Power grid inspection method and device, computer device and storage medium

Abstract

The application relates to a power grid inspection method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: acquiring an inspection image of a power grid and inspection item information corresponding to the inspection image; determining image category information of the inspection image and defect information of an inspection object in the inspection image according to the inspection image; and generating an inspection report corresponding to the inspection image according to the inspection item information, the image category information and the defect information, so as to realize automatic processing, analysis and management of power grid inspection data and improve the inspection efficiency of the power grid. Since the inspection item information identifies the inspection configuration information of the power grid, the image category information identifies the content category in the inspection image, and the defect information identifies the identification result of the safety hidden danger of the inspection object in the inspection image, the hidden trouble fault in the power grid can be found and positioned in time through the inspection report, so that the stability and safety of the power grid operation are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power grids, and in particular to a power grid inspection method and device, computer equipment and a storage medium. BACKGROUND

[0002] With the continuous expansion of power grid interconnection and the scale of power grids, the safety and stability of power grid operation have attracted much attention. Due to the diverse operating environment of power grid lines, manual inspection is difficult. In addition, as the power grid lines continue to extend, the inspection workload continues to increase, and the demand for inspection resources also increases. Therefore, it is an urgent problem to be solved to realize fine inspection of power grid lines and improve the operation and maintenance efficiency of power grid lines.

[0003] In order to overcome the many defects of manual inspection, unmanned aerial vehicles are applied to the daily inspection work of power grid lines. However, the image data obtained by the unmanned aerial vehicle needs to be transmitted or stored and brought back to the office for manual uploading and processing, which cannot timely discover hidden dangers and leads to low inspection efficiency. SUMMARY

[0004] Therefore, it is necessary to provide a power grid inspection method and device, computer equipment, computer readable storage medium and computer program product capable of improving inspection efficiency in view of the above technical problems.

[0005] In a first aspect, the present application provides a power grid inspection method, comprising:

[0006] obtaining an inspection image of a power grid;

[0007] obtaining inspection item information corresponding to the inspection image; wherein the inspection item information is used to identify the inspection configuration information of the power grid;

[0008] determining image category information of the inspection image and defect information of an inspection object in the inspection image according to the inspection image; wherein the defect information is used to identify the identification result that the inspection object in the inspection image has a safety hidden danger;

[0009] generating an inspection report corresponding to the inspection image according to the inspection item information, the image category information and the defect information.

[0010] In one embodiment, the determination of the image category information of the inspection image according to the inspection image comprises:

[0011] identifying the inspection object in the inspection image by using a preset first image classification algorithm;

[0012] obtaining a historical inspection image and historical inspection information of the historical inspection image according to the inspection object; wherein the historical inspection image comprises the inspection object;

[0013] establishing a correlation between the inspection item information and the historical inspection information;

[0014] determining image category information of the inspection image according to the inspection object and the correlation.

[0015] In one of the embodiments, the determining of the defect information of the inspection object in the inspection image according to the inspection image comprises:

[0016] identifying, by using a preset second image classification algorithm, whether the inspection object in the inspection image has a safety hidden danger;

[0017] In a case where it is determined that the inspection object has a safety hidden danger, it is determined that the inspection object has a defect, and a defect type of the inspection object is determined; wherein the defect type comprises at least one of a device defect type, a device body type, and an external hidden danger type.

[0018] In one of the embodiments, the identifying of whether the inspection object in the inspection image has a safety hidden danger comprises:

[0019] obtaining a historical defect image having the inspection object;

[0020] determining a similarity between the historical defect image and the inspection image;

[0021] In a case where the similarity is greater than a preset threshold, identifying, by using a pre-trained defect identification model, whether the inspection object in the inspection image has a safety hidden danger.

[0022] In one of the embodiments, after the determining of the defect information of the inspection object in the inspection image according to the inspection image is performed, the power grid inspection method further comprises:

[0023] obtaining a defect level of the defect information; wherein the defect level is positively correlated with a maintenance timeliness;

[0024] In a case where the defect level is greater than a preset level, outputting an alarm signal.

[0025] In one of the embodiments, the power grid inspection method further comprises:

[0026] obtaining, according to the inspection item information, a same item inspection image for the power grid and same item inspection information, same item image information, and same item defect information corresponding to the same item inspection image; wherein the same item inspection image and the inspection image have a same item identifier of an inspection item;

[0027] According to the inspection item information, the image category information and the defect information of the inspection image, and the same inspection information, the same image information and the same defect information, a project inspection report corresponding to the inspection item is generated.

[0028] In one of the embodiments, in the case that the defect information indicates that the inspection object has a defect, the power grid inspection method further comprises:

[0029] According to the inspection report, an inspection processing scheme corresponding to a defect type of the inspection object is generated;

[0030] Obtaining scheme execution information of executing the inspection processing scheme;

[0031] According to the scheme execution information, the inspection report is updated.

[0032] In a second aspect, the present application further provides a power grid inspection device, characterized in that comprising:

[0033] The first obtaining module is configured to obtain an inspection image of a power grid.

[0034] The second obtaining module is configured to obtain inspection item information corresponding to the inspection image, wherein the inspection item information is used to identify inspection configuration information of the power grid.

[0035] The determining module is configured to determine image category information of the inspection image and defect information of an inspection object in the inspection image according to the inspection image, wherein the defect information is used to identify an identification result of a safety hazard of the inspection object in the inspection image.

