A new energy station inspection task scheduling method and device based on digital twinning

Abstract

This invention discloses a method and apparatus for scheduling inspection tasks at new energy power stations based on digital twins. The method includes: constructing a digital twin model of the new energy power station; acquiring real-time data from the new energy power station; prioritizing tasks based on the synchronized real-time data in the digital twin model; assigning target inspection equipment to each task according to the priority ranking; performing global path planning for each target inspection equipment to determine its inspection path; simulating the inspection trajectory of each target inspection equipment in real-time using the digital twin model based on the inspection path, and determining whether there are path conflicts between the equipment; if so, adjusting the timing or path of the target inspection equipment's inspection path to avoid conflicts. This method enables intelligent task scheduling and rational planning of inspection paths.

Description

Technical Field

[0001] This invention relates to the field of intelligent operation and maintenance technology for new energy power stations, and in particular to a method and device for scheduling inspection tasks of new energy power stations based on digital twins. Background Technology

[0002] With the large-scale development of new energy power plants, unmanned inspection has become an industry trend, but the existing inspection task scheduling and path planning have the following problems: Problem 1: Scheduling relies on manual experience: The existing platform relies on manual assignment for the allocation of inspection tasks such as wind turbine blade inspection and photovoltaic panel hot spot detection. It cannot dynamically adjust the scheduling according to equipment status and environmental changes, resulting in waste of equipment resources.

[0003] Problem 2: Poor equipment coordination: Drones, robots, and other equipment operate independently, with each planning its own path, which can easily lead to repeated inspections, such as the same area being covered multiple times by drones and robots or blind spots in the inspection.

[0004] Problem 3: Lack of path optimization: Traditional path planning does not take into account the complex environment of energy stations, such as dense photovoltaic arrays and wind turbine tower obstacles, resulting in low inspection efficiency and high equipment energy consumption.

[0005] In summary, the existing inspection schemes for new energy power stations suffer from problems such as inefficient task scheduling, low equipment coordination, and unreasonable route planning. Summary of the Invention

[0006] The purpose of this invention is to provide a method and apparatus for scheduling inspection tasks at new energy power stations based on digital twins, which can solve at least one of the above-mentioned problems in the prior art.

[0007] To solve the above-mentioned technical problems, the present invention provides the following technical solution: This invention provides a method for scheduling inspection tasks at new energy power stations based on digital twins, wherein the method includes: Construct a digital twin model of a new energy power station, wherein the digital twin model is a virtual mapping of the new energy power station; The real-time data of the new energy power station is acquired, including the status data of the inspection equipment, environmental data, and equipment defect early warning data in the new energy power station, and synchronized to the digital twin model. Based on the real-time data synchronized in the digital twin model, the tasks to be assigned are prioritized. Based on the aforementioned priority ranking, target inspection equipment is assigned to each task to be assigned. Global path planning is performed for each of the target inspection devices to determine the inspection path for each of the target inspection devices; The digital twin model simulates the inspection trajectory of each target inspection device in real time based on the inspection path, and determines whether there are path conflicts between devices. If such conflicts exist, adjust the timing or path of the target inspection equipment to avoid path conflicts between equipment.

[0008] Optionally, the method further includes: When the status of any of the target inspection equipment changes abruptly or the environment of the new energy power station changes, the tasks are reassigned based on the real-time data received by the digital twin model, and the inspection paths of the inspection equipment to execute each task are planned.

[0009] Optionally, the method further includes: The task scheduling results and the target inspection equipment execution data are synchronized to the intelligent unmanned inspection platform for new energy power stations. The task scheduling results include: a task allocation list and an inspection path planning map; the target inspection equipment execution data includes: the real-time location of the target inspection equipment and the progress of the tasks assigned to the target inspection equipment.

[0010] Optionally, the steps for constructing a digital twin model of a new energy power station include: The equipment layout and obstacle information of the new energy power station are collected using lidar. Using the high-precision map of the new energy power station, historical equipment ledger data, equipment layout information, and obstacle information, the geographical environment and equipment layout of the new energy power station are reconstructed in three dimensions to generate a digital twin model of the new energy power station; wherein, the equipment layout includes: photovoltaic panel array, wind turbine location, and inspection equipment base station; the geographical environment includes: terrain and obstacle distribution.

