Intelligent phase-controlled vacuum circuit breaker health assessment method, device and circuit breaker

Abstract

The present application provides a health assessment method, device, and circuit breaker for an intelligent phase-controlled vacuum circuit breaker, and relates to the technical field of circuit breaker health assessment. The method comprises: performing vacuum detection on the arc extinguishing chamber in the intelligent phase-controlled vacuum circuit breaker to obtain the vacuum degree; performing a heat analysis of the vacuum circuit breaker based on the vacuum degree to obtain a heat parameter, performing a zero-crossing monitoring error analysis, and obtaining a zero-crossing error coefficient; mapping the zero-crossing error coefficient based on the operating time parameter of the vacuum circuit breaker, calculating a zero-crossing deviation coefficient, performing confidence processing based on the zero-crossing deviation coefficient and the analysis deviation coefficient of the heat analysis and the zero-crossing monitoring error analysis to obtain a zero-crossing confidence degree; assigning a weight based on the zero-crossing confidence degree, performing a health calculation based on the vacuum degree and the zero-crossing error coefficient, and obtaining the health degree of the vacuum circuit breaker. The method solves the technical problem of inaccurate health assessment of intelligent phase-controlled vacuum circuit breakers in the prior art.

Description

Technical Field

[0001] The present invention relates to the field of circuit breaker health assessment, and in particular to an intelligent phase-controlled vacuum circuit breaker health assessment method, device, and circuit breaker. Background Art

[0002] Intelligent phase-controlled vacuum circuit breakers are core devices for power switching and protection in power systems, and their health directly impacts the safety and reliability of the power grid. However, traditional health assessment methods typically rely on vacuum level testing or other single operating parameters, failing to consider the impact of factors such as vacuum level drop and heating effects, resulting in inaccurate health assessments of intelligent phase-controlled vacuum circuit breakers. Summary of the Invention

[0003] The present invention addresses the technical problem of inaccurate health evaluation of intelligent phase-controlled vacuum circuit breakers in the prior art and provides a health evaluation method, device and circuit breaker for intelligent phase-controlled vacuum circuit breakers.

[0004] The technical solution of the present invention to solve the above technical problems is as follows:

[0005] In a first aspect, the present invention provides a health assessment method for an intelligent phase-controlled vacuum circuit breaker, comprising:

[0006] Perform vacuum degree detection on the arc extinguishing chamber in the intelligent phase-controlled vacuum circuit breaker to obtain the vacuum degree;

[0007] performing a heating analysis of the vacuum circuit breaker according to the vacuum degree to obtain heating parameters, and performing a zero-crossing monitoring error analysis based on the heating parameters to obtain a zero-crossing error coefficient;

[0008] According to the operating time parameter of the vacuum circuit breaker, mapping is performed to obtain a mapped zero-crossing error coefficient, and the zero-crossing deviation coefficient is calculated with the zero-crossing error coefficient; confidence processing is performed on the zero-crossing deviation coefficient and the analysis deviation coefficients of the heating analysis and the zero-crossing monitoring error analysis to obtain a zero-crossing confidence;

[0009] A weight is allocated according to the zero-crossing confidence, and a health calculation is performed based on the vacuum degree and the zero-crossing error coefficient to obtain the health of the vacuum circuit breaker.

[0010] In a second aspect, the present invention provides an intelligent phase-controlled vacuum circuit breaker health assessment device, comprising:

[0011] Memory for storing computer software programs;

[0012] The processor is configured to read and execute the computer software program, thereby implementing the health assessment method for an intelligent phase-controlled vacuum circuit breaker as described in the first aspect.

[0013] In a third aspect, the present invention provides an intelligent phase-controlled vacuum circuit breaker, comprising: performing health assessment using the intelligent phase-controlled vacuum circuit breaker health assessment method described in the first aspect.

[0014] The beneficial effects of the present invention are:

[0015] Compared with the prior art, the present application first detects the vacuum degree of the arc extinguishing chamber in the intelligent phase-controlled vacuum circuit breaker to obtain the vacuum degree. Through the physical association between the capacitance parameter and the vacuum degree and the index mapping mechanism, the vacuum degree of the arc extinguishing chamber in the vacuum circuit breaker is obtained, providing the necessary data basis for the health assessment of the vacuum circuit breaker. Secondly, the heating analysis of the vacuum circuit breaker is performed according to the vacuum degree to obtain the heating parameters. The zero-crossing monitoring error analysis is performed based on the heating parameters to obtain the zero-crossing error coefficient. According to the mapping relationship between the vacuum degree and the heating parameters, the heating predictor constructed by machine learning is used to perform heating analysis on different vacuum degrees to obtain the heating parameters. Then, according to the relationship between the heating parameters and the zero-crossing error coefficient, the zero-crossing monitoring error analysis of different heating parameters is performed by the zero-point error analyzer to obtain the zero-crossing error coefficient, providing a reliable data basis for the weight adjustment of the subsequent health calculation. Next, based on the operating time parameters of the vacuum circuit breaker, the zero-crossing error coefficient is mapped and then calculated with the zero-crossing error coefficient to obtain the zero-crossing deviation coefficient. Confidence processing is performed on the zero-crossing deviation coefficient and the analytical deviation coefficients of the heat analysis and zero-crossing monitoring error analysis to obtain the zero-crossing confidence level. This quantifies the credibility of the zero-crossing error coefficient output by the model prediction, improving the reliability of the condition monitoring of the intelligent phase-controlled vacuum circuit breaker. Finally, weights are assigned based on the zero-crossing confidence level, and the health level is calculated based on the vacuum level and the zero-crossing error coefficient to obtain the health level of the vacuum circuit breaker. The preset weights are adaptively corrected based on the zero-crossing confidence level. The health level of the vacuum circuit breaker is obtained by combining the zero-crossing health level and the vacuum health level, which can be used to evaluate the health of the vacuum circuit breaker.

