Vacuum circuit breaker vacuum degree early warning method and system, medium and processor

Abstract

The invention relates to the technical field of vacuum monitoring, and discloses a vacuum circuit breaker vacuum degree early warning method and system, a medium and a processor, and the method comprises the steps: obtaining voltage data of different arcing time gradient tests in vacuum arc extinguish chamber samples in different vacuum states; processing the voltage data through time window cutting and threshold screening to obtain voltage characteristic data; inputting the voltage characteristic data into a BP neural network model for training to obtain a vacuum degree prediction model with an output vacuum degree prediction result; processing the voltage data of the vacuum arc-extinguishing chamber collected in real time, and inputting the processed voltage data into the trained vacuum degree prediction model to obtain a vacuum degree prediction result; and outputting a vacuum degree early warning strategy of the vacuum arc-extinguishing chamber according to the vacuum degree prediction result. According to the invention, the vacuum degree change condition of the vacuum arc-extinguishing chamber is monitored in real time according to the action of the circuit breaker, so that the problems of insulation performance reduction, insufficient arc-extinguishing capability and the like caused by vacuum degree reduction are avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of vacuum monitoring, and particularly to a method, a system, a medium and a processor for early warning of the vacuum degree of a vacuum circuit breaker. Background Art

[0002] The vacuum interrupter relies on vacuum as the medium for arc extinguishing. Accurately judging whether the vacuum degree of the vacuum interrupter decreases is of great significance for evaluating the operating state of the vacuum circuit breaker.

[0003] If the vacuum degree in the vacuum interrupter drops, it is often difficult to reliably extinguish the arc, which may cause interruption failure. Traditional vacuum degree monitoring methods often rely on offline means, or sensors need to be arranged on the body of the vacuum interrupter, and their detection means are difficult to directly measure the vacuum degree of the vacuum circuit breaker online. Summary of the Invention

[0004] Aiming at the problem that it is difficult to directly measure the vacuum degree of the vacuum circuit breaker online in the prior art, the present invention provides a method, a system, a medium and a processor for early warning of the vacuum degree of the vacuum circuit breaker, which can realize the online measurement of the vacuum degree of the vacuum circuit breaker. The specific technical solutions are as follows:

[0005] A method for early warning of the vacuum degree of a vacuum circuit breaker includes:

[0006] Obtaining voltage data of different arcing time gradients in vacuum interrupter samples in different vacuum states;

[0007] Processing the voltage data through time window cutting and threshold screening to obtain voltage characteristic data;

[0008] Inputting the voltage characteristic data into a BP neural network model for training to obtain a vacuum degree prediction model capable of outputting a vacuum degree prediction result;

[0009] Inputting the voltage data of the vacuum interrupter collected in real time into the trained vacuum degree prediction model to obtain a vacuum degree prediction result;

[0010] Outputting a vacuum degree early warning strategy for the vacuum interrupter according to the vacuum degree prediction result.

[0011] Preferably, the obtaining voltage data of different arcing time gradients in vacuum interrupter samples in different vacuum states includes:

[0012] Obtaining voltage data of different arcing time gradients in vacuum interrupter samples in normal vacuum state and abnormal vacuum state respectively.

[0013] Preferably, the processing the voltage data through time window cutting and threshold screening to obtain voltage characteristic data includes:

[0014] Divide and partition the voltage data at a preset time interval;

[0015] Use a comparison function to determine whether the divided data is arc voltage;

[0016] Compare the data determined to be arc voltage with a preset voltage threshold, and screen out the data that meets the conditions as voltage characteristic data.

[0017] Preferably, the preset voltage threshold is a dynamic voltage threshold; the dynamic voltage threshold is adjusted according to the ambient temperature and the bus voltage fluctuation range.

[0018] Preferably, the vacuum degree early warning strategy for the vacuum interrupter output according to the vacuum degree prediction result includes:

[0019] Calculate the confidence level of the normal result and the confidence level of the abnormal result according to the vacuum degree prediction result, and the vacuum degree prediction result includes the normal prediction value, the abnormal prediction value and the total number of prediction times;

[0020] Compare the confidence level of the normal result and the confidence level of the abnormal result, and output the vacuum degree state of the vacuum interrupter according to the comparison result.

