Intelligent high-voltage circuit breaker control system device safety protection method and system

Abstract

The invention discloses an intelligent high-voltage circuit breaker control system device safety protection method and system, and the method comprises the steps: obtaining the historical fault data of a circuit breaker, and building a fault research and judgment intelligent model library according to the historical fault data of the circuit breaker; extracting time domain typical fault features of the historical fault data of the circuit breaker by using an integrated learning method, and constructing a typical fault feature data set; performing fault diagnosis on the typical fault feature data set by using a random forest algorithm, and establishing a circuit breaker fault diagnosis model; and inputting the real-time operation data of the circuit breaker into the circuit breaker fault diagnosis model for detection to obtain a diagnosis result, and comparing the diagnosis result with the fault research and judgment intelligent model library to obtain a fault maintenance scheme. According to the method, rapid fault diagnosis and accurate device fault positioning are realized, instructive opinions are provided for field operation and maintenance personnel, the power supply recovery time is shortened, the equipment is simple and easy to maintain, and the reliability and stability of the high-voltage switch equipment during system operation can be effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent safety protection of high-voltage power systems, and in particular to a safety protection method and system for intelligent high-voltage circuit breaker control system components. Background Art

[0002] With the vigorous development of the power industry and the increasing scale of the power grid, the safe and stable operation of the high-voltage power system has become a key cornerstone to support the sustainable development of the social economy. As the core component of the power system, the operating status of the high-voltage circuit breaker is directly related to the overall safety and stability of the power grid. However, with the enhancement of the interconnectivity of the power grid and the continuous growth of electricity demand, the operating environment faced by high-voltage circuit breakers and their control systems has become increasingly complex and changeable, which has put forward higher requirements for the operation and maintenance management and fault prevention of the equipment. In this context, the application of intelligent technology is particularly important. It can not only improve the operation and maintenance efficiency of the system, but also effectively prevent and quickly respond to faults through real-time monitoring and intelligent analysis, thereby ensuring the safe and stable operation of the power grid.

[0003] At present, although the application potential of intelligent technology in high-voltage power systems is huge, the traditional high-voltage circuit breaker control system still exposes many problems in fault operation and maintenance. First, the failure to find faults in time is a major pain point. The traditional manual inspection method is limited by time, manpower and other factors, and it is difficult to achieve real-time monitoring of equipment status, resulting in faults often being detected only after the system shows obvious abnormalities, at which time the fault has already had an adverse impact on the operation of the power grid. Secondly, inaccurate fault location is also a major challenge. Due to the lack of efficient real-time data monitoring and intelligent analysis methods, fault location often relies on the experience judgment and trial and error method of operation and maintenance personnel, which is not only cumbersome and error-prone, but also increases the difficulty and cost of fault handling. In addition, the limited transmission of expert knowledge and the high cost of operation and maintenance are also issues that cannot be ignored. The valuable expert knowledge accumulated in the power system is difficult to quickly popularize to the front-line operation and maintenance personnel, and the traditional manual inspection mode is accompanied by high labor costs, which restrict the improvement of the operation and maintenance level of high-voltage power systems to varying degrees. Therefore, the development of intelligent high-voltage circuit breaker control systems and device safety protection methods is of great significance to solving the above problems and improving the efficiency and safety of power grid operation and maintenance. Summary of the invention

[0004] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0005] In view of the above existing problems, the present invention is proposed. Therefore, the present invention provides an intelligent high-voltage circuit breaker control system device safety protection method to solve the problems of untimely fault detection, inaccurate positioning and low processing efficiency of traditional high-voltage switchgear.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides a method for protecting components of an intelligent high-voltage circuit breaker control system, comprising:

[0008] Acquire historical fault data of the circuit breaker, and establish a fault analysis intelligent model library based on the historical fault data of the circuit breaker;

[0009] Extracting typical fault features in the time domain of the historical fault data of the circuit breaker using an integrated learning method, and constructing a typical fault feature data set;

[0010] Using a random forest algorithm to perform fault diagnosis on the typical fault feature data set, and establishing a circuit breaker fault diagnosis model;

[0011] The real-time operation data of the circuit breaker is input into the circuit breaker fault diagnosis model for detection to obtain the diagnosis result, and the diagnosis result is compared with the fault analysis intelligent model library to obtain the fault maintenance plan.

