Transformer substation inspection method based on image processing

Abstract

The invention belongs to the technical field of power grids, provides a transformer substation inspection method based on image processing, and aims to solve the problem that in the prior art, when automatic inspection equipment is adopted to conduct automatic inspection on a transformer substation, the photographing quality of photographing the transformer substation is low. The method comprises the following steps: determining illumination and point locations suitable for automatic inspection of a transformer substation, and issuing an inspection task corresponding to the inspection point location to specific inspection equipment according to the type of the inspection equipment under the condition that the illumination and the point locations are both suitable; therefore, the proper inspection equipment is adopted to automatically collect the images of the corresponding parts of the transformer substation at the proper time and the proper angle position, the shooting quality of the transformer substation during automatic inspection of the transformer substation can be improved, and the high-quality collected images are obtained; therefore, the accuracy of transformer station state evaluation and the accuracy of transformer station fault identification are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power grids, and in particular to a substation inspection method based on image processing. Background Art

[0002] In recent years, routine inspection of substations has become very important in power grid systems. In traditional technologies, with the development of intelligent automatic equipment, inspection of substations has gradually adopted automated inspection equipment including but not limited to drones and intelligent robots, that is, taking photos of substations through automated inspection equipment, and analyzing and judging the status of substations through the images collected by the photos, providing a basis for fault identification of substations, saving manpower, and improving inspection efficiency.

[0003] In traditional technology, when an automated inspection device including but not limited to drones and intelligent robots is used to inspect a substation, the general processing flow is to issue an inspection task, assign the inspection task to an automated inspection device such as a drone and an intelligent robot, and the automated inspection device inspects the substation and takes photos to collect images of the substation to obtain inspection results. The inspection results are generally collected images of the substation, and then the collected images are analyzed and judged to evaluate the status of the substation and identify faults in the substation. For example, in one scenario, a controlled drone conducts a high-altitude inspection of the substation, and an intelligent robot conducts a ground and low-altitude inspection of the substation. The high-altitude inspection results corresponding to the high-altitude inspection of the substation by the drone and the ground and low-altitude inspection results corresponding to the ground and low-altitude inspection of the substation by the intelligent robot are combined to complete the inspection of the substation and obtain a status image of the substation.

[0004] The above-mentioned inspection method of combining drones and intelligent robots to automatically inspect substations, although based on the automation of substation inspection, improves the efficiency of inspection, but is limited by the preset inspection program of the automated inspection equipment. The automated inspection equipment cannot handle different inspection conditions flexibly according to the on-site conditions like manual inspection. Therefore, unless it is in the ideal shooting state corresponding to the preset inspection program of the automated inspection equipment, there is a risk of low shooting quality of the substation when the automated inspection equipment automatically inspects the substation. Therefore, how to collect high-quality substation status images through automated inspection equipment has become an urgent problem to be solved. Summary of the invention

[0005] The technical problem solved by the present invention is that when the automatic inspection equipment is used to automatically inspect the substation in the traditional power grid technology, there is a technical problem that the quality of photographing the substation is low.

[0006] To solve the above technical problems, the present invention provides the following technical solutions: in response to an instruction to perform automatic inspection on a target substation, determine an expected inspection time period corresponding to the automatic inspection of the target substation; determine whether the expected inspection time period is within a preset inspection time period; when the expected inspection time period is within the preset inspection time period, obtain the expected lighting conditions corresponding to the target substation in the expected inspection time period; determine whether the expected lighting conditions meet the preset lighting conditions; when the expected lighting conditions meet the preset lighting conditions, obtain a set of inspection points corresponding to the automatic inspection of the target substation, the set of inspection points including the inspection points corresponding to the automatic inspection of the target substation and the height of the inspection points relative to the ground; according to the height, determine the type of target inspection equipment corresponding to the inspection task of executing the inspection point; according to the target inspection equipment type, obtain the set of inspection equipment corresponding to the target inspection equipment type; according to the set of inspection equipment, determine the target inspection equipment corresponding to the inspection task.

[0007] As a preferred solution of the substation inspection of the present invention, obtaining the expected lighting conditions corresponding to the target substation in the expected inspection time period includes: Obtaining the weather forecast corresponding to the target substation during the expected inspection period, wherein the weather forecast includes weather conditions; Determine whether the weather condition meets the preset inspection weather conditions; When the weather condition meets the preset inspection weather condition, obtaining the historical light data of the target substation corresponding to the expected inspection time period; The illumination data corresponding to the target substation in the expected inspection time period is predicted according to the historical illumination data to obtain the expected illumination conditions.

