A method for generating power plant video inspection strategies based on digital twins

Abstract

This invention provides a method for generating a power plant video inspection strategy based on digital twins, comprising the following steps: S1, supplementing the inspection points and industrial television system camera models based on a 3D model to improve the power plant digital twin model; S2, marking the attributes of each inspection point and industrial television system camera; S3, conducting spatial visibility analysis of the inspection points from the industrial television cameras, recording the spatial visibility into the inspection point-camera binary pair; S4, generating preset points for the industrial television system cameras and forming a triplet inspection strategy of inspection point-camera-preset point. This invention, based on the spatial analysis capabilities of 3D models, achieves automatic analysis of many-to-many spatial visibility between industrial television system cameras and inspection points, as well as automatic calculation of camera preset points and automatic generation of the inspection point-camera-preset point triplet inspection strategy, improving the efficiency of inspection strategy generation and configuration, and avoiding the defects of manual configuration.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of equipment inspection, and particularly relates to a power station video inspection strategy generation method based on digital twinning. BACKGROUND

[0002] As a key energy storage facility of new power systems, the safe and stable operation of pumped storage power stations is of great significance to the stable operation of new energy consumption and power systems. Regular inspection is an effective means for power stations to timely grasp the operation status of equipment and ensure the safe and stable operation of equipment, and is therefore carried out regularly in pumped storage power stations. At present, the inspection is generally carried out by staff with paper inspection forms or handheld inspection terminals along the preset inspection route, and the equipment on the inspection route that needs to be inspected is manually inspected and recorded.

[0003] With the construction needs of new power systems, pumped storage has entered a large-scale development stage, and the operation and maintenance presents a contradiction between large personnel demand and few professionals. Therefore, gradually reducing the number of on-site personnel using digital technology is a common industry demand. For this reason, the industry has carried out a lot of research on artificial inspection replacement technologies, including robot inspection, unmanned aerial vehicle inspection, and video inspection. Among them, video inspection will be a necessary part of future unmanned inspection because it can use the existing industrial television system of power stations. At present, the recognition algorithm related to video inspection is very mature, and it can effectively replace on-site manual inspection with high recognition accuracy for common cabinet and device indicator lights, pressure plate status, handle position, digital and pointer meter (including liquid level meter) reading, valve position, switch body opening and closing position, oil level, knife switch, and ground knife mechanical position indication. However, the current video inspection mainly adopts the way of manually configuring camera preset positions, forming a preset position-inspection point binary group inspection strategy. This method requires operation and maintenance personnel to manually form an inspection strategy before carrying out video inspection, and enter the preset positions corresponding to the strategy into the industrial television system. The preset positions include camera pose and zoom ratio, and the pose includes horizontal and pitch rotation angle. Therefore, the operation and maintenance personnel need to manually judge and test and adjust the preset attributes of hundreds of industrial television cameras and thousands of inspection points on site, complete the identification and establishment of the many-to-many relationship between the cameras and the inspection points, and therefore the number of preset positions may be up to thousands, which will bring heavy workload to the on-site operation and maintenance personnel, and is prone to omissions, misconfigurations, errors, and mistakes.

[0004] Chinese Patent Publication No. CN118233597A discloses an intelligent inspection method, system, and storage medium for hydropower stations. This invention utilizes intelligent video inspection of key equipment and areas, capturing and identifying equipment in key areas according to the inspection process to filter out hazardous areas. When inspection personnel enter a hazardous area, timely boundary alarms or inspection precaution reminders are provided, significantly improving the efficiency and intelligence of inspection tasks. While this invention proposes setting preset camera positions according to actual scenario needs, it does not address how to set preset positions for industrial television system cameras. Chinese Patent Publication No. CN111597231A discloses an intelligent substation inspection system based on multi-source heterogeneous system data mining. This system achieves linked inspections based on equipment IDs in the production management system by integrating multiple systems. However, it also does not address how to set preset points for industrial television cameras and generate inspection strategies, and requires manual definition of the preset points to be inspected. It is evident that while existing technologies have proposed video inspection systems and methods, they have not yet proposed a method for generating video inspection strategies for industrial television systems. Manual configuration will introduce a large amount of workload and will inevitably lead to omissions, misconfigurations, incorrect recordings, and other issues, which will directly affect the efficiency, quality, and even feasibility of video inspection. Summary of the Invention

[0005] The main objective of this invention is to provide a method for generating power plant video inspection strategies based on digital twins, addressing the aforementioned problems.

