Power grid data intelligent supervision system and method based on Internet of Things

Abstract

The invention discloses a power grid data intelligent supervision system and method based on the Internet of Things, and relates to the technical field of information management. A power equipment operation parameter item set is established, a certain operation state of power equipment is used as a target state before a target fault occurs, and a fault reference value of the target fault is calculated; the method comprises the following steps: acquiring two pieces of power equipment with different operation parameter items, respectively recording the two pieces of power equipment as first target equipment and second target equipment, calculating the weight of each operation parameter item in a historical record of a target fault, calculating the weighted fault rate of each operation parameter item, and when third target equipment is in a target state, calculating the weighted fault rate of each operation parameter item; obtaining the similarity degree of the historical records of the same operation parameter items, and comparing the operation parameter items of the third target equipment with the operation parameter items of the first target equipment and the second target equipment to obtain the association degree between the third target equipment and the first target equipment and the association degree between the third target equipment and the second target equipment; and establishing a state evaluation model of the third target equipment.

Description

Technical Field

[0001] The present invention relates to the technical field of information management, and in particular to an intelligent monitoring system and method for power grid data based on the Internet of Things. Background Art

[0002] As the demand for electricity increases, the power grid is in a stage of continuous development and expansion. The increasing scale of the power grid has a significant impact on the fault detection of power equipment in the power grid system. In order to reduce the workload of power grid maintenance, the existing technology connects power equipment to the Internet of Things system of power grid equipment and remotely manages the power equipment through computer networks.

[0003] In the prior art, a method is usually adopted in which fault records of the power grid system are collected, the operating characteristics of the power equipment related to the fault are extracted, and early warnings are issued for the related faults. In the existing power equipment management system, a management method in which fault data and fault characteristics correspond one to one is often adopted. This method requires recording the power equipment corresponding to each fault, and cannot deal with power equipment without fault records. For example, when a newly added power equipment has an operating characteristic similar to an existing record, it is impossible to determine whether a fault will occur in the power system. Summary of the invention

[0004] The purpose of the present invention is to provide an intelligent monitoring system and method for power grid data based on the Internet of Things to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: a method for intelligent supervision of power grid data based on the Internet of Things: Step S100: In a power system composed of a plurality of power devices, a set of power device operation parameter items is established, a certain fault in the power system is set as a target fault, a certain operation state of the power device before the target fault occurs is set as the target state, and a fault reference value of the target fault is calculated according to the historical records of the operation state; Step S200: obtaining two power devices with different operating parameter items from the power system, respectively recording them as a first target device and a second target device, calculating the weight of each operating parameter item in the first target device and the second target device in the historical records of target faults, and calculating the weighted failure rate of each operating parameter item; Step S300: acquiring a third target device in the power system, where the third target device has at least one same operating parameter item as the first target device and the second target device, and when it is detected that the third target device is in the target state, acquiring the similarity of the historical records of the same operating parameter item between the third target device and the first target device and the second target device; Step S400: By comparing the operating parameter items of the third target device with the operating parameter items of the first target device and the second target device, the degree of association between the third target device and the first target device and the second target device respectively is obtained, and a state assessment model for the third target device is established. The calculation result of the state assessment model is compared with the weighted failure rate of the operating parameter items to generate alarm information.

[0006] Furthermore, step S100 includes: Step S101: Obtain the operating parameters of each power device in the power system, and collect the operating parameters of the power devices into a set W, W (w1, w2, w3, ..., w p ), where set W is a set of operating parameter items of power equipment, w1, w2, w3, ... and w p Respectively represent the operating parameters of the first, second, third, ... and pth power equipment, wherein any one of the power equipment includes at least one device operating parameter in the operating parameter item set; Step S102: Obtain the operation status records of each power device in the time period T1 before the target fault occurs from the management log of the power device, and set a certain abnormal state of the power device as the target state; The target state represents the macroscopic operating state of the power equipment. This state is easy to detect, but it cannot accurately warn of risks in the power system. The condition of a certain device being in the target state is affected by its own operating conditions and will also be disturbed by the outside world. Therefore, when the power equipment is detected to be in the target state, the power system may or may not fail. Step S103: acquiring two electric power devices in the electric power system, which are respectively recorded as a first target device and a second target device, and the first target device and the second target device include different operating parameter items; Step S104: acquiring m1 historical records from the operation status record of the first target device, wherein among the m1 historical records, there are n1 historical records of target faults occurring in the power system within a time period T1 after the first target device appears in the target state; Obtain m2 historical records from the operating status record of the second target device, among which there are n2 historical records of target faults occurring in the power system within a time period T1 after the first target device appears in the target state; Step S105: Calculate the first fault reference value C1, C1=n1 / m1, calculate the second fault reference value C2, C2=n2 / m2, and calculate the comprehensive fault reference value C0, C0=(n1+n2) / (m1+m2).