[0011] Optionally, the inspection equipment status data includes: the remaining battery power of the drone, the robot's range, and the camera's online status; the environmental data includes: wind speed and light intensity; and the equipment defect early warning data includes: early warning of wind turbine blade cracks based on artificial intelligence visual recognition.

[0012] Optionally, the step of performing global path planning for each of the target inspection devices to determine the inspection path for each of the target inspection devices includes: For each task to be assigned, the improved A* algorithm is used to determine the target inspection equipment to perform the task based on the terrain weight of the new energy power station and the motion constraints of the inspection equipment. An initial inspection path is planned for each target inspection equipment to ensure that the inspection area of ​​each target inspection equipment covers the target area and avoids obstacles.

[0013] This invention also provides a digital twin-based new energy power station inspection task scheduling device, wherein the device includes: The model building module is used to build a digital twin model of the new energy power station, wherein the digital twin model is a virtual mapping of the new energy power station; The data acquisition module is used to acquire real-time data of the new energy power station, wherein the real-time data includes the status data of the inspection equipment, environmental data and equipment defect early warning data in the new energy power station, and synchronizes them to the digital twin model. The sorting module is used to prioritize the tasks to be assigned based on the real-time data synchronized in the digital twin model. The task allocation module is used to assign target inspection equipment to each task to be assigned according to the priority order. The path planning module is used to perform global path planning for each of the target inspection devices to determine the inspection path of each of the target inspection devices; The multi-device collaborative path optimization module is used to simulate the inspection trajectory of each target inspection device in real time based on the inspection path using the digital twin model, and to determine whether there is a path conflict between devices; if so, the timing or path of the inspection path of the target inspection device is adjusted to avoid path conflicts between devices.

[0014] Optionally, the device further includes: The dynamic replanning module is used to reallocate tasks and plan the inspection paths of the inspection equipment to execute each task based on the real-time data received by the digital twin model when the state of any of the target inspection equipment changes abruptly or the environment of the new energy power station changes.

[0015] Optionally, the device further includes: The platform integration module is used to synchronize the task scheduling results and the target inspection equipment execution data to the smart unmanned inspection platform for new energy power stations. The task scheduling results include: a task allocation list and an inspection path planning map; the target inspection equipment execution data includes: the real-time location of the target inspection equipment and the progress of the tasks assigned to the target inspection equipment.

[0016] Optionally, the model building module includes: The first submodule is used to collect equipment layout information and obstacle information of the new energy power station through lidar; The second submodule is used to reconstruct the geographical environment and equipment layout of the new energy power station in three dimensions using the high-precision map of the new energy power station, historical equipment ledger data, equipment layout information, and obstacle information, and generate a digital twin model of the new energy power station; wherein, the equipment layout includes: photovoltaic panel array, wind turbine location, and inspection equipment base station; the geographical environment includes: terrain and obstacle distribution.

[0017] Optionally, the inspection equipment status data includes: the remaining battery power of the drone, the robot's range, and the camera's online status; the environmental data includes: wind speed and light intensity; and the equipment defect early warning data includes: early warning of wind turbine blade cracks based on artificial intelligence visual recognition.

[0018] Optionally, the path planning module is specifically used for: For each task to be assigned, the improved A* algorithm is used to determine the target inspection equipment to perform the task based on the terrain weight of the new energy power station and the motion constraints of the inspection equipment. An initial inspection path is planned for each target inspection equipment to ensure that the inspection area of ​​each target inspection equipment covers the target area and avoids obstacles.

[0019] This invention provides a digital twin-based scheduling scheme for new energy power plant inspection tasks. The scheme involves: constructing a digital twin model of the new energy power plant; acquiring real-time data of the power plant; prioritizing tasks based on the synchronized real-time data in the digital twin model; assigning target inspection equipment to each task according to the priority ranking; performing global path planning for each target inspection equipment to determine its inspection path; simulating the inspection trajectory of each target inspection equipment in real-time using the digital twin model based on the inspection path, and determining whether there are path conflicts between equipment; if so, adjusting the timing or path of the target inspection equipment's inspection path to avoid conflicts. This scheme offers several advantages: firstly, by dynamically allocating tasks based on real-time data, it enables intelligent task scheduling and improves task response speed; secondly, by employing a multi-device collaboration mechanism to resolve path conflicts and perform global optimization, it reduces redundant inspection areas and improves equipment utilization; and thirdly, by planning inspection paths based on complex power plant environments, it reduces equipment energy consumption and increases inspection coverage. Attached Figure Description