[0036] The generating module is configured to generate an inspection report corresponding to the inspection image according to the inspection item information, the image category information and the defect information.

[0037] In a third aspect, the present application further provides a computer device. The computer device comprises a memory and a processor, the memory stores a computer program, and the processor implements the steps of the method of any one of the above embodiments when executing the computer program.

[0038] In a fourth aspect, the present application further provides a computer readable storage medium. The computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the steps of the method of any one of the above embodiments.

[0039] In a fifth aspect, the present application further provides a computer program product. The computer program product comprises a computer program, and the computer program is executed by a processor to implement the steps of the method of any one of the above embodiments.

[0040] The power grid inspection method, device, computer equipment, storage medium and computer program product can acquire an inspection image of a power grid, acquire inspection item information corresponding to the inspection image, and determine image category information of the inspection image and defect information of an inspection object in the inspection image according to the inspection image, so that a corresponding inspection report of the inspection image can be generated according to the inspection item information, the image category information and the defect information, and automatic processing, analysis and management of power grid inspection data are realized, and the inspection efficiency of the power grid is improved. Since the inspection item information identifies the inspection configuration information of the power grid, the image category information identifies the content category in the inspection image, and the defect information identifies the identification result of the safety hazard of the inspection object in the inspection image, the hidden trouble fault in the power grid can be found and located in time through the inspection report, and therefore the stability and safety of the operation of the power grid are improved. BRIEF DESCRIPTION OF DRAWINGS

[0041] Figure 1 A flowchart of a power grid inspection method in an embodiment is shown;

[0042] Figure 2 A flowchart of a power grid inspection method in another embodiment is shown;

[0043] Figure 3 A flowchart of a power grid inspection method in another embodiment is shown;

[0044] Figure 4 A flowchart of a power grid inspection method in another embodiment is shown;

[0045] Figure 5 A flowchart of a power grid inspection method in another embodiment is shown;

[0046] Figure 6 A flowchart of a power grid inspection method in another embodiment is shown;

[0047] Figure 7 A flowchart of a power grid inspection method in another embodiment is shown;

[0048] Figure 8 A flowchart of a power grid inspection method in another embodiment is shown;

[0049] Figure 9 A flowchart of a power grid inspection method in another embodiment is shown;

[0050] Figure 10 A flowchart of a power grid inspection method in another embodiment is shown;

[0051] Figure 11 A block diagram of a power grid inspection device in an embodiment is shown;

[0052] Figure 12 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0053] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0054] In one embodiment, such as Figure 1 As shown, a power grid inspection method is provided. This method can be applied to any of the following: a terminal, a server, a system where the terminal and server interact, or an intelligent platform. This embodiment does not impose any limitations. The server may include a cloud server or a local server. This embodiment illustrates the application of this method to a terminal. In this embodiment, the power grid inspection method may include the following steps S101 to S104.

[0055] S101: Acquire inspection images of the power grid.

[0056] For example, the inspection equipment can be a smart device with photography capabilities or a smart device with communication and storage capabilities, such as a drone or a camera, without any limitation. For example, the terminal can simultaneously receive inspection images sent by one or more inspection devices, without any limitation.

[0057] S102: Obtain the inspection item information corresponding to the inspection image.

[0058] Inspection project information is used to identify the inspection configuration information of the inspected power grid. Inspection project information may include at least one of the following: voltage level, line name, maintenance team, inspection section, equipment model, analyst, inspection type, reviewer, inspection method, time range, project name, and remarks. For example, after the terminal acquires an inspection image, it can generate inspection project information corresponding to the inspection image based on a preset power grid ledger and the equipment information corresponding to the inspection equipment. The preset power grid ledger may include one or more combinations of project tables, report tables, and data classification tables, without any limitations.

[0059] S103: Based on the inspection images, determine the image category information of the inspection images and the defect information of the inspection objects in the inspection images.

[0060] The image category information can include at least one of scene information, data source information, and an inspection object. The scene information refers to a power grid line to be inspected, and can include a power transmission line and a power distribution line. The data source information refers to a light source of an environment in which the power grid to be inspected is located, and can include visible light and thermal infrared light. The inspection object refers to an object to be inspected, and can include a device and a part in the power grid line, and environmental information near the line that can cause a hidden danger. The defect information is used to identify a recognition result of a hidden danger of the inspection object in the inspection image.

[0061] S104: generating an inspection report corresponding to the inspection image according to the inspection item information, the image category information, and the defect information.

[0062] The power grid inspection method described above, the inspection item information obtained identifies the inspection configuration information of the power grid to be inspected, the image category information determined based on the inspection image identifies the content category in the inspection image, and the defect information determined based on the inspection image identifies the recognition result of the hidden danger of the inspection object in the inspection image. Therefore, the hidden danger fault in the power grid can be found and located in time through the inspection report, thereby improving the stability and safety of the power grid operation, and realizing automatic processing, analysis, and management of the power grid inspection data, and improving the inspection efficiency of the power grid.

[0063] In one embodiment, as shown in FIG. 10, in step S103, the image category information of the inspection image is determined according to the inspection image, which can include steps S201 to S204. Figure 2

[0064] S201: identifying the inspection object in the inspection image by using a preset first image classification algorithm.

[0065] The first image classification algorithm can be one or a combination of K-Nearest Neighbor (KNN), Support Vector Machine (SVM), Back Propagation Neural Network (BP neural network), Convolutional Neural Networks (CNN), and transfer learning, or other image classification algorithms, which are not limited herein.

