Power grid equipment inspection scheme generation method and system, storage medium and electronic equipment

Abstract

The invention provides a power grid equipment inspection scheme generation method and system, a storage medium and electronic equipment, and the method comprises the steps: obtaining the current operation data, the current environment data and the equipment number of target power grid equipment every first preset time, according to the device number, historical fault data and a device type corresponding to the target power grid device are called from a preset database; constructing an inspection scheme generation model, and obtaining predicted inspection times and at least one predicted inspection item based on the inspection scheme generation model; and obtaining an actual inspection frequency and at least one actual inspection item, and updating the inspection scheme generation model according to the actual inspection frequency and the actual inspection item. Dynamic adjustment and personalized customization of power grid equipment inspection can be realized, so that resource configuration is optimized, the operation and maintenance cost is reduced, the reliability of equipment is improved, and the service life of the equipment is prolonged.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid equipment inspection, and in particular to a method, system, storage medium and electronic device for generating a power grid equipment inspection plan. Background Art

[0002] The technical inspection plan for power grid equipment is an important guarantee to ensure the normal operation of equipment and the safety of the power grid. Existing technical inspection plans are usually manually compiled by experts or technicians, relying on experience and judgment, and are difficult to cope with the complex failure modes and changing operating environments of equipment. Therefore, the existing plans have certain lags and inflexibility, and often cannot adapt to changes in equipment status in real time, which in turn affects the operation and maintenance efficiency, fault prevention and equipment reliability of power grid equipment.

[0003] Therefore, with the intelligent development of power systems, how to optimize technical inspection plans through automation and intelligent means and improve the accuracy and dynamic adaptability of power grid equipment management has become a technical problem to be solved. Summary of the invention

[0004] The purpose of the present invention is to provide a method, system, storage medium and electronic device for generating an inspection plan for power grid equipment, aiming to solve the problem that the traditional way of generating inspection plans cannot adapt to changes in equipment status in real time, thereby affecting the operation and maintenance efficiency, fault prevention and equipment reliability of power grid equipment.

[0005] In a first aspect, the present invention provides a method for generating a power grid equipment inspection plan, the method comprising:

[0006] Acquire current operation data, current environment data and device number of the target power grid device at a first preset time interval, and retrieve historical fault data and device type corresponding to the target power grid device from a preset database according to the device number;

[0007] Constructing an inspection plan generation model according to the operation data, the environmental data, the historical fault data and the equipment type in the kth cycle, and obtaining the predicted inspection number and at least one predicted inspection item of the target power grid equipment in the kth cycle based on the inspection plan generation model;

[0008] Obtaining the actual number of inspections and at least one actual inspection item selected by the operation and maintenance personnel in the kth cycle, and updating the inspection plan generation model according to the actual number of inspections and the actual inspection items;

[0009] The operating data, environmental data, historical fault data and equipment type in the k+1th cycle are input into the updated inspection plan generation model to obtain the predicted inspection times and at least one predicted inspection item of the target power grid equipment in the k+1th cycle.

[0010] In summary, according to the above-mentioned power grid equipment inspection plan generation method, by combining the real-time monitoring data of the power grid equipment, such as historical fault data, environmental data and equipment operation data, etc., an inspection plan generation model is constructed that can take into account the structural and functional characteristics of different equipment, and then the inspection plan of the target power grid equipment is obtained in a targeted manner to ensure the comprehensiveness and effectiveness of the inspection content; in addition, the inspection plan generation model is updated in real time based on the inspection feedback results of the equipment, thereby ensuring the continuous optimization and precision of the inspection plan.

[0011] Further, the step of constructing an inspection scheme generation model according to the operation data, the environmental data, the historical fault data and the equipment type in the kth cycle, and obtaining the predicted inspection number and at least one predicted inspection item of the target power grid equipment in the kth cycle based on the inspection scheme generation model includes:

[0012] The inspection plan generation model is constructed according to the following formula:

[0013] F=α·f D (D)+β·f E (E)+δ·f H (H)+γ·f s (S)

[0014] P i =p 1×n (D)·p n×1 (E)·p 1×k (H)·p k×n (FM)·p n×1 (S)

[0015] Among them, F represents the predicted inspection times, f D (D) represents the influence function of the equipment type factor, f E (E) represents the influence function of environmental factors, f H (H) represents the influence function of historical failure factors, f s (S) represents the influence function of the operating status factor, α, β, δ, γ represent the weight coefficients of the corresponding factors, P i represents the score of the i-th inspection item, p 1×n (D) represents the score matrix of the device type factor, p n×1 (E) represents the scoring matrix of environmental factors, p 1×k (H) represents the score matrix of historical failure factors, p k×n (FM) represents the score matrix of failure mode factors, p n×1 (S) represents the score matrix of the operating status factors.