[0007] Further, step S200 includes: Step S201: Obtain the operating parameter items of the first target device, and collect the operating parameter items of the first target device into a first device item set, which is recorded as D EV1 , obtain the operating parameter items of the second target device, and collect the operating parameter items of the second target device into a second device item set, and the second device item set is recorded as D EV2 ; Step S202: Obtain the total number of operation parameter items in the first equipment item set and the second equipment item set, recorded as g0, and obtain the number of times the kth operation parameter item in the operation parameter item set appears in the first equipment item set, recorded as g 1k , the number of times it appears in the second equipment item set, denoted as g 2k ; Step S203: Calculate the weight γ of the kth operating parameter item k , γ k =(g 1k +g 2k ) / g0, calculate the weighted failure rate R of the kth operating parameter item k , R k =γ k ×C0; The weighted failure rate of the operating parameter item indicates the correlation between the same type of fault in the power grid and the operating parameter item of the power equipment. When a certain operating parameter item appears more frequently in the fault record, the weight of the operating parameter item becomes higher. When the power equipment includes this operating parameter item, the probability of failure increases.

[0008] Furthermore, step S300 includes: Step S301: monitoring the status of the third target device. When the third target device is monitored to be in the target operating state, recording the time point t0, and setting the time period with the end time t0 and the time length T2 as the target time period, wherein T2≥T1; Step S302: Obtain the operating parameter items of the third target device and collect them into a third device item set, the third device item set is recorded as D EV3 , get the first comparison set R EP1 and the second alignment set R EP2 , R EP1 =D EV1 ∩D EV3 , R EP2 =D EV2 ∩D EV3 , using the operating parameter items in the first comparison set as the first comparison parameter items, and using the operating parameter items in the second comparison set as the second comparison parameter items; Step S303: obtaining a historical record of a first comparison parameter item of a first target device in a target time period, drawing a function graph of a value of the first comparison parameter item changing with time, recorded as a first change function, obtaining a historical record of a second comparison parameter item of a second target device in a target time period, drawing a function graph of a value of the second comparison parameter item changing with time, recorded as a second change function; Obtain the historical record of the first comparison parameter item of the third target device in the target time period, draw a function image of the value of the first comparison parameter item changing with time, recorded as a third change function, obtain the historical record of the first comparison parameter item of the first target device in the target time period, draw a function image of the value of the second comparison parameter item changing with time, recorded as a fourth change function; Step S304: obtaining a similarity between the first change function and the third change function as α, and obtaining a similarity between the second change function and the fourth change function as β.

[0009] Furthermore, step S400 includes: Step S401: Calculate the fault risk value of the target operating state and obtain the feature set of the third target device operating parameter item, D EVf =R EP1 ∪R EP2 , where D EVf represents a feature set, obtains the weighted failure rates of various operating parameter items in the feature set, obtains the sum of the weighted failure rates in the feature set, denoted as H, and uses H as the failure risk value of the target operating state; Step S402: Calculate the membership degree F1 of the third target device with respect to the first target device, where F1=N r1 / N v3 , where Nr1 represents the number of running parameter items in the first alignment set, N v3 represents the number of operating parameter items in the third device item set, and calculates the membership F2 of the third device to the second target device, F2=N r2 / N v3 , where N r3 represents the number of run parameter items in the second alignment set; Step S403: Establishing a state assessment model Q of the third target device regarding the target operating state. ;

[0010] and The two parameters compare the correlation between the third target device and the first target device and the second target. This correlation is the correlation between the operating states of the operating data. In order to better infer the state of the third target device, the main reference device and the subordinate reference device of the third target device are distinguished through the two parameters, and the reference degree of the corresponding power device is obtained; Step S404: bring the parameters into the status assessment model, calculate the status assessment parameter q of the third target device, and when q>H, issue a risk warning to the relevant management personnel.

