Intelligent switch maintenance method, system, storage medium and electronic device

Abstract

A maintenance method, system, storage medium and electronic device for an intelligent switch, the method comprising: constructing a rough set based on historical data and real-time data of the intelligent switch and a preset intelligent decision table; determining the minimum reduction according to the rough set; determining the value range of each parameter of the intelligent switch when the intelligent switch is in a fault state based on the minimum reduction, and determining the current fault state of the intelligent switch. The maintenance method for an intelligent switch provided by the embodiment of the present invention can accurately determine whether the intelligent switch is currently in a fault state based on incomplete, uncertain and inaccurate data detected by the intelligent switch, and further can accurately determine whether the intelligent switch is in a fault state when the data obtained in real time by the intelligent switch is inaccurate, uncertain and incomplete. When the intelligent switch is in a fault state, the technicians can carry out targeted maintenance to ensure the safe and smooth operation of the power grid.

Description

Technical Field

[0001] The present invention relates to the field of power grid control technology, and in particular to an intelligent switch maintenance method, system, storage medium and electronic equipment. Background Art

[0002] Smart switches are power distribution switches that control smart distribution networks. If the smart switch is turned off, the power distribution of the corresponding line will be turned off. Therefore, smart switches are key equipment for controlling power supply in the distribution network area. If the smart switch is broken, it will cause power outages in the relevant local power grid and requires timely maintenance. Therefore, it is necessary to detect smart switches in a timely manner to avoid sudden failures of smart switches and power outages.

[0003] Since the voltage data, current data, fault data of smart switches in the power grid and the temperature data and humidity data of the environment in which they are located may be inaccurate, uncertain and incomplete, these factors affect the correctness of the maintenance decision of the smart switches. Therefore, the maintenance decision problem of smart switches under the conditions of inaccurate, uncertain and incomplete data has always been a difficult point. Summary of the invention

[0004] (I) Purpose of the invention

[0005] The purpose of the present invention is to provide a maintenance method and system for an intelligent switch, which constructs a rough set through historical data, real-time data and a preset intelligent decision table of the intelligent switch, and determines the minimum reduction according to the rough set, determines the value range of each parameter of the intelligent switch when the intelligent switch is in a fault state according to the minimum reduction, and determines whether the intelligent switch is currently in a fault state, and further enables accurate determination of whether the intelligent switch is in a fault state when the data obtained in real time by the intelligent switch is inaccurate, uncertain and incomplete, thereby improving the detection efficiency of the intelligent switch.

[0006] (II) Technical solution

[0007] To solve the above problems, a first aspect of the present invention provides a maintenance method for an intelligent switch, comprising: constructing a rough set based on historical data and real-time data of the intelligent switch and a preset intelligent decision table; each piece of the historical data includes one or more parameters of the temperature, humidity, voltage, current, fault state, and fault cause of the intelligent switch at the same time point; determining a minimum reduction according to the rough set; determining the value range of each parameter of the intelligent switch when the intelligent switch is in a fault state based on the minimum reduction, and determining whether the intelligent switch is currently in a fault state.

[0008] Preferably, the rough set includes a condition attribute set and a decision attribute set; the condition attribute set is a set of fault states of the intelligent switches; the fault state of each of the intelligent switches includes one or more parameters in the temperature set, humidity set, voltage set, current set, and fault state of the intelligent switch, and parameters of the same type constitute a set; the decision attribute set includes multiple decision attribute values, each state in the fault state set corresponds to a decision attribute value, and the decision attribute value is used to determine whether the intelligent switch needs maintenance.

[0009] Preferably, the construction of a rough set based on the historical data and real-time data of the intelligent switch and a preset intelligent decision table includes: constructing an initial rough set based on the historical data and real-time data of the intelligent switch and a preset intelligent decision table; the fault state of each intelligent switch in the condition attribute set of the initial rough set and the parameter corresponding to the fault state are taken as one piece of data; wherein the preset intelligent decision table includes multiple parameters of the intelligent switch and the corresponding state of the intelligent switch when each parameter is in multiple numerical ranges, and the maintenance decision value corresponding to the state; deleting multiple pieces of data with the same parameters in the condition attribute set in the initial rough set into one piece of data; deleting parameters in each data in the condition attribute set that are inconsistent with the data type contained in the intelligent decision table to obtain the condition attribute set; the real-time data of the intelligent switch includes: the current voltage value and current value of the intelligent switch, the temperature of the environment described by the intelligent switch, and the humidity of the environment where the intelligent switch is located.