[0016] Further, the step of constructing an inspection scheme generation model according to the operating data, the environmental data, the historical fault data and the equipment type in the kth cycle, and obtaining the predicted inspection number and at least one predicted inspection item of the target power grid equipment in the kth cycle based on the inspection scheme generation model also includes:

[0017] Determine whether the score of the inspection item is greater than a first preset score threshold;

[0018] If the score of the inspection item is greater than the first preset score threshold, the inspection item is determined to be a predicted inspection item.

[0019] Traverse the scores of all inspection items and obtain all predicted inspection items.

[0020] Furthermore, the influence function of the device type factor is obtained according to the following formula:

[0021]

[0022] Among them, α1, α2, and a3 all represent the polynomial weight coefficients of the device type factor, and D represents the identifier of the device type factor. represents the impact of equipment age on inspection frequency, λ i represents the annual decay factor of the i-th stage, and n represents the total number of stages;

[0023] The influence function of environmental factors is obtained according to the following formula

[0024]

[0025] Among them, T env Indicates the average temperature of the environment where the device is located, T optimal It represents a standard temperature set according to the equipment design requirements. μ1, μ2, and μ3 all represent the climate impact weights. T represents the nonlinear influence coefficient of temperature deviation on the number of inspections, C represents the climate conditions in the area where the target power grid equipment is located, and H altitude Indicates the altitude of the target power grid equipment, η H Indicates the influence coefficient related to the altitude influence coefficient;

[0026] The influence function of historical fault factors is obtained according to the following formula:

[0027] f H (H) = η1·log(1+H1)+η2·H2 θ

[0028] Among them, H1 represents the frequency of target power grid equipment failure, H2 represents the most serious degree of target power grid equipment in historical failures, η1 and η2 represent the weight coefficients of the impact of historical failure records on the number of inspections, θ represents the parameter of the intensity of the influence of the adjustment function, log(1+H1) is used to simulate the decreasing effect of historical equipment failures on the inspection frequency, and H2 θ Indicates the impact of the severity of the fault on the number of inspections;

[0029] The influence function of the operating status factor is obtained according to the following formula:

[0030]

[0031] Among them, S i is the i-th operating state of the target power grid equipment, S1 is normal operation, S2 is overload operation, S3 is underload operation, S4 is shutdown state, S5 is fault state, μ i Represents the weight of the i-th running state.

[0032] Furthermore, the score matrix of the device type factor is obtained according to the following formula:

[0033] p 1×n (D) = [N1, N2, ..., N i ]

[0034] If the i-th inspection item is applicable to the equipment type of the target power grid equipment, then N i is 1, if the i-th check item is not applicable to the device type of the target power grid device, then N i is 0;

[0035] The scoring matrix of environmental factors is obtained according to the following formula:

[0036] p n×1 (E) = [E1, E2, ..., E i , E n ] T

[0037] If the i-th inspection item is applicable to the climate environment where the target power grid equipment is located, then E i is 1, if the i-th inspection item is not applicable to the climate environment where the target power grid equipment is located, then E i is 0, T represents the transpose of the matrix;

[0038] The score matrix of the operating status factors is obtained according to the following formula:

[0039] p n×1 (S) = [S1, S2, ..., S n ] T

[0040] If the i-th inspection item is applicable to the operating status of the target power grid equipment, then S n is 1, if the i-th inspection item is not applicable to the operating status of the target power grid equipment, then S n is 0;

[0041] The score matrix of historical failure factors is obtained according to the following formula:

[0042] p 1×k (H) = k1[M1, M2, ..., M k ]+k2[N1,N2,…,N k ]+[S1,S2,…,S k ]

[0043] Among them, M k Respectively represent the frequency of the kth failure mode in history, N k It represents the feedback score of the kth predictive inspection item implemented in the last inspection. If the implemented predictive inspection item detects a problem, the score is 1; if the predictive inspection item is not implemented, the score is 0; if the implemented predictive inspection item does not detect a problem, the score is -1. k represents the kth fault mode, k1 represents the historical fault weight coefficient, and k2 represents the inspection item feedback weight coefficient;

[0044] The scoring matrix of past failure mode factors is based on the following formula:

[0045]

[0046] Among them, S k×n is the normalized cosine similarity score between the k-th fault mode and the n-th inspection item:

[0047]

[0048] and They represent the semantic feature vectors of the kth failure mode and the nth inspection item respectively.