[0011] In order to better implement the above method, a power grid data intelligent supervision system based on the power grid data intelligent supervision method of the Internet of Things is also proposed. The system includes: a fault record management module, a weighted fault rate calculation module, an equipment comparison module and a status evaluation module, wherein the fault record management module is used to obtain the historical operation records of the power equipment and calculate the fault reference value of the target fault, the weighted fault rate calculation module is used to calculate the weighted failure rate of each operating parameter item, the equipment comparison module is used to compare the degree of association between the third target equipment and the first target equipment and the second target equipment, and the status evaluation module is used to perform status evaluation on the third target equipment.

[0012] Furthermore, the fault record management module includes: an electric power equipment management unit, a target state management unit, a historical record management unit and a fault reference value calculation unit, wherein the electric power equipment management unit is used to obtain the operating parameters of the electric power equipment and collect them to obtain a set of electric power equipment operating parameter items, the target state management unit is used to obtain the target state of the electric power equipment, the historical record management unit is used to obtain the historical operating records of the electric power equipment, and the fault reference value calculation unit is used to calculate a first fault reference value, a second fault reference value and a comprehensive fault reference value.

[0013] Furthermore, the weighted failure rate calculation module includes: an operating parameter item management unit, a parameter item set management unit and a weight calculation unit, wherein the operating parameter item management unit is used to manage the operating parameter items of the first target device and the second target device, the parameter item set management unit is used to manage the device item set corresponding to the first target device and the second target device, and the weight calculation unit is used to calculate the weight of the operating parameter item and the weighted failure rate of the operating parameter item.

[0014] Furthermore, the device comparison module includes: a device detection unit, a comparison parameter acquisition unit and a parameter comparison unit, wherein the device detection unit is used to perform status monitoring on the third target device, the comparison parameter acquisition unit is used to obtain a first comparison parameter item and a second comparison parameter item, and the parameter comparison unit is used to compare the similarity of operating parameters between the third target device and the first target device and the second target device.

[0015] Furthermore, the status assessment module includes: a risk management unit, a membership calculation unit, an assessment model management unit and an information reminder unit, wherein the risk management unit is used to obtain a fault risk value, the membership calculation unit is used to calculate the membership of the third target device with the first target device and the second target device, the assessment model management unit is used to manage the status assessment model of the third target device, and the information reminder unit is used to calculate the status assessment parameters of the third target device, and when the alarm conditions are met, a risk warning is issued to relevant managers.

[0016] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: the present invention constructs the operating parameters of the power equipment, the relationship between the equipment status and the power grid fault through the existing fault records of the power equipment, compares the types of the power equipment, and infers the possible risks in the power grid system by detecting the same abnormal state in the absence of abnormal records of the equipment. This is conducive to early warning of the risks of the power grid when the operation records of the power equipment are not updated in time, and on the other hand, it reduces the amount of data collection of the power equipment comparison data in the construction of the power system operation management system. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings: Figure 1 It is a structural schematic diagram of an intelligent monitoring system for power grid data based on the Internet of Things of the present invention; Figure 2 It is a flow chart of an intelligent monitoring method for power grid data based on the Internet of Things of the present invention. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] See also Figure 1 and Figure 2 , the present invention provides a technical solution: Step S100: In a power system composed of a plurality of power devices, a set of power device operation parameter items is established, a certain fault in the power system is set as a target fault, a certain operation state of the power device before the target fault occurs is set as the target state, and a fault reference value of the target fault is calculated according to the historical records of the operation state; Wherein, step S100 includes: Step S101: Obtain the operating parameters of each power device in the power system, and collect the operating parameters of the power devices into a set W, W (w1, w2, w3, ..., w p ), where set W is a set of operating parameter items of power equipment, w1, w2, w3, ... and w p Respectively represent the operating parameters of the first, second, third, ... and pth power equipment, wherein any one of the power equipment includes at least one device operating parameter in the operating parameter item set; Step S102: Obtain the operation status records of each power device in the time period T1 before the target fault occurs from the management log of the power device, and set a certain abnormal state of the power device as the target state; Examples of target conditions that can be used include: the temperature of the power equipment, the vibration of the power equipment, and the humidity in the power equipment environment; Step S103: acquiring two electric power devices in the electric power system, which are respectively recorded as a first target device and a second target device, and the first target device and the second target device include different operating parameter items; Step S104: acquiring m1 historical records from the operation status record of the first target device, wherein among the m1 historical records, there are n1 historical records of target faults occurring in the power system within a time period T1 after the first target device appears in the target state; Obtain m2 historical records from the operating status record of the second target device, among which there are n2 historical records of target faults occurring in the power system within a time period T1 after the first target device appears in the target state; Step S105: Calculate the first fault reference value C1, C1=n1 / m1, calculate the second fault reference value C2, C2=n2 / m2, and calculate the comprehensive fault reference value C0, C0=(n1+n2) / (m1+m2); Step S200: obtaining two power devices with different operating parameter items from the power system, respectively recording them as a first target device and a second target device, calculating the weight of each operating parameter item in the first target device and the second target device in the historical records of target faults, and calculating the weighted failure rate of each operating parameter item; Wherein, step S200 includes: Step S201: Obtain the operating parameter items of the first target device, and collect the operating parameter items of the first target device into a first device item set, which is recorded as D EV1 , obtain the operating parameter items of the second target device, and collect the operating parameter items of the second target device into a second device item set, and the second device item set is recorded as D EV2 ; Step S202: Obtain the total number of operation parameter items in the first equipment item set and the second equipment item set, recorded as g0, and obtain the number of times the kth operation parameter item in the operation parameter item set appears in the first equipment item set, recorded as g 1k , the number of times it appears in the second equipment item set, denoted as g 2k ; Step S203: Calculate the weight γ of the kth operating parameter item k , γ k =(g 1k +g 2k ) / g0, calculate the weighted failure rate R of the kth operating parameter item k , R k =γ k ×C0.

