Method and device for generating movement paths for multiple drones for inspecting industrial structures

Abstract

The present invention relates to a method and device for generating a movement path of a plurality of drones for inspecting an industrial structure. The method and device for generating a movement path of a plurality of drones for inspecting an industrial structure according to an embodiment of the present invention can identify a path that a drone can move and a path that the drone cannot move at a plurality of inspection points based on industrial structure information, and can derive an optimal movement path by optimizing a vehicle path problem model using a metaheuristic solution method so as to maximize the operational efficiency of the plurality of drones. In addition, the vehicle path problem model is further solved using an exact solution method, and a solution method can be determined from the exact solution method or the metaheuristic solution method based on the number of inspection points. This makes it possible to flexibly respond to on-site conditions and deliver accurate results.

Description

[Technical field]

[0001] The present invention relates to a method for generating movement paths for multiple drones for inspecting industrial structures. Specifically, the present invention relates to a method for generating movement paths for multiple drones for inspecting industrial structures, the method setting optimal movement paths for drones to move to multiple inspection points set in advance according to the structure, external shape, and characteristics of the industrial structure. [Background technology]

[0002] The material described in this section is merely provided as background information for the present embodiment and may not constitute prior art. Recently, with the Fourth Industrial Revolution, drone-based photography technology has been commercialized and is being incorporated into many technologies. In particular, there are efforts to apply drone technology to industrial sites and the development of related technologies. Conventionally, the method of checking the condition of industrial structures has been to take pictures of the main parts of the industrial structures using a telephoto camera or to have a person approach the parts directly to carry out the inspection. The method using such a telephoto camera has the disadvantage that it is difficult to check the accurate results, and the method of having a person directly inspect the structures has the disadvantages of requiring many people and multiple devices, as well as the risk of accidents, and taking a lot of time and money. Therefore, there is a need for technology that utilizes drones to inspect industrial structures, and there is a demand for a general-purpose method and device for generating movement paths for multiple drones that can be applied to industrial structures of various sizes and shapes. In addition, when inspecting industrial structures using drones, it is desirable to use multiple drones to inspect the industrial structures, taking into account their size and structure. Therefore, there is a need for a method and device for generating an optimal drone movement path that does not cause collisions between multiple drones, taking into account the battery capacity and cost of the drones. Summary of the Invention [Problem to be solved by the invention]

[0003] The object of the present invention is to provide a method and apparatus for generating movement paths for multiple drones used to inspect industrial structures, which identifies possible and inaccessible routes for drones at multiple inspection points based on industrial structure information, optimizes a vehicle path problem model using a metaheuristic solution method to maximize the operational efficiency of multiple drones, and derives the optimal movement path. Another object of the present invention is to provide a method and device for generating movement paths for multiple drones for inspecting industrial structures, which is configured to further solve the vehicle path problem model with an exact solution method, and can determine a solution method from the exact solution method or the metaheuristic solution method based on the number of multiple inspection points, thereby providing accurate results while flexibly responding to on-site conditions. The object of the present invention is not limited to the object mentioned above, and other objects and advantages of the present invention not mentioned will be understood by the following description and will become more clearly understood by the embodiments of the present invention. Furthermore, it will be easily understood that the objects and advantages of the present invention can be realized by the means and combinations thereof as claimed in the claims. [Means for solving the problem]

[0004] To solve the above problem, a path generation device for generating movement paths of multiple drones for inspecting an industrial structure according to some embodiments of the present invention includes a data transceiver unit for receiving industrial structure information and multiple inspection points of the industrial structure, a path identification unit for identifying paths along which the drone can move and paths along which the drone cannot move at the multiple inspection points in consideration of the industrial structure information and defining connection relationships between the inspection points corresponding to the paths along which the drone can move, a graph completion unit for defining virtual paths between inspection points for which the connection relationships are not defined and completing relationships between the multiple inspection points, a problem solving unit for solving a vehicle path problem model configured based on the multiple inspection points and outputting a solution, and a path generation unit for generating movement paths of the multiple drones based on the output solution. a problem solving unit configured to solve the vehicle path problem model through a metaheuristic solving method, the problem solving unit being configured to: search for a solution based on weights according to a connection relationship between the multiple inspection points; evaluate the suitability of the searched solution by performing a suitability evaluation on the operational efficiency of the multiple drones as a standard; terminate problem solving if the evaluated suitability satisfies an algorithm termination condition; and change weights and repeat problem solving if the evaluated suitability does not satisfy an algorithm termination condition; and when problem solving has been performed a preset number of times, the problem solving unit terminates problem solving and outputs the searched solution. In addition, the metaheuristic solution is an ant colony system (ACS), and the problem solver can search for a solution by further utilizing pheromone information accumulated in an existing route as positive feedback. In addition, the problem solving unit is configured to solve the vehicle path problem model using an exact solution method, and the problem solving unit determines a solution method for the vehicle path problem model from among the metaheuristic solution method or the exact solution method depending on the number of multiple inspection points of the industrial structure, and the problem solving unit can solve the solution method for the vehicle path problem model using the metaheuristic solution method when the number of multiple inspection points of the industrial structure exceeds a predetermined reference inspection point threshold, and solve the solution method for the vehicle path problem model using the exact solution method when the number of multiple inspection points of the industrial structure is equal to or less than the predetermined reference inspection point threshold.

