Unmanned aerial vehicle urban gas pipeline inspection method and system based on digital twinning

Abstract

The invention discloses an unmanned aerial vehicle urban gas pipeline inspection method and system based on digital twinning. The method comprises the steps that a digital twinning model of an urban gas pipeline is constructed in advance; the urban gas pipeline is inspected through the unmanned aerial vehicle to obtain inspection data, and the inspection data is sent to the digital twinborn model through the 5G technology; and presenting the inspection data and an inspection result determined based on the inspection data through the digital twinborn model. According to the invention, the digital twinborn technology, the 5G communication technology, the artificial intelligence technology and the unmanned aerial vehicle technology are integrated, the digital twinborn model is constructed by using the digital twinborn technology, the inspection data is collected by using the unmanned aerial vehicle, and the inspection data is transmitted to the digital twinborn model through the 5G communication technology. And finally, performing fault detection based on the inspection data by using an artificial intelligence technology, and displaying the inspection data and an inspection result. In this way, efficient, accurate and real-time routing inspection of urban gas pipelines is achieved, and routing inspection data can be provided for users in real time.

Description

Technical Field

[0001] This application relates to the technical field of gas inspection, and particularly to a method and system for inspecting urban gas pipelines by an unmanned aerial vehicle (UAV) based on digital twin. Background Art

[0002] With the wide application of gas in the energy field, ensuring the safe operation of gas pipelines has become crucial. With the increasing demand for gas pipeline inspection, traditional inspections mainly rely on manual inspections and ground UAV inspections. However, traditional manual inspections can only cover a limited area per person per day, and the inspection cycle is long, making it difficult to cover all pipeline areas. Although ground UAVs can conduct inspections along preset paths, their moving speed is slow and they are greatly restricted by terrain.

[0003] Therefore, the existing technology still needs to be improved. Summary of the Invention

[0004] The technical problem to be solved by this application is to provide a method and system for inspecting urban gas pipelines by an unmanned aerial vehicle based on digital twin in view of the deficiencies of the existing technology.

[0005] To solve the above technical problem, in the first aspect of this application, a method for inspecting urban gas pipelines by an unmanned aerial vehicle based on digital twin is provided. Specifically, the method for inspecting urban gas pipelines by an unmanned aerial vehicle based on digital twin specifically includes: Pre-construct a digital twin model of urban gas pipelines; Inspect urban gas pipelines by an unmanned aerial vehicle to obtain inspection data of urban gas pipelines, and send the inspection data to the digital twin model through 5G technology; Present the inspection data and the inspection results determined based on the inspection data through the digital twin model, where the inspection results are determined by a fault detection model deployed based on the digital twin model based on the inspection data.

[0006] In the method for inspecting urban gas pipelines by an unmanned aerial vehicle based on digital twin, specifically, the pre-construction of the digital twin model of urban gas pipelines specifically includes: Obtain the actual layout data and fault detection requirements of urban gas pipelines; Use digital twin technology to construct a digital twin model for urban gas pipelines based on the actual layout data; Based on the fault detection requirements, construct an artificial intelligence model for the urban gas pipelines, and deploy the artificial intelligence model set on the digital twin model.

[0007] The described method for inspecting urban gas pipelines by drones based on digital twins, wherein the drone is equipped with a high-definition camera, an infrared thermal imager, an environmental gas detector, and a lidar.

[0008] The described method for inspecting urban gas pipelines by drones based on digital twins, wherein the process of using the drone to inspect urban gas pipelines to obtain inspection data of urban gas pipelines specifically includes: Controlling the drone to perform inspections according to a preset inspection path; Real-time collecting pipeline data of urban gas pipelines and environmental data of the surrounding environment of urban gas pipelines through the drone to obtain inspection data.

[0009] The described method for inspecting urban gas pipelines by drones based on digital twins, wherein a path planning model is deployed in the digital twin model; the process of controlling the drone to perform inspections according to a preset inspection path specifically includes: Constructing an inspection path for the drone and controlling the drone to perform inspections according to the inspection path; Periodically reading the historical prior data of the urban gas pipelines, wherein the historical prior data includes historical inspection data and historical inspection paths; According to the obtained historical prior data of the urban gas pipelines and the actual layout data of the urban gas pipelines, using the path planning model in the digital twin model to construct a planned inspection path for the drone; Taking the planned inspection path as the inspection path of the drone and controlling the drone to perform inspections according to the preset inspection path.