[0020] Step S300: acquiring a third target device in the power system, where the third target device has at least one same operating parameter item as the first target device and the second target device, and when it is detected that the third target device is in the target state, acquiring the similarity of the historical records of the same operating parameter item between the third target device and the first target device and the second target device; Wherein, step S300 includes: Step S301: monitoring the status of the third target device. When the third target device is monitored to be in the target operating state, recording the time point t0, and setting the time period with the end time t0 and the time length T2 as the target time period, wherein T2≥T1; Step S302: Obtain the operating parameter items of the third target device and collect them into a third device item set, and the third device item set is recorded as D EV3 , get the first comparison set R EP1 and the second alignment set R EP2 , R EP1 =D EV1 ∩D EV3 , R EP2 =D EV2 ∩D EV3 , using the operating parameter items in the first comparison set as the first comparison parameter items, and using the operating parameter items in the second comparison set as the second comparison parameter items; Step S303: obtaining a historical record of a first comparison parameter item of a first target device in a target time period, drawing a function graph of a value of the first comparison parameter item changing with time, recorded as a first change function, obtaining a historical record of a second comparison parameter item of a second target device in a target time period, drawing a function graph of a value of the second comparison parameter item changing with time, recorded as a second change function; Obtain the historical record of the first comparison parameter item of the third target device in the target time period, draw a function image of the value of the first comparison parameter item changing with time, recorded as a third change function, obtain the historical record of the first comparison parameter item of the first target device in the target time period, draw a function image of the value of the second comparison parameter item changing with time, recorded as a fourth change function; Step S304: obtaining a similarity between the first change function and the third change function as α, and obtaining a similarity between the second change function and the fourth change function as β; Methods for comparing function similarity include: comparing image similarity of function images, collecting data on function images, calculating data distances between data, performing spectrum analysis on functions, and comparing spectrum similarity.

[0021] Step S400: By comparing the operating parameter items of the third target device with the operating parameter items of the first target device and the second target device, the association degree between the third target device and the first target device and the second target device is obtained, a state assessment model of the third target device is established, and a calculation result of the state assessment model is compared with the weighted failure rate of the operating parameter items to generate alarm information; Wherein, step S400 includes: Step S401: Calculate the fault risk value of the target operating state and obtain the feature set of the third target device operating parameter item, D EVf =R EP1 ∪R EP2 , where D EVf represents a feature set, obtains the weighted failure rates of various operating parameter items in the feature set, obtains the sum of the weighted failure rates in the feature set, denoted as H, and uses H as the failure risk value of the target operating state; Step S402: Calculate the membership degree F1 of the third target device with respect to the first target device, where F1=N r1 / N v3 , where Nr1 represents the number of running parameter items in the first alignment set, N v3 represents the number of operating parameter items in the third device item set, and calculates the membership F2 of the third device to the second target device, F2=N r2 / N v3 , where N r3 represents the number of run parameter items in the second alignment set; Step S403: Establishing a state assessment model Q of the third target device regarding the target operating state. , Step S404: bring the parameters into the status assessment model, calculate the status assessment parameter q of the third target device, and when q>H, issue a risk warning to the relevant management personnel.