[0012] As a preferred solution of the intelligent high-voltage circuit breaker control system device safety protection method described in the present invention, wherein: using an integrated learning method to extract the time domain typical fault characteristics of the circuit breaker historical fault data, constructing a typical fault characteristic data set includes:

[0013] In the sampling stage, N samples are extracted from the historical fault data of the circuit breaker with replacement, and N rounds of sampling are performed to obtain N training sets;

[0014] In the training phase, the training set is trained using a machine learning algorithm to obtain a plurality of base learners, and typical time-domain fault features that are critical to classifying fault categories are screened and obtained according to feature importance evaluation results of the base learners;

[0015] In the concentration stage, the feature importance evaluation results of multiple base learners are combined using the average voting strategy to obtain a typical fault feature dataset.

[0016] As a preferred solution of the intelligent high-voltage circuit breaker control system device safety protection method described in the present invention, wherein: the base learner includes:

[0017] Calculate the error rate of the base learner, select and adjust the base learner according to the error rate, and calculate the error rate of the base learner as:

[0018] H(y i (x)≠f(x))=α

[0019] Among them, y i is the base learner, α is the base classifier error rate, f is the true function, and x is the input feature.

[0020] As a preferred solution of the intelligent high-voltage circuit breaker control system device safety protection method described in the present invention, wherein: using a random forest algorithm to perform fault diagnosis on the typical fault feature data set, establishing a circuit breaker fault diagnosis model includes:

[0021] A bootstrap sampling method is used to randomly select N samples with replacement from the typical fault feature data set;

[0022] When constructing each node of each tree in the random forest algorithm, a fault feature subset containing m features is randomly selected, and the optimal fault feature is selected from the fault feature subset for node splitting;

[0023] A decision tree is recursively constructed based on randomly selected samples and feature subsets. If the set depth is reached, the decision tree construction is stopped and the fault category is determined based on the decision tree.

[0024] As a preferred solution of the intelligent high-voltage circuit breaker control system device safety protection method of the present invention, it also includes:

[0025] Setting multiple parameter combinations of the random forest algorithm, calculating the accuracy of the random forest algorithm under each parameter combination using a cross-validation strategy, and selecting the best parameter combination as the final parameter of the random forest algorithm according to the accuracy;

[0026] Calculate the harmonic mean of the precision and recall of the random forest algorithm, adjust the parameters of the random forest algorithm, or re-screen typical fault features in the time domain.

[0027] As a preferred solution of the intelligent high-voltage circuit breaker control system device safety protection method of the present invention, wherein: inputting the real-time operation data of the circuit breaker into the circuit breaker fault diagnosis model for detection includes:

[0028] Real-time operation data of the circuit breaker is obtained. If the real-time operation data exceeds a preset threshold, it is determined that the circuit breaker is faulty. The data of the faulty circuit breaker is input into a circuit breaker fault diagnosis model to obtain a diagnosis result.

[0029] As a preferred solution of the intelligent high-voltage circuit breaker control system device safety protection method described in the present invention, the fault analysis intelligent model library includes fault categories, typical fault characteristics, fault causes, and fault repair solutions.

[0030] In a second aspect, the present invention provides a system for protecting components of an intelligent high-voltage circuit breaker control system, comprising:

[0031] A data acquisition module, used to acquire historical fault data of the circuit breaker;

[0032] A fault judgment model library generation module is used to establish a fault judgment intelligent model library based on the historical fault data of the circuit breaker;

[0033] A feature extraction module, used to extract the typical fault features in the time domain of the historical fault data of the circuit breaker by using an integrated learning method, and to construct a typical fault feature data set;

[0034] A diagnosis module establishment module is used to perform fault diagnosis on the typical fault feature data set using a random forest algorithm to establish a circuit breaker fault diagnosis model;

[0035] A fault diagnosis module, used for inputting the real-time operation data of the circuit breaker into the circuit breaker fault diagnosis model for detection to obtain the diagnosis result;

[0036] The fault adjustment solution acquisition module is used to compare the diagnosis result with the fault analysis intelligent model library to obtain a fault repair solution.