[0010] The described method for inspecting urban gas pipelines by drones based on digital twins, wherein an overlap prediction model is deployed in the digital twin model; there are multiple drones for inspecting urban gas pipelines, and before taking the planned inspection path as the inspection path of the drone, the method further includes: Obtaining the historical inspection paths of each drone except the drone corresponding to the planned inspection path; Based on the planned inspection path and the obtained historical inspection paths, inputting them into the overlap prediction model, and determining the overlap degree corresponding to the planned inspection path through the overlap prediction model; If the overlap degree is less than a preset overlap degree threshold, taking the planned inspection path as the inspection path of the drone; If the degree of overlap is greater than or equal to a preset overlap threshold, update the historical inspection path of the drone corresponding to the planned inspection path using the planned inspection path, and re - execute the step of constructing a planned inspection path for the drone by using the path planning model through the digital twin model according to the obtained historical prior data of the urban gas pipeline and the actual layout data of the urban gas pipeline.

[0011] The above - mentioned method for inspecting urban gas pipelines by drones based on digital twins, wherein a fault prediction model is deployed in the digital twin model; the method further includes: Read the historical inspection data of the urban gas pipeline at preset time intervals; Based on the historical inspection data, perform risk prediction on the urban gas pipeline through the fault prediction model to obtain a risk prediction result; Perform preventive maintenance operations based on the risk prediction result.

[0012] The second aspect of the present application provides a system for inspecting urban gas pipelines by drones based on digital twins, wherein the system for inspecting urban gas pipelines by drones based on digital twins specifically includes: A construction module for pre - constructing a digital twin model of an urban gas pipeline; An inspection module for inspecting an urban gas pipeline by a drone to obtain inspection data of the urban gas pipeline, and sending the inspection data to the digital twin model through 5G technology; A detection module for presenting the inspection data and an inspection result determined based on the inspection data through the digital twin model, wherein the inspection result is determined based on the inspection data by a fault detection model deployed in the digital twin model.

[0013] The third aspect of the present application provides a computer - readable storage medium, which stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps in any of the above - mentioned methods for inspecting urban gas pipelines by drones based on digital twins.

[0014] The fourth aspect of the present application provides a terminal device, which includes: a processor and a memory; A computer - readable program executable by the processor is stored on the memory; When the processor executes the computer - readable program, it implements the steps in any of the above - mentioned methods for inspecting urban gas pipelines by drones based on digital twins.

[0015] Beneficial effects: Compared with the prior art, the present application provides a method and system for inspecting urban gas pipelines by drones based on digital twins. The method specifically includes pre - constructing a digital twin model of urban gas pipelines; using drones to inspect urban gas pipelines to obtain inspection data of the urban gas pipelines, and sending the inspection data to the digital twin model through 5G technology; presenting the inspection data and the inspection results determined based on the inspection data through the digital twin model. The present application integrates digital twin technology, 5G communication technology, artificial intelligence technology and drone technology. It uses digital twin technology to construct a digital twin model, uses drones to collect inspection data, and transmits the inspection data to the digital twin model through 5G communication technology. Finally, it uses artificial intelligence technology to detect faults based on the inspection data and display the inspection data and inspection results. This not only realizes efficient, accurate and real - time inspection of urban gas pipelines, but also can provide inspection data to users in real time. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] To more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for description in the embodiments. Obviously, the following - described drawings are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0017] Figure 1 It is a flowchart of the method for inspecting urban gas pipelines by drones based on digital twins provided by the embodiments of the present application.

[0018] Figure 2 It is a schematic flowchart of the process of planning the inspection path.

[0019] Figure 3 It is a schematic block diagram of the system for inspecting urban gas pipelines by drones based on digital twins provided by the embodiments of the present application.

[0020] Figure 4 It is a schematic block diagram of the terminal device provided by the embodiments of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0021] The embodiments of the present application provide a method and system for inspecting urban gas pipelines by drones based on digital twins. To make the purpose, technical solutions and effects of the present application clearer and more definite, the following further elaborates on the present application with reference to the attached drawings and by way of examples. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0022] Those skilled in the art of this technology can understand that, unless specifically stated, the singular forms "a", "an", "the" and "said" used herein may also include the plural forms. It should be further understood that the term "including" used in the specification of this application means the presence of the described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or their groups. It should be understood that when we say an element is "connected" or "coupled" to another element, it can be directly connected or coupled to other elements, or there may also be intermediate elements. In addition, the "connection" or "coupling" used herein may include wireless connection or wireless coupling. The phrase "and / or" used herein includes all or any unit and all combinations of one or more associated listed items.