[0066] S202: obtaining a historical inspection image and historical inspection information of the historical inspection image according to the inspection object.

[0067] ​The historical inspection image includes an inspection object. For example, the terminal can query and obtain the historical inspection image with the inspection object and the historical inspection information of the historical inspection image in the database storing the inspection image according to the inspection object. The historical inspection information is used to identify the historical inspection configuration information of the power grid.

[0068] S203: Establish an association relationship between the inspection item information and the historical inspection information.

[0069] S204: Determine the image category information of the inspection image according to the inspection object and the association relationship.

[0070] The power grid inspection method described above, since the historical inspection image also has an inspection object, when identifying the inspection image, the association relationship between the historical inspection information of the historical inspection image and the inspection item information of the inspection image is used to identify the inspection image, which improves the accuracy of identifying the inspection image, thereby improving the inspection efficiency of the power grid, and also helps to improve the management efficiency of the same inspection object.

[0071] In one embodiment, as shown in FIG. 3, Figure 3 Step S103, determining the defect information of the inspection object in the inspection image according to the inspection image, can include the following steps S301 and S302.

[0072] S301: Use a preset second image classification algorithm to identify whether the inspection object in the inspection image has a safety hazard.

[0073] The second image classification algorithm can be one or a combination of KNN algorithm, SVM algorithm, BP neural network, CNN and transfer learning, or other image classification algorithms, which are not limited here. Identifying whether the inspection object in the inspection image has a safety hazard can be regarded as identifying whether the inspection image is a defect image. The defect image is used to represent the image in which the inspection object has a safety hazard.

[0074] S302: In the case where it is determined that the inspection object has a safety hazard, it is determined that the inspection object has a defect, and the defect type of the inspection object is determined.

[0075] Defect types can include at least one of the following: equipment defects, equipment body defects, and external hazards. Equipment defects refer to defects in power grid ancillary facilities, such as signs, phase markers, warning signs, and various technical testing equipment attached to the line body. These can include signage devices, lightning protection devices, bird protection devices, online insulator testing devices, online temperature measuring devices, and other devices. Equipment body defects refer to defects in the components, accessories, and parts that make up the line body. These can include conductors, ground wires, insulators, hardware, poles, guy wires, grounding devices, foundations, and cables. External hazards refer to situations where the external environment poses a potential threat to the safe operation of the line. These can include wind deflection hazards, crossing hazards, construction hazards, and other hazards.

[0076] If it is determined that an inspected object poses a safety hazard, the defect information includes the existence of a defect in the inspected object and the type of defect. If it is determined that an inspected object does not pose a safety hazard, and it can be concluded that the inspected object is free of defects, then the defect information includes the absence of defects in the inspected object.

[0077] The aforementioned power grid inspection method can identify whether there are safety hazards in the inspected objects in the inspection images, and can also determine the type of defects in the inspected objects, thereby providing a more accurate basis for subsequent handling of potential problems. This is conducive to improving the efficiency and accuracy of handling power grid problems, and further improving the management efficiency of power grid inspection data.

[0078] In one embodiment, such as Figure 4 As shown, step S301, identifying whether there are safety hazards in the inspection object in the inspection image, may include the following steps S401 to S403.

[0079] S401: Obtain historical defect images of the inspected objects.

[0080] Historical defect images refer to images from previous inspections that contain inspected objects and where those objects pose safety hazards. For example, one or more historical defect images can be retrieved from a database based on the inspected objects in the inspection images.

[0081] S402: Determine the similarity between historical defect images and inspection images.

[0082] S403: When the similarity is greater than a preset threshold, a pre-trained defect recognition model is used to identify whether there are safety hazards in the inspection objects in the inspection images.

[0083] The preset threshold is pre-set and can be obtained according to experience or experiment, and is not limited herein. When the similarity between the historical defect image and the inspection image is greater than the preset threshold, it indicates that the similarity between the inspection image and the historical inspection image is high, and the possibility of the inspection object in the inspection image having a safety hazard is large. In this case, the inspection image can be regarded as a suspected defect image, and the inspection object in the inspection image is further identified by using the defect identification model. For example, the suspected defect image in the inspection image can be screened according to image classification information of the inspection image, such as scene information and data source information.

[0084] The defect identification model refers to a neural network model based on artificial intelligence (AI) that is pre-established and trained, and is used to identify whether the inspection object has a safety hazard. The defect identification model can be a CNN model, a deep neural network (DNN) model, a convolutional recurrent neural network (CRNN) model, and the like, and is not limited herein.

[0085] The power grid inspection method described above performs preliminary screening on the inspection image by using the historical defect image, and further identifies the inspection image by using the defect identification model, thereby improving the accuracy of identifying whether the inspection object in the inspection image has a safety hazard, reducing the data volume of model identification, improving the identification efficiency of the inspection image, and thereby improving the inspection efficiency of the power grid.

[0086] In one embodiment, as shown in FIG. 5, after step S103 of determining the defect information of the inspection object in the inspection image according to the inspection image is performed, the power grid inspection method can further include steps S501 and S502. Figure 5

[0087] S501: Obtain a defect level of the defect information.

