Method, device and system for creating digital twin model of power pipe gallery

Abstract

The invention relates to a method, a device and a system for creating a digital twin model of an electric power pipe gallery. The method comprises the following steps: dividing an electric power pipe gallery area into a plurality of sub-areas, respectively distributing the plurality of divided sub-areas to a plurality of robots deployed in the electric power pipe gallery, respectively creating task instructions of the robots, and respectively sending the task instructions to the robots, the task instructions are used for instructing the robots to collect, process and feed back point cloud data and environmental parameters of the corresponding sub-regions, integrating the processed point cloud data and environmental parameters fed back by the robots, and creating the digital twin model of the power pipe gallery based on the integrated point cloud data and environmental parameters. By adopting the method, the digital twin model of the power pipe gallery can be efficiently created.

Description

Technical Field

[0001] The present application relates to the technical field of digital twins, and in particular, to a method, device, system, computer device, computer-readable storage medium, and computer program product for creating a digital twin model of a power pipe gallery. Background Art

[0002] To create a digital twin model, generally, a three-dimensional model is manually drawn, or a mobile lidar scanner or an unmanned aerial vehicle (UAV) lidar scanner is used to assist in creating a virtual model.

[0003] With the acceleration of the urbanization process, as an important part of the urban power grid, the complexity and importance of power pipe galleries are becoming increasingly prominent. If a digital twin model of a power pipe gallery needs to be created, directly drawing the model manually is very inefficient, while using a mobile lidar scanner for assistance usually requires staff to carry a lidar scanner into the power pipe gallery scene, which poses a safety hazard, and UAVs are even unable to fly in the narrow and complex space environment of the power pipe gallery.

[0004] Therefore, there is a need to provide an efficient solution for creating a digital twin model of a power pipe gallery. Summary of the Invention

[0005] Based on this, in view of the above technical problems, it is necessary to provide a method, system, device, computer device, computer-readable storage medium, and computer program product for efficiently creating a digital twin model of a power pipe gallery.

[0006] In a first aspect, the present application provides a method for creating a digital twin model of a power pipe gallery, including:

[0007] Dividing the power pipe gallery area into multiple sub-areas, and respectively allocating the divided multiple sub-areas to multiple robots deployed in the power pipe gallery;

[0008] Respectively creating task instructions for each robot, and respectively sending the task instructions to each robot, where the task instructions are used to instruct the robot to collect, process, and feedback the point cloud data and environmental parameters of the corresponding sub-area;

[0009] Integrating the processed point cloud data and environmental parameters fed back by each robot;

[0010] Based on the integrated point cloud data and environmental parameters, creating a digital twin model of the power pipe gallery.

[0011] In a second aspect, the present application further provides a system for creating a digital twin model of a power pipe gallery, including: multiple robots and a control platform that are communicatively connected to each other, and each of the robots is respectively deployed in different areas of the power pipe gallery;

[0012] The control platform is configured to: divide the power pipe gallery area into multiple sub-areas, respectively assign the divided multiple sub-areas to multiple robots deployed in the power pipe gallery, respectively create task instructions for each robot, and send the task instructions to each robot;

[0013] The robot is configured to: respond to the received task instruction, collect, process and feedback the point cloud data and environmental parameters of the corresponding sub-area to the control platform according to the preset task plan;

[0014] The control platform is further configured to: integrate the processed point cloud data and environmental parameters fed back by each robot, and create a digital twin model of the power pipe gallery based on the integrated point cloud data and environmental parameters.

[0015] In a third aspect, the present application further provides a device for creating a digital twin model of a power pipe gallery, including:

[0016] An area division module, configured to divide the power pipe gallery area into multiple sub-areas, and respectively assign the divided multiple sub-areas to multiple robots deployed in the power pipe gallery;

[0017] An instruction sending module, configured to respectively create task instructions for each robot, and send the task instructions to each robot, where the task instructions are used to instruct the robot to collect, process and feedback the point cloud data and environmental parameters of the corresponding sub-area;

[0018] A data integration module, configured to integrate the processed point cloud data and environmental parameters fed back by each robot;

[0019] A model creation module, configured to create a digital twin model of the power pipe gallery based on the integrated point cloud data and environmental parameters.

[0020] In a fourth aspect, the present application further provides a computer device, including a memory and a processor, where the memory stores a computer program, and when the processor executes the computer program, the steps in any one of the above-mentioned embodiments of the method for creating a digital twin model of a power pipe gallery are implemented.

[0021] In a fifth aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps in any one of the above-mentioned embodiments of the method for creating a digital twin model of a power pipe gallery are implemented.