[0023] Those skilled in the art of this technology can understand that, unless otherwise defined, all terms used herein (including technical terms and scientific terms) have the same meaning as the general understanding of those of ordinary skill in the field to which this application belongs. It should also be understood that terms such as those defined in a general dictionary should be understood to have a meaning consistent with the meaning in the context of the prior art, and will not be interpreted with an idealized or overly formal meaning unless specifically defined as here.

[0024] It should be understood that the sequence numbers and magnitudes of the steps in this embodiment do not mean the order of execution. The order of execution of each process is determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0025] The following further illustrates the application content by describing the embodiments in conjunction with the accompanying drawings.

[0026] This embodiment provides a method for inspecting urban gas pipelines by drones based on digital twins, as Figure 1 shown, the method includes: S10. Pre-build a digital twin model of the urban gas pipeline.

[0027] Specifically, the digital twin model is a digital model tailored for urban gas pipelines, realizing comprehensive real-time monitoring of urban gas pipelines. For example, through digital twin technology, the pressure, leakage, corrosion, deformation, etc. of the pipe network can be monitored and inspected in real time. In addition, the digital twin model can also monitor the environment around urban gas pipelines in real time to quickly detect leakage in case of leakage.

[0028] Exemplarily, the pre-building of the digital twin model of the urban gas pipeline specifically includes: Obtain the actual layout data and fault detection requirements of the urban gas pipeline; Using digital twin technology, a digital twin model is constructed for urban gas pipelines based on the actual layout data; Based on the fault detection requirements, an artificial intelligence model is constructed for the urban gas pipelines, and the artificial intelligence model set is deployed in the digital twin model.

[0029] Specifically, the actual layout data is used to construct a static topology model of urban gas pipelines. The actual layout data can include the inherent data of the pipeline, the pipeline location data, and the pipeline operation data. The inherent data of the pipeline can include detailed information such as pipeline material, diameter, and wall thickness. These data provide the basis for constructing an accurate pipeline static model. The pipeline location data can include pipeline geographical coordinates, burial depth, and relative position relationships with other facilities, which helps to reproduce the actual layout of the pipeline in the digital space. The pipeline operation data includes daily operation status, such as pressure changes, flow records, and historical maintenance records. These data are crucial for analyzing the operation efficiency of the pipeline, predicting potential failures, and formulating maintenance strategies. In addition, the inherent data of the pipeline can also include pipeline design specifications, safety standards, and historical accident records. These data provide key information for evaluating the safety performance of the pipeline and formulating emergency response plans. Combining these multi-dimensional data, the digital twin model can comprehensively reflect the actual conditions of urban gas pipelines and provide strong support for subsequent inspection, monitoring, and maintenance work.

[0030] The fault detection requirements can be set based on the operation requirements of urban gas pipelines or can be user-defined. The fault detection requirements determine the artificial intelligence models that need to be equipped for the digital twin model in order to use these artificial intelligence models to meet specific fault detection requirements. In other words, the fault detection requirements consist of multiple requirement items, and each requirement item can correspond to a dedicated artificial intelligence model to achieve the goal of that requirement item. For example, the fault detection requirements can include items such as fault detection, fault prediction, inspection path planning, and overlap degree detection. Then, after constructing the digital twin model, artificial intelligence technology will be used to construct corresponding fault detection models, fault prediction models, path planning models, and overlap degree prediction models, and these models will be deployed in the digital twin model.

[0031] In one implementation, the digital twin model is equipped with a fault detection model, a fault prediction model, a path planning model, and an overlap degree prediction model. The fault detection model is used to detect faults in urban gas pipelines. The fault prediction model is used to predict fault risks for the fault prediction model. The path planning model is used to plan the inspection path of drones for urban gas pipelines. The overlap degree prediction model is used to calculate the overlap degree between the inspection path planned by the path planning model and the historical inspection path.

[0032] The fault detection model can be trained based on inspection data. Among them, the training inspection data for training the fault detection model can be the inspection data of urban gas pipelines or the simulated inspection data of urban gas pipelines. That is to say, the training inspection data for training the fault detection model will be obtained first, and then the neural network model will be deeply learned based on the training inspection data to obtain the fault detection model.

[0033] The fault prediction model can be trained based on the inspection data sequence. The training inspection data sequence for training the fault detection model can include several inspection data. Each inspection data in the several inspection data is the inspection data before the prediction moment. That is, each inspection data in the several inspection data is historical inspection data relative to the prediction moment. That is to say, several inspection data sequences can be constructed, and then each inspection data sequence is used as a training data, and the neural network model is deeply learned with this training data to obtain the fault prediction model.

