Pole-mounted circuit breaker state early warning method, device, equipment and storage medium

Abstract

The application provides a pole-mounted circuit breaker state early warning method, device, equipment and storage medium, the method comprises the steps of: obtaining current data, vibration data and switch operation data of the pole-mounted circuit breaker; correcting the state early warning model according to the switch operation data; inputting the current data into the preset current repair model to obtain current standard data, and determining the current disconnection time according to the current data; determining the arc duration and arc disturbance data of the pole-mounted circuit breaker according to the current disconnection time, the current data and the current standard data; determining the arc characteristic data according to the arc duration and the arc disturbance data, and obtaining the arc characteristic vector after vector processing; vectorizing the vibration data to obtain a vibration feature vector; inputting the arc characteristic vector and the vibration feature vector into the corrected state early warning model for fusion analysis to obtain the aging evaluation value of the pole-mounted circuit breaker, and outputting a state early warning prompt according to the aging evaluation value.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of big data, and in particular to a state early warning method, device and equipment of a pole-mounted circuit breaker and a storage medium. BACKGROUND

[0002] In modern power systems, pole-mounted circuit breakers are key components for protecting electrical equipment from short-circuit and overload damage. Their operating state directly affects the safety and stability of the power grid and the reliability of power supply. Traditionally, the maintenance and repair of pole-mounted circuit breakers mainly rely on periodic manual inspection, which faces many challenges. First, manual inspection is not only time-consuming and labor-intensive, but also inefficient, making it difficult to cover widely distributed power facilities, especially in remote or harsh environments. Second, it is often difficult to accurately determine the internal wear and tear or potential failure of a pole-mounted circuit breaker by visual observation and conventional instrument detection, resulting in many hidden dangers that cannot be discovered in time. More importantly, this post-maintenance approach cannot provide early warning of failures. Once a pole-mounted circuit breaker fails, it may cause a large-scale power outage, resulting in economic losses. SUMMARY

[0003] The present application provides a state early warning method, device and equipment of a pole-mounted circuit breaker, which is used to analyze the data of the pole-mounted circuit breaker and provide early warning of abnormal states of the pole-mounted circuit breaker.

[0004] In a first aspect, the present application provides a state early warning method of a pole-mounted circuit breaker, which comprises:

[0005] obtaining current data, vibration data and switch operation data of the pole-mounted circuit breaker;

[0006] correcting a preset state early warning model according to the switch operation data to obtain a corrected state early warning model;

[0007] inputting the current data into a preset current repair model to obtain current standard data, and determining a current disconnection time according to the current data;

[0008] determining arc duration and arc disturbance data of the pole-mounted circuit breaker according to the current disconnection time, the current data and the current standard data;

[0009] determining arc feature data according to the arc duration and the arc disturbance data, performing vector processing on the arc feature data to obtain an arc feature vector, and performing vectorization processing on the vibration data to obtain a vibration feature vector;

[0010] The arc feature vector and the vibration feature vector are input into the corrected state early warning model for fusion analysis to obtain an aging evaluation value of the pole-mounted circuit breaker, and a state early warning prompt is output according to the aging evaluation value.

[0011] In a second aspect, the embodiments of the present application provide a pole-mounted circuit breaker state early warning device, which comprises:

[0012] A data acquisition module is configured to acquire current data, vibration data and switch operation data of the pole-mounted circuit breaker.

[0013] A model correction module is configured to correct a preset state early warning model according to the switch operation data to obtain a corrected state early warning model.

[0014] A data repair module is configured to input the current data into a preset current repair model to obtain current standard data, and determine a current disconnection time according to the current data.

[0015] A data extraction module is configured to determine arc duration and arc disturbance data of the pole-mounted circuit breaker according to the current disconnection time, the current data and the current standard data.

[0016] A vector conversion module is configured to determine arc feature data according to the arc duration and the arc disturbance data, perform vector processing on the arc feature data to obtain an arc feature vector, and perform vectorization processing on the vibration data to obtain a vibration feature vector.

[0017] A result output module is configured to input the arc feature vector and the vibration feature vector into the corrected state early warning model for fusion analysis to obtain an aging evaluation value of the pole-mounted circuit breaker, and output a state early warning prompt according to the aging evaluation value.

[0018] In a third aspect, the embodiments of the present application provide an electronic device, which comprises a memory and a processor.