[0016] Through the above technical solution, this application fully considers that insufficient vacuum will lead to an increase in the arc extinguishing energy in the arc extinguishing chamber of the vacuum circuit breaker, causing abnormal heating parameters, which in turn affects the thermal deformation of mechanical components and sensor accuracy, resulting in an increase in zero-crossing monitoring errors and undermining the accuracy of the intelligent phase-controlled function. Then, using vacuum as the core indicator, combined with multi-dimensional data such as heating parameters, zero-crossing error coefficients, and operating time, through machine learning modeling and confidence correction, the health of the vacuum circuit breaker is obtained, thereby improving the accuracy of the health assessment of the intelligent phase-controlled vacuum circuit breaker. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A flow chart of the health evaluation method for an intelligent phase-controlled vacuum circuit breaker provided by the present invention;

[0018] Figure 2This is a structural schematic diagram of the intelligent phase-controlled vacuum circuit breaker health assessment device provided by the present invention.

[0019] In the accompanying drawings, the components represented by the reference numerals are as follows:

[0020] An intelligent phase-controlled vacuum circuit breaker health assessment device 200 , a memory 210 , a processor 220 , and a computer program 211 . DETAILED DESCRIPTION

[0021] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative efforts shall fall within the scope of protection of the present invention.

[0022] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of the technical features indicated. Therefore, a feature specified as "first" or "second" may explicitly or implicitly include one or more of the specified features. In the description of the present invention, "plurality" means two or more, unless otherwise specifically defined.

[0023] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or illustration". Any embodiment of the present invention described as "for example" is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any person skilled in the art to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes are not elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed herein.

[0024] Example 1, as Figure 1 As shown, an embodiment of the present invention provides a health assessment method for an intelligent phase-controlled vacuum circuit breaker, comprising:

[0025] S10: Perform vacuum degree detection on the arc extinguishing chamber in the intelligent phase-controlled vacuum circuit breaker to obtain the vacuum degree;

[0026] The arc extinguishing chamber is the core component of the vacuum circuit breaker. The vacuum degree of the arc extinguishing chamber is usually maintained at 10 -4 ~10 -6The vacuum level is on the order of Pa. In this vacuum environment, the gas molecule density is extremely low, and the arc plasma diffusion rate is extremely fast. When the current crosses zero, the arc is quickly extinguished, preventing reignition and thus achieving arc extinction. Furthermore, the arc extinguishing chamber relies on a high vacuum environment for efficient arc extinguishing. A drop in vacuum, for example due to seal failure, contact erosion, or material aging, directly weakens the arc extinguishing capability and reduces insulation strength, leading to problems such as increased contact erosion and abnormal heating. Therefore, the vacuum level of the arc extinguishing chamber can be used to assess the health of the vacuum circuit breaker.

[0027] In order to solve the above problems, the present application performs vacuum degree detection on the arc extinguishing chamber in the intelligent phase-controlled vacuum circuit breaker to obtain the vacuum degree.

[0028] Specifically, step S10 in the method includes:

[0029] Detect the capacitance parameters of the arc extinguishing chamber in the vacuum circuit breaker;

[0030] According to the capacitance parameter, the corresponding vacuum degree is obtained by indexing, wherein the capacitance parameter and the vacuum degree of the arc extinguishing chamber have an index corresponding relationship, and indexing is performed based on the index corresponding relationship.

[0031] In the embodiment of the present application, the capacitance parameter of the arc extinguishing chamber in the vacuum circuit breaker is first detected. This is because the capacitance parameter of the arc extinguishing chamber in the vacuum circuit breaker has a mapping relationship with the vacuum degree. Specifically, the arc extinguishing chamber of the vacuum circuit breaker is essentially a capacitive element composed of moving and static contacts, a shielding cover, etc., which can be simplified into a parallel plate capacitor model: C = , where C is the equivalent capacitance, is the vacuum dielectric constant, A is the contact equivalent area, and d is the contact distance. When the vacuum degree of the arc extinguishing chamber decreases, the density of internal gas molecules increases, which may cause oxidation or deposition of impurities on the contact surface, change the surface state of the electrode, and thus cause the contact equivalent area A to change; it may also be accompanied by contact ablation or deformation, which will cause the contact distance d to change; it may also be due to the enhanced polarization effect of gas molecules, and the vacuum dielectric constant Deviates from the vacuum state. Therefore, when the vacuum degree of the arc extinguishing chamber changes, the capacitance parameters of the arc extinguishing chamber will change. That is, there is a mapping relationship between the capacitance parameters of the arc extinguishing chamber in the vacuum circuit breaker and the vacuum degree. For example, the capacitance parameters of the arc extinguishing chamber can be measured using a Xilin bridge or a digital bridge to measure the capacitance of the arc extinguishing chamber at the power frequency. A high-precision capacitance sensor can also be connected in series in the secondary circuit of the circuit breaker to collect the capacitance parameters in the operating state in real time to avoid power outage detection. For example, the capacitance value of the arc extinguishing chamber at the power frequency measured by the digital bridge is 10.8pF.