[0037] In a third aspect, the present invention provides a computing device, comprising:

[0038] Memory and processor;

[0039] The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions. When the computer executable instructions are executed by the processor, the steps of the intelligent high-voltage circuit breaker control system component safety protection method are implemented.

[0040] In a fourth aspect, the present invention provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the intelligent high-voltage circuit breaker control system component safety protection method.

[0041] Compared with the prior art, the present invention has the following beneficial effects: the present invention can discover the potential safety hazards in the real-time operation status of equipment and systems earlier through the intelligent high-voltage circuit breaker control system device safety protection strategy and apparatus. Compared with the traditional method, the use of artificial intelligence algorithm can also achieve rapid fault diagnosis and accurate positioning of device faults, provide guiding opinions for on-site operation and maintenance personnel, reduce the time to restore power supply, and the equipment is simple and easy to maintain, which can effectively improve the reliability and stability of high-voltage switchgear during system operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0043] Figure 1 A schematic diagram of the overall process of a method for protecting components of an intelligent high-voltage circuit breaker control system according to an embodiment of the present invention DETAILED DESCRIPTION

[0044] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0045] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0046] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0047] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0048] At the same time, in the description of the present invention, it should be noted that the orientations or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the orientations or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the system or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0049] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0050] Example 1

[0051] Reference Figure 1 , which is an embodiment of the present invention, provides a method for protecting components of an intelligent high-voltage circuit breaker control system, comprising:

[0052] S100: Acquire historical fault data of the circuit breaker, and establish a fault analysis intelligent model library based on the historical fault data of the circuit breaker;

[0053] Preferably, the fault analysis intelligent model library includes fault categories, typical fault characteristics, fault causes, and fault repair solutions;

[0054] Specifically, the historical fault data of the circuit breaker is comprehensively collected through data acquisition equipment. The historical fault data includes but is not limited to the time when the fault occurred, the symptoms of the fault, the fault handling process, the maintenance records, etc. The collected historical fault data is deeply analyzed and processed, and the faults are carefully classified in combination with expert experience and actual maintenance cases, and the specific causes of each type of fault are clarified; on this basis, an intelligent model library for fault analysis is constructed, which not only contains detailed classifications and typical feature descriptions of various types of faults, but also covers the possible causes of each type of fault and the corresponding maintenance solutions;

[0055] It should be noted that with the extension of operating time and the continuous emergence of new fault types, the fault analysis intelligent model library can be continuously updated and optimized. By continuously collecting new fault data and feeding it back to the model, the accuracy and adaptability of the model can be further improved, ensuring that the high-voltage circuit breaker control system always maintains an efficient and stable operating state in a complex and changeable operating environment.

[0056] S102: extracting typical fault features in the time domain of historical fault data of circuit breaker by using an integrated learning method, and constructing a typical fault feature data set;

[0057] In the embodiment of the present application, fault characteristics are mainly extracted for abnormal IGBT switching frequency, IGBT short circuit fault, over-limit temperature rise of thermistor circuit, Hall device fault, inverter circuit fault, etc. to establish a fault characteristic data set;

[0058] In the embodiment of the present application, the abnormal IGBT switching frequency is represented by:

[0059] H min ≤H≤H max

[0060] Among them, H min The minimum value of IGBT switching frequency setting, H max Set the maximum value for the IGBT switching frequency;

[0061] In the embodiment of the present application, the temperature rise of the thermistor probe circuit exceeding the limit is expressed as:

[0062]

[0063] Among them, T(t) is the actual output value, T i (t) is the measured value during normal operation, T max is the maximum allowable operating temperature, α is the temperature setting coefficient when fault occurs, and △t is the over-limit time;