[0049] Furthermore, the step of obtaining the actual number of inspections and at least one actual inspection item selected by the operation and maintenance personnel in the kth cycle, and updating the inspection plan generation model according to the actual number of inspections and the actual inspection items includes:

[0050] After each inspection, p is updated according to the inspection results of the actual inspection items. 1×k (H) and the frequency M and feedback score N of the historical fault mode, and upload the latest fault data about the target power grid equipment to update f according to the fault data H(H) includes the frequency H1 of target grid equipment failure and the most serious degree H2 of target grid equipment failure in history.

[0051] In a second aspect, the present invention provides a system for generating a power grid equipment inspection plan, the system comprising:

[0052] A data acquisition module, used to obtain the current operation data, current environment data and device number of the target power grid device at a first preset time interval, and retrieve the historical fault data and device type corresponding to the target power grid device from a preset database according to the device number;

[0053] A first inspection plan generation module is used to build an inspection plan generation model according to the operation data, the environmental data, the historical fault data and the equipment type in the kth cycle, and obtain the predicted inspection number and at least one predicted inspection item of the target power grid equipment in the kth cycle based on the inspection plan generation model;

[0054] A model updating module, used to obtain the actual number of inspections and at least one actual inspection item selected by the operation and maintenance personnel in the kth cycle, and update the inspection plan generation model according to the actual number of inspections and the actual inspection items;

[0055] The second inspection plan generation module is used to input the operating data, environmental data, historical fault data and equipment type in the k+1th cycle into the updated inspection plan generation model to obtain the predicted inspection times and at least one predicted inspection item of the target power grid equipment in the k+1th cycle.

[0056] In a third aspect, the present invention provides a storage medium, wherein the storage medium stores one or more programs, which, when executed by a processor, implement the above-mentioned method for generating a power grid equipment inspection plan.

[0057] In a fourth aspect, the present invention provides an electronic device, the electronic device comprising a memory and a processor, wherein:

[0058] The memory is used to store computer programs;

[0059] When the processor is used to execute the computer program stored in the memory, the above-mentioned method for generating a power grid equipment inspection plan is implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 A flowchart of a method for generating a power grid equipment inspection plan according to an embodiment of the present invention;

[0061] Figure 2 The present invention is a schematic diagram of the structure of a system for generating a power grid equipment inspection plan according to an embodiment of the present invention.

[0062] The following specific implementation manner will further illustrate the present invention in conjunction with the above-mentioned drawings. DETAILED DESCRIPTION

[0063] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below. Obviously, the described embodiments are 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. Unless otherwise defined, the technical terms or scientific terms used herein should be understood by people with general skills in the field to which the present invention belongs. "Including" and similar words used in this article mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects.

[0064] like Figure 1 As shown, an embodiment of the present invention provides a method for generating a power grid equipment inspection plan, the method comprising steps S101 to S104, wherein:

[0065] Step S101: acquiring current operation data, current environment data and device number of a target power grid device at a first preset time interval, and retrieving historical fault data and device type corresponding to the target power grid device from a preset database according to the device number;

[0066] It should be noted that the purpose of setting the first preset time is to continuously monitor the target power grid equipment in real time, so as to continuously adjust the inspection plan in real time according to the relevant data of the target power grid equipment.

[0067] In addition, illustratively, in some embodiments, various relevant data and operation data of the target power grid equipment are collected through a variety of sensors, monitoring equipment and external environmental data sources. After the relevant data are collected, these data need to be pre-processed. These data will be processed by denoising, formatting, missing value filling, standardization, etc. to ensure the integrity, accuracy and consistency of the data, and provide reliable data support for the subsequent solution generation.

[0068] Furthermore, the preset database includes a variety of power grid equipment and historical fault data and equipment types corresponding to each power grid equipment, so as to quickly generate an inspection plan based on the preset database. In addition, the preset database also includes a rule base corresponding to each type of data, as follows:

[0069] Equipment type rules: Different technical inspection plans are set for different types of power grid equipment, such as transformers, circuit breakers, and power distribution equipment. Each equipment type will define the corresponding inspection frequency, inspection items, etc. in the rule base based on its working principle and common failure mode.

[0070] Environmental Conditions Rules: For different environments where the equipment is located, such as cold, humid, and windy, corresponding adjustment plans are defined in the rule base. For example, in a low-temperature environment, the equipment may need additional inspection frequency, and temperature-related inspection items will be set in the rule base.

[0071] Historical fault record rules: Based on the historical fault data of power grid equipment, such as whether equipment has ever experienced overheating, short circuit, corrosion, etc., a corresponding technical inspection plan is set for each type of equipment in the rule base. For equipment with frequent failures, the system will automatically increase the inspection frequency. If a similar failure has occurred in the equipment history, the rule base will recommend corresponding inspection items based on historical failures.