[0019] The memory is configured to store a computer program.

[0020] The processor is configured to execute the computer program and implement the pole-mounted circuit breaker state early warning method as any of the embodiments of the present application when executing the computer program.

[0021] In a fourth aspect, the embodiments of the present application provide a computer readable storage medium, which stores a computer program, and the computer program causes a processor to implement the pole-mounted circuit breaker state early warning method as any of the embodiments of the present application when the computer program is executed by the processor.

[0022] The embodiment of the present application provides a state early warning method of a pole-mounted circuit breaker, which comprises the following steps: obtaining current data, vibration data and switch operation data of the pole-mounted circuit breaker; correcting a preset state early warning model according to the switch operation data to obtain a corrected state early warning model; inputting the current data into a preset current repair model to obtain current standard data, and determining a current disconnection time according to the current data; determining arc duration and arc disturbance data of the pole-mounted circuit breaker according to the current disconnection time, the current data and the current standard data; determining arc characteristic data according to the arc duration and the arc disturbance data, performing vector processing on the arc characteristic data to obtain an arc characteristic vector, and performing vectorization processing on the vibration data to obtain a vibration characteristic vector; inputting the arc characteristic vector and the vibration characteristic vector into the corrected state early warning model for fusion analysis to obtain an aging evaluation value of the pole-mounted circuit breaker, and outputting a state early warning prompt according to the aging evaluation value. Through the above method, the state early warning model is corrected through the switch operation data, the prediction accuracy of the state early warning model is improved, the current disconnection time is determined through the current data, the current standard data is obtained through the repair of the current data, and the current duration can be accurately analyzed according to the current standard data, the current data and the current disconnection time, so that the arc disturbance data is obtained, the arc characteristic data for evaluating arc damage is obtained according to the current duration and the arc disturbance data, and the corrected state early warning model can more accurately evaluate the aging evaluation value of the pole-mounted circuit breaker in combination with the vibration data, automatic state early warning of the pole-mounted circuit breaker is realized, possible faults of the pole-mounted circuit breaker can be judged in advance, manual intervention is prompted, circuit faults are reduced, and economic losses are reduced. BRIEF DESCRIPTION OF DRAWINGS

[0023] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0024] Figure 1 A schematic flow chart of a state early warning method of a pole-mounted circuit breaker provided by the embodiment of the present application is shown in the figure.

[0025] Figure 2 A schematic diagram of a current waveform provided by the embodiment of the present application is shown in the figure.

[0026] Figure 3 A schematic block diagram of a state early warning device of a pole-mounted circuit breaker provided by the embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0027] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0028] The flowchart shown in the attached diagram is for illustrative purposes only and does not necessarily include all content and operations / steps, nor does it necessarily have to be performed in the order described. For example, some operations / steps can be broken down, combined, or partially merged, so the actual execution order may change depending on the actual situation.

[0029] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the scope of the application. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0030] It should also be further understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0031] Please see Figure 1 , Figure 1 This application also provides a schematic flowchart of a status early warning method for pole-mounted circuit breakers. (See attached diagram.) Figure 1 As shown, the specific steps of the status early warning method for the pole-mounted circuit breaker include: S101-S106.

[0032] S101. Obtain the current data, vibration data, and switch operation data of the pole-mounted circuit breaker.

[0033] For example, the current data of the pole-mounted circuit breaker can be collected by a current transformer or a smart meter. For example, the current data is collected by a current transformer installed on the power supply side or the load side of the pole-mounted circuit breaker, which can monitor the current intensity and waveform passing through the circuit breaker in real time. The current transformer converts the large current into a small current (usually 5A or 1A) in proportion, which is convenient for safe measurement and remote transmission to the data collection system. The vibration data of the pole-mounted circuit breaker can be collected by an acceleration sensor. The acceleration sensor is directly installed on the housing or key components of the circuit breaker, which can sense and record the vibration data of the device during operation, including vibration frequency and amplitude. These vibration data are crucial for detecting mechanical wear, imbalance or looseness and other faults. The switch operation data of the pole-mounted circuit breaker is collected by the control unit of the pole-mounted circuit breaker. The current in the power grid is fluctuating, and during the collection of the original current data, obvious noise points are removed, missing values are filled, and standardization processing is performed by using a low-pass filter, Kalman filter, wavelet denoising and the like.