[0022] In a sixth aspect, the present application further provides a computer program product, including a computer program, and when the computer program is executed by a processor, the steps in any one of the above-mentioned embodiments of the method for creating a digital twin model of a power pipe gallery are implemented.

[0023] The above-mentioned method, system, device, computer equipment, computer-readable storage medium and computer program product for creating a digital twin model of a power pipe gallery first deploy multiple robots in a distributed manner in the power pipe gallery to cover key areas. Subsequently, by dividing a large area into multiple small areas and assigning them to different robots to work simultaneously, the data collection speed can be significantly accelerated. Moreover, each robot focuses on a specific sub-area it is responsible for, and can collect detailed point cloud data and environmental parameters in this area, thereby improving the accuracy and integrity of the overall data. Subsequently, the point cloud data and environmental parameters of the sub-areas that the robots are responsible for are integrated to create a digital twin model of the power pipe gallery. Throughout the modeling process, multiple robots with flexible movement are used to replace staff to enter the power pipe gallery for collaborative data collection. This can not only efficiently collect data, quickly generate a digital twin model of the power pipe gallery, but also reduce manpower requirements, solve potential safety hazards for personnel, and enhance the safety of the entire modeling process. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the drawings required for use in the description of the embodiments of the present application or related technologies. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings.

[0025] Figure 1 It is an application environment diagram of the method for creating a digital twin model of a power pipe gallery in an embodiment;

[0026] Figure 2 It is a flowchart of the method for creating a digital twin model of a power pipe gallery in an embodiment;

[0027] Figure 3 It is a flowchart of the step of dividing and assigning areas to robots in an embodiment;

[0028] Figure 4 It is a flowchart of the method for creating a digital twin model of a power pipe gallery in another embodiment;

[0029] Figure 5 It is a structural block diagram of a system for creating a digital twin model of a power pipe gallery in an embodiment;

[0030] Figure 6 It is a structural block diagram of a device for creating a digital twin model of a power pipe gallery in an embodiment;

[0031] Figure 7 It is an internal structure diagram of a computer device in an embodiment. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0032] In order to make the objectives, technical solutions, and advantages of this application clearer, the following further elaborates on this application in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely used to explain this application and are not used to limit this application.

[0033] The method for creating a digital twin model of a power pipe gallery provided by the embodiments of this application can be applied to an application environment as Figure 1 shown. Among them, the robot 102 communicates with the control platform 104 through a network. The data storage system can store the data that the control platform 104 needs to process. The data storage system can be integrated on the control platform 104, or placed on the cloud or other network servers.

[0034] Specifically, it can be that staff pre-deploy multiple flexible robots inside the power pipe gallery scene to cover the key areas of the power pipe gallery. Subsequently, the control platform 104 obtains the spatial information of the power pipe gallery area, divides the power pipe gallery area into multiple sub-areas, and assigns the divided multiple sub-areas to the multiple robots 102 deployed in the power pipe gallery respectively. Subsequently, task instructions for each robot 102 are created respectively, and the task instructions are sent to each robot respectively. After each robot receives the task instructions, they work together, and respectively collect the point cloud data and environmental parameters of the sub-areas they are responsible for according to the sensors and lidars carried by themselves, and the collected data is processed and then fed back to the control platform 104 in real time. The control platform 104 integrates the processed point cloud data and environmental parameters fed back by each robot, and creates a digital twin model of the power pipe gallery based on the integrated point cloud data and environmental parameters.

[0035] Among them, the robot 102 includes but is not limited to wheeled robots, tracked robots, and crawling robots, etc. The control platform 104 can be but is not limited to various personal computers, laptop computers, smart phones, tablet computers, Internet of Things devices, portable wearable devices, and servers, etc. Among them, the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0036] In an exemplary embodiment, as Figure 2 shown, a method for creating a digital twin model of a power pipe gallery is provided. Taking this method applied to the control platform 104 in Figure 1 as an example for illustration, it includes the following steps (hereinafter simply referred to as S) S202 to S206. Among them:

[0037] S202, divide the power pipe gallery area into multiple sub-areas, and assign the divided multiple sub-areas to the multiple robots deployed in the power pipe gallery respectively.

[0038] A power cable tunnel is a large tunnel or ditch underground in a city used to accommodate and protect power transmission and distribution cables, telecommunication cables, etc., and is usually called an integrated utility tunnel. In this embodiment, the robot is a flexible automated device deployed inside the power cable tunnel, responsible for performing specific tasks such as data collection and inspection.