[0020] The accompanying drawings, which form part of this specification, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an undue limitation of the invention. In the drawings: Figure 1 This is a flowchart illustrating a digital twin-based new energy power station inspection task scheduling method according to an embodiment of this application; Figure 2 This is a system architecture diagram of a smart unmanned inspection platform for new energy power stations, representing an embodiment of this application. Figure 3 This is a structural block diagram illustrating a digital twin-based new energy power station inspection task scheduling device according to an embodiment of this application. Detailed Implementation

[0021] The present invention will now be described in detail with reference to the accompanying drawings and embodiments. It should be noted that, unless otherwise specified, the embodiments and features described herein can be combined with each other.

[0022] The following detailed description is exemplary and intended to provide further detailed explanation of the invention. Unless otherwise specified, all technical terms used in this invention have the same meaning as commonly understood by one of ordinary skill in the art. The terminology used in this invention is for describing particular embodiments only and is not intended to limit the scope of exemplary embodiments according to the invention.

[0023] This invention aims to solve the problems of inefficient task scheduling, low equipment coordination, and unreasonable path planning in the inspection of new energy power plants. It achieves intelligent scheduling and globally optimal path planning based on real-time data, thereby improving inspection efficiency and equipment utilization. Specifically, it relates to an intelligent scheduling and path optimization scheme for energy plant inspection tasks based on digital twins, applicable to the collaborative management and efficient operation of various types of inspection equipment such as drones, robots, and cameras in new energy power plants such as photovoltaic power plants and wind farms.

[0024] To make the technical problems, technical solutions and advantages of the present invention clearer, a detailed description will be given below in conjunction with the accompanying drawings and specific embodiments.

[0025] The following description, in conjunction with the accompanying drawings, details the digital twin-based new energy power station inspection task scheduling scheme provided in this application through specific embodiments and application scenarios.

[0026] As attached Figure 1 As shown in the figure, the new energy power station inspection task scheduling method based on digital twin in this application includes the following steps: Step 101: Construct a digital twin model of the new energy power station.

[0027] The digital twin model serves as a virtual mapping of the new energy power station, with each feature in the model matching the actual characteristics of the power station. During path planning and subsequent inspections, the digital twin model can be used to simulate the inspection trajectory of the equipment, allowing for early prediction of potential path conflicts and timely adjustment of the inspection paths to ensure successful completion of the inspection.

[0028] In one optional embodiment, the digital twin model of a new energy power station can be constructed by: collecting equipment layout information and obstacle information of the new energy power station using lidar; and reconstructing the geographical environment and equipment layout of the new energy power station in three dimensions using a high-precision map of the new energy power station, historical equipment ledger data, equipment layout information, and obstacle information, thereby generating a digital twin model of the new energy power station.

[0029] Equipment layout may include, but is not limited to: photovoltaic panel arrays, wind turbine locations, and inspection equipment base stations; geographical environment may include, but is not limited to: terrain and obstacle distribution.

[0030] Step 102: Obtain real-time data from the new energy power station.

[0031] The real-time data includes status data of inspection equipment, environmental data, and equipment defect early warning data in the new energy power station, which is synchronized to the digital twin model. In actual implementation, real-time data from the new energy power station can be transmitted to the digital twin model via 5G / fiber optics to achieve synchronous updates of virtual and real data. The real-time data from the new energy power station can be collected by the intelligent unmanned inspection platform and sent to the inspection task scheduling device, which then synchronizes the data to the digital twin model via 5G / fiber optics.

[0032] The status data of the inspection equipment includes, but is not limited to: the remaining power of the drone, the range of the robot, and the online status of the camera; environmental data includes, but is not limited to: wind speed and light intensity; equipment defect early warning data includes, but is not limited to: early warning of wind turbine blade cracks by artificial intelligence visual recognition.

[0033] Step 103: Prioritize the tasks to be assigned based on the real-time data synchronized in the digital twin model.

[0034] In this embodiment, a multi-dimensional priority evaluation system is established based on real-time data from the digital twin model to determine the priority ranking of tasks to be assigned. For example, priority ranking can be performed based on three dimensions: urgency, timeliness, and device compatibility.

