Method and system for detecting vacuum degree of vacuum arc-extinguishing chamber

Abstract

The invention relates to the technical field of electrical engineering, in particular to a method and system for detecting the vacuum degree of a vacuum arc extinguish chamber, and the method comprises the steps: collecting voltage signals of the vacuum arc extinguish chamber when the vacuum arc extinguish chamber is switched on and off under different vacuum degrees, constructing a vacuum degree recognition model, training the vacuum degree recognition model through a data set, and obtaining the vacuum degree of the vacuum arc extinguish chamber. Obtaining a trained vacuum degree identification model; and detecting the vacuum degree of the vacuum arc-extinguishing chamber by using the trained vacuum degree identification model. According to the detection method provided by the invention, the vacuum degree identification model is trained by using the data set formed by the features extracted from the data acquired in the experiment, so that the accuracy of vacuum degree classification of the vacuum degree identification model is remarkably improved. According to the detection method, the vacuum arc-extinguishing chamber does not need to be contacted, the structure of the vacuum arc-extinguishing chamber does not need to be changed, insulation of all parts cannot be threatened, and real-time, accurate and reliable online detection of the vacuum arc-extinguishing chamber is achieved.

Description

Technical Field

[0001] The present invention relates to the field of electrical engineering technology, and more particularly to a method and system for detecting the vacuum degree of a vacuum interrupter. Background Art

[0002] Vacuum circuit breakers use vacuum as arc extinguishing and insulating medium, and have the advantages of light weight, small size, long life, excellent breaking performance, high reliability and environmental protection. At present, they occupy an absolute dominant position in the medium voltage power system and are developing towards the field of high voltage and high current. As the core component of vacuum circuit breakers, vacuum interrupter plays a very important role in the successful breaking process of vacuum circuit breakers.

[0003] The vacuum interrupter is an important part of the vacuum circuit breaker, and its vacuum degree detection is crucial for normal operation. The national standard requires that the vacuum degree of the interrupter should be at least 6.6×10 -2 Pa. The existing detection methods are divided into two categories: online detection and offline detection. Among them, online detection mainly includes several methods such as coupling capacitor method, photoelectric conversion method, rotating electric field probe detection method, etc. The coupling capacitor method technology is relatively mature, with a simple structure and low cost. It has been applied to many occasions, but its accuracy needs to be further improved. The photoelectric conversion method requires the detection probe to have a very high detection accuracy. However, due to the harsh operating environment of the vacuum circuit breaker, the use of this method to achieve online monitoring will have a great impact on the accuracy of the probe, and the optical element itself will have stability and measurement error problems. The subsequent data information processing of the rotating electric field probe detection method is relatively cumbersome, and the circuit processing process is also relatively complicated, which will affect the detection accuracy to a certain extent, so the practicality is poor. Therefore, there is a need for a vacuum degree detection method that does not need to directly contact the vacuum arc chamber, does not need to change the arc chamber structure, and does not threaten the insulation of various parts of the circuit breaker. Summary of the invention

[0004] (I) Purpose of the invention

[0005] The purpose of the present invention is to provide a method and system for detecting the vacuum degree of a vacuum interrupter, which does not require direct contact with the vacuum interrupter, does not require changing the structure of the vacuum interrupter, and does not threaten the insulation of various parts; and can improve the detection accuracy of the vacuum degree of the vacuum interrupter.

[0006] (II) Technical solution

[0007] In order to solve the above problems, the present invention provides a method for detecting the vacuum degree of a vacuum interrupter, comprising:

[0008] Collect voltage signals when the vacuum interrupter is disconnected at different vacuum degrees;

[0009] Performing feature analysis on the voltage signal to extract features of the voltage signal;

[0010] constructing a data set according to the characteristics of the voltage signal;

[0011] Constructing a vacuum degree recognition model, and training the vacuum degree recognition model using the data set to obtain a trained vacuum degree recognition model;

[0012] The trained vacuum degree recognition model is used to detect the vacuum degree of the vacuum interrupter.

[0013] In another aspect of the present invention, preferably, collecting the voltage signal when the vacuum interrupter is disconnected at different vacuum degrees includes:

[0014] Set the acquisition channel;

[0015] The collection channel includes a capacitor, a switch, a vacuum interrupter and an exhaust component;

[0016] The capacitor, the switch and the vacuum interrupter are connected to form a loop;

[0017] The capacitor is used to supply power to the circuit, and the switch is used to control the opening and closing of the circuit;

[0018] The exhaust component is communicated with the vacuum interrupter, and the vacuum interrupter achieves a vacuum state through the exhaust component.