[0088] The defect level of the inspection object is used to indicate the degree of danger of the inspection object having a safety hazard. The defect level is positively correlated with the maintenance timeliness. A larger defect level indicates a higher degree of danger of the inspection object, and the inspection object urgently needs to be maintained. That is, the maintenance timeliness of the inspection object is higher. A smaller defect level indicates a lower degree of danger of the inspection object, and the maintenance timeliness of the inspection object is lower.

[0089] S502: Output an alarm signal in a case where the defect level is greater than a preset level.

[0090] ​The preset level is preset, and can be determined according to power grid inspection experience and power grid operation conditions, without any limitation. The defect level greater than the preset level indicates that the danger level of the inspection object in the inspection image is higher, the inspection object has an issue that needs to be handled urgently, the maintenance is higher in timeliness, and the inspection object urgently needs to be maintained. The alarm signal is used to notify the staff to quickly handle the inspection object.

[0091] The power grid inspection method can determine the defect information of the inspection object in the inspection image, and can also determine the defect level corresponding to the defect information of the inspection object. When the inspection object has an issue that needs to be handled urgently, the staff can be timely notified to implement emergency measures, the processing efficiency of the inspection issue is improved, and the safety of the power grid operation is further improved.

[0092] In one embodiment, as shown in Figure 6 The power grid inspection method can further include steps S601 and S602.

[0093] S601: According to the inspection item information, the same item inspection image of the power grid and the same item inspection information, same item image information and same item defect information corresponding to the same item inspection image are obtained.

[0094] The same item inspection image has the same project identifier of the inspection project as the inspection image. That is, the same item inspection image and the inspection image are images taken for the same inspection project. The project identifier is used to identify the inspection project, and the inspection project can be set according to the power grid inspection demand, for example, an inspection project is formulated for a certain power transmission line, without any limitation.

[0095] The same item inspection information is used to identify the inspection configuration information of the inspection power grid. The same item image information is used to identify the content category in the same item inspection image. The same item defect information is used to identify the identification result of the safety hidden danger of the inspection object in the same item inspection image.

[0096] S602: According to the inspection project information, image category information and defect information of the inspection image, and the same item inspection information, same item image information and same item defect information, a project inspection report corresponding to the inspection project is generated.

[0097] The power grid inspection method can automatically generate the inspection report of the inspection image, and can also automatically generate the project inspection report of the inspection project corresponding to the inspection image, realizes the automatic statistics and classification of the power grid inspection data, and improves the automatic management level of the power grid inspection data.

[0098] In one embodiment, as shown in Figure 7 The power grid inspection method can further include steps S701 to S703 when the defect information of the inspection object is that the inspection object has a defect.

[0099] S701: generating an inspection processing scheme corresponding to the defect type of the inspection object according to the inspection report.

[0100] For example, the terminal pre-stores the defect type, the inspection processing scheme, and the correspondence between the defect type and the inspection processing scheme. In the case where it is determined that the inspection object in the inspection image has a defect, the inspection processing scheme corresponding to the defect type of the inspection object in the inspection report can be queried according to the defect type. The inspection processing scheme is used to identify a scheme for solving the hidden danger of the inspection object, and can be prepared in advance according to the power grid maintenance experience, which is not limited herein.

[0101] S702: obtaining scheme execution information of executing the inspection processing scheme.

[0102] After the inspection processing scheme is generated based on step S701, the inspection object in the inspection image can be maintained according to the inspection processing scheme. For example, the inspection object can be photographed by using the inspection device to obtain the inspection image corresponding to the inspection object, and then the scheme execution information of executing the inspection processing scheme can be obtained according to the inspection image. The scheme execution information is used to identify the execution progress and execution situation of the inspection processing scheme.

[0103] S703: updating the inspection report according to the scheme execution information.

[0104] The power grid inspection method can generate an inspection processing scheme for an inspection report, and update the records in the inspection report according to the inspection execution information of the inspection processing scheme, so as to track the situation of the inspection object in the inspection image, improve the integrity of the power grid inspection data, improve the integrity of the power grid inspection management process, and improve the management level of the power grid inspection.

[0105] In one embodiment, as shown in Figure 8 The power grid inspection method can further include steps S801 and S802.

[0106] S801: obtaining device information of an inspection device for photographing an inspection image.

[0107] For example, the device information corresponding to the inspection device can be obtained according to the operation of the inspection device. The device information can include one or more combinations of device model, device configuration information, device communication information, device command response information, and log information.

[0108] S802: determining a management operation for the inspection device according to the device information.

[0109] The management operation can include one or more combinations of device addition, device deletion, and device update.

[0110] The aforementioned power grid inspection method can monitor the operation of inspection equipment and take corresponding management measures based on the operation status. It can promptly detect faults in the inspection equipment, improve the safety and stability of the inspection equipment operation, and ensure the reliability and accuracy of the inspection data sent by the inspection equipment.

[0111] In one embodiment, such as Figure 9 As shown, the power grid inspection method may also include the following steps S901 to S903.

[0112] S901: Obtain network status information of the inspection equipment that captures inspection images.

[0113] Network status information is used to identify the current network status of the inspected network, which may include network connection status, data transmission status, etc.

[0114] S902: If the network status information indicates that the inspection equipment is experiencing network abnormalities, adjust the network configuration of the inspection equipment.

[0115] The network status information indicates an abnormal network condition for the inspection equipment, meaning the equipment cannot use the network normally, and data transmission between the terminal and the equipment is not possible. In this situation, the terminal can send adjustment information to the inspection equipment so that the equipment can reconfigure its network accordingly.