[0035] Urgency level: Characterized by the equipment defect warning level, such as "Level 1 alarm" for wind turbine failure taking precedence over "Level 3 alarm" for photovoltaic panel stains.

[0036] Timeliness: Inspection tasks that need to be completed within a specific time window; such as the midday hot spot detection of photovoltaic panels.

[0037] Equipment compatibility: Match the task to the equipment function, such as adapting drones to high-altitude wind turbine inspections and robots to ground-based photovoltaic panel inspections.

[0038] It should be noted that the above is only an example of prioritizing based on three dimensions: urgency, timeliness, and device compatibility. In actual implementation, any two of these dimensions or other dimensions can be combined for prioritization. This application does not impose any specific restrictions on this.

[0039] Step 104: Assign target inspection equipment to each task to be assigned according to priority.

[0040] Based on the priority of each task to be assigned, the task is automatically assigned to the optimal device, namely the target inspection device. If the task to be assigned needs to be performed in the air, it will be assigned to the drone with sufficient power and closest to the target area.

[0041] It should be noted that task queueing is supported during task allocation. For example, in the event of a sudden failure, low-priority tasks can be paused and high-priority tasks can be allocated after execution.

[0042] Step 105: Perform global path planning for each target inspection device to determine the inspection path for each target inspection device.

[0043] This step involves global path planning. In one optional embodiment, global path planning is performed for each target inspection device to determine the inspection path for each target inspection device. This can be achieved by: for each task to be assigned, using an improved A* algorithm based on the terrain weight of the new energy power station and the motion constraints of the inspection device, determining the target inspection device to perform the assigned task, and planning an initial inspection path for each target inspection device to ensure that the inspection area of ​​each target inspection device covers the target area and avoids obstacles.

[0044] Obstacles can be wind turbine towers, cable trenches, etc. in new energy power plants.

[0045] The A* algorithm is a highly efficient heuristic search algorithm widely used in path planning and graph search. Also known as the A-Star algorithm, it is a classic heuristic search algorithm used to find the minimum-cost path from a starting point to a destination in a graph or state space. It was proposed by Peter Hart, Nils Nilsson, and Bertram Raphael in 1968. The core idea of ​​the A* algorithm is to use a heuristic function to estimate the distance from the current node to the target node, thereby guiding the search in a more promising direction, reducing unnecessary searches, and improving algorithm efficiency.

[0046] Step 106: Simulate the inspection trajectory of each target inspection device in real time based on the inspection path using a digital twin model, and determine whether there are path conflicts between devices.

[0047] If there is a path conflict between devices, proceed to step 107; if there is no path conflict between devices, directly synchronize the task scheduling result and the execution data of the target inspection equipment to the smart unmanned inspection platform of the new energy power station.

[0048] Step 107: If it exists, adjust the timing or path of the inspection path of the target inspection equipment to avoid path conflicts between equipment.

[0049] Step 107 is the conflict resolution mechanism. This mechanism simulates the movement trajectory of the equipment in real time through a digital twin model. If a path conflict is detected, such as the drone and the robot intersecting in the same area, the path timing is automatically adjusted, such as delaying the departure time of a certain device, or the spatial trajectory is adjusted, such as the drone increasing its flight altitude.

[0050] In one alternative embodiment, the digital twin-based new energy power station inspection task scheduling method, in addition to having a conflict resolution mechanism, also has a task dynamic replanning mechanism.

[0051] The task dynamic replanning mechanism can be as follows: when the status of any target inspection equipment changes suddenly or the environment of the new energy power station changes, the task is reassigned based on the real-time data received by the digital twin model, and the inspection path of the inspection equipment to execute each task is planned.

[0052] Global path planning, conflict resolution mechanisms, and task dynamic replanning mechanisms are important components of multi-device collaborative path optimization.

[0053] In an optional embodiment, the digital twin-based new energy power station inspection task scheduling method further includes a process of interfacing with a smart inspection platform. Specifically, this involves synchronizing the task scheduling results and the execution data of the target inspection equipment to the smart unmanned inspection platform for new energy power stations. The smart unmanned inspection platform for new energy power stations supports visualized monitoring and manual intervention of tasks, such as manually adjusting the path. The system structure diagram of the smart unmanned inspection platform for new energy power stations is shown below. Figure 2 As shown, it includes: a device layer, a transmission layer, and a platform layer. The device layer includes drones, inspection robots, and cameras; the transmission layer includes an inspection host that collects data from various devices for analysis by the intelligent unmanned inspection platform, and transmits the collected data to the platform layer or a digital twin-based new energy station inspection task scheduling device independent of the intelligent unmanned inspection platform via 5G, wireless transmission, or fiber optics. The platform layer includes functional modules such as real-time video monitoring, inspection data analysis, intelligent report generation, equipment management, alarm statistics management, access control, path planning, process management, and AI artificial intelligence support modules.