[0005] In addition, the vehicle path problem model may be configured to take into account the battery capacity of the multiple drones and to configure inspection points that overlap between the sub-movement paths to correspond exclusively to starting points (depots). In addition, the graph completion unit may search for paths corresponding to elements that are 0 among elements, excluding diagonal matrices, in an adjacency matrix indicating the connection relationships of the plurality of check points, and identify pairs of check points that do not form a connection relationship. In addition, the graph completion unit may define the virtual path as a detour path that connects a pair of check points that does not have the connection relationship through at least one check point. In addition, the route identification unit generates a three-dimensional model of the industrial structure based on the industrial structure information, and uses the three-dimensional model of the industrial structure to identify routes along which the drone can move and routes along which the drone cannot move at the multiple inspection points. A method for generating movement paths of multiple drones for inspecting an industrial structure according to some embodiments of the present invention includes the steps of receiving industrial structure information and multiple inspection points of the industrial structure, identifying possible routes for the drone to move at the multiple inspection points and routes for which the drone cannot move, considering the industrial structure information, defining connection relationships between the inspection points corresponding to the possible routes for the drone to move, defining virtual routes between the inspection points for which the connection relationships are not defined to complete the relationship between the multiple inspection points, solving a vehicle path problem model configured based on the multiple inspection points and outputting a solution, and generating the movement paths based on the output solution, wherein the movement paths are determined based on the number of drones. the step of outputting the solution includes solving the vehicle path problem model through a metaheuristic solving method configured to search for a solution based on weights according to a connection relationship between the plurality of inspection points, evaluate the suitability of the searched solution by performing a suitability evaluation on the basis of operational efficiency for the plurality of drones, terminate problem solving if the evaluated suitability satisfies an algorithm termination condition, and change weights and repeat problem solving if the evaluated suitability does not satisfy an algorithm termination condition, and the step of outputting the solution includes ending problem solving and outputting the searched solution when problem solving has been performed a preset number of times.

[0006] An industrial structure inspection system according to some embodiments of the present invention includes a plurality of drones for inspecting an industrial structure, a plurality of control devices corresponding to each of the plurality of drones, and a path generation device for generating movement paths for the plurality of drones, the movement paths including sub-movement paths corresponding to each of the plurality of drones, and a path generation device for providing the sub-movement paths to at least one of the corresponding drones and the control devices, the path generation device including a data transceiver unit for receiving industrial structure information and a plurality of inspection points of the industrial structure, a path identification unit for identifying paths along which the drone can move and paths along which the drone cannot move at the plurality of inspection points in consideration of the industrial structure information and defining connection relationships between the inspection points corresponding to the paths along which the drone can move, a graph completion unit for completing relationships between the plurality of inspection points by defining virtual paths between the inspection points for which the connection relationships are not defined, and a path generation unit for generating a path based on the plurality of inspection points. the problem solving unit solves a vehicle path problem model configured to solve a vehicle path problem model configured to output a solution based on a predetermined number of problem solving iterations, and a path generating unit generates movement paths for a plurality of drones based on the output solution, the movement paths for the plurality of drones including sub-movement paths corresponding to each of the plurality of drones, the problem solving unit searches for a solution based on weights according to a connection relationship between the plurality of inspection points, evaluates suitability of the searched solution by performing a suitability evaluation on the basis of operational efficiency for the plurality of drones, and solves the vehicle path problem model through a metaheuristic solving method configured to terminate problem solving if the evaluated suitability satisfies an algorithm termination condition, and change weights and repeat problem solving if the evaluated suitability does not satisfy an algorithm termination condition, and the problem solving unit terminates problem solving and outputs the searched solution when problem solving has been performed a predetermined number of times. In addition, the drone is configured to fly autonomously according to the movement path or fly according to a control signal of the control device, and the drone is further configured to generate position information and provide the generated position information to the control device, and the control device can display the movement path and the position information together on a display and provide them to a user. Effect of the Invention

[0007] The method and apparatus for generating a movement path for inspecting an industrial structure according to an embodiment of the present invention can identify routes that a drone can and cannot move at multiple inspection points based on industrial structure information, and can optimize a vehicle path problem model using a metaheuristic solution method to maximize the operational efficiency of multiple drones, thereby deriving an optimal movement path. In addition, the route generation device and method for generating a travel route for an industrial structure inspection is configured to further solve the vehicle route problem model using an exact solution method, and can determine a solution method from the exact solution method or the metaheuristic solution method based on the number of inspection points, thereby enabling accurate results to be delivered while flexibly responding to on-site conditions. In addition to the above, specific effects of the present invention will be described together with the following description of specific matters for carrying out the invention. [Brief description of the drawings]

[0008] [Figure 1] FIG. 1 is a conceptual diagram for explaining an inspection system for an industrial structure according to some embodiments of the present invention. [Diagram 2] FIG. 2 is a block diagram for explaining the configuration of the control device in detail. [Diagram 3] Figure 3 is a block diagram for explaining the configuration of the drone in detail. [Figure 4] FIG. 4 is a block diagram for explaining the configuration of the path generating device in detail. [Diagram 5] FIG. 5 is an exemplary diagram for explaining a process of generating a travel route in the route generating device. [Figure 6] FIG. 6 is an example image of a visualization of a connectivity graph. [Figure 7] FIG. 7 is an example image for explaining the process of completing a connectivity graph. [Figure 8] FIG. 8 is an example image for explaining the process of completing a connectivity graph. [Figure 9] FIG. 9 is an example image for explaining the process of completing a connectivity graph. [Figure 10] FIG. 10 is an exemplary image showing the generated travel path. [Figure 11] FIG. 11 is a flowchart of a method for generating movement paths for multiple drones for inspection of an industrial structure according to some embodiments of the present invention. [Figure 12] FIG. 12 is a flow chart for explaining the details of step S140 of FIG. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] The terms or words used in this specification and claims should not be interpreted as being limited to their general or dictionary meanings. They should be interpreted as meanings and concepts consistent with the technical idea of ​​the present invention, based on the principle that the inventor can define the concept of the term or word to best describe his / her invention. In addition, the embodiments described in this specification and the configurations shown in the drawings are merely one embodiment in which the present invention is realized, and do not represent the entire technical idea of ​​the present invention, so it should be understood that there may be various equivalents, modifications, and applicable examples that can replace them at the time of this application. Terms such as first, second, A, B, etc., used in this specification and claims can be used to describe various components, but the components should not be limited by the terms. The terms are used only to distinguish one component from another. For example, a first component can be named as a second component, and similarly, the second component can be named as a first component, without departing from the scope of the invention. The term "and / or" includes a combination of multiple related listed items or any of multiple related listed items. The terms used in the present specification and claims are merely used to describe specific embodiments and are not intended to limit the present invention. A singular expression includes a plural expression unless otherwise clearly indicated in the context. It should be understood that the terms "include" or "have" in this application do not preclude the presence or additional possibility of features, numbers, steps, operations, components, parts, or combinations thereof described in the specification. Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0010] Terms, such as those defined in commonly used dictionaries, should be construed to have a meaning consistent with the contextual meaning of the relevant art, and not to be construed as having an idealized or overly formal meaning, unless expressly defined in this application. Furthermore, the configurations, processes, steps, or methods included in the respective embodiments of the present invention may be shared within a range that is not technically inconsistent with each other. Hereinafter, an inspection system and method for an industrial structure according to some embodiments of the present invention will be described in detail with reference to FIGS. FIG. 1 is a conceptual diagram for explaining an inspection system for industrial structures according to some embodiments of the present invention, FIG. 2 is a block diagram for explaining in detail the configuration of a control device, and FIG. 3 is a block diagram for explaining in detail the configuration of a drone. Referring to FIG. 1, an inspection system (10) for an industrial structure according to some embodiments of the present invention may include a path generating device (100), a plurality of control devices (200), and a plurality of drones (300). The inspection system (10) for an industrial structure may be a system that performs inspection of the industrial structure using a drone (300). In an embodiment, the industrial structure may mean a large-scale facility that requires a large number of personnel and costs for inspection, or that is too dangerous for humans to directly perform the inspection. The industrial structure may be a building constructed for the purpose of operating a factory or a business, but is not limited thereto. Such an industrial structure may also include a large passenger aircraft as shown in FIG. 1 as an example.