[0072] Operation status rules: According to the different operation status of power grid equipment, such as normal, overload, shutdown, etc., the corresponding technical inspection scheme will be defined in the rule base. When the equipment is in failure mode, the system will automatically increase the inspection frequency and select inspection items according to the health status of the equipment.

[0073] Failure mode rules: Based on the different failure modes that may occur in the equipment, such as mechanical failure, appearance failure, internal failure, failure caused by environmental factors, etc., the corresponding technical inspection plans are defined in the rule base. According to different failure modes, the rule base sets corresponding inspection items.

[0074] Step S102: constructing an inspection plan generation model according to the operation data, the environmental data, the historical fault data and the equipment type in the kth cycle, and obtaining the predicted inspection number and at least one predicted inspection item of the target power grid equipment in the kth cycle based on the inspection plan generation model;

[0075] In this step, the inspection plan generation model is constructed according to the following formula:

[0076] F=α·f D (D)+β·f E (E)+δ·f H (H)+γ·f s (S)

[0077] P i =p 1×n (D)·p n×1 (E)·p 1×k (H)·p k×n (FM)·p n×1(S)

[0078] Among them, F represents the predicted inspection frequency, in units of times / month or times / year. Regarding the above generation model, D is the equipment type, E is the environment in which the equipment is located, such as high temperature, humidity, high altitude, etc., H is the frequency of historical equipment failures, such as high frequency, medium frequency, and low frequency, S is the operating status of the equipment, such as normal, overload, underload, fault, etc., f D (D) represents the influence function of the equipment type factor, f E (E) represents the influence function of environmental factors, f H (H) represents the influence function of historical failure factors, f s (S) represents the influence function of the operating status factor, α, β, δ, and γ represent the weight coefficients of the corresponding factors, that is, the influence of each factor on the inspection frequency. These coefficients can be determined by historical data or expert experience. i represents the score of the i-th inspection item, p 1×n (D) represents the score matrix of the device type factor, p n×1 (E) represents the scoring matrix of environmental factors, p 1×k (H) represents the score matrix of historical failure factors, p k×n (FM) represents the score matrix of failure mode factors, p n×1 (S) represents the score matrix of the operating status factor, about P i The n in the algorithm represents the selected inspection item set, that is, the total number of inspection items, which usually includes multiple inspection items, such as temperature inspection, appearance inspection, operating voltage, current inspection, protection device inspection, oil leakage inspection, etc.

[0079] In summary, designing the calculation method of the inspection frequency and inspection items of power grid equipment by integrating equipment type rules, environmental condition rules, historical fault record rules, operating status rules and failure mode rules is a comprehensive and systematic equipment management strategy that can maximize the accuracy and flexibility of the inspection plan.

[0080] Specifically, the equipment type rule ensures that targeted inspection content is formulated according to the structure and functional characteristics of different equipment; the environmental condition rule can take into account the impact of the equipment's environment, such as high temperature, humidity or high altitude, and thus adjust the inspection frequency and items; the historical fault record rule identifies potential high-risk equipment through the equipment's fault history data, increases the inspection frequency in a targeted manner, and avoids the recurrence of faults; the operating status rule enables the inspection plan to be dynamically adjusted according to the equipment's operating status, ensuring timely attention to faulty equipment; and the failure mode rule identifies potential problems in advance by analyzing the types of failures that may occur in the equipment, ensuring the comprehensiveness and effectiveness of the inspection content.

[0081] This approach of comprehensively considering multiple factors can not only improve the efficiency and accuracy of inspections, but also achieve dynamic adjustment and personalized customization, thereby optimizing resource allocation, reducing operation and maintenance costs, and improving equipment reliability and service life. At the same time, the integration of multi-dimensional information can help operation and maintenance personnel make more scientific and reasonable decisions when formulating inspection plans, and effectively avoid the risks caused by excessive or insufficient inspections of equipment.

[0082] In addition, in some embodiments, in order to obtain the inspection items that need to be implemented, after obtaining the score of each inspection item according to the above model, it is necessary to determine whether the score of the inspection item is greater than the first preset score threshold; if the score of the inspection item is greater than the first preset score threshold, the inspection item is determined to be a predicted inspection item; the scores of all inspection items are traversed to obtain all predicted inspection items. In other words, all the predicted inspection items finally obtained are inspection items with higher scores.