[0039] In practical applications, it can be that the control platform uses the overall structure data of the power cable tunnel (hereinafter referred to as the tunnel) provided by the geographic information system, including coordinates, length, width, etc., and uses a partitioning algorithm to divide the entire area into multiple sub-areas, generate the boundary information of each sub-area, record the coordinates of the starting point and the ending point, and assign a unique identifier (ID) to each sub-area. Subsequently, according to the number and layout of the sub-areas, combined with the position and number of the robots, the number and position of the robots deployed in the tunnel are determined. Subsequently, the sub-areas can be bound to specific robots to ensure that each robot is responsible for one or more adjacent sub-areas.

[0040] S204, create task instructions for each robot respectively, and send the task instructions to each robot. The task instructions are used to instruct the robot to collect, process and feedback the point cloud data and environmental parameters of the corresponding sub-area.

[0041] The task instructions are information packets containing specific operation steps and parameters, used to guide the robot to complete tasks such as data collection and data processing. The point cloud data is a dense point set generated by the robot through three-dimensional laser scanning technology, accurately describing the geometric shape of the power cable tunnel. The environmental parameters include key factors affecting the safety of the tunnel and the operation of equipment, such as temperature, humidity, gas concentration (such as CO2, methane).

[0042] In specific implementation, the control platform can define the tasks for each sub-region based on the sub-regions responsible for each robot and the parameters of the robot, including the starting point, ending point, scanning frequency, parameter acquisition interval, etc. Subsequently, these parameters are combined into structured task instructions. Then, the task instructions are transmitted from the control platform to each robot using a wireless communication module (such as Wi-Fi, 4G, 5G, or a proprietary protocol) and a distributed algorithm. After receiving the task instructions, the robot starts lidar scanning within the area it is responsible for. During the scanning process, three-dimensional point cloud data is collected in real time, and environmental parameters (such as temperature, humidity, light intensity, etc.) are collected through additional sensors. After the data is collected, it can also be preliminarily processed through the built-in edge computing module, including denoising, filtering, etc. Then, the processed data is transmitted back to the control platform in real time or regularly through the wireless communication module. Considering the signal interference problem in the power pipe gallery environment, the robot can adopt multiple communication methods (such as Wi-Fi, Bluetooth, 4G, etc.) to ensure stable data transmission. Further, since the amount of collected data may be large, in order to reduce the data transmission volume and ensure data security, the robot can also compress and encrypt the data to be fed back.

[0043] S206, integrate the processed point cloud data and environmental parameters fed back by each robot.

[0044] After the control platform receives the point cloud data and environmental parameters fed back by the robot, it first checks the integrity of the data packet to ensure that there is no lost or damaged data. Subsequently, the encrypted and compressed data is decrypted and decompressed to restore the original data format. Then, the received point cloud data and environmental parameters are integrated, including but not limited to removing noise points, calibrating the coordinate system, adjusting the time stamp, and data fusion, etc., to improve the accuracy of subsequent processing.

[0045] S208, create a digital twin model of the power pipe gallery based on the integrated point cloud data and environmental parameters.

[0046] The digital twin model is a virtual digital copy that reflects the state, attributes, and behaviors of the physical entity in real time.

[0047] After integrating the point cloud data and environmental parameters, the control platform can use modeling algorithms such as point cloud segmentation and feature extraction algorithms to generate a high-precision digital twin model of the power cable tunnel. Further, the generated digital twin model can be quality evaluated to check for problems such as data inconsistency, insufficient coverage, or geometric distortion. If quality problems are found in the model, supplementary scanning instructions need to be sent to the relevant robots, requiring them to rescan specific areas or adjust scanning parameters. According to the evaluation results and actual application feedback, optimize the data processing algorithm and task allocation strategy to improve the overall efficiency and modeling accuracy of the system. Finally, the finally generated digital twin model can be exported in various formats (such as 3D point cloud, mesh model, etc.) and provided for the operation and maintenance management department of the power cable tunnel to use.

[0048] In the above method for creating a digital twin model of a power cable tunnel, first, multiple robots are distributedly deployed in the power cable tunnel to cover key areas. Subsequently, by dividing a large area into multiple small areas and assigning them to different robots to work simultaneously, the data acquisition speed can be significantly accelerated. Moreover, each robot focuses on a specific sub-area it is responsible for and can detail the acquisition of point cloud data and environmental parameters in that area, thereby improving the accuracy and integrity of the overall data. Subsequently, integrate the point cloud data and environmental parameters of the sub-areas that the robots feedback they are responsible for to create a digital twin model of the power cable tunnel. Throughout the modeling process, multiple robots with flexible movement are used to replace workers to enter the power cable tunnel for collaborative data acquisition. This can not only efficiently acquire data and quickly generate a digital twin model of the power cable tunnel but also reduce manpower requirements, solve personnel safety hazards, and enhance the safety of the entire modeling.

