Artificial Intelligence-Based Grid Equipment Problem Requirement Identification Method, Device, and Medium

Abstract

The present invention provides a method, device and medium for identifying problem requirements of power grid equipment based on artificial intelligence, including: establishing a risk problem database of power grid equipment; performing real-time monitoring on the operation data of power grid equipment, screening out potential hazard data from the operation data, and converting the potential hazard data into potential hazard risk problems corresponding to the potential hazard data; performing diversion processing on the potential hazard risk problems, and cleaning up the potential hazard risk problems after the diversion processing. Through the technical solution provided by the present invention, the technical problem that the potential hazard problems of power grid equipment during normal operation cannot be effectively eliminated in the prior art can be solved.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid equipment fault detection, and more particularly, to a method, device, and medium for identifying problem requirements of power grid equipment based on artificial intelligence. Background Art

[0002] Currently, as people's demand for electricity consumption is increasing day by day, electricity is applied to all walks of life, which not only leads to a continuous increase in demand but also makes power grid equipment become more and more complex. During daily use, power grid equipment is no longer just a power transmission tool but also undertakes various feedback functions of the power system. To ensure the normal operation of power grid equipment, it is often necessary to monitor the power grid equipment.

[0003] However, the existing monitoring of power grid equipment mainly stays in the mode of "solving problems when there are problems", that is, after discovering problems that occur during the operation of power grid equipment, solving the problems. It is impossible to clear the upcoming problems in time before the problems occur during the normal operation of power grid equipment, so as to ensure the long-term normal operation of power grid equipment. Summary of the Invention

[0004] The main object of the present invention is to provide a method, device, and medium for identifying problem requirements of power grid equipment based on artificial intelligence, so as to solve the technical problem that the hidden danger problems during the normal operation of power grid equipment cannot be effectively cleared in the prior art.

[0005] To achieve the above object, according to one aspect of the present invention, a method for identifying problem requirements of power grid equipment based on artificial intelligence is provided, including:

[0006] Establish a risk problem database for power grid equipment;

[0007] Real-time monitor the operation data of power grid equipment, screen out hidden danger data from the operation data, and convert the hidden danger data into corresponding hidden danger risk problems;

[0008] Perform a diversion process on the hidden danger risk problems, and clean up the hidden danger risk problems after the diversion process.

[0009] Further, establishing a risk problem database for power grid equipment includes:

[0010] Collect problem data of power grid equipment;

[0011] Combine and classify the problem data according to at least two different classification methods to obtain different categories of problem data packets;

[0012] Summarize different categories of problem data packets to obtain a problem database.

[0013] Further, the problem data is combined and classified according to at least two different classification methods to obtain problem data packets of different categories, including:

[0014] Combined classification is performed according to the application scenarios of power grid equipment and the administrative levels to which the power grid equipment belongs; the application scenarios of power grid equipment include: production operation, power consumption planning, infrastructure power consumption, business expansion, and artificial customer service; the administrative levels of power grid equipment include district / county level, station level, branch line level, substation level, and meter level;

[0015] Any link in the application scenario of power grid equipment is combined with any level in the administrative level of power grid equipment to form a combined category, and the problem data is divided into problem data packets of different categories according to the combined category.

[0016] Further, problem data of power grid equipment is collected, including:

[0017] Collect problem data of power grid equipment during production operation, power consumption planning, infrastructure power consumption, business expansion, and artificial customer service, and store it in the cloud or storage device.

[0018] Further, problem data packets of different categories are summarized to obtain a problem database, including:

[0019] Define the problem data as a xy , where x represents classification according to the administrative level of power grid equipment, and the administrative levels include district / county level, station level, branch line level, substation level, and meter level; y represents classification according to the production link of power grid equipment, and the production links include production operation, power consumption planning, infrastructure power consumption, business expansion, and artificial customer service;

[0020] Define the data corresponding to the production operation link in the problem data as a x1 ;

[0021] Define the data corresponding to the power consumption planning link in the problem data as a x2 ;

[0022] Define the data corresponding to the infrastructure power consumption link in the problem data as a x3 ;

[0023] Define the data corresponding to the business expansion link in the problem data as a x4 ;

[0024] Define the data corresponding to the artificial customer service link in the problem data as a x5 ;

[0025] Define the data corresponding to the district / county level in the problem data as a1y ;

[0026] Define the data corresponding to the site level in the problem data as a 2y ;

[0027] Define the data corresponding to the branch line level in the problem data as a 3y ;

[0028] Define the data corresponding to the substation level in the problem data as a 4y ;

[0029] Define the data corresponding to the meter level in the problem data as a 5y ;

[0030] Organize the problem data into a matrix form for arrangement to form a problem database;

[0031] Among them, the matrix form of the problem data is:

[0032]

[0033] Furthermore, monitor the operation data of grid equipment, screen out potential hazard data from the operation data, and convert the potential hazard data into potential hazard risk problems corresponding to the potential hazard data, including:

[0034] Monitor the operation data of grid equipment during operation;

[0035] Perform correction calculations on the operation data to generate corrected operation data; compare and calculate the corrected operation data with the problem data in the problem database;

[0036] Identify the potential hazard data existing in the corrected operation data, and convert the potential hazard data into potential hazard risk problems corresponding to the potential hazard data;

[0037] According to the group where the problem data corresponding to the potential hazard data is located, identify the group where the potential hazard risk problem is located.

