A method and system for intelligent control of power distribution equipment based on artificial intelligence

Abstract

The present invention relates to the technical field of equipment management, and specifically to an intelligent management and control method and system for power distribution equipment based on artificial intelligence, comprising: a collection module collects historical fault records of each power distribution equipment in a target distribution station, real-time operation records of each power distribution equipment when it is determined that the equipment operating parameters are abnormal, and location information of each power distribution equipment in the target distribution station; analyzes the degree of equipment abnormality according to the equipment operating parameters of each power distribution equipment in the historical fault records; matches corresponding fault representations and equipment abnormality degrees according to real-time operation records, and analyzes the degree of fault impact of each power distribution equipment; and constructs maintenance correlation models between each power distribution equipment according to the location information and fault impact degree of each power distribution equipment, so as to timely judge the degree of abnormal impact of the equipment and formulate reasonable maintenance plans, thereby reducing the abnormal probability of power grid operation.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment management, and in particular to an intelligent management and control method and system for power distribution equipment based on artificial intelligence. Background Art

[0002] Distribution equipment is a general term for high-voltage distribution cabinets, generators, transformers, power lines and other equipment in the power system. As the end of the normal operation of the power grid, it is responsible for converting the high-voltage electric energy transmitted to the power equipment into low-voltage electric energy that meets the requirements of the power equipment through transformers or other devices, so as to supply various power equipment in the power system. It is equivalent to the core position of information exchange management. Therefore, all distribution equipment is required to operate normally at all times. Once equipment failure, data transmission, storage and system operation threats occur, the operation of the entire power grid will be affected.

[0003] Due to the large number and variety of distribution equipment in large distribution stations, when conducting a specific evaluation and analysis of distribution equipment failures, it is necessary to first understand the probability of equipment failure and the impact of the failure. Otherwise, the higher the impact of the failure, the higher the probability of failure, and the greater the risk. At the same time, when multiple devices fail in the station, due to the different distances between different devices and the impact of the failure, the equipment maintenance sequence still has certain defects. Therefore, how to identify abnormal distribution equipment and formulate a perfect maintenance sequence has become an urgent problem to be solved. Summary of the invention

[0004] The purpose of the present invention is to provide an artificial intelligence-based intelligent management and control method and system for power distribution equipment to solve the problems raised in the above-mentioned background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: an intelligent management and control method of power distribution equipment based on artificial intelligence, comprising the following steps:

[0006] S100, collecting historical fault records of each power distribution equipment in the target distribution station, generating a fault representation set of each power distribution equipment; constructing a historical state change graph according to the equipment operating parameters of each power distribution equipment in the historical fault records, and analyzing the abnormality degree of the corresponding power distribution equipment in each historical fault record according to the historical state change graph;

[0007] The target distribution station in the above steps is a large distribution station, and there is a certain distance between the positions of the distribution equipment in the large distribution station; at the same time, each historical fault record includes the equipment type, fault characterization, fault time point, maintenance time and same fault time, among which the maintenance time refers to the time consumed for the maintenance of the distribution equipment this time, and the same fault time refers to the time interval between the time when the distribution equipment fails this time and the last time the same type of fault occurred;

[0008] S200, based on the real-time operation records of each power distribution device, determine in real time whether the equipment parameters are abnormal, capture the real-time operation records of each power distribution device when the equipment operation parameters are determined to be abnormal, and then match the corresponding fault representations and the degree of equipment abnormality according to the real-time operation records to build the state change trajectory of each power distribution device; match the similarity of each historical state change graph based on the state change trajectory of each power distribution device; filter the fault representation set of each power distribution device according to the degree of work abnormality; analyze the degree of fault impact of each power distribution device according to the selected fault representations;

[0009] S300, obtaining the location information of each power distribution equipment in the target power distribution station, and constructing the maintenance correlation model between each power distribution equipment according to the location information and the degree of fault impact of each power distribution equipment;

[0010] S400: Formulate a fault maintenance sequence for a target distribution station according to a maintenance correlation model between each distribution device.