[0054] The task scheduling results include: a task allocation list and an inspection path planning map; the target inspection equipment execution data includes: the real-time location of the target inspection equipment and the progress of the tasks assigned to the target inspection equipment.

[0055] The present application provides a digital twin-based method for scheduling inspection tasks at new energy power stations. This method involves: constructing a digital twin model of the new energy power station; acquiring real-time data from the power station; prioritizing tasks based on the synchronized real-time data in the digital twin model; assigning target inspection equipment to each task according to the priority ranking; performing global path planning for each target inspection equipment to determine its inspection path; simulating the inspection trajectory of each target inspection equipment in real-time using the digital twin model based on the inspection path, and determining whether there are path conflicts between equipment; if so, adjusting the timing or path of the target inspection equipment's inspection path to avoid conflicts. This solution, in three aspects, achieves intelligent task scheduling and improves task response speed by dynamically allocating tasks based on real-time data; globally optimizes the process by using a multi-device collaboration mechanism to resolve path conflicts, reducing redundant inspection areas and improving equipment utilization; and plans inspection paths based on complex power station environments, reducing equipment energy consumption and increasing inspection coverage.

[0056] The following example illustrates the new energy power station inspection task scheduling method based on digital twins provided in this application.

[0057] Taking a large-scale wind-solar-storage integrated power station of Huaneng Group as an example, the power station includes 100 wind turbines, 500,000 square meters of photovoltaic array, 5 inspection drones, 10 tracked robots and 20 fixed cameras. The system of this invention is deployed to realize collaborative inspection.

[0058] The digital twin-based scheduling method for new energy power plant inspection tasks includes the following process: (1) Construction of digital twin model The three-dimensional reconstruction of the site's terrain and equipment layout accurately maps the locations of wind turbines at a height of 120m, photovoltaic panel arrays at a spacing of 1.5m, three drone nests, and eight robot charging piles. Real-time data access: drone battery level (e.g., "Drone 1: 70%)", robot location (e.g., "Robot 3: Column A, Row 5 of the photovoltaic zone"), ambient wind speed (8 m / s), AI warning (e.g., "Wind turbine blade 23 suspected of having a crack").

[0059] (2) Task scheduling and inspection path optimization: Task priority ranking: "Crack detection of wind turbine blade 23" is marked as the highest priority task and assigned to "Drone 1", which is the closest and has sufficient power; "Hot spot detection in column B of photovoltaic area" is marked as a secondary task and assigned to "Robot 5"; Inspection path planning: Plan a path for UAV 1 from "nest → wind turbine 23 → return to nest" to avoid the airspace of wind turbines 22 and 24; plan a path for robot 5 from "charging pile → photovoltaic area B column → inspection along the line" to avoid the ground cable trench. Conflict resolution: Through simulation using a digital twin model, it was discovered that "Drone 1 and Robot 5 are highly overlapping near Wind Turbine 23". The flight altitude of Drone 1 was automatically adjusted from 80m to 100m to avoid conflict.

[0060] (3) Integration with the intelligent unmanned inspection platform for new energy power stations: The scheduling results and paths are synchronized to the intelligent unmanned inspection platform in real time. The operation and maintenance personnel can monitor the task progress through the visual interface of the intelligent unmanned inspection platform. When drone 1 completes the inspection and uploads the image, the intelligent unmanned inspection platform automatically triggers the next task assignment.

[0061] Figure 3 The structural block diagram of the new energy power station inspection task scheduling device based on digital twin is shown in the embodiment of this application.