[0010] Preferably, determining the minimum reduction based on the rough set includes: determining the classification quality of the conditional attribute set in the rough set; the classification quality is the ratio of the number of correctly classified elements in the conditional attribute set to the total number of all elements; and determining the minimum reduction based on the classification quality.

[0011] Preferably, the classification quality is obtained by the following method:

[0012]

[0013] Wherein, K is the intelligent switch maintenance knowledge set, the intelligent switch maintenance knowledge set is composed of intelligent switch fault judgment rules, and the intelligent switch judgment rules are generated by the condition attribute set clustering corresponding to the historical data of the intelligent switch and its corresponding decision attribute set; | apr K| represents the lower approximate cardinality of the intelligent switch maintenance knowledge set K with respect to the condition attribute set C; U represents the set of all elements; |U| represents the cardinality of the set of all elements. apr K represents the lower approximation of the intelligent switch maintenance knowledge set K with respect to the condition attribute set C; γ c (K) is the classification quality.

[0014] According to a second aspect of the present invention, a maintenance system for an intelligent switch is provided, comprising a client and a server; the client is used to obtain historical data and real-time data of the intelligent switch; the server comprises a rough set construction module, a minimum reduction determination module and a calculation module; the rough set construction module is used to construct a rough set based on the historical data and the real-time data of the switch and a preset intelligent decision table; each piece of the historical data comprises one or more parameters of the temperature, humidity, voltage, current, fault state, and cause of the fault of the intelligent switch at the same time point; the minimum reduction determination module is used to determine the minimum reduction according to the rough set; the calculation module is used to determine the value range of each parameter of the intelligent switch when the intelligent switch is in a fault state based on the minimum reduction, and determine whether the intelligent switch is currently in a fault state.

[0015] Preferably, the rough set includes a condition attribute set and a decision attribute set; the condition attribute set is a set of fault states of the intelligent switches; the fault state of each of the intelligent switches includes one or more parameters in the temperature set, humidity set, voltage set, current set, and fault state of the intelligent switch, and parameters of the same type constitute a set; the decision attribute set includes multiple decision attribute values, each state in the fault state set corresponds to a decision attribute value, and the decision attribute value is used to determine whether the intelligent switch needs maintenance.

[0016] Preferably, the rough set construction module is used to construct an initial rough set based on the historical data and real-time data of the intelligent switch and a preset intelligent decision table; the fault state of each intelligent switch and the parameter corresponding to the fault state in the condition attribute set of the initial rough set are taken as one piece of data; wherein the preset intelligent decision table includes multiple parameters of the intelligent switch and the corresponding state of the intelligent switch when each parameter is in multiple numerical ranges, and the maintenance decision value corresponding to the state; multiple pieces of data with the same parameters in the condition attribute set in the initial rough set are deleted into one piece of data; the parameters inconsistent with the data type included in the intelligent decision table are deleted from each data in the condition attribute set to obtain the condition attribute set; the real-time data of the intelligent switch include: the current voltage value and current value of the intelligent switch, the temperature of the environment described by the intelligent switch, and the humidity of the environment where the intelligent switch is located.

[0017] Preferably, it also includes a conditional attribute set determination module, which is used to determine the classification quality of the conditional attribute set in the rough set; the classification quality is the ratio of the number of correctly classified elements in the conditional attribute set to the total number of all elements; the minimum reduction is determined according to the classification quality.

[0018] Preferably, the classification quality is obtained by the following method:

[0019]

[0020] Wherein, K is the intelligent switch maintenance knowledge set, the intelligent switch maintenance knowledge set is composed of intelligent switch fault judgment rules, and the intelligent switch judgment rules are generated by the condition attribute set clustering corresponding to the historical data of the intelligent switch and its corresponding decision attribute set; | apr K| represents the lower approximate cardinality of the intelligent switch maintenance knowledge set K with respect to the condition attribute set C; U represents the set of all elements; |U| represents the cardinality of the set of all elements. apr K represents the lower approximation of the intelligent switch maintenance knowledge set K with respect to the condition attribute set C; γ c (K) is the classification quality.

[0021] According to a third aspect of the present invention, a storage medium is provided, the storage medium including a stored computer program, wherein when the computer program is executed, a device where the storage medium is located is controlled to execute the method described in the first aspect.