[0011] The path generating device (100), the multiple control devices (200), and the multiple drones (300) can exchange data via a network. In this case, the network can include a network using a wired Internet technology, a wireless Internet technology, and a short-range communication technology. The wired Internet technology can include, for example, at least one of a local area network (LAN) and a wide area network (WAN). The wireless Internet technology may include at least one of, for example, Wireless LAN (WLAN), Digital Living Network Alliance (DLNA), Wireless Broadband (Wibro), World Interoperability for Microwave Access (Wimax), High Speed ​​Downlink Packet Access (HSDPA), High Speed ​​Uplink Packet Access (HSUPA), IEEE 802.16, Long Term Evolution (LTE), Long Term Evolution-Advanced (LTE-A), Wireless Mobile Broadband Service (WMBS), and 5G New Radio (NR) technology. However, the present embodiment is not limited thereto. The short-range communication technology may include at least one of, for example, Bluetooth, RFID (Radio Frequency Identification), Infrared Data Association (IrDA), UWB (Ultra-Wideband), ZigBee, Near Field Communication (NFC), Ultra Sound Communication (USC), Visible Light Communication (VLC), Wi-Fi, Wi-Fi Direct, and 5G New Radio (NR). However, the present embodiment is not limited thereto.

[0012] The drone (300), the control device (200), and the path generating device (100) communicating through the network may comply with technical standards and standard communication methods for mobile communication. For example, the standard communication method may include at least one of GSM (Global System for Mobile communication), CDMA (Code Division Multi Access), CDMA2000 (Code Division Multi Access 2000), EV-DO (Enhanced Voice-Data Optimized or Enhanced Voice-Data Only), WCDMA (Wideband CDMA), HSDPA (High Speed ​​Downlink Packet Access), HSUPA (High Speed ​​Uplink Packet Access), LTE (Long Term Evolution), LTEA (Long Term Evolution-Advanced), and 5G NR (New Radio). However, the present embodiment is not limited thereto. For example, each drone (300) may be connected to a corresponding control device (200) via short-range communication technology, and each control device (200) may be connected to the path generating device (100) via wired or wireless Internet technology, but is not limited thereto. In an embodiment, the path generating device (100) may receive a plurality of inspection points for inspecting an industrial structure. The path generating device (100) may generate a movement path for a plurality of drones to move through the generated plurality of inspection points. The process of generating a movement path by the path generating device (100) will be described later. The movement path generated by the path generating device (100) may include a plurality of sub-movement paths divided according to the number of drones, and each drone (300) and its corresponding control device (200) may be provided with one of the plurality of sub-movement paths.

[0013] The control device (200) may be a user device for controlling a corresponding drone (300). Referring to Figure 2, the control device (200) may include a control unit (210), a display unit (220), a communication unit (230), a processor (240), and a memory (250). The control unit (210) can receive user control input. For example, the control unit (210) can include, but is not limited to, a joystick for controlling the direction of the drone and at least one button for inputting user commands. In response to user operation via the control unit (210), the processor (240) can generate a user control signal that controls the direction of movement of the drone (300) or controls the operation of components included in the drone (300). The memory (250) is configured to store data required for data processing by the processor (240) or data generated by the data processing by the processor (240). The communication unit (230) can be configured to exchange data with at least one of the path generation device (100) and the drone (300) via a network. The processor (240) transmits the generated control signal to the drone (300) via the communication unit (230) to allow a user to manually fly the drone (300). Furthermore, the processor (240) can display the sub-movement route received from the route generation device (100) on the display unit (220) and assist the user in manually operating the drone (300) by referring to the sub-movement route. That is, the user can operate the drone (300) by referring to the sub-movement route displayed on the display unit (220) and can operate the drone (300) to follow the sub-movement route. Referring to FIG. 3, the drone (300) may include a body (310) for flight, a sensor (320), a communication unit (330), a processor (340), and a memory (350). The main body (310) is configured to make the drone (300) float in the air and move in one direction, taking into account lift, gravity, thrust, and drag acting on the drone (300). The main body (310) may include a plurality of rotors configured to generate lift to overcome gravity and to make the aircraft float in the air, and generate thrust to overcome air resistance. The main body (310) may move in one direction or change direction depending on the rotation speed of the rotors.