[0034] The path planning model can be trained based on pipeline location data, inspection data, and historical inspection paths. Among them, the inspection data in the training data for training the path planning model can be all the inspection data collected when the drone conducts inspections according to the historical inspection path; or the inspection data is the inspection data collected at the previous moment of the planning moment, and the historical inspection path is the inspection path corresponding to the previous moment of the planning moment; or the inspection data is the inspection data collected at the previous moment of the planning moment, and the historical inspection path includes multiple historical inspection paths before the planning moment in chronological order. In the embodiments of the present application, the inspection data in the training data for training the path planning model is the inspection data collected at the previous moment of the planning moment, and the historical inspection path includes multiple historical inspection paths before the planning moment in chronological order. In this way, path planning is carried out according to the latest operation data of urban gas pipelines and the recent multiple inspection paths, so that the planned path can more accurately inspect urban gas pipelines and improve the comprehensiveness of inspections.

[0035] The overlap prediction model can be trained based on the inspection path pair, which includes the planned inspection path output by the path planning model and several historical inspection paths. The historical inspection paths are the historical inspection paths of each drone except the drone corresponding to the planned inspection path. For example, the drones used for inspecting urban gas pipelines include multiple drones. Denote the drone that is currently planning the inspection path as the first drone, and the remaining drones except the first drone as the second drones. Then the planned inspection path is the inspection path planned for the first drone by the path planning model, and the several historical inspection paths include at least one historical inspection path of each second drone, and the planning times of at least one historical inspection path of each second drone are consecutive, and the latest planning time is the closest to the planning time of the planned inspection path of the first drone.

[0036] It can be seen from this that the digital twin model in the embodiments of the present application is constructed by combining artificial intelligence and digital twin technology. The digital twin technology provides rich data sources for AI. Through the digital twin model, AI can obtain the real-time operation data of urban gas pipelines, and these operation data provide strong support for the analysis and decision-making of AI. Secondly, AI can optimize the digital twin model, which can improve the accuracy and reliability of the digital twin model. For example, AI can predict the failure trend of equipment by analyzing the pipeline operation time, and arrange the maintenance plan in advance, so as to reduce the operation risk of urban gas pipelines. In addition, the integration of AI and digital twin can also achieve intelligent inspection. Under the control of AI, the drone can plan the inspection route according to the information provided by the digital twin model, improving the inspection efficiency. At the same time, AI can perform real-time analysis on the data collected by the drone, timely discover abnormal situations, and take corresponding measures.

[0037] S20. Inspect the urban gas pipeline by drone to obtain the inspection data of the urban gas pipeline, and send the inspection data to the digital twin model through 5G technology.

[0038] Specifically, the inspection data is collected by a drone, which includes the pipeline operation data of urban gas pipelines and the surrounding environmental data. In other words, when the drone inspects urban gas pipelines, it collects the pipeline operation data of urban gas pipelines and the surrounding environmental data. Among them, the drone can be equipped with a high-definition camera, an infrared thermal imager, an environmental gas detector, a lidar, etc., and collects the inspection data of urban gas pipelines through the high-definition camera, the infrared thermal imager, the environmental gas detector, the lidar, etc. The lidar is used to construct a three-dimensional map to achieve autonomous obstacle avoidance. The high-definition camera and the infrared camera are used for taking pictures and videos to obtain temperature field images and environmental images of gas equipment, etc. The environmental gas detector is used to detect the environmental data of urban gas pipelines, such as methane, carbon monoxide, ammonia, sulfur dioxide, etc. in the environment.

[0039] Exemplarily, the inspection of urban gas pipelines by a drone to obtain the inspection data of urban gas pipelines specifically includes: Controlling the drone to perform inspections according to a preset inspection path; Collecting the pipeline data of urban gas pipelines and the environmental data of the surrounding environment of urban gas pipelines in real time through the drone to obtain inspection data.

[0040] Specifically, the inspection path is the path adopted when the drone starts to conduct inspections, that is, the initial inspection path of the drone. It can be constructed based on historical prior data during the initial inspection or preset by the user, etc. After the drone starts the inspection, it will conduct inspections according to this inspection path and collect the historical prior data of urban gas pipelines in real time.