[0008] The beneficial effects of the present invention are as follows: when automatically inspecting a target substation, the target substation is photographed as much as possible under lighting conditions and locations suitable for shooting to realize automatic inspection of the target substation, and the target device type of the inspection device is determined according to the height of the inspection point, so that suitable automatic inspection equipment is used to collect images of corresponding parts of the substation at a suitable time and angle, which can improve the quality of shooting of the substation by drones or intelligent robots when performing automatic inspections of the substation, obtain high-quality collected images, improve the accuracy of substation status assessment and the accuracy of substation fault identification, and take into account both the inspection efficiency and inspection quality of automatic inspections of substations. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1A schematic diagram of a process flow of a substation inspection method based on image processing provided by an embodiment of the present invention; Figure 2 A schematic diagram of the system architecture of a substation inspection method based on image processing provided by an embodiment of the present invention; Figure 3 A schematic diagram of a first sub-process of a substation inspection method based on image processing provided by an embodiment of the present invention; Figure 4 A schematic diagram of a second sub-process of the substation inspection method based on image processing provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0010] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, but not all of the embodiments.

[0011] The embodiment of the present invention provides a substation inspection method based on image processing, which can be applied to but not limited to computer devices such as laptops, desktop computers, servers, etc., and is used when automatically inspecting substations in the field of power grids, including but not limited to.

[0012] In view of the technical problem that the quality of photographing the substation is low when the automatic inspection equipment is used to perform automatic inspection on the substation in the traditional technology, the inventor proposes a substation inspection method based on image processing in an embodiment of the present invention. The core idea of ​​the embodiment of the present invention is: in response to the instruction of automatic inspection on the substation, the illumination and point suitable for automatic inspection of the substation are determined. When the illumination and point are suitable, the target device type of the inspection device is determined according to the height of the inspection point, and the inspection task corresponding to the inspection point is sent to the specific inspection device according to the type of the inspection device, so as to realize the acquisition of images of the corresponding parts of the substation by using suitable automatic inspection equipment at the appropriate time and appropriate angle position, so as to improve the shooting quality of the substation when the drone or intelligent robot performs automatic inspection on the substation, so as to improve the accuracy of the substation status assessment and the accuracy of the fault identification of the substation, and at the same time of improving the inspection efficiency, it can flexibly deal with the influence of different weather conditions, shooting time and other environmental factors on the shooting quality, improve the quality of the automatic inspection of the substation, and take into account the inspection efficiency and inspection quality of the automatic inspection of the substation.

[0013] Example 1, please refer to Figure 1 and Figure 2 , Figure 1 A schematic diagram of a flow chart of a substation inspection method based on image processing provided by an embodiment of the present invention, Figure 2A schematic diagram of the system architecture of a substation inspection method based on image processing provided by an embodiment of the present invention. Figure 1 As shown, in this embodiment, the substation inspection method based on image processing provided by the embodiment of the present invention is applied to, but not limited to Figure 2 The inspection control end shown in the figure includes but is not limited to the following steps S11-S18: S11. In response to an instruction to perform automatic inspection on a target substation, determine an expected inspection time period corresponding to the automatic inspection on the target substation.

[0014] Explanatory, the expected inspection time period refers to the time period from the start of the inspection of the target substation by the automatic inspection equipment to the end of the inspection. The expected inspection time period includes but is not limited to the following two calculation forms: 1) The instruction to automatically inspect the target substation includes a specified time period for the inspection. For example, the instruction includes automatically inspecting the target substation from 9:00 am to 10:00 am on the same day.

[0015] 2) The instruction to automatically inspect the target substation includes the inspection start time of the automatic inspection of the target substation, and then the expected inspection time period is determined based on the inspection start time, combined with the time required for the automatic inspection device to start the inspection of the target substation and end the inspection, including but not limited to. In one example, the instruction to automatically inspect the target substation includes the inspection start time of 9:00 am, and the time required for the automatic inspection device to start the inspection of the target substation and end the inspection is estimated to be 2 hours based on manual experience, then the expected inspection time period is from 9:00 am to 11:00 am, during which time period the automatic inspection device will automatically inspect the target substation. In another example, an instruction for automatically inspecting a target substation includes that the start time for the automatic inspection of the target substation is 9:00 a.m., and the time required for the automatic inspection equipment to depart and arrive at the target substation is 0.5 hours, and the time required for the automatic inspection equipment to start and end the inspection of the target substation is 2 hours. Then, the expected inspection time period is from 9:00 a.m. to 11:30 a.m. During this time period, the automatic inspection equipment will automatically inspect the target substation, and the same applies to other situations of the expected inspection time period.

[0016] See also Figure 2The inspection control end receives an instruction to perform automatic inspection on the target substation. The instruction can be triggered manually or automatically based on the settings of other applications. There is no limitation here. When it is determined to perform automatic inspection on the target substation, in response to the instruction to perform automatic inspection on the target substation, the expected inspection time period corresponding to the automatic inspection on the target substation is determined. The expected inspection time period is as described above. The expected inspection time period can be the corresponding time period of the reservation situation, or it can be triggered to start the automatic inspection of the target substation when the instruction to perform automatic inspection on the target substation is received.