[0034] S102, correcting the preset state early warning model according to the switch operation data to obtain a corrected state early warning model.

[0035] For example, the switch operation data includes the number of switch operations, switch time, switch speed, switch operation record, etc., and in order to simplify the correction process, in this application, the preset state early warning model is corrected by the number of switch operations in the switch operation data. During the correction, the activation function of the state early warning model is mainly corrected. By correcting the activation function of the state early warning model, the output result of the state early warning model is affected, and the early warning accuracy of the state early warning model for each pole-mounted circuit breaker is improved. In this process, the corresponding relationship between different numbers of switch operations and the expected remaining life or failure probability of the pole-mounted circuit breaker needs to be analyzed. For example, as the number of switch operations increases, the expected life of the pole-mounted circuit breaker may gradually decrease, and after a certain number of times, the failure probability increases significantly. Therefore, the greater the number of switch operations of the pole-mounted circuit breaker, the smaller the coefficient for calculating the remaining life in the activation function of the state early warning model.

[0036] The state early warning model is corrected by the switch operation data, which is beneficial to improve the accuracy of the state early warning model in evaluating each pole-mounted circuit breaker.

[0037] S103, inputting the current data into the preset current repair model to obtain current standard data, and determining the current disconnection time according to the current data.

[0038] In the conventional method, the occurrence time of the arc is determined by temperature sensors, sound sensors and other devices. However, the accuracy of the measurement is low, and when the arc duration needs to be accurately analyzed, the error is very large. Since the arc phenomenon is transient, the arc current generated will usually introduce some abnormal high-frequency components into the current data, which will cause the original current data to have distortion points. By comparing the generated simulated arc standard data with the current data, the occurrence time of the arc can be accurately determined, thereby improving the accuracy of calculating the arc duration.

[0039] In S104, the arc duration and the arc disturbance current data of the pole-mounted circuit breaker are determined according to the current disconnection time, the current data and the current standard data.

[0040] In the example, the time when the alternating current amplitude zero-crossing point in the current data is not the current disconnection time, and the current disconnection time is the starting time when the current amplitude in the current data is continuously at zero. After the switch of the pole-mounted circuit breaker is opened, the arc will still cause the arc current to exist in the circuit, and the current in the circuit will disappear only after the amplitude of the arc current returns to zero. The current amplitude of the current data will continue to be at zero until the next closing of the pole-mounted circuit breaker. According to the current disconnection time, an arc occurrence time is determined, and the current data and the standard current data are compared to determine the current distortion time, i.e., the arc occurrence time. The time between the arc occurrence time and the current disconnection time is the arc duration, i.e., the time when the arc exists. The current data between the arc occurrence time and the current disconnection time is the arc disturbance current data.

[0041] In S105, the arc feature data is determined according to the arc duration and the arc disturbance current data, the arc feature data is vector processed to obtain an arc feature vector, and the vibration data is vectorized to obtain a vibration feature vector.

[0042] In the example, in order to reduce the data analysis amount of the model, the data before and after the arc occurrence time is usually analyzed, and the arc duration data and the arc disturbance current data have been extracted according to the arc occurrence time. The generation of the arc often causes abnormal vibration of the pole-mounted circuit breaker due to the release of energy, and the vibration data is usually not generated in the normal power-on process. Therefore, when analyzing the vibration data, the arc occurrence time and the current disconnection time are also referred to for data interception, and then vectorization is performed. Data vectorization is the process of converting original data into a numerical form that can be understood and processed by machine learning and data mining algorithms. For numerical data, normalization processing is generally required to reduce the difference between data, and then a feature matrix or vector is combined, for example, the arc feature data is a multi-dimensional feature matrix determined according to the arc duration and the arc disturbance current data.

[0043] S106, input the arc feature vector and the vibration feature vector into the corrected state early warning model for fusion analysis to obtain an aging evaluation value of the pole-mounted circuit breaker, and output a state early warning prompt according to the aging evaluation value.