[0006] Therefore, the above-mentioned objective of the present invention is achieved through the following technical solution:

[0007] A method for generating a power plant video inspection strategy based on digital twins includes the following steps:

[0008] S1. Based on the completed 3D model of the power plant, supplement the inspection points and the camera models of the industrial television system to improve the digital twin model of the power plant.

[0009] S2. Mark the attributes of each inspection point and industrial television system camera within the digital twin model of the power plant;

[0010] S3. Based on the digital twin model of the power plant, conduct spatial visibility analysis of industrial TV cameras on inspection points, including visual angle visibility and field of view visibility, and record the spatial visibility in the inspection point-camera binary.

[0011] S4. Based on the spatial visibility analysis results, generate preset points for industrial television system cameras and form a three-element inspection strategy of inspection point-camera-preset point.

[0012] While adopting the above technical solutions, the present invention may also adopt or combine the following technical solutions:

[0013] As a preferred technical solution of the present application: in step S2, the inspection point attribute at least includes device code, inspection object type, spatial plane, plane size and visible view angle α。

[0014] As a preferred technical solution of the present application: the inspection point attribute further includes normal vector, the origin of the normal vector is the center point of the spatial plane, and the normal vector is perpendicular to the spatial plane.

[0015] As a preferred technical solution of the present application: in step S2, the camera attribute at least includes device code, initial position, sensor size h , aperture value N , zoom range, horizontal rotation angle range of the holder, vertical rotation angle range of the holder, visible angle range and visible distance range.

[0016] As a preferred technical solution of the present application: the visible angle range of the camera includes horizontal visible angle range and vertical visible angle range, the horizontal visible angle range is determined in combination with the initial normal vector and the horizontal rotation angle range of the holder, the vertical visible angle range is determined in combination with the initial normal vector and the vertical rotation angle range of the holder, and the initial normal vector is obtained according to the initial position of the camera.

[0017] As a preferred technical solution of the present application: the visible distance range of the camera is the range between the nearest visible distance L min and the farthest visible distance L max , and the calculation formula is as follows:

[0018] L min = uf min 2 / ( f min 2 + uNC );

[0019] L max = uf max 2 / ( f max 2 - uNC );

[0020] C = h / 1000;

[0021] In the formula, u is the object distance, fmin fmin is the minimum focal length, f min fmax is the maximum focal length, N F is the aperture value, C E is the allowable circle of confusion radius, h S is the sensor size.

[0022] As a preferred technical solution of the present application: step S3 further comprises the following sub-steps:

[0023] S31, judge whether the inspection point is within the visual distance range of the camera, if not, the field of view is not visible, and the next inspection point is repeated step S31, otherwise the next step is entered;

[0024] S32, construct the space vector between the inspection point and the camera of the industrial television system, the space vector direction is the camera of the industrial television system pointing to the center point of the space plane of the inspection point, judge whether the space vector is within the visual angle range of the camera of the industrial television system, if not, the visual angle is not visible, and the next inspection point is returned to step S31, otherwise the next step is entered;

[0025] S33, calculate the included angle a between the normal vector of the inspection point and the space vector, if 180°-a>α, the visual angle is not visible, and the next inspection point is returned to step S31, otherwise the next step is entered;

[0026] S34, collision analysis is performed on the space vector in the digital twin model of the power station, if there is a collision point, the field of view is not visible, and the next inspection point is returned to step S31, otherwise the inspection point-camera binary tuple is recorded, the next industrial television system camera is entered, and step S31 is returned until the space visibility analysis of all inspection points and cameras is completed.

