A high-voltage circuit breaker state monitoring and early warning method based on intelligent learning

Abstract

The present invention belongs to the field of high-voltage circuit breaker monitoring and early warning, relates to data analysis technology, and is used to solve the problem that the prior art cannot separately filter diagnostic parameters and early warning parameters from the operating parameters of the high-voltage circuit breaker. Specifically, it is a high-voltage circuit breaker state monitoring and early warning method based on intelligent learning, comprising the following steps: generating an analysis cycle, obtaining all historical fault data of the high-voltage circuit breaker within the analysis cycle, the historical fault data including the fault type and the fault parameter group, the fault parameter group including the closing current, closing time, opening time, rated current and rated voltage of the high-voltage circuit breaker when the fault occurs, and marking the parameter type in the fault parameter group as an explicit parameter or an implicit parameter; the present invention marks the explicit parameters according to relevant values, and the key parameters indicate that there is a large difference in the numerical value of the explicit parameters under the fault state and the normal operating state, that is, the operating state feedback and early warning analysis of the high-voltage circuit breaker can be performed through the key parameter monitoring.

Description

Technical Field

[0001] The present invention belongs to the field of high-voltage circuit breaker monitoring and early warning, relates to data analysis technology, and specifically is a high-voltage circuit breaker state monitoring and early warning method based on intelligent learning. Background Art

[0002] High-voltage circuit breakers are key equipment in the power system, responsible for control and protection to ensure the safe and stable operation of the power system; they are used to connect or disconnect load current when the equipment is operating normally, and when the equipment fails or is seriously overloaded, the high-voltage circuit breaker can automatically and quickly cut off the fault current to prevent accidents; high-voltage circuit breakers are mainly composed of conductive circuits, arc extinguishing chambers, casings, insulating supports, operating and transmission mechanisms, etc.

[0003] The high-voltage circuit breaker state monitoring and early warning method in the prior art can only perform state assessment based on the operating value range of its various parameters. However, the numerical characteristics of the operating parameters of the high-voltage circuit breaker in fault warning and fault diagnosis are not the same. In particular, the numerical differences of some parameters are not large whether in a fault state or in a normal operating state. Therefore, how to respectively screen diagnostic parameters and early warning parameters from the operating parameters of the high-voltage circuit breaker for state monitoring and early warning, so as to improve the monitoring and early warning effect of the high-voltage circuit breaker, is a technical problem that needs to be solved urgently in this field.

[0004] In view of the above technical problems, this application proposes a solution. Summary of the invention

[0005] The purpose of the present invention is to provide a high-voltage circuit breaker state monitoring and early warning method based on intelligent learning, which is used to solve the problem that the prior art cannot separately filter diagnostic parameters and early warning parameters from the operating parameters of the high-voltage circuit breaker.

[0006] The technical problem to be solved by the present invention is: how to provide a high-voltage circuit breaker state monitoring and early warning method based on intelligent learning that can respectively filter diagnostic parameters and early warning parameters from the operating parameters of the high-voltage circuit breaker.

[0007] The purpose of the present invention can be achieved through the following technical solutions:

[0008] A high-voltage circuit breaker state monitoring and early warning method based on intelligent learning comprises the following steps:

[0009] Step 1: Analyze the types of historical faults of high-voltage circuit breakers: generate an analysis cycle, obtain all historical fault data of the high-voltage circuit breaker within the analysis cycle, the historical fault data includes the fault type and the fault parameter group, the fault parameter group includes the closing current, closing time, opening time, rated current and rated voltage of the high-voltage circuit breaker at the time of the fault, and mark the parameter type in the fault parameter group as an explicit parameter or an implicit parameter;

[0010] Step 2: Perform parameter correlation analysis on the fault type of the high-voltage circuit breaker and mark the explicit parameters as key parameters of the fault type;

[0011] Step 3: Perform data cleaning on key parameters of each fault type of high-voltage circuit breaker;

[0012] Step 4: Analyze the fault characteristics of the high-voltage circuit breaker: form a feature set from the key parameters of all fault types, mark the ratio of the number of elements corresponding to the same key parameter in the feature set to the total number of all elements in the feature set as the feature coefficient of the key parameter, and compare the feature coefficient of the key parameter with the preset feature threshold: if the feature coefficient is less than the feature threshold, mark the corresponding key parameter as a diagnostic parameter; if the feature coefficient is greater than or equal to the feature threshold, mark the corresponding key parameter as a depth parameter;

[0013] Step 5: Perform range analysis on the depth parameters and construct a monitoring and early warning data set, and send the monitoring and early warning data set to the database for storage.