[0038] Furthermore, perform correction calculations on the operation data to generate corrected operation data, including:

[0039] Call the operation data;

[0040] Operate and correct the operation data into corrected operation data; the operation formula for operating and correcting the operation data into corrected operation data is as follows:

[0041] Define the operation data as A xy ;

[0042] Define the corrected operation data as A′ xy ;

[0043] A′xy = γ * A xy ;

[0044]

[0045] d i = x - y;

[0046] where γ is the correction coefficient; n is the total number of problem data; d i is the difference between x in a xy and y in a xy .

[0047] Furthermore, the corrected operation data is compared and calculated with the problem data in the problem database, including:

[0048] Compare A' xy and a xy for comparison and calculation. Define A as the risk parameter value corresponding to the risk problem, and the calculation method is as follows:

[0049]

[0050] When A ≥ 0, determine that the corresponding corrected operation data is potential hazard data;

[0051] When A < 0, determine that the corresponding corrected operation data is not potential hazard data.

[0052] According to another aspect of the present invention, there is provided a device for identifying problem requirements of power grid equipment based on artificial intelligence, including:

[0053] A problem database module for storing power grid risk problems and forming a power grid risk problem database;

[0054] An analysis and calculation module for real-time monitoring of the operation data of power grid equipment, screening out potential hazard data from the operation data, and converting the potential hazard data into potential hazard risk problems corresponding to the potential hazard data;

[0055] A shunt module for shunting the risk problems and then cleaning the shunted risk problems.

[0056] According to still another aspect of the present invention, there is provided a non-volatile storage medium storing multiple instructions suitable for being loaded and executed by a processor to perform the above-provided method for identifying problem requirements of power grid equipment based on artificial intelligence.

[0057] Applying the technical solution of the present invention, by establishing a complete database of power grid risk problems, then monitoring the data that appears during the actual operation of the power grid equipment, and converting the potential hazard data into corresponding potential hazard risk problems. Comparing the potential hazard risk problems with the data in the power grid risk problem database, and promptly diverting and resolving the potential hazard problems that are about to occur, so as to achieve the technical effect of preventing problems before they occur. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] The accompanying drawings forming a part of this application are used to provide a further understanding of the present invention. The schematic embodiments and descriptions thereof of the present invention are used to explain the present invention and do not constitute an improper limitation to the present invention. In the drawings:

[0059] Figure 1 shows a schematic flow chart of a method for identifying power grid equipment problem requirements based on artificial intelligence according to an embodiment of the present invention;

[0060] Figure 2 shows a schematic flow chart of establishing a risk problem database for power grid equipment according to an embodiment of the present invention;

[0061] Figure 3 shows a schematic flow chart of monitoring the operation data of power grid equipment in real time, screening out potential hazard data from the operation data, and converting the potential hazard data into potential hazard risk problems corresponding to the potential hazard data according to an embodiment of the present invention;

[0062] Figure 4 shows a schematic diagram of a device for identifying power grid equipment problem requirements based on artificial intelligence according to an embodiment of the present invention;

[0063] Figure 5 shows a schematic diagram of a system for identifying power grid equipment problem requirements based on artificial intelligence according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0064] It should be noted that, without conflict, the embodiments in this application and the features in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.

[0065] As Figure 1 shown, an embodiment of the present invention provides a method for identifying power grid equipment problem requirements based on artificial intelligence, including: S1: Establishing a risk problem database for power grid equipment; S2: Monitoring the operation data of power grid equipment in real time, screening out potential hazard data from the operation data, and converting the potential hazard data into potential hazard risk problems corresponding to the potential hazard data; S3: Diverting and processing the potential hazard risk problems, and cleaning the potential hazard risk problems after the diversion and processing.

[0066] By adopting the method for identifying the problem requirements of power grid equipment using artificial intelligence provided in this embodiment, a complete power grid risk problem database is established. Then, the data that appears during the actual operation of the power grid equipment is monitored, and the potential hazard data is converted into corresponding potential hazard risk problems. The potential hazard risk problems are compared with the data in the power grid risk problem database, and the upcoming potential hazard problems are promptly diverted and resolved to achieve the technical effect of preventing problems before they occur. Therefore, through the technical solution provided in this embodiment, the technical problem in the prior art that the potential hazard problems during the normal operation of power grid equipment cannot be effectively eliminated can be solved.