[0044] For example, in the corrected state early warning model, the arc feature vector and the vibration feature vector are combined at the feature level to form a composite feature vector containing information of both. This step can include simple splicing or creating more efficient and representative feature combinations through feature engineering methods (such as feature interaction, principal component analysis, etc.). The corrected state early warning model processes and analyzes the composite feature vector to produce one or a series of prediction outputs, including the aging evaluation value. The aging evaluation value reflects the current health status and potential aging degree of the circuit breaker, and the higher the value, the closer the circuit breaker state is to or has reached the stage of needing maintenance or replacement. According to the comparison between the calculated aging evaluation value and the preset threshold, the corresponding state early warning prompt is generated. For example, if the evaluation value exceeds the mild aging threshold but is lower than the moderate aging threshold, the system may issue a maintenance suggestion; if it exceeds the severe aging threshold, an urgent maintenance or replacement warning is triggered immediately. Through the above steps, the comprehensive analysis of arc and vibration features can effectively evaluate the aging degree of the pole-mounted circuit breaker, realize accurate state early warning, and provide strong support for the safe and stable operation of the power system.

[0045] The method comprises the following steps: acquiring current data, vibration data and switch operation data of the pole-mounted circuit breaker; correcting a preset state early warning model according to the switch operation data to obtain a corrected state early warning model; inputting the current data into a preset current repair model to obtain current standard data, and determining a current disconnection time according to the current data; determining arc duration and arc disturbance data of the pole-mounted circuit breaker according to the current disconnection time, the current data and the current standard data; determining arc feature data according to the arc duration and the arc disturbance data, performing vector processing on the arc feature data to obtain an arc feature vector, and performing vectorization processing on the vibration data to obtain a vibration feature vector; inputting the arc feature vector and the vibration feature vector into the corrected state early warning model for fusion analysis to obtain an aging evaluation value of the pole-mounted circuit breaker, and outputting a state early warning prompt according to the aging evaluation value. Through the above method, the state early warning model is corrected through the switch operation data, the prediction accuracy of the state early warning model is improved, the current disconnection time is determined through the current data, the current standard data is obtained by repairing the current data, and the current duration can be accurately analyzed according to the current standard data, the current data and the current disconnection time, so as to obtain the arc disturbance data. According to the current duration and the arc disturbance data, the arc feature data for evaluating the arc damage can be obtained, and the corrected state early warning model can more accurately evaluate the aging evaluation value of the pole-mounted circuit breaker in combination with the vibration data. The automatic state early warning of the pole-mounted circuit breaker is realized, which helps to judge the possible failure of the pole-mounted circuit breaker in advance, so as to prompt manual intervention, reduce circuit failure, and further reduce economic loss.

[0046] In order to more clearly introduce the technical scheme of the present application, the technical scheme of the present application will be introduced through specific embodiments below. It should be noted that the specific embodiments are used to expand the description of the technical scheme of the present application, and are not intended to limit the present application.

[0047] In some embodiments, determining the arc duration and the arc disturbance data of the pole-mounted circuit breaker according to the current disconnection time, the current data and the current standard data comprises: determining a current distortion interval according to the current disconnection time and a preset interval duration; comparing the current data and the current standard data in the current distortion interval, setting a time when the current data deviates from the current standard data as an arc occurrence time; determining the arc duration according to the current disconnection time and the arc occurrence time; and taking the current data corresponding to the current distortion interval as the arc disturbance data.

[0048] For example, refer to Figure 2 , Figure 2 A schematic diagram of a current waveform is shown. As Figure 2As shown in the current data, the starting moment when the current amplitude is continuously at zero is the current breaking moment (t2). The intersection of the waveform of the current data and the waveform of the current standard data is the arc occurrence moment (t1). The above schematic diagram is used for data display and illustration. In actual application, the control unit can directly compare the numerical values to determine the current breaking moment and the arc occurrence moment. The current value corresponding to the current breaking moment is the initial arc current value.

[0049] In some embodiments, the arc characteristic data is determined according to the arc duration and the arc disturbance current data, including: determining the initial arc current value from the arc disturbance current data according to the arc occurrence moment; and calculating the arc characteristic data according to a preset characteristic calculation formula, the arc duration and the initial arc current value.

[0050] For example, in the embodiments of the present application, the arc characteristic data includes arc energy, which is used to evaluate the suppression effect of the pole-mounted circuit breaker on the arc, thereby evaluating the state of the pole-mounted circuit breaker. The arc energy is calculated according to a preset characteristic calculation formula, the arc duration and the initial arc current value, wherein the characteristic calculation formula is specifically:

[0051] ;

[0052] wherein E is the arc energy, C is a constant coefficient, C is determined by the model of the pole-mounted circuit breaker, β is the arc extinguishing medium coefficient of the circuit breaker, β is determined by the type of the arc extinguishing medium of the pole-mounted circuit breaker, t is the arc duration, and I0 is the initial arc current value.