[0064] The extraction of typical fault features in the time domain of historical fault data of circuit breakers using ensemble learning methods mainly includes three stages: sampling stage, training stage and concentration stage;

[0065] Preferably, in the sampling stage, N samples are extracted from the historical fault data of the circuit breaker with replacement, and N rounds of sampling are performed to obtain N training sets;

[0066] Preferably, in the training phase, a machine learning algorithm is used to train the training set to obtain multiple base learners, and based on the feature importance evaluation results of the base learners, typical fault features in the time domain that are critical to classifying the fault categories are screened and obtained;

[0067] Preferably, the error rate of the base learner is calculated, and the base learner is selected and adjusted according to the error rate. The error rate of the base learner is calculated as:

[0068] H(y i (x)≠f(x))=α

[0069] Among them, y i is the base learner, α is the base classifier error rate, f is the true function, and x is the input feature;

[0070] Preferably, in the concentration stage, the feature importance evaluation results of multiple base learners are combined using an average voting strategy to obtain a typical fault feature data set;

[0071] In the embodiment of the present application, the average voting strategy is expressed as:

[0072]

[0073] Among them, y iis the base learner, x is the input feature, Z(x) is the final feature obtained by evaluation voting, y i is the base learner;

[0074] Specifically, taking IGBT fault as an example, when the fault current is detected to be greater than the minimum allowed value, an ensemble learning algorithm is used to extract typical fault features. First, 6 samples are extracted from the sample set for 6 rounds of training to obtain 6 training sets; then, the training sets are trained to obtain 6 base learners; secondly, the results of the 6 base learners obtained above are averaged and voted to obtain the final result;

[0075] It should be noted that the present invention, through the application of integrated learning methods and the fine processing of three stages of sampling, training and concentration, not only effectively extracts the time domain characteristics of various typical faults such as IGBT switching frequency anomaly, IGBT short circuit fault, thermistor loop temperature rise exceeding the limit, Hall device fault, inverter circuit fault, etc. from a large amount of historical data, but also ensures the high importance of the selected features for fault classification through error rate evaluation and screening of base learners; finally, the results of multiple base learners are integrated through the average voting strategy to construct a more accurate and comprehensive typical fault feature data set, which improves the accuracy and efficiency of fault identification, provides solid data support for subsequent fault diagnosis and maintenance, and enhances the reliability and stability of the circuit breaker system.

[0076] S104: Using a random forest algorithm to perform fault diagnosis on a typical fault feature data set, and establishing a circuit breaker fault diagnosis model;

[0077] Preferably, a bootstrap sampling method is used to randomly select N samples with replacement from a typical fault feature data set;

[0078] Preferably, when constructing each node of each tree in the random forest algorithm, a fault feature subset containing m features is randomly selected, and the optimal fault feature is selected from the fault feature subset for node splitting;

[0079] Preferably, a decision tree is recursively constructed based on randomly selected samples and feature subsets. If a set depth is reached, construction of the decision tree is stopped, and the fault category is determined based on the decision tree.

[0080] Preferably, multiple parameter combinations of the random forest algorithm are set, the accuracy of the random forest algorithm under each parameter combination is calculated using a cross-validation strategy, and the best parameter combination is selected as the final parameter of the random forest algorithm according to the accuracy;

[0081] Preferably, the harmonic mean of the precision and recall of the random forest algorithm is calculated, and the parameters of the random forest algorithm are adjusted or typical fault features in the time domain are re-screened;

[0082] In the embodiment of the present application, the harmonic mean calculation formula is expressed as:

[0083]

[0084] Among them, Precision is the precision rate, Recall is the recall rate;

[0085] Precision: The proportion of samples that are actually positive among the samples predicted by the model to be positive. The calculation formula is:

[0086]

[0087] Among them, TP represents true positive examples, that is, the number of samples that are actually positive and predicted as positive by the model, and FP represents false positive examples, that is, the number of samples that are actually negative but predicted as positive by the model;