[0067] It should be noted that the diversion processing can be understood as classifying the corresponding problems and diverting them to the corresponding specific production links and administrative levels, and then corresponding processing is carried out by the corresponding staff or operating system.

[0068] Specifically, in the process of establishing the risk problem database of power grid equipment, it includes obtaining the risk problems of power grid equipment and the problem data corresponding to the risk problems (including parameter values such as voltage, current, temperature, no-load, overload, etc.).

[0069] Furthermore, the risk problem database includes specific risk parameters and the risk problems corresponding to the corresponding risk parameters (such as overload problems, etc.). The risk problem database also includes the processing methods corresponding to the corresponding problem data. In this way, after finding the corresponding problem data, the suggestions for the corresponding processing methods can be quickly obtained to facilitate the staff to confirm whether to clean according to the corresponding processing methods, which is convenient for the staff to carry out corresponding operations.

[0070] Furthermore, in a preferred embodiment, there can be multiple processing methods corresponding to the corresponding problem data in the risk problem database. For example, for the same problem data, there can be multiple corresponding processing methods.

[0071] As Figure 2 shown, in this embodiment, establishing the risk problem database of power grid equipment includes: S11: Collecting the problem data of power grid equipment; S12: Combining and classifying the problem data according to at least two different classification methods to obtain different categories of problem data packets; S13: Summarizing the different categories of problem data packets to obtain the problem database. By adopting such a method, it is convenient to classify the risk problem data, so as to facilitate subsequent comparison with the potential hazard data, thereby facilitating the improvement of the accuracy of judging the potential hazard data.

[0072] Specifically, the problem data is combined and classified according to at least two different classification methods to obtain problem data packets of different categories, including: combining and classifying according to the application scenarios of power grid equipment and the administrative levels to which the power grid equipment belongs; the application scenarios of power grid equipment include: production operation, power consumption planning, infrastructure power consumption, business expansion, and artificial customer service, and the administrative levels of power grid equipment include county level, site level, branch line level, substation level, and meter level; any link in the application scenarios of power grid equipment is combined with any level in the administrative levels of power grid equipment to form a combined category, and the problem data is divided into problem data packets of different categories according to the combined category. In this way, it is convenient to perform combined classification according to the application scenarios of power grid equipment and the administrative levels to which they belong, thereby facilitating the improvement of the classification accuracy of risk problem data, facilitating the subsequent rapid determination of the categories of risk problems, and thus performing corresponding cleaning operations.

[0073] It should be noted that artificial customer service is a separate category of scenario, and artificial customer service is in a parallel relationship with production operation, power consumption planning, etc. Because of the use of power grid equipment, different data sets will be generated for different scenarios. Therefore, we statistically analyze the data in the form of data sets, so the scenario of artificial customer service is listed separately.

[0074] In this embodiment, the problem data of power grid equipment is collected, including: collecting the problem data of power grid equipment during production operation, power consumption planning, infrastructure power consumption, business expansion, and artificial customer service, and storing it in the cloud or storage device. By using this method, it is convenient to effectively ensure the breadth of collection of problem data, so as to fully collect sufficient problem data, so as to provide accurate basis for subsequent analysis and judgment.

[0075] Specifically, after collecting the problem data of power grid equipment during production operation, power consumption planning, infrastructure power consumption, business expansion, and artificial customer service, the problem data during production operation, power consumption planning, infrastructure power consumption, business expansion, and artificial customer service can be screened and marked respectively, and the problem data is divided into different groups according to production operation, power consumption planning, infrastructure power consumption, business expansion, and artificial customer service processes.

[0076] It should be noted that the production and operation links mainly refer to the problems involved in the grid equipment in the fields of industrial electricity consumption, household electricity consumption, and commercial electricity consumption in factories; the electricity consumption planning link refers to the problems involved in the grid equipment for monitoring, regulating, and operating the entire power system during the future electricity consumption planning stage; the infrastructure electricity consumption refers to the problems involved in the electricity consumption link at construction sites during urban construction; the business expansion electricity consumption refers to the problems involved in new electricity consumption scenarios, such as the grid equipment involved in the field of new energy vehicles; the artificial customer service mainly refers to the problems feedback during the operation of the grid equipment.

[0077] It should be noted that the grid equipment at the district and county level involves the following problem data:

[0078] Asset scale information, including the number of substations, the number of transformers, the capacity of transformers, the number of switches at each voltage level, the number of 10kV feeders, etc.;

[0079] Load and user information, including current load, this year's load peak, the same period load, the number of users, the number and list of important and sensitive users, etc.;

[0080] Heavy overload information, including the number and list of heavily overloaded main transformers, 35kV and above, the number and list of heavily overloaded lines, the number and list of 10kV heavily overloaded lines, the number and list of 10kV heavily overloaded distribution transformers, etc.; Low voltage information, mainly reflected in the number and list of low voltage buses, the number and list of low voltage areas, the number and list of low voltage customers, the low voltage demands and list, etc.;

[0081] Power outage information; mainly reflected in the number and list of power outage main transformers, the number and list of power outage lines, the number and list of power outage 10kV feeders, the number and list of power outage 10kV distribution transformers, the number and list of power outage demands, etc.

