumption ratio coefficients and the temporal correlation encoding feature vector between the second-scale power consumption ratio coefficients to obtain a temporal core information anchoring encoding vector between the first-scale power consumption ratio coefficients and a temporal core information anchoring encoding vector between the second-scale power consumption ratio coefficients; S432, performing a multi-granularity interaction response encoding on the temporal core information anchoring encoding vector between the first-scale power consumption ratio coefficients and the temporal core information anchoring encoding vector between the second-scale power consumption ratio coefficients to obtain the temporal multi-scale correlation encoding feature vector between the power consumption ratio coefficients.

[0045] More specifically, in a specific example of the present application, step S431 includes: First, constructing a semantic self-correlation association matrix of the temporal correlation encoding feature vector between the first-scale power consumption ratio coefficients and the temporal correlation encoding feature vector between the second-scale power consumption ratio coefficients to obtain a temporal self-correlation association matrix between the first-scale power consumption ratio coefficients and a temporal self-correlation association matrix between the second-scale power consumption ratio coefficients, which is expressed by the formula:

[0046]

[0047] where, (·)T denotes the transpose of a vector, v1 denotes the temporal correlation coding feature vector between the first-scale power consumption ratio coefficients, v2 denotes the temporal correlation coding feature vector between the second-scale power consumption ratio coefficients, M1 denotes the temporal autocorrelation correlation matrix between the first-scale power consumption ratio coefficients, and M2 denotes the temporal autocorrelation correlation matrix between the second-scale power consumption ratio coefficients. is a linear mapping function.

[0048] That is, in this application, through linear mapping and outer product operations, the mutual correlations between the components in the temporal correlation coding feature vector between the first-scale power consumption ratio coefficients and the temporal correlation coding feature vector between the second-scale power consumption ratio coefficients are made explicit, so as to construct the semantic autocorrelation correlation matrix of the two, and generate the temporal autocorrelation correlation matrix between the first-scale power consumption ratio coefficients and the temporal autocorrelation correlation matrix between the second-scale power consumption ratio coefficients. In this way, not only the global structure of the temporal correlation coding feature vector between the first-scale power consumption ratio coefficients and the temporal correlation coding feature vector between the second-scale power consumption ratio coefficients is retained, but also the internal semantic patterns can be captured.

[0049] Then, the temporal autocorrelation correlation matrix between the first-scale power consumption ratio coefficients and the temporal autocorrelation correlation matrix between the second-scale power consumption ratio coefficients are respectively input into the core information anchoring network based on autocorrelation decoupling to obtain the temporal core information anchoring coding vector between the first-scale power consumption ratio coefficients and the temporal core information anchoring coding vector between the second-scale power consumption ratio coefficients, which is expressed by the formula:

[0050]

[0051] where, f Anchor (·) represents the core information anchoring network, decouple(·) represents the decoupling function, x 11 、x 12 、x 1i and x 1n respectively represent the 1st, 2nd, ith, and nth row vectors in the temporal autocorrelation correlation matrix between the first-scale power consumption ratio coefficients, n is the number of rows of the temporal autocorrelation correlation matrix between the first-scale power consumption ratio coefficients, x 21 、x 22 、x 2i and x 2n respectively represent the 1st, 2nd, ith, and nth row vectors in the temporal autocorrelation correlation matrix between the second-scale power consumption ratio coefficients, W 1i and W 2i respectively represent the temporal correlation feature weight matrix between the first-scale power consumption ratio coefficients and the temporal correlation feature weight matrix between the second-scale power consumption ratio coefficients, b 1i and b 2irespectively represent the temporal correlation feature bias vector between the first-scale power consumption ratio coefficients and the temporal correlation feature bias vector between the second-scale power consumption ratio coefficients, represent the temporal correlation feature importance score conversion vector between the first-scale power consumption ratio coefficients, represent the temporal correlation feature importance score conversion vector between the second-scale power consumption ratio coefficients, represent matrix multiplication, e 1i represent x 1i the corresponding temporal correlation feature importance score factor between the first-scale power consumption ratio coefficients, e 2i represent x 2i the corresponding temporal correlation feature importance score factor between the second-scale power consumption ratio coefficients, a 1i represent e 1i the corresponding normalized temporal correlation feature importance score factor between the first-scale power consumption ratio coefficients, a 2i represent e 2i the corresponding normalized temporal correlation feature importance score factor between the second-scale power consumption ratio coefficients, Sigmoid(·) represents the sigmoid function, c1 represents the temporal core information anchoring coding vector between the first-scale power consumption ratio coefficients, and c2 represents the temporal core information anchoring coding vector between the second-scale power consumption ratio coefficients.