[0088] Recall: The proportion of samples that are correctly predicted as positive by the model among all samples that are actually positive. The calculation formula is:

[0089]

[0090] Among them, TP represents true positive examples, that is, the number of samples that are actually positive and predicted as positive by the model, FP represents false positive examples, and FN represents false negative examples, that is, the number of samples that are actually positive but predicted as negative by the model;

[0091] In another possible embodiment, only the precision or recall of the random forest algorithm may be calculated, or another variant of the F1 score, the weighted harmonic mean, may be introduced; taking the weighted harmonic mean as an example, this variant is optimized for unbalanced data sets. This variant not only considers the balance between precision and recall, but also introduces a weight factor to give different importance to the two; assuming that there is a class imbalance problem in the data set, that is, the positive samples are far less than the negative samples. In order to improve the model's recognition ability for positive samples, a weight value is introduced to give the recall rate a higher weight.

[0092] Specifically, a self-service sampling method is used to randomly extract N=1000 samples with replacement from the fault feature data set, and this process is repeated 100 times to generate 100 different training subsets, each of which contains randomly selected samples for constructing each decision tree in the random forest; for each tree in the random forest, a subset containing m=5 features is randomly selected from the fault feature data set, and when constructing each node of the tree, the algorithm selects the optimal feature from this feature subset for node splitting, that is, the samples in the node are divided into two subsets according to the feature, so that the proportion of samples of the same fault category in the divided subsets is the highest; the decision tree is constructed in a recursive manner until a preset tree depth is reached, and the maximum depth set by the present invention is 10, and the decision tree is constructed. The fault category of the input sample is judged according to the tree structure and the node splitting rule;

[0093] At the same time, in order to find the best random forest parameter combination, the present invention sets multiple parameter values, the number of trees ranges from 50 to 200, the feature subset size ranges from 3 to 7, etc.; and uses a cross-validation strategy to calculate the model accuracy under each parameter combination, and by comparing the accuracy under different parameter combinations, select the parameter combination with the highest accuracy as the final parameter; use the selected best parameter combination to train the random forest model, and calculate the harmonic mean of its precision and recall to evaluate the model performance. If the F1 score does not meet the set threshold, the set threshold of F1 is a score higher than 0.9 in the present invention, fine-tune the parameters of the random forest, such as increasing the number of trees or adjusting the feature subset size, or re-checking and screening the typical fault features in the time domain to further improve the diagnostic ability of the model;

[0094] It should be noted that the bootstrap sampling method is used to randomly extract samples from the data set with replacement, which effectively increases the generalization ability of the model and reduces the risk of overfitting. When constructing each decision tree of the random forest, a subset containing m features is randomly selected for node splitting, which not only improves the diversity of the model, but also enables the model to focus on the features that are most critical to the classification task.

[0095] It should also be noted that multiple parameter combinations are evaluated through a cross-validation strategy, and the best parameter combination is selected based on accuracy, which further improves the diagnostic accuracy and stability of the model; by calculating the harmonic mean of the precision and recall of the random forest algorithm, the accuracy and completeness of the model in identifying faults can be comprehensively evaluated. The F1 score, as a comprehensive indicator of precision and recall, can intuitively reflect the overall performance of the model in fault diagnosis tasks; when the F1 score does not meet the requirements, adjusting the random forest algorithm parameters or re-screening typical fault characteristics in the time domain according to the evaluation results can optimize the model in a targeted manner and improve its diagnostic capabilities in complex fault scenarios.