[0032] Secondly, according to the capacitance parameter, the corresponding vacuum degree is obtained by indexing, wherein the capacitance parameter and the vacuum degree of the arc extinguishing chamber have an index correspondence relationship, and indexing is performed based on the index correspondence relationship. For example, since there is a mapping relationship between the capacitance parameter and the vacuum degree of the arc extinguishing chamber in the vacuum circuit breaker, an index table of capacitance parameter and vacuum degree can be established accordingly. For example, the arc extinguishing chamber is evacuated to different vacuum degrees in the laboratory, such as 10 −5 Pa~10 −1 Pa, and measure the corresponding capacitance parameters, and then build an index table. For example, an index table can be built based on the capacitance value and its corresponding vacuum degree: capacitance value 10.2pF, vacuum degree 0.5×10 −4 Pa, capacitance value 10.6pF, vacuum degree 1×10 −4 Pa, capacitance value 11.1pF, vacuum degree 2×10 −3 Pa, etc., the indexing process can substitute the measured capacitance value into the index table for matching and directly obtain the corresponding vacuum degree. For example, the capacitance parameter 10.6pF of the arc extinguishing chamber in the vacuum circuit breaker is substituted into the pre-built index table, and the corresponding vacuum degree is 1×10 − 4 Pa.

[0033] In summary, compared to existing technologies, this application detects the vacuum level of the arc extinguishing chamber within an intelligent phase-controlled vacuum circuit breaker to obtain the vacuum level. Thus, through the physical association between capacitance parameters and vacuum level and an index mapping mechanism, the vacuum level of the arc extinguishing chamber within the vacuum circuit breaker is obtained, providing the necessary data foundation for evaluating the health of the vacuum circuit breaker.

[0034] S20: performing a heating analysis of the vacuum circuit breaker according to the vacuum degree to obtain heating parameters, and performing a zero-crossing monitoring error analysis based on the heating parameters to obtain a zero-crossing error coefficient;

[0035] Insufficient vacuum will lead to increased arc extinguishing energy and increased contact temperature, that is, abnormal heating parameters, which will in turn affect the thermal deformation of the mechanical components of the vacuum circuit breaker and the accuracy of the sensor, resulting in an increase in the zero-crossing point monitoring error and destroying the accuracy of the intelligent phase control function.

[0036] In response to the above problems, the present application performs heating analysis of the vacuum circuit breaker according to the vacuum degree to obtain heating parameters, performs zero-crossing monitoring error analysis based on the heating parameters to obtain a zero-crossing error coefficient.

[0037] Specifically, step S20 in the method includes:

[0038] Call the fever predictor;

[0039] The vacuum degree is input into the heating predictor, and the output is analyzed to obtain heating parameters, wherein the heating parameters include heating temperature.

[0040] In the embodiment of the present application, a decrease in vacuum degree will lead to a decrease in the insulation performance of the arc extinguishing chamber of the vacuum circuit breaker, an increase in arc energy, and an increase in contact erosion, which in turn causes abnormal heating. That is, a mapping relationship is established between the vacuum degree and the heating parameter. The heating state of the circuit breaker can be predicted based on the vacuum degree. Specifically:

[0041] First, the pre-trained heating predictor is called. For example, the heating predictor is constructed based on the mapping relationship between vacuum degree and heating parameters, and uses a machine learning model trained with historical data. By inputting vacuum degree, the output heating parameters can be predicted. For example, the vacuum degree 1×10 −4 Pa is input into the pre-trained fever predictor to predict the output fever parameter: 40℃.

[0042] Secondly, the vacuum degree is input into the heating predictor, and the output is analyzed to obtain heating parameters, wherein the heating parameters include heating temperature.

[0043] Specifically, the training steps of the "fever predictor" include:

[0044] According to the operation data of the vacuum circuit breaker in the historical time, a sample vacuum degree set is collected, and the heating parameters of the vacuum circuit breaker under different sample vacuum degrees are collected, and the sample heating parameter set is obtained by annotation;

[0045] Build a machine learning-based fever predictor;

[0046] The sample vacuum degree set and the sample heating parameter set are used to perform supervised training on the heating predictor, and the training is stopped after the test accuracy meets the requirement.

[0047] In the embodiment of the present application, first, based on the operation data of the vacuum circuit breaker in the historical time, a sample vacuum degree set is collected, and the heating parameters of the vacuum circuit breaker under different sample vacuum degrees are collected, and the sample heating parameter set is obtained by annotation. For example, the vacuum degree of the vacuum circuit breaker at different operation stages can be collected based on the historical operation database, for example, 0.5×10 − 4 Pa, 1×10 −4 Pa, 2×10 −3 Pa, etc., as a sample vacuum degree set, and then the temperature of the vacuum circuit breaker under different sample vacuum degrees, for example, 35°C, 40°C, 42°C, etc., is collected. Based on this, the sample vacuum degree set is labeled to obtain a sample heating parameter set with a temperature label, wherein the temperature collection can use an infrared thermal imager or an embedded temperature sensor to collect the vacuum circuit breaker contact temperature.

[0048] Secondly, a machine learning-based heating predictor is constructed. For example, machine learning models can include random forests, LSTM networks, and multi-layer perceptrons. Random forests excel at processing high-dimensional nonlinear relationships, while LSTM networks excel at capturing long-term dependencies in time series data. For example, a multi-layer perceptron (MLP) model primarily consists of an input layer, two hidden layers, and an output layer. The input layer receives features such as vacuum level and heating parameters. The hidden layer uses the ReLU activation function to capture the mapping between vacuum level and heating parameters. For example, a decrease in vacuum level leads to an increase in arc energy, which in turn triggers a chain reaction of increased contact temperature. The output layer directly predicts the steady-state contact temperature and limits it to a safe threshold through physical constraints.