[0014] The sensor (320) may detect the configuration of the industrial structure and generate sensing information. The sensor (320) may include an image sensor, and the sensing information may be image information generated by photographing the exterior of the industrial structure. A user may check cracks and damage that have occurred on the exterior of the industrial structure through the image information. Furthermore, the sensor (320) may include a lidar sensor, and may maintain a distance between the drone (300) and the industrial structure using sensing information detected through the lidar sensor. Furthermore, the sensor (320) may be configured to include a GPS, and the sensing information of the drone (300) may include location information. The communication unit (330) can be configured to exchange data with the corresponding control device (200) or route generating device (100) via a network. In response to a control signal provided from the control device (200) via the communication unit (330), the processor (340) can control the main body unit (310) and the sensor (320) to inspect industrial structures using the drone (300). The memory (350) is configured to store data required for data processing by the processor (340) or data generated by the data processing by the processor (340). Here, the drone (300) can be manually flown by being controlled by a corresponding control device (200), but is not limited thereto. The drone (300) can be configured to automatically fly along a sub-movement path generated by the path generation device (100). That is, the processor (340) can control the main body (310) and the sensor (320) so that the drone (300) automatically flies along the sub-movement path to inspect the industrial structure. In the embodiment, the image information and the position information among the sensing information generated by the drone (300) may be provided in real time or quasi-real time by the corresponding control device (200). The processor (240) of the control device (200) may display the image information on the display unit (220) to assist the user in checking the state of the industrial structure in real time or quasi-real time. In addition, the processor (240) of the control device (200) may display the position information together with the sub-movement path displayed on the display unit (220) to assist the user in checking the real-time position of the drone (300) and controlling the drone (300). In the manual operation mode, the user may control the drone (300) to follow the sub-movement path in consideration of the real-time position of the drone (300). In the automatic operation mode, the user may compare the position of the drone (300) with the sub-movement path to monitor the autonomous flight state of the drone (300). In an exemplary embodiment, if the user determines that the drone (300) deviates from the sub-travel path, the user can change the operation state of the drone (300) to a manual operation mode to manually operate the drone (300). The path generation device 100 can generate a travel path for inspecting an industrial structure based on a plurality of inspection points of the industrial structure. Hereinafter, a process of generating a travel path performed by the path generation device will be described with reference to Figs. 4 to 10.

[0015] Fig. 4 is a block diagram for explaining the configuration of a route generating device in detail. Fig. 5 is an exemplary diagram for explaining a process of generating a moving route in the route generating device. Fig. 6 is an exemplary image for visualizing a connection graph. Figs. 7 to 9 are exemplary images for explaining a process of completing a connection graph. Fig. 10 is an exemplary image showing a generated moving route. The drone can inspect industrial structures by visiting specific inspection points or by moving along a route connecting the inspection points and inspecting the configuration on the route. Therefore, an optimal movement route can be generated by defining multiple inspection points according to the structure of the industrial structure and determining the optimal order in which the drone should visit the multiple inspection points. Determining the order in which the multiple drones (300) visit the multiple inspection points is an NP hard problem, and corresponds to a vehicle routing problem with a constraint on the vehicle capacity considering the battery capacity limit of the drones (300). The route generation device (100) according to an embodiment of the present invention can configure a vehicle route problem model based on the multiple inspection points of an industrial structure, solve the configured vehicle route problem model using a metaheuristic solution or an exact solution to derive an optimal solution, and generate movement routes for the multiple drones based on the derived solution. Specifically, referring to Fig. 4, the path generation device (100) includes a data transceiver unit (110), a path identification unit (120), a graph completion unit (130), a problem solving unit (140), and a path generation unit (150). In Fig. 4, the data transceiver unit (110), the path identification unit (120), the graph completion unit (130), the problem solving unit (140), and the path generation unit (150) are shown as separate blocks that are separated from one another, but this is only a functional division of the components that make up the path generation device (100) according to the operations performed by the corresponding components. Therefore, depending on the embodiment, some or all of the above components may be integrated into the same device. 5 shows the main steps for generating a travel route in the route generating device 100 and the relationship between each component in a matching manner, which will be described below with reference to FIGS.

[0016] The data transceiver (110) may receive a plurality of inspection points of the industrial structure to be inspected. The plurality of inspection points of the industrial structure may be predefined in consideration of the characteristics, specifications, and inspection distance of the drone of the industrial structure. The plurality of inspection points may be defined as positions corresponding to specific configurations of the industrial structure that require detailed inspection, but are not limited thereto, and may be defined as positions for generating a path to pass through the specific configuration that requires inspection. The drone (300) may inspect key parts at each inspection point while being fixed in position for a certain period of time, and may inspect key parts of the industrial structure while moving between the inspection points. In addition, the data transceiver 110 may receive industrial structure information including information on the characteristics and specifications of the industrial structure. In an embodiment, the plurality of inspection points of the industrial structure and the industrial structure information may be, but is not limited to, data received from a control server (not shown) of the industrial structure. In addition, the data transceiver unit (110) may be configured to transmit the movement route generated through a process described below to at least one of the multiple drones (300) and the multiple control devices (200). The route identification unit (120) can identify possible routes and improper routes at a plurality of inspection points, taking into consideration the industrial structure information. Theoretically, multiple inspection points can be connected to form a route. However, considering the structure of the industrial structure actually implemented and the flight characteristics of the drone (300), which does not easily navigate in curves, there may be points where it is difficult or practically impossible to navigate. In other words, multiple inspection points may not be connected due to the geometric limitations of the industrial structure. The route identification unit (120) can identify routes along which the drone cannot move, taking into account the industrial structure information. The route identification unit (120) identifies routes along which the drone cannot move, taking into account the industrial structure information, and the route identification unit (120) does not need to configure a connection relationship between inspection points corresponding to routes along which the drone cannot move. The route identification unit (120) can define a route of multiple inspection points as a route along which the drone can move, rather than a route along which the drone cannot move physically.