[0053] In some embodiments, the current data is input into a preset current repair model to obtain current standard data, including: obtaining the regional maximum value and the regional minimum value corresponding to the current data; dividing the current data into multiple current analysis data according to the adjacent regional maximum value and the regional minimum value; performing data decomposition on the current analysis data to obtain current amplitude data and current frequency data; calculating the first amplitude mean value and the amplitude standard deviation of the current amplitude data; determining the amplitude distortion point from the current amplitude data according to the first amplitude mean value and the amplitude standard deviation; obtaining current amplitude reference data on both sides of the amplitude distortion point with the amplitude distortion point as the center; calculating the second amplitude mean value of the current amplitude reference data, and taking the second amplitude mean value as the repair amplitude; and repairing the amplitude distortion point according to the current frequency data and the repair amplitude to obtain the current standard data.

[0054] By identifying the regional maximum value and the regional minimum value in the current data, the original current data is cut into multiple segments of "current analysis data" which are more manageable. This method can effectively distinguish different modes or periods of current changes, and facilitate subsequent detailed analysis. By calculating the first amplitude mean value and the amplitude standard deviation of the current amplitude data The concentration trend and fluctuation degree of the current signal can be quantified. For example, if the current amplitude at a certain time point or time period exceeds ±3 , the time point or time period can be considered as an amplitude distortion point. When processing the amplitude distortion point, the amplitude distortion point is reconstructed by the current amplitude reference data on both sides of the amplitude distortion point, the average amplitude of the current amplitude reference data is taken as the reconstructed amplitude of the amplitude distortion point, the original current frequency of the amplitude distortion point is taken as the reconstructed frequency, or the average frequency of the current amplitude reference data is taken as the reconstructed frequency, so as to obtain the current standard data.

[0055] In some embodiments, the state warning model includes a first activation function, and the state warning model is corrected according to the switch operation data to obtain a corrected state warning model, including: matching the switch operation data in a preset switch life evaluation table to obtain a switch life evaluation value, the switch life evaluation table including: switch operation times and corresponding switch life evaluation values; correcting the first activation function according to the switch life evaluation value to obtain a second activation function; taking the state warning model corresponding to the second activation function as the corrected state warning model.

[0056] For example, the life of the switch is closely related to the number of its operations. By collecting and analyzing historical data, the relationship between the number of switch operations and the life of the pole-mounted circuit breaker is obtained, including the number of opening and closing times. Then, based on industry standards or device-specific degradation models, these operation times are converted into switch life evaluation values. This may involve considering the effects of material fatigue, arc wear, etc. to more accurately reflect the current health status of the switch. The state warning model usually uses an activation function to map the monitoring data of the switch into a predefined warning interval. It should be noted that the activation function in this application is a Sigmoid function.

[0057] By introducing the life evaluation value of the switch, the "first activation function" in the state warning model is dynamically adjusted, i.e. "corrected", so that the state warning model is more suitable for specific pole-mounted circuit breakers, and the warning model can better reflect the performance degradation of the switch due to long-term use, thereby improving the accuracy of the state warning model. This correction can improve the timeliness and accuracy of the warning, and avoid premature or late maintenance alerts.

[0058] In some embodiments, the state early warning model comprises a state early warning network and a decision network, the state early warning network comprises a first long short-term memory network, a second long short-term memory network and a threshold cycle network, the decision network comprises a fully connected layer and a second activation function, the arc feature vector and the vibration feature vector are input into the corrected state early warning model for fusion analysis to obtain an aging evaluation value of the pole-mounted circuit breaker, comprising: hidden state feature extraction on the arc feature vector by the first long short-term memory network in the state early warning network to obtain a first hidden state feature vector; hidden state feature extraction on the vibration feature vector by the second long short-term memory network in each state early warning network to obtain a second hidden state feature vector; input of the first hidden state feature vector and the second hidden state feature vector into the threshold cycle network for feature integration to generate an aging feature vector; input of the aging feature vector into the decision network, and failure cause analysis on the aging feature vector by the fully connected layer and the Sigmoid function in the decision network to obtain the failure cause and the credibility of the failure cause.