[0019] In another aspect of the present invention, preferably, the collecting of voltage signals when the vacuum interrupter is disconnected at different vacuum degrees further comprises:

[0020] The vacuum interrupter is closed and the vacuum interrupter is evacuated to a vacuum state;

[0021] charging the capacitor, disconnecting the switch, and acquiring a voltage signal under the vacuum state;

[0022] The vacuum state includes an abnormal vacuum state and a normal vacuum state;

[0023] The vacuum state is cyclically set to an abnormal vacuum state and a normal vacuum state to collect voltage signals.

[0024] In another aspect of the present invention, preferably, the abnormal vacuum state is a state in which the pressure is higher than 6.6×10 -2 Pa;

[0025] The normal vacuum state is when the pressure is lower than 6.6×10 -2 Pa.

[0026] In another aspect of the present invention, preferably, performing feature analysis on the voltage signal to extract the feature of the voltage signal comprises:

[0027] Performing time domain waveform analysis on the voltage signal to obtain time domain characteristics;

[0028] The time domain features are converted into frequency domain features using a fast Fourier transform algorithm to extract spectrum information, where the spectrum information is the feature of the voltage signal.

[0029] In another aspect of the present invention, preferably, the vacuum degree identification model is based on a Bayesian neural network algorithm;

[0030] The Bayesian neural network algorithm includes a feedforward neural network structure and Bayesian reasoning;

[0031] The feedforward neural network structure consists of an input layer, a hidden layer, and an output layer. The input data of the input layer includes spectrum information, and the output data of the output layer is whether the vacuum degree is abnormal.

[0032] The Bayesian inference estimates the posterior distribution of the parameter through Bayes' theorem:

[0033]

[0034] Among them, p(θ|D) is the posterior distribution of weight θ given data D; p(D|θ) is the likelihood function, which represents the probability of occurrence of training data D given weight θ; p(θ) is the prior distribution of weight, which is Gaussian distribution; p(D) is the evidence, that is, the marginal probability of the data, which is set to a constant.

[0035] In another aspect of the present invention, preferably, using the data set to train the vacuum degree recognition model comprises:

[0036] Dividing the data set into a training set and a test set;

[0037] Taking the characteristic of the voltage signal as input and whether the vacuum degree is abnormal as output, the vacuum degree recognition model is trained using the training set to obtain a first vacuum degree recognition model;

[0038] Using the test set to verify the accuracy of the first vacuum degree recognition model, if the accuracy meets a preset threshold, a trained vacuum degree recognition model is obtained;

[0039] If the accuracy rate does not meet the preset threshold, parameters of the first vacuum degree recognition model are adjusted until the accuracy rate meets the preset threshold, so as to obtain a trained vacuum degree recognition model.

[0040] In another aspect of the present invention, preferably, taking the characteristic of the voltage signal as input and whether the vacuum degree is abnormal as output, using the training set to train the vacuum degree recognition model, and obtaining the first vacuum degree recognition model comprises:

[0041] During the training process, the model parameters are adjusted using the gradient descent method; the gradient descent method is calculated using the following formula:

[0042] θ 1 =θ 0 -α▽J(θ)

[0043] Among them, θ is the model parameter, α is the learning rate, and J(θ) is the loss function.

[0044] In another aspect of the present invention, preferably, the method further comprises:

[0045] Displaying the detection result of the vacuum degree of the vacuum interrupter;

[0046] The test results include abnormal and normal;

[0047] If the detection result is abnormal, an alarm is issued;

[0048] If the test result is normal, continue testing.

[0049] In another aspect of the present invention, preferably, a system for detecting the vacuum degree of a vacuum interrupter comprises:

[0050] Acquisition module: collects voltage signals when the vacuum interrupter is disconnected under different vacuum degrees;

[0051] Extraction module: performing feature analysis on the voltage signal to extract features of the voltage signal;

[0052] Construction module: constructing a data set according to the characteristics of the voltage signal;

[0053] Training module: constructing a vacuum degree recognition model, and using the data set to train the vacuum degree recognition model to obtain a trained vacuum degree recognition model;

[0054] Detection module: detects the vacuum degree of the vacuum interrupter using the trained vacuum degree recognition model.