[0014] Furthermore, in step one, the specific process of marking the parameter type as an explicit parameter or an implicit parameter includes: forming a parameter set of the fault type from all fault parameter groups corresponding to the same fault type, forming a subset of the parameter type in the parameter set from fault parameters of the same type in the parameter set, performing variance calculation on the subset of the parameter type to obtain an explicit value of the parameter type relative to the fault type, and comparing the explicit value with the explicit threshold: if the explicit value is less than the explicit threshold, marking the parameter type as an explicit parameter of the fault type; if the explicit value is greater than or equal to the explicit threshold, marking the parameter type as an implicit parameter of the fault type.

[0015] Furthermore, in step 2, the specific process of marking the explicit parameter as the key parameter of the fault type includes: obtaining the normal operating value range of the high-voltage circuit breaker in the explicit parameter, marking the average value of the maximum value and the minimum value of the normal operating value range as the standard measurement value of the explicit parameter, summing up all elements of the corresponding subset of the explicit parameter and taking the average value to obtain the standard verification value of the explicit parameter, marking the absolute value of the difference between the standard verification value and the standard measurement value as the relevant value of the explicit parameter, and comparing the relevant value of the explicit parameter with a preset relevant threshold: if the relevant value is less than the relevant threshold, the explicit parameter is marked as an irrelevant parameter of the fault type; if the relevant value is greater than or equal to the relevant threshold, the explicit parameter is marked as a key parameter of the fault type.

[0016] Furthermore, in step three, the specific process of data cleaning of key parameters of each fault type of the high-voltage circuit breaker includes: comparing the explicit value of the subset corresponding to the key parameter with the preset cleaning threshold: if the explicit value is less than the cleaning threshold, the data cleaning process ends; if the explicit value is greater than or equal to the explicit threshold, the maximum element and the minimum element in the subset corresponding to the key parameter are eliminated, and then the explicit value of the subset corresponding to the key parameter is recalculated and compared with the cleaning threshold again, and so on, until the explicit value is less than the cleaning threshold.

[0017] Further, in step 5, the specific process of performing range analysis on the depth parameters includes: marking the subset of the depth parameters corresponding to the fault type as the analysis set of the depth parameters, obtaining the overlap data CH and the coverage data FG of the depth parameter analysis set; The warning coefficient YJ of the depth parameter is obtained, where a1 and a2 are both proportional coefficients, and a1>a2>1, and TZ is the characteristic coefficient of the depth parameter; the warning coefficient YJ of the depth parameter is compared with the preset warning threshold YJmax: if the warning coefficient YJ is less than the warning threshold YJmax, the corresponding depth parameter is marked as a diagnostic parameter; if the warning coefficient YJ is greater than or equal to the warning threshold YJmax, the corresponding depth parameter is marked as a warning parameter.

[0018] Furthermore, the process of obtaining the overlapping data CH includes: marking the intersection of all subsets in the depth parameter analysis set as the overlapping set, and marking the difference between the maximum element and the minimum element in the overlapping set as the overlapping data CH; the process of obtaining the coverage data FG includes: marking the union of all subsets in the depth parameter analysis set as the coverage set, and marking the difference between the maximum element and the minimum element in the coverage set as the coverage data FG.

[0019] Furthermore, the construction process of the monitoring and early warning data set includes: the warning range of the warning parameter is constituted by the maximum element and the minimum element of the warning parameter coverage set, the diagnostic range of the diagnostic parameter relative to the fault type is marked by the maximum element and the minimum element of the subset corresponding to the diagnostic parameter and the fault type, and the monitoring and early warning data set is constituted by the warning range of all warning parameters and the diagnostic range of the diagnostic parameter relative to the fault type.

[0020] Further, it is applied to a high-voltage circuit breaker state monitoring and early warning system based on intelligent learning, and the high-voltage circuit breaker state monitoring and early warning system based on intelligent learning includes a type analysis module, a correlation analysis module, a data cleaning module, a feature analysis module, a depth analysis module and a storage module; the type analysis module, the correlation analysis module, the data cleaning module, the feature analysis module, the depth analysis module and the storage module are sequentially connected in communication;

[0021] The type analysis module is used to perform type analysis on historical faults of the high-voltage circuit breaker and mark the parameter type as an explicit parameter or an implicit parameter of the fault type;

[0022] The correlation analysis module is used to perform parameter correlation analysis on the fault type of the high-voltage circuit breaker and mark the explicit parameters as irrelevant parameters or key parameters of the fault type;

[0023] The data cleaning module is used to clean the key parameters of each fault type of the high-voltage circuit breaker;

[0024] The feature analysis module is used to analyze the fault features of the high-voltage circuit breaker and mark key parameters as diagnostic parameters or depth parameters;

[0025] The depth analysis module is used to perform range analysis on the depth parameters and construct a monitoring and early warning data set, and send the monitoring and early warning data set to the storage module for storage.