[0096] S106: Input the real-time operation data of the circuit breaker into the circuit breaker fault diagnosis model for detection to obtain the diagnosis result, compare the diagnosis result with the fault analysis intelligent model library, and obtain the fault repair plan;

[0097] Preferably, real-time operation data of the circuit breaker is obtained. If the real-time operation data exceeds a preset threshold, it is determined that the circuit breaker is faulty, and the data of the faulty circuit breaker is input into a circuit breaker fault diagnosis model to obtain a diagnosis result;

[0098] In the embodiment of the present application, the actual detected value is compared with the device's own parameters, and a fault state is indicated when the value exceeds the specified parameter by 15%;

[0099] Specifically, taking abnormal IGBT switching frequency, IGBT short circuit fault and over-limit temperature rise of thermistor circuit as examples, when abnormal IGBT switching frequency fault is detected, the corresponding maintenance plan will be immediately recommended, including first checking the IGBT drive circuit to confirm whether the waveform, amplitude and frequency of the drive signal are abnormal; if the drive circuit is normal, further check the switching frequency parameter settings in the control algorithm, and may need to be adjusted accordingly; if the above measures cannot solve the problem, the system will recommend replacing a new IGBT module to ensure that the circuit breaker returns to normal working state;

[0100] For IGBT short-circuit faults, once the system confirms it, it will immediately prompt to take emergency shutdown measures to prevent the fault from expanding. The maintenance plan is to remind the staff to check whether the IGBT module is physically damaged and decide whether to replace it with a new one according to the situation; at the same time, check the effectiveness of the protection circuit to ensure that it can respond quickly when similar faults occur in the future;

[0101] When the temperature rise of the thermistor probe circuit exceeds the limit, maintenance plans such as enhancing heat dissipation, adjusting load, cleaning and maintenance, or replacing the thermistor probe are proposed based on the diagnosis results to reduce the temperature inside the circuit breaker or the surrounding environment, prevent further damage to the equipment due to overheating, and ensure that the circuit breaker can operate under safe and stable conditions.

[0102] The above is a schematic scheme of a device safety protection method for an intelligent high-voltage circuit breaker control system of this embodiment. It should be noted that the technical scheme of the device safety protection system of the intelligent high-voltage circuit breaker control system and the technical scheme of the device safety protection method of the intelligent high-voltage circuit breaker control system described above belong to the same concept. The details of the technical scheme of the device safety protection system of the intelligent high-voltage circuit breaker control system in this embodiment that are not described in detail can all be referred to the description of the technical scheme of the device safety protection method of the intelligent high-voltage circuit breaker control system described above.

[0103] The intelligent high-voltage circuit breaker control system device safety protection system in this embodiment includes:

[0104] A data acquisition module, used to acquire historical fault data of the circuit breaker;

[0105] A fault judgment model library generation module is used to establish a fault judgment intelligent model library based on the historical fault data of the circuit breaker;

[0106] A feature extraction module is used to extract typical fault features in the time domain of historical fault data of circuit breakers using an integrated learning method and construct a typical fault feature data set;

[0107] A diagnosis module is used to establish a module for fault diagnosis of typical fault feature data sets using a random forest algorithm and to establish a circuit breaker fault diagnosis model;

[0108] A fault diagnosis module is used to input the real-time operation data of the circuit breaker into the circuit breaker fault diagnosis model for detection and obtaining the diagnosis result;

[0109] The fault adjustment plan acquisition module is used to compare the diagnosis results with the fault analysis intelligent model library to obtain the fault repair plan.

[0110] This embodiment further provides a computing device, which is applicable to the case of intelligent high-voltage circuit breaker control system component safety protection, including:

[0111] Memory and processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the intelligent high-voltage circuit breaker control system device safety protection method proposed in the above embodiment.

[0112] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for realizing the safety protection of components of an intelligent high-voltage circuit breaker control system as proposed in the above embodiment is implemented.

[0113] The storage medium proposed in this embodiment and the method for realizing safety protection of components of an intelligent high-voltage circuit breaker control system proposed in the above embodiment belong to the same inventive concept. The technical details not fully described in this embodiment can be referred to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0114] Through the above description of the implementation methods, the technicians in the relevant field can clearly understand that the present invention can be implemented by means of software and necessary general hardware, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ReadOnly, Memory, ROM), random access memory (RandomAccess Memory, RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform the methods of various embodiments of the present invention.

[0115] Example 2

[0116] Referring to Tables 1-4, an embodiment of the present invention provides a method for protecting components of an intelligent high-voltage circuit breaker control system. In order to verify its beneficial effects, comparison results of two solutions are provided.