[0049] In an exemplary embodiment, as Figure 3 shown, S202 includes:

[0050] S222, obtain the spatial structure information and / or equipment distribution information of the power cable tunnel area, and the position information of each robot.

[0051] The spatial structure information of the power cable tunnel area refers to the physical layout of the power cable tunnel area, including but not limited to dimensional information such as length, width, and height, as well as the shape and connection method of the channels. The equipment distribution information refers to the position information of various equipment arranged in the power cable tunnel, such as the specific positions of important facilities such as cable brackets, joint boxes, and sensors. The position information of the robot refers to the real-time coordinates or relative positions of the robot performing the task in the tunnel.

[0052] In practical applications, it can be that the staff pre-collects the spatial structure information and equipment distribution information of the power cable tunnel through a sensor network, obtains the precise position of the robot deployed in the power cable tunnel through a positioning system, and then stores the spatial structure information, equipment distribution information, and the position information of the robot in the control platform.

[0053] In some other embodiments, it can also be that the control platform obtains the spatial structure information and equipment distribution information of the power cable tunnel in real time through an integrated sensor network (such as RFID tags, lidar scanners, cameras, etc.). At the same time, it uses a positioning system (such as GPS, UWB ultra-wideband technology, etc.) to obtain the precise position information of each robot, or receives the position information reported by the robot in real time.

[0054] S242, based on the spatial structure information and / or equipment distribution information, divide the power cable tunnel area into multiple sub-areas.

[0055] Subsequently, the control platform analyzes the spatial structure and equipment distribution of the tunnel, considers factors such as the importance of the equipment and the maintenance frequency, divides the entire tunnel into several sub-areas, assigns a specific identifier to each sub-area, and records its boundary information.

[0056] S262, based on the position information of each robot, allocate the divided multiple sub-areas to different robots respectively.

[0057] Then, according to the current position of the robot, it can also combine its status such as load capacity and battery life, consider the collaborative work of multiple robots, and through a distributed algorithm, allocate the divided sub-areas to different robots to be responsible for, so as to ensure that each robot can efficiently access the sub-area it is responsible for.

[0058] In this embodiment, according to the tunnel spatial structure information and the position of the robot, intelligently planning and allocating the tasks of the robot can optimize the allocation of resources.

[0059] In an exemplary embodiment, create the task instructions for each robot respectively, including: obtaining the scanning parameters and position information of each robot, and creating the task instructions for each robot based on the scanning parameters, position information of each robot, and the sub-area corresponding to the robot.

[0060] The scanning parameters of the robot refer to the sensor settings or configurations used by the robot when performing tasks, such as the scanning frequency, angle range, resolution, etc. of the lidar. These parameters determine the quality and type of data that the robot can obtain.

[0061] In specific implementation, the control platform first communicates with the robots, collects their current scanning parameters from each robot, and receives the real-time position information reported by the robots. It can also obtain the position information of the robots through the positioning system. Subsequently, based on the scanning parameters, position information, and sub-region details, the control platform will formulate specific task instructions, specifically including determining the optimal path that each robot should take, the specific tasks to be completed (such as checking the status of a certain section of cable), adjusting the sensor settings to adapt to specific task requirements, and dynamically adjusting the scanning parameters and movement paths of the robots according to the task requirements. In some other embodiments, it can also be to create the task instructions for each robot only based on the scanning parameters, position information, and the sub-regions responsible by the robots. The task instructions include the starting point, ending point, scanning frequency, parameter acquisition interval, etc. The robots themselves plan the paths for executing the tasks and dynamically adjust the scanning parameters according to the task requirements. It can be specifically set according to the actual situation and is not uniquely limited here.

[0062] In this embodiment, by considering the specific scanning parameters and current positions of each robot, the most suitable task instructions can be customized for each robot, and each robot can execute the tasks with its optimal performance and complete the specified work more accurately.

[0063] In an exemplary embodiment, S206 includes: removing redundant data in the processed point cloud data fed back by each robot, performing stitching, registration, and fusion processing on the processed point cloud data, and performing data preprocessing on the environmental parameters.