[0041] Furthermore, the drone can be configured with an autonomous obstacle avoidance function and a path planning function. That is, during the process of controlling the drone to perform inspections according to a preset inspection path, the inspection path of the drone can be adjusted periodically, that is, a new inspection path can be planned for the drone periodically. Among them, the new inspection path can be planned by the above-mentioned path planning model. This can be deployed in the digital twin model and can also be deployed in the drone. The drone can determine whether to perform path planning through the digital twin model or through the path planning model carried by itself according to its operating load. For example, when the operating load is greater than the preset load threshold, path planning is performed through the digital twin model. When the operating load is less than or equal to the preset load threshold, path planning is performed through the path planning model carried by itself. This method can flexibly select the path planning method according to the actual load situation, improving the inspection efficiency. When the operating load is heavy, using the digital twin model for path planning can more accurately determine the optimal path, reducing the energy consumption and time cost of the drone. When the operating load is light, planning through the path planning model carried by the drone itself can reduce the dependence on the digital twin model, improving the autonomy and flexibility of the drone.

[0042] Of course, in practical applications, other methods can also be used to determine the execution entity of path planning. For example, it can be determined according to the operating load and the remaining computing resources. Specifically, first determine whether the remaining computing resources meet the operating requirements of the path planning model. When the requirements are not met, path planning is performed through the digital twin model. When the requirements are met, obtain the inspection task level configured by the drone, select a preset load threshold according to the inspection task level and the remaining computing resources, and finally compare the operating load with the selected preset load threshold. When the operating load is less than or equal to the preset load threshold, path planning is performed through the path planning model carried by itself. When the operating load is greater than the preset load threshold, path planning is preferentially performed through the digital twin model. In this way, a more intelligent selection of the appropriate path planning method can be made according to the actual situation of the drone. If the remaining computing resources are insufficient, directly using the digital twin model for path planning can ensure the accuracy and reliability of path planning, avoiding planning failures or poor planning results caused by insufficient computing resources. If the remaining computing resources are sufficient, the preset load threshold can be flexibly adjusted according to the inspection task level and the remaining computing resources, thereby improving the autonomy and flexibility of the drone as much as possible while ensuring the quality of path planning. This path planning method that comprehensively considers the operating load, the remaining computing resources, and the inspection task level can further improve the inspection efficiency and the intelligent level of the drone.

[0043] The following takes the path planning performed by the path planning model configured through the twin data model as an example for illustration.

[0044] Exemplarily, as Figure 2 shown, the control of the drone to perform inspection according to a preset inspection path specifically includes: H10. Construct an inspection path for the drone and control the drone to perform inspection according to the inspection path; H20. Periodically read the historical prior data of the urban gas pipeline, where the historical prior data includes historical inspection data and historical inspection paths; H30. According to the obtained historical prior data of the urban gas pipeline and the actual layout data of the urban gas pipeline, use the path planning model through the digital twin model to construct a planned inspection path for the drone; H40. Take the planned inspection path as the inspection path of the drone and control the drone to perform inspection according to the preset inspection path.

[0045] Specifically, the period can be an interval period with a preset interval time, or the period can be when the drone completes an inspection task. The inspection path can be planned for the drone during the process of the drone performing the inspection task, or an inspection path can be planned for each inspection task of the drone, etc.

[0046] During the inspection process of the drone, the historical prior data of the urban gas pipeline will be periodically read. The historical prior data is the historical data collected within a preset time period before the acquisition moment. The historical prior data includes historical inspection data and historical inspection paths. Then, based on the historical prior data, path planning is carried out through the digital twin model using the pre-deployed path planning model to obtain the planned inspection path of the drone. This application uses a path planning model based on deep learning technology for path planning, and can comprehensively consider various factors such as the structural layout, equipment distribution, and potential risk areas of the urban gas pipeline, and plan the optimal inspection path for the drone. This can not only improve the inspection efficiency, but also ensure the safe operation of the drone in a complex environment.

[0047] Further, after obtaining the planned inspection path of the drone, the planned inspection path can be directly used as the inspection path of the drone, or it can be determined whether to use the planned inspection path as the inspection path of the drone through interaction with the user. It can also be to first detect whether there is a user-specified planned path. When there is a user-specified planned path, the planned inspection path can be abandoned and the user-specified planned path can be continued to be executed. It can also be to read the latest inspection results. If there is no risk area, the user-specified planned path can be continued to be executed. If there is a risk area and the planned inspection path includes the risk area, the planned inspection path can be used as the inspection path. If there is a risk area but the planned inspection path does not include the risk area, the inspection path is re-planned for the drone with the inspection nodes in the risk area as constraints.

[0048] In one implementation, since the coverage of urban gas pipelines is relatively wide, in order to improve the inspection speed of urban gas pipelines, multiple drones can be controlled simultaneously to inspect urban gas pipelines. Then, when there are multiple drones inspecting urban gas pipelines, after obtaining the planned inspection path, the overlap between the planned inspection path and the inspected paths of other drones can be detected to avoid the problem of some areas being repeatedly inspected while some areas are missed.