[0055] (III) Beneficial effects

[0056] The above technical solution of the present invention has the following beneficial technical effects:

[0057] The detection method of the present invention uses a data set formed by extracting features from experimentally collected data to train a vacuum degree recognition model, thereby significantly improving the accuracy of vacuum degree classification of the vacuum degree recognition model. The detection method of the present invention does not need to contact the vacuum interrupter, does not need to change the structure of the vacuum interrupter, does not threaten the insulation of various parts, and realizes real-time, accurate and reliable online detection of the vacuum interrupter. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 is an overall flow chart of an embodiment of the present invention;

[0059] Figure 2 is a schematic diagram of a collection channel according to an embodiment of the present invention;

[0060] Figure 3 is a schematic diagram of the structure of a detection system according to an embodiment of the present invention;

[0061] Reference numerals:

[0062] 1: Capacitor, 2: Inductor, 3: Switch, 4: Vacuum interrupter, 5: Oscilloscope, 6: High voltage coil. DETAILED DESCRIPTION

[0063] In order to make the purpose, technical scheme and advantages of the present invention clearer, the present invention is further described in detail below in conjunction with specific embodiments and with reference to the accompanying drawings. It should be understood that these descriptions are only exemplary and are not intended to limit the scope of the present invention. In addition, in the following description, the description of well-known structures and technologies is omitted to avoid unnecessary confusion of the concept of the present invention.

[0064] The accompanying drawings show schematic diagrams of structures according to embodiments of the present invention. These figures are not drawn to scale, and some details are magnified and some details may be omitted for the purpose of clarity. The shapes of various regions and layers shown in the figures and the relative sizes and positional relationships therebetween are only exemplary, and may deviate in practice due to manufacturing tolerances or technical limitations, and those skilled in the art may additionally design regions / layers with different shapes, sizes, and relative positions according to actual needs.

[0065] Obviously, the described embodiments are only some embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0066] In addition, the technical features involved in the different embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0067] The present invention will be described in more detail below with reference to the accompanying drawings. In each of the accompanying drawings, the same elements are represented by similar reference numerals. For the sake of clarity, the various parts in the accompanying drawings are not drawn to scale.

[0068] Embodiment 1

[0069] A method for detecting the vacuum degree of a vacuum interrupter. Figure 1 FIG. 1 shows an overall flow chart of an embodiment of the present invention, as shown in FIG. Figure 1As shown, including:

[0070] Collect the voltage signal when the vacuum interrupter is broken under different vacuum degrees; this step is to obtain the voltage response data of the vacuum interrupter under different vacuum conditions. Different vacuum degrees can be simulated by experimental equipment, and the vacuum interrupter is broken under each vacuum degree. At the same time, a high-precision voltage sensor or oscilloscope is used to record the voltage signal at the moment of breaking. During the experiment, the consistency of experimental conditions, such as temperature, pressure, etc., is ensured to reduce the influence of external factors on the experimental results.

[0071] The voltage signal is subjected to characteristic analysis to extract the characteristics of the voltage signal; key information that can reflect the change of vacuum degree is extracted from the collected voltage signal. Signal processing techniques, such as Fourier transform and wavelet transform, can be used to perform frequency domain or time-frequency domain analysis on the voltage signal to extract characteristic parameters such as amplitude, frequency, and phase of the signal.

[0072] According to the characteristics of the voltage signal, a data set is constructed; the extracted characteristic parameters and the corresponding vacuum degree values ​​are combined into a data set for subsequent model training. The characteristic parameters under each vacuum degree are taken as a sample, and whether the vacuum degree is abnormal is taken as a label to construct a data set required for supervised learning.

[0073] A vacuum degree recognition model is constructed, and the vacuum degree recognition model is trained using the data set to obtain a trained vacuum degree recognition model; the training enables the model to accurately recognize the voltage signal characteristics under different vacuum degrees. During the training process, the model will continuously adjust its parameters to minimize the prediction error.

[0074] The vacuum degree of the vacuum interrupter is detected using the trained vacuum degree recognition model. The trained model is applied to actual detection to quickly and accurately determine the vacuum degree of the vacuum interrupter. In actual application, the voltage signal of the vacuum interrupter to be detected is first collected and the characteristic parameters are extracted; then the characteristic parameters are input into the trained vacuum degree recognition model, and the model will output whether the predicted vacuum degree is abnormal.