[0021] A vacuum breaker vacuum degree early warning system, which is applied to the foregoing vacuum breaker vacuum degree early warning method, includes:

[0022] A voltage acquisition unit, which is used to acquire voltage data from different vacuum interrupter samples in different vacuum states during different arcing time gradient tests;

[0023] A data processing unit, which is used to process the voltage data through time window cutting and threshold screening to obtain voltage characteristic data;

[0024] A model training unit, which is used to input the voltage characteristic data into a BP neural network model for training to obtain a vacuum degree prediction model capable of outputting a vacuum degree prediction result;

[0025] A prediction unit, which is used to input the voltage data of the real-time collected vacuum interrupter into the trained vacuum degree prediction model to obtain a vacuum degree prediction result;

[0026] An early warning unit, which is used to output a vacuum degree early warning strategy for the vacuum interrupter according to the vacuum degree prediction result.

[0027] A computer-readable storage medium, the computer-readable storage medium includes a stored program, wherein when the program runs, it controls the device where the computer-readable storage medium is located to execute the foregoing vacuum breaker vacuum degree early warning method.

[0028] A processor is used to run a program. When the program runs, it executes the aforementioned method for warning the vacuum degree of a vacuum circuit breaker.

[0029] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0030] A method for warning the vacuum degree of a vacuum circuit breaker according to the present invention can quickly output a predicted result of the vacuum degree by collecting voltage data of a vacuum interrupter in real time and inputting the collected data into a trained vacuum degree prediction model. By monitoring the change of the vacuum degree of the vacuum interrupter in real time during the operation of the circuit breaker, the operation state of the circuit breaker can be evaluated. This real-time monitoring ability enables the operation and maintenance personnel of the power system to timely master the vacuum state of the vacuum circuit breaker, and avoid problems such as reduced insulation performance and insufficient arc extinguishing ability caused by the decrease of the vacuum degree. Description of the Drawings

[0031] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for use in the description of the specific embodiments or the prior art. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn to scale.

[0032] Figure 1 It is a flowchart of a method for warning the vacuum degree of a vacuum circuit breaker according to the present invention.

[0033] Figure 2 It is a schematic diagram of the composition of a device for warning the vacuum degree of a vacuum circuit breaker according to the present invention.

[0034] Figure 3 It is a schematic diagram of a system for warning the vacuum degree of a vacuum circuit breaker according to the present invention.

[0035] The reference numerals in the drawings are as follows:

[0036] 1 - Vacuum interrupter; 2 - Voltage measurement and acquisition device; 3 - Host computer. Detailed Embodiments

[0037] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are some but not all of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0038] It should be understood that when used in this specification and the appended claims, the terms "comprising" and "including" indicate the presence of the described features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or their groups.

[0039] It should also be understood that the terms used in the specification of the present invention are for the purpose of describing particular embodiments only and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly dictates otherwise, the singular forms "a", "an", and "the" are intended to include the plural forms.

[0040] It should be further understood that the term "and / or" used in the specification of the present invention and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0041] Please refer to the following embodiments Figures 1 to 3 。

[0042] An embodiment of the present application provides a vacuum degree warning device for a vacuum circuit breaker, which includes three parts: a vacuum interrupter 1 to be measured, a voltage measurement and acquisition device 2, and a host computer 3. The voltage measurement and acquisition device 2 includes a voltage probe and an analog-to-digital conversion module. The voltage measurement and acquisition device 2 is installed at both ends of the vacuum interrupter 1 to be measured and is installed close to the vacuum interrupter. At the same time, the voltage probe should be firmly installed, including but not limited to methods such as bolts, to avoid high-frequency interference caused by vibration. The voltage probe has a high-frequency response, reaching greater than or equal to 500 MHz. The analog-to-digital conversion module also needs to have a high sampling rate, reaching above 5 GHz.

[0043] The vacuum interrupter 1 to be measured is connected to the voltage measurement and acquisition device 2, and the connection method uses a BNC coaxial cable. The host computer 3 is also connected to the voltage measurement and acquisition device 2, and the connection method can be through a network cable or the like. A gigabit high-speed network cable is selected for network cable transmission.