[0022] In the examples: The first target device includes: operating parameter 1, operating parameter 2, operating parameter 3, operating parameter 4, and operating parameter 5; The second target device includes: operating parameter 2, operating parameter 3, operating parameter 4, operating parameter 6, and operating parameter 7; The third target device includes: operating parameter 2, operating parameter 3, operating parameter 5, operating parameter 6, and operating parameter 8; Four pieces of historical data of the target state of the first target device are collected, of which one piece has a target fault in the power grid system, and the first fault reference value C1=1÷4=0.25 is calculated; 10 pieces of historical data of the target state of the second target device are collected, of which 3 pieces have target faults in the power grid system, and the second fault reference value C2=3÷10=0.3 is calculated; Calculate the comprehensive fault reference value C0 = (1 + 3) ÷ (4 + 10) = 0.2857; Referring to the operating parameter items included in the third target device, a first comparison set R is obtained. EP1 = (operation parameter 2, operation parameter 3, operation parameter 5), obtain the second comparison set R EP2 = (operation parameter 2, operation parameter 3, operation parameter 6), feature set D EVf =(operating parameter 2, operating parameter 3, operating parameter 5, operating parameter 6); For the feature set D EVf The weighted failure rate is calculated by running the parameter items in: Operating parameter 2: 0.2857×2÷10=0.05714, operating parameter 3: 0.2857×2÷10=0.05714, Operating parameter 5: 0.28572×1÷10=0.02857, operating parameter 6: 0.28572×1÷10=0.02857; Failure risk value H = 0.17142; In the embodiment, the membership degree F1= F2=3 / 5; Get the similarity of the first set of parameter items: α1=0.4, β1=0.3; The calculated state assessment parameter value q1=0.1628, q1<H, no alarm is issued at this time; Get the similarity of the second set of parameter items: α2=0.2, β1=0.6; The calculated state assessment parameter value q2=0.1725, q2>H, at which time an alarm is issued.

[0023] The system includes: Fault record management module, weighted fault rate calculation module, equipment comparison module and status assessment module; The fault record management module is used to obtain the historical operation record of the power equipment and calculate the fault reference value of the target fault. The fault record management module includes: a power equipment management unit, a target state management unit, a historical record management unit and a fault reference value calculation unit. The power equipment management unit is used to obtain the operation parameters of the power equipment and collect them to obtain a set of power equipment operation parameter items. The target state management unit is used to obtain the target state of the power equipment. The historical record management unit is used to obtain the historical operation record of the power equipment. The fault reference value calculation unit is used to calculate the first fault reference value, the second fault reference value and the comprehensive fault reference value. The weighted failure rate calculation module is used to calculate the weighted failure rate of each operation parameter item, wherein the weighted failure rate calculation module includes: an operation parameter item management unit, a parameter item set management unit and a weight calculation unit, wherein the operation parameter item management unit is used to manage the operation parameter items of the first target device and the second target device, the parameter item set management unit is used to manage the device item set corresponding to the first target device and the second target device, and the weight calculation unit is used to calculate the weight of the operation parameter item and the weighted failure rate of the operation parameter item; The device comparison module is used to compare the degree of association between the third target device and the first target device and the second target device, wherein the device comparison module includes: a device detection unit, a comparison parameter acquisition unit and a parameter comparison unit, wherein the device detection unit is used to perform status monitoring on the third target device, the comparison parameter acquisition unit is used to acquire the first comparison parameter item and the second comparison parameter item, and the parameter comparison unit is used to compare the similarity of the operating parameters of the third target device with those of the first target device and the second target device; Among them, the status assessment module is used to perform status assessment on the third target device, wherein the status assessment module includes: a risk management unit, a membership calculation unit, an assessment model management unit and an information reminder unit, wherein the risk management unit is used to obtain a fault risk value, the membership calculation unit is used to calculate the membership of the third target device with the first target device and the second target device, the assessment model management unit is used to manage the status assessment model of the third target device, and the information reminder unit is used to calculate the status assessment parameters of the third target device, and when the alarm conditions are met, a risk warning is issued to relevant managers.