[0082] It should be noted that the problem data at the site level includes:

[0083] Asset scale information, mainly reflected in the number of transformers, the capacity of transformers, the number of switches at each voltage level, the number of 10kV feeders, etc.;

[0084] Load and user information, mainly reflected in current load, this year's load peak, the same period load, the number of users, the number and list of important and sensitive users, etc.;

[0085] Heavy overload information, including whether there is a main transformer heavy overload, list, the number and list of 35kV and above heavy overload lines, the number and list of 10kV heavy overload lines, the number and list of 10kV heavy overload distribution transformers, the number of heavy overload days and the maximum load, the duration, etc.;

[0086] Low-voltage information is mainly reflected in the number and list of low-voltage busbars, the number and list of low-voltage power supply areas, the number and list of low-voltage customers, low-voltage demands and lists, etc.;

[0087] Project situation is mainly reflected in the project situation, etc.; Workload information is mainly reflected in the number of infrastructure and production construction ((in the substation + downstream line distribution transformers));

[0088] Power outage information is mainly reflected in the number and list of main transformers out of power, the number and list of power outage lines, the number and list of 10kV feeders out of power, the number and list of 10kV distribution transformers out of power, the number and list of power outage demands, etc.

[0089] It should be noted that the problem data at the branch line level includes:

[0090] Asset scale information is mainly reflected in the name of the superior substation, line details, downstream distribution transformer numbers, etc.; Load and user information is mainly reflected in the current load, this year's load peak, the same period load, the number of users, the number and list of important and sensitive users, etc.;

[0091] Heavy overload information includes whether the superior main transformer is overloaded, whether this feeder is overloaded, the number and list of 10kV overloaded distribution transformers, the number of overloaded days and the maximum load, the duration, etc.; Low-voltage information is mainly reflected in whether the connected busbar is low-voltage, the number and list of low-voltage power supply areas, the number and list of low-voltage customers, low-voltage demands and lists, etc.;

[0092] Project situation is mainly reflected in the project situation, etc.; Workload information is mainly reflected in the number of infrastructure and production construction ((in the substation + downstream line distribution transformers));

[0093] Power outage information is mainly reflected in the number and list of main transformers out of power, the number and list of power outage lines, the number and list of 10kV feeders out of power, the number and list of 10kV distribution transformers out of power, the number and list of power outage demands, etc.

[0094] It should be noted that the problem data at the substation level includes:

[0095] Equipment ledger information is mainly reflected in the production year, sectionalizing switch, branch line, wire diameter, line length, switch setting value, reactive power compensation device, etc.;

[0096] Equipment monitoring information is mainly reflected in voltage and current data, load rate, three-phase unbalance rate, etc.; Customer information is mainly reflected in customer files, customer demand information, power consumption information, etc.;

[0097] Project information is mainly reflected in project basic information, project progress information, etc.;

[0098] Supplementary information is mainly reflected in operation information, line loss information, key user locations, etc.

[0099] Specifically, summarize problem data packets of different categories to obtain a problem database, including: define the problem data as a xy , where x represents classification according to the administrative level of power grid equipment, and the administrative levels include district / county level, site level, branch line level, substation level, and electricity meter level; y represents classification according to the production link of power grid equipment, and the production links include production operation, power consumption planning, infrastructure power consumption, business expansion, and artificial customer service;

[0100] Define the data corresponding to the production operation link in the problem data as a x1 ;

[0101] Define the data corresponding to the power consumption planning link in the problem data as a x2 ;

[0102] Define the data corresponding to the infrastructure power consumption link in the problem data as a x3 ;

[0103] Define the data corresponding to the business expansion link in the problem data as a x4 ;

[0104] Define the data corresponding to the artificial customer service link in the problem data as a x5 ;

[0105] Define the data corresponding to the district / county level in the problem data as a 1y ;

[0106] Define the data corresponding to the site level in the problem data as a 2y ;

[0107] Define the data corresponding to the branch line level in the problem data as a 3y ;

[0108] Define the data corresponding to the substation level in the problem data as a 4y ;

[0109] Define the data corresponding to the electricity meter level in the problem data as a 5y ;

[0110] Arrange the problem data in matrix form to form a problem database;

[0111] Among them, the matrix form of the problem data is:

[0112]

[0113] Adopting such a method can facilitate the classification and sorting of problem data for subsequent quick judgment and classification.