[0049] Based on this, when there are multiple drones inspecting urban gas pipelines, before using the planned inspection path as the inspection path of the drone, the method further includes: Obtaining the historical inspection paths of each drone except the drone corresponding to the planned inspection path; Based on the planned inspection path and the obtained historical inspection paths, input them into the overlap prediction model, and determine the overlap degree corresponding to the planned inspection path through the overlap prediction model; If the overlap degree is less than the preset overlap degree threshold, use the planned inspection path as the inspection path of the drone; If the overlap degree is greater than or equal to the preset overlap degree threshold, use the planned inspection path to update the historical inspection path of the drone corresponding to the planned inspection path, and re-execute the step of constructing the planned inspection path for the drone through the path planning model using the digital twin model according to the obtained historical prior data of the urban gas pipeline and the actual layout data of the urban gas pipeline.

[0050] Specifically, the overlap prediction model is an overlap prediction model deployed in the digital twin model. Through this overlap prediction model, the overlap between the planned inspection path and the inspected paths of other drones can be predicted. Among them, the historical inspection paths of each drone except the drone corresponding to the planned inspection path can be one, that is, the inspection path closest to the current moment in terms of the planned time, or multiple, that is, multiple inspection paths closest to the current time in terms of the planned time.

[0051] After obtaining the historical inspection paths of each drone except the drone corresponding to the planned inspection path, the obtained historical inspection paths and the planned inspection path can be input into the overlap prediction model. The overlap corresponding to the planned inspection path is output through the overlap prediction model, and based on this overlap, it is determined whether the planned inspection path can be used as the inspection path of the drone. Specifically, if the overlap is less than the preset overlap threshold, the planned inspection path is used as the inspection path of the drone; if the overlap is greater than or equal to the preset overlap threshold, the planned inspection path is used as a historical inspection path, and this historical inspection path is added to the historical inspection paths used as input items of the path planning model for re-path planning.

[0052] In addition, when obtaining the historical inspection paths of each drone except the drone corresponding to the planned inspection path, the historical inspection paths of the drones with overlapping areas with the inspection area of the drone corresponding to the planned inspection path can be obtained. In this way, the overlap prediction can be performed only based on the historical inspection paths of the drones with overlapping areas, which can reduce the computational amount of the overlap prediction while ensuring the accuracy of the overlap prediction. The inspection area of the drone is preset. When configuring the inspection area for the drone, when planning the inspection path for the drone, the inspection area corresponding to the drone can be used as a constraint condition, that is, when performing path planning, the inspection area corresponding to the drone can be informed to the path planning model, so that the path planning model plans the inspection path for the drone within this inspection area.

[0053] S30. Present the inspection data and the inspection results determined based on the inspection data through the digital twin model.

[0054] Specifically, the inspection result is determined by a fault detection model deployed based on the digital twin model based on the inspection data. The inspection result may include the fault condition of the urban gas pipeline and the risk areas in the urban gas pipeline, etc. That is to say, through the fault detection model, the gas pipeline in the urban gas pipeline where a fault occurs and the risk areas with fault risks (for example, areas where the sulfur dioxide concentration is higher than the preset concentration threshold, etc.) can be detected. By using the fault detection model to determine the inspection result of the gas pipeline in this application, the operation status of the gas pipeline can be monitored in real time and fault problems can be discovered in time, providing a decision-making basis for emergency response.

[0055] The digital twin model is a visualization model. Through the digital twin model, the inspection data can be presented to the user in real time, enabling the user to intuitively understand the operation status of the urban gas pipeline through the digital twin platform and discover potential problems in time. For example, through the three-dimensional visualization model, the layout and operation of the urban gas pipeline can be clearly seen, etc., improving the management efficiency and accuracy of the urban gas pipeline.

[0056] In one implementation, the method for inspecting urban gas pipelines by an unmanned aerial vehicle based on digital twin further includes: Reading the historical inspection data of the urban gas pipeline at preset time intervals; Based on the historical inspection data, performing risk prediction on the urban gas pipeline through the fault prediction model to obtain a risk prediction result; Performing preventive maintenance operations based on the risk prediction result.

[0057] Specifically, the historical inspection data may include all the historical inspection data between the current reading time and the previous reading time, or may be the historical inspection data within multiple preset times before the current reading time. Among them, the historical inspection data may include historical operation data and historical environmental data. The fault prediction model is pre-constructed for risk prediction of urban gas pipelines. Among them, the trigger condition for using the fault prediction model pre-carried by the digital twin model can be that the inspection result is normal, that is, there is no gas pipeline fault and no risk area. That is to say, when the inspection result obtained by using the fault detection model is normal, then use the fault prediction model to perform fault prediction on the urban gas pipeline, pre-judge the gas pipeline fault and risk area in advance, discover potential faults and safety hazards, and thus avoid risks from the source.