[0052] That is, in order to purify redundant feature information, the present application uses a core information anchoring network based on autocorrelation decoupling to refine and purify the internal information of the features of the temporal autocorrelation association matrix between the first-scale power consumption ratio coefficients and the temporal autocorrelation association matrix between the second-scale power consumption ratio coefficients. Through feature decoupling, local feature importance evaluation, and feature weighted aggregation, the feature parts highly correlated with the core semantics in the temporal autocorrelation association matrix between the first-scale power consumption ratio coefficients and the temporal autocorrelation association matrix between the second-scale power consumption ratio coefficients are highlighted, and at the same time, the redundant information is denoised, so as to extract the core anchor point representation with refined structure, that is, the temporal core information anchoring coding vector between the first-scale power consumption ratio coefficients and the temporal core information anchoring coding vector between the second-scale power consumption ratio coefficients.

[0053] Figure 5 is a flowchart of sub-step S432 of the intelligent control method for a vacuum circuit breaker according to an embodiment of the present application. As Figure 5As shown, the step S432 includes the steps of: S4321, performing feature granularity response interaction encoding on the first-scale power consumption ratio coefficient temporal core information anchored encoding vector and the second-scale power consumption ratio coefficient temporal core information anchored encoding vector to obtain a temporal multi-scale feature granularity response interaction encoding vector between power consumption ratio coefficients; S4322, performing eigenvalue granularity response interaction encoding on the first-scale power consumption ratio coefficient temporal core information anchored encoding vector and the second-scale power consumption ratio coefficient temporal core information anchored encoding vector to obtain a temporal multi-scale eigenvalue granularity response interaction encoding vector between power consumption ratio coefficients; S4323, fusing the temporal multi-scale feature granularity response interaction encoding vector between power consumption ratio coefficients and the temporal multi-scale eigenvalue granularity response interaction encoding vector between power consumption ratio coefficients to obtain the temporal multi-scale contrast encoding vector between power consumption ratio coefficients.

[0054] In a specific example of the present application, the step S4321 is expressed by the formula:

[0055]

[0056] where tanh(·) represents the tanh function, W VT represents the temporal multi-scale interaction feature weight matrix between power consumption ratio coefficients, b VT represents the temporal multi-scale interaction feature bias vector between power consumption ratio coefficients, and E granular represents the temporal multi-scale feature granularity response interaction encoding vector between power consumption ratio coefficients.

[0057] That is, by leveraging the powerful non-linear fitting ability of the neural network, from the perspective of the overall structure of the features, the potential association between the first-scale power consumption ratio coefficient temporal core information anchored encoding vector and the second-scale power consumption ratio coefficient temporal core information anchored encoding vector is analyzed. In this way, the synergistic effects and differences between the two at different scales can be captured, and the generated temporal multi-scale feature granularity response interaction encoding vector between power consumption ratio coefficients integrates the core temporal interaction information between power consumption ratio coefficients at different scales, providing an effective feature basis for subsequent intelligent control decisions.

[0058] In a specific example of the present application, the step S4322 is expressed by the formula:

[0059]

[0060] where E value represents the temporal multi-scale eigenvalue granularity response interaction encoding vector between power consumption ratio coefficients.

[0061] That is, from the perspective of eigenvalues, an interactive encoding is performed on the time-series core information anchoring encoding vector between the first-scale power consumption ratio coefficients and the time-series core information anchoring encoding vector between the second-scale power consumption ratio coefficients. By focusing on the specific values of the eigenvalues and their changes at different scales, the mutual influence and correlation between the eigenvalues at different scales are analyzed to obtain the time-series multi-scale eigenvalue granularity response interactive encoding vector between the power consumption ratio coefficients. In this way, the time-series correlation between different scales can be further explored at the numerical level, and the interactive encoding information of the feature granularity can be supplemented.