[0116] S903: If the number of times the network configuration is adjusted exceeds the preset number, output the maintenance signal corresponding to the network status information.

[0117] The preset number of adjustments can be a value determined in advance based on experience, and no restrictions are imposed here. If the number of network configuration adjustments exceeds the preset number, it indicates that the network cannot be automatically restored to normal operation of the inspection equipment. In this case, manual intervention is required to repair the inspection equipment.

[0118] The aforementioned power grid inspection method can adaptively adjust the network configuration when the network status of the inspection equipment is abnormal. Furthermore, it can output a maintenance signal when the inspection equipment cannot resolve the abnormal network status problem, promptly notifying staff to maintain the inspection equipment. This ensures the reliability of the inspection data transmitted with the inspection equipment, thereby improving the accuracy of power grid inspection data.

[0119] To better understand, combine Figure 10 The power grid inspection method provided in the above embodiments will be introduced. For example... Figure 10 As shown, the power grid inspection method includes the following steps S1001 to S1010.

[0120] S1001: Acquire inspection images of the power grid.

[0121] S1002: Obtain the inspection item information corresponding to the inspection image.

[0122] S1003: Identify the inspection object in the inspection image by using the CNN algorithm, obtain the historical inspection image and the historical inspection information of the historical inspection image, establish the association relationship between the inspection item information and the historical inspection information, and determine the image category information of the inspection image.

[0123] S1004: Identify whether the inspection object in the inspection image has a safety hidden danger by using the KNN algorithm, determine that the inspection object has a defect in the case that the inspection object has a safety hidden danger, and determine the defect type of the inspection object.

[0124] S1005: Obtain the same item inspection image of the power grid, the same item inspection information, the same item image information and the same item defect information corresponding to the same item inspection image according to the inspection item information, and generate the inspection report corresponding to the inspection image and the project inspection report corresponding to the project.

[0125] S1006: Obtain the defect level of the defect information, and output an alarm signal in the case that the defect level is greater than a preset level.

[0126] S1007: In the case that the defect information of the inspection object indicates that the inspection object has a defect, generate the inspection processing scheme corresponding to the defect type of the inspection object according to the inspection report, obtain the scheme execution information of executing the inspection processing scheme, and update the inspection report.

[0127] S1008: Obtain the device information of the inspection device for shooting the inspection image, and determine the management operation of the inspection device according to the device information.

[0128] S1009: Obtain the network state information of the inspection device, adjust the network configuration of the inspection device in the case that the network state information indicates that the network of the inspection device is abnormal, and output a maintenance signal corresponding to the network state information in the case that the number of times of adjusting the network configuration is greater than a preset number of times.

[0129] It should be understood that although each step in the flowchart involved in each embodiment as described above is displayed in sequence according to the arrow, these steps are not necessarily executed in sequence according to the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other sequences. Moreover, at least part of the steps in the flowchart involved in each embodiment as described above can include multiple steps or stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence of these steps or stages is not necessarily sequential, but can be executed in rotation or alternation with at least part of other steps or steps or stages in other steps.

[0130] Based on the same inventive concept, the embodiments of the present application also provide a power grid inspection device for implementing the power grid inspection method described above. The implementation scheme of the device for solving the problem is similar to the implementation scheme described in the above method, so the specific limitations in one embodiment of the power grid inspection device provided below can refer to the limitations of the power grid inspection method described above, which will not be repeated here.

[0131] In one embodiment, as shown in Figure 11 A power grid inspection device 1100 is provided, which includes a first acquisition module 1101, a second acquisition module 1102, a determination module 1103, and a generation module 1104.

[0132] The first acquisition module 1101 is configured to acquire an inspection image of a power grid.

[0133] The second acquisition module 1102 is configured to acquire inspection item information corresponding to the inspection image, wherein the inspection item information is used to identify inspection configuration information for inspecting the power grid.

[0134] The determination module 1103 is configured to determine image category information of the inspection image and defect information of an inspection object in the inspection image according to the inspection image, wherein the defect information is used to identify an identification result of a safety hazard of the inspection object in the inspection image.

[0135] The generation module 1104 is configured to generate an inspection report corresponding to the inspection image according to the inspection item information, the image category information, and the defect information.

[0136] In one embodiment, the determination module 1103 is configured to identify the inspection object in the inspection image by using a preset first image classification algorithm, acquire a historical inspection image and historical inspection information of the historical inspection image according to the inspection object, wherein the historical inspection image includes the inspection object, establish an association relationship between the inspection item information and the historical inspection information, and determine the image category information of the inspection image according to the inspection object and the association relationship.

[0137] In one embodiment, the determination module 1103 is configured to identify whether the inspection object in the inspection image has a safety hazard by using a preset second image classification algorithm, determine that the inspection object has a defect and determine a defect type of the inspection object in a case where it is determined that the inspection object has a safety hazard, wherein the defect type includes at least one of a device defect type, a device body type, and an external hidden danger type.

[0138] In one embodiment, the determining module 1103 is configured to acquire a historical defect image of the inspection object; determine a similarity between the historical defect image and the inspection image; and in a case where the similarity is greater than a preset threshold, use a pre-trained defect recognition model to identify whether the inspection object in the inspection image has a safety hazard.