[0022] According to a fourth aspect of the present invention, an electronic device is provided, the device comprising a storage medium and one or more processors, the storage medium is coupled to the processor, the processor is configured to execute program instructions stored in the storage medium; when the program instructions are executed, the method of the first aspect is executed.

[0023] (III) Beneficial effects

[0024] The above technical solution of the present invention has the following beneficial technical effects:

[0025] The method and system provided by the embodiment of the present invention construct a rough set through historical data and real-time data of an intelligent switch and a preset intelligent decision table, and determine the minimum reduction according to the rough set, determine the value range of each parameter of the intelligent switch when the intelligent switch is in a fault state according to the minimum reduction, and determine whether the intelligent switch is currently in a fault state, and further enable the fault state of the intelligent switch to be determined when the data obtained in real time by the intelligent switch is inaccurate, uncertain and incomplete, so that the technicians can timely repair the faulty power grid in a targeted manner to maintain the safe and smooth operation of the power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 It is a flow chart of a rough set method for intelligent decision-making for intelligent switch maintenance according to the first embodiment of the present invention;

[0027] Figure 2This is a flow chart of a rough set reduction algorithm for intelligent decision-making for intelligent switch maintenance in the first embodiment of the present invention;

[0028] Figure 3 It is a structural diagram of a rough set information system for intelligent switch maintenance intelligent decision-making according to the second embodiment of the present invention. DETAILED DESCRIPTION

[0029] In order to make the purpose, technical scheme and advantages of the present invention clearer, the present invention is further described in detail below in conjunction with specific embodiments and with reference to the accompanying drawings. It should be understood that these descriptions are only exemplary and are not intended to limit the scope of the present invention. In addition, in the following description, the description of well-known structures and technologies is omitted to avoid unnecessary confusion of the concept of the present invention.

[0030] In addition, the technical features involved in the different embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0031] Figure 1 It is a flow chart of the rough set method for intelligent decision-making for intelligent switch maintenance according to the first embodiment of the present invention.

[0032] like Figure 1 As shown, a maintenance method of an intelligent switch includes: Step S101-Step S103:

[0033] Step S101: construct a rough set based on historical data and real-time data of the intelligent switch and a preset intelligent decision table.

[0034] Among them, the rough set includes condition attribute set and decision attribute set.

[0035] The condition attribute set is a set of fault states of the smart switches; the fault state of each smart switch includes one or more parameters of the temperature set, humidity set, voltage set, current set, and fault state of the smart switch, and parameters of the same type constitute a set. The fault state includes the presence of a fault, the absence of a fault state, and the presence of a fault risk.

[0036] For example, a piece of historical data of the smart switch is January 1, 2020, the temperature of the smart switch is the first temperature, the humidity is the first humidity, the voltage is the first voltage, the current is the first current, the fault state is faulted, and the fault cause is overload. For another example, the historical data of the smart switch can also be January 2, 2020, the humidity of the smart switch is the second humidity, the voltage is the second voltage, and the fault state is not faulted. For another example, the historical data of the smart switch can also be January 3, 2020, the temperature of the smart switch is the third temperature, the humidity is the third humidity, the fault state is that there is a hidden fault, and the cause of the hidden fault is that the power grid corresponding to the smart switch has equipment damage.

[0037] In some embodiments, the smart switch is embedded with multiple sensors, and the embedded sensors detect the voltage, current, temperature, humidity and other data of the smart switch. The smart switch can judge the state of the power grid based on the above data detected, and disconnect the power grid when the smart switch detects a fault state.

[0038] It should be noted that due to unknown factors such as sensor aging, unstable operating environment of the smart switch, network bandwidth fluctuations, signal interference, sudden accidents, natural disasters, and human damage, the data collected by the sensors embedded in the smart switch may be inaccurate and incomplete. If pure mathematical assumptions are used to eliminate or avoid this uncertainty, the detection effect will be unsatisfactory. Therefore, it is not easy to make an accurate judgment on the fault state of the smart switch. The present application makes full use of the historical data of the smart switch through the rough set theory, effectively analyzes various incomplete information such as inaccurate, inconsistent, and incomplete, and accurately detects the current fault state of the smart switch.

[0039] In some embodiments, the real-time data of the smart switch refers to, for example, at the current time point, the temperature of the smart switch is the second temperature, the humidity is the second humidity, the voltage is the second voltage, the current is the second current, the fault state and one or more of the fault state.