[0017] S12: Determine whether the expected inspection time period is within a preset inspection time period.

[0018] Explanatory, the inspection time period is pre-set, i.e., the preset inspection time period, and the preset inspection time period indicates a time suitable for photographing the target substation to automatically inspect the target substation. Due to factors including but not limited to the four seasons of the year and different regions, the duration and intensity of illumination are different, and the time period for photographing the target substation to automatically inspect the target substation is different in different regions and seasons. Therefore, for each target substation, according to factors such as the region and season where the target substation is located, a time period suitable for photographing to automatically inspect the target substation is pre-set, i.e., the preset inspection time period. Exemplarily, for the same target substation, the preset inspection time period in summer is from 5:30 am to 19:00 pm, and the preset inspection time period in winter is from 8:00 am to 16:00 pm.

[0019] Further, determining whether the expected inspection time period is before the preset inspection time period further includes: Obtaining the geographical location and current date of the target substation; An inspection time period is set according to the geographical location and the current date to obtain a preset inspection time period.

[0020] Explanatory, the geographical location and current date of the target substation are obtained. The geographical location can determine the time zone. Combined with the current date, the season of the target substation can be determined, and the inspection time period is automatically set according to the season. Thus, the inspection time period is automatically set according to the geographical location and the current date to obtain the preset inspection time period. Exemplarily, according to the geographical location and the current date of the target substation, if the target substation is determined to be in summer, the preset inspection time period in summer can be automatically set to 5:30 am to 7:00 pm. If the target substation is determined to be in winter, the preset inspection time period in winter can be automatically set to 8:00 am to 4:00 pm. The same is true for other seasons such as spring, summer, autumn and winter, including holidays, etc., and the inspection time period can be set in an automatic setting manner to obtain the preset inspection time period. Compared with the method of manually setting the inspection time period in the traditional technology, it can strengthen the control of the automatic inspection time setting, improve the timeliness of the automatic inspection of the substation, avoid the passive sabotage of the relevant personnel when setting or the arbitrariness of the preset inspection time period, and improve the work efficiency of the automatic inspection of the substation.

[0021] Based on the setting of the above-mentioned preset inspection time period, after the expected inspection time period corresponding to the automatic inspection of the target substation is determined, it is judged whether the expected inspection time period is within the preset inspection time period. If the expected inspection time period is within the preset inspection time period, it indicates that it is suitable to shoot the target substation for automatic inspection of the target substation from the perspective of time factors. If the expected inspection time period is not within the preset inspection time period, it indicates that it is not suitable to shoot the target substation for automatic inspection of the target substation from the perspective of time factors, and it is necessary to change the time of the automatic inspection or perform other processing.

[0022] S13: if the expected inspection time period is not within the preset inspection time period, not obtaining the expected lighting condition of the target substation corresponding to the expected inspection time period; S14: When the expected inspection time period is within a preset inspection time period, obtaining the expected lighting condition of the target substation corresponding to the expected inspection time period.

[0023] Explanatory, the expected light condition means the predicted light condition of the target substation in a future period corresponding to the expected inspection time period. The expected light condition can be predicted based on, but not limited to, weather conditions. Exemplarily, when the light condition corresponding to the expected inspection time period is predicted using weather conditions as an example, the weather forecast corresponding to the target substation in the expected inspection time period is obtained, wherein the weather forecast includes weather conditions, and the prediction is made based on the weather conditions and the historical light data corresponding to the time period at the location.

[0024] In the case where the expected inspection time period is not within the preset inspection time period, it indicates that the expected inspection time period is not suitable for automatic inspection of the target substation, and the expected light conditions corresponding to the target substation in the expected inspection time period are not obtained. No subsequent processing is required, and processing measures such as reminders that it is not suitable for automatic inspection can be taken for processing. For example, in the case where the expected inspection time period is not within the preset inspection time period, a reminder that it is not suitable for automatic inspection of the target substation is issued, and the content "the expected inspection time period is not within the preset inspection time period" is used for reminder. At the same time, in the case where the expected inspection time period is within the preset inspection time period, the expected light conditions corresponding to the target substation in the expected inspection time period are obtained, and then the subsequent automatic substation inspection processing is further performed.

[0025] Further, obtaining the expected lighting condition corresponding to the target substation in the expected inspection time period includes: Obtaining the weather forecast corresponding to the target substation during the expected inspection period, wherein the weather forecast includes weather conditions; Determine whether the weather condition meets the preset inspection weather conditions; When the weather condition meets the preset inspection weather condition, obtaining the historical light data of the target substation corresponding to the expected inspection time period; The illumination data corresponding to the target substation in the expected inspection time period is predicted according to the historical illumination data to obtain the expected illumination conditions.