[0083] In addition, in some embodiments, the influence function of the device type factor is obtained according to the following formula:

[0084]

[0085] Among them, α1, α2, and a3 all represent the polynomial weighted coefficients of the equipment type factor, which are used to adjust the impact of the equipment type on the inspection frequency (number of inspections) and reflect the nonlinear impact of different equipment on the inspection demand. D represents the identifier of the equipment type factor, that is, each device will be assigned a specific value according to its different types (such as transformers, circuit breakers, distribution equipment, etc.). Indicates the impact of equipment age on inspection frequency. This part uses an exponential decay model to represent the impact of equipment age on inspection frequency. As the equipment age increases, the inspection frequency will increase. i represents the annual attenuation factor of the i-th stage, that is, the influence of age on the inspection frequency. As the age of the equipment increases, this value will gradually slow down the increase in inspection frequency. D (D) The n in the algorithm represents the total number of stages, γ i It represents the coefficient related to the equipment type, that is, the specific impact of the equipment age on the inspection frequency. It can be determined through historical data, industry experience, etc. For example, 0 to 5 years, 5 to 10 years, and 10 to 15 years are used as the division stages. Different age periods have different attenuation factors and weight coefficients.

[0086] In addition, in some embodiments, the influence function of the environmental factor is obtained according to the following formula:

[0087] f E (E) = μ1·(a T ·|T env -Toptimal |)+μ2·(C)+μ3·exp(-η H ·H altitude )

[0088] Among them, T env Indicates the average temperature of the environment where the device is located, T optimal It represents a standard temperature set according to the equipment design requirements. μ1, μ2, and μ3 all represent the climate impact weights. T represents the nonlinear influence coefficient of temperature deviation on the number of inspections, C represents the climate conditions in the area where the target power grid equipment is located, such as strong winds, high rainfall, high pollution, etc., all of which are assigned a specific value, and H altitude Indicates the altitude of the target power grid equipment, η H Indicates the influence coefficient related to altitude influence coefficient. The higher the altitude, the worse the equipment's adaptability to the environment, and the inspection frequency needs to be increased.

[0089] In addition, in some embodiments, the influence function of the historical fault factor is obtained according to the following formula:

[0090] f H (H) = η1·log(1+H1)+η2·H2 θ

[0091] Among them, H1 represents the frequency of target power grid equipment failure, H2 represents the most serious degree of historical failure of the target power grid equipment, and its corresponding H2 θ The maximum value of η1 and η2 are the weight coefficients of the impact of historical fault records on the number of inspections, θ is the parameter of the intensity of the influence of the adjustment function, log(1+H1) is used to simulate the decreasing effect of historical equipment faults on the inspection frequency. For the equipment fault records, the initial fault has a greater impact on the inspection frequency, but as the number of faults increases, the impact gradually decreases, H2 θ Indicates the impact of the severity of the fault on the number of inspections. Severe faults will cause the health of the equipment to deteriorate, requiring more inspections to avoid further risks.

[0092] In addition, in some embodiments, the influence function of the operating status factor is obtained according to the following formula:

[0093]

[0094] Among them, S i is the i-th operating state of the target power grid equipment, S1 is normal operation, S2 is overload operation, S3 is underload operation, S4 is shutdown state, S5 is fault state, μ i Represents the weight of the i-th running state.

[0095] In addition, in some embodiments, the score matrix of the device type factor is obtained according to the following formula:

[0096] p 1×n (D) = [N1, N2, ..., N i ]

[0097] If the i-th inspection item is applicable to the equipment type of the target power grid equipment, then N i is 1, if the i-th check item is not applicable to the device type of the target power grid device, then N i is 0.

[0098] Secondly, the scoring matrix of environmental factors is obtained according to the following formula:

[0099] p n×1 (E) = [E1, E2, ..., E n ] T

[0100] If the i-th inspection item is applicable to the climate environment where the target power grid equipment is located, then E i is 1, if the i-th inspection item is not applicable to the climate environment where the target power grid equipment is located, then E i is 0, T represents the transpose of the matrix;

[0101] The score matrix of the operating status factors is obtained according to the following formula:

[0102] p n×1 (S) = [S1, S2, ..., S n ] T

[0103] If the i-th inspection item is applicable to the operating status of the target power grid equipment, then S n is 1, if the i-th inspection item is not applicable to the operating status of the target power grid equipment, then S n is 0.