[0062] In a specific example of the present application, the step S4323 includes: concatenating and fusing the time-series multi-scale feature granularity response interactive encoding vector between the power consumption ratio coefficients and the time-series multi-scale eigenvalue granularity response interactive encoding vector between the power consumption ratio coefficients to obtain the time-series multi-scale contrast encoding vector between the power consumption ratio coefficients, which is expressed by the formula:

[0063] V f = concat[E granular ; E value

[0064] where concat(·) represents the concatenation function, and V f represents the time-series multi-scale contrast encoding vector between the power consumption ratio coefficients.

[0065] That is, in order to integrate the interactive information of the feature granularity and the eigenvalue granularity in the present application, the time-series multi-scale feature granularity response interactive encoding vector between the power consumption ratio coefficients and the time-series multi-scale eigenvalue granularity response interactive encoding vector between the power consumption ratio coefficients are concatenated to generate the time-series multi-scale contrast encoding vector between the power consumption ratio coefficients, providing a richer feature basis for subsequent analysis and decision-making.

[0066] ​Specifically, this application takes into account that the difference in the modeling representations between the time-series multi-scale feature granularity response interaction coding vectors among power consumption ratio coefficients and the time-series multi-scale eigenvalue granularity response interaction coding vectors among power consumption ratio coefficients may cause unstable perturbations in the feature manifold interface of the time-series multi-scale contrast coding vectors among power consumption ratio coefficients that incorporate multi-granularity information after fusion. Therefore, in a preferred example of this application, the step S4323 includes: performing feature distribution gradient constraint correction based on bidirectional interaction on the time-series multi-scale feature granularity response interaction coding vectors among power consumption ratio coefficients and the time-series multi-scale eigenvalue granularity response interaction coding vectors among power consumption ratio coefficients to obtain optimized time-series multi-scale feature granularity response interaction coding vectors among power consumption ratio coefficients and optimized time-series multi-scale eigenvalue granularity response interaction coding vectors among power consumption ratio coefficients; performing cascade fusion on the optimized time-series multi-scale feature granularity response interaction coding vectors among power consumption ratio coefficients and the optimized time-series multi-scale eigenvalue granularity response interaction coding vectors among power consumption ratio coefficients to obtain the time-series multi-scale contrast coding vectors among power consumption ratio coefficients, which is expressed by the formula:

[0067]

[0068]

[0069] V f =concat[E granular ';E value ']

[0070] where E gi is the eigenvalue at the i-th position in E granular , E vi is the eigenvalue at the i-th position in E value , cos(·) represents the cosine function, E gi ' is the optimized eigenvalue corresponding to E gi , E vi ' is the optimized eigenvalue corresponding to E vi , E granular ' is the optimized time-series multi-scale feature granularity response interaction coding vector among power consumption ratio coefficients, and E value ' is the optimized time-series multi-scale eigenvalue granularity response interaction coding vector among power consumption ratio coefficients.

[0071] Here, the temporal multi-scale eigenvalue granularity response interaction coding vector between power consumption ratio coefficients is used as an extensibility constraint representation. For the overall feature interaction distribution growth under the eigenvalue-by-eigenvalue diffusion process, an interface shape perturbation deviation modeling of the overall distribution of the temporal multi-scale feature granularity response interaction coding vector between power consumption ratio coefficients is performed based on the growth index representation under the extensibility constraint. That is, for the interaction interface gradient under each eigenvalue granularity as the perturbation contribution factor, the growth index stabilization contribution of the gradient diffusion under eigenvalue interdependence is determined to achieve the growth mode gradient correction dominated by perturbation stabilization, and improve the manifold interface stability of the response interaction coding vector between the features.

[0072] Specifically, in step S44, based on the temporal multi-scale correlation coding feature vector between the power consumption ratio coefficients, the judgment result is determined. In a specific example of the present application, step S44 includes: inputting the temporal multi-scale correlation coding feature vector between the power consumption ratio coefficients into a power consumption anomaly diagnoser based on a classifier to obtain the judgment result, and the judgment result is used to indicate whether the power consumption of the vacuum circuit breaker is abnormal. Specifically, the classifier is trained with a large amount of historical power consumption data and can accurately distinguish the temporal feature correlation patterns between the multi-component power consumption ratio coefficients in the normal power consumption state and the abnormal power consumption state of the vacuum circuit breaker. Therefore, when receiving the temporal multi-scale correlation coding feature vector between the power consumption ratio coefficients, it can combine the knowledge it has learned, quickly and accurately judge the current power consumption state of the vacuum circuit breaker, and output the corresponding judgment result, thereby realizing the intelligent diagnosis of the power consumption anomaly of the vacuum circuit breaker.