[0058] Of course, in practical applications, in order to reduce the computing resources required by the digital twin model, when the inspection result obtained by using the fault detection model is normal, risk assessment can be performed based on the inspection data (for example, comparing each operation data item in the inspection data with its corresponding risk threshold). When the evaluation result of the risk assessment indicates a risk, the historical inspection data of the urban gas pipeline is read, and fault prediction is performed through the fault prediction model to further confirm whether there are potential fault hazards. This can minimize unnecessary fault prediction operations on the premise of ensuring the safe operation of the urban gas pipeline, thereby reducing the consumption of computing resources of the digital twin model. In addition, when the time interval between the current time and the execution time of the previous execution of the fault prediction model reaches a preset duration, the historical inspection data of the urban gas pipeline can be triggered to be read to perform a risk prediction through the fault prediction model to obtain a risk prediction result.

[0059] In summary, this embodiment provides a method and system for inspecting urban gas pipelines by drones based on digital twins. The method specifically includes pre-constructing a digital twin model of the urban gas pipeline; inspecting the urban gas pipeline by drones to obtain inspection data of the urban gas pipeline, and sending the inspection data to the digital twin model through 5G technology; presenting the inspection data and the inspection result determined based on the inspection data through the digital twin model. This application integrates digital twin technology, 5G communication technology, artificial intelligence technology, and drone technology. It uses digital twin technology to construct a digital twin model, uses drones to collect inspection data, and transmits the inspection data to the digital twin model through 5G communication technology. Finally, artificial intelligence technology is used to perform fault detection based on the inspection data and display the inspection data and the inspection result. This not only realizes efficient, accurate, and real-time inspection of urban gas pipelines but also can provide inspection data to users in real time.

[0060] Based on the above method for inspecting urban gas pipelines by drones based on digital twins, this embodiment provides a system for inspecting urban gas pipelines by drones based on digital twins, as Figure 3 shown. The system for inspecting urban gas pipelines by drones based on digital twins specifically includes: A construction module 100 for pre-constructing a digital twin model of the urban gas pipeline; An inspection module 200 for inspecting the urban gas pipeline by drones to obtain inspection data of the urban gas pipeline, and sending the inspection data to the digital twin model through 5G technology; The detection module 300 is configured to present the inspection data and the inspection results determined based on the inspection data through the digital twin model, wherein the inspection results are determined by a fault detection model deployed based on the digital twin model based on the inspection data.

[0061] Based on the above method for inspecting urban gas pipelines by drones based on digital twins, this embodiment provides a computer-readable storage medium storing one or more programs, which can be executed by one or more processors to implement the steps in the method for inspecting urban gas pipelines by drones based on digital twins as described in the above embodiment.

[0062] Based on the above method for inspecting urban gas pipelines by drones based on digital twins, this application also provides a terminal device, as Figure 4 shown, which includes at least one processor 20; a display screen 21; and a memory 22, and may further include a communication interface 23 and a bus 24. Among them, the processor 20, the display screen 21, the memory 22, and the communication interface 23 can communicate with each other through the bus 24. The display screen 21 is set to display a user guidance interface preset in the initial setting mode. The communication interface 23 can transmit information. The processor 20 can call the logical instructions in the memory 22 to execute the method in the above embodiment.

[0063] In addition, when the logical instructions in the above-mentioned memory 22 are implemented in the form of a software functional unit and sold or used as an independent product, they can be stored in a computer-readable storage medium.

[0064] The memory 22, as a computer-readable storage medium, can be set to store software programs and computer-executable programs, such as program instructions or modules corresponding to the methods in the embodiments of the present disclosure. The processor 20 executes functional applications and data processing by running the software programs, instructions, or modules stored in the memory 22, that is, implements the methods in the above embodiments.

[0065] The memory 22 may include a program storage area and a data storage area. Among them, the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created according to the use of the terminal device and the like. In addition, the memory 22 may include a high-speed random access memory and may also include a non-volatile memory. For example, various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disc, may also be a transient storage medium.

[0066] In addition, the specific processes of loading and executing multiple instructions in the above-mentioned storage medium and the terminal device have been described in detail in the above method, and will not be repeated here one by one.