[0027] As a preferred technical solution of the present application: step S4 further comprises the following sub-steps:

[0028] S41, for the camera-inspection point binary tuple, construct the space vector of the camera and the inspection point, the space vector direction is the camera pointing to the center point of the space plane of the inspection point;

[0029] S42, calculate the horizontal rotation angle of the holder and the pitch rotation angle of the holder according to the space vector;

[0030] S43, according to the distance between the camera and the inspection point, calculate the focal length f , if f is greater than the maximum focal length f max or less than the minimum focal length f min , then enter the next camera-inspection point binary tuple, and return to step S41, the formula is as follows:

[0031] f =2 uH / h ;

[0032] wherein, u is the object distance between the camera and the inspection point, H is the diagonal length of the inspection point space plane, h is the sensor size;

[0033] S44, configure the pan angle, tilt angle and focal length of the gimbal as a preset point to form an inspection point-camera-preset point three-element group inspection strategy, and turn to the next camera-inspection point two-element group and return to step S41.

[0034] As a preferred technical solution of the present application: further comprising step S5, inspection point inspection strategy optimization, specifically comprising the following sub-steps:

[0035] S51, for each inspection point-camera-preset point three-element group inspection strategy to which the inspection point belongs, calculate the spatial view angle b , the formula is as follows:

[0036] b =180°- a ;

[0037] wherein, a is the angle between the spatial vector between the inspection point and the camera and the normal vector of the inspection point, and the direction of the spatial vector is that the camera points to the center point of the inspection point space plane;

[0038] S52, define the inspection strategy with the smallest spatial view angle as the first inspection strategy of the inspection point;

[0039] S53, if the distance between the camera and the inspection point in the first inspection strategy is greater than the middle value of the camera visual distance range and there is another inspection strategy, define the inspection strategy with the second smallest spatial view angle as the second inspection strategy of the inspection point.

[0040] Compared with the prior art, the present application has the following beneficial effects:

[0041] Based on the spatial analysis capability of the three-dimensional model, the present application realizes the automatic analysis of the spatial visibility between the camera and the inspection point of the industrial television system, the automatic calculation of the camera preset point, and the automatic generation of the inspection point-camera-preset point three-element group inspection strategy, improves the inspection strategy generation and strategy configuration efficiency, and can avoid the situations of missing configuration, misconfiguration, missing recording, and misrecording existing in manual configuration. BRIEF DESCRIPTION OF DRAWINGS

[0042] Figure 1A flowchart of a power station video inspection strategy generation method based on digital twinning provided by the present application.

[0043] Figure 2 A flowchart of the inspection strategy optimization step of the inspection point. DETAILED DESCRIPTION

[0044] The present application will be further described in detail below in combination with the drawings and specific embodiments.

[0045] As shown in the drawings, Figure 1 A power station video inspection strategy generation method based on digital twinning, specifically comprising the following steps:

[0046] S1, based on the power station completion three-dimensional model, supplement the inspection points and the industrial television system camera model, perfect the power station digital twinning model;

[0047] S2, attribute marking is carried out on each inspection point and industrial television system camera in the power station digital twinning model;

[0048] The inspection point attribute at least includes equipment code, inspection object type, spatial plane, plane size and visual angle α。

[0049] Taking the power cabinet inspection point of the freezer room of a certain pumped storage power station as an example, the inspection object type of this inspection point includes state indicator light, rectangular digital display meter, square pointer meter, on-off switch, etc., among which the visual angle of the indicator light is as high as 70 degrees, the visual angle of the digital display meter is also as high as 50 degrees, the visual angle of the pointer meter is only 5 degrees, and the visual angle of the on-off switch is also as high as 70 degrees, so the visual angle of this inspection point is 5 degrees.

[0050] The inspection point attribute also includes normal vector, the starting point of the normal vector is the center point of the spatial plane, the normal vector is perpendicular to the spatial plane and points inward, and the spatial plane is the front cabinet surface of the power cabinet.