[0117] In this application implementation case, the method of the present invention is used to build a database containing rich fault information by recording in detail the operating parameters and fault manifestations when each fault occurs;

[0118] This embodiment mainly performs comprehensive detection and diagnosis on three common faults: abnormal IGBT switching frequency, IGBT short circuit fault, and over-limit temperature rise of thermistor circuit. The relevant data are shown in Table 1, Table 2, and Table 3.

[0119] Table 1 IGBT switching frequency abnormal fault characteristic data

[0120] Fault type Typical fault characteristic data Abnormal IGBT switching frequency Switching frequency fluctuation range: ±10Hz Abnormal duration: 5 seconds

[0121] Table 2 IGBT short circuit fault characteristic data

[0122] Fault type Typical fault characteristic data IGBT short circuit failure Short circuit current peak: 1200A Short circuit time: 0.01 seconds

[0123] Table 3 Thermistor probe circuit temperature rise over limit fault characteristic data

[0124] Fault type Typical fault characteristic data Thermistor circuit temperature rise exceeds the limit Temperature rise rate: 5℃ / s Maximum temperature: 120℃ Duration: 1 minute

[0125] Based on the typical fault characteristic data of abnormal IGBT switching frequency, IGBT short circuit fault and over-limit temperature rise of thermistor circuit shown in Table 1, Table 2 and Table 3, a circuit breaker fault diagnosis model is constructed. These characteristic data intuitively reflect the unique performance of various fault types, providing a solid data foundation for subsequent model training and decision tree construction.

[0126] In order to fully verify the effectiveness of the present invention in high-voltage circuit breaker fault diagnosis, based on the operating parameters and fault manifestations of common faults such as abnormal IGBT switching frequency, IGBT short circuit fault, and over-limit temperature rise of thermistor circuit recorded in detail in the early stage, as shown in Table 1, Table 2, and Table 3, on this basis, the method of the present invention is compared with the traditional manual detection method and the method of extracting features using only the random forest algorithm, not only using the integrated method, to obtain the specific performance of different methods in fault detection accuracy and detection time. The results are shown in Table 4;

[0127] Table 4 Fault type detection accuracy of different methods

[0128] Fault type Method of the present invention Manual detection method Only using random forest algorithm Abnormal IGBT switching frequency 91.67％ 74.33％ 82.50％ IGBT short circuit failure 87.25％ 72.75％ 78.40％ Thermistor circuit temperature rise exceeds the limit 89.91％ 74.17％ 87.50％ Average detection time (minutes) 13 30 19

[0129] As shown in Table 4, the comparative analysis of the detection accuracy and detection time of different methods for three types of faults, namely, abnormal IGBT switching frequency, IGBT short circuit fault, and over-limit temperature rise of thermistor circuit, clearly shows the significant advantages of the method of the present invention in fault diagnosis;

[0130] The method of the present invention is not only superior to manual detection and the method using only the random forest algorithm in terms of detection accuracy, but also significantly shortens the detection time, effectively improving the efficiency and accuracy of fault diagnosis. These advantages are due to the circuit breaker fault diagnosis model constructed by the method of the present invention, which makes full use of the rich fault feature data and realizes the rapid and accurate identification of fault types through advanced technologies such as deep learning.

[0131] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An intelligent high-voltage circuit breaker control system component safety protection method, characterized in that: include: Acquire historical fault data of the circuit breaker, and establish a fault analysis intelligent model library based on the historical fault data of the circuit breaker; Extracting typical fault features in the time domain of the historical fault data of the circuit breaker using an integrated learning method, and constructing a typical fault feature data set; Using a random forest algorithm to perform fault diagnosis on the typical fault feature data set, and establishing a circuit breaker fault diagnosis model; The real-time operation data of the circuit breaker is input into the circuit breaker fault diagnosis model for detection to obtain the diagnosis result, and the diagnosis result is compared with the fault analysis intelligent model library to obtain the fault maintenance plan.