[0024] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0025] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for intelligent monitoring of power grid data based on the Internet of Things, characterized in that: The method comprises the following steps: Step S100: In a power system composed of a plurality of power devices, a set of power device operation parameter items is established, a certain fault in the power system is set as a target fault, a certain operation state of the power device before the target fault occurs is set as the target state, and a fault reference value of the target fault is calculated according to the historical record of the operation state; Step S200: obtaining two power devices with different operating parameter items from the power system, recording them as a first target device and a second target device respectively, calculating the weight of each operating parameter item in the first target device and the second target device in the historical records of target faults, and calculating the weighted fault rate of each operating parameter item; Step S300: acquiring a third target device in the power system, wherein the third target device has at least one same operating parameter item as the first target device and the second target device, and when it is detected that the third target device is in the target state, acquiring the similarity of the historical records of the same operating parameter item between the third target device and the first target device and the second target device; Step S400: By comparing the operating parameter items of the third target device with the operating parameter items of the first target device and the second target device, the degree of association between the third target device and the first target device and the second target device respectively is obtained, and a status assessment model for the third target device is established. The calculation result of the status assessment model is compared with the weighted failure rate of the operating parameter items to generate an alarm message.

2. The method for intelligent monitoring of power grid data based on the Internet of Things according to claim 1 is characterized in that: Step S100 includes: Step S101: Obtain the operating parameters of each power device in the power system, and collect the operating parameters of the power devices into a set W, W (w1, w2, w3, ..., w p ), where set W is a set of operating parameter items of power equipment, w1, w2, w3, ... and w p Respectively represent the operating parameters of the first, second, third, ... and pth power equipment, wherein any of the power equipment at least includes a device operating parameter in a set of operating parameter items; Step S102: Obtain the operation status records of each power device in the time period T1 before the target fault occurs from the management log of the power device, and set a certain abnormal state of the power device as the target state; Step S103: acquiring two electric power devices in the electric power system, which are respectively recorded as a first target device and a second target device, wherein the first target device and the second target device include different operating parameter items; Step S104: acquiring m1 historical records from the operation status record of the first target device, wherein among the m1 historical records, there are n1 historical records of the target fault occurring in the power system within a time period T1 after the first target device appears in the target state; Obtain m2 historical records from the operating status record of the second target device, wherein among the m2 historical records, there are n2 historical records of the target fault occurring in the power system within a time period T1 after the first target device occurs in the target state; Step S105: Calculate the first fault reference value C1, C1=n1 / m1, calculate the second fault reference value C2, C2=n2 / m2, and calculate the comprehensive fault reference value C0, C0=(n1+n2) / (m1+m2).

3. The method for intelligent monitoring of power grid data based on the Internet of Things according to claim 2 is characterized in that: Step S200 includes: Step S201: Acquire the operating parameter items of the first target device, and collect the operating parameter items of the first target device into a first device item set, which is recorded as D EV1 , obtain the operating parameter items of the second target device, and collect the operating parameter items of the second target device into a second device item set, wherein the second device item set is recorded as D EV2 ; Step S202: Obtain the total number of operation parameter items in the first equipment item set and the second equipment item set, recorded as g0, and obtain the number of times the kth operation parameter item in the operation parameter item set appears in the first equipment item set, recorded as g 1k , the number of times it appears in the second equipment item set, denoted as g 2k ; Step S203: Calculate the weight γ of the kth operating parameter item k , γ k =(g 1k +g 2k ) / g0, calculate the weighted failure rate R of the kth operating parameter item k , R k =γ k ×C0.

4. The method for intelligent monitoring of power grid data based on the Internet of Things according to claim 3 is characterized in that: Step S300 includes: Step S301: monitoring the status of the third target device. When the third target device is monitored to be in the target operating state, recording the time point t0, and setting the time period with the end time t0 and the time length T2 as the target time period, wherein T2≥T1; Step S302: Obtain the operating parameter items of the third target device and collect them into a third device item set, the third device item set is recorded as D EV3 , get the first comparison set R EP1 and the second alignment set R EP2 , R EP1 =D EV1 ∩D EV3 , R EP2 =D EV2 ∩D EV3 , using the operating parameter items in the first comparison set as the first comparison parameter items, and using the operating parameter items in the second comparison set as the second comparison parameter items; Step S303: obtaining a historical record of a first comparison parameter item of a first target device in a target time period, drawing a function graph of a value of the first comparison parameter item changing with time, recorded as a first change function, obtaining a historical record of a second comparison parameter item of a second target device in a target time period, drawing a function graph of a value of the second comparison parameter item changing with time, recorded as a second change function; Obtain the historical record of the first comparison parameter item of the third target device in the target time period, draw a function image of the value of the first comparison parameter item changing with time, recorded as a third change function, obtain the historical record of the first comparison parameter item of the first target device in the target time period, draw a function image of the value of the second comparison parameter item changing with time, recorded as a fourth change function; Step S304: obtaining a similarity between the first change function and the third change function as α, and obtaining a similarity between the second change function and the fourth change function as β.