[0051] The visual angle of the inspection point is determined according to the inspection object type, and the minimum value of the visual angles of each inspection object in the inspection point is taken as the visual angle of the inspection point.

[0052] The camera attribute at least includes equipment code, initial position, sensor size h , aperture value N , zoom range, horizontal rotation angle range of the pan-tilt, vertical rotation angle range of the pan-tilt, visual angle range and visual distance range.

[0053] The camera's viewing angle range includes the horizontal viewing angle range and the vertical viewing angle range. The horizontal viewing angle range is determined by combining the initial normal vector and the pan-tilt unit's horizontal rotation angle range. The vertical viewing angle range is determined by combining the initial normal vector and the pitch rotation angle range. The initial normal vector is obtained based on the camera's initial position, which is generally provided by the installation unit, including the installation height and installation angle. If the installation unit does not provide this information, it can be obtained by measuring on-site.

[0054] Currently, commonly used cameras in power plants mainly include two types: bullet cameras and PTZ cameras. Bullet cameras only offer zoom capability and do not support rotation; therefore, the horizontal and vertical rotation angles of the PTZ unit are both 0. The sensor size... h Aperture value N The zoom range and zoom range are parameters of the camera lens.

[0055] The camera's field of view range is the closest visible distance. L min and maximum visible distance L max The range between them is calculated using the following formula:

[0056] L min = uf min 2 / ( f min 2 + uNC );

[0057] L max = uf max 2 / ( f max 2 - uNC );

[0058] C = h / 1000;

[0059] In the formula, u For object distance, f min For the minimum focal length, f min For maximum focal length, N This is the aperture value. C To allow for the radius of the dispersion circle, h This refers to the sensor size.

[0060] Currently, the PTZ cameras from mainstream video surveillance manufacturers such as Hikvision and Dahua, which are commonly used in power plants, have a maximum viewing distance of tens or even hundreds of meters.

[0061] S3. Based on the digital twin model of the power plant, conduct spatial visibility analysis of industrial TV cameras on inspection points, including visual angle visibility and field of view visibility, and record the spatial visibility in the inspection point-camera binary.

[0062] Visuality of view mainly analyzes whether the inspection point is within the camera's field of view and whether the azimuth angle between the camera and the inspection point is less than the inspection point's field of view. Visuality of field of view mainly analyzes whether the inspection point is within the camera's field of view and whether there are any obstructions between them.

[0063] S31. Determine whether the inspection point is within the camera's line of sight. L min , L max If not (the distance between the two) L < L min or L > L max If the field of view is not visible, proceed to the next inspection point and repeat step S31; otherwise, proceed to the next step.

[0064] S32. Construct a spatial vector between the inspection point and the industrial television system camera to represent the azimuth angle of the inspection point relative to the camera. The direction of the spatial vector is from the industrial television system camera to the center point of the spatial plane of the inspection point. Determine whether the spatial vector is within the viewing angle range of the industrial television system camera. If the azimuth angle between the two is greater than the viewing angle of the inspection point, it means that the video frame obtained by the camera cannot be used to accurately identify the status or numbers of each inspection object on the inspection. Therefore, the camera is not visible to the inspection point. Move to the next inspection point and return to step S31. Otherwise, proceed to the next step.

[0065] S33. Calculate the angle α between the normal vector of the inspection point and the spatial vector. If 180°-a>α, then the azimuth angle between the camera and the inspection point is greater than the visible angle of the inspection point. The video frame obtained by the camera cannot be used to accurately identify the status or numbers of each inspection object on the inspection. Therefore, the camera is not visible to the inspection point. Move to the next inspection point and return to step S31. Otherwise, proceed to the next step.

[0066] S34. Perform collision analysis on spatial vectors within the digital twin model of the power station. If a collision point exists, it indicates that the camera cannot obtain a complete and accurate video frame of the inspection point, and the camera is not visible to the inspection point. Proceed to the next inspection point and return to step S31. Otherwise, record it in the inspection point-camera binary pair, proceed to the next industrial television system camera, and return to step S31 until the spatial visibility analysis of all inspection points and cameras is completed.