[0040] In some embodiments, the decision attribute set is a set of reasons for the fault state of the intelligent switch, wherein the reason for the fault state of the intelligent switch includes one of a short circuit fault, a fire fault, an overload fault, an aging fault, and no fault in the power grid corresponding to the intelligent switch. Each state in the fault state set corresponds to a decision attribute value, and the decision attribute value is used to determine whether the intelligent switch needs maintenance. For example, if the decision attribute value is no fault, it means that the intelligent switch does not need maintenance, and if the decision attribute value is a short circuit fault, a fire fault, an overload fault, or an aging fault in the power grid corresponding to the intelligent switch, it means that the intelligent switch needs maintenance.

[0041] Table 1 below is a preset intelligent decision table provided by an embodiment:

[0042]

[0043] In one embodiment, the construction of a rough set based on historical data and real-time data of the intelligent switch and a preset intelligent decision table includes:

[0044] Firstly, an initial rough set is constructed based on historical data and real-time data of the intelligent switch and a preset intelligent decision table; the fault state of each intelligent switch and the parameters corresponding to the fault state in the condition attribute set of the initial rough set are taken as one piece of data.

[0045] The preset intelligent decision table includes multiple parameters of the intelligent switch, states of the intelligent switch corresponding to each parameter in multiple numerical ranges, and maintenance decision values ​​corresponding to the states.

[0046] Secondly, multiple pieces of data with the same parameters in the condition attribute set in the initial rough set are deleted to one piece of data, that is, only one piece of the multiple pieces of data with the same parameters is retained.

[0047] Parameters in each data in the conditional attribute set that are inconsistent with the data type included in the intelligent decision table are deleted to obtain a conditional attribute set.

[0048] Step S102: determining the minimum reduction according to the rough set.

[0049] Step S103: determining the value range of each parameter of the intelligent switch when the intelligent switch is in a fault state based on the minimum reduction, and determining the current fault state of the intelligent switch.

[0050] In one embodiment, determining the minimum reduction according to the rough set further includes:

[0051] The classification quality of the conditional attribute set in the rough set is determined; the classification quality is the ratio of the number of correctly classified elements in the conditional attribute set to the total number of all elements.

[0052] A minimum reduction is determined based on the classification quality.

[0053] In some embodiments, the classification quality is obtained by:

[0054]

[0055] Wherein, K is the intelligent switch maintenance knowledge set, the intelligent switch maintenance knowledge set is composed of intelligent switch fault judgment rules, and the intelligent switch judgment rules are generated by the condition attribute set clustering corresponding to the historical data of the intelligent switch and its corresponding decision attribute set; | apr K| represents the lower approximate cardinality of the intelligent switch maintenance knowledge set K with respect to the condition attribute set C; U represents the set of all elements; |U represents the cardinality of the set of all elements, apr K represents the lower approximation of the intelligent switch maintenance knowledge set K with respect to the condition attribute set C; γ c (K) is the classification quality, Indicates the ratio of misclassified elements to the total elements.

[0056] In some embodiments, the classification quality of each condition attribute in the rough set corresponding to all parameters of the real-time data is calculated respectively, and the corresponding condition attribute element with the largest classification quality is confirmed as the minimum reduction.

[0057] It can be understood that the classification quality of the conditional attribute set corresponding to a certain parameter of the real-time data and the element is found. The higher the classification quality, the closer the current element of the corresponding real-time data is to the element of the conditional attribute set. Therefore, the corresponding conditional attribute element with the highest classification quality is confirmed as the minimum simplification.

[0058] For example, if the temperature of the real-time data is 50°C, and the classification quality of the temperature attribute set of the conditional attribute set corresponding to the temperature is calculated, the second element has the highest classification quality. Then the temperature attribute in the minimum reduction is the second element of the temperature attribute set of the conditional attribute set. According to the above method, the elements with the highest classification quality corresponding to other elements of the real-time data are found, and the set of all the elements with the highest classification quality found corresponds to the minimum reduction.