[0073] In the above intelligent control method for vacuum circuit breakers, in step S5, in response to the determination result that there is an abnormality in the power consumption of the vacuum circuit breaker, the type of power consumption abnormality of the vacuum circuit breaker is determined to obtain a set of power consumption abnormality types. That is, if the determination result is that there is an abnormality in the power consumption of the vacuum circuit breaker, it means that there may be potential fault hazards in the vacuum circuit breaker, and it is necessary to further determine the specific type of power consumption abnormality in order to take corresponding maintenance measures. In the specific implementation process, the abnormal situation can be carefully classified in combination with the pre-set power consumption abnormality type judgment rules. For example, by establishing a fault feature database, the typical features corresponding to different power consumption abnormality types are stored and marked. When the analysis result shows that the power consumption proportion coefficient of the contact resistance continues to exceed the normal range within a certain period of time, and there is no obvious abnormal change in the power consumption of the operating mechanism and the control circuit during this period, and the change relationship between the power consumption of the contact resistance and parameters such as temperature and contact pressure shows a specific abnormal trend, it is determined as the power consumption abnormality type of the contact resistance and added to the set of power consumption abnormality types. Similarly, for the abnormal power consumption of the operating mechanism and the abnormal power consumption of the control circuit, etc., similar rules are also used for judgment and classification to form a set of power consumption abnormality types. In this way, intuitive fault information can be provided for maintenance personnel, so that maintenance personnel can prepare maintenance tools and spare parts targeted, and formulate detailed maintenance plans. For example, if it is determined that the power consumption of the operating mechanism is abnormal, maintenance personnel can focus on checking the wear condition of the parts of the operating mechanism, the lubrication state, and the operating performance of the motor, etc.; if it is the abnormal power consumption of the control circuit, the electronic components and line connections of the control circuit can be carefully checked, so as to improve the fault handling efficiency, reduce the power outage time, and reduce the losses brought to the power system by equipment failures.

[0074] In addition, if in response to the determination result that there is no abnormality in the power consumption of the vacuum circuit breaker, in order to maintain high standards of safety and reliability, the system will automatically start a cyclic monitoring mechanism. This mechanism depends on the pre-set time interval and regularly re-evaluates various parameters of the vacuum circuit breaker. In this way, even in a non-fault state, the real-time status of the equipment health can be ensured. This continuous monitoring helps to detect any potential problems early, so as to take measures to prevent small problems from evolving into serious faults. It should be noted that after confirming that there is no abnormality in the power consumption of the vacuum circuit breaker, the relevant environmental factors will also be evaluated. This includes temperature, humidity, and other external conditions that may affect the equipment performance. Understanding these environmental variables is very important for comprehensively grasping the working status of the equipment. For example, under extreme climate conditions, even if the current detection results show that everything is normal, additional protective measures may be needed just in case. Therefore, the system will adjust the monitoring frequency or set warning thresholds according to the real-time obtained environmental data to ensure the best operating state in any situation.

[0075] In the above intelligent control method for vacuum circuit breakers, in step S6, the set of abnormal power consumption types is fed back to the remote monitoring center of the vacuum circuit breaker. Here, the remote monitoring center serves as the core hub for monitoring the equipment of the entire power system and can monitor and manage the operating states of multiple vacuum circuit breakers in real time and comprehensively. By feeding back the set of abnormal power consumption types to the remote monitoring center, it is convenient for the monitoring personnel to promptly grasp the abnormal conditions of each device, enabling them to coordinate the operation and maintenance resources from a global perspective, uniformly arrange the maintenance work, achieve efficient management of the power system equipment, improve the operation and maintenance efficiency, and ensure the stable operation of the power system.

[0076] Specifically, first, the center is equipped with efficient data cleaning tools to remove the error or redundant information that may be mixed in during the transmission process. Only by ensuring the quality of the data can a reliable basis be provided for subsequent analysis. Then, by applying advanced data analysis algorithms, such as machine learning models, the historical operating data of each vacuum circuit breaker and the currently received set of abnormal power consumption types can be deeply mined. These algorithms can not only identify the immediate problems but also predict the possible future fault modes, thus providing a basis for formulating preventive maintenance strategies.