[0011] Furthermore, in S100, the specific steps are as follows:

[0012] S110, based on the historical fault records of each power distribution equipment in the target distribution station, obtain the equipment type, fault representation, fault time point, maintenance duration and fault duration of each corresponding power distribution equipment in the historical fault records, and then generate the fault representation set of each corresponding power distribution equipment according to the fault representation corresponding to the historical fault record;

[0013] S120, based on the historical fault records of a certain power distribution equipment, obtaining the equipment operating parameters of a certain power distribution equipment at each time node in the historical fault records, wherein the equipment operating parameters refer to the working voltage, workload and temperature of a certain power distribution equipment during operation; obtaining the equipment status value of a certain power distribution equipment by associating and weighting the working voltage, workload and temperature in the equipment operating parameters, and constructing an equipment status change diagram of a certain power distribution equipment based on the historical fault records according to the equipment status values ​​at each time node;

[0014] In the above steps, the device state value A=e1*U1+e2*U2+e1*U3 of a certain power distribution device is obtained according to the associated weighting of the working voltage U1, the workload U2 and the temperature U3, wherein e1, e2 and e3 represent the associated weight values ​​of the working voltage, the workload and the temperature respectively;

[0015] S130, respectively capture the fault time node t0, fault end time node t1 and maintenance time node t of a certain power distribution equipment in the equipment change diagram, wherein the maintenance time node refers to the time node corresponding to the start of maintenance of a certain power distribution equipment in the equipment state change diagram; at the same time, capture the equipment state values ​​x0, x1 and x2 corresponding to the three corresponding time nodes, and obtain the equipment abnormality degree X=|x0+x1-x2|*(t1-t) / (t1-t0) of a certain power distribution equipment in the historical fault record;

[0016] In the above steps, when the value of x0+x1-x2 is larger, it means that when a certain power distribution equipment fails, the equipment status value changes more; at the same time, t1-t represents the fault repair time, and t1-t0 represents the fault time, then the larger (t1-t) / (t1-t0) is, the longer the fault repair time is; at this time, when the equipment status value changes more and the fault repair time is longer, the corresponding equipment abnormality is higher;

[0017] By weighting the equipment operating parameters of each distribution equipment in the historical fault records to construct a historical status change diagram, and analyzing the changes in equipment status values ​​under fault duration and maintenance duration in the historical status change diagram, it is helpful to confirm the degree of equipment abnormality in each historical fault record based on the proportion of equipment status value and maintenance duration, and judge the degree of historical equipment failure.

[0018] Furthermore, in S200, the specific steps are as follows:

[0019] S210, obtaining the real-time operation record of a certain power distribution equipment, and analyzing and judging in real time whether the equipment operation parameters are abnormal; if an abnormality occurs, obtaining the real-time operation record within the set time period (u1-a) to (u1+a) according to the time node u1 at which the abnormality occurs, and obtaining the state change trajectory of a certain power distribution equipment within the set time period (u1-a) to (u1+a) according to the equipment operation parameters in the real-time operation record;

[0020] The process of judging whether the equipment operating parameters are abnormal in the above steps includes: when the value of any equipment operating parameter among the working voltage, working load and temperature exceeds or falls below the set threshold value β, judging that the corresponding power distribution equipment is abnormal;

[0021] S220, based on the device state change graphs obtained in each historical fault record of a certain distribution device, the state change trajectory is compared with each device state change graph for similarity, and each device state change graph greater than the similarity threshold α is extracted; according to each historical fault record corresponding to each extracted device state change graph, the fault representation Q and the device abnormality degree X corresponding to each historical fault record are captured to generate a similar fault set A = {{Q1, X1}, {Q2, X2}, ...,

[0022] {Qn, Xn}}, where {Q1, X1}, {Q2, X2}, …, {Qn, Xn} represent the fault representation Q and the equipment abnormality degree X corresponding to the 1st, 2nd, …, nth historical fault records with similar state change trajectories, respectively;

[0023] S230, collect all the abnormality levels of the devices with the same type as a certain fault representation i in the similar fault set A, confirm that the number of the abnormality levels of the collected devices is m, and calculate the sum of the abnormality levels of the corresponding devices as HX; then, according to the number of abnormality levels of the devices m and the sum of the abnormality levels of the devices HX, the fault impact level of a certain distribution device when an abnormality occurs within a set time period is obtained as follows: Y = σ1*σ2*[∑(m / n)*HX]; wherein σ1 represents the type of fault representation in the similar fault set A, and σ2 represents the fault impact factor of a certain distribution device;