[0044] In this embodiment, the voltage probe in the voltage measurement and acquisition device 2 is installed at both ends of the vacuum interrupter 1 to be measured. Due to its high-frequency response, it can accurately sense the change of the voltage signal at both ends of the vacuum interrupter. When the vacuum degree of the vacuum interrupter changes, its electrical characteristics will also change accordingly, which will cause the characteristic parameters (such as amplitude, frequency, waveform, etc.) of the voltage signal at both ends to change. The voltage probe collects these changing voltage signals in real time. The collected analog voltage signal is transmitted to the analog-to-digital conversion module in the voltage measurement and acquisition device 2, which can quickly convert the analog signal into a digital signal. The digital signal after analog-to-digital conversion is transmitted from the voltage measurement and acquisition device 2 to the host computer 3 through a BNC coaxial cable. At the same time, the host computer 3 and the voltage measurement and acquisition device 2 are also connected through a gigabit high-speed network cable for transmitting control instructions and realizing stable and high-speed data transmission. After receiving the digital signal, the host computer 3 uses the built-in algorithm and model to analyze and process the signal. By analyzing the characteristic parameters of the voltage signal, if it is found that the vacuum degree has an abnormal change and reaches the preset warning threshold, the host computer 3 will issue a warning signal in time to remind the staff to take corresponding measures.

[0045] An embodiment of the present application provides a method for warning the vacuum degree of a vacuum circuit breaker, which is applied to the vacuum degree warning device of the vacuum circuit breaker in the foregoing embodiment, and includes:

[0046] Step S1, obtaining voltage data from tests with different arcing time gradients in vacuum interrupter samples in different vacuum states;

[0047] By obtaining the voltage data from tests with different arcing time gradients in the vacuum interrupter samples in the normal vacuum state and the abnormal vacuum state respectively. Specifically, it includes:

[0048] The process of collecting voltage data in the normal vacuum state:

[0049] S01. Connect the voltage measurement and acquisition device to a detachable vacuum interrupter, where the vacuum degree of the detachable vacuum interrupter can be adjusted, and the breaking current of the detachable vacuum interrupter is set to the rated current;

[0050] S02. Pump the vacuum degree of the detachable vacuum interrupter to a vacuum degree of 10 -4 Pa;

[0051] S03. Set the voltage measurement range of the analog-to-digital conversion module to 400V;

[0052] S04. The host computer issues a control signal for the detachable vacuum interrupter. The detachable vacuum interrupter starts to separate the contacts and generates a vacuum arc. At the same time, the voltage probe synchronously records the high-frequency voltage signal of the vacuum arc and uploads it to the host computer for storage;

[0053] S05. Adjust the host computer control signal to change the opening time of the detachable vacuum interrupter, and set the arcing time to 9 ms, 8 ms, 7 ms, 6 ms, 5 ms, 4 ms, 3 ms, and 2 ms respectively. Then record the high-frequency voltage signal of the vacuum arc and upload it to the host computer for storage.

[0054] Process of collecting voltage data in abnormal vacuum state:

[0055] S11. Adjust the vacuum degree of the detachable vacuum interrupter to 10 -1 Pa.

[0056] S12. Repeat the above steps S03 - S05;

[0057] By conducting different arcing time gradient tests on samples of vacuum interrupters in normal vacuum state (10 -4 Pa) and abnormal vacuum state (10 -1 Pa), voltage data under various working conditions are comprehensively collected. The test data include combinations of different vacuum degrees and arcing times, which can reflect the characteristics of the vacuum interrupter under different working states. And by setting the breaking current of the detachable vacuum interrupter to the rated current, adjusting the vacuum degree to a specific value, and precisely controlling the arcing time, the test can truly simulate various situations of the vacuum circuit breaker in actual operation.

[0058] Step S2. Process the voltage data through time window cutting and threshold screening to obtain voltage characteristic data; specifically including:

[0059] S21. Divide the voltage data at preset time intervals;

[0060] Intercept the voltage signal, take the voltage during the arcing stage as training data, and cut the data at 1 ms intervals. Discard the data with a duration less than 1 ms.

[0061] Divide the voltage data at 1 ms intervals, only retain the voltage during the arcing stage and discard the data with a duration less than 1 ms, effectively removing irrelevant data, improving the data processing efficiency, and at the same time collecting key information during the arcing stage.

[0062] S22. Use a comparison function to determine whether the divided data is arc voltage;

[0063] S23. Compare the data determined to be arc voltage with a preset voltage threshold, and screen out the data that meets the conditions as voltage characteristic data.