[0049] Finally, the sample vacuum degree set and the sample heating parameter set are used to conduct supervised training on the heating predictor, and the training is stopped after the test accuracy meets the requirements. For example, the training process of the heating predictor can be achieved through the following technical paths: 1. Training data preparation, the sample vacuum degree set and the sample heating parameter set are divided into a training set, a validation set, and a test set in a ratio of 7:1.5:1.5. 2. Model training, the labeled sample vacuum degree set and the sample heating parameter set are input into the model in batches, the mapping relationship between the vacuum degree and the heating parameter is captured through the hidden layer, the output layer predicts the steady-state temperature of the contact, and then the mean square error between the predicted temperature and the labeled sample heating parameter is calculated, which is used as the loss function to evaluate the current performance of the model, and then with the help of optimizers such as Adam, the model parameters are back-propagated and adjusted according to the gradient information of the loss function to reduce the prediction error. After multiple rounds of iterative training and test verification, when the prediction accuracy of the model on the independent test set reaches more than 95%, it is considered to converge, and a trained heating predictor is obtained.

[0050] Furthermore, the “performing zero-crossing monitoring error analysis based on heating parameters to obtain a zero-crossing error coefficient” includes:

[0051] Calling a zero-point error analyzer, wherein the zero-point error analyzer is trained using a sample heating parameter set and a sample zero-point error coefficient set,

[0052] The heating parameters are input into a zero-point error analyzer, and a zero-point error coefficient is obtained as an output.

[0053] In the embodiment of the present application, the zero crossing point refers to the zero crossing moment when the instantaneous value of the AC voltage or current changes with the sinusoidal law, transitions from the positive half cycle to the negative half cycle or from the negative half cycle to the positive half cycle. There are two zero crossing points in a complete cycle, such as the current zero crossing point and the voltage zero crossing point. When the current crosses zero, the deionization effect of the arc plasma dominates, becoming a natural arc extinction window. When the voltage crosses zero, the electric field strength is zero, and the direction of charge movement switches. At this time, closing the circuit breaker can effectively reduce the excitation inrush current.

[0054] Furthermore, in intelligent phase-controlled vacuum circuit breakers, precisely controlling the opening of contacts near the current zero-crossing point can reduce contact erosion by leveraging the arc's natural extinction characteristics. Closing at the voltage zero-crossing point can also reduce mechanical shock and electromagnetic transients. However, if the actual operating time deviates from the theoretical zero-crossing point, this can lead to increased arc energy during opening, causing abnormal contact heating, or inrush current during closing, accelerating equipment aging. Therefore, the zero-crossing error coefficient is a key parameter for assessing circuit breaker health.

[0055] Furthermore, insufficient vacuum can lead to increased arc extinguishing energy, causing contact temperature to rise. Heat, in turn, can cause thermal expansion of the contact material and deformation of the mechanical structure, which in turn affects the accuracy of zero-crossing detection. For example, thermal expansion of the contacts can change the opening and closing times, leading to zero-crossing monitoring deviations. Therefore, in order to improve the accuracy of zero-crossing monitoring, a zero-crossing monitoring error analysis can be performed based on the heating parameters to obtain the zero-crossing error coefficient. Specifically:

[0056] First, call the zero-point error analyzer, wherein the zero-point error analyzer is trained using a sample heating parameter set and a sample zero-crossing error coefficient set. For example, the heating parameters can be obtained from the output of the aforementioned heating predictor, or the heating parameters can be collected by an infrared thermal imager or an embedded temperature sensor as a sample heating parameter set, and then the zero-crossing error coefficients under different heating parameters are collected, wherein the detection of the zero-crossing point can be achieved by a hardware zero-crossing comparator or software waveform analysis, and the zero-crossing error coefficient can be obtained by synchronously collecting the actual zero-crossing point and the theoretical zero-crossing point of the circuit breaker, and then calculated by the following formula: zero-crossing error coefficient = (half-cycle time measured zero-crossing time - theoretical zero-crossing time) × 100%. For example, the zero-crossing error coefficients of 2%, 3%, 5%, etc. are obtained by the above formula as the sample zero-crossing error coefficient set.

[0057] For example, the construction and training of a zero-point error analyzer can be achieved through the following technical path: 1. Training data preparation: The sample heating parameter set and the sample zero-crossing error coefficient set are divided into a training set, a validation set, and a test set in a ratio of 7:1.5:1.5. 2. Model construction: Taking a deep neural network (DNN) as an example, a three-layer fully connected network is first constructed, with an input layer of 10 nodes, a hidden layer of 64 / 32 nodes, and an output layer of 1 node. The input layer receives standardized heating parameters (e.g., temperature normalized to [0, 1]). The hidden layer uses the ReLU activation function to capture the nonlinear mapping between heating parameters and zero-crossing error coefficients. The output layer generates predicted zero-crossing error coefficients through a linear transformation. 3. Model training: The Adam optimizer can be used during training, with the mean squared error (MSE) as the loss function. A learning rate of 0.001 is set with cosine annealing decay. The dropout rate (0.2-0.5) is adjusted every 50 iterations using the validation set to prevent overfitting. 4. Model evaluation and optimization: Calculate the mean absolute error (MAE) and coefficient of determination (R²) on the test set. Stop training when MAE ≤ 1.2° and R² > 0.9 to obtain a trained zero-point error analyzer.