[0067] S4, generating a preset point of the camera of the industrial television system based on the result of the spatial visibility analysis, and forming a three-element inspection strategy of the inspection point-camera-preset point.

[0068] S41, constructing a spatial vector of the camera and the inspection point for the camera-inspection point two-element group, and the direction of the spatial vector is the direction of the camera pointing to the center point of the spatial plane of the inspection point;

[0069] S42, calculating the horizontal rotation angle of the holder and the pitch rotation angle of the holder according to the spatial vector;

[0070] S43, calculating the focal length according to the distance between the camera and the inspection point f , if f is greater than the maximum focal length f max or is less than the minimum focal length f min , then turn to the next camera-inspection point two-element group and return to step S41, and the formula is as follows:

[0071] f =2 uH / h ;

[0072] In the formula, u is the object distance between the camera and the inspection point, H is the diagonal length of the spatial plane of the inspection point, h is the sensor size;

[0073] S44, configuring the horizontal rotation angle of the holder, the pitch rotation angle of the holder and the focal length as the preset point to form the three-element inspection strategy of the inspection point-camera-preset point, and turning to the next camera-inspection point two-element group and returning to step S41.

[0074] Because temporary obstacles may appear between the camera and the inspection point during actual use on site, the automatically generated inspection strategy cannot complete the identification and inspection of the inspection point based on image recognition after being called. Therefore, multiple inspection strategies can be further configured according to the characteristics of the inspection strategy itself, as shown in Figure 2 , and further comprising step S5, inspection strategy optimization of the inspection point:

[0075] S51, calculating the spatial viewing angle b for each inspection point-camera-preset point three-element inspection strategy to which the inspection point belongs, and the formula is as follows:

[0076] b =180°- a ;

[0077] In the formula, ais an angle between a space vector between the inspection point and the camera and a normal vector of the inspection point, and the space vector direction is a direction in which the camera points to a center point of a space plane of the inspection point;

[0078] S52, defining the inspection strategy with the minimum space view angle as a first inspection strategy of the inspection point;

[0079] S53, if the distance between the camera and the inspection point in the first inspection strategy is greater than a middle value of the visible distance range of the camera and other inspection strategies exist, defining the inspection strategy with the second minimum space view angle as a second inspection strategy of the inspection point.

[0080] After the inspection strategies of all the inspection points are generated, the actual inspection task of the power station can call the inspection strategies to complete the inspection work of the inspection points, and if the image recognition model of the inspection system background finds that the state or value of the inspection object of a certain inspection point cannot be accurately recognized, the second inspection strategy of the inspection point can be called to perform supplementary inspection, so as to complete the inspection work of all the inspection points.

[0081] So far, the technical solutions of the present application have been described in combination with the specific experimental processes shown in the accompanying drawings, but the protection scope of the present application is not limited to these specific embodiments. Those skilled in the art can make equivalent changes or replacements to the related technical features without departing from the principles of the present application, and the technical solutions after the changes or replacements will all fall within the protection scope of the present application.