[0104] In addition, in some embodiments, the score matrix of historical fault factors is obtained according to the following formula:

[0105] p 1×k (H) = k1[M1, M2, ..., M k ]+k[N1,N2,…,N k ]+[S1,S2,…,S k ]

[0106] Among them, M k Respectively represent the frequency of the kth failure mode in history, N kIt represents the feedback score of the kth predictive inspection item implemented in the last (k-1th) inspection. If the implemented predictive inspection item detects a problem, the score is 1; if the predictive inspection item is not implemented, the score is 0; if the implemented predictive inspection item does not detect a problem, the score is -1. k represents the kth fault mode, k1 represents the historical fault weight coefficient, and k2 represents the inspection item feedback weight coefficient;

[0107] The scoring matrix of past failure mode factors is based on the following formula:

[0108]

[0109] Among them, S k×n is the normalized cosine similarity score between the k-th fault mode and the n-th inspection item:

[0110]

[0111] and They represent the semantic feature vectors of the kth failure mode and the nth inspection item respectively.

[0112] Step S103: obtaining the actual number of inspections and at least one actual inspection item selected by the operation and maintenance personnel in the kth cycle, and updating the inspection plan generation model according to the actual number of inspections and the actual inspection items;

[0113] It should be noted that in this step, by introducing an update mechanism to adjust the inspection frequency and inspection item priority in real time based on the inspection feedback results of the equipment, the continuous optimization and precision of the inspection plan can be ensured. After each inspection, the system dynamically updates the weights and priorities in the rule base based on the latest historical fault records, fault severity, feedback scores and other parameters, thereby achieving an accurate assessment of the health status of the equipment. This method based on real-time feedback and incremental learning not only improves inspection efficiency and reduces the occurrence of faults, but also effectively avoids blind inspections and waste of resources, making the maintenance of power grid equipment more intelligent, efficient and reliable.

[0114] Specifically, each time an inspection is completed, p is updated according to the inspection results of the actual inspection items. 1×k (H) and the frequency M and feedback score N of the historical fault mode, and upload the latest fault data about the target power grid equipment to update f according to the fault data H The frequency H1 of target power grid equipment failure in (H) and the most serious degree H2 of target power grid equipment in historical failures are used to update the inspection plan generation model.

[0115] Step S104: input the operating data, environmental data, historical fault data and equipment type in the k+1th cycle into the updated inspection plan generation model to obtain the predicted inspection times and at least one predicted inspection item of the target power grid equipment in the k+1th cycle.

[0116] This step is mainly to illustrate that the solution of this embodiment is to cyclically monitor the target power grid equipment and update the inspection plan generation model in real time according to the latest inspection feedback, so as to achieve dynamic adjustment and personalized customization of the target power grid equipment, thereby optimizing resource allocation, reducing operation and maintenance costs, and improving equipment reliability and service life. At the same time, integrating multi-dimensional information can help operation and maintenance personnel make more scientific and reasonable decisions when formulating inspection plans, and effectively avoid the risks caused by excessive or insufficient inspections of equipment.

[0117] In summary, according to the above-mentioned power grid equipment inspection plan generation method, by combining the real-time monitoring data of the power grid equipment, such as historical fault data, environmental data and equipment operation data, etc., an inspection plan generation model is constructed that can take into account the structural and functional characteristics of different equipment, and then the inspection plan of the target power grid equipment is obtained in a targeted manner to ensure the comprehensiveness and effectiveness of the inspection content; in addition, the inspection plan generation model is updated in real time based on the inspection feedback results of the equipment, thereby ensuring the continuous optimization and precision of the inspection plan.

[0118] like Figure 2 As shown, an embodiment of the present invention further provides a system for generating a power grid equipment inspection plan, the system comprising:

[0119] The data acquisition module 10 is used to obtain the current operation data, current environment data and device number of the target power grid device at a first preset time interval, and retrieve the historical fault data and device type corresponding to the target power grid device from a preset database according to the device number;

[0120] A first inspection plan generation module 20 is used to construct an inspection plan generation model according to the operation data, the environmental data, the historical fault data and the equipment type in the kth cycle, and obtain the predicted inspection number and at least one predicted inspection item of the target power grid equipment in the kth cycle based on the inspection plan generation model;

[0121] The model updating module 30 is used to obtain the actual number of inspections and at least one actual inspection item selected by the operation and maintenance personnel in the kth cycle, and update the inspection plan generation model according to the actual number of inspections and the actual inspection items;

[0122] The second inspection plan generation module 40 is used to input the operating data, environmental data, historical fault data and equipment type in the k+1th cycle into the updated inspection plan generation model to obtain the predicted inspection times and at least one predicted inspection item of the target power grid equipment in the k+1th cycle.

[0123] Another aspect of the present invention further provides a storage medium on which one or more programs are stored, and when the programs are executed by a processor, the above-mentioned method for generating a power grid equipment inspection plan is implemented.