[0024] Among them, when there are more types of fault representations and the sum of the abnormality levels of the equipment corresponding to the fault representations is larger, the fault impact of a certain power distribution equipment is greater;

[0025] By obtaining the equipment status change trajectory when the equipment operating parameters are abnormal based on the real-time operation records, and filtering the historical fault records according to the status change trajectory, the fault impact degree of the distribution equipment under the status change trajectory is analyzed, which is conducive to the subsequent judgment of the equipment maintenance sequence.

[0026] Furthermore, in S300, the specific steps are as follows:

[0027] S310, setting the distribution equipment with abnormal operating parameters in the target distribution station as abnormal equipment, and obtaining the fault impact degree Y of each abnormal equipment and the location information in the target distribution station;

[0028] S320. Obtain the fault impact degree Y1 of a certain distribution equipment and the fault impact degree Y2 of another distribution equipment in the target distribution station respectively, and then construct a maintenance correlation model W=R / [|Y1-Y2|*d] between a certain distribution equipment and another distribution equipment according to the fault impact degrees Y1 and Y2; wherein d represents the location distance between a certain distribution equipment and another distribution equipment, and R represents the maintenance correlation parameter of the target distribution station.

[0029] Furthermore, in S400, the specific steps are as follows:

[0030] S410, based on all abnormal devices in the target distribution station, capture the abnormal device g1 with the greatest fault impact Y, and collect other abnormal devices to form a set of other abnormal devices; use the maintenance correlation model W to match the abnormal device with the greatest maintenance correlation with the abnormal device g1 in the set of other abnormal devices, as the maintenance-related device g2 of the abnormal device g1; then use the maintenance correlation model W to match the maintenance-related device g3 of the maintenance-related device g2; based on this, formulate the fault maintenance sequence of the target distribution station according to the maintenance-related devices of the corresponding abnormal devices matched in sequence;

[0031] S420: Generate a fault repair record for the target distribution station based on the established fault repair sequence.

[0032] Intelligent management and control system for power distribution equipment, the system includes: data acquisition module, fault analysis module, real-time judgment module, model building module and intelligent maintenance module;

[0033] The data acquisition module collects historical fault records of each power distribution equipment in the target power distribution station, real-time operation records of each power distribution equipment when it is determined that the equipment operation parameters are abnormal, and location information of each power distribution equipment in the target power distribution station;

[0034] The fault analysis module analyzes the degree of equipment abnormality based on the equipment operating parameters of each power distribution equipment in the historical fault records;

[0035] The real-time judgment module matches the corresponding fault characteristics and equipment abnormality levels according to the real-time operation records to analyze the fault impact of each power distribution equipment;

[0036] Through the model building module, the maintenance correlation model between each power distribution equipment is constructed according to the location information and fault impact degree of each power distribution equipment;

[0037] The intelligent maintenance module is used to formulate the fault maintenance sequence of the target distribution station according to the maintenance correlation model between each distribution equipment.

[0038] Further, the data acquisition module includes a fault record acquisition unit, an operation record acquisition unit and a position acquisition unit;

[0039] The fault record collection unit is used to collect the historical fault records of each distribution equipment in the target distribution station and generate a fault representation set for each distribution equipment; the operation record collection unit is used to collect the real-time operation records of each distribution equipment when it is judged that the equipment operation parameters are abnormal; the location collection unit is used to collect the location information of each distribution equipment in the target distribution station.

[0040] Further, the fault analysis module includes a state change analysis unit and an abnormality degree analysis unit;

[0041] The state change analysis unit is used to construct a historical state change diagram based on the equipment operating parameters of each distribution equipment in the historical fault records; the abnormality degree analysis unit is used to analyze the abnormality degree of the corresponding distribution equipment in each historical fault record based on the historical state change diagram.