[0139] In one embodiment, the power grid inspection device 1100 further includes an output module configured to acquire a defect level of the defect information, wherein the defect level is positively correlated with maintenance timeliness; and in a case where the defect level is greater than a preset level, output an alarm signal.

[0140] In one embodiment, the second acquisition module 1102 is configured to acquire, according to the inspection item information, a same-item inspection image of the power grid and same-item inspection information, same-item image information and same-item defect information corresponding to the same-item inspection image, wherein the same-item inspection image has a same item identifier of the inspection item as the inspection image.

[0141] The generating module 1104 is configured to generate an item inspection report corresponding to the inspection item according to the inspection item information, the image category information and the defect information of the inspection image, and the same-item inspection information, the same-item image information and the same-item defect information.

[0142] In one embodiment, the power grid inspection device 1100 further includes an updating module configured to generate, according to the inspection report, an inspection processing scheme corresponding to a defect type of the inspection object; acquire scheme execution information of executing the inspection processing scheme; and update the inspection report according to the scheme execution information.

[0143] The above power grid inspection device includes a first acquisition module, a second acquisition module, a determining module and a generating module, acquires an inspection image of a power grid first, then acquires inspection item information corresponding to the inspection image, and determines image category information of the inspection image and defect information of an inspection object in the inspection image according to the inspection image, so as to generate an inspection report corresponding to the inspection image according to the inspection item information, the image category information and the defect information, and realize automatic processing, analysis and management of power grid inspection data, and improve the inspection efficiency of the power grid. Since the inspection item information identifies the inspection configuration information of the inspection power grid, the image category information identifies the content category in the inspection image, and the defect information identifies the identification result of the safety hazard of the inspection object in the inspection image, the inspection report can timely find and locate hidden faults in the power grid, thereby being conducive to improving the stability and safety of the power grid operation.

[0144] The modules in the power grid inspection device can be implemented by software, hardware, or a combination thereof. The modules can be embedded in or independent of a processor in a computer device in hardware form, or stored in a memory in the computer device in software form, so that the processor can call and execute the operations corresponding to the modules.

[0145] In one embodiment, a computer device, which can be a server, has an internal structure as shown in Figure 12 The computer device includes a processor, a memory, and a network interface connected by a system bus. The processor of the computer device provides computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for running the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store inspection data. The network interface of the computer device is used to communicate with external terminals through network connections. The computer program is executed by the processor to implement a power grid inspection method.

[0146] Those skilled in the art can understand that Figure 12 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not limit the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0147] In one embodiment, a computer device includes a memory and a processor. The memory stores a computer program. The processor executes the computer program to implement the following steps:

[0148] Obtain an inspection image of a power grid;

[0149] Obtain inspection item information corresponding to the inspection image; wherein the inspection item information is used to identify inspection configuration information for inspecting the power grid;

[0150] According to the inspection image, determine image category information of the inspection image and defect information of an inspection object in the inspection image; wherein the defect information is used to identify an identification result that the inspection object in the inspection image has a safety hazard;

[0151] According to the inspection item information, the image category information, and the defect information, generate an inspection report corresponding to the inspection image.

[0152] In one embodiment, the processor executing the computer program further implements the following steps:

[0153] identify the inspection object in the inspection image by using a preset first image classification algorithm;

[0154] obtain historical inspection information of a historical inspection image according to the inspection object, wherein the historical inspection image comprises the inspection object;

[0155] establish an association between the inspection item information and the historical inspection information;

[0156] determine image category information of the inspection image according to the inspection object and the association.

[0157] In one embodiment, the processor, when executing the computer program, further implements the following steps:

[0158] identify whether the inspection object in the inspection image has a safety hazard by using a preset second image classification algorithm;

[0159] In a case where it is determined that the inspection object has a safety hazard, it is determined that the inspection object has a defect, and a defect type of the inspection object is determined, wherein the defect type comprises at least one of a device defect type, a device body type, and an external hidden danger type.

[0160] In one embodiment, the processor, when executing the computer program, further implements the following steps:

[0161] obtain a historical defect image having the inspection object;

[0162] determine a similarity between the historical defect image and the inspection image;

[0163] In a case where the similarity is greater than a preset threshold, identify whether the inspection object in the inspection image has a safety hazard by using a pre-trained defect identification model.

[0164] In one embodiment, the processor, when executing the computer program, further implements the following steps:

[0165] after determining defect information of the inspection object in the inspection image according to the inspection image, obtain a defect level of the defect information, wherein the defect level is positively correlated with maintenance timeliness;

[0166] In a case where the defect level is greater than a preset level, output an alarm signal.

[0167] In one embodiment, the processor, when executing the computer program, further implements the following steps:

[0168] According to the inspection item information, same item inspection information, same item image information and same item defect information corresponding to the same item inspection image of the power grid are obtained, wherein the same item inspection image and the inspection image have the same item identifier of the inspection item;

[0169] According to the inspection item information, the image category information and the defect information of the inspection image, and the same item inspection information, the same item image information and the same item defect information, a project inspection report corresponding to the inspection item is generated.

[0170] In one embodiment, the processor further implements the following steps when executing the computer program:

[0171] In the case that the defect information indicates that the inspection object has a defect, according to the inspection report, an inspection processing scheme corresponding to the defect type of the inspection object is generated;

[0172] Obtaining scheme execution information of executing the inspection processing scheme;

[0173] According to the scheme execution information, the inspection report is updated.