[0026] Explanatoryly, lighting can be quantified. Lighting is generally realized through light intensity, and its unit is lux (lx). For example, lighting conditions suitable for shooting include but are not limited to outdoor natural light, cloudy and overcast weather, and strong sunlight, and are quantified into light intensities as lighting conditions suitable for shooting.

[0027] Determine whether the weather conditions meet the preset inspection weather conditions, for example, determine whether the weather conditions are sunny or cloudy. When the weather conditions are sunny or cloudy and meet the preset inspection weather conditions, obtain the historical light data corresponding to the target substation in the expected inspection time period, such as obtaining the historical light data corresponding to the light intensity at the same location and in the same time period in the previous 3 or 5 years. In this case, the historical light data is sequence-based data. Then, based on the historical light data, predict the light data corresponding to the target substation in the expected inspection time period to obtain the expected light conditions. For example, adopt an algorithm including but not limited to the average value algorithm, regression analysis, and time series analysis method to make a prediction based on the historical light data to obtain the light data corresponding to the target substation in the expected inspection time period and obtain the expected light conditions.

[0028] Further, judging whether the weather condition meets the preset inspection weather conditions includes: Determine whether the weather condition is disastrous weather; When the weather condition does not belong to disastrous weather, determining that the weather condition meets the preset inspection weather condition; In the case where the weather condition is disastrous weather, it is determined that the weather condition does not meet the preset inspection weather conditions.

[0029] Explanatory, determine whether the weather conditions are disastrous weather, for example, whether they are disastrous weather such as strong winds, heavy rains, hail, tornadoes, cold waves, frost, heavy fog, etc. If the weather conditions are not disastrous weather, determine that the weather conditions meet the preset inspection weather conditions; if the weather conditions are disastrous weather, determine that the weather conditions do not meet the preset inspection weather conditions.

[0030] Due to the different climate conditions in different regions and seasons, there is a risk of sudden changes in weather conditions in some regions or seasons, and the weather conditions in summer are particularly sudden. By judging the expected lighting conditions corresponding to the target substation during the expected inspection period, including but not limited to the weather conditions, the negative effects of severe weather such as catastrophic weather can be avoided, and the quality of photography of substations by drones or intelligent robots during automatic inspections can be improved to obtain high-quality captured images.

[0031] S15: Determine whether the expected lighting condition meets the preset lighting condition.

[0032] Explanatoryly, suitable lighting conditions for shooting for automatic inspection of the target substation are pre-set, that is, preset lighting conditions. Suitable lighting conditions for shooting include but are not limited to outdoor natural light, cloudy and overcast weather, and light intensity corresponding to strong sunlight. Under these lighting conditions, the target substation can be photographed for automatic inspection.

[0033] ‌ Determine whether the expected lighting conditions meet the preset lighting conditions, that is, determine whether the expected lighting conditions are the lighting intensities corresponding to outdoor natural light, cloudy and overcast weather, and strong sunlight. When the expected lighting conditions are the lighting intensities corresponding to outdoor natural light, cloudy and overcast weather, and strong sunlight, it is suitable to photograph the target substation for automatic inspection of the target substation. When the expected lighting conditions are not the lighting intensities corresponding to outdoor natural light, cloudy and overcast weather, and strong sunlight, for example, in disastrous weather conditions such as strong winds, heavy rains, hail, tornadoes, cold waves, frost, and heavy fog, it is not suitable to photograph the target substation for automatic inspection of the target substation.

[0034] S16. When the expected lighting condition meets the preset lighting condition, obtain a set of inspection points corresponding to the automatic inspection of the target substation, wherein the set of inspection points includes the inspection points corresponding to the automatic inspection of the target substation and the heights of the inspection points relative to the ground; S17: When the expected lighting condition does not meet the preset lighting condition, a set of inspection points corresponding to the automatic inspection of the target substation is not obtained.

[0035] Explanatoryly, when the expected lighting conditions meet the preset lighting conditions, it indicates that the expected lighting conditions are suitable for automatic inspection of the target substation, and a set of inspection points corresponding to the automatic inspection of the target substation is determined. The inspection point set includes the inspection points corresponding to the automatic inspection of the target substation, and the inspection points include the height of the shooting position relative to the ground, wherein the inspection point is the position where the target substation is photographed. The inspection points include but are not limited to the position, height, and angle. Usually, the target substation is automatically inspected by photographing the target substation from various angles to fully obtain the required target substation image information. Therefore, the automatic inspection of the target substation is composed of several inspection points, which is a set of inspection points. Furthermore, when the expected lighting conditions meet the preset lighting conditions, it indicates that the expected lighting conditions are not suitable for automatic inspection of the target substation, and the set of inspection points corresponding to the automatic inspection of the target substation is not obtained. No subsequent processing is required, and measures such as reminders that are not suitable for automatic inspection can be taken. For example, when the expected lighting conditions do not meet the preset lighting conditions, a reminder that it is not suitable for automatic inspection of the target substation is issued, and the content "the expected lighting conditions do not meet the preset lighting conditions" is used as a reminder.