[0058] Next, the heating parameter is input into a zero-point error analyzer, which outputs a zero-point error coefficient. For example, a heating parameter (e.g., 40°C) is input into the zero-point error analyzer, which outputs a zero-point error coefficient (e.g., 3.5%). This zero-point error coefficient can be used to adjust the weights in subsequent health calculations.

[0059] In summary, compared with the prior art, the present application performs a heating analysis of the vacuum circuit breaker according to the vacuum degree to obtain heating parameters, performs a zero-crossing monitoring error analysis based on the heating parameters, and obtains a zero-crossing error coefficient. In this way, according to the mapping relationship between vacuum degree and heating parameters, a heating predictor constructed by machine learning is used to perform heating analysis on different vacuum degrees to obtain heating parameters, and then, according to the relationship between heating parameters and zero-crossing error coefficients, a zero-crossing monitoring error analysis is performed on different heating parameters through a zero-point error analyzer to obtain a zero-crossing error coefficient, providing a reliable data basis for the weight adjustment of subsequent health calculations.

[0060] S30: Mapping a zero-crossing error coefficient according to the operating time parameter of the vacuum circuit breaker, calculating a zero-crossing deviation coefficient with the zero-crossing error coefficient, and performing confidence processing on the zero-crossing deviation coefficient and analysis deviation coefficients of heating analysis and zero-crossing monitoring error analysis to obtain a zero-crossing confidence level;

[0061] The running time will cause the vacuum circuit breaker to age, which will in turn lead to zero-crossing detection errors. The longer the running time, the more serious the aging of the vacuum circuit breaker and the greater the zero-crossing detection error.

[0062] In response to the above problems, the present application maps the operating time parameters of the vacuum circuit breaker to obtain a mapped zero-crossing error coefficient, calculates the zero-crossing deviation coefficient with the zero-crossing error coefficient, and performs confidence processing on the zero-crossing deviation coefficient and the analysis deviation coefficients of the heating analysis and the zero-crossing monitoring error analysis to obtain the zero-crossing confidence.

[0063] Specifically, step S30 in the method includes:

[0064] Obtaining an operating time parameter of the vacuum circuit breaker;

[0065] Inputting the running time parameter into a zero-crossing error table, and mapping to obtain a mapped zero-crossing error coefficient, wherein the zero-crossing error table is constructed based on a mapping relationship between the sample running time parameter and the sample mapped zero-crossing error coefficient;

[0066] Calculating the error amplitude of the zero-crossing error coefficient and the mapped zero-crossing error coefficient as a zero-crossing deviation coefficient;

[0067] Obtain the analysis error rate of fever analysis and zero-crossing monitoring error analysis, and calculate the analysis deviation coefficient;

[0068] The similarity between the zero-crossing deviation coefficient and the analysis deviation coefficient is calculated to obtain the zero-crossing confidence.

[0069] In the embodiment of the present application, the operating time parameter of the vacuum circuit breaker is first obtained. For example, the operating time parameter of the vacuum circuit breaker can be obtained based on historical data, for example, 1 year.

[0070] Secondly, the operating time parameter is input into the zero-crossing error table, and a mapping zero-crossing error coefficient is obtained by mapping, wherein the zero-crossing error table is constructed based on the mapping relationship between the sample operating time parameter and the sample mapping zero-crossing error coefficient. Specifically, the operating time will cause the vacuum circuit breaker to age, which in turn causes the zero-crossing detection error. The longer the operating time, the more serious the aging of the vacuum circuit breaker and the greater the zero-crossing detection error. Therefore, a zero-crossing error table can be constructed based on the mapping relationship between the operating time parameter and the mapping zero-crossing error coefficient. For example, by collecting circuit breaker samples with different operating times, such as 0.5 years, 1 year, 3 years, 5 years, 10 years, etc., as sample operating time parameters, and measuring the mapping zero-crossing error coefficients under standard working conditions under different operating time parameters, such as 1.3%, 1.5%, 2.5%, 3.3%, and 4.5%, as sample mapping zero-crossing error coefficients, and then constructing the zero-crossing error table based on the sample operating time parameters and the sample mapping zero-crossing error coefficients. Exemplarily, the operating time parameter of the vacuum circuit breaker (eg, 1 year) is input into the zero-crossing error table, and mapped to obtain a mapped zero-crossing error coefficient (eg, 1.5%).

[0071] Next, the error magnitude between the zero-crossing error coefficient and the mapped zero-crossing error coefficient is calculated as the zero-crossing deviation coefficient. The zero-crossing deviation coefficient = |zero-crossing error coefficient - mapped zero-crossing error coefficient|. The zero-crossing deviation coefficient reflects the deviation magnitude between the zero-crossing error coefficient and the mapped zero-crossing error coefficient, that is, the degree of deviation between the current predicted error and the expected aging error. A large zero-crossing deviation coefficient may indicate an abnormal factor, such as abnormal contact heating or sensor failure. For example, if the zero-crossing error coefficient obtained from the zero-crossing error analyzer output is 3.5%, and the mapped zero-crossing error coefficient obtained from the zero-crossing error table mapping is 1.5%, then the zero-crossing deviation coefficient = |3.5% - 1.5%| = 2%.