[0042] Furthermore, the real-time judgment module includes an abnormality judgment unit, a trajectory matching unit and an abnormality degree analysis unit;

[0043] The abnormality judgment unit is used to judge whether the equipment parameters are abnormal in real time based on the real-time operation records of each distribution equipment; the trajectory matching unit is used to match the corresponding fault representation and the degree of equipment abnormality according to the real-time operation records to construct the state change trajectory of each distribution equipment, and match the historical state change diagrams in the historical fault records based on the state change trajectory; the abnormality degree analysis unit is used to analyze the fault impact degree of each distribution equipment according to the equipment abnormality degree and the corresponding equipment abnormality number.

[0044] Furthermore, the intelligent maintenance module includes a sequence analysis unit and an equipment maintenance unit;

[0045] The sequence analysis unit is used to match the order of the corresponding abnormal equipment in sequence based on the maintenance correlation model, and then formulate the fault maintenance order of the target distribution station according to the matched abnormal equipment order; the equipment maintenance unit is used to generate a fault maintenance record for the target distribution station based on the formulated fault maintenance order.

[0046] Compared with the prior art, the beneficial effects achieved by the present invention are:

[0047] The present invention constructs a historical state change graph by weighting the equipment operating parameters of each power distribution equipment in the historical fault records, and analyzes the changes in the equipment status value under the fault duration and maintenance duration in the historical state change graph, which is beneficial to confirming the equipment abnormality degree of each historical fault record according to the proportion of the equipment status value and the maintenance duration, and judging the historical fault degree of the equipment; by obtaining the equipment state change trajectory when the equipment operating parameters are abnormal according to the real-time operation records, and screening the historical fault records according to the state change trajectory, the fault impact degree of the power distribution equipment under the state change trajectory is analyzed, which is beneficial to the subsequent judgment of the maintenance sequence of the equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] 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:

[0049] Figure 1 It is a structural diagram of an intelligent management and control system for power distribution equipment based on artificial intelligence of the present invention;

[0050] Figure 2It is a flow chart of an intelligent management and control method of power distribution equipment based on artificial intelligence of the present invention. DETAILED DESCRIPTION

[0051] 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.

[0052] See also Figure 1 ,The present invention provides a technical solution: an intelligent management and control system for power distribution equipment, the system includes: a data acquisition module, a fault analysis module, a real-time judgment module, a model building module and an intelligent maintenance module;

[0053] The data acquisition module collects historical fault records of each power distribution equipment in the target power distribution station, real-time operation records of each power distribution equipment when it is determined that the equipment operation parameters are abnormal, and location information of each power distribution equipment in the target power distribution station;

[0054] The data acquisition module includes a fault record acquisition unit, an operation record acquisition unit and a position acquisition unit;

[0055] The fault record collection unit is used to collect the historical fault records of each distribution equipment in the target distribution station and generate a fault representation set for each distribution equipment; the operation record collection unit is used to collect the real-time operation records of each distribution equipment when it is judged that the equipment operation parameters are abnormal; the location collection unit is used to collect the location information of each distribution equipment in the target distribution station.

[0056] The fault analysis module analyzes the degree of equipment abnormality based on the equipment operating parameters of each power distribution equipment in the historical fault records;

[0057] The fault analysis module includes a state change analysis unit and an abnormality degree analysis unit;

[0058] The state change analysis unit is used to construct a historical state change diagram based on the equipment operating parameters of each distribution equipment in the historical fault records; the abnormality degree analysis unit is used to analyze the abnormality degree of the corresponding distribution equipment in each historical fault record based on the historical state change diagram.

[0059] The real-time judgment module matches the corresponding fault characteristics and equipment abnormality levels according to the real-time operation records to analyze the fault impact of each power distribution equipment;

[0060] The real-time judgment module includes an abnormality judgment unit, a trajectory matching unit and an abnormality degree analysis unit;

[0061] The abnormality judgment unit is used to judge whether the equipment parameters are abnormal in real time based on the real-time operation records of each distribution equipment; the trajectory matching unit is used to match the corresponding fault representation and the degree of equipment abnormality according to the real-time operation records to construct the state change trajectory of each distribution equipment, and match the historical state change diagrams in the historical fault records based on the state change trajectory; the abnormality degree analysis unit is used to analyze the fault impact degree of each distribution equipment according to the equipment abnormality degree and the corresponding equipment abnormality number.