[0067] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and are not intended to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for inspecting urban gas pipelines by an unmanned aerial vehicle based on digital twin, characterized in that, The described method for inspecting urban gas pipelines by drones based on digital twins specifically includes: Pre - construct a digital twin model of urban gas pipelines; Use drones to inspect urban gas pipelines to obtain inspection data of urban gas pipelines, and send the inspection data to the digital twin model through 5G technology; Present the inspection data and the inspection results determined based on the inspection data through the digital twin model, where the inspection results are determined by a fault detection model deployed based on the digital twin model based on the inspection data.

2. The method for inspecting urban gas pipelines by drones based on digital twins according to claim 1, wherein, The pre - construction of the digital twin model of urban gas pipelines specifically includes: Obtain the actual layout data and fault detection requirements of urban gas pipelines; Use digital twin technology to construct a digital twin model for urban gas pipelines based on the actual layout data; Based on the fault detection requirements, construct an artificial intelligence model for the urban gas pipelines and deploy the artificial intelligence model set to the digital twin model.

3. The method for inspecting urban gas pipelines by drones based on digital twins according to claim 1, characterized in that The drones are equipped with high - definition cameras, infrared thermal imagers, environmental gas detectors, and lidar.

4. The method for inspecting urban gas pipelines by drones based on digital twins according to claim 1, wherein, The process of using drones to inspect urban gas pipelines to obtain inspection data of urban gas pipelines specifically includes: Control the drones to conduct inspections according to a preset inspection path; Collect the pipeline data of urban gas pipelines and the environmental data of the surrounding environment of urban gas pipelines in real - time through the drones to obtain inspection data.

5. The method for inspecting urban gas pipelines by drones based on digital twins according to claim 4, wherein, A path planning model is deployed in the digital twin model; the process of controlling the drones to conduct inspections according to a preset inspection path specifically includes: Construct an inspection path for the drones and control the drones to conduct inspections according to the inspection path; Periodically read the historical prior data of the urban gas pipelines, where the historical prior data includes historical inspection data and historical inspection paths; According to the obtained historical prior data of the urban gas pipelines and the actual layout data of the urban gas pipelines, use the path planning model through the digital twin model to construct a planned inspection path for the drones; Take the planned inspection path as the inspection path of the drones and control the drones to conduct inspections according to the preset inspection path.

6. The method for inspecting urban gas pipelines by drones based on digital twins according to claim 5, wherein, An overlap degree prediction model is deployed in the digital twin model; there are multiple drones for inspecting urban gas pipelines. Before taking the planned inspection path as the inspection path of the drones, the method further includes: Obtain the historical inspection paths of each drone except the drone corresponding to the planned inspection path; Based on the planned inspection path and the obtained historical inspection paths, input them into the overlap degree prediction model, and determine the overlap degree corresponding to the planned inspection path through the overlap degree prediction model; If the overlap degree is less than the preset overlap degree threshold, take the planned inspection path as the inspection path of the drones; If the overlap degree is greater than or equal to a preset overlap degree threshold, update the historical inspection path of the drone corresponding to the planned inspection path by using the planned inspection path, and re - execute the step of constructing a planned inspection path for the drone by using the path planning model through the digital twin model according to the obtained historical prior data and actual layout data of the urban gas pipeline.

7. The method for inspecting urban gas pipelines by drones based on digital twins according to claim 1, wherein, The digital twin model is deployed with a fault prediction model; the method further includes: Read the historical inspection data of the urban gas pipeline at every preset time interval; Based on the historical inspection data, perform risk prediction on the urban gas pipeline through the fault prediction model to obtain a risk prediction result; Perform preventive maintenance operations based on the risk prediction result.

8. An unmanned aerial vehicle (UAV) urban gas pipeline inspection system based on digital twin, characterized in that, The digital - twin - based unmanned aerial vehicle (UAV) urban gas pipeline inspection system specifically includes: A construction module, used to pre - construct a digital twin model of the urban gas pipeline; An inspection module, used to inspect the urban gas pipeline by using a UAV to obtain inspection data of the urban gas pipeline, and send the inspection data to the digital twin model through 5G technology; A detection module, used to present the inspection data and the inspection result determined based on the inspection data through the digital twin model, where the inspection result is determined by a fault detection model deployed based on the digital twin model based on the inspection data.

9. A computer-readable storage medium, characterized in that, The computer - readable storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps in the digital - twin - based UAV urban gas pipeline inspection method according to any one of claims 1 - 7.

10. A terminal device, characterized in that, It includes: A processor and a memory; The memory stores a computer - readable program executable by the processor; When the processor executes the computer - readable program, it implements the steps in the digital - twin - based UAV urban gas pipeline inspection method according to any one of claims 1 - 7.

Images