[0072] Furthermore, the analysis error rates of the fever analysis and the zero-crossing monitoring error analysis are obtained, and the analysis deviation coefficient is calculated. This is because both the fever analysis and the zero-crossing monitoring error analysis use model predictions, and the accuracy of the model predictions cannot reach 100%, that is, there must be an analysis error rate. For example, based on the historical prediction data of the fever predictor and the zero-point error analyzer, the respective prediction error rates can be counted, and then the mean is calculated to obtain the analysis deviation coefficient. For example, if the historical prediction error rates of the fever predictor and the zero-point error analyzer are 5% and 3%, respectively, then the analysis deviation coefficient = (5% + 3%) / 2 = 4%. The analysis deviation coefficient can reflect the comprehensive analysis error of the fever predictor and the zero-point error analyzer.

[0073] Finally, the similarity between the zero-crossing deviation coefficient and the analysis deviation coefficient is calculated to obtain the zero-crossing confidence, wherein similarity = 1 / (1+Euclidean distance between the zero-crossing deviation coefficient and the analysis deviation coefficient), zero-crossing confidence = (1+similarity) / 2, the closer the zero-crossing deviation coefficient and the analysis deviation coefficient are, the smaller the Euclidean distance is, the greater the similarity is, the greater the similarity is, the closer the predicted zero-crossing error coefficient of the fever predictor and the zero-point error analyzer is to the mapped zero-crossing error coefficient output by the zero-crossing error table mapping, that is, the more reliable the model prediction is, the greater the zero-crossing confidence is. Exemplarily, the similarity can be calculated as the cosine similarity of the zero-crossing deviation coefficient and the analysis deviation coefficient. For example, the Euclidean distance between the zero-crossing deviation coefficient of 2% and the analysis deviation coefficient of 4% is first calculated to be 2%, then the similarity is calculated to be 1 / (1+2%)=0.9804, and finally the zero-crossing confidence is calculated to be (1+0.9804) / 2=0.9902.

[0074] In summary, compared to the prior art, this application maps the zero-crossing error coefficient based on the operating time parameters of the vacuum circuit breaker, calculates the zero-crossing deviation coefficient based on the zero-crossing error coefficient, and performs confidence processing based on the zero-crossing deviation coefficient and the analysis deviation coefficients of the heating analysis and zero-crossing monitoring error analysis to obtain the zero-crossing confidence. In this way, the credibility of the zero-crossing error coefficient output by the model prediction is quantified, improving the reliability of the state monitoring of the intelligent phase-controlled vacuum circuit breaker.

[0075] S40: allocating weights according to the zero-crossing confidence, performing health calculation based on the vacuum degree and the zero-crossing error coefficient, and obtaining the health of the vacuum circuit breaker.

[0076] The arc extinguishing chamber vacuum degree, zero-crossing error coefficient, and mapped zero-crossing error coefficient are obtained through the above steps. Among them, the vacuum degree directly reflects the sealing strength of the arc extinguishing chamber, the zero-crossing error coefficient is related to the mechanical action timing offset, and the mapped error coefficient quantifies the aging accumulation of the equipment during long-term operation. Based on this, the health status of the vacuum circuit breaker can be evaluated.

[0077] To address the above problem, the present application allocates weights according to the zero-crossing confidence, calculates the healthiness based on the vacuum degree and the zero-crossing error coefficient, and obtains the healthiness of the vacuum circuit breaker.

[0078] Specifically, step S40 in the method includes:

[0079] Obtain the preset vacuum degree weight and the preset zero-crossing point weight;

[0080] Using the zero-crossing confidence, the preset zero-crossing weight is corrected and calculated to obtain the zero-crossing weight, and the vacuum degree weight is calculated;

[0081] Calculating the vacuum health and the zero-crossing health according to the vacuum degree, the zero-crossing error coefficient and the mapped zero-crossing error coefficient;

[0082] According to the zero-crossing weight and the vacuum weight, the zero-crossing health and the vacuum health are weighted and calculated to obtain the health of the vacuum circuit breaker.

[0083] In the embodiment of the present application, a preset vacuum degree weight and a preset zero-crossing point weight are first obtained. For example, the vacuum degree reflects the insulation state of the arc extinguishing chamber of the vacuum circuit breaker, and the zero-crossing point error coefficient reflects the reliability of the phase control function. Therefore, the vacuum degree weight can be preset to a higher value, for example, the preset vacuum degree weight is 0.6, and the preset zero-crossing point weight is 0.4.

[0084] Secondly, the zero-crossing confidence level is adopted to perform a correction calculation on the preset zero-crossing weight to obtain the zero-crossing weight, and the vacuum weight is calculated, wherein the zero-crossing weight = zero-crossing confidence level * preset zero-crossing weight, and the vacuum weight = 1-zero-crossing weight. For example, the zero-crossing confidence level can reflect the model's prediction credibility for the zero-crossing error coefficient. When the prediction credibility is low, the zero-crossing weight ratio is reduced to avoid the interference of abnormal data on the evaluation results, and achieve a dynamic balance in which reliable data is highly weighted and suspicious data is lowly weighted. For example, when the zero-crossing confidence level is 0.9902, the zero-crossing weight = 0.9902*0.4 = 0.396, and the vacuum weight = 1-0.396 = 0.604. In this way, the preset zero-crossing weight is corrected and calculated according to the zero-crossing confidence level.