[0026] The present invention has the following beneficial effects:

[0027] The historical faults of high-voltage circuit breakers are analyzed by type, and explicit parameters and implicit parameters are extracted according to the fault types and parameter types in the historical fault data. The explicit parameters are parameters whose values ​​have certain characteristics under the fault state, and the displayed values ​​under the fault state are less random, indicating that the values ​​of the explicit parameters have certain rules under the fault state. Therefore, the extraction of explicit parameters provides data support for related analysis;

[0028] Perform parameter correlation analysis on the fault types of high-voltage circuit breakers, and mark explicit parameters as key parameters and irrelevant parameters according to the relevant values. Key parameters indicate that there is a large difference between the values ​​of explicit parameters in the fault state and the normal operation state, that is, the operating status feedback and early warning analysis of high-voltage circuit breakers can be performed through key parameter monitoring;

[0029] The fault characteristics of high-voltage circuit breakers are analyzed, and a feature set is constructed. Then, the proportion of the number of elements corresponding to the key parameters in the feature set is analyzed to obtain the characteristic coefficient. The diagnostic attribute and warning attribute of the key parameters are determined by combining the characteristic coefficient and the warning coefficient. Finally, the diagnostic range of the diagnostic parameters and the warning range of the warning parameters are extracted respectively, and a monitoring and warning data set is constructed. Numerical feature extraction is used to provide a monitoring and warning measurement basis for high-voltage circuit breakers, thereby improving the state monitoring effect and fault diagnosis efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. 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 paying creative work.

[0031] Figure 1 This is a flow chart of a method according to Embodiment 1 of the present invention;

[0032] Figure 2 This is a system block diagram of Embodiment 2 of the present invention. DETAILED DESCRIPTION

[0033] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. Embodiment 1

[0034] like Figure 1 As shown, a high-voltage circuit breaker state monitoring and early warning method based on intelligent learning includes the following steps:

[0035] Step 1: Perform type analysis on historical faults of high-voltage circuit breakers: Generate an analysis cycle, obtain all historical fault data of high-voltage circuit breakers within the analysis cycle, the historical fault data includes fault type and fault parameter group, the fault parameter group includes closing current, closing time, opening time, rated current and rated voltage of the high-voltage circuit breaker during the fault, all fault parameter groups corresponding to the same fault type constitute a parameter set of the fault type, the fault parameters of the same type in the parameter set constitute a subset of the parameter type in the parameter set, and perform variance calculation on the subset of the parameter type to obtain the parameter type relative to the fault type The explicit value of the fault type is compared with the explicit threshold: if the explicit value is less than the explicit threshold, the parameter type is marked as the explicit parameter of the fault type; if the explicit value is greater than or equal to the explicit threshold, the parameter type is marked as the implicit parameter of the fault type; according to the fault type and parameter type in the historical fault data, explicit parameters and implicit parameters are extracted. The explicit parameter is a parameter with certain characteristics in the fault state, and the displayed value in the fault state is less random, indicating that the value of the explicit parameter has a certain regularity in the fault state. Therefore, the extraction of explicit parameters provides data support for related analysis;

[0036] Step 2: Perform parameter correlation analysis on the fault type of the high-voltage circuit breaker: obtain the normal operating value range of the high-voltage circuit breaker in the explicit parameters, mark the average value of the maximum value and the minimum value of the normal operating value range as the standard measurement value of the explicit parameter, sum and average all elements of the corresponding subset of the explicit parameter to obtain the standard verification value of the explicit parameter, mark the absolute value of the difference between the standard verification value and the standard measurement value as the correlation value of the explicit parameter, and compare the correlation value of the explicit parameter with the preset correlation threshold: if the correlation value is less than the correlation threshold, the explicit parameter is marked as an irrelevant parameter of the fault type; if the correlation value is greater than or equal to the relevant threshold, the explicit parameter is marked as a key parameter of the fault type; according to the correlation value, the explicit parameter is marked as a key parameter and an irrelevant parameter, and the key parameter indicates that there is a large difference between the value of the explicit parameter in the fault state and the normal operating state, that is, the operating status feedback and early warning analysis of the high-voltage circuit breaker can be performed through key parameter monitoring;