[0062] Through the model building module, the maintenance correlation model between each power distribution equipment is constructed according to the location information and fault impact degree of each power distribution equipment;

[0063] The intelligent maintenance module formulates the fault maintenance sequence of the target distribution station according to the maintenance correlation model between each distribution equipment;

[0064] The intelligent maintenance module includes a sequence analysis unit and an equipment maintenance unit;

[0065] The sequence analysis unit is used to match the order of the corresponding abnormal equipment in sequence based on the maintenance correlation model, and then formulate the fault maintenance order of the target distribution station according to the matched abnormal equipment order; the equipment maintenance unit is used to generate a fault maintenance record for the target distribution station based on the formulated fault maintenance order.

[0066] See also Figure 2 The present invention provides a technical solution: an intelligent management and control method for power distribution equipment based on artificial intelligence, comprising the following steps:

[0067] S100, collecting historical fault records of each power distribution equipment in the target distribution station, generating a fault representation set of each power distribution equipment; constructing a historical state change graph according to the equipment operating parameters of each power distribution equipment in the historical fault records, and analyzing the abnormality degree of the corresponding power distribution equipment in each historical fault record according to the historical state change graph;

[0068] The target distribution station in the above steps is a large distribution station, and there is a certain distance between the positions of the distribution equipment in the large distribution station; at the same time, each historical fault record includes the equipment type, fault characterization, fault time point, maintenance time and same fault time, among which the maintenance time refers to the time consumed for the maintenance of the distribution equipment this time, and the same fault time refers to the time interval between the time when the distribution equipment fails this time and the last time the same type of fault occurred;

[0069] In S100, the specific steps are as follows:

[0070] S110, based on the historical fault records of each power distribution equipment in the target distribution station, obtain the equipment type, fault representation, fault time point, maintenance duration and fault duration of each corresponding power distribution equipment in the historical fault records, and then generate the fault representation set of each corresponding power distribution equipment according to the fault representation corresponding to the historical fault record;

[0071] S120, based on the historical fault records of a certain power distribution equipment, obtaining the equipment operating parameters of a certain power distribution equipment at each time node in the historical fault records, wherein the equipment operating parameters refer to the working voltage, workload and temperature of a certain power distribution equipment during operation; obtaining the equipment status value of a certain power distribution equipment by associating and weighting the working voltage, workload and temperature in the equipment operating parameters, and constructing an equipment status change diagram of a certain power distribution equipment based on the historical fault records according to the equipment status values ​​at each time node;

[0072] In the above steps, the device state value A=e1*U1+e2*U2+e1*U3 of a certain power distribution device is obtained according to the associated weighting of the working voltage U1, the workload U2 and the temperature U3, wherein e1, e2 and e3 represent the associated weight values ​​of the working voltage, the workload and the temperature respectively;

[0073] S130, respectively capture the fault time node t0, fault end time node t1 and maintenance time node t of a certain power distribution equipment in the equipment change diagram, wherein the maintenance time node refers to the time node corresponding to the start of maintenance of a certain power distribution equipment in the equipment state change diagram; at the same time, capture the equipment state values ​​x0, x1 and x2 corresponding to the three corresponding time nodes, and obtain the equipment abnormality degree X=|x0+x1-x2|*(t1-t) / (t1-t0) of a certain power distribution equipment in the historical fault record;

[0074] In the above steps, when the value of x0+x1-x2 is larger, it means that when a certain distribution equipment fails, the equipment status value changes more; at the same time, t1-t represents the fault repair time, and t1-t0 represents the fault duration. Then, when (t1-t) / (t1-t0) is larger, it means that the fault repair time is longer; at this time, when the equipment status value changes more and the fault repair time is longer, the corresponding equipment abnormality is higher.