[0124] Another aspect of the present invention further provides an electronic device, comprising a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory to implement the above-mentioned method for generating a power grid equipment inspection plan.

[0125] Those skilled in the art will appreciate that the logic and / or steps represented in the flowchart or otherwise described herein, for example, may be considered as an ordered list of executable instructions for implementing logical functions, and may be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For purposes of this specification, "computer-readable medium" may be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0126] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0127] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or a combination thereof: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0128] Although the embodiments of the present invention are described in detail above, it is obvious to those skilled in the art that various modifications and variations can be made to these embodiments. However, it should be understood that such modifications and variations are within the scope and spirit of the present invention as described in the claims. Moreover, the present invention described herein may have other embodiments and may be implemented or realized in a variety of ways.

Claims

1. A method for generating a power grid equipment inspection plan, characterized in that: The method comprises: Acquire current operation data, current environment data and device number of the target power grid device at a first preset time interval, and retrieve historical fault data and device type corresponding to the target power grid device from a preset database according to the device number; Constructing an inspection plan generation model according to the operation data, the environmental data, the historical fault data and the equipment type in the kth cycle, and obtaining the predicted inspection number and at least one predicted inspection item of the target power grid equipment in the kth cycle based on the inspection plan generation model; Obtaining the actual number of inspections and at least one actual inspection item selected by the operation and maintenance personnel in the kth cycle, and updating the inspection plan generation model according to the actual number of inspections and the actual inspection items; The operating data, environmental data, historical fault data and equipment type in the k+1th cycle are input into the updated inspection plan generation model to obtain the predicted inspection times and at least one predicted inspection item of the target power grid equipment in the k+1th cycle.

2. The method for generating a power grid equipment inspection plan according to claim 1, characterized in that: The step of constructing an inspection scheme generation model according to the operation data, the environmental data, the historical fault data and the equipment type in the kth cycle, and obtaining the predicted inspection number and at least one predicted inspection item of the target power grid equipment in the kth cycle based on the inspection scheme generation model includes: The inspection plan generation model is constructed according to the following formula: F=α·f D (D)+β·f E (E)+δ·f H (H)+γ·f s (S) P i =p 1×n (D)·p n×1 (E)·p 1×k (H)·p k×n (FM)·p n×1 (S) Among them, F represents the predicted inspection times, f D (D) represents the influence function of the equipment type factor, f E (E) represents the influence function of environmental factors, f H (H) represents the influence function of historical failure factors, f s (S) represents the influence function of the operating status factor, α, β, δ, γ represent the weight coefficients of the corresponding factors, P i represents the score of the i-th inspection item, p 1×n (D) represents the score matrix of the device type factor, p n×1 (E) represents the scoring matrix of environmental factors, p 1×k (H) represents the score matrix of historical failure factors, p k×n (FM) represents the score matrix of failure mode factors, p n×1 (S) represents the score matrix of the operating status factors.

3. The method for generating a power grid equipment inspection plan according to claim 2, characterized in that: The step of constructing an inspection scheme generation model according to the operating data, the environmental data, the historical fault data and the equipment type in the kth cycle, and obtaining the predicted inspection number and at least one predicted inspection item of the target power grid equipment in the kth cycle based on the inspection scheme generation model also includes: Determine whether the score of the inspection item is greater than a first preset score threshold; If the score of the inspection item is greater than the first preset score threshold, the inspection item is determined to be a predicted inspection item. Traverse the scores of all inspection items and obtain all predicted inspection items.

4. The method for generating a power grid equipment inspection plan according to claim 3, characterized in that: The influence function of the device type factor is obtained according to the following formula: Among them, α1, α2, and a3 all represent the polynomial weight coefficients of the device type factor, and D represents the identifier of the device type factor. represents the impact of equipment age on inspection frequency, λ i represents the annual decay factor of the i-th stage, n represents the total number of stages, γ i represents the coefficient related to the device type; The influence function of environmental factors is obtained according to the following formula f E (E)=μ1·(a T ·|T env -T optimal |)+μ2·(C)+μ3·exp(-η H ·H altitude ) Among them, T env Indicates the average temperature of the environment where the device is located, T optimal It represents a standard temperature set according to the equipment design requirements. μ1, μ2, and μ3 all represent the climate impact weights. T represents the nonlinear influence coefficient of temperature deviation on the number of inspections, C represents the climate conditions in the area where the target power grid equipment is located, and H altitude Indicates the altitude of the target power grid equipment, η H Indicates the influence coefficient related to the altitude influence coefficient; The influence function of historical fault factors is obtained according to the following formula: f H (H)=η1·log(1+H1)+η2·H2 θ Among them, H1 represents the frequency of target power grid equipment failure, H2 represents the most serious degree of target power grid equipment in historical failures, η1 and η2 represent the weight coefficients of the impact of historical failure records on the number of inspections, θ represents the parameter of the intensity of the influence of the adjustment function, log(1+H1) is used to simulate the decreasing effect of historical equipment failures on the inspection frequency, and H2 θ Indicates the impact of the severity of the fault on the number of inspections; The influence function of the operating status factor is obtained according to the following formula: Among them, S i is the i-th operating state of the target power grid equipment, S1 is normal operation, S2 is overload operation, S3 is underload operation, S4 is shutdown state, S5 is fault state, μ i Represents the weight of the i-th running state.