[0174] In one embodiment, a computer readable storage medium is provided, and the computer readable storage medium stores a computer program. The computer program is executed by a processor to implement the following steps:

[0175] Obtaining an inspection image of a power grid;

[0176] Obtaining inspection item information corresponding to the inspection image; wherein the inspection item information is used to identify the inspection configuration information of the power grid;

[0177] According to the inspection image, image category information of the inspection image and defect information of an inspection object in the inspection image are determined; wherein the defect information is used to identify the identification result of the safety hidden danger of the inspection object in the inspection image;

[0178] According to the inspection item information, the image category information and the defect information, a project inspection report corresponding to the inspection image is generated.

[0179] In one embodiment, the computer program is executed by the processor to further implement the following steps:

[0180] Using a preset first image classification algorithm, the inspection object in the inspection image is identified;

[0181] According to the inspection object, a historical inspection image and historical inspection information of the historical inspection image are obtained; wherein the historical inspection image includes the inspection object;

[0182] establishing a correlation between the inspection item information and the historical inspection information;

[0183] determining image category information of the inspection image according to the inspection object and the correlation.

[0184] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0185] using a preset second image classification algorithm to identify whether the inspection object in the inspection image has a safety hazard;

[0186] In a case where it is determined that the inspection object has a safety hazard, it is determined that the inspection object has a defect, and a defect type of the inspection object is determined; wherein the defect type includes at least one of a device defect category, a device body category, and an external hidden danger category.

[0187] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0188] obtaining a historical defect image having the inspection object;

[0189] determining a similarity between the historical defect image and the inspection image;

[0190] In a case where the similarity is greater than a preset threshold, using a pre-trained defect identification model to identify whether the inspection object in the inspection image has a safety hazard.

[0191] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0192] after determining defect information of the inspection object in the inspection image according to the inspection image, obtaining a defect level of the defect information; wherein the defect level is positively correlated with maintenance timeliness;

[0193] In a case where the defect level is greater than a preset level, outputting an alarm signal.

[0194] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0195] obtaining, according to the inspection item information, a same-item inspection image for the power grid and same-item inspection information, same-item image information, and same-item defect information corresponding to the same-item inspection image; wherein the same-item inspection image has a same item identifier as the inspection image;

[0196] According to the inspection item information, the image category information and the defect information of the inspection image, and the same inspection information, the same image information and the same defect information, a project inspection report corresponding to the inspection item is generated.

[0197] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0198] In the case that the defect information indicates that the inspection object has a defect, according to the inspection report, an inspection processing scheme corresponding to the defect type of the inspection object is generated;

[0199] Obtaining scheme execution information of executing the inspection processing scheme;

[0200] According to the scheme execution information, the inspection report is updated.

[0201] In one embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the following steps:

[0202] Obtaining an inspection image of a power grid;

[0203] Obtaining inspection item information corresponding to the inspection image; wherein the inspection item information is used to identify inspection configuration information for inspecting the power grid;

[0204] According to the inspection image, image category information of the inspection image and defect information of an inspection object in the inspection image are determined; wherein the defect information is used to identify an identification result of the inspection object in the inspection image having a safety hazard;

[0205] According to the inspection item information, the image category information and the defect information, an inspection report corresponding to the inspection image is generated.

[0206] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0207] Using a preset first image classification algorithm, the inspection object in the inspection image is identified;

[0208] According to the inspection object, a historical inspection image and historical inspection information of the historical inspection image are obtained; wherein the historical inspection image includes the inspection object;

[0209] An association relationship between the inspection item information and the historical inspection information is established;

[0210] According to the inspection object and the association relationship, image category information of the inspection image is determined.

[0211] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0212] Using the preset second image classification algorithm, identify whether the inspection object in the inspection image has a safety hazard;

[0213] In the case where it is determined that the inspection object has a safety hazard, determine that the inspection object has a defect, and determine the defect type of the inspection object; wherein the defect type includes at least one of the device defect class, the device body class, and the external hidden danger class.

[0214] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0215] Obtain a historical defect image with the inspection object;

[0216] Determine the similarity between the historical defect image and the inspection image;

[0217] In the case where the similarity is greater than a preset threshold, use a pre-trained defect recognition model to identify whether the inspection object in the inspection image has a safety hazard.

[0218] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0219] After executing the defect information of the inspection object in the inspection image according to the inspection image, obtain the defect level of the defect information; wherein the defect level is positively correlated with the maintenance timeliness;

[0220] In the case where the defect level is greater than a preset level, output an alarm signal.

[0221] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0222] According to the inspection item information, obtain a same item inspection image for the power grid and same item inspection information, same item image information and same item defect information corresponding to the same item inspection image; wherein the same item inspection image and the inspection image have the same inspection item identifier.

[0223] According to the inspection item information, the image category information and the defect information of the inspection image, and the same item inspection information, the same item image information and the same item defect information, generate a project inspection report corresponding to the inspection item.

[0224] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0225] In a case where the defect information is that the inspection object has a defect, generating, according to the inspection report, an inspection processing scheme corresponding to a defect type of the inspection object;

[0226] Obtaining scheme execution information of executing the inspection processing scheme;

[0227] Updating the inspection report according to the scheme execution information.

[0228] It should be noted that the data involved in the present application (including but not limited to data for analysis, stored data, displayed data, etc.) are all information and data authorized by the user or authorized by all parties.