[0114] As shown Figure 3 in the figure, in this embodiment, the operation data of the power grid equipment is monitored, the hidden danger data is screened out from the operation data, and the hidden danger data is converted into the hidden danger risk problem corresponding to the hidden danger data, including: S21: monitoring the operation data of the power grid equipment during operation; S22: performing correction calculation on the operation data to generate corrected operation data; comparing and calculating the corrected operation data with the problem data in the problem database; S23: identifying the hidden danger data existing in the corrected operation data, and converting the hidden danger data into the hidden danger risk problem corresponding to the hidden danger data; S24: identifying the group where the hidden danger risk problem is located according to the group where the problem data corresponding to the hidden danger data is located. By adopting such a method, it is possible to facilitate the accurate judgment of the hidden danger data, the hidden danger risk problem corresponding to the hidden danger data, and the group corresponding to the hidden danger risk problem, so as to facilitate subsequent targeted and rapid processing.

[0115] Specifically, performing correction calculation on the operation data to generate corrected operation data includes:

[0116] Invoking the operation data;

[0117] Performing operation correction on the operation data to generate corrected operation data; the operation formula for performing operation correction on the operation data to generate corrected operation data is as follows:

[0118] Defining the operation data as A xy ;

[0119] Defining the corrected operation data as A' xy ;

[0120] A' xy =γ*A xy ;

[0121]

[0122] d i =x - y;

[0123] where γ is the correction coefficient; n is the total number of times of the problem data; d i is the difference between x in a xy and y in a xy . In this way, it is possible to facilitate the correction of the operation data so as to obtain the actual and accurate operation data, that is, the corrected operation data.

[0124] It should be noted that the operation data here can be real-time data.

[0125] In this embodiment, comparing and calculating the corrected operation data with the problem data in the problem database includes:

[0126] Compare A xy and a xy for comparative calculation. Define A as the risk parameter value corresponding to the risk problem, and the calculation method is as follows:

[0127]

[0128] When A≥0, determine that the corresponding corrected operation data is potential hazard data;

[0129] When A<0, determine that the corresponding corrected operation data is not potential hazard data. By using this method, it is convenient to accurately judge whether the corrected operation data is potential hazard data and improve the accuracy of judgment.

[0130] As Figure 4 shown, Embodiment 2 of the present invention provides a device for identifying problem requirements of power grid equipment based on artificial intelligence, including a problem database module 01, an analysis and calculation module 02, and a shunt module 03. The problem database module 01 is used to store power grid risk problems and form a power grid risk problem database. The analysis and calculation module 02 is used to monitor the operation data of power grid equipment in real time, screen out potential hazard data from the operation data, and convert the potential hazard data into potential hazard risk problems corresponding to the potential hazard data. The shunt module 03 is used to perform shunt processing on the risk problems and then clean up the risk problems after shunt processing.

[0131] Specifically, the problem database module 01 includes:

[0132] A collection unit, which is used to collect the problem data of the power grid equipment in the processes of production operation, power consumption planning, infrastructure power consumption, business expansion, and artificial customer service, and store it in the cloud or storage device;

[0133] A screening and grouping unit, which is used to screen and mark the problem data in the processes of production operation, power consumption planning, infrastructure power consumption, business expansion, and artificial customer service; and is used to divide the problem data into different groups according to production operation, power consumption planning, infrastructure power consumption, business expansion, and artificial customer service;

[0134] A packaging unit, which is used to package the problem data in different groups to form problem data packets;

[0135] An integration unit, which is used to form the problem database from several problem data packets.

[0136] It should be noted that the screening and grouping unit includes:

[0137] The link classification subunit is used to classify the problem data according to different links of the production operation, the power consumption plan, the infrastructure power consumption, the business expansion, and the manual customer service;

[0138] The level classification subunit is used to classify the problem data according to different administrative levels of the power grid equipment, divided into district / county level, site level, branch line level, substation level, and meter level;

[0139] The definition subunit is used to define the problem data as a xy ;

[0140] The matrix subunit arranges the problem data in a matrix form as:

[0141]

[0142] wherein, the x represents the district / county level, the site level, the branch line level, the substation level, and the meter level in the division according to the administrative level; y represents different production links of the production operation, the power consumption plan, the infrastructure power consumption, the business expansion, and the manual customer service that occur according to different production links of the power grid equipment.

[0143] It should be noted that the problem data of the power grid equipment at the district / county level involves the following:

[0144] Asset scale information, including the number of substations, the number of transformers, the capacity of transformers, the number of switches of each voltage level, the number of 10kV feeders, etc.;

[0145] Load and user information, including the current load, the load peak this year, the same-period load, the number of users, the number and list of important and sensitive users, etc.;

[0146] Heavy overload information, including the number and list of heavy overload main transformers, 35kV and above, the number and list of heavy overload lines, the number and list of 10kV heavy overload lines, the number and list of 10kV heavy overload distribution transformers, etc.; Low voltage information, mainly reflected in the number and list of low voltage buses, the number and list of low voltage areas, the number and list of low voltage customers, the low voltage demands and list, etc.;

[0147] Power outage information; mainly reflected in the number and list of power outage main transformers, the number and list of power outage lines, the number and list of power outage 10kV feeders, the number and list of power outage 10kV distribution transformers, the number and list of power outage demands, etc.