[0077] In addition to data processing, the effective transmission of information is also one of the key factors in ensuring the stable operation of the power system. Supported by modern communication technologies, a stable communication link is established between the remote monitoring center and vacuum circuit breakers everywhere. This includes not only the application of high-speed communication technologies such as 5G networks but also data transmission protocols optimized for specific application scenarios. For example, in some extreme environments, such as remote areas or under adverse weather conditions, how to ensure the stability of data transmission becomes a challenge. For this reason, engineers have developed a series of highly adaptable data transmission solutions to ensure the secure transmission of critical data even under poor network conditions.

[0078] Furthermore, the user interface design of the remote monitoring center is also crucial for improving work efficiency. An intuitive and easy-to-operate interface can greatly reduce the time required for monitoring personnel to understand information and increase their speed of making correct decisions. The interface usually displays various parameters from different vacuum circuit breakers, including but not limited to the contact resistance of the contacts, the status information of the operating mechanism and the control circuit. In addition, devices with abnormal conditions are highlighted through color coding or alarm sounds, etc., so that the monitoring personnel can quickly locate the problems. More importantly, detailed help documents and operation guides are integrated into the interface, facilitating new employees to quickly get started and master the necessary skills.

[0079] Furthermore, the remote monitoring center also undertakes the task of coordinating operation and maintenance resources. Once it is determined that the power consumption of a certain vacuum circuit breaker or certain vacuum circuit breakers is abnormal, the center will arrange the corresponding maintenance team to go to the site for handling according to the specific situation. This involves complex scheduling algorithms, aiming to maximize resource utilization while minimizing the maintenance response time. For example, by analyzing factors such as the distance between different locations, traffic conditions, and the professional skills of maintenance personnel, the system can automatically recommend the optimal dispatch plan. This method not only improves the emergency response efficiency but also reduces the power outage risk caused by equipment failures.

[0080] In summary, the intelligent control method for vacuum circuit breakers based on the embodiments of the present application is elucidated. It uses a neural network model based on deep learning to perform multi-scale temporal correlation aggregation analysis on the power consumption proportional coefficients of the contact resistance, operating mechanism, and control circuit in the vacuum circuit breaker, so as to capture the multi-scale temporal dynamic correlation characteristics between the power consumption proportional coefficients of multiple components, reveal the power consumption influence law between different components inside the vacuum circuit breaker, and thus realize the accurate judgment of the abnormal power consumption state of the vacuum circuit breaker by considering the temporal dynamic interaction relationship between the power consumptions of different components. By considering the temporal power consumption change trends of each component and the dynamic correlation pattern between them, this method can analyze the power consumption state of the vacuum circuit breaker more comprehensively, identify the abnormal power consumption situation of the vacuum circuit breaker, and thus better meet the power consumption abnormal detection requirements under various complex working conditions.

[0081] Furthermore, an intelligent control system for vacuum circuit breakers is also provided.

[0082] Figure 6 is a block diagram of the intelligent control system for vacuum circuit breakers according to the embodiments of the present application. As Figure 6As shown in the figure, the intelligent control system 100 of a vacuum circuit breaker according to an embodiment of the present application includes: a contact resistance power consumption ratio coefficient acquisition module 110, configured to acquire a time queue of the power consumption ratio coefficient of the contact resistance of the contacts in the vacuum circuit breaker; an operating structure power consumption ratio coefficient acquisition module 120, configured to acquire a time queue of the power consumption ratio coefficient of the operating structure in the vacuum circuit breaker; a control circuit power consumption ratio coefficient acquisition module 130, configured to acquire a time queue of the power consumption ratio coefficient of the control circuit in the vacuum circuit breaker; a power consumption anomaly determination module 140, configured to determine whether the power consumption of the vacuum circuit breaker is abnormal based on the time queue of the power consumption ratio coefficient of the contact resistance of the contacts, the time queue of the power consumption ratio coefficient of the operating structure, and the time queue of the power consumption ratio coefficient of the control circuit, wherein determining whether the power consumption of the vacuum circuit breaker is abnormal includes: performing multi-scale time series correlation aggregation analysis and cross-time series scale core feature anchoring interaction based on the power consumption ratio coefficient on the contact resistance of the contacts, the operating structure, and the control circuit to obtain a determination result; a power consumption anomaly type determination module 150, configured to, in response to the determination result indicating that the power consumption of the vacuum circuit breaker is abnormal, determine the power consumption anomaly type of the vacuum circuit breaker to obtain a set of power consumption anomaly types; and a power consumption anomaly feedback module 160, configured to feedback the set of power consumption anomaly types to the remote monitoring center of the vacuum circuit breaker.