[0064] In specific implementation, the control platform for integrating point cloud data may include: removing redundant data from the processed point cloud data fed back by each robot, and performing stitching, registration, and fusion processing on the processed point cloud data. Among them, removing redundant data includes: through statistical analysis, finding duplicate or overly dense point clouds, or dividing the pipe gallery into multiple grid cells by spatially dividing points, and only retaining the key points within each cell to reduce the data volume, or identifying and removing noise points through the Random Sample Consensus (RANSAC) algorithm to maintain the main structural information. The stitching process includes: according to the previously divided regions, corresponding the scanning results of each robot to the corresponding sub-regions, and then, through feature extraction, performing point cloud matching at the junction of adjacent regions to ensure the coherence of the stitched data. The registration process includes: using an algorithm based on point-to-point or point-to-plane, extracting key feature points from each sub-region and performing matching to ensure the consistency of the coordinates of each part, and then adjusting the positions and postures of each sub-region according to the matching results to reduce the overall error. The fusion process may include: assigning different weights according to the data quality or importance of each sub-region, and performing fusion processing on the point cloud data of each sub-region to generate a more accurate overall model. Further, for the void regions in the point cloud (such as regions not scanned), interpolation methods or deep learning-based completion algorithms such as PointNet++ can be used to fill in the missing parts.

[0065] For the processing of environmental parameters, it may include denoising, interpolation, etc. to ensure the integrity and accuracy of the data.

[0066] In this embodiment, after removing redundant data, unnecessary calculations are reduced and the processing speed is improved. Through effective stitching, registration, and fusion, a high-precision three-dimensional model can be generated to accurately reflect the structure of the pipe gallery.

[0067] In an exemplary embodiment, as Figure 4 shown, S208 includes: S228, performing three-dimensional reconstruction on the integrated point cloud data to obtain an initial digital twin model of the power pipe gallery, and embedding the integrated environmental parameters into the initial digital twin model of the power pipe gallery to obtain the digital twin model of the power pipe gallery.

[0068] In this embodiment, after integrating the point cloud data and environmental parameters, it can be by projecting the point cloud data onto a two-dimensional image through a plane segmentation method, using edge detection and feature extraction techniques to identify the structure of the pipe gallery, and then, through plane fitting, restoring the three-dimensional geometric information to obtain an initial digital twin model of the power pipe gallery. In some other embodiments, it can also be through semantic segmentation by a deep learning model (such as Mask R-CNN, PointNet++) to identify objects (such as equipment, pipelines, etc.) and generate a high-precision initial digital twin model of the power pipe gallery.

[0069] Next, through spatial indexing techniques (such as grid partitioning or K-d trees), the environmental parameters can be associated with the position information of the 3D point cloud data. For example, corresponding parameter values such as temperature and humidity are assigned to each 3D coordinate point. Further, the environmental parameters can be embedded into the initial digital twin model of the power cable tunnel in the form of color mapping to obtain the digital twin model of the power cable tunnel. For example, temperature can be represented by a heat map (warm colors indicate high temperature and cold colors indicate low temperature), and gas concentration can be represented by transparency or color gradient. Through the dynamic interaction interface, users can view the distribution of environmental parameters in different regions in real time, and the digital twin model of the power cable tunnel supports historical data playback and predictive analysis functions.

[0070] Furthermore, after combining the environmental parameters with the digital twin model of the power cable tunnel, the digital twin model of the power cable tunnel can be updated in real time. For example, the color mapping can be dynamically adjusted according to the sensor data stream (such as Internet of Things devices).

[0071] In this embodiment, by embedding environmental parameters (such as temperature, humidity, gas concentration, etc.) into the digital twin model of the power cable tunnel, the model is not only a static display tool but also can be used as a dynamic monitoring platform, allowing staff to monitor the environmental conditions in the power cable tunnel in real time and predict possible future events based on historical data analysis, and taking preventive measures in advance.

[0072] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are shown in sequence according to the arrows, these steps do not necessarily need to be executed in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps has no strict order limitation, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time but can be executed at different times, and the execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.

[0073] Based on the same inventive concept, an embodiment of the present application further provides a system for creating a digital twin model of a power cable tunnel, as Figure 5 shown. The system includes: multiple robots 502 and a control platform 504 that are communicatively connected to each other. Each of the robots 502 is deployed in different regions of the power cable tunnel, where:

[0074] The control platform 504 is configured to: divide the power pipe gallery area into multiple sub-areas, allocate the divided multiple sub-areas to multiple robots deployed in the power pipe gallery respectively, create task instructions for each robot respectively, and send the task instructions to each robot respectively.

[0075] The robot 502 is configured to: in response to the received task instruction, collect, process and feedback the point cloud data and environmental parameters of the corresponding sub-area to the control platform according to the preset task plan.

[0076] The control platform is further configured to: integrate the processed point cloud data and environmental parameters fed back by each robot 502, and create a digital twin model of the power pipe gallery based on the integrated point cloud data and environmental parameters.

[0077] As described in the above embodiments, the control platform is responsible for overall task allocation, coordinating the work of multiple robots, and integrating the feedback data of all robots to create a digital twin model of the power pipe gallery. The robots are deployed in different areas of the power pipe gallery. According to the received task instructions, they collect the point cloud data and environmental parameters of the corresponding sub-areas, and feedback the processed data to the control platform.