[0075] Furthermore, in this embodiment, collecting the voltage signal when the vacuum interrupter is disconnected at different vacuum degrees includes:

[0076] Set the acquisition channel; Figure 2 FIG. 4 shows a schematic diagram of a collection channel according to an embodiment of the present invention. Figure 2 As shown,

[0077] The collection channel includes a capacitor 1, a switch 3, a vacuum interrupter 4 and an exhaust component;

[0078] The capacitor 1, the switch 3 and the vacuum interrupter 4 are connected to form a loop;

[0079] The capacitor 1 is used to supply power to the circuit, and the switch 3 is used to control the opening and closing of the circuit;

[0080] The exhaust component is communicated with the vacuum interrupter chamber 4, and the vacuum interrupter chamber is in a vacuum state through the exhaust component.

[0081] The acquisition channel also includes an inductor 2, an oscilloscope 5 and a high-voltage coil 6. The inductor 2 and the high-voltage coil 6 are arranged in a loop, and the oscilloscope 5 is connected to the high-voltage coil 6 for acquiring voltage signals.

[0082] The collecting of voltage signals when the vacuum interrupter is disconnected at different vacuum degrees also includes:

[0083] The vacuum interrupter is sealed and evacuated to a vacuum state; the cavity in the detachable interrupter is evacuated to an abnormal vacuum state by opening the mechanical pump and the molecular valve of the exhaust component;

[0084] Charging the capacitor, disconnecting the switch, and opening the switch by using an operating mechanism; obtaining a voltage signal under the vacuum state;

[0085] The vacuum state includes an abnormal vacuum state and a normal vacuum state;

[0086] The vacuum state is cyclically set to an abnormal vacuum state and a normal vacuum state to collect voltage signals.

[0087] The abnormal vacuum state is when the pressure is higher than 6.6×10 -2 Pa;

[0088] The normal vacuum state is a pressure lower than 6.6×10 -2 Pa.

[0089] Furthermore, in this embodiment, performing feature analysis on the voltage signal to extract features of the voltage signal includes:

[0090] The voltage signal is subjected to time domain waveform analysis to obtain time domain characteristics, including extraction of parameters such as peak value, mean value, effective value and waveform factor, etc. These parameters can reflect the cathode spot transient characteristics of the arc under different vacuum conditions.

[0091] The time domain features are converted into frequency domain features using the fast Fourier transform algorithm to extract spectrum information, such as main frequency components, frequency distribution, and energy spectrum density. These frequency domain features help identify the relationship between the frequency characteristic changes of the arc voltage and the vacuum degree.

[0092] Wavelet packet transform is used to perform multi-scale analysis on voltage signals to obtain the frequency characteristics of signals at different time scales.

[0093] Furthermore, in this embodiment, the vacuum degree identification model is based on a Bayesian neural network algorithm.

[0094] The Bayesian neural network algorithm consists of a feedforward neural network and Bayesian reasoning:

[0095] The feedforward neural network comprises an input layer, a hidden layer and an output layer. The input layer is the characteristics of the voltage signal, and the output layer is the vacuum state, including normal and abnormal.

[0096] Bayesian inference estimates the posterior distribution of parameters through Bayes' theorem:

[0097]

[0098] Among them, p(θ|D) is the posterior distribution of weight θ given data D; p(D|θ) is the likelihood function, which represents the probability of occurrence of training data D given weight θ; p(θ) is the prior distribution of weight, which is Gaussian distribution; p(D) is the evidence, that is, the marginal probability of the data, which is set to a constant.

[0099] Using the data set to train the vacuum degree recognition model includes:

[0100] The data set is divided into a training set and a test set; the division ratio may be 8:2;

[0101] Taking the characteristic of the voltage signal as input and whether the vacuum degree is abnormal as output, the vacuum degree recognition model is trained using the training set to obtain a first vacuum degree recognition model;

[0102] The accuracy of the first vacuum degree recognition model is verified using the test set. If the accuracy meets a preset threshold, a trained vacuum degree recognition model is obtained. The preset threshold may be set to 90%.

[0103] If the accuracy rate does not meet the preset threshold, parameters of the first vacuum degree recognition model are adjusted until the accuracy rate meets the preset threshold, so as to obtain a trained vacuum degree recognition model.

[0104] Taking the characteristic of the voltage signal as input and whether the vacuum degree is abnormal as output, the vacuum degree recognition model is trained using the training set to obtain the first vacuum degree recognition model, which includes:

[0105] During the training process, the gradient descent method is used to adjust the model parameters to minimize the prediction error.