5. The method for intelligent monitoring of power grid data based on the Internet of Things according to claim 4 is characterized in that: Step S400 includes: Step S401: Calculate the fault risk value of the target operating state and obtain the feature set of the third target device operating parameter item, D EVf =R EP1 ∪R EP2 , where D EVf represents a feature set, obtains the weighted failure rates of various operating parameter items in the feature set, obtains the sum of the weighted failure rates in the feature set, denoted as H, and uses H as the failure risk value of the target operating state; Step S402: Calculate the membership degree F1 of the third target device with respect to the first target device, where F1=N r1 / N v3 , where Nr1 represents the number of running parameter items in the first alignment set, N v3 represents the number of operating parameter items in the third device item set, and calculates the membership F2 of the third device to the second target device, F2=N r2 / N v3 , where N r3 represents the number of run parameter items in the second alignment set; Step S403: Establishing a state assessment model Q of the third target device regarding the target operating state. ； Step S404: bring the parameters into the status assessment model, calculate the status assessment parameter q of the third target device, and when q>H, issue a risk warning to the relevant management personnel.

6. An intelligent monitoring system for power grid data based on the Internet of Things, used to execute an intelligent monitoring method for power grid data based on the Internet of Things as described in any one of claims 1 to 5, characterized in that: The system includes the following modules: a fault record management module, a weighted fault rate calculation module, an equipment comparison module and a status evaluation module, wherein the fault record management module is used to obtain the historical operation records of the power equipment and calculate the fault reference value of the target fault, the weighted fault rate calculation module is used to calculate the weighted fault rate of each operation parameter item, the equipment comparison module is used to compare the degree of association between the third target equipment and the first target equipment and the second target equipment, and the status evaluation module is used to perform status evaluation on the third target equipment.

7. The intelligent monitoring system for power grid data based on the Internet of Things according to claim 6 is characterized by: The fault record management module includes: an electric power equipment management unit, a target state management unit, a historical record management unit and a fault reference value calculation unit, wherein the electric power equipment management unit is used to obtain the operating parameters of the electric power equipment and collect them to obtain a set of electric power equipment operating parameter items, the target state management unit is used to obtain the target state of the electric power equipment, the historical record management unit is used to obtain the historical operating records of the electric power equipment, and the fault reference value calculation unit is used to calculate a first fault reference value, a second fault reference value and a comprehensive fault reference value.

8. The intelligent monitoring system for power grid data based on the Internet of Things according to claim 6 is characterized by: The weighted failure rate calculation module includes: an operation parameter item management unit, a parameter item set management unit and a weight calculation unit, wherein the operation parameter item management unit is used to manage the operation parameter items of the first target device and the second target device, the parameter item set management unit is used to manage the device item set corresponding to the first target device and the second target device, and the weight calculation unit is used to calculate the weight of the operation parameter item and the weighted failure rate of the operation parameter item.

9. The intelligent monitoring system for power grid data based on the Internet of Things according to claim 6 is characterized by: The device comparison module includes: a device detection unit, a comparison parameter acquisition unit and a parameter comparison unit, wherein the device detection unit is used to perform status monitoring on the third target device, the comparison parameter acquisition unit is used to obtain a first comparison parameter item and a second comparison parameter item, and the parameter comparison unit is used to compare the similarity of the operating parameters of the third target device with the first target device and the second target device.

10. The intelligent monitoring system for power grid data based on the Internet of Things according to claim 6 is characterized by: The status assessment module includes: a risk management unit, a membership calculation unit, an assessment model management unit and an information reminder unit, wherein the risk management unit is used to obtain a fault risk value, the membership calculation unit is used to calculate the membership of the third target device with the first target device and the second target device, the assessment model management unit is used to manage the status assessment model of the third target device, and the information reminder unit is used to calculate the status assessment parameters of the third target device. When the alarm conditions are met, a risk warning is issued to relevant managers.

Images