[0148] It should be noted that the problem data at the site level includes:

[0149] Asset scale information, mainly reflected in the number of transformers, the capacity of transformers, the number of switches of each voltage level, the number of 10kV feeders, etc.;

[0150] Load and user information, mainly reflected in the current load, this year's load peak, the same period load, the number of users, the number and list of important and sensitive users, etc.;

[0151] Overload information, including whether there is main transformer overload, list, the number and list of overload lines above 35kV, the number and list of 10kV overload lines, the number and list of 10kV overload distribution transformers, the number of overload days and the maximum load, the duration, etc.;

[0152] Low voltage information, mainly reflected in the number and list of low voltage busbars, the number and list of low voltage substations, the number and list of low voltage customers, the low voltage demands and list, etc.;

[0153] Project situation, mainly reflected in the project situation, etc.; Workload information, mainly reflected in the number of construction works of infrastructure and production types ((within the substation + distribution transformers of lower-level lines);

[0154] Power outage information, mainly reflected in the number and list of power outage main transformers, the number and list of power outage lines, the number and list of power outage 10kV feeders, the number and list of power outage 10kV distribution transformers, the number and list of power outage demands, etc.

[0155] It should be noted that the problem data at the branch line level includes:

[0156] Asset scale information, mainly reflected in the name of the superior substation, line details, the number of lower-level distribution transformers, etc.; Load and user information, mainly reflected in the current load, this year's load peak, the same period load, the number of users, the number and list of important and sensitive users, etc.;

[0157] Overload information, including whether the superior main transformer is overloaded, whether this feeder is overloaded, the number and list of 10kV overload distribution transformers, the number of overload days and the maximum load, the duration, etc.; Low voltage information, mainly reflected in whether the connected busbar is of low voltage, the number and list of low voltage substations, the number and list of low voltage customers, the low voltage demands and list, etc.;

[0158] Project situation, mainly reflected in the project situation, etc.; Workload information, mainly reflected in the number of construction works of infrastructure and production types ((within the substation + distribution transformers of lower-level lines);

[0159] Power outage information, mainly reflected in the number and list of power outage main transformers, the number and list of power outage lines, the number and list of power outage 10kV feeders, the number and list of power outage 10kV distribution transformers, the number and list of power outage demands, etc.

[0160] It should be noted that the problem data at the substation level includes:

[0161] Equipment ledger information, mainly reflected in the production year, sectional switch, branch line, wire diameter, line length, switch setting value, reactive power compensation device, etc.;

[0162] Equipment monitoring information is mainly reflected in voltage and current data, load rate, three-phase unbalance rate, etc.; customer information is mainly reflected in customer files, customer demand information, power consumption information, etc.

[0163] Project information is mainly reflected in project basic information, project progress information, etc.

[0164] Supplementary information is mainly reflected in operation information, line loss information, location of key users, etc.

[0165] Among them, the y represents different production links of production operation, power consumption planning, infrastructure power consumption, business expansion, and artificial customer service that appear according to different production links of the grid equipment.

[0166] Define the data corresponding to the production operation link in the problem data as a x1 ;

[0167] Define the data corresponding to the power consumption planning link in the problem data as a x2 ;

[0168] Define the data corresponding to the infrastructure power consumption link in the problem data as a x3 ;

[0169] Define the data corresponding to the business expansion link in the problem data as a x4 ;

[0170] Define the data corresponding to the artificial customer service link in the problem data as a x5 ;

[0171] Define the data corresponding to the district / county level in the problem data as a 1y ;

[0172] Define the data corresponding to the site level in the problem data as a 2y ;

[0173] Define the data corresponding to the branch line level in the problem data as a 3y ;

[0174] Define the data corresponding to the substation level in the problem data as a 4y ;

[0175] Define the data corresponding to the electricity meter level in the problem data as a 5y 。

[0176] Specifically, the analysis and calculation module 02 includes: a monitoring unit, a correction and comparison unit, a conversion unit, and an identification unit. The monitoring unit is used to monitor the real-time data of the power grid equipment during operation; the correction and comparison unit is used to perform correction calculations on the real-time data to generate corrected real-time data; and is used to perform comparison calculations on the corrected real-time data and the problem data in the problem database; the conversion unit is used to identify potential hazard data in the corrected real-time data and convert the potential hazard data into risk problems; the identification unit is used to identify the group where the risk problem is located according to the group where the problem data is located.