[0106] The algorithm based on the gradient descent method is:

[0107] Among them, θ is the model parameter, α is the learning rate, and J(θ) is the loss function.

[0108] Furthermore, in this embodiment, the method further includes:

[0109] The test results of the vacuum degree of the vacuum interrupter are displayed; real-time monitoring data, alarm information and historical records can be displayed. The interface can be a PC or mobile device application, which is convenient for maintenance personnel to check the equipment status at any time. It supports data export function, allowing users to save monitoring data and analysis results as reports for subsequent analysis and recording.

[0110] The test results include abnormal and normal;

[0111] If the detection result is abnormal, an alarm is issued; the alarm is automatically triggered to notify relevant maintenance personnel to ensure timely maintenance and inspection of the equipment.

[0112] If the test result is normal, continue testing.

[0113] The detection method of the present invention uses a data set formed by extracting features from experimentally collected data to train a vacuum degree recognition model, thereby significantly improving the accuracy of vacuum degree classification of the vacuum degree recognition model. The detection method of the present invention does not need to contact the vacuum interrupter, does not need to change the structure of the vacuum interrupter, does not threaten the insulation of various parts, and realizes real-time, accurate and reliable online detection of the vacuum interrupter.

[0114] Embodiment 2

[0115] A vacuum degree detection system for a vacuum interrupter. Figure 3 FIG. 1 shows a schematic diagram of the structure of a detection system according to an embodiment of the present invention. Figure 3 As shown, including:

[0116] Acquisition module: collects voltage signals when the vacuum interrupter is disconnected under different vacuum degrees;

[0117] Extraction module: performing feature analysis on the voltage signal to extract features of the voltage signal;

[0118] Construction module: constructing a data set according to the characteristics of the voltage signal;

[0119] Training module: constructing a vacuum degree recognition model, and using the data set to train the vacuum degree recognition model to obtain a trained vacuum degree recognition model;

[0120] Detection module: detects the vacuum degree of the vacuum interrupter using the trained vacuum degree recognition model.

[0121] It should be understood that the above specific embodiments of the present invention are only used to illustrate or explain the principles of the present invention, and do not constitute a limitation of the present invention. Therefore, any modifications, equivalent substitutions, improvements, etc. made without departing from the spirit and scope of the present invention should be included in the protection scope of the present invention. In addition, the appended claims of the present invention are intended to cover all changes and modifications that fall within the scope and boundaries of the appended claims, or the equivalent forms of such scope and boundaries.

[0122] In the above description, the technical details of patterning and etching of each layer are not described in detail. However, those skilled in the art should understand that various means in the prior art can be used to form layers, regions, etc. of desired shapes. In addition, in order to form the same structure, those skilled in the art can also design methods that are not completely the same as the methods described above.

[0123] The present invention has been described above with reference to the embodiments of the present invention. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of the present invention. The scope of the present invention is defined by the appended claims and their equivalents. Without departing from the scope of the present invention, a person skilled in the art may make various substitutions and modifications, which should all fall within the scope of the present invention.

[0124] Although the embodiments of the present invention have been described in detail, it should be understood that the various changes, substitutions, and alterations could be made hereto without departing from the spirit and scope of the invention.

[0125] Obviously, the above embodiments are merely examples for the purpose of clear explanation, and are not intended to limit the implementation methods. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the implementation methods here. The obvious changes or modifications derived therefrom are still within the scope of protection of the invention.

Claims

1. A method for detecting the vacuum degree of a vacuum interrupter, characterized in that: include: Collect voltage signals when the vacuum interrupter is disconnected at different vacuum degrees; Performing feature analysis on the voltage signal to extract features of the voltage signal; constructing a data set according to the characteristics of the voltage signal; Constructing a vacuum degree recognition model, and training the vacuum degree recognition model using the data set to obtain a trained vacuum degree recognition model; The vacuum degree of the vacuum interrupter is detected using the trained vacuum degree recognition model.

2. The method for detecting the vacuum degree of a vacuum interrupter according to claim 1, characterized in that: The voltage signals collected when the vacuum interrupter is disconnected at different vacuum degrees include: Set the acquisition channel; The collection channel comprises a capacitor (1), a switch (3), a vacuum interrupter (4) and an exhaust component; The capacitor (1), the switch (3) and the vacuum interrupter are connected to form a circuit; The capacitor (1) is used to supply power to the circuit, and the switch (3) is used to control the opening and closing of the circuit; The exhaust component is in communication with the vacuum interrupter (4), and the vacuum interrupter (4) is in a vacuum state through the exhaust component.