[0059] The method and system provided by the embodiment of the present invention construct a rough set through the historical data and real-time data of the intelligent switch and the preset intelligent decision table, and determine the minimum reduction according to the rough set, determine the value range of each parameter of the intelligent switch when the intelligent switch is in a faulty state according to the minimum reduction, and determine whether the intelligent switch is currently in a faulty state, and further enable the fault state of the intelligent switch to be determined when the data obtained in real time by the intelligent switch is inaccurate, uncertain and incomplete, so that the technicians can timely repair the faulty power grid in a targeted manner to maintain the safe and smooth operation of the power grid. The method can make intelligent decisions on the maintenance of the intelligent switch more accurately, thereby improving the accuracy and intelligence of the maintenance of the intelligent switch and preventing the danger of intelligent switch maintenance loopholes.

[0060] Figure 2 It is a flow chart of a rough set simplification algorithm for intelligent decision-making for intelligent switch maintenance according to the first embodiment of the present invention.

[0061] like Figure 2As shown, the process includes: inputting the condition attribute set C and decision attribute set K of the intelligent decision for maintenance of intelligent switches, wherein the condition attribute set C and decision attribute set K are obtained by constructing a rough set based on the historical data and real-time data of the intelligent switch and the preset intelligent decision table; the reduced set R of the condition attribute set C of the intelligent decision for maintenance of intelligent switches is initialized to an empty set. Then, the set R is assigned to the temporary set T, and any unprocessed element x is taken from the set C and the set R, and it is calculated whether the classification quality is less than the corresponding classification quality of the temporary set. If so, the temporary set T is updated, and the classification quality of the real-time data and the condition attribute set is calculated to be greater than or equal to the decision classification quality. If so, the minimum reduced set is obtained. Among them, γ RU{x} (K) represents the classification quality of the union of the reduced set R and the set {x}, γ T (K) represents the classification quality of the temporary set T, γ R (K) represents the classification quality of the reduced set R, γ C (K) represents the classification quality of the decision condition attribute set C.

[0062] Figure 3 It is a structural diagram of a rough set information system for intelligent switch maintenance intelligent decision-making according to the second embodiment of the present invention.

[0063] like Figure 3 As shown, a maintenance system for an intelligent switch includes a data acquisition module, a rough set construction module, a minimum reduction determination module, and a calculation module.

[0064] The data acquisition module is used to obtain historical data and real-time data of the intelligent switch.

[0065] A rough set construction module is used to construct a rough set based on the historical data of the switch, the real-time data and a preset intelligent decision table; each piece of the historical data includes one or more parameters of the temperature, humidity, voltage, current, fault state and fault cause of the intelligent switch at the same time point.

[0066] A minimum reduction determination module, used for determining a minimum reduction according to the rough set;

[0067] A calculation module is used to determine, based on the minimum reduction, the value range of each parameter of the intelligent switch when the intelligent switch is in a fault state, and determine whether the intelligent switch is currently in a fault state.

[0068] In some embodiments, the rough set includes a condition attribute set and a decision attribute set; the condition attribute set is a set of fault states of the intelligent switch; each fault state of the intelligent switch corresponds to one or more parameters of the temperature, humidity, voltage, current, fault state, and cause of the fault of the intelligent switch, and parameters of the same type constitute a set; the decision attribute set includes multiple decision attribute values, each state in the fault state set corresponds to a decision attribute value, and the decision attribute value is used to determine whether the intelligent switch needs maintenance.

[0069] In some embodiments, a rough set construction module is used to construct an initial rough set based on historical data and real-time data of the intelligent switch and a preset intelligent decision table; the fault state of each of the intelligent switches and the parameters corresponding to the fault state in the condition attribute set of the initial rough set are taken as a piece of data.

[0070] The preset intelligent decision table includes multiple parameters of the intelligent switch and the corresponding states of the intelligent switch when each parameter is in multiple value ranges, and the maintenance decision value corresponding to the state;

[0071] A plurality of data having the same parameters in the condition attribute set in the initial rough set are deleted to one piece of data.

[0072] Parameters inconsistent with the data types included in the intelligent decision table are deleted from each data in the conditional attribute set to obtain the conditional attribute set.

[0073] The real-time data of the smart switch includes: the current voltage value and current value of the smart switch, the temperature of the environment of the smart switch, and the humidity of the environment of the smart switch.

[0074] In some embodiments, the minimum reduction module is used to determine the classification quality of the conditional attribute set in the rough set; the classification quality is the ratio of the number of correctly classified elements in the conditional attribute set to the total number of all elements. The minimum reduction is determined according to the classification quality.