[0064] Preprocess the partitioned data, and use a comparison function to determine whether the partitioned data is the arc voltage. Since the arc voltage of a vacuum arc is usually several tens of volts, the threshold is set at 5V. Screen the arc voltage data by setting a voltage threshold of 5V, removing the data that does not conform to the characteristics of the vacuum arc voltage, and ensuring that the screened data can accurately represent the characteristics of the vacuum arc.

[0065] Step S3: Input the voltage characteristic data into a BP neural network model for training to obtain a vacuum degree prediction model capable of outputting the vacuum degree prediction result.

[0066] Group the high-frequency voltage signals of the vacuum arc in the voltage database into a training group and a test group. Among them, the training group accounts for 80%, and the test group accounts for 20%. Based on the MATLAB software, use the newff function to establish a BP neural network model; the output results of the neural network are divided into normal and warning. Among them, a vacuum degree of 10 -1 Pa is divided into the warning training group, and 10 -4 Pa is divided into the normal training group, and the test group also uses the same labeling method.

[0067] Based on the MATLAB software and the vacuum arc voltage data of the training group, use train to train the BP neural network model, and based on the MATLAB software, test the vacuum degree prediction model based on the BP neural network until the prediction accuracy rate reaches more than 90% and export the vacuum degree prediction model based on the BP neural network.

[0068] Use the MATLAB software to construct a BP neural network model, divide the voltage characteristic data into a training group and a test group, use a large amount of data for training, and continuously optimize the model parameters so that the model can learn the relationship between the vacuum arc voltage and the vacuum degree. When the prediction accuracy rate reaches more than 90%, it indicates that the model has high accuracy and can accurately output the vacuum degree prediction result.

[0069] Step S4: Input the voltage data of the vacuum interrupter collected in real time into the trained vacuum degree prediction model to obtain the vacuum degree prediction result.

[0070] Input the voltage data of the vacuum interrupter collected in real time and processed through Step S2 into the established vacuum degree prediction model based on the BP neural network for prediction, and output normal values S1, S2…, and output abnormal values E1, E2….

[0071] Step S5: Output the vacuum degree warning strategy of the vacuum interrupter according to the vacuum degree prediction result.

[0072] Calculate the confidence level P of the normal result according to the vacuum degree prediction result S and the confidence level P of the abnormal result E, the vacuum degree prediction results include normal prediction values, abnormal prediction values, and the total number of prediction times; calculate the confidence level of the BP neural network output results. The calculation method of the normal probability is as follows:

[0073]

[0074] By comparing the confidence level P of the normal result S and the confidence level P of the abnormal result E , and output the vacuum degree state of the vacuum interrupter according to the comparison result. According to the confidence level of the output result, the vacuum degree early warning strategy is as follows:

[0075] Compare P S and P E , and make an analysis and judgment based on their magnitudes:

[0076] When P S is greater than P E , it reminds the user that the vacuum interrupter is normal and outputs the credibility P S ;

[0077] When P S is less than P E , it warns the user that the vacuum interrupter has a fault and outputs the credibility P E ;

[0078] When P S is equal to P E , it reminds the user that it is necessary to perform an operation here, repeat steps S4 - S5, continue to monitor the vacuum degree. If P S is still equal to P E , it warns the user that the vacuum interrupter is abnormal.

[0079] By calculating the confidence level of the normal result and the confidence level of the abnormal result, judge the state of the vacuum interrupter according to their magnitudes, and output the corresponding early warning strategy. It can not only accurately judge the normal or abnormal state of the vacuum interrupter, but also provide more valuable information for users. When the result is uncertain, repeat the monitoring steps to further improve the accuracy of the judgment.

[0080] In this embodiment, the acquired voltage data is intercepted, and only the voltage data in the arcing stage is retained as the training data. This operation is because the voltage signal in the arcing stage is closely related to the vacuum degree of the vacuum interrupter, while the signals in other stages may interfere with the analysis results. The intercepted voltage data in the arcing stage is cut at a preset time interval of 1 ms. For data segments less than 1 ms, since it is difficult to accurately reflect the voltage characteristics and may introduce errors, they are discarded. And a specially written comparison function is used to judge the divided data one by one to determine whether these data belong to the arc voltage. This comparison function is designed based on the general characteristics of the vacuum arc voltage and the statistical laws of the test data, and can effectively identify the data that conforms to the arc voltage characteristics.