[0062] The new energy power station inspection task scheduling device based on digital twin in this application includes the following functional modules: The model building module 301 is used to build a digital twin model of the new energy power station, wherein the digital twin model is a virtual mapping of the new energy power station; The data acquisition module 302 is used to acquire real-time data of the new energy power station, wherein the real-time data includes the status data of the inspection equipment, environmental data and equipment defect early warning data in the new energy power station, and synchronizes them to the digital twin model. The sorting module 303 is used to prioritize the tasks to be assigned based on the real-time data synchronized in the digital twin model. Task allocation module 304 is used to allocate target inspection equipment to each task to be allocated according to the priority order. The path planning module 305 is used to perform global path planning for each of the target inspection devices to determine the inspection path of each of the target inspection devices. The multi-device collaborative path optimization module 306 is used to simulate the inspection trajectory of each target inspection device in real time based on the inspection path using the digital twin model, and to determine whether there is a path conflict between devices; if so, the timing or path of the inspection path of the target inspection device is adjusted to avoid path conflicts between devices.

[0063] Optionally, the device further includes: The dynamic replanning module is used to reallocate tasks and plan the inspection paths of the inspection equipment to execute each task based on the real-time data received by the digital twin model when the state of any of the target inspection equipment changes abruptly or the environment of the new energy power station changes.

[0064] Optionally, the device further includes: The platform integration module is used to synchronize the task scheduling results and the target inspection equipment execution data to the smart unmanned inspection platform for new energy power stations. The task scheduling results include: a task allocation list and an inspection path planning map; the target inspection equipment execution data includes: the real-time location of the target inspection equipment and the progress of the tasks assigned to the target inspection equipment.

[0065] Optionally, the model building module includes: The first submodule is used to collect equipment layout information and obstacle information of the new energy power station through lidar; The second submodule is used to reconstruct the geographical environment and equipment layout of the new energy power station in three dimensions using the high-precision map of the new energy power station, historical equipment ledger data, equipment layout information, and obstacle information, and generate a digital twin model of the new energy power station; wherein, the equipment layout includes: photovoltaic panel array, wind turbine location, and inspection equipment base station; the geographical environment includes: terrain and obstacle distribution.

[0066] Optionally, the inspection equipment status data includes: the remaining battery power of the drone, the robot's range, and the camera's online status; the environmental data includes: wind speed and light intensity; and the equipment defect early warning data includes: early warning of wind turbine blade cracks based on artificial intelligence visual recognition.

[0067] Optionally, the path planning module is specifically used for: For each task to be assigned, the improved A* algorithm is used to determine the target inspection equipment to perform the task based on the terrain weight of the new energy power station and the motion constraints of the inspection equipment. An initial inspection path is planned for each target inspection equipment to ensure that the inspection area of ​​each target inspection equipment covers the target area and avoids obstacles.

[0068] The new energy power station inspection task scheduling device based on digital twin provided in this application has the following advantages: First, it can realize intelligent task scheduling and improve task response speed by dynamically allocating tasks based on real-time data. Second, it can reduce repeated inspection areas and improve the utilization rate of inspection equipment by adopting a multi-device collaboration mechanism to resolve path conflicts and perform global optimization. Third, it can reduce the energy consumption of inspection equipment and improve the inspection coverage rate by planning inspection paths according to the complex power station environment.

[0069] The embodiments provided in this application Figure 3The digital twin-based new energy power station inspection task scheduling device shown can achieve Figure 1 The various processes implemented in the method implementation examples will not be described again here to avoid repetition.

[0070] This application also provides an electronic device, which includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus.

[0071] The memory is used to store computer programs; the processor is used to execute the programs stored in the memory to implement the digital twin-based new energy power station inspection task scheduling process in the above embodiments.

[0072] The communication bus mentioned above can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into address bus, data bus, control bus, etc. The communication interface is used for communication between the aforementioned terminal and other devices.

[0073] The memory may include random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0074] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0075] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0076] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for scheduling inspection tasks at new energy power stations based on digital twins, characterized in that, include: Construct a digital twin model of a new energy power station, wherein the digital twin model is a virtual mapping of the new energy power station; The real-time data of the new energy power station is acquired, including the status data of the inspection equipment, environmental data, and equipment defect early warning data in the new energy power station, and synchronized to the digital twin model. Based on the real-time data synchronized in the digital twin model, the tasks to be assigned are prioritized. Based on the aforementioned priority ranking, target inspection equipment is assigned to each task to be assigned. Global path planning is performed for each of the target inspection devices to determine the inspection path for each of the target inspection devices; The digital twin model simulates the inspection trajectory of each target inspection device in real time based on the inspection path, and determines whether there are path conflicts between devices. If such conflicts exist, adjust the timing or path of the target inspection equipment to avoid path conflicts between equipment.