[0075] In some embodiments, the classification quality is obtained by:

[0076]

[0077] Wherein, K is the intelligent switch maintenance knowledge set, the intelligent switch maintenance knowledge set is composed of intelligent switch fault judgment rules, and the intelligent switch judgment rules are generated by the condition attribute set clustering corresponding to the historical data of the intelligent switch and its corresponding decision attribute set; | aprK| represents the lower approximate cardinality of the intelligent switch maintenance knowledge set K with respect to the condition attribute set C; U represents the set of all elements; |U| represents the cardinality of the set of all elements. apr K represents the lower approximation of the intelligent switch maintenance knowledge set K with respect to the condition attribute set C; γ c (K) is the classification quality.

[0078] In a specific embodiment, a maintenance system for an intelligent switch includes an intelligent switch and a server. The intelligent switch is used to obtain historical data and real-time data of the intelligent switch, and send the acquired historical data and real-time data of the intelligent switch to the server. The server includes a rough set construction module, a minimum reduction determination module and a calculation module.

[0079] The rough set construction module is used to construct a rough set based on the historical data of the switch, the real-time data and a preset intelligent decision table; each piece of the historical data includes one or more parameters of the temperature, humidity, voltage, current, fault state and fault cause of the intelligent switch at the same time point.

[0080] The minimum reduction determination module is used to determine the minimum reduction according to the rough set.

[0081] A calculation module is used to determine, based on the minimum reduction, the value range of each parameter of the intelligent switch when the intelligent switch is in a fault state, and determine whether the intelligent switch is currently in a fault state.

[0082] In some embodiments, the intelligent switch maintenance intelligent decision server is the computing basic organization and storage center for intelligent switch maintenance related data collection and intelligent decision-making. It is composed of a high-performance multi-core CPU, a disk array, and a high-performance memory, providing the best CPU resources and memory resources for the rough set information system of intelligent switch maintenance intelligent decision-making.

[0083] Another embodiment of the present invention provides a storage medium, wherein the storage medium includes a stored computer program, wherein when the computer program is executed, the device where the storage medium is located is controlled to execute the method provided in the first embodiment.

[0084] Another embodiment of the present invention provides an electronic device, the device including a storage medium and one or more processors, the storage medium is coupled to the processor, and the processor is configured to execute program instructions stored in the storage medium; when the program instructions are executed, the method provided in the first embodiment is executed.

[0085] It should be understood that the above specific embodiments of the present invention are only used to illustrate or explain the principles of the present invention, and do not constitute a limitation of the present invention. Therefore, any modifications, equivalent substitutions, improvements, etc. made without departing from the spirit and scope of the present invention should be included in the protection scope of the present invention. In addition, the appended claims of the present invention are intended to cover all changes and modifications that fall within the scope and boundaries of the appended claims, or the equivalent forms of such scope and boundaries.

Claims

1. A maintenance method for an intelligent switch, characterized in that: include: A rough set is constructed based on the historical data and real-time data of the intelligent switch and a preset intelligent decision table; each piece of the historical data includes one or more parameters of the temperature, humidity, voltage, current, fault state, and cause of the fault state of the intelligent switch at the same time point; wherein the preset intelligent decision table includes multiple parameters of the intelligent switch and the states of the intelligent switch corresponding to each parameter in multiple value ranges, and the maintenance decision value corresponding to the state; Determining a minimum reduction according to the rough set; Determine, based on the minimum reduction, the value range of each parameter of the intelligent switch when the intelligent switch is in a fault state, and determine the current fault state of the intelligent switch; The step of determining the minimum reduction according to the rough set specifically includes: Determining the classification quality of the condition attribute set in the rough set; the classification quality is the ratio of the number of correctly classified elements in the condition attribute set to the total number of all elements; Determine the minimum reduction according to the classification quality; the rough set includes a condition attribute set and a decision attribute set; The condition attribute set is a set of fault states of the smart switch; each fault state of the smart switch corresponds to one or more parameters of the temperature, humidity, voltage, current, fault state, etc. of the smart switch, and parameters of the same type constitute a set; The decision attribute set is a set of reasons for the fault state of the intelligent switch, and the decision attribute value is used to determine whether the intelligent switch needs to be repaired; The classification quality is obtained by: Wherein, K is the intelligent switch maintenance knowledge set, the intelligent switch maintenance knowledge set is composed of intelligent switch fault judgment rules, and the intelligent switch judgment rules are generated by the condition attribute set clustering corresponding to the historical data of the intelligent switch and its corresponding decision attribute set; | apr K| represents the lower approximate cardinality of the intelligent switch maintenance knowledge set K with respect to the condition attribute set C; U represents the set of all elements; |U| represents the cardinality of the set of all elements. apr K represents the lower approximation of the intelligent switch maintenance knowledge set K with respect to the condition attribute set C; γ c (K) is the classification quality.