[0081] A method for predicting the vacuum degree of a vacuum circuit breaker according to the present invention realizes accurate monitoring and timely warning of the vacuum degree of the vacuum circuit breaker through a complete process from data acquisition, processing, model training to real-time monitoring and warning. It can quickly notify the user when an abnormality occurs in the vacuum interrupter, and monitor the change of the vacuum degree of the vacuum interrupter in real time through the operation of the circuit breaker, and then evaluate the operating state of the circuit breaker. This real-time monitoring ability enables the power system operation and maintenance personnel to timely grasp the vacuum state of the vacuum circuit breaker, avoid problems such as reduced insulation performance and insufficient arc extinguishing ability caused by the decrease of the vacuum degree, and also avoid equipment failures caused by abnormal vacuum degree, ensuring the safe and stable operation of the power system. At the same time, by using the BP neural network model for data processing and analysis, intelligent prediction and diagnosis of the vacuum degree are realized, reducing the subjectivity and error of manual judgment, and improving the accuracy and efficiency of monitoring.

[0082] Specifically, in a preferred embodiment of the present application, the preset voltage threshold is a dynamic voltage threshold; the dynamic voltage threshold is adjusted according to the ambient temperature and the bus voltage fluctuation range.

[0083] The voltage is adaptively adjusted according to the ambient temperature and the bus voltage fluctuation range, and the adjustment formula is:

[0084] V t = V1 + α|ΔT| + βV2

[0085] In the formula, V t is the dynamic voltage threshold; V1 is the basic voltage threshold; α is the ambient temperature adjustment coefficient, which reflects the influence degree of the ambient temperature on the voltage threshold; ΔT is the absolute value of the difference between the current temperature and 25°C; β is the bus voltage adjustment coefficient, which reflects the influence degree of the bus voltage on the voltage threshold; V2 represents the effective value of the bus voltage.

[0086] Since the change in ambient temperature will affect the arc characteristics of the vacuum circuit breaker and the accuracy of voltage measurement. Therefore, the dynamic voltage threshold can be adjusted according to the ambient temperature. For example, when the temperature rises, the arc voltage may drop slightly, and at this time, the voltage threshold can be appropriately reduced; conversely, when the temperature drops, the voltage threshold can be appropriately increased. At the same time, the fluctuation of the bus voltage will directly affect the measured voltage signal. The dynamic voltage threshold can be adjusted according to the fluctuation range of the bus voltage. For example, when the bus voltage fluctuates greatly, the fluctuation range of the threshold is increased to avoid misjudgment; when the bus voltage is stable, a smaller threshold range is maintained to improve the detection accuracy.

[0087] The embodiment of the present application also provides a vacuum degree warning system for a vacuum circuit breaker, which is applied to the vacuum degree warning method of the foregoing vacuum circuit breaker, and includes:

[0088] A voltage acquisition unit, configured to acquire voltage data of different arc burning time gradients in a vacuum interrupter sample in different vacuum states;

[0089] A data processing unit, configured to process the voltage data through time window cutting and threshold screening to obtain voltage characteristic data;

[0090] A model training unit, configured to input the voltage characteristic data into a BP neural network model for training to obtain a vacuum degree prediction model capable of outputting a vacuum degree prediction result;

[0091] A prediction unit, configured to input the voltage data of the vacuum interrupter collected in real time into the trained vacuum degree prediction model to obtain a vacuum degree prediction result;

[0092] An early warning unit, configured to output a vacuum degree early warning strategy for the vacuum interrupter according to the vacuum degree prediction result.

[0093] The function explanations of the units in this embodiment are the same as those of a vacuum degree warning method for a vacuum circuit breaker, and the technical effects are the same, so they will not be repeated here.

[0094] The embodiment of the present application also provides a computer-readable storage medium, where the computer-readable storage medium includes a stored program, and when the program runs, it controls the device where the computer-readable storage medium is located to execute the foregoing vacuum degree warning method for a vacuum circuit breaker.

[0095] The technical effect of this embodiment is the same as that of a vacuum degree warning method for a vacuum circuit breaker in the embodiment, and will not be repeated here.

[0096] The present invention can be used in numerous general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and so on.

[0097] The embodiment of the present application further provides a processor for running a program, wherein when the program runs, it executes the aforementioned method for warning the vacuum degree of a vacuum circuit breaker.