[0059] In some embodiments, the state early warning prompt comprises a maintenance prompt and a replacement prompt, and the state early warning prompt is output according to the aging evaluation value, comprising: outputting the maintenance prompt if the aging evaluation value is greater than a preset first aging threshold; and outputting the replacement prompt if the aging evaluation value is greater than a preset second aging threshold, the second aging threshold being greater than the first aging threshold.

[0060] Please refer to Figure 3 , Figure 3 The embodiments of the present application also provide a schematic block diagram of a pole-mounted circuit breaker state early warning device, which is used to execute the pole-mounted circuit breaker state early warning method described above. The pole-mounted circuit breaker state early warning device 300 can be configured in a server.

[0061] The server can be a stand-alone server, a server cluster, a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content distribution networks (CDN) and big data and artificial intelligence platforms, etc.

[0062] As shown in Figure 3 , the pole-mounted circuit breaker state early warning device 300 comprises a data acquisition module 301, a model correction module 302, a data repair module 303, a data extraction module 304, a vector conversion module 305 and a result output module 306.

[0063] The data acquisition module 301 is configured to acquire current data, vibration data and switch operation data of the pole-mounted circuit breaker.

[0064] The model correction module 302 is configured to correct the preset state warning model according to the switch operation data to obtain a corrected state warning model.

[0065] In some embodiments, when the model correction module 302 is configured to correct the preset state warning model according to the switch operation data to obtain a corrected state warning model, and the state warning model is configured to include a first activation function, the model correction module 302 is specifically configured to: match the switch operation data with a preset switch life evaluation table to obtain a switch life evaluation value, the switch life evaluation table including switch operation times and corresponding switch life evaluation values; correct the first activation function according to the switch life evaluation value to obtain a second activation function; and take a state warning model corresponding to the second activation function as the corrected state warning model.

[0066] The data repair module 303 is configured to input the current data into a preset current repair model to obtain current standard data, and determine a current disconnection time according to the current data.

[0067] In some embodiments, when the data repair module 303 is configured to input the current data into a preset current repair model to obtain current standard data, the data repair module 303 is specifically configured to: obtain a regional maximum value and a regional minimum value corresponding to the current data; divide the current data into multiple current analysis data according to adjacent regional maximum values and regional minimum values; perform data decomposition on the current analysis data to obtain current amplitude data and current frequency data; calculate a first amplitude mean value and an amplitude standard deviation of the current amplitude data; determine an amplitude distortion point from the current amplitude data according to the first amplitude mean value and the amplitude standard deviation; obtain current amplitude reference data on both sides of the amplitude distortion point as a center to calculate a second amplitude mean value of the current amplitude reference data, and take the second amplitude mean value as a repair amplitude; and repair the amplitude distortion point according to the current frequency data and the repair amplitude to obtain the current standard data.

[0068] The data extraction module 304 is configured to determine arc duration and arc turbulence data of the pole-mounted circuit breaker according to the current disconnection time, the current data and the current standard data.

[0069] In some embodiments, when the data extraction module 304 is configured to determine arc duration and arc turbulence data of the pole-mounted circuit breaker according to the current disconnection time, the current data and the current standard data, the data extraction module 304 is specifically configured to: determine a current distortion interval according to the current disconnection time and a preset interval duration; compare the current data and the current standard data in the current distortion interval, and set a time when the current data deviates from the current standard data as an arc occurrence time; determine the arc duration according to the current disconnection time and the arc occurrence time; and take the current data corresponding to the current distortion interval as the arc turbulence data.

[0070] The vector transformation module 305 is configured to determine arc characteristic data according to the arc duration and the arc disturbance flow data, perform vector processing on the arc characteristic data to obtain an arc characteristic vector, and perform vectorization processing on the vibration data to obtain a vibration characteristic vector.

[0071] In some embodiments, when the vector transformation module 305 is configured to determine the arc characteristic data according to the arc duration and the arc disturbance flow data, the vector transformation module 305 is specifically configured to: determine an initial arc current value from the arc disturbance flow data according to an arc occurrence time; and calculate the arc characteristic data according to a preset characteristic calculation formula, the arc duration, and the initial arc current value.

[0072] The result output module 306 is configured to input the arc characteristic vector and the vibration characteristic vector into the corrected state early warning model for fusion analysis to obtain an aging evaluation value of the pole-mounted circuit breaker, and output a state early warning prompt according to the aging evaluation value.