[0177] Specifically, the working processes of the correction unit and the comparison unit are as follows:

[0178] Call the operation data;

[0179] Operate and correct the operation data into the corrected operation data; the operation formula for operating and correcting the operation data into the corrected operation data is as follows:

[0180] Define the real-time data as A xy ;

[0181] Define the corrected real-time data as A' xy ;

[0182] A' xy = γ * A xy ;

[0183]

[0184] d i = x - y;

[0185] Where γ is the correction coefficient; n is the total number of times of the problem data; d i is the difference between x and y;

[0186] It should be noted that due to inaccurate measurement or real-time error of the operation data, a correction system is introduced to correct the magnitude of the operation data, so that the corrected operation data is more stable and accurate.

[0187] Compare A' xy with a xy and perform a comparison calculation. Define A as a risk problem, and the calculation method is as follows:

[0188]

[0189] When A ≥ U, the potential hazard data is identified;

[0190] When A < U, it is determined that there is no potential hazard data.

[0191] It should be noted that the corrected real-time data is used here to compare with four-fifths of the problem data, so that when the corrected real-time data is close to the problem data, an alarm or reminder will be generated, enabling problems to be detected in a timely manner before they occur, and taking precautions. The * in the formula represents the multiplication sign.

[0192] As Figure 5 shown, Embodiment 3 of the present invention provides a system for identifying power grid equipment problem requirements based on artificial intelligence, which includes: a device 0331 for identifying power grid equipment problem requirements based on artificial intelligence and a terminal device 0332, and the terminal device 0332 is electrically connected to the device 0331 for identifying power grid equipment problem requirements based on artificial intelligence; the terminal device 0332 includes a display 03321 and a processor 03322, and the display 03321 is used to display risk problems; the processor 03322 is electrically connected to the display 03321, and the processor 03322 is used to call the analysis and calculation module.

[0193] Embodiment 4 of the present invention provides a non-volatile storage medium, which stores multiple instructions, and the instructions are suitable for being loaded and executed by a processor to perform the above-provided method for identifying power grid equipment problem requirements based on artificial intelligence.

[0194] From the above description, it can be seen that the above embodiments of the present invention achieve the following technical effects: by establishing a complete power grid risk problem database, then monitoring the data that appears during the actual operation of the power grid equipment and converting it into risk problems. Comparing the risk problems with the data in the power grid risk problem database, and promptly solving the problems that are about to occur, achieving the technical effect of taking precautions.

[0195] It should be noted that the terms used here are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present application. As used here, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or their combinations.

[0196] Unless otherwise specifically stated, the relative arrangements, numerical expressions, and numerical values of the components and steps set forth in these embodiments do not limit the scope of the present application. At the same time, it should be understood that, for ease of description, the dimensions of the various parts shown in the drawings are not drawn in actual proportional relationships. Technologies, methods, and devices known to those of ordinary skill in the relevant art may not be discussed in detail, but where appropriate, the said technologies, methods, and devices should be regarded as part of the description. In all the examples shown and discussed here, any specific values should be construed as merely exemplary and not as a limitation. Therefore, other examples of the exemplary embodiments may have different values. It should be noted that like reference numerals and letters denote like items in the following drawings, and thus, once an item is defined in one drawing, further discussion thereof is not required in subsequent drawings.

[0197] In the description of the present application, it should be understood that the orientation or positional relationships indicated by orientation terms such as "front, rear, upper, lower, left, right", "lateral, vertical, perpendicular, horizontal", and "top, bottom", etc. are generally based on the orientation or positional relationships shown in the drawings, and are only for the convenience of describing the present application and simplifying the description. Without contrary statements, these orientation terms do not indicate and imply that the device or element referred to must have a specific orientation or be constructed and operated in a specific orientation, and thus should not be construed as limiting the protection scope of the present application; the orientation terms "inside, outside" refer to the inside and outside relative to the contour of each component itself.

[0198] For ease of description, spatial relative terms such as "above", "over", "on the upper surface", "upper", etc. may be used here to describe the spatial positional relationship of one device or feature to other devices or features as shown in the drawings. It should be understood that the spatial relative terms are intended to encompass different orientations in use or operation in addition to the orientation depicted in the drawings for the device. For example, if the device in the drawing is inverted, the device described as "above" or "over" other devices or structures will then be positioned "below" or "under" other devices or structures. Thus, the exemplary term "above" can include both the orientations of "above" and "below". The device can also be positioned in other different ways (rotated 90 degrees or in other orientations), and corresponding interpretations should be made for the spatial relative descriptions used here.

[0199] In addition, it should be noted that the use of terms such as "first", "second", etc. to limit components is only for the convenience of distinguishing the corresponding components. Without additional statements, the above terms have no special meanings, and thus should not be construed as limiting the protection scope of the present application.