[0083] Here, those skilled in the art can understand that the specific operations of the various modules in the above intelligent control system of the vacuum circuit breaker have been described in detail in the description of the above Figures 1 to 5 intelligent control method of the vacuum circuit breaker, and therefore, the repeated description thereof will be omitted.

[0084] The basic principles of the present invention have been described above in conjunction with specific embodiments. However, it should be noted that the advantages, advantages, effects, etc. mentioned in the present invention are only examples and not limitations, and it cannot be considered that these advantages, advantages, effects, etc. are essential for each embodiment of the present invention. In addition, the specific details of the above embodiments are only for the purposes of illustration and easy understanding, and are not limitations. The above details do not limit the present invention to necessarily adopt the above specific details for implementation.

[0085] In the above embodiments, the descriptions of the respective embodiments have their own emphases. For parts not detailed or recorded in a certain embodiment, reference may be made to the relevant descriptions of other embodiments. In the several embodiments provided by the present invention, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For example, the unit division is only a logical function division, and there may be other division methods in actual implementation. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0086] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above exemplary embodiments, and can be implemented in other specific forms without departing from the spirit or basic characteristics of the present invention. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be included in the present invention. Any reference signs in the claims should not be regarded as limiting the claimed rights.

[0087] In addition, it is obvious that the word "including" does not exclude other units or steps, and the singular does not exclude the plural. The multiple units stated in the system claims can also be implemented by one unit through software or hardware.

[0088] Finally, it should be noted that the above description has been given for purposes of illustration and description. In addition, the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. An intelligent control method for a vacuum circuit breaker, characterized in that, Including: Step 1: Obtain the time queue of the power consumption proportionality coefficient of the contact resistance in the vacuum circuit breaker; Step 2: Obtain the time queue of the power consumption proportionality coefficient of the operating structure in the vacuum circuit breaker; Step 3: Obtain the time queue of the power consumption proportionality coefficient of the control circuit in the vacuum circuit breaker; Step 4: Based on the time queue of the power consumption proportionality coefficient of the contact resistance, the time queue of the power consumption proportionality coefficient of the operating structure, and the time queue of the power consumption proportionality coefficient of the control circuit, determine whether the power consumption of the vacuum circuit breaker is abnormal. Among them, determining whether the power consumption of the vacuum circuit breaker is abnormal includes: performing multi-scale time series correlation aggregation analysis and cross-time-scale core feature anchoring interaction based on the power consumption proportionality coefficient for the contact resistance, the operating structure, and the control circuit to obtain a judgment result; Step 5: In response to the judgment result that the power consumption of the vacuum circuit breaker is abnormal, determine the power consumption abnormal type of the vacuum circuit breaker to obtain a set of power consumption abnormal types; Step 6: Feed back the set of power consumption abnormal types to the remote monitoring center of the vacuum circuit breaker.

2. The intelligent control method of the vacuum circuit breaker according to claim 1, wherein The said Step 4 includes: Perform data structuring processing on the time queue of the power consumption proportionality coefficient of the contact resistance, the time queue of the power consumption proportionality coefficient of the operating structure, and the time queue of the power consumption proportionality coefficient of the control circuit to obtain a multi-component power consumption proportionality coefficient time series aggregation matrix; Perform multi-scale time series correlation analysis between the power consumption proportionality coefficients on the multi-component power consumption proportionality coefficient time series aggregation matrix to obtain a first-scale time series correlation coding feature vector between the power consumption proportionality coefficients and a second-scale time series correlation coding feature vector between the power consumption proportionality coefficients; Perform cross-time-scale feature interaction coding based on core information anchoring on the first-scale time series correlation coding feature vector between the power consumption proportionality coefficients and the second-scale time series correlation coding feature vector between the power consumption proportionality coefficients to obtain a time series multi-scale correlation coding feature vector between the power consumption proportionality coefficients; Based on the time series multi-scale correlation coding feature vector between the power consumption proportionality coefficients, determine the judgment result.