[0078] In practical applications, it can be that the control platform divides the entire power pipe gallery area into multiple sub-areas according to the spatial structure information and / or equipment distribution information of the power pipe gallery area, and the position information of each robot. Subsequently, the control platform defines the tasks of each sub-area based on the sub-areas responsible for each robot and the parameters of the robot, including the starting point, ending point, scanning frequency, parameter acquisition interval, etc. Subsequently, these parameters are combined into structured task instructions. Subsequently, the task instructions are transmitted from the control platform to each robot using a wireless communication module (such as Wi-Fi, 4G, 5G or a proprietary protocol) and a distributed algorithm.

[0079] After receiving the task instruction, the robot will start lidar scanning in the area it is responsible for. During the scanning process, three-dimensional point cloud data is collected in real time, and environmental parameters (such as temperature, humidity, light intensity, etc.) are collected through additional sensors. After collecting the point cloud data and environmental parameters, the data can also be preliminarily processed through the built-in edge computing module, including denoising, filtering, etc. processing. Subsequently, the processed data is transmitted back to the control platform in real time or regularly through the wireless communication module.

[0080] After receiving the environmental parameters and point cloud data transmitted back by the robot, the control platform can first perform denoising, interpolation and outlier processing on the environmental parameters. Subsequently, redundant data in the point cloud data is removed, and the processed point cloud data is subjected to stitching, registration, fusion processing and hole filling processing. The specific processing process refers to the content in the above embodiments of the method for creating a digital twin model of the power pipe gallery, which will not be elaborated here.

[0081] After integrating the point cloud data and environmental parameters, it is possible to project the point cloud data into a two-dimensional image by means of plane segmentation, and use edge detection and feature extraction techniques to identify the structure of the utility tunnel. Then, the three-dimensional geometric information is restored by means of plane fitting to obtain an initial digital twin model of the power utility tunnel. Next, through a spatial indexing technique (such as grid partitioning or K-d tree), the environmental parameters can be associated with the position information of the three-dimensional point cloud data. For example, corresponding parameter values such as temperature and humidity are assigned to each three-dimensional coordinate point. Further, the environmental parameters can be embedded into the initial digital twin model of the power utility tunnel in the form of color mapping to obtain a digital twin model of the power utility tunnel. Through a dynamic interaction interface, users can view the distribution of environmental parameters in different regions in real time, and this model supports dynamic updates to reflect the changes in the physical environment in the tunnel in real time.

[0082] In the above digital twin model creation system for the power utility tunnel, multiple robots are first distributedly deployed in the power utility tunnel to cover key areas. Subsequently, by dividing a large area into multiple small areas and assigning them to different robots to work simultaneously, the data collection speed can be significantly accelerated. Moreover, each robot focuses on a specific sub-region it is responsible for and can collect the point cloud data and environmental parameters in this region in detail, thereby improving the accuracy and integrity of the overall data. Subsequently, the point cloud data and environmental parameters of the sub-region that the robot is responsible for are integrated to create a digital twin model of the power utility tunnel. In the whole system, multiple robots with flexible movement replace workers to enter the power utility tunnel to cooperate in data collection. This can not only efficiently collect data and quickly generate a digital twin model of the power utility tunnel, but also reduce the manpower requirement, solve the potential safety hazards of personnel, and enhance the safety of the entire modeling.

[0083] In some other exemplary embodiments, the robot is further configured to: adjust the task path and data collection strategy according to the real-time position information, load information, and environmental information of the area where it is located.

[0084] In the actual execution of tasks, the robot can dynamically adjust its task path and collection strategy according to its real-time position, load conditions and the complexity of the surrounding environment. Specifically, it can dynamically adjust the path and collect data according to the real-time position information by applying the improved A* algorithm or RRT (Rapidly-exploring Random Tree) algorithm. Considering the collaborative work of multiple robots, a distributed path planning strategy is adopted to avoid collisions and path conflicts between robots. At the same time, the robot is equipped with a weight sensor and a force feedback system to monitor the load status of the robot in real time, and dynamically adjust the priority and intensity of the data collection task according to the preset load threshold. For example, when the robot is overloaded, the path planning can be adjusted to avoid high-load areas or reduce the frequency of data collection in this area, or an alarm can be triggered immediately and the data collection task can be suspended to prevent equipment damage.

[0085] In this embodiment, the robot dynamically adjusts the task path and data collection strategy based on the position information and load conditions, which can reduce overload work, reduce the wear and failure rate of mechanical parts, and improve overall efficiency.