[0075] S200, based on the real-time operation records of each power distribution device, determine in real time whether the equipment parameters are abnormal, capture the real-time operation records of each power distribution device when the equipment operation parameters are determined to be abnormal, and then match the corresponding fault representations and the degree of equipment abnormality according to the real-time operation records to build the state change trajectory of each power distribution device; match the similarity of each historical state change graph based on the state change trajectory of each power distribution device; filter the fault representation set of each power distribution device according to the degree of work abnormality; analyze the degree of fault impact of each power distribution device according to the selected fault representations;

[0076] In S200, the specific steps are as follows:

[0077] S210, obtaining the real-time operation record of a certain power distribution equipment, and analyzing and judging in real time whether the equipment operation parameters are abnormal; if an abnormality occurs, obtaining the real-time operation record within the set time period (u1-a) to (u1+a) according to the time node u1 at which the abnormality occurs, and obtaining the state change trajectory of a certain power distribution equipment within the set time period (u1-a) to (u1+a) according to the equipment operation parameters in the real-time operation record;

[0078] The process of judging whether the equipment operating parameters are abnormal in the above steps includes: when the value of any equipment operating parameter among the working voltage, working load and temperature exceeds or falls below the set threshold value β, judging that the corresponding power distribution equipment is abnormal;

[0079] S220, based on the device state change graphs obtained in each historical fault record of a certain distribution device, the state change trajectory is compared with each device state change graph for similarity, and each device state change graph greater than the similarity threshold α is extracted; according to each historical fault record corresponding to each extracted device state change graph, the fault representation Q and the device abnormality degree X corresponding to each historical fault record are captured to generate a similar fault set A = {{Q1, X1}, {Q2, X2}, ...,

[0080] {Qn, Xn}}, where {Q1, X1}, {Q2, X2}, …, {Qn, Xn} represent the fault representation Q and the equipment abnormality degree X corresponding to the 1st, 2nd, …, nth historical fault records similar to the same state change trajectory, respectively;

[0081] S230, collect all the abnormality levels of the devices with the same type as a certain fault representation i in the similar fault set A, confirm that the number of the abnormality levels of the collected devices is m, and calculate the sum of the abnormality levels of the corresponding devices as HX; then, according to the number of abnormality levels of the devices m and the sum of the abnormality levels of the devices HX, the fault impact level of a certain distribution device when an abnormality occurs within a set time period is obtained as follows: Y = σ1*σ2*[∑(m / n)*HX]; wherein σ1 represents the type of fault representation in the similar fault set A, and σ2 represents the fault impact factor of a certain distribution device;

[0082] Among them, when there are more types of fault representations and the sum of the abnormality levels of the equipment corresponding to the fault representations is larger, the fault impact of a certain power distribution equipment is greater.

[0083] S300, obtaining the location information of each power distribution equipment in the target power distribution station, and constructing the maintenance correlation model between each power distribution equipment according to the location information and the degree of fault impact of each power distribution equipment;

[0084] In S300, the specific steps are as follows:

[0085] S310, setting the distribution equipment with abnormal operating parameters in the target distribution station as abnormal equipment, and obtaining the fault impact degree Y of each abnormal equipment and the location information in the target distribution station;

[0086] S320. Obtain the fault impact degree Y1 of a certain distribution equipment and the fault impact degree Y2 of another distribution equipment in the target distribution station respectively, and then construct a maintenance correlation model W=R / [|Y1-Y2|*d] between a certain distribution equipment and another distribution equipment according to the fault impact degrees Y1 and Y2; wherein d represents the location distance between a certain distribution equipment and another distribution equipment, and R represents the maintenance correlation parameter of the target distribution station.

[0087] S400, formulating a fault maintenance sequence of a target distribution station according to a maintenance correlation model between each distribution equipment;

[0088] In S400, the specific steps are as follows:

[0089] S410, based on all abnormal devices in the target distribution station, capture the abnormal device g1 with the greatest fault impact Y, and collect other abnormal devices to form a set of other abnormal devices; use the maintenance correlation model W to match the abnormal device with the greatest maintenance correlation with the abnormal device g1 in the set of other abnormal devices, as the maintenance-related device g2 of the abnormal device g1; then use the maintenance correlation model W to match the maintenance-related device g3 of the maintenance-related device g2; based on this, formulate the fault maintenance sequence of the target distribution station according to the maintenance-related devices of the corresponding abnormal devices matched in sequence;

[0090] S420: Generate a fault repair record for the target distribution station based on the established fault repair sequence.