3. The intelligent control method of the vacuum circuit breaker according to claim 2, characterized in that, Performing multi-scale time series correlation analysis between the power consumption proportionality coefficients on the multi-component power consumption proportionality coefficient time series aggregation matrix to obtain a first-scale time series correlation coding feature vector between the power consumption proportionality coefficients and a second-scale time series correlation coding feature vector between the power consumption proportionality coefficients includes: Use a first convolutional neural network to perform two-dimensional convolutional coding and feature activation on the multi-component power consumption proportionality coefficient time series aggregation matrix to obtain the first-scale time series correlation coding feature vector between the power consumption proportionality coefficients; Use a second convolutional neural network to perform two-dimensional convolutional coding and feature activation on the multi-component power consumption proportionality coefficient time series aggregation matrix to obtain the second-scale time series correlation coding feature vector between the power consumption proportionality coefficients, where the first convolutional neural network and the second convolutional neural network have different convolutional kernel sizes and strides.

4. The intelligent control method of the vacuum circuit breaker according to claim 3, characterized in that, Perform cross-temporal scale feature interaction encoding based on core information anchoring on the temporal correlation encoding feature vector between the first-scale power consumption ratio coefficients and the temporal correlation encoding feature vector between the second-scale power consumption ratio coefficients to obtain a temporal multi-scale correlation encoding feature vector between power consumption ratio coefficients, including: Extract the temporal core information of the temporal correlation encoding feature vector between the first-scale power consumption ratio coefficients and the temporal correlation encoding feature vector between the second-scale power consumption ratio coefficients respectively to obtain a temporal core information anchoring encoding vector between the first-scale power consumption ratio coefficients and a temporal core information anchoring encoding vector between the second-scale power consumption ratio coefficients; Perform multi-granularity interaction response encoding on the temporal core information anchoring encoding vector between the first-scale power consumption ratio coefficients and the temporal core information anchoring encoding vector between the second-scale power consumption ratio coefficients to obtain the temporal multi-scale correlation encoding feature vector between power consumption ratio coefficients.

5. The intelligent control method of the vacuum circuit breaker according to claim 4, characterized in that, Extract the temporal core information of the temporal correlation encoding feature vector between the first-scale power consumption ratio coefficients and the temporal correlation encoding feature vector between the second-scale power consumption ratio coefficients respectively to obtain a temporal core information anchoring encoding vector between the first-scale power consumption ratio coefficients and a temporal core information anchoring encoding vector between the second-scale power consumption ratio coefficients, including: Construct semantic self-correlation association matrices of the temporal correlation encoding feature vector between the first-scale power consumption ratio coefficients and the temporal correlation encoding feature vector between the second-scale power consumption ratio coefficients to obtain a temporal self-correlation association matrix between the first-scale power consumption ratio coefficients and a temporal self-correlation association matrix between the second-scale power consumption ratio coefficients; Input the temporal self-correlation association matrix between the first-scale power consumption ratio coefficients and the temporal self-correlation association matrix between the second-scale power consumption ratio coefficients into a core information anchoring network based on self-correlation decoupling respectively to obtain the temporal core information anchoring encoding vector between the first-scale power consumption ratio coefficients and the temporal core information anchoring encoding vector between the second-scale power consumption ratio coefficients.

6. The intelligent control method of the vacuum circuit breaker according to claim 5, characterized in that, Perform multi-granularity interaction response encoding on the temporal core information anchoring encoding vector between the first-scale power consumption ratio coefficients and the temporal core information anchoring encoding vector between the second-scale power consumption ratio coefficients to obtain the temporal multi-scale correlation encoding feature vector between power consumption ratio coefficients, including: Perform feature granularity response interaction encoding on the temporal core information anchoring encoding vector between the first-scale power consumption ratio coefficients and the temporal core information anchoring encoding vector between the second-scale power consumption ratio coefficients to obtain a temporal multi-scale feature granularity response interaction encoding vector between power consumption ratio coefficients; Perform eigenvalue granularity response interaction encoding on the temporal core information anchoring encoding vector between the first-scale power consumption ratio coefficients and the temporal core information anchoring encoding vector between the second-scale power consumption ratio coefficients to obtain a temporal multi-scale eigenvalue granularity response interaction encoding vector between power consumption ratio coefficients; Fuse the temporal multi-scale feature granularity response interaction encoding vector between power consumption ratio coefficients and the temporal multi-scale eigenvalue granularity response interaction encoding vector between power consumption ratio coefficients to obtain the temporal multi-scale contrast encoding vector between power consumption ratio coefficients.