[0036] S18. Determine the type of target inspection equipment corresponding to the inspection task for executing the inspection point according to the height; S19. According to the target inspection device type, obtain an inspection device set corresponding to the target inspection device type; S20. Determine, according to the inspection device set, a target inspection device corresponding to executing the inspection task.

[0037] Explanatoryly, based on the inspection point set, the inspection points and their corresponding heights are obtained. According to the heights, the target inspection equipment type corresponding to the inspection task at the inspection points is determined to be a drone device or an intelligent robot device. Then, according to the target inspection equipment type, the inspection equipment set corresponding to the target inspection equipment type is obtained. The inspection equipment set is generally composed of several automatic inspection equipment. According to the inspection equipment set, the target inspection equipment corresponding to the inspection task is determined, that is, which inspection equipment included in the inspection equipment set performs the inspection task of the inspection point on the target substation.

[0038] In an embodiment of the present invention, by responding to an instruction to perform automatic inspection on a target substation, an expected inspection time period corresponding to the automatic inspection of the target substation is determined, and first a judgment is made as to whether the expected inspection time period is within a preset inspection time period. If the expected inspection time period is within the preset inspection time period, the expected lighting conditions corresponding to the target substation in the expected inspection time period are obtained, and then a judgment is made as to whether the expected lighting conditions meet the preset lighting conditions. If the expected lighting conditions meet the preset lighting conditions, a set of inspection points corresponding to the automatic inspection of the target substation is obtained, the inspection point set including the inspection points corresponding to the automatic inspection of the target substation, the inspection points including the height of the shooting position relative to the ground, and according to the height, a target inspection device type corresponding to the inspection task of executing the inspection point is determined, and according to the target inspection device type, a set of inspection devices corresponding to the target inspection device type is obtained, and according to the inspection device set, a target inspection device corresponding to the inspection task is determined. The target inspection equipment is used, so that when the target substation is automatically inspected, the target substation can be photographed under suitable lighting conditions and points for shooting as much as possible to realize automatic inspection of the target substation. Whether it is suitable for inspection can be determined by lighting conditions such as weather conditions and inspection time, and the target equipment type of the inspection equipment can be determined according to the height of the inspection point, so that the appropriate automatic inspection equipment can be used to collect images of the corresponding parts of the substation at the appropriate time and angle. The shooting quality of the substation when the drone or intelligent robot performs automatic inspection of the substation can be improved, and high-quality collected images can be obtained to improve the accuracy of substation status assessment and fault identification of the substation. While improving the inspection efficiency, it can flexibly respond to the impact of different weather conditions, shooting time and other environmental factors on the shooting quality, improve the quality of automatic inspection of the substation, and take into account the inspection efficiency and inspection quality of the automatic inspection of the substation.

[0039] In one embodiment, see Figure 3 , Figure 3 The first sub-process diagram of the substation inspection method based on image processing provided by the embodiment of the present invention. Figure 3As shown, in this embodiment, obtaining a set of inspection points corresponding to automatic inspection of the target substation includes: S31, performing three-dimensional space rasterization processing on the target substation, and determining a feasible space corresponding to automatic inspection of the target substation; S32, taking the target substation as the center body, determining a three-dimensional cuboid space model enveloping the target substation; S33, taking the six faces of the rectangular space model as shooting targets, determining the inspection points corresponding to the automatic inspection of the target substation in the feasible space; S34. All the inspection points are combined into a set to obtain an inspection point set.

[0040] Explanatoryly, the three-dimensional space rasterization processing of the target substation is to model the target substation in three-dimensional space, and on the basis of the modeling, based on the three-dimensional space, the image data of the three-dimensional model corresponding to the target substation is divided into a grid structure according to certain rules, and the image data is organized, photographed and analyzed through this grid structure to obtain a spatial grid and spatial grid points, and determine the feasible space corresponding to the automatic inspection of the target substation. The feasible space represents the space excluding the space where the power equipment of the substation is located and the prohibited space generated by maintaining a certain safety distance from the inspection equipment. The feasible space includes spatial grid points and ground road points, and the inspection points can only be located in the feasible space.

[0041] Then, taking the target substation as the central body, a rectangular space model of the three-dimensional space enveloping the target substation is determined. The rectangular space model contains the target substation and normalizes the target substation in shape, which is conducive to photographing the target substation and processing the photographed images. The six faces of the rectangular space model are taken as shooting targets, so that based on the face features of the rectangular block, the inspection points corresponding to the automatic inspection of the target substation are determined in the feasible space, and all the inspection points are combined into a set to obtain an inspection point set.