[0037] Step 3: Data cleaning of key parameters of each fault type of high-voltage circuit breaker: compare the explicit value of the subset corresponding to the key parameter with the preset cleaning threshold: if the explicit value is less than the cleaning threshold, the data cleaning process ends; if the explicit value is greater than or equal to the explicit threshold, the maximum element and the minimum element in the subset corresponding to the key parameter are removed, and then the explicit value of the subset corresponding to the key parameter is recalculated and compared with the cleaning threshold again, and so on, until the explicit value is less than the cleaning threshold;

[0038] Step 4: Analyze the fault characteristics of the high-voltage circuit breaker: construct a feature set from the key parameters of all fault types, mark the ratio of the number of elements corresponding to the same key parameter in the feature set to the total number of all elements in the feature set as the feature coefficient of the key parameter, and compare the feature coefficient of the key parameter with the preset feature threshold: if the feature coefficient is less than the feature threshold, the corresponding key parameter is marked as a diagnostic parameter; if the feature coefficient is greater than or equal to the feature threshold, the corresponding key parameter is marked as a depth parameter; construct the feature set, and then analyze the proportion of the number of elements corresponding to the key parameters in the feature set to obtain the feature coefficient, combine the feature coefficient and the warning coefficient to determine the diagnostic attribute and warning attribute of the key parameter, and finally extract the diagnostic range of the diagnostic parameter and the warning range of the warning parameter respectively, and construct a monitoring and warning data set, and provide a monitoring and warning measurement basis for the high-voltage circuit breaker by extracting numerical features, thereby improving the state monitoring effect and fault diagnosis efficiency;

[0039] Step 5: Perform range analysis on the depth parameters: mark the subset of the fault type corresponding to the depth parameters as the analysis set of the depth parameters, obtain the coincidence data CH and the coverage data FG of the depth parameter analysis set, and the process of obtaining the coincidence data CH includes: marking the intersection of all subsets in the depth parameter analysis set as the coincidence set, and marking the difference between the maximum element and the minimum element in the coincidence set as the coincidence data CH; the process of obtaining the coverage data FG includes: marking the union of all subsets in the depth parameter analysis set as the coverage set, and marking the difference between the maximum element and the minimum element in the coverage set as the coverage data FG; through the formula The warning coefficient YJ of the depth parameter is obtained, where a1 and a2 are both proportional coefficients, and a1>a2>1, and TZ is the characteristic coefficient of the depth parameter; the warning coefficient YJ of the depth parameter is compared with the preset warning threshold YJmax: if the warning coefficient YJ is less than the warning threshold YJmax, the corresponding depth parameter is marked as a diagnostic parameter; if the warning coefficient YJ is greater than or equal to the warning threshold YJmax, the corresponding depth parameter is marked as a warning parameter; the warning range of the warning parameter is composed of the maximum element and the minimum element of the warning parameter coverage set, the diagnostic range of the diagnostic parameter relative to the fault type is marked by the maximum element and the minimum element of the subset corresponding to the diagnostic parameter and the fault type, the warning range of all warning parameters and the diagnostic range of the diagnostic parameter relative to the fault type constitute a monitoring warning data set, and the monitoring warning data set is sent to the database for storage. Embodiment 2

[0040] like Figure 2As shown, a high-voltage circuit breaker state monitoring and early warning system based on intelligent learning includes a type analysis module, a correlation analysis module, a data cleaning module, a feature analysis module, a depth analysis module and a storage module; the type analysis module, the correlation analysis module, the data cleaning module, the feature analysis module, the depth analysis module and the storage module are communicatively connected in sequence.

[0041] The type analysis module is used to perform type analysis on historical faults of the high-voltage circuit breaker and mark the parameter type as an explicit parameter or an implicit parameter of the fault type;

[0042] The correlation analysis module is used to perform parameter correlation analysis on the fault type of the high-voltage circuit breaker and mark the explicit parameters as irrelevant parameters or key parameters of the fault type;

[0043] The data cleaning module is used to clean the key parameters of each fault type of the high-voltage circuit breaker;

[0044] The feature analysis module is used to analyze the fault features of the high-voltage circuit breaker and mark key parameters as diagnostic parameters or depth parameters;

[0045] The depth analysis module is used to perform range analysis on the depth parameters and construct a monitoring and early warning data set, and send the monitoring and early warning data set to the storage module for storage.