[0200] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, various modifications and variations can be made to the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. An artificial intelligence-based method for identifying power grid equipment problem requirements, characterized in that, Including: Establishing a risk problem database for power grid equipment; Real-time monitoring of the operation data of the power grid equipment, screening out potential hazard data from the operation data, and converting the potential hazard data into corresponding potential hazard risk problems; Conducting a diversion process on the potential hazard risk problems, and cleaning the potential hazard risk problems after the diversion process; The establishing of the risk problem database for power grid equipment includes: Collecting the problem data of the power grid equipment; Combining and classifying the problem data according to at least two different classification methods to obtain problem data packets of different categories; Summarizing the problem data packets of different categories to obtain the risk problem database; The combining and classifying the problem data according to at least two different classification methods to obtain problem data packets of different categories includes: Conducting combination classification according to the application scenarios of the power grid equipment and the administrative levels to which the power grid equipment belongs; the application scenarios of the power grid equipment include: production operation, power consumption planning, infrastructure power consumption, business expansion, and artificial customer service; the administrative levels of the power grid equipment include district and county levels, site levels, branch line levels, substation levels, and meter levels; Combining any link in the application scenarios of the power grid equipment with any level in the administrative levels of the power grid equipment to form a combined category, and classifying the problem data into problem data packets of different categories according to the combined category; The summarizing the problem data packets of different categories to obtain the risk problem database includes: Define the problem data as a xy , where x represents classification according to the administrative level of the power grid equipment, and the administrative level includes the district / county level, the site level, the branch line level, the substation level, and the electricity meter level; y represents classification according to the production link of the power grid equipment, and the production link includes production operation, electricity consumption planning, infrastructure electricity consumption, business expansion, and artificial customer service; Define the data in the problem data corresponding to the production operation link as a x1 ; Define the data in the problem data corresponding to the link of the power consumption plan as a x2 ; Define the data corresponding to the infrastructure power consumption link in the problem data as a x3 ; Define the data in the problem data corresponding to the link of the business expansion as a x4 ; Define the data corresponding to the link of the artificial customer service in the problem data as a x5 ; Define the data corresponding to the district / county level in the problem data as a 1y ; Define the data corresponding to the site level in the problem data as a 2y ; Define the data corresponding to the branch level in the problem data as a 3y ; Define the data corresponding to the substation level in the problem data as a 4y ; Define the data corresponding to the meter level in the problem data as a 5y ; Sorting the problem data in a matrix form to form the problem database; Wherein, the matrix form of the problem data is: The monitoring of the operation data of the power grid equipment, screening out potential hazard data from the operation data, and converting the potential hazard data into corresponding potential hazard risk problems includes: Monitoring the operation data of the power grid equipment during the operation process; Performing a correction calculation on the operation data to generate corrected operation data; comparing and calculating the corrected operation data with the problem data in the problem database; Identifying the potential hazard data existing in the corrected operation data, and converting the potential hazard data into corresponding potential hazard risk problems; Identifying the group where the potential hazard risk problem is located according to the group where the problem data corresponding to the potential hazard data is located; The performing a correction calculation on the operation data to generate corrected operation data includes: Invoking the operation data; Calculating and correcting the operation data into the corrected operation data; the operation formula for calculating and correcting the operation data into the corrected operation data is as follows: Define the operating data as A xy ; Define the corrected operating data as A′ xy ; A′ xy = γ * A xy ; d i = x - y; Among them, γ is the correction coefficient; n is the total number of times of the problem data; d i is the a xy between x in and the a xy difference between y in 2. The method for identifying power grid equipment problem requirements based on artificial intelligence according to claim 1, characterized in that The collecting the problem data of the power grid equipment includes: Collecting the problem data of the power grid equipment during production operation, power consumption planning, infrastructure power consumption, business expansion, and artificial customer service, and storing it in the cloud or storage device.

3. The method for identifying power grid equipment problem requirements based on artificial intelligence according to claim 1, characterized in that The comparing and calculating the corrected operation data with the problem data in the problem database includes: Compare A' xy with a xy and perform a comparative calculation. Define A as the risk parameter value corresponding to the risk issue. The calculation method is as follows: When A≥0, determining that the corresponding corrected operation data is the potential hazard data; When A < 0, it is determined that the corresponding corrected operation data is not potential hazard data.

4. A device for identifying problem requirements of power grid equipment based on artificial intelligence, characterized in that, The device is applicable to the artificial intelligence-based power grid equipment problem requirement identification method according to any one of claims 1 to 3. The device includes: A problem database module for storing power grid risk problems and forming a power grid risk problem database; An analysis and calculation module for monitoring the operation data of the power grid equipment in real time, screening out potential hazard data from the operation data, and converting the potential hazard data into potential hazard risk problems corresponding to the potential hazard data; A shunt module for shunting the risk problems and then cleaning the risk problems after the shunting process.

5. A non-volatile storage medium, characterized in that, The non-volatile storage medium stores multiple instructions, and the instructions are applicable to be loaded and executed by a processor for the artificial intelligence-based power grid equipment problem requirement identification method according to any one of claims 1 to 3.

Images