[0085] Again, according to the vacuum degree, the zero-crossing error coefficient and the mapped zero-crossing error coefficient, the vacuum health degree and the zero-crossing health degree are calculated. For example, the similarity between the vacuum degree and the standard vacuum degree can be calculated as the vacuum health degree, and the reciprocal of the mean of the zero-crossing error coefficient and the mapped zero-crossing error coefficient can be calculated as the zero-crossing health degree. The standard vacuum degree can be obtained by obtaining the ideal vacuum degree of a newly manufactured vacuum circuit breaker, such as 10 −5 Pa, as the benchmark for health evaluation, similarity = 1 / (1 + Euclidean distance between vacuum degree and standard vacuum degree), zero-crossing health = 2 / (zero-crossing error coefficient + mapping zero-crossing error coefficient). For example, the vacuum degree is 1×10 −4 Pa, the ideal vacuum degree is 10 −5 Pa, the zero-crossing error coefficient is 3.5%, and the mapped zero-crossing error coefficient is 1.5%. Then the Euclidean distance between the vacuum degree and the standard vacuum degree = 9×10 −5 , similarity = 1 / (1+9×10 −5 ) = 0.99991, as the vacuum health, the zero-crossing health = 2 / (3.5% + 1.5%) = 40.

[0086] Finally, based on the zero-crossing weight and vacuum weight, the zero-crossing health and vacuum health are weighted and calculated to obtain the health of the vacuum circuit breaker, where the health of the vacuum circuit breaker = zero-crossing weight * zero-crossing health + vacuum weight * vacuum health. For example, if the calculated zero-crossing weight is 0.396, the vacuum weight is 0.604, the zero-crossing health is 40, and the vacuum health is 0.99991, then the health of the vacuum circuit breaker = 0.396 * 40 + 0.604 * 0.99991 = 16.6. The health of the vacuum circuit breaker can comprehensively reflect the multi-dimensional operating characteristics of the vacuum circuit breaker from insulation performance to aging status. The better the health of the vacuum circuit breaker, the greater the health of the vacuum circuit breaker.

[0087] In summary, compared to the prior art, this application assigns weights based on zero-crossing confidence, calculates health based on the vacuum level and zero-crossing error coefficient, and obtains the health of the vacuum circuit breaker. In this way, the preset weights are adaptively corrected based on the zero-crossing confidence level, and the health of the vacuum circuit breaker is obtained by combining the zero-crossing health level and the vacuum health level. This can be used to evaluate the health of the vacuum circuit breaker.

[0088] In summary, the embodiments of the present application have at least the following technical effects:

[0089] Compared to existing technologies, this application first detects the vacuum level of the arc extinguishing chamber within an intelligent phase-controlled vacuum circuit breaker to obtain the vacuum level. This is achieved through the physical association between capacitance parameters and vacuum level, and an index mapping mechanism. This provides the necessary data foundation for evaluating the health of the vacuum circuit breaker.

[0090] Secondly, the present application performs a heating analysis of the vacuum circuit breaker according to the vacuum degree to obtain heating parameters, performs a zero-crossing monitoring error analysis based on the heating parameters, and obtains a zero-crossing error coefficient. In this way, according to the mapping relationship between vacuum degree and heating parameters, a heating predictor constructed by machine learning is used to perform heating analysis on different vacuum degrees to obtain heating parameters. Then, according to the relationship between heating parameters and zero-crossing error coefficients, a zero-crossing monitoring error analysis is performed on different heating parameters through a zero-point error analyzer to obtain a zero-crossing error coefficient, providing a reliable data basis for the weight adjustment of subsequent health calculations.

[0091] Again, this application maps the zero-crossing error coefficient based on the operating time parameters of the vacuum circuit breaker, calculates the zero-crossing deviation coefficient with the zero-crossing error coefficient, and performs confidence processing based on the zero-crossing deviation coefficient and the analysis deviation coefficient of the heating analysis and zero-crossing monitoring error analysis to obtain the zero-crossing confidence. In this way, the credibility of the zero-crossing error coefficient output by the model prediction is quantified, and the reliability of the state monitoring of the intelligent phase-controlled vacuum circuit breaker is improved.

[0092] Finally, the present application assigns weights based on the zero-crossing confidence level, calculates the health level based on the vacuum level and the zero-crossing error coefficient, and obtains the health level of the vacuum circuit breaker. In this way, the preset weights are adaptively corrected based on the zero-crossing confidence level, and the health level of the vacuum circuit breaker is obtained by combining the zero-crossing health level and the vacuum health level. This can be used to evaluate the health of the vacuum circuit breaker.

[0093] Through the above technical solution, this application fully considers that insufficient vacuum will lead to an increase in the arc extinguishing energy in the arc extinguishing chamber of the vacuum circuit breaker, causing abnormal heating parameters, which in turn affects the thermal deformation of mechanical components and sensor accuracy, resulting in an increase in zero-crossing monitoring errors and undermining the accuracy of the intelligent phase-controlled function. Then, using vacuum as the core indicator, combined with multi-dimensional data such as heating parameters, zero-crossing error coefficients, and operating time, through machine learning modeling and confidence correction, the health of the vacuum circuit breaker is obtained, thereby improving the accuracy of the health assessment of the intelligent phase-controlled vacuum circuit breaker.

[0094] Example 2, as Figure 2 As shown, an embodiment of the present invention provides an intelligent phase-controlled vacuum circuit breaker health assessment device, which includes: a memory 210 for storing a computer software program 211; a processor 220 for reading and executing the computer software program, thereby implementing an intelligent phase-controlled vacuum circuit breaker health assessment method.

[0095] In a third embodiment, an embodiment of the present invention provides an intelligent phase-controlled vacuum circuit breaker, which is used to perform health assessment using the health assessment method for the intelligent phase-controlled vacuum circuit breaker provided in the first embodiment.

[0096] It should be noted that, in the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0097] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0098] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0099] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0100] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0101] Although preferred embodiments of the present invention have been described, additional changes and modifications to these embodiments may occur to those skilled in the art once the basic inventive concepts become known.