[0046] A high-voltage circuit breaker state monitoring and early warning method based on intelligent learning generates an analysis cycle during operation, obtains all historical fault data of the high-voltage circuit breaker within the analysis cycle, the historical fault data includes fault types and fault parameter groups, extracts explicit parameters in the parameter types in the fault parameter groups, performs parameter correlation analysis on the fault types of the high-voltage circuit breaker and marks key parameters, then analyzes the fault characteristics of the high-voltage circuit breaker and performs range analysis on the depth parameters to obtain early warning parameters and diagnostic parameters, and a monitoring and early warning data set is formed by the early warning ranges of all early warning parameters and the diagnostic ranges of the diagnostic parameters relative to the fault types.

[0047] The above contents are merely examples and explanations of the structure of the present invention. The technicians in this technical field may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the structure of the invention or exceed the scope defined by the claims, they should all fall within the protection scope of the present invention.

[0048] The above formulas are obtained by collecting a large amount of data and performing software simulation to select a formula close to the actual value. The coefficients in the formula are set by technicians in this field according to actual conditions; for example: Formula ; A technician in this field collects multiple groups of sample data and sets a corresponding warning coefficient for each group of sample data; substitutes the set warning coefficient and the collected sample data into the formula, any two formulas constitute a binary linear equation system, the calculated coefficients are screened and averaged, and the values ​​of a1 and a2 are obtained to be 4.28 and 2.15 respectively;

[0049] The size of the coefficient is to quantify each parameter to obtain a specific value for subsequent comparison. The size of the coefficient depends on the amount of sample data and the preliminary setting of the corresponding warning coefficient for each group of sample data by technical personnel in this field; as long as it does not affect the proportional relationship between the parameter and the quantified value, such as the warning coefficient is proportional to the value of the overlapping data.

[0050] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0051] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A high-voltage circuit breaker state monitoring and early warning method based on intelligent learning, characterized in that: The following steps are involved: Step 1: Analyze the types of historical faults of high-voltage circuit breakers: generate an analysis cycle, obtain all historical fault data of the high-voltage circuit breaker within the analysis cycle, the historical fault data includes the fault type and the fault parameter group, the fault parameter group includes the closing current, closing time, opening time, rated current and rated voltage of the high-voltage circuit breaker at the time of the fault, and mark the parameter type in the fault parameter group as an explicit parameter or an implicit parameter; Step 2: Perform parameter correlation analysis on the fault type of the high-voltage circuit breaker and mark the explicit parameters as key parameters of the fault type; Step 3: Perform data cleaning on key parameters of each fault type of high-voltage circuit breaker; Step 4: Analyze the fault characteristics of the high-voltage circuit breaker: form a feature set from the key parameters of all fault types, mark the ratio of the number of elements corresponding to the same key parameter in the feature set to the total number of all elements in the feature set as the feature coefficient of the key parameter, and compare the feature coefficient of the key parameter with a preset feature threshold: if the feature coefficient is less than the feature threshold, mark the corresponding key parameter as a diagnostic parameter; If the feature coefficient is greater than or equal to the feature threshold, the corresponding key parameter is marked as a depth parameter; Step 5: Perform range analysis on the depth parameters and construct a monitoring and early warning data set, and send the monitoring and early warning data set to the database for storage.

2. A high-voltage circuit breaker state monitoring and early warning method based on intelligent learning according to claim 1, characterized in that: In step one, the specific process of marking the parameter type as an explicit parameter or an implicit parameter includes: forming a parameter set of the fault type from all fault parameter groups corresponding to the same fault type, forming a subset of the parameter type in the parameter set from fault parameters of the same type in the parameter set, performing variance calculation on the subset of the parameter type to obtain an explicit value of the parameter type relative to the fault type, and comparing the explicit value with the explicit threshold: if the explicit value is less than the explicit threshold, marking the parameter type as an explicit parameter of the fault type; if the explicit value is greater than or equal to the explicit threshold, marking the parameter type as an implicit parameter of the fault type.