2. The intelligent high-voltage circuit breaker control system component safety protection method according to claim 1, characterized in that: The typical fault features in the time domain of the historical fault data of the circuit breaker are extracted by using an integrated learning method, and a typical fault feature data set is constructed, including: In the sampling stage, N samples are extracted from the historical fault data of the circuit breaker with replacement, and N rounds of sampling are performed to obtain N training sets; In the training phase, the training set is trained using a machine learning algorithm to obtain a plurality of base learners, and typical time-domain fault features that are critical to classifying fault categories are screened and obtained according to feature importance evaluation results of the base learners; In the concentration stage, the feature importance evaluation results of multiple base learners are combined using the average voting strategy to obtain a typical fault feature dataset.

3. The intelligent high-voltage circuit breaker control system component safety protection method according to claim 1 or 2, characterized in that: The base learners include: Calculate the error rate of the base learner, select and adjust the base learner according to the error rate, and calculate the error rate of the base learner as: H(y i (x)≠f(x))=α Among them, y i is the base learner, α is the base classifier error rate, f is the true function, and x is the input feature.

4. The intelligent high-voltage circuit breaker control system component safety protection method according to claim 3 is characterized in that: The random forest algorithm is used to perform fault diagnosis on the typical fault feature data set, and a circuit breaker fault diagnosis model is established, including: A bootstrap sampling method is used to randomly select N samples with replacement from the typical fault feature data set; When constructing each node of each tree in the random forest algorithm, a fault feature subset containing m features is randomly selected, and the optimal fault feature is selected from the fault feature subset for node splitting; A decision tree is recursively constructed based on randomly selected samples and feature subsets. If the set depth is reached, the decision tree construction is stopped and the fault category is determined based on the decision tree.

5. The intelligent high-voltage circuit breaker control system component safety protection method according to claim 4, characterized in that: Also includes, Setting multiple parameter combinations of the random forest algorithm, calculating the accuracy of the random forest algorithm under each parameter combination using a cross-validation strategy, and selecting the best parameter combination as the final parameter of the random forest algorithm according to the accuracy; Calculate the harmonic mean of the precision and recall of the random forest algorithm, adjust the parameters of the random forest algorithm, or re-screen typical fault features in the time domain.

6. The intelligent high-voltage circuit breaker control system component safety protection method according to claim 5, characterized in that: Inputting the real-time operation data of the circuit breaker into the circuit breaker fault diagnosis model for detection includes: Real-time operation data of the circuit breaker is obtained. If the real-time operation data exceeds a preset threshold, it is determined that the circuit breaker is faulty. The data of the faulty circuit breaker is input into a circuit breaker fault diagnosis model to obtain a diagnosis result.

7. The intelligent high-voltage circuit breaker control system component safety protection method according to claim 1, characterized in that: The intelligent model library for fault analysis includes fault categories, typical fault characteristics, fault causes, and fault repair solutions.

8. An intelligent high-voltage circuit breaker control system component safety protection system, characterized in that: include, A data acquisition module, used to acquire historical fault data of the circuit breaker; A fault judgment model library generation module is used to establish a fault judgment intelligent model library based on the historical fault data of the circuit breaker; A feature extraction module, used to extract the typical fault features in the time domain of the historical fault data of the circuit breaker by using an integrated learning method, and to construct a typical fault feature data set; A diagnosis module establishment module is used to perform fault diagnosis on the typical fault feature data set using a random forest algorithm to establish a circuit breaker fault diagnosis model; A fault diagnosis module, used for inputting the real-time operation data of the circuit breaker into the circuit breaker fault diagnosis model for detection to obtain the diagnosis result; The fault adjustment solution acquisition module is used to compare the diagnosis result with the fault analysis intelligent model library to obtain a fault repair solution.

9. An electronic device, comprising: Memory and processor; The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions. When the computer executable instructions are executed by the processor, the steps of the intelligent high-voltage circuit breaker control system component safety protection method described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the intelligent high-voltage circuit breaker control system component safety protection method as described in any one of claims 1 to 7.

Images