[0073] In some embodiments, the state early warning model includes a state early warning network and a decision network, the state early warning network includes a first long short-term memory network, a second long short-term memory network, and a threshold cycle network, the decision network includes a fully connected layer and a second activation function, and when the result output module 306 is configured to input the arc characteristic vector and the vibration characteristic vector into the corrected state early warning model for fusion analysis to obtain the aging evaluation value of the pole-mounted circuit breaker, the result output module 306 is specifically configured to: perform hidden state feature extraction on the arc characteristic vector through the first long short-term memory network in the state early warning network to obtain a first hidden state feature vector; perform hidden state feature extraction on the vibration characteristic vector through the second long short-term memory network in each state early warning network to obtain a second hidden state feature vector; input the first hidden state feature vector and the second hidden state feature vector into the threshold cycle network for feature integration to generate an aging feature vector; and input the aging feature vector into the decision network, and perform aging evaluation and aging cause analysis on the aging feature vector through the fully connected layer and the Sigmoid function in the decision network to obtain the aging evaluation value and the aging cause.

[0074] In some embodiments, the state early warning prompt includes a maintenance prompt and a replacement prompt, and when the result output module 306 is configured to output the state early warning prompt according to the aging evaluation value, the result output module 306 is specifically configured to: output the maintenance prompt if the aging evaluation value is greater than a preset first aging threshold; and output the replacement prompt if the aging evaluation value is greater than a preset second aging threshold, the second aging threshold being greater than the first aging threshold.

[0075] An electronic device is provided, and the electronic device includes a memory and a processor. The memory is configured to store a computer program. The processor is configured to execute the computer program and implement the method for state early warning of a pole-mounted circuit breaker according to any one of the embodiments of the present application.

[0076] A computer readable storage medium is provided, and the computer readable storage medium stores a computer program. The computer program is configured to enable a processor to implement the method for state early warning of a pole-mounted circuit breaker according to any one of the embodiments of the present application when the computer program is executed by the processor.

[0077] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present application, and these modifications or replacements should be covered within 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.

Claims

1. A method for early warning of the status of a pole-mounted circuit breaker, characterized in that, The method includes: Acquire current data, vibration data, and switch operation data of the pole-mounted circuit breaker; The switch operation data is matched against a preset switch lifespan assessment table to obtain a switch lifespan assessment value. The switch lifespan assessment table includes: the number of switch operations and their corresponding switch lifespan assessment values. The first activation function of a preset state warning model is corrected based on the switch lifespan assessment value to obtain a second activation function. The state warning model corresponding to the second activation function is used as the corrected state warning model. The state warning model includes a state warning network and a decision network. The state warning network includes a first long short-term memory network, a second long short-term memory network, and a threshold recurrent network. The decision network includes a fully connected layer and the second activation function. The process involves: acquiring the regional maxima and minima corresponding to the current data; dividing the current data into multiple current analysis data sets based on adjacent regional maxima and minima; performing data decomposition on the current analysis data to obtain current amplitude data and current frequency data; calculating the first amplitude mean and amplitude standard deviation of the current amplitude data; determining amplitude distortion points from the current amplitude data based on the first amplitude mean and amplitude standard deviation; acquiring current amplitude reference data on both sides of the amplitude distortion point as the center; calculating the second amplitude mean of the current amplitude reference data and using the second amplitude mean as the repair amplitude; repairing the amplitude distortion point based on the current frequency data and the repair amplitude to obtain current standard data; and determining the current disconnection time based on the current data. Based on the current disconnection time, the current data, and the current standard data, determine the arc duration and arc disturbance data of the pole-mounted circuit breaker; Arc feature data is determined based on the arc duration and arc disturbance data, and the arc feature data is vectorized to obtain an arc feature vector. Similarly, the vibration data is vectorized to obtain a vibration feature vector. The arc feature vector is extracted by a first long short-term memory network in the state warning network to obtain a first hidden state feature vector; the vibration feature vector is extracted by a second long short-term memory network in each state warning network to obtain a second hidden state feature vector; the first and second hidden state feature vectors are input into the threshold recurrent network for feature integration to generate an aging feature vector; the aging feature vector is input into the decision network, and the aging feature vector is evaluated and the cause of aging is analyzed by the fully connected layer and the sigmoid function in the decision network to obtain the aging assessment value and the cause of aging; a state warning prompt is output based on the aging assessment value.