2. The method according to claim 1, characterized in that, The method further includes: When the status of any of the target inspection equipment changes abruptly or the environment of the new energy power station changes, the tasks are reassigned based on the real-time data received by the digital twin model, and the inspection paths of the inspection equipment to execute each task are planned.

3. The method according to claim 2, characterized in that, The method further includes: The task scheduling results and the target inspection equipment execution data are synchronized to the intelligent unmanned inspection platform for new energy power stations. The task scheduling results include: a task allocation list and an inspection path planning map; the target inspection equipment execution data includes: the real-time location of the target inspection equipment and the progress of the tasks assigned to the target inspection equipment.

4. The method according to claim 1, characterized in that, The steps for constructing a digital twin model of a new energy power station include: The equipment layout and obstacle information of the new energy power station are collected using lidar. Using the high-precision map of the new energy power station, historical equipment ledger data, equipment layout information, and obstacle information, the geographical environment and equipment layout of the new energy power station are reconstructed in three dimensions to generate a digital twin model of the new energy power station; wherein, the equipment layout includes: photovoltaic panel array, wind turbine location, and inspection equipment base station; the geographical environment includes: terrain and obstacle distribution.

5. The method according to claim 1, characterized in that, The inspection equipment status data includes: the remaining battery power of the drone, the robot's range, and the camera's online status; the environmental data includes: wind speed and light intensity; the equipment defect early warning data includes: early warning of wind turbine blade cracks based on artificial intelligence visual recognition.

6. The method according to claim 1, characterized in that, The steps of performing global path planning for each of the target inspection devices to determine the inspection path for each of the target inspection devices include: For each task to be assigned, the improved A* algorithm is used to determine the target inspection equipment to perform the task based on the terrain weight of the new energy power station and the motion constraints of the inspection equipment. An initial inspection path is planned for each target inspection equipment to ensure that the inspection area of ​​each target inspection equipment covers the target area and avoids obstacles.

7. A new energy power station inspection task scheduling device based on digital twin, characterized in that, The device includes: The model building module is used to build a digital twin model of the new energy power station, wherein the digital twin model is a virtual mapping of the new energy power station; The data acquisition module is used to acquire real-time data of the new energy power station, wherein the real-time data includes the status data of the inspection equipment, environmental data and equipment defect early warning data in the new energy power station, and synchronizes them to the digital twin model. The sorting module is used to prioritize the tasks to be assigned based on the real-time data synchronized in the digital twin model. The task allocation module is used to assign target inspection equipment to each task to be assigned according to the priority order. The path planning module is used to perform global path planning for each of the target inspection devices to determine the inspection path of each of the target inspection devices; The multi-device collaborative path optimization module is used to simulate the inspection trajectory of each target inspection device in real time based on the inspection path using the digital twin model, and to determine whether there is a path conflict between devices; if so, the timing or path of the inspection path of the target inspection device is adjusted to avoid path conflicts between devices.

8. The apparatus according to claim 7, characterized in that, The device further includes: The dynamic replanning module is used to reallocate tasks and plan the inspection paths of the inspection equipment to execute each task based on the real-time data received by the digital twin model when the state of any of the target inspection equipment changes abruptly or the environment of the new energy power station changes.

9. The apparatus according to claim 8, characterized in that, The device further includes: The platform integration module is used to synchronize the task scheduling results and the target inspection equipment execution data to the smart unmanned inspection platform for new energy power stations. The task scheduling results include: a task allocation list and an inspection path planning map; the target inspection equipment execution data includes: the real-time location of the target inspection equipment and the progress of the tasks assigned to the target inspection equipment.

10. The apparatus according to claim 7, characterized in that, The model building module includes: The first submodule is used to collect equipment layout information and obstacle information of the new energy power station through lidar; The second submodule is used to reconstruct the geographical environment and equipment layout of the new energy power station in three dimensions using the high-precision map of the new energy power station, historical equipment ledger data, equipment layout information, and obstacle information, and generate a digital twin model of the new energy power station; wherein, the equipment layout includes: photovoltaic panel array, wind turbine location, and inspection equipment base station; the geographical environment includes: terrain and obstacle distribution.

Images