[0017] The route identification unit (120) may determine route identification based on a 3D model implemented based on the industrial structure information. In an embodiment, the route identification unit (120) may implement a 3D model of the industrial structure based on the industrial structure information, and may reflect a plurality of determined inspection points in the 3D model of the industrial structure and display them together. The route identification unit (120) identifies routes on which the drone (300) can move and routes on which the drone (300) cannot move by utilizing a plurality of inspection points displayed together with the 3D model of the industrial structure. The route identification unit 120 may determine a possible route between a plurality of inspection points and determine a weight for the determined route. Here, the weight may be, but is not limited to, a travel cost that is applied in proportion to the distance between the inspection points or the travel time between the inspection points. Since an inspection point is not connected to an impossible route, the route identification unit 120 may not set a weight for the impossible route. The route identification unit 120 may connect all possible routes of a plurality of inspection points and represent the connection relationship of the plurality of inspection points as a connection graph that visualizes the connection relationship. The connection relationship may be conveyed to a user in the form of a connection graph as visualized information as shown in FIG. 6. In the case of a connection graph formed through the path identification unit 120, it corresponds to a state in which only movable paths are connected and have the form of an incomplete graph. Referring to Fig. 7, in the connection graph of nodes 1 to 5, it can be seen that no connection relationship is formed between node 1 and node 2, node 1 and node 3, node 2 and node 4, node 3 and node 5, and node 4 and node 5. It can be seen that in an adjacency matrix representing the relationship between nodes 1 to 5, the corresponding path is represented by 0, and a path with a connection relationship is represented by 1. In other words, a pair of check points that is determined to be an impossible path and has no connection relationship can be represented by 0 in the adjacency matrix. A complete graph is a graph in which connections between all nodes (check points) are formed. Referring to Fig. 8, it can be seen that all connections between nodes 1 to 5 are formed. That is, it can be seen that only the diagonal matrix is ​​represented by 0 in the adjacency matrix showing the relationship between nodes 1 to 5. In the present embodiment, the vehicle routing problem (VRP) can only be solved as a complete graph, i.e., the connections between the multiple checkpoints connected through the route identification unit 120 are incompletely connected and require completion to solve the vehicle routing problem (VRP). The graph completion unit 130 may generate a virtual path for completing the connection relationships of the plurality of check points, where completion may mean forming all the connections between the plurality of check points.

[0018] First, the graph completion unit 130 can generate a virtual path so that a connection relationship is defined between a pair of check points that are not connected to each other in a connection graph. The graph completion unit 130 can search for a path corresponding to an element that is 0 among elements excluding a diagonal matrix in an adjacency matrix indicating the connection relationship between a plurality of check points by using a Dijkstra algorithm. The graph completion unit 130 can search for an element that is 0 among elements excluding a diagonal matrix, and define a virtual path for the connection relationship between the corresponding pair of check points. Here, the virtual path may mean a detour path connected through at least one check point. The graph completion unit 130 may set a detour path for a pair of check points that is not connected. Referring to FIG. 9, the path (dotted line) set between node 1 and node 2 may be an implicit virtual path, and the path that is actually applied may be defined as a detour path passing through another pair of check points. As a result, a plurality of check points may be converted into a completed state in which a complete graph can be constructed. That is, the adjacency matrix of the complete graph of a plurality of check points may be in a state in which all elements except for the diagonal matrix are not zero. In such a completed state, a solution for a plurality of check points is possible. In addition, the detour path is a path connected via at least one check point, and may be weighted higher than a state in which the pair of check points is directly connected in the connected graph. That is, a high detour cost is applied, and the detour path may be naturally eliminated in the process of deriving an optimal path, which will be described later. In another embodiment, the graph completion unit 130 may identify check points that are not connected and set arbitrary weights to the identified check points to define a virtual route. The arbitrary weights correspond to values ​​higher than the weights based on the distance and travel time between pairs of check points, and high detour costs are applied to the check points, which are naturally eliminated in the process of deriving an optimal route, which will be described later. The problem solving unit (140) may solve an optimal path of a plurality of fully connected inspection points, i.e., inspection points represented by a complete graph, by configuring a vehicle path model. The problem solving unit (140) may solve an optimal path by configuring a vehicle path problem model (CVRP) having a constraint condition on a vehicle capacity considering a battery capacity limit of the drone (300). In addition, the vehicle path problem model may formalize the problem by adding a condition such that an inspection point overlapping between sub-movement paths corresponds exclusively to a starting point (depot) while considering a plurality of drones and the battery capacity (use time) of the drones. Therefore, it is possible to simultaneously operate a plurality of drones corresponding to the number of sub-movement paths and inspect industrial structures. In an embodiment, a vehicle path problem model that performs optimization of an objective function while satisfying the following constraints may be configured by a linear integer programming method as shown in the following Equation 1.

[0019]

number

[0020] Constraint (5) explicitly specifies the capacity constraint, which ensures that the total flight time of the drone is equal to or less than the flight time according to the drone's battery capacity. This allows the optimal route to be set taking into account the drone's battery capacity. The sub-tour prevention constraints (6) ensure that the path always starts from the origin and eventually returns to the origin. The remaining necessary constraints (7) specify the definition domain of the variables; binary decision variables can be either 0 or 1. The problem solving unit 140 may solve the vehicle path problem model (CVRP) formalized as described above using an exact solution or a metaheuristic solution. In an embodiment, the problem solving unit 140 may determine a solution method according to the number of inspection points generated in consideration of the industrial structure information. The problem solving unit 140 may include a threshold value of a reference inspection point preset according to the type and size of the industrial structure. The problem solving unit (140) can determine a method for solving the vehicle path problem model (CVRP) according to a threshold value of the reference inspection points. If the number of multiple inspection points exceeds the threshold value, it may consume a lot of time and resources for accurate calculation, and it may be difficult to immediately respond to on-site requirements. In order to output an efficient result, it is necessary to appropriately select a solving method. The problem solver (140) may use an exact solution to solve the problem if the number of the multiple inspection points is equal to or less than a threshold. In an embodiment, the problem solver (140) may solve the vehicle path problem model through a branch and bound method. The branch and bound method may systematically enumerate all candidate solutions, estimate upper and lower bounds of the optimization values, and eliminate solutions that are determined to be unlikely. Solutions derived from the eliminated solutions are not considered, reducing unnecessary time consumption and enabling the optimal solution to be derived. Here, when the number of inspection points (nodes) is large, the difference in calculation time between the two methods may increase exponentially. When the number of inspection points is greater than a threshold, the problem solving unit (140) may perform a solution using a metaheuristic solution. In the case of industrial structures, since the structure is complex and the size is large, a large number of inspection points may be derived, and for such industrial structures, a problem solution using a metaheuristic solution may be a more appropriate solution method.