[0042] The embodiment of the present invention performs three-dimensional rasterization processing on the target substation and constructs a corresponding rectangular model, thereby regularizing the power equipment contained in the irregular substation, thereby facilitating the photographing of the target substation and processing the photographed image, and can improve the shooting quality of the substation when the drone or intelligent robot performs automatic inspection of the substation, obtain high-quality collected images, and improve the accuracy of substation status assessment and fault identification of the substation. While improving the inspection efficiency, it can flexibly respond to the influence of different weather conditions, shooting time and other environmental factors on the shooting quality, improve the quality of automatic inspection of the substation, and take into account both the inspection efficiency and inspection quality of the automatic inspection of the substation.

[0043] In one embodiment, see Figure 4 , Figure 4 The second sub-flow diagram of the substation inspection method based on image processing provided by the embodiment of the present invention. Figure 4 As shown, in this embodiment, the six faces of the rectangular space model are taken as shooting targets, and the inspection points corresponding to the automatic inspection of the target substation are determined in the feasible space, including: S41, taking each face of the cuboid space model as a sub-shooting target, determining a face position code of the sub-shooting target corresponding to the target substation; S42, determining the inspection point corresponding to the sub-shooting target in the feasible space based on a preset shooting potential algorithm; S43. Arrange all the inspection points according to the surface position code to obtain the inspection points corresponding to the automatic inspection of the target substation.

[0044] Explanatoryly, each face of the rectangular space model is taken as a sub-shooting target, and the face position code of the sub-shooting target corresponding to the target substation is determined, that is, the rectangular space model is divided with each face of the rectangular space model as an independent shooting unit, and the faces corresponding to the sub-shooting targets are coded and sorted, so as to facilitate the shooting of the rectangular space model and the processing of the shot images, and then based on the preset shooting potential algorithm, the inspection points corresponding to the sub-shooting targets are determined in the feasible space, and all the inspection points are arranged according to the face position code to obtain the inspection points corresponding to the automatic inspection of the target substation.

[0045] Among them, the preset shooting potential algorithm is an algorithm for determining the inspection points based on the shooting potential of the spatial point. For each shooting object of the target substation, the shooting potential of different inspection points corresponding to the shooting object is calculated, and a point suitable for shooting the shooting object is determined from a number of inspection points according to the calculated shooting potential as the inspection point for this shooting. The preset shooting potential algorithm includes but is not limited to generating inspection points according to the calculation results of the shooting potential and the spatial relationship by optimization algorithms such as greedy algorithms and genetic algorithms. In addition, the shooting potential of the spatial point is a model involving the influence of shooting distance, shooting angle, lighting, occlusion and camera zoom multiple. For example, the spatial point Shooting on the device The calculation method of is shown in the following formula (1): , formula (1); in, Indicates the concentration of the surface information element. It is used to characterize the different importance of different areas on the equipment surface for inspection. Represents the device face element, with spatial coordinates (x, y, z). θ represents the angle between the line connecting the face element and point P and the normal vector S of the device surface, that is, the shooting angle.

[0046] The embodiment of the present invention takes each face of the rectangular space model as a sub-shooting target and determines the inspection point in combination with the shooting potential algorithm, fully considering the factors affecting the shooting quality including but not limited to lighting when shooting the target substation, and the premise is that the expected lighting conditions meet the preset lighting conditions, thereby considering the impact of lighting on the shooting quality from large to small levels, and can not only flexibly respond to the impact of different weather conditions, shooting time and other environmental factors on the shooting quality, but also consider the impact of different shooting points on the shooting quality, further improving the shooting quality of the automatic inspection of the target substation.

[0047] In one embodiment, determining the inspection point corresponding to the sub-shooting target in the feasible space includes: Determine the inspection point corresponding to the sub-shooting target in the feasible space, and determine the point position code corresponding to the inspection point; The surface position code and the point position code are formed into a corresponding relationship as the point information of the inspection point.

[0048] Explanatoryly, each face of the rectangular space model is taken as a sub-shooting target. For the sub-shooting target of each face, especially when there are multiple inspection points on each face, for example, when the area of ​​each face is relatively large and there are multiple inspection points, the inspection point corresponding to the sub-shooting target is determined in the feasible space, and the point position code corresponding to the inspection point is determined. The point position code represents the position code of the inspection point on the face corresponding to the sub-shooting target. Therefore, especially when there are multiple inspection points, the images taken by each inspection point are recorded in order, and then the correspondence between the face position code and the point position code is used as the point information of the inspection point. Subsequently, the captured images corresponding to the inspection points are recorded in correspondence with the point information, which can improve the orderliness of the images collected for automatic inspection of the target substation.