[0229] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned embodiments. Any reference to a memory, database or other medium used in the embodiments provided by the present application can include at least one of a non-volatile and volatile memory. The non-volatile memory can include a read-only memory (Read-Only Memory, ROM), a magnetic tape, a floppy disk, a flash memory, an optical storage, a high-density embedded non-volatile memory, a resistive memory (ReRAM), a magnetoresistive random access memory (Magnetoresistive Random Access Memory, MRAM), a ferroelectric memory (Ferroelectric Random Access Memory, FRAM), a phase change memory (Phase Change Memory, PCM), a graphene memory, etc. The volatile memory can include a random access memory (Random Access Memory, RAM) or an external cache memory, etc. As an illustration but not limitation, the RAM can be in various forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), etc. The database involved in the embodiments provided by the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided by the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.

[0230] Any technical features in the above embodiments can be combined, and for the sake of brevity, not all possible combinations are described above, however, as long as the combinations of technical features do not have contradictions, they shall be considered within the scope of the present disclosure.

[0231] The above embodiments only express several implementation manners of the present application, and the description is relatively specific and detailed, but it shall not be understood as a limitation on the patent scope of the present application. It shall be pointed out that, for ordinary skilled persons in the art, several modifications and improvements can be made without departing from the concept of the present application, and these shall be within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims

1. A power grid inspection method, characterized in that, include: Acquire inspection images of the power grid; The inspection item information corresponding to the inspection image is obtained based on the preset power grid ledger and the equipment information corresponding to the inspection equipment; wherein, the inspection item information is used to identify the inspection configuration information for inspecting the power grid; The inspection object in the inspection image is identified using a preset first image classification algorithm; historical inspection images and historical inspection information of the historical inspection images are obtained based on the inspection object; an association relationship is established between the inspection item information and the historical inspection information; the image category information of the inspection image is determined based on the inspection object and the association relationship; the historical inspection image includes the inspection object; the image category information includes at least one of scene information, data source information, and inspection object; Based on the inspection image, defect information of the inspected object in the inspection image is determined; wherein, the defect information is used to identify the identification result that there is a safety hazard in the inspected object in the inspection image; Based on the inspection item information, the image category information, and the defect information, an inspection report corresponding to the inspection image is generated; Based on the inspection project information, obtain the same inspection image for the power grid, as well as the same inspection information, same image information, and same defect information corresponding to the same inspection image; based on the inspection project information, image category information, and defect information of the inspection image, as well as the same inspection information, same image information, and same defect information, generate a project inspection report corresponding to the inspection project; wherein, the same inspection image and the inspection image have the same project identifier for the same inspection project.

2. The power grid inspection method according to claim 1, characterized in that, The step of determining the defect information of the inspected object in the inspection image based on the inspection image includes: Using a pre-defined second image classification algorithm, identify whether there are any safety hazards in the inspection objects in the inspection images; If it is determined that the inspection object has a safety hazard, it is determined that the inspection object has a defect, and the defect type of the inspection object is determined; wherein, the defect type includes at least one of equipment defect type, equipment body type, and external hazard type.

3. The power grid inspection method according to claim 2, characterized in that, The process of identifying whether there are safety hazards in the inspection objects in the inspection image includes: Obtain historical defect images of the inspected objects; Determine the similarity between the historical defect image and the inspection image; If the similarity is greater than a preset threshold, a pre-trained defect recognition model is used to identify whether there are any safety hazards in the inspection objects in the inspection image.

4. The power grid inspection method according to claim 1, characterized in that, After determining the defect information of the inspected object in the inspection image based on the inspection image, the power grid inspection method further includes: The defect level of the defect information is obtained; wherein the defect level is positively correlated with the timeliness of maintenance. If the defect level is greater than a preset level, an alarm signal is output.

5. The power grid inspection method according to claim 1, characterized in that, When the defect information indicates that the inspected object has a defect, the power grid inspection method further includes: Based on the inspection report, an inspection handling plan corresponding to the defect type of the inspected object is generated; Obtain the execution information of the inspection processing plan; Update the inspection report based on the execution information of the aforementioned plan.

6. A power grid inspection device, characterized in that, include: The first acquisition module is used to acquire inspection images of the power grid; The second acquisition module is used to acquire the inspection item information corresponding to the inspection image; Based on the inspection project information, obtain the same inspection image for the power grid, as well as the same inspection information, same image information, and same defect information corresponding to the same inspection image; wherein, the inspection project information is used to identify the inspection configuration information for inspecting the power grid; the same inspection image and the inspection image have the same project identifier for the same inspection project; The determination module is used to identify the inspection objects in the inspection images using a preset first image classification algorithm; obtain historical inspection images and historical inspection information of the historical inspection images based on the inspection objects; establish a correlation between the inspection item information and the historical inspection information; determine the image category information of the inspection images based on the inspection objects and the correlation; and determine the defect information of the inspection objects in the inspection images based on the inspection images. The defect information is used to identify the identification result of safety hazards in the inspection objects in the inspection images. The historical inspection images include the inspection objects. The image category information includes at least one of scene information, data source information, and inspection objects. The generation module is used to generate an inspection report corresponding to the inspection image based on the inspection item information, the image category information, and the defect information; and to generate a project inspection report corresponding to the inspection item based on the inspection item information, the image category information, and the defect information of the inspection image, as well as the same inspection information, the same image information, and the same defect information.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 5.

Images