[0021] Referring to FIG. 5, the problem solving unit 140 can search for a solution based on weights according to the connection relationship between the multiple inspection points. The problem solving unit 140 can evaluate the suitability of the searched solution by evaluating the suitability of the solution based on the operational efficiency of the multiple drones. Specifically, the problem solving unit 140 can check whether the inspection time of each drone is maximized and evaluate the suitability so that an efficient movement path can be derived with a small number of drones. The problem solving unit 140 according to the embodiment can output an optimal solution through a suitability determination algorithm min(max(inspection time of each drone)) that maximizes the inspection time of each drone and minimizes the number of multiple drones. This makes it possible to generate a movement path for multiple drones that can make the most of the multiple inspection points with a minimum number of drones. The problem solving unit (140) ends the problem solving if the evaluated fitness satisfies the algorithm termination condition, and changes the graph weight and repeats the problem solving if the evaluated fitness does not satisfy the algorithm termination condition. The problem solving unit (140) ends the problem solving and outputs the result if the evaluated fitness satisfies the algorithm termination condition or if the problem solving has been performed a preset number of times. In the embodiment, the problem solving unit (140) may derive an optimal solution through an ant colony system (ACS) among metaheuristic solving methods. The ant colony system is a metaheuristic solving method that imitates the ability of real ants to find the shortest path from food to a house. Specifically, the ant colony system (ACS) is a system that applies the principle of ants, called agents, secreting pheromones on each path while moving toward a destination, and agents that pass through thereafter select the next path using the pheromone information accumulated on that path to heuristic search. The problem solving unit (140) may search for a solution by further utilizing the pheromone information accumulated on an existing path as positive feedback information. That is, the problem solving unit (140) may execute problem solving (complete a search path) by further utilizing the positive feedback (pheromone information) as well as weights according to the connection relationship between a plurality of check points, and may thereby output a more optimized path.

[0022] The path generating unit (150) may generate a movement path based on the optimal solution derived from the problem solving unit (140) and the complete graph. The movement path may include sub-movement paths along which the drones (300) move to a plurality of inspection points, respectively. The number of the drones (300) may be a minimum, and the sub-movement paths may be configured so that each drone has as much flight time as possible. The only node that overlaps between the sub-movement paths may be the starting point (depot). Thus, a number of drones corresponding to the number of sub-movement paths are operated simultaneously to inspect the industrial structure. In addition, in the embodiment, the problem solving unit (140) may display the generated movement path together with a 3D model of the industrial structure. Figure 10 illustrates an example of a schematic 3D model of the industrial structure together with the generated movement path, and it can be seen that the movement path is made up of four sub-movement paths. That is, each of the four drones can inspect the industrial structure along the corresponding sub-movement path. In addition, in an embodiment, the moving route may further include speed information corresponding to the inspection points, so that the drone (300) moves through the inspection points in order according to the moving route, and can be controlled to move along each route according to a set speed. According to an embodiment of the present invention, a route generation device for generating movement routes for multiple drones for inspecting industrial structures can identify routes that drones can and cannot travel at multiple inspection points based on industrial structure information, and can optimize a vehicle route problem model using a metaheuristic solution method to maximize the operational efficiency of the multiple drones, thereby deriving an optimal movement route. In addition, the route generation device for generating a travel route for inspecting an industrial structure is configured to further solve the vehicle route problem model by an exact solution method, and can determine a solution method from the exact solution method or the metaheuristic solution method based on the number of inspection points, thereby enabling accurate results to be transmitted while flexibly responding to on-site conditions. Hereinafter, a method for generating a movement path of a plurality of drones for inspecting an industrial structure according to some embodiments of the present invention will be described with reference to Figures 11 to 12. The method for generating a movement path of a plurality of drones for inspecting an industrial structure according to the embodiments is a method performed by the path generating device according to Figures 1 to 10, and parts that overlap with the above-mentioned embodiments will be omitted or simplified.

[0023] 11 is a flowchart of a method for generating a movement path for multiple drones for inspecting an industrial structure according to some embodiments of the present invention. FIG. 12 is a flowchart for explaining the detailed steps of step (S140) of FIG. Referring to FIG. 11, a method for generating movement paths of multiple drones for inspecting an industrial structure according to an embodiment includes: The method includes a step of receiving industrial structure information and a plurality of inspection points of the industrial structure (S100), a step of identifying routes along which the drone can move and routes along which the drone cannot move at the plurality of inspection points based on the industrial structure information (S110), a step of defining connections between the inspection points corresponding to routes along which the drone can move (S120), a step of defining virtual routes between the inspection points for which the connections are not defined, and completing the relationships between the plurality of inspection points (S130), a step of solving a vehicle path problem model constructed based on the plurality of inspection points and outputting a solution (S140), and a step of generating the movement path based on the output solution (S150). Here, the movement path may include sub-movement paths corresponding to each of the multiple drones. In an embodiment, the step of outputting the solution (S140) may include solving the vehicle path problem model through a metaheuristic solution method configured to search for a solution based on weights corresponding to the connectivity of the plurality of inspection points, evaluate the suitability of the searched solution by evaluating the suitability of the solution based on the operational efficiency of the plurality of drones, terminate problem solving if the evaluated suitability satisfies an algorithm termination condition, and change the weights and repeat problem solving if the evaluated suitability does not satisfy the algorithm termination condition. In an embodiment, the step of outputting the solution (S140) may terminate the problem solving and output the searched solution when the problem solving is performed a preset number of times. In an embodiment, the metaheuristic solution is an ant colony system (ACS), and the step of outputting the solution (S140) may include searching for a solution by further utilizing pheromone information accumulated in an existing route as positive feedback.