[0049] The embodiments of the present invention combine the surface position code and the point position code of the inspection point as the point information of the inspection point, and subsequently record the captured image corresponding to the inspection point and the point information in correspondence, thereby improving the orderliness of the images collected for automatic inspection of the target substation, facilitating the processing and analysis of the images collected for automatic inspection of the target substation, and improving the efficiency of processing the automatic inspection of the substation, while taking into account both the inspection efficiency and the inspection quality of the automatic inspection of the substation.

[0050] In one embodiment, after the surface position code and the point position code are formed into a corresponding relationship as the point information of the inspection point, the method further includes: Acquire a first image collected by a preset drone when performing an inspection mission, and determine first point information corresponding to the first image at the target substation; Acquire a second image collected by a preset intelligent robot when performing an inspection task, and determine second point information corresponding to the second image at the target substation; The first image and the second image are combined into a whole image according to the first point information and the second point information, so as to obtain an inspection image corresponding to the automatic inspection of the target substation.

[0051] Explanatoryly, a first image captured by a preset UAV when performing an inspection task is obtained, and first point information corresponding to the first image in the target substation is determined. The first point information includes a surface position code and a point position code. The surface position code indicates the surface to which the inspection point belongs in the rectangular parallelepiped corresponding to the target substation, and the point position code indicates the position order of the inspection point in the surface of the rectangular parallelepiped corresponding to the target substation. A second image captured by a preset intelligent robot when performing an inspection task is obtained, and second point information corresponding to the second image in the target substation is determined. The second point information is similar to the first point information. The first and second are only used to distinguish different point information and are not used to limit different point information. Then, according to the first point information and the second point information, that is, according to the order of the surface and the order of the points, the first image and the second image are sequentially combined into a whole image to obtain an inspection image corresponding to automatic inspection of the target substation.

[0052] The embodiments of the present invention record the captured images and point information of the inspection points corresponding to the drone and the intelligent robot respectively, and combine all the images into a whole image according to the point information, so as to obtain the inspection image corresponding to the automatic inspection of the target substation. This can improve the orderly processing of the images collected for the automatic inspection of the target substation, facilitate the processing and analysis of the images collected for the automatic inspection of the target substation, improve the efficiency of the processing of the automatic inspection of the substation, take into account the inspection efficiency and inspection quality of the automatic inspection of the substation, and improve the accuracy of the substation status assessment and the accuracy of the substation fault identification.

[0053] In one embodiment, determining the type of target inspection equipment corresponding to the inspection task of executing the inspection point according to the height includes: Determining whether the height is greater than or equal to a preset height threshold; When the height is greater than or equal to a preset height threshold, the target inspection equipment type is determined to be a drone equipment type, and then a preset drone included in the drone equipment type is used to perform the inspection task; When the height is less than a preset height threshold, the target inspection equipment type is determined to be an intelligent robot equipment type, and then a preset intelligent robot included in the intelligent robot equipment type is used to perform the inspection task.

[0054] Explanatoryly, determine whether the height is greater than or equal to the preset height threshold. When the height is greater than or equal to the preset height threshold, determine the target inspection equipment type as a drone equipment type, and send the inspection task corresponding to the inspection point to the preset drone, so that the preset drone included in the drone equipment type is used to perform the inspection task. When the height is less than the preset height threshold, determine the target inspection equipment type as an intelligent robot equipment type, and send the inspection task corresponding to the inspection point to the preset intelligent robot, so that the preset intelligent robot included in the intelligent robot equipment type is used to perform the inspection task, thereby combining the drone and the intelligent robot according to the height of the inspection point to realize automatic inspection of the target substation.

[0055] The embodiments of the present invention determine that the target device type of the inspection equipment is a drone or an intelligent robot according to the height of the inspection point, and send the inspection task of the inspection point to a specific drone or intelligent robot according to the target device type. The drone and the intelligent robot then collect images of the corresponding substation according to the inspection point, thereby improving the inspection efficiency of the target substation on the basis of high-quality collected images, taking into account the inspection quality and efficiency of the automatic inspection of the substation, and improving the accuracy of the substation status assessment and the accuracy of the substation fault identification.

[0056] It should be noted that the substation inspection method based on image processing described in the above embodiments can recombine the technical features contained in different embodiments as needed to obtain a combined implementation plan, but all of them are within the protection scope required by the present invention.