[0102] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the present invention and its equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. The health evaluation method of an intelligent phase-controlled vacuum circuit breaker is characterized by: The method comprises: Perform vacuum degree detection on the arc extinguishing chamber in the intelligent phase-controlled vacuum circuit breaker to obtain the vacuum degree; performing a heating analysis of the vacuum circuit breaker according to the vacuum degree to obtain heating parameters, and performing a zero-crossing monitoring error analysis based on the heating parameters to obtain a zero-crossing error coefficient; According to the operating time parameter of the vacuum circuit breaker, mapping is performed to obtain a mapped zero-crossing error coefficient, and the zero-crossing deviation coefficient is calculated with the zero-crossing error coefficient; confidence processing is performed on the zero-crossing deviation coefficient and the analysis deviation coefficients of the heating analysis and the zero-crossing monitoring error analysis to obtain a zero-crossing confidence; A weight is allocated according to the zero-crossing confidence, and a health calculation is performed based on the vacuum degree and the zero-crossing error coefficient to obtain the health of the vacuum circuit breaker.

2. The health evaluation method of an intelligent phase-controlled vacuum circuit breaker according to claim 1, characterized in that: Perform vacuum degree detection on the arc extinguishing chamber in the intelligent phase-controlled vacuum circuit breaker to obtain the vacuum degree, including: Detect the capacitance parameters of the arc extinguishing chamber in the vacuum circuit breaker; According to the capacitance parameter, the corresponding vacuum degree is obtained by indexing, wherein the capacitance parameter and the vacuum degree of the arc extinguishing chamber have an index corresponding relationship, and indexing is performed based on the index corresponding relationship.

3. The health evaluation method of an intelligent phase-controlled vacuum circuit breaker according to claim 1, characterized in that: Performing heat analysis on the vacuum circuit breaker according to the vacuum degree to obtain heat parameters includes: Call the fever predictor; The vacuum degree is input into the heating predictor, and the output is analyzed to obtain heating parameters, wherein the heating parameters include heating temperature.

4. The health evaluation method of an intelligent phase-controlled vacuum circuit breaker according to claim 3 is characterized in that: The training step of the fever predictor comprises: According to the operation data of the vacuum circuit breaker in the historical time, a sample vacuum degree set is collected, and the heating parameters of the vacuum circuit breaker under different sample vacuum degrees are collected, and the sample heating parameter set is obtained by annotation; Build a machine learning-based fever predictor; The sample vacuum degree set and the sample heating parameter set are used to perform supervised training on the heating predictor, and the training is stopped after the test accuracy meets the requirement.

5. The health evaluation method of an intelligent phase-controlled vacuum circuit breaker according to claim 1, characterized in that: Perform zero-crossing monitoring error analysis based on heating parameters to obtain the zero-crossing error coefficient, including: Calling a zero-point error analyzer, wherein the zero-point error analyzer is trained using a sample heating parameter set and a sample zero-point error coefficient set, The heating parameters are input into a zero-point error analyzer, and a zero-point error coefficient is obtained as an output.

6. The health evaluation method of an intelligent phase-controlled vacuum circuit breaker according to claim 1, characterized in that: According to the operating time parameter of the vacuum circuit breaker, a mapped zero-crossing error coefficient is mapped and obtained, and a zero-crossing deviation coefficient is calculated with the zero-crossing error coefficient. Confidence processing is performed on the zero-crossing deviation coefficient and the analysis deviation coefficients of the heating analysis and the zero-crossing monitoring error analysis to obtain a zero-crossing confidence, including: Obtaining an operating time parameter of the vacuum circuit breaker; Inputting the running time parameter into a zero-crossing error table, and mapping to obtain a mapped zero-crossing error coefficient, wherein the zero-crossing error table is constructed based on a mapping relationship between the sample running time parameter and the sample mapped zero-crossing error coefficient; Calculating the error amplitude of the zero-crossing error coefficient and the mapped zero-crossing error coefficient as a zero-crossing deviation coefficient; Obtain the analysis error rate of fever analysis and zero-crossing monitoring error analysis, and calculate the analysis deviation coefficient; The similarity between the zero-crossing deviation coefficient and the analysis deviation coefficient is calculated to obtain the zero-crossing confidence.

7. The health evaluation method of an intelligent phase-controlled vacuum circuit breaker according to claim 1, characterized in that: Allocating weights according to the zero-crossing confidence, and performing health calculation based on the vacuum degree and the zero-crossing error coefficient to obtain the health of the vacuum circuit breaker includes: Obtain the preset vacuum degree weight and the preset zero-crossing point weight; Using the zero-crossing confidence, the preset zero-crossing weight is corrected and calculated to obtain the zero-crossing weight, and the vacuum degree weight is calculated; Calculating the vacuum health and the zero-crossing health according to the vacuum degree, the zero-crossing error coefficient and the mapped zero-crossing error coefficient; According to the zero-crossing weight and the vacuum weight, the zero-crossing health and the vacuum health are weighted and calculated to obtain the health of the vacuum circuit breaker.

8. Intelligent phase-controlled vacuum circuit breaker health assessment device, characterized in that: include: Memory for storing computer software programs; A processor is used to read and execute the computer software program, thereby implementing the intelligent phase-controlled vacuum circuit breaker health assessment method according to any one of claims 1 to 7.

9. Intelligent phase-controlled vacuum circuit breaker, characterized in that: The health status is assessed by the method according to any one of claims 1 to 7.

Images