3. The method for detecting the vacuum degree of a vacuum interrupter according to claim 2, characterized in that: The voltage signal collected when the vacuum interrupter (4) is disconnected at different vacuum degrees also includes: The vacuum interrupter (4) is sealed, and the vacuum interrupter (4) is evacuated to a vacuum state; Charging the capacitor (1), disconnecting the switch (3), and acquiring a voltage signal under the vacuum state; The vacuum state includes an abnormal vacuum state and a normal vacuum state; The vacuum state is cyclically set to an abnormal vacuum state and a normal vacuum state to collect voltage signals.

4. The method for detecting the vacuum degree of a vacuum interrupter according to claim 3, characterized in that: The abnormal vacuum state is when the pressure is higher than 6.6×10 -2 Pa; The normal vacuum state is a pressure lower than 6.6×10 -2 Pa.

5. The method for detecting the vacuum degree of a vacuum interrupter according to claim 1, characterized in that: Performing feature analysis on the voltage signal to extract features of the voltage signal includes: Performing time domain waveform analysis on the voltage signal to obtain time domain characteristics; The time domain features are converted into frequency domain features using a fast Fourier transform algorithm to extract spectrum information, where the spectrum information is the feature of the voltage signal.

6. The method for detecting the vacuum degree of a vacuum interrupter according to claim 1, characterized in that: The vacuum degree identification model is based on a Bayesian neural network algorithm; The Bayesian neural network algorithm includes a feedforward neural network structure and Bayesian reasoning; The feedforward neural network structure consists of an input layer, a hidden layer, and an output layer. The input data of the input layer includes spectrum information, and the output data of the output layer is whether the vacuum degree is abnormal. The Bayesian inference estimates the posterior distribution of the parameter through Bayes' theorem: Among them, p(θ|D) is the posterior distribution of weight θ given data D; p(D|θ) is the likelihood function, which represents the probability of occurrence of training data D given weight θ; p(θ) is the prior distribution of weight, which is Gaussian distribution; p(D) is the evidence, that is, the marginal probability of the data, which is set to a constant.

7. The method for detecting the vacuum degree of a vacuum interrupter according to claim 1, characterized in that: Using the data set to train the vacuum degree recognition model includes: Dividing the data set into a training set and a test set; Taking the characteristic of the voltage signal as input and whether the vacuum degree is abnormal as output, the vacuum degree recognition model is trained using the training set to obtain a first vacuum degree recognition model; Using the test set to verify the accuracy of the first vacuum degree recognition model, if the accuracy meets a preset threshold, a trained vacuum degree recognition model is obtained; If the accuracy rate does not meet the preset threshold, parameters of the first vacuum degree recognition model are adjusted until the accuracy rate meets the preset threshold, so as to obtain a trained vacuum degree recognition model.

8. The method for detecting the vacuum degree of a vacuum interrupter according to claim 5, characterized in that: Taking the characteristic of the voltage signal as input and whether the vacuum degree is abnormal as output, the vacuum degree recognition model is trained using the training set to obtain the first vacuum degree recognition model, which includes: During the training process, the model parameters are adjusted using the gradient descent method, which is calculated using the following formula: Among them, θ is the model parameter, α is the learning rate, and J(θ) is the loss function.

9. The method for detecting the vacuum degree of a vacuum interrupter according to claim 1, characterized in that: The method further comprises: Displaying the detection result of the vacuum degree of the vacuum interrupter; The test results include abnormal and normal; If the detection result is abnormal, an alarm is issued; If the test result is normal, continue testing.

10. A vacuum degree detection system for a vacuum interrupter, characterized in that: include: Acquisition module: collects voltage signals when the vacuum interrupter is disconnected under different vacuum degrees; Extraction module: performing feature analysis on the voltage signal to extract features of the voltage signal; Construction module: constructing a data set according to the characteristics of the voltage signal; Training module: constructing a vacuum degree recognition model, and using the data set to train the vacuum degree recognition model to obtain a trained vacuum degree recognition model; Detection module: detects the vacuum degree of the vacuum interrupter using the trained vacuum degree recognition model.

Images