2. The status early warning method for pole-mounted circuit breakers as described in claim 1, characterized in that, The step of determining the arc duration and arc disturbance data of the pole-mounted circuit breaker based on the current disconnection time, the current data, and the current standard data includes: The current distortion range is determined based on the current disconnection time and the preset range duration; In the current distortion range, the current data and the current standard data are compared, and the moment when the current data deviates from the current standard data is set as the moment when the electric arc occurs. The duration of the electric arc is determined based on the time when the current is disconnected and the time when the electric arc occurs. The current data corresponding to the current distortion range is used as the arc disturbance data.

3. The status early warning method for pole-mounted circuit breakers as described in claim 2, characterized in that, The step of determining arc characteristic data based on the arc duration and the arc disturbance data includes: Based on the time of arc occurrence, the initial arc current value is determined from the arc disturbance data; The arc characteristic data are obtained by calculating based on the preset characteristic calculation formula, the arc duration, and the initial arc current value.

4. The status early warning method for pole-mounted circuit breakers as described in claim 1, characterized in that, The status warning prompts include: maintenance prompts and replacement prompts. Based on the aging assessment values, status warning prompts are output, including: If the aging assessment value is greater than the preset first aging threshold, the maintenance prompt is output. If the aging assessment value is greater than the preset second aging threshold, the replacement prompt is output, where the second aging threshold is greater than the first aging threshold.

5. A status early warning device for a pole-mounted circuit breaker, characterized in that, The status warning device for the pole-mounted circuit breaker includes: The data acquisition module is used to acquire current data, vibration data, and switch operation data of the pole-mounted circuit breaker; The model calibration module is used to match the switch operation data with a preset switch lifespan assessment table to obtain a switch lifespan assessment value. The switch lifespan assessment table includes: the number of switch operations and their corresponding switch lifespan assessment values. The module also calibrates the first activation function of a preset state warning model based on the switch lifespan assessment value to obtain a second activation function. The state warning model corresponding to the second activation function is used as the calibrated state warning model. The state warning model includes a state warning network and a decision network. The state warning network includes a first long short-term memory network, a second long short-term memory network, and a threshold recurrent network. The decision network includes a fully connected layer and the second activation function. The data repair module is used to: acquire the regional maximum and minimum values ​​corresponding to the current data; divide the current data into multiple current analysis data based on adjacent regional maximum and minimum values; decompose the current analysis data to obtain current amplitude data and current frequency data; calculate the first amplitude mean and amplitude standard deviation of the current amplitude data; determine the amplitude distortion point from the current amplitude data based on the first amplitude mean and amplitude standard deviation; acquire current amplitude reference data on both sides of the amplitude distortion point as the center; calculate the second amplitude mean of the current amplitude reference data and use the second amplitude mean as the repair amplitude; repair the amplitude distortion point based on the current frequency data and the repair amplitude to obtain current standard data; and determine the current disconnection time based on the current data. The data extraction module is used to determine the arc duration and arc disturbance data of the pole-mounted circuit breaker based on the current disconnection time, the current data, and the current standard data. The vector conversion module is used to determine arc feature data based on the arc duration and the arc disturbance data, perform vector processing on the arc feature data to obtain arc feature vectors, and perform vectorization processing on the vibration data to obtain vibration feature vectors. The result output module is used to extract hidden state features from the arc feature vector through the first long short-term memory network in the state warning network to obtain a first hidden state feature vector; to extract hidden state features from the vibration feature vector through the second long short-term memory network in each state warning network to obtain a second hidden state feature vector; to input the first hidden state feature vector and the second hidden state feature vector into the threshold recurrent network for feature integration to generate an aging feature vector; to input the aging feature vector into the decision network, and to perform aging estimation and aging cause analysis on the aging feature vector through the fully connected layer and the sigmoid function in the decision network to obtain an aging assessment value and an aging cause; and to output a state warning prompt based on the aging assessment value.

6. An electronic device, characterized in that, The electronic device includes a memory and a processor; The memory is used to store computer programs; The processor is configured to execute the computer program and, in executing the computer program, implement the status warning method for the pole-mounted circuit breaker as described in any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, causes the processor to implement the status warning method for a pole-mounted circuit breaker as described in any one of claims 1 to 4.

Images