2. The intelligent switch maintenance method according to claim 1, characterized in that: Said A rough set is constructed based on the historical data and real-time data of the intelligent switch and the preset intelligent decision table, including: An initial rough set is constructed based on historical data and real-time data of the intelligent switch and a preset intelligent decision table; the fault state of each intelligent switch and the parameter corresponding to the fault state in the condition attribute set of the initial rough set are taken as a piece of data; Deleting multiple pieces of data with the same parameters in the condition attribute set in the initial rough set to one piece of data; Deleting parameters in each data in the conditional attribute set that are inconsistent with the data type included in the intelligent decision table to obtain the conditional attribute set; The real-time data of the smart switch includes: the current voltage value and current value of the smart switch, the temperature of the environment where the smart switch is located, and the humidity of the environment where the smart switch is located.

3. An intelligent switch maintenance system, characterized in that: include: A data acquisition module is used to obtain historical data and real-time data of the intelligent switch; A rough set construction module is used to construct a rough set based on the historical data of the switch, the real-time data and a preset intelligent decision table; each piece of the historical data includes one or more parameters of the temperature, humidity, voltage, current, fault state and fault cause of the intelligent switch at the same time point; wherein the preset intelligent decision table includes multiple parameters of the intelligent switch and the states of the intelligent switch corresponding to each parameter in multiple value ranges, and the maintenance decision value corresponding to the state; the rough set includes a condition attribute set and a decision attribute set; The condition attribute set is a set of fault states of the smart switch; each fault state of the smart switch corresponds to one or more parameters of the temperature, humidity, voltage, current, fault state, etc. of the smart switch, and parameters of the same type constitute a set; The decision attribute set is a set of reasons for the fault state of the intelligent switch, and the decision attribute value is used to determine whether the intelligent switch needs to be repaired; The minimum reduction determination module is used to determine the minimum reduction according to the rough set, including: determining the classification quality of the condition attribute set in the rough set; the classification quality is the ratio of the number of correctly classified elements in the condition attribute set to the total number of all elements; determining the minimum reduction according to the classification quality; the classification quality is obtained by the following method: Wherein, K is the intelligent switch maintenance knowledge set, and the intelligent switch maintenance knowledge set is composed of intelligent switch fault judgment rules, and the intelligent switch judgment rules are generated by the condition attribute set clustering corresponding to the historical data of the intelligent switch and the corresponding decision attribute set; | apr K | represents the lower approximate cardinality of the intelligent switch maintenance knowledge set K with respect to the condition attribute set C; U represents the set of all elements; | U | is represented as the cardinality of the set of all elements, apr K represents the lower approximation of the intelligent switch maintenance knowledge set K with respect to the condition attribute set C; γ c (K) is the classification quality; A calculation module is used to determine, based on the minimum reduction, the value range of each parameter of the intelligent switch when the intelligent switch is in a fault state, and determine whether the intelligent switch is currently in a fault state.

4. The system according to claim 3, characterized in that The rough set construction module is used to construct an initial rough set based on the historical data and real-time data of the intelligent switch and a preset intelligent decision table; The fault state of each of the intelligent switches and the parameters corresponding to the fault state in the condition attribute set of the initial rough set are taken as a piece of data; Deleting multiple pieces of data with the same parameters in the condition attribute set in the initial rough set to one piece of data; Delete parameters in each data of the conditional attribute set that are inconsistent with the data type included in the intelligent decision table to obtain the conditional attribute set; The real-time data of the smart switch includes: the current voltage value and current value of the smart switch, the temperature of the environment where the smart switch is located, and the humidity of the environment where the smart switch is located.

5. A storage medium, characterized in that: The storage medium includes a stored computer program, Wherein, when the computer program is running, the device where the storage medium is located is controlled to execute the method according to any one of claims 1-2.

6. An electronic device, characterized in that: It includes a storage medium and one or more processors, wherein the storage medium is coupled to the processor, and the processor is configured to execute program instructions stored in the storage medium; when the program instructions are executed, the method according to any one of claims 1-2 is executed.

Images