[0098] The technical effect of this embodiment is the same as that of the method for warning the vacuum degree of a vacuum circuit breaker in Embodiment 1, and will not be repeated here.

[0099] The processor in this embodiment can be a central processing unit (CPU), a controller, a microcontroller, or other data processing chips.

[0100] Those of ordinary skill in the art can realize that the units of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the components of each example have been generally described according to their functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0101] In the embodiments provided by the present invention, it should be understood that the division of units is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units can be combined into one unit, one unit can be split into multiple units, or some features can be ignored, etc.

[0102] In addition, the functional units in each embodiment of the present invention can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0103] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, read-only memories (ROMs), random access memories (RAMs), mobile hard disks, magnetic disks, or optical discs that can store program codes.

[0104] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the various embodiments of the present invention, and they should all be covered by the scope of the claims and the description of the present invention.

Claims

1. A method for warning the vacuum degree of a vacuum circuit breaker, characterized in that, Including: Obtaining voltage data from tests with different arcing time gradients in vacuum interrupter samples under different vacuum states; Processing the voltage data through time window cutting and threshold screening to obtain voltage characteristic data; Inputting the voltage characteristic data into a BP neural network model for training to obtain a vacuum degree prediction model capable of outputting a vacuum degree prediction result; Inputting the voltage data of the vacuum interrupter collected in real time, which has been processed, into the trained vacuum degree prediction model to obtain a vacuum degree prediction result; Outputting a vacuum degree warning strategy for the vacuum interrupter according to the vacuum degree prediction result.

2. The vacuum degree early warning method of a vacuum circuit breaker according to claim 1, characterized in that The obtaining of voltage data from tests with different arcing time gradients in vacuum interrupter samples under different vacuum states; Including: Obtaining voltage data from tests with different arcing time gradients in vacuum interrupter samples in normal and abnormal vacuum states respectively.

3. A method for warning the vacuum degree of a vacuum circuit breaker according to claim 1, characterized in that, The processing of the voltage data through time window cutting and threshold screening to obtain voltage characteristic data includes: Dividing the voltage data at a preset time interval; Judging whether the divided data is arc voltage through a comparison function; Comparing the data judged to be arc voltage with a preset voltage threshold, and screening out the data that meets the conditions as voltage characteristic data.

4. A method for warning the vacuum degree of a vacuum circuit breaker according to claim 3, characterized in that The preset voltage threshold is a dynamic voltage threshold; the dynamic voltage threshold is adjusted according to the ambient temperature and the bus voltage fluctuation range.

5. A method for warning the vacuum degree of a vacuum circuit breaker according to claim 1, characterized in that, The outputting of a vacuum degree warning strategy for the vacuum interrupter according to the vacuum degree prediction result includes: Calculating a normal result confidence level and an abnormal result confidence level according to the vacuum degree prediction result, where the vacuum degree prediction result includes a normal prediction value, an abnormal prediction value, and a total number of predictions; Comparing the normal result confidence level and the abnormal result confidence level, and outputting the vacuum degree state of the vacuum interrupter according to the comparison result.

6. A vacuum degree early warning system for a vacuum circuit breaker, characterized in that, Applied to the vacuum circuit breaker vacuum degree warning method according to any one of claims 1 to 5, including: A voltage acquisition unit for obtaining voltage data from tests with different arcing time gradients in vacuum interrupter samples under different vacuum states; A data processing unit for processing the voltage data through time window cutting and threshold screening to obtain voltage characteristic data; a model training unit for inputting the voltage characteristic data into a BP neural network model for training to obtain a vacuum degree prediction model capable of outputting a vacuum degree prediction result; A prediction unit for inputting the voltage data of the vacuum interrupter collected in real time into the trained vacuum degree prediction model to obtain a vacuum degree prediction result; A warning unit for outputting a vacuum degree warning strategy for the vacuum interrupter according to the vacuum degree prediction result.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein when the program runs, it controls the device where the computer-readable storage medium is located to execute the vacuum circuit breaker vacuum degree warning method according to any one of claims 1 to 5.

8. A processor, characterized in that, The processor is used to run the program, wherein when the program runs, it executes the vacuum circuit breaker vacuum degree warning method according to any one of claims 1 to 5.

Images