[0091] 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. An intelligent management and control method for power distribution equipment based on artificial intelligence, characterized in that: The following steps are involved: S100, collecting historical fault records of each power distribution equipment in the target distribution station, generating a fault representation set of each power distribution equipment; analyzing the degree of equipment abnormality according to the equipment operating parameters of each power distribution equipment in the historical fault records; In S100, the specific steps are as follows: S110, based on the historical fault records of each power distribution equipment in the target distribution station, obtain the equipment type, fault representation, fault time point, maintenance duration and fault duration of each corresponding power distribution equipment in the historical fault records, and then generate the fault representation set of each corresponding power distribution equipment according to the fault representation corresponding to the historical fault record; S120, based on the historical fault records of a certain power distribution equipment, obtaining the equipment operating parameters of a certain power distribution equipment at each time node in the historical fault records, wherein the equipment operating parameters refer to the working voltage, workload and temperature of a certain power distribution equipment during operation; obtaining the equipment status value of a certain power distribution equipment by associating and weighting the working voltage, workload and temperature in the equipment operating parameters, and constructing an equipment status change diagram of a certain power distribution equipment based on the historical fault records according to the equipment status values ​​at each time node; S130, respectively capture the fault time node t0, fault end time node t1 and maintenance time node t of a certain power distribution equipment in the equipment change diagram, wherein the maintenance time node refers to the time node corresponding to the start of maintenance of a certain power distribution equipment in the equipment state change diagram; at the same time, capture the equipment state values ​​x0, x1 and x2 corresponding to the three corresponding time nodes, and obtain the equipment abnormality degree X=|x0+x1-x2|*(t1-t) / (t1-t0) of a certain power distribution equipment in the historical fault record; S200, capturing the real-time operation records of each power distribution device when it is determined that the device operation parameters are abnormal, matching the corresponding fault characteristics and the degree of device abnormality according to the real-time operation records, and analyzing the degree of fault impact of each power distribution device; In S200, the specific steps are as follows: S210, obtaining the real-time operation record of a certain power distribution equipment, and analyzing and judging in real time whether the equipment operation parameters are abnormal; if an abnormality occurs, obtaining the real-time operation record within the set time period (u1-a) to (u1+a) according to the time node u1 at which the abnormality occurs, and obtaining the state change trajectory of a certain power distribution equipment within the set time period (u1-a) to (u1+a) according to the equipment operation parameters in the real-time operation record; S220. Based on the device state change graphs obtained in each historical fault record of a certain power distribution device, the state change trajectory is compared with each device state change graph for similarity, and each device state change graph greater than the similarity threshold α is extracted; according to each historical fault record corresponding to each extracted device state change graph, the fault representation Q and the device abnormality degree X corresponding to each historical fault record are captured to generate a similar fault set A={{Q1, X1}, {Q2, X2}, ..., {Qn, Xn}}, wherein {Q1, X1}, {Q2, X2}, ..., {Qn, Xn} respectively represent the fault representation Q and the device abnormality degree X corresponding to the 1st, 2nd, ..., nth historical fault records similar to the state change trajectory; S230, collect all the abnormality levels of the equipment with the same type as a certain fault representation i in the similar fault set A, confirm that the number of the abnormality levels of the collected equipment is m, and calculate the sum of the abnormality levels of the corresponding equipment to be HX; then, according to the number of abnormality levels of the equipment m and the sum of the abnormality levels of the equipment HX, the fault impact level of a certain distribution equipment when an abnormality occurs within a set time period is obtained as follows: Y=σ1*σ2*[∑(m / n)*HX]; wherein σ1 represents the type of fault representation in the similar fault set A, and σ2 represents the fault impact factor of a certain distribution equipment; S300, obtaining the location information of each power distribution equipment in the target power distribution station, and constructing the maintenance correlation model between each power distribution equipment according to the location information and the degree of fault impact of each power distribution equipment; In S300, the specific steps are as follows: S310, setting the distribution equipment with abnormal operating parameters in the target distribution station as abnormal equipment, and obtaining the fault impact degree Y of each abnormal equipment and the location information in the target distribution station; S320, respectively obtain the fault impact degree Y1 of a certain distribution equipment and the fault impact degree Y2 of another distribution equipment in the target distribution station, and then construct a maintenance correlation model W=R / [|Y1-Y2|*d] between a certain distribution equipment and another distribution equipment according to the fault impact degrees Y1 and Y2; wherein d represents the location distance between a certain distribution equipment and another distribution equipment, and R represents the maintenance correlation parameter of the target distribution station; S400, formulating a fault maintenance sequence of a target distribution station according to a maintenance correlation model between each distribution equipment; In S400, the specific steps are as follows: S410, based on all abnormal devices in the target distribution station, capture the abnormal device g1 with the greatest fault impact Y, and collect other abnormal devices to form a set of other abnormal devices; use the maintenance correlation model W to match the abnormal device with the greatest maintenance correlation with the abnormal device g1 in the set of other abnormal devices, as the maintenance-related device g2 of the abnormal device g1; then use the maintenance correlation model W to match the maintenance-related device g3 of the maintenance-related device g2; based on this, formulate the fault maintenance sequence of the target distribution station according to the maintenance-related devices of the corresponding abnormal devices matched in sequence; S420: Generate a fault repair record for the target distribution station based on the established fault repair sequence.