[0086] In an exemplary embodiment, the robot is also configured to: perform at least one of denoising, filtering, compression and feature extraction on point cloud data and environmental parameters through a built-in edge computing module, and extract target attribute data from the processed point cloud data, wherein the target attribute data includes the geometric shape of the object, the spatial topological structure of the current corridor, and the location information and status information of the equipment in the power corridor, and the processed point cloud data includes the target attribute data.

[0087] In specific implementation, after collecting point cloud data and environmental parameters, the robot can remove sensor noise and environmental interference (such as light reflection, vibration, etc.) data, remove abnormal points or low-quality data, retain high-quality point cloud data, and compress point cloud data to reduce the amount of data stored and transmitted. Subsequently, the processed point cloud data can be feature extracted through the built-in edge computing module, including extracting the geometric shape of the object, such as using the 3D shape matching algorithm to identify the three-dimensional shape information of the standard geometric shape of power equipment (such as switch cabinets, transformers, etc.); extracting the spatial topological structure of the current corridor, such as extracting the direction, branches and connection relationship of the corridor by calculating the distance and connection relationship between the point clouds, extracting the location information and status information of the equipment in the power corridor, that is, locating the equipment position in the corridor and monitoring its operating status (such as temperature, vibration, etc.).

[0088] In this embodiment, the robot can provide a basis for path planning and task execution by extracting the geometric shape and spatial layout of objects in the power pipeline corridor, and support fault prediction and maintenance decisions by real-time monitoring of equipment status.

[0089] Based on the same inventive concept, an embodiment of the present application further provides a device for creating a digital twin model of a power pipe gallery for implementing the method for creating a digital twin model of a power pipe gallery involved above. The solution provided by this device for solving problems is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the device for creating a digital twin model of a power pipe gallery provided below can refer to the limitations on the method for creating a digital twin model of a power pipe gallery in the above text, and will not be repeated here.

[0090] In an exemplary embodiment, as Figure 6 shown, a device 600 for creating a digital twin model of a power pipe gallery is provided, including: a region division module 610, an instruction sending module 620, a data integration module 630, and a model creation module 640, where:

[0091] The region division module 610 is configured to divide the power pipe gallery region into multiple sub-regions, and respectively allocate the divided multiple sub-regions to multiple robots deployed in the power pipe gallery.

[0092] The instruction sending module 620 is configured to respectively create task instructions for each robot, and send the task instructions to each robot. The task instructions are used to instruct the robot to collect, process, and feedback the point cloud data and environmental parameters of the corresponding sub-region.

[0093] The data integration module 630 is configured to integrate the processed point cloud data and environmental parameters fed back by each robot.

[0094] The model creation module 640 is configured to create a digital twin model of the power pipe gallery based on the integrated point cloud data and environmental parameters.

[0095] In some exemplary embodiments, the region division module 610 is further configured to obtain the spatial structure information and / or equipment distribution information of the power pipe gallery region, as well as the position information of each robot, divide the power pipe gallery region into multiple sub-regions based on the spatial structure information and / or equipment distribution information, and respectively allocate the divided multiple sub-regions to different robots based on the position information of each robot.

[0096] In some exemplary embodiments, the instruction sending module 620 is configured to obtain the scanning parameters and position information of each robot, and create task instructions for each robot based on the scanning parameters, position information of each robot, and the sub-region corresponding to the robot.

[0097] In some exemplary embodiments, the data integration module 630 is further configured to remove redundant data in the processed point cloud data fed back by each robot, and perform stitching, registration, and fusion processing on the processed point cloud data.

[0098] In some exemplary embodiments, the model creation module 640 is further configured to perform three-dimensional reconstruction on the integrated point cloud data to obtain an initial digital twin model of the power pipe gallery, and embed the integrated environmental parameters into the initial digital twin model of the power pipe gallery to obtain the digital twin model of the power pipe gallery.

[0099] Each module in the above-mentioned digital twin model creation device of the power pipe gallery can be implemented in whole or in part by software, hardware, and their combination. The above-mentioned modules can be embedded in the processor in the computer device in hardware form or be independent of the processor, or can be stored in the memory in the computer device in software form, so that the processor can call and execute the operations corresponding to the above-mentioned modules.

[0100] In an exemplary embodiment, a computer device is provided. The computer device can be a server, and its internal structure diagram can be as Figure 7 shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data such as robot position information, point cloud data, and environmental parameters. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it implements a method for creating a digital twin model of a power pipe gallery.

[0101] Those skilled in the art can understand that Figure 7 the structure shown in

[0102] is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have a different component layout.