[0024] In an embodiment, the step of outputting the solution (S140) may further comprise solving the vehicle path problem model using an exact solution method. In an embodiment, the step of outputting the solution (S140) may include determining a solution method for the vehicle path problem model from among the metaheuristic solution method or the exact solution method depending on the number of inspection points of the industrial structure. Referring to FIG. 12, the step of outputting the solution (S140) may include a step of comparing the number of a plurality of inspection points of the industrial structure with a preset reference inspection point threshold (S142), a step of solving a solution method for the vehicle path problem model using a metaheuristic solution method when the number of a plurality of inspection points of the industrial structure exceeds the preset reference inspection point threshold (S144), and a step of solving the solution method for the vehicle path problem model using the exact solution method when the number of a plurality of inspection points of the industrial structure is equal to or less than the preset reference inspection point threshold (S146). In an embodiment, the vehicle path problem model may be configured to take into account the battery capacity of the multiple drones and to configure inspection points that overlap between the sub-movement paths to correspond exclusively to starting points (depots). In an embodiment, the step of completing the relationship between the plurality of inspection points (S130) may include searching for a path corresponding to an element that is 0 among elements excluding a diagonal matrix in an adjacency matrix indicating the connection relationship between the plurality of inspection points, and identifying pairs of inspection points that do not form a connection relationship. In an embodiment, the virtual path may be defined as a detour path that connects a pair of check points that do not have the connection relationship through at least one check point. In an embodiment, the step (S110) of identifying routes along which the drone can move and routes along which the drone cannot move at the multiple inspection points taking into account the industrial structure information may generate a 3D model of the industrial structure based on the industrial structure information, and use the 3D model of the industrial structure to identify routes along which the drone can move and routes along which the drone cannot move at the multiple inspection points. The method for generating movement paths of a plurality of drones for inspecting industrial structures according to the embodiment can also be embodied in the form of a computer-readable medium storing instructions and data executable by a computer. In this case, the instructions and data can be stored in the form of a program code, and when executed by a processor, a predetermined program module can be generated to perform a predetermined operation. In addition, the computer-readable medium can be any available medium accessible by a computer, including both volatile and non-volatile media, and both separate and non-separate media. In addition, the computer-readable medium can be a computer recording medium, but the computer recording medium can include all volatile and non-volatile, separate and non-separate media embodied in any method or technology for storing information such as computer-readable instructions, data structures, program modules, or other data. For example, the computer recording medium can be a magnetic storage medium such as a HDD and SSD, an optical storage medium such as a CD, a DVD, and a Blu-ray disc, or a memory included in a server accessible via a network.

[0025] In addition, the method for generating movement paths of a plurality of drones for inspecting an industrial structure according to the embodiment may be embodied as a computer program (or a computer program product) including instructions executable by a computer. The computer program includes programmable machine instructions processed by a processor, and may be embodied in a high-level programming language, an object-oriented programming language, an assembly language, a machine language, or the like. In addition, the computer program is recorded in a tangible computer-readable recording medium (e.g., a memory, a hard disk, a magnetic / optical medium, or a solid-state drive (SSD), etc.). Therefore, the method for generating a movement path of a plurality of drones for inspecting an industrial structure according to the embodiment can be embodied by executing the computer program as described above by a computing device. The computing device may include at least a processor, a memory, a storage device, a high-speed interface connected to the memory and a high-speed expansion port, and a low-speed interface connected to a low-speed bus and the storage device. Each of these components is connected to each other using various buses and may be mounted on a common motherboard or in any other suitable manner. Here, a processor may process instructions within a computing device, including instructions stored in a memory or storage device, for example to display graphical information to provide a Graphic User Interface (GUI) on an external input or output device, such as a display connected to a high speed interface. In alternative embodiments, multiple processors and / or multiple buses may be used, along with multiple memories and memory configurations, as appropriate. Additionally, a processor may be embodied in a chipset, which may be comprised of chips containing multiple independent analog and / or digital processors. Also, memory stores information within a computing device. In one example, memory may be comprised of a volatile memory unit or a collection thereof. In another example, memory may be comprised of a non-volatile memory unit or a collection thereof. Additionally, memory may be other forms of computer readable media, such as, for example, a magnetic disk or an optical disk. A storage device can provide a large amount of storage space to a computing device. A storage device can be a computer readable medium or a configuration that includes such a medium. For example, a storage device can include a device in a Storage Area Network (SAN) or other configuration, and can be a floppy disk drive, a hard disk drive, an optical disk drive, a tape drive, a flash memory, or other similar semiconductor memory device, or an array of devices.

[0026] The above description is merely an illustrative example of the technical idea of ​​the present embodiment, and various modifications and variations may be made by a person having ordinary knowledge in the technical field to which the present embodiment belongs, without departing from the essential characteristics of the present embodiment. Therefore, the present embodiment is intended to explain, not to limit, the technical idea of ​​the present embodiment, and the scope of the technical idea of ​​the present embodiment is not limited by such an embodiment. The scope of protection of the present embodiment should be interpreted according to the following claims, and all technical ideas within the scope equivalent thereto should be interpreted as being included in the scope of the present embodiment.