2. An intelligent management and control system for power distribution equipment for implementing the intelligent management and control method for power distribution equipment based on artificial intelligence as described in claim 1, characterized in that: The system includes: a data acquisition module, a fault analysis module, a real-time judgment module, a model building module and an intelligent maintenance module; The data acquisition module collects historical fault records of each power distribution device in the target power distribution station, real-time operation records of each power distribution device when it is determined that the equipment operation parameters are abnormal, and location information of each power distribution device in the target power distribution station; Analyze the degree of equipment abnormality according to the equipment operating parameters of each power distribution equipment in the historical fault records through the fault analysis module; The real-time judgment module matches the corresponding fault characteristics and the degree of equipment abnormality according to the real-time operation records to analyze the degree of fault impact of each power distribution equipment; The maintenance correlation model between each power distribution equipment is constructed respectively according to the location information and the fault impact degree of each power distribution equipment through the model construction module; The intelligent maintenance module is used to formulate a fault maintenance sequence for the target distribution station according to the maintenance correlation model between the distribution equipment.

3. The intelligent management and control system for power distribution equipment according to claim 2 is characterized in that: The data acquisition module includes a fault record acquisition unit, an operation record acquisition unit and a position acquisition unit; The fault record collection unit is used to collect historical fault records of each distribution equipment in the target distribution station and generate a fault representation set of each distribution equipment; the operation record collection unit is used to collect real-time operation records of each distribution equipment when it is determined that the equipment operation parameters are abnormal; the location collection unit is used to collect location information of each distribution equipment in the target distribution station.

4. The intelligent management and control system for power distribution equipment according to claim 2 is characterized in that: The fault analysis module includes a state change analysis unit and an abnormality degree analysis unit; The state change analysis unit is used to construct a historical state change diagram according to the equipment operation parameters of each distribution equipment in the historical fault records; the abnormality degree analysis unit is used to analyze the abnormality degree of the corresponding distribution equipment in each historical fault record according to the historical state change diagram.

5. The intelligent management and control system for power distribution equipment according to claim 2 is characterized in that: The real-time judgment module includes an abnormality judgment unit, a trajectory matching unit and an abnormality degree analysis unit; The abnormality judgment unit is used to judge whether the equipment parameters are abnormal in real time based on the real-time operation records of each distribution equipment; the trajectory matching unit is used to match the corresponding fault representation and the degree of equipment abnormality according to the real-time operation records to construct the state change trajectory of each distribution equipment, and match the historical state change diagrams in the historical fault records based on the state change trajectory; the abnormality degree analysis unit is used to analyze the fault impact degree of each distribution equipment according to the equipment abnormality degree and the corresponding equipment abnormality number.

6. The intelligent management and control system for power distribution equipment according to claim 2, characterized in that: The intelligent maintenance module includes a sequence analysis unit and an equipment maintenance unit; The sequence analysis unit is used to match the order of corresponding abnormal equipment in sequence based on the maintenance correlation model, and then formulate the fault maintenance order of the target distribution station according to the matched abnormal equipment order; the equipment maintenance unit is used to generate a fault maintenance record for the target distribution station based on the formulated fault maintenance order.

Images