[0057] It should be understood by those skilled in the art that the embodiments of the present invention may be provided as methods, systems or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware aspects. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program codes. Among them, the storage medium may be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read-Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, magnetic disk or optical disk. These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0058] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A substation inspection method based on image processing, It is characterized in that include: In response to an instruction to perform automatic inspection on a target substation, determining an expected inspection time period corresponding to the automatic inspection on the target substation; Determining whether the expected inspection time period is within a preset inspection time period; When the expected inspection time period is within a preset inspection time period, obtaining the expected lighting condition of the target substation corresponding to the expected inspection time period; Determining whether the expected lighting condition meets the preset lighting condition; When the expected lighting condition meets the preset lighting condition, a set of inspection points corresponding to the automatic inspection of the target substation is obtained, wherein the set of inspection points includes the inspection points corresponding to the automatic inspection of the target substation and the heights of the inspection points relative to the ground; Determine, according to the height, the type of target inspection equipment corresponding to the inspection task for executing the inspection point; According to the target inspection device type, obtaining the inspection device set corresponding to the target inspection device type; According to the inspection device set, a target inspection device corresponding to executing the inspection task is determined.

2. The substation inspection method based on image processing according to claim 1, It is characterized in that Obtaining the expected lighting conditions corresponding to the target substation during the expected inspection time period, including: Obtaining the weather forecast corresponding to the target substation during the expected inspection period, wherein the weather forecast includes weather conditions; Determine whether the weather condition meets the preset inspection weather conditions; When the weather condition meets the preset inspection weather condition, obtaining the historical light data of the target substation corresponding to the expected inspection time period; The illumination data corresponding to the target substation in the expected inspection time period is predicted according to the historical illumination data to obtain the expected illumination conditions.

3. The substation inspection method based on image processing according to claim 2, It is characterized in that Determining whether the weather condition meets the preset inspection weather conditions includes: Determine whether the weather condition is disastrous weather; When the weather condition does not belong to disastrous weather, it is determined that the weather condition meets the preset inspection weather condition.

4. The substation inspection method based on image processing according to claim 1, It is characterized in that Obtaining a set of inspection points corresponding to automatic inspection of the target substation, including: Performing three-dimensional grid processing on the target substation, and determining a feasible space corresponding to automatic inspection of the target substation; Taking the target substation as the center body, determining a three-dimensional rectangular space model enveloping the target substation; Taking the six faces of the cuboid space model as shooting targets, determining the inspection points corresponding to the automatic inspection of the target substation in the feasible space; All the inspection points are combined into a set to obtain an inspection point set.

5. The substation inspection method based on image processing according to claim 4, It is characterized in that Taking the six faces of the cuboid space model as shooting targets, determining the inspection points corresponding to the automatic inspection of the target substation in the feasible space, including: Taking each face of the cuboid space model as a sub-shooting target, determining a face position code of the sub-shooting target corresponding to the target substation; Based on a preset shooting potential algorithm, determining the inspection point corresponding to the sub-shooting target in the feasible space; According to the surface position code, all the inspection points are arranged to obtain the inspection points corresponding to the automatic inspection of the target substation.

6. The substation inspection method based on image processing according to claim 5, It is characterized in that Determining the inspection point corresponding to the sub-shooting target in the feasible space includes: Determine the inspection point corresponding to the sub-shooting target in the feasible space, and determine the point position code corresponding to the inspection point; The surface position code and the point position code are formed into a corresponding relationship as the point information of the inspection point.

7. The substation inspection method based on image processing according to claim 6, It is characterized in that After the surface position code and the point position code are formed into a corresponding relationship as the point information of the inspection point, the method further includes: Acquire a first image collected by a preset drone when performing an inspection mission, and determine first point information corresponding to the first image at the target substation; Acquire a second image collected by a preset intelligent robot when performing an inspection task, and determine second point information corresponding to the second image at the target substation; The first image and the second image are combined into a whole image according to the first point information and the second point information, so as to obtain an inspection image corresponding to the automatic inspection of the target substation.

8. The substation inspection method based on image processing according to claim 1, It is characterized in that Determining the type of target inspection equipment corresponding to the inspection task of the inspection point according to the height includes: Determining whether the height is greater than or equal to a preset height threshold; When the height is greater than or equal to a preset height threshold, the target inspection equipment type is determined to be a drone equipment type, and then a preset drone included in the drone equipment type is used to perform the inspection task; When the height is less than a preset height threshold, the target inspection equipment type is determined to be an intelligent robot equipment type, and then a preset intelligent robot included in the intelligent robot equipment type is used to perform the inspection task.

9. The substation inspection method based on image processing according to claim 1, It is characterized in that The method further comprises: When the expected inspection time period is not within the preset inspection time period, or when the expected lighting condition does not meet the preset lighting condition, a prompt is issued indicating that it is not suitable to perform automatic inspection on the target substation.

10. The substation inspection method based on image processing according to claim 1, It is characterized in that Determining whether the expected inspection time period is before the preset inspection time period further includes: Obtaining the geographical location and current date of the target substation; An inspection time period is set according to the geographical location and the current date to obtain a preset inspection time period.

Images