5. The method for generating a power grid equipment inspection plan according to claim 4, characterized in that: The scoring matrix of the device type factor is obtained according to the following formula p 1×n (D)=[N1,N2,…,N i ] If the i-th inspection item is applicable to the equipment type of the target power grid equipment, then N i is 1, if the i-th check item is not applicable to the device type of the target power grid device, then N i is 0; The scoring matrix of environmental factors is obtained according to the following formula: p n×1 (E)=[E1,E2,…,E i ,THE n ] T If the i-th inspection item is applicable to the climate environment where the target power grid equipment is located, then E i is 1, if the i-th inspection item is not applicable to the climate environment where the target power grid equipment is located, then E i is 0, T represents the transpose of the matrix; The score matrix of the operating status factors is obtained according to the following formula: p n×1 (S)=[S1,S2,…,S n ] T If the i-th inspection item is applicable to the operating status of the target power grid equipment, then S n is 1, if the i-th inspection item is not applicable to the operating status of the target power grid equipment, then S n is 0; The score matrix of historical failure factors is obtained according to the following formula: p 1×k (H)=k1[M1,M2,…,M k ]+k2[N1,N2,…,N k ]+[S1,S2,…,S k ] Among them, M k Respectively represent the frequency of the kth failure mode in history, N k It represents the feedback score of the kth predictive inspection item implemented in the last inspection. If the implemented predictive inspection item detects a problem, the score is 1; if the predictive inspection item is not implemented, the score is 0; if the implemented predictive inspection item does not detect a problem, the score is -1. k represents the kth fault mode, k1 represents the historical fault weight coefficient, and k2 represents the inspection item feedback weight coefficient; The scoring matrix of past failure mode factors is based on the following formula: Among them, S k×n is the normalized cosine similarity score between the k-th fault mode and the n-th inspection item: and They represent the semantic feature vectors of the kth failure mode and the nth inspection item respectively.

6. The method for generating a power grid equipment inspection plan according to claim 5, characterized in that: The step of obtaining the actual number of inspections and at least one actual inspection item selected by the operation and maintenance personnel in the kth cycle, and updating the inspection plan generation model according to the actual number of inspections and the actual inspection items includes: After each inspection, p is updated according to the inspection results of the actual inspection items. 1×k (H) and the frequency M and feedback score N of the historical fault mode, and upload the latest fault data about the target power grid equipment to update f according to the fault data H (H) includes the frequency H1 of target grid equipment failure and the most serious degree H2 of target grid equipment failure in history.

7. A power grid equipment inspection plan generation system, characterized in that: The system comprises: A data acquisition module, used to obtain the current operation data, current environment data and device number of the target power grid device at a first preset time interval, and retrieve the historical fault data and device type corresponding to the target power grid device from a preset database according to the device number; A first inspection plan generation module is used to build an inspection plan generation model according to the operation data, the environmental data, the historical fault data and the equipment type in the kth cycle, and obtain the predicted inspection number and at least one predicted inspection item of the target power grid equipment in the kth cycle based on the inspection plan generation model; A model updating module, used to obtain the actual number of inspections and at least one actual inspection item selected by the operation and maintenance personnel in the kth cycle, and update the inspection plan generation model according to the actual number of inspections and the actual inspection items; The second inspection plan generation module is used to input the operating data, environmental data, historical fault data and equipment type in the k+1th cycle into the updated inspection plan generation model to obtain the predicted inspection times and at least one predicted inspection item of the target power grid equipment in the k+1th cycle.

8. A storage medium, characterized in that: The storage medium stores one or more programs, which, when executed by a processor, implement the method for generating a power grid equipment inspection plan as described in any one of claims 1 to 6.

9. An electronic device, comprising a memory and a processor, wherein: The memory is used to store computer programs; When the processor is used to execute the computer program stored in the memory, it implements the method for generating a power grid equipment inspection plan as described in any one of claims 1-6.

Images