[0103] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in any of the above-described embodiments of the method for creating a digital twin model of a power pipe gallery are implemented.

[0104] In one embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the steps in any of the above-described embodiments of the method for creating a digital twin model of a power pipe gallery are implemented.

[0105] It should be noted that the user information (including but not limited to user device information such as robot information, user personal information, etc.) and data (including but not limited to data for analysis such as point cloud data and environmental data, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with relevant regulations.

[0106] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in this application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in this application can be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, data processing logics based on quantum computing, artificial intelligence (AI) processors, etc., without limitation.

[0107] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered to be within the scope recorded in this application.

[0108] The above-described embodiments merely represent several implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all fall within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims

1. A method for creating a digital twin model of a power pipe gallery, characterized in that The method includes: Dividing the power pipe gallery area into multiple sub-areas, and respectively allocating the divided multiple sub-areas to multiple robots deployed in the power pipe gallery; Respectively creating task instructions for each robot, and sending the task instructions to each robot, where the task instructions are used to instruct the robot to collect, process, and feedback the point cloud data and environmental parameters of the corresponding sub-area; Integrating the processed point cloud data and environmental parameters fed back by each robot; Based on the integrated point cloud data and environmental parameters, creating a digital twin model of the power pipe gallery.

2. The method according to claim 1, wherein The dividing the power pipe gallery area into multiple sub-areas and respectively allocating the divided multiple sub-areas to multiple robots deployed in the power pipe gallery includes: Obtaining the spatial structure information and / or equipment distribution information of the power pipe gallery area, and the position information of each of the robots; Based on the spatial structure information and / or equipment distribution information, dividing the power pipe gallery area into multiple sub-areas; Based on the position information of each of the robots, respectively allocating the divided multiple sub-areas to different robots.

3. The method according to claim 1, wherein The respectively creating task instructions for each robot includes: Obtaining the scanning parameters and position information of each robot; Based on the scanning parameters, position information of each robot, and the sub-area corresponding to the robot, creating task instructions for each robot.

4. The method according to any one of claims 1 to 3, characterized in that Integrating the processed point cloud data fed back by each robot includes: Removing redundant data from the processed point cloud data fed back by each robot; Performing stitching, registration, and fusion processing on the processed point cloud data.

5. The method according to any one of claims 1 to 3, characterized in that The creating a digital twin model of the power pipe gallery based on the integrated point cloud data and environmental parameters includes: Performing three-dimensional reconstruction on the integrated point cloud data to obtain an initial digital twin model of the power pipe gallery; Embedding the integrated environmental parameters into the initial digital twin model of the power pipe gallery to obtain a digital twin model of the power pipe gallery.

6. A digital twin model creation system for a power pipe gallery, characterized in that, The system includes: multiple robots and a control platform that are communicatively connected to each other, and each of the robots is respectively deployed in different areas of the power pipe gallery; The control platform is configured to: divide the power pipe gallery area into multiple sub-areas, and respectively allocate the divided multiple sub-areas to multiple robots deployed in the power pipe gallery, respectively create task instructions for each robot, and send the task instructions to each robot respectively; The robot is configured to: respond to the received task instructions, and collect, process, and feedback the point cloud data and environmental parameters of the corresponding sub-area to the control platform according to a preset task plan; The control platform is further configured to: integrate the processed point cloud data and environmental parameters fed back by each robot, and create a digital twin model of the power pipe gallery based on the integrated point cloud data and environmental parameters.

7. The system according to claim 6, wherein The robot is further configured to: adjust the task path and data collection strategy according to the real-time position information, load information, and environmental information of its area.

8. The system according to claim 6, wherein The robot is further configured to perform at least one of denoising, filtering, compressing, and feature extraction on the point cloud data and the environmental parameters through a built-in edge computing module, and extract target attribute data from the processed point cloud data, where the target attribute data includes the geometric shape of an object, the spatial topology structure of a current pipe gallery, and the position information and status information of the devices in the power pipe gallery, and the processed point cloud data includes the target attribute data.

9. A device for creating a digital twin model of a power pipe gallery, characterized in that, The device includes: a region division module, configured to divide the power pipe gallery region into multiple sub-regions, and respectively allocate the divided multiple sub-regions to multiple robots deployed in the power pipe gallery; an instruction sending module, configured to create task instructions for each robot respectively, and send the task instructions to each robot respectively, where the task instructions are used to instruct the robot to collect, process, and feedback the point cloud data and environmental parameters of the corresponding sub-region; a data integration module, configured to integrate the processed point cloud data and environmental parameters feedback by each robot; a model creation module, configured to create a digital twin model of the power pipe gallery based on the integrated point cloud data and environmental parameters.

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

Images