Claims

1. A route generation device that generates movement routes of multiple drones for inspecting industrial structures, A data transceiver unit for receiving industrial structure information and a plurality of inspection points of the industrial structure; A route identification unit that identifies routes along which the drone can move and routes along which the drone cannot move at the plurality of inspection points in consideration of the industrial structure information, and defines a connection relationship between the inspection points corresponding to the routes along which the drone can move; a graph completion unit that completes the relationships between the plurality of check points by defining virtual paths between the check points whose connection relationships are not defined; A problem solving unit that solves a vehicle path problem model based on the plurality of inspection points and outputs a solution; and A route generating unit that generates a route for a plurality of drones based on the output solution, The movement paths of the plurality of drones include sub-movement paths corresponding to each of the plurality of drones; The problem solving unit searches for a solution based on weights according to the connection relationships of the plurality of inspection points, evaluates the suitability of the searched solution based on the operational efficiency of the plurality of drones, and ends the problem solving if the evaluated suitability satisfies an algorithm termination condition. If the evaluated suitability does not satisfy an algorithm termination condition, the weights are changed and the problem solving is repeated. Solving the vehicle path problem model through a metaheuristic solving method, the problem solving unit terminates the problem solving and outputs the searched solution when the problem solving has been repeated a preset number of times. Path generation device.

2. The metaheuristic solution is an ant colony system (ACS), The problem solving unit further utilizes the pheromone information accumulated in the existing route as positive feedback to search for a solution. The route generating device according to claim 1 .

3. The problem solver is further configured to solve the vehicle path problem model using an exact solution method; the problem solving unit determines a method for solving the vehicle path problem model from among the metaheuristic solving method or the exact solving method according to a number of a plurality of inspection points of the industrial structure; the problem solving unit solves the solution method of the vehicle path problem model using the metaheuristic solving method when the number of the plurality of inspection points of the industrial structure exceeds a preset threshold value of a reference inspection point, and solves the solution method of the vehicle path problem model using the exact solving method when the number of the plurality of inspection points of the industrial structure is equal to or less than the preset threshold value of a reference inspection point; The route generating device according to claim 1 .

4. The vehicle path problem model is Considering the battery capacity of the plurality of drones, the inspection points overlapping between the sub-movement paths are configured to correspond exclusively to starting points (depots); The route generating device according to claim 1 .

5. The graph completion unit: searching for paths corresponding to elements that are 0 among elements, excluding diagonal matrices, in an adjacency matrix indicating connections between the plurality of inspection points, to identify pairs of inspection points that are not connected; The route generating device according to claim 1 .

6. The graph completion unit: The virtual path is defined as a detour path that connects a pair of the inspection points that are not connected through at least one inspection point. The route generating device according to claim 5 .

7. The route identification unit generating a three-dimensional model of the industrial structure based on the industrial structure information, and using the three-dimensional model of the industrial structure to identify routes along which the drone can move and routes along which the drone cannot move at the plurality of inspection points; The route generating device according to claim 1 .

8. A method for generating movement paths for a plurality of drones for inspecting an industrial structure, comprising: receiving industrial structure information, a plurality of inspection points of the industrial structure; identifying routes along which drones can move and routes along which drones cannot move at the plurality of inspection points, taking into account the industrial structure information; Defining a connection relationship between inspection points corresponding to a route along which the drone can move; defining a virtual path between the inspection points whose connection relationships are not defined, thereby completing the relationships between the plurality of inspection points; solving a vehicle path problem model configured based on the plurality of check points and outputting a solution; and generating the travel path based on the output solution, The movement path includes sub-movement paths corresponding to each of a plurality of drones; The step of outputting the solution includes solving the vehicle path problem model through a metaheuristic solution method configured to search for a solution based on weights according to the connection relationship of the plurality of inspection points, evaluate the suitability of the searched solution based on the operational efficiency of the plurality of drones, and terminate the problem solving if the evaluated suitability satisfies an algorithm termination condition, and change the weights and repeat the problem solving if the evaluated suitability does not satisfy an algorithm termination condition; The step of outputting the solution includes terminating the problem solving and outputting the searched solution when the problem solving is repeated a preset number of times. A method for generating movement paths for multiple drones for the inspection of industrial structures.

9. Multiple drones for the inspection of industrial structures; A plurality of control devices corresponding to the plurality of drones; and A system for inspecting an industrial structure, comprising: a route generation device for generating a movement route for the plurality of drones, the movement route including a sub-movement route corresponding to each of the plurality of drones; and a route generation device for providing the sub-movement route to at least one of the corresponding drones and a control device, The path generation device includes: A data transceiver unit for receiving industrial structure information and a plurality of inspection points of the industrial structure; A route identification unit that identifies routes along which the drone can move and routes along which the drone cannot move at the plurality of inspection points in consideration of the industrial structure information, and defines a connection relationship between the inspection points corresponding to the routes along which the drone can move; a graph completion unit that completes the relationships between the plurality of check points by defining virtual paths between the check points whose connection relationships are not defined; A problem solving unit that solves a vehicle path problem model based on the plurality of inspection points and outputs a solution; and A route generating unit that generates a route for a plurality of drones based on the output solution, The movement paths of the plurality of drones include sub-movement paths corresponding to each of the plurality of drones; The problem solving unit searches for a solution based on weights according to the connection relationships of the plurality of inspection points, evaluates the suitability of the searched solution based on the operational efficiency of the plurality of drones, and ends the problem solving if the evaluated suitability satisfies an algorithm termination condition. If the evaluated suitability does not satisfy an algorithm termination condition, the weights are changed and the problem solving is repeated. Solving the vehicle path problem model through a metaheuristic solving method, the problem solving unit terminates the problem solving and outputs the searched solution when the problem solving has been repeated a preset number of times. Inspection system for industrial structures.

10. The drone is configured to fly autonomously along the travel path or according to control signals from the controller; The drone is further configured to generate position information and provide the generated position information to the controller; The control device displays the travel route and the position information together on a display and provides them to a user. The industrial structure inspection system according to claim 9.

Images