3. A high-voltage circuit breaker state monitoring and early warning method based on intelligent learning according to claim 2, characterized in that: In step 2, the specific process of marking the explicit parameter as the key parameter of the fault type includes: obtaining the normal operating value range of the high-voltage circuit breaker in the explicit parameter, marking the average value of the maximum value and the minimum value of the normal operating value range as the standard measurement value of the explicit parameter, summing up all elements of the corresponding subset of the explicit parameter and taking the average value to obtain the standard verification value of the explicit parameter, marking the absolute value of the difference between the standard verification value and the standard measurement value as the relevant value of the explicit parameter, and comparing the relevant value of the explicit parameter with a preset relevant threshold: if the relevant value is less than the relevant threshold, the explicit parameter is marked as an irrelevant parameter of the fault type; if the relevant value is greater than or equal to the relevant threshold, the explicit parameter is marked as a key parameter of the fault type.

4. A high-voltage circuit breaker state monitoring and early warning method based on intelligent learning according to claim 3, characterized in that: In step three, the specific process of data cleaning of key parameters of each fault type of the high-voltage circuit breaker includes: comparing the explicit value of the subset corresponding to the key parameter with the preset cleaning threshold: if the explicit value is less than the cleaning threshold, the data cleaning process ends; if the explicit value is greater than or equal to the explicit threshold, the maximum element and the minimum element in the subset corresponding to the key parameter are eliminated, and then the explicit value of the subset corresponding to the key parameter is recalculated and compared with the cleaning threshold again, and so on, until the explicit value is less than the cleaning threshold.

5. A high-voltage circuit breaker state monitoring and early warning method based on intelligent learning according to claim 4, characterized in that: In step 5, the specific process of performing range analysis on the depth parameters includes: marking the subset of the depth parameters corresponding to the fault type as the analysis set of the depth parameters, obtaining the overlap data CH and coverage data FG of the depth parameter analysis set; using the formula The warning coefficient YJ of the depth parameter is obtained, where a1 and a2 are both proportional coefficients, and a1>a2>1, and TZ is the characteristic coefficient of the depth parameter; the warning coefficient YJ of the depth parameter is compared with the preset warning threshold YJmax: if the warning coefficient YJ is less than the warning threshold YJmax, the corresponding depth parameter is marked as a diagnostic parameter; if the warning coefficient YJ is greater than or equal to the warning threshold YJmax, the corresponding depth parameter is marked as a warning parameter.

6. A high-voltage circuit breaker state monitoring and early warning method based on intelligent learning according to claim 5, characterized in that: The process of obtaining the overlapping data CH includes: marking the intersection of all subsets in the depth parameter analysis set as the overlapping set, and marking the difference between the maximum element and the minimum element in the overlapping set as the overlapping data CH; the process of obtaining the covering data FG includes: marking the union of all subsets in the depth parameter analysis set as the covering set, and marking the difference between the maximum element and the minimum element in the covering set as the covering data FG.

7. A high-voltage circuit breaker state monitoring and early warning method based on intelligent learning according to claim 6, characterized in that: The construction process of the monitoring and early warning data set includes: the warning range of the warning parameter is formed by the maximum element and the minimum element of the warning parameter coverage set, the diagnostic range of the diagnostic parameter relative to the fault type is marked by the maximum element and the minimum element of the subset corresponding to the diagnostic parameter and the fault type, and the monitoring and early warning data set is formed by the warning range of all warning parameters and the diagnostic range of the diagnostic parameter relative to the fault type.

8. A high-voltage circuit breaker state monitoring and early warning method based on intelligent learning according to any one of claims 1 to 7, characterized in that: Applied to a high-voltage circuit breaker state monitoring and early warning system based on intelligent learning, the high-voltage circuit breaker state monitoring and early warning system based on intelligent learning includes a type analysis module, a correlation analysis module, a data cleaning module, a feature analysis module, a depth analysis module and a storage module; the type analysis module, the correlation analysis module, the data cleaning module, the feature analysis module, the depth analysis module and the storage module are sequentially connected in communication; The type analysis module is used to perform type analysis on historical faults of the high-voltage circuit breaker and mark the parameter type as an explicit parameter or an implicit parameter of the fault type; The correlation analysis module is used to perform parameter correlation analysis on the fault type of the high-voltage circuit breaker and mark the explicit parameters as irrelevant parameters or key parameters of the fault type; The data cleaning module is used to clean the key parameters of each fault type of the high-voltage circuit breaker; The feature analysis module is used to analyze the fault features of the high-voltage circuit breaker and mark key parameters as diagnostic parameters or depth parameters; The depth analysis module is used to perform range analysis on the depth parameters and construct a monitoring and early warning data set, and send the monitoring and early warning data set to the storage module for storage.

Images