Claims

1. A method for generating a power station video inspection strategy based on digital twinning, characterized in that, The method comprises the following steps: S1, based on the completion of the power station three-dimensional model of supplementary inspection points and industrial television system camera model, perfect power station digital twin model; S2, attribute marking is carried out on each inspection point and industrial television system camera in the power station digital twin model; S3, based on the power station digital twin model, the space visibility analysis of industrial television camera to inspection point is carried out, including visual angle visibility and visual field visibility, and the space visibility is recorded in the inspection point-camera binary group; S4, based on the space visibility analysis result, the preset point of industrial television system camera is generated, and the three-element inspection strategy of inspection point-camera-pre-set point is formed; In step S2, the inspection point attribute at least includes equipment code, inspection object type, space plane, plane size and visible angle α; The inspection point visible angle is determined according to the inspection object type, and the minimum value of the visible angle of each inspection object in the inspection point is taken as the visible angle of the inspection point. The camera attribute at least includes equipment code, initial position, sensor size h, aperture value N, zoom range, horizontal rotation angle range of the holder, vertical rotation angle range of the holder, visible angle range and visible distance range; Step S3 further comprises the following substeps: S31, it is judged whether the inspection point is in the visible distance range of the camera, if not, the visual field is not visible, and the next inspection point is repeated step S31, otherwise, the next step is entered; S32, the space vector between the inspection point and the industrial television system camera is constructed, the space vector direction is that the industrial television system camera points to the space plane center point of the inspection point, it is judged whether the space vector is in the visible angle range of the industrial television system camera, if not, the visual angle is not visible, the next inspection point is entered and returns to step S31, otherwise, the next step is entered; S33, the included angle a between the normal vector of the inspection point and the space vector is calculated, if 180°-a>α, the visual angle is not visible, the next inspection point is entered and returns to step S31, otherwise, the next step is entered; S34, collision analysis is carried out on the space vector in the power station digital twin model, if there is a collision point, the visual field is not visible, the next inspection point is entered and returns to step S31, otherwise, the inspection point-camera binary group is recorded, the next industrial television system camera is entered, and returns to step S31 until the space visibility analysis of all inspection points and cameras is completed.

2. The method of claim 1, wherein: The inspection point attribute further includes the normal vector, the normal vector starts from the space plane center point, and the normal vector is perpendicular to the space plane.

3. The method of claim 1, wherein: The camera visible angle range includes horizontal visible angle range and vertical visible angle range, the horizontal visible angle range is determined in combination with the initial normal vector and the horizontal rotation angle range of the holder, the vertical visible angle range is determined in combination with the initial normal vector and the vertical rotation angle range, and the initial normal vector is obtained according to the initial position of the camera.

4. The method of claim 1, wherein: The camera visual distance range is between the nearest visual distance L min and the farthest visual distance L max , and the calculation formula is as follows: L min =uf min 2 / (f min 2 +uNC); L max =uf max 2 / (f max 2 -uNC); C = h / 1000; In the formula, u is the object distance, and f min For the minimum focal length, f min Where N is the maximum focal length, C is the aperture value, C is the radius of the circle of confusion, and h is the sensor size.

5. The method of claim 1, wherein: Step S4 further comprises the following substeps: S41, for the camera-inspection point binary group, the space vector of the camera and the inspection point is constructed, and the space vector direction is that the camera points to the space plane center point of the inspection point; S42, the horizontal rotation angle of the holder and the vertical rotation angle of the holder are calculated according to the space vector; S43, according to the distance between the camera and the inspection point, calculate the focal length f, if f is greater than the maximum focal length f max or less than the minimum focal length f min , then go to the next camera-inspection point pair, and return to step S41, the formula is as follows: f =2uH / h; Wherein, u is the object distance between the camera and the inspection point, H is the diagonal length of the inspection point space plane, and h is the sensor size; S44, configure the gimbal horizontal rotation angle, the gimbal pitch rotation angle, and the focal length as the preset point to form the inspection point-camera-pre-set point three-element group inspection strategy, switch to the next camera-inspection point two-element group, and return to step S41.

6. The method of claim 1, wherein: Further comprising step S5, inspection point inspection strategy optimization, specifically comprising the following sub-steps: S51, for each inspection point-camera-pre-set point three-element group inspection strategy to which the inspection point belongs, calculate the space view angle b, the formula is as follows: b=180°-a; Wherein, a is the included angle between the space vector between the inspection point and the camera and the normal vector of the inspection point, and the space vector direction is that the camera points to the center point of the inspection point space plane; S52, define the inspection strategy with the smallest space view angle as the first inspection strategy of the inspection point; S53, if the distance between the camera and the inspection point in the first inspection strategy is greater than the middle value of the camera visual distance range and there is another inspection strategy, define the inspection strategy with the second smallest space view angle as the second inspection strategy of the inspection point.

Images