7. The intelligent control method of the vacuum circuit breaker according to claim 6, characterized in that Fusing the time-series multi-scale feature granularity response interaction coding vectors between the power consumption proportion coefficients and the time-series multi-scale feature value granularity response interaction coding vectors between the power consumption proportion coefficients to obtain the time-series multi-scale contrast coding vectors between the power consumption proportion coefficients, including: Cascading and fusing the time-series multi-scale feature granularity response interaction coding vectors between the power consumption proportion coefficients and the time-series multi-scale feature value granularity response interaction coding vectors between the power consumption proportion coefficients to obtain the time-series multi-scale contrast coding vectors between the power consumption proportion coefficients.

8. The intelligent control method of the vacuum circuit breaker according to claim 6, characterized in that Fusing the time-series multi-scale feature granularity response interaction coding vectors between the power consumption proportion coefficients and the time-series multi-scale feature value granularity response interaction coding vectors between the power consumption proportion coefficients to obtain the time-series multi-scale contrast coding vectors between the power consumption proportion coefficients, including: Performing feature distribution gradient constraint correction based on bidirectional interaction on the time-series multi-scale feature granularity response interaction coding vectors between the power consumption proportion coefficients and the time-series multi-scale feature value granularity response interaction coding vectors between the power consumption proportion coefficients to obtain optimized time-series multi-scale feature granularity response interaction coding vectors between the power consumption proportion coefficients and optimized time-series multi-scale feature value granularity response interaction coding vectors between the power consumption proportion coefficients; Cascading and fusing the optimized time-series multi-scale feature granularity response interaction coding vectors between the power consumption proportion coefficients and the optimized time-series multi-scale feature value granularity response interaction coding vectors between the power consumption proportion coefficients to obtain the time-series multi-scale contrast coding vectors between the power consumption proportion coefficients.

9. The intelligent control method of the vacuum circuit breaker according to claim 6, characterized in that, Based on the time-series multi-scale correlation coding feature vectors between the power consumption proportion coefficients, determining the judgment result, including: Inputting the time-series multi-scale correlation coding feature vectors between the power consumption proportion coefficients into a power consumption anomaly diagnostic device based on a classifier to obtain the judgment result, and the judgment result is used to indicate whether the power consumption of the vacuum circuit breaker is abnormal.

10. An intelligent control system for a vacuum circuit breaker, characterized in that, Including: A contact resistance power consumption proportion coefficient acquisition module, configured to acquire a time queue of the power consumption proportion coefficients of the contact resistance of the contacts in the vacuum circuit breaker; An operating structure power consumption proportion coefficient acquisition module, configured to acquire a time queue of the power consumption proportion coefficients of the operating structure in the vacuum circuit breaker; A control circuit power consumption proportion coefficient acquisition module, configured to acquire a time queue of the power consumption proportion coefficients of the control circuit in the vacuum circuit breaker; A power consumption anomaly judgment module, configured to judge whether the power consumption of the vacuum circuit breaker is abnormal based on the time queue of the power consumption proportion coefficients of the contact resistance of the contacts, the time queue of the power consumption proportion coefficients of the operating structure, and the time queue of the power consumption proportion coefficients of the control circuit. Among them, judging whether the power consumption of the vacuum circuit breaker is abnormal includes: performing multi-scale time-series correlation aggregation analysis and cross-time-scale core feature anchoring interaction on the contact resistance, the operating structure, and the control circuit based on the power consumption proportion coefficients to obtain a judgment result; A power consumption anomaly type determination module, configured to determine the power consumption anomaly type of the vacuum circuit breaker to obtain a set of power consumption anomaly types in response to the judgment result indicating that the power consumption of the vacuum circuit breaker is abnormal; A power consumption anomaly feedback module, configured to feedback the set of power consumption anomaly types to the remote monitoring center of the vacuum circuit breaker.

Images