Multi-type unmanned aerial vehicle nest site selection method and device based on patrol task allocation

Abstract

The application discloses a multi-type unmanned aerial vehicle nest site selection method and device based on inspection task allocation, which comprises the following steps: based on the inspection task, a first target function corresponding to the number of unmanned aerial vehicle nests and a first constraint condition corresponding to the position of the unmanned aerial vehicle nests are given respectively; based on the first target function and the first constraint condition, a candidate address set is obtained; according to the inspection cost, the inspection range and the inspection area of each type of unmanned aerial vehicle, a second target function and a second constraint condition based on the unmanned aerial vehicle type decision and the inspection task are constructed; based on the second target function and the second constraint condition, a meta-heuristic optimization algorithm is used to optimize in the candidate address set, and a target nest position set corresponding to each type of unmanned aerial vehicle is obtained. The application realizes the reasonable setting of each type of unmanned aerial vehicle nest, allows each type of unmanned aerial vehicle to be used in combination in the power inspection process, fully plays the advantages of each type of unmanned aerial vehicle, and ensures the efficient inspection of the unmanned aerial vehicle.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of unmanned aerial vehicle nest site selection, and particularly relates to a multi-type unmanned aerial vehicle nest site selection method and device based on inspection task allocation. BACKGROUND

[0002] With the continuous expansion of the power grid scale and the continuous increase of power facilities, the power inspection task becomes more and more heavy and complex. The traditional inspection method mainly relies on manual work, but this method has problems of low inspection efficiency, great safety hidden danger, high cost and the like. Therefore, using unmanned aerial vehicles for power inspection has become a trend.

[0003] The unmanned aerial vehicle inspection has advantages of flexibility, high efficiency, safety and the like, and can significantly improve the inspection efficiency and quality and reduce the inspection cost. In the unmanned aerial vehicle inspection, the fixed-wing unmanned aerial vehicle and the multi-rotor unmanned aerial vehicle each has advantages. The fixed-wing unmanned aerial vehicle has advantages of fast speed and long range, and is suitable for large-scale and long-distance inspection; and the multi-rotor unmanned aerial vehicle has advantages of low flight height, flexible maneuvering, simple operation and low cost, and is suitable for fine inspection task.

[0004] At present, in actual application, the fixed-wing unmanned aerial vehicle or the multi-rotor unmanned aerial vehicle is separately used for power inspection. Although the fixed-wing unmanned aerial vehicle has advantages of fast speed and long range, it cannot hover and vertically take off like the multi-rotor unmanned aerial vehicle, and therefore the inspection capability in complex terrain and narrow space is limited. Although the multi-rotor unmanned aerial vehicle is flexible, the endurance, flight speed and communication distance are relatively limited, and it is difficult to meet the demand of large-scale and long-distance inspection.

[0005] How to combine the fixed-wing unmanned aerial vehicle and the multi-rotor unmanned aerial vehicle in the power inspection process to give full play to respective advantages is a problem to be solved at present. However, before using the combined inspection, how to reasonably set the nest of the fixed-wing unmanned aerial vehicle and the multi-rotor unmanned aerial vehicle to ensure the efficient inspection of the unmanned aerial vehicle is a problem to be solved at present. SUMMARY

[0006] In view of the defects in the prior art, the application provides a multi-type unmanned aerial vehicle nest site selection method based on inspection task allocation, which comprises the following steps:

[0007] Based on the inspection task, a first target function corresponding to the number of unmanned aerial vehicle nests and a first constraint condition corresponding to the position of the unmanned aerial vehicle nest are given respectively;

[0008] Based on the first target function and the first constraint condition, a candidate address set is obtained;

[0009] According to the inspection cost, the inspection range and the inspection area of each type of unmanned aerial vehicle, a second target function and a second constraint condition based on the unmanned aerial vehicle type decision and the inspection task are constructed.

[0010] Based on the second objective function and the second constraint condition, an optimization is performed in the candidate address set by a meta-heuristic optimization algorithm to obtain a target nest position set corresponding to each type of unmanned aerial vehicle.

[0011] According to the technical solution, the number of unmanned aerial vehicle nests is limited and a candidate address set is obtained by analyzing the inspection task, and then the inspection cost, inspection range and inspection area of each type of unmanned aerial vehicle are further limited in the economic aspect, and the meta-heuristic optimization algorithm is used to optimize the candidate address set to obtain a target nest position set, thereby realizing reasonable setting of the nests of each type of unmanned aerial vehicle, allowing each type of unmanned aerial vehicle to be used in combination during power inspection, fully exerting the advantages of each type of unmanned aerial vehicle and ensuring efficient inspection of the unmanned aerial vehicle.

[0012] In a possible implementation, the first objective function is specifically represented as:

[0013]

[0014] The first constraint condition is specifically represented as:

[0015]

[0016] wherein x j is a result of establishing a nest at the jth undetermined address, and x j is a Boolean variable, J is a set of undetermined addresses in the inspection area, X ij is a relationship between the jth undetermined address and the i th target inspection device, and X ij is a Boolean variable, and I is a set of all target inspection devices in the inspection area.

[0017] In a possible implementation, the candidate address set is obtained based on the first objective function and the first constraint condition, and the method comprises the following steps:

[0018] The first objective function and the first constraint condition are used to obtain an undetermined address set.

[0019] Based on the undetermined address set, a corresponding relationship is established between each target inspection device in the inspection area and the nearest undetermined address to obtain the candidate address set.

[0020] In a possible implementation, the inspection cost includes a construction cost, a flight cost and a penalty cost,

[0021] According to the inspection cost, the inspection range and the inspection area of each type of unmanned aerial vehicle, a second objective function and a second constraint condition based on the unmanned aerial vehicle type decision and the inspection task are constructed, and the second objective function and the second constraint condition specifically comprise:

[0022] The construction cost, flight cost and penalty cost of each type of unmanned aerial vehicle are obtained, the corresponding relationship and flight distance of each type of unmanned aerial vehicle and the target inspection equipment are combined, the probability of nest failure of each type of unmanned aerial vehicle is analyzed, and a second objective function is constructed;

[0023] The inspection range of each type of unmanned aerial vehicle, the flight distance of each type of unmanned aerial vehicle and the target inspection equipment, the corresponding relationship of each type of unmanned aerial vehicle and the target inspection equipment are analyzed, and the second constraint condition is constructed in combination with the number of each type of unmanned aerial vehicle.

[0024] In a possible implementation, the types of unmanned aerial vehicles include fixed-wing unmanned aerial vehicles and multi-rotor unmanned aerial vehicles; the second objective function is specifically represented as:

[0025]

[0026] Wherein, J * is a set of candidate addresses for building nests, I is a set of all target inspection equipment in the inspection area, c1 is the construction cost of the fixed-wing unmanned aerial vehicle nest, y j is the result of building a fixed-wing unmanned aerial vehicle nest at the jth candidate address, and y j is a Boolean variable, c0 is the construction cost of the multi-rotor unmanned aerial vehicle nest, z j is the result of building a multi-rotor unmanned aerial vehicle nest at the jth candidate address, and z j is a Boolean variable, T is the total running time of the inspection system including each type of unmanned aerial vehicle, f i is the inspection service demand frequency of the ith target inspection equipment, a is the flight cost per unit distance of the unmanned aerial vehicle, d ij is the flight distance between the ith target inspection equipment and the jth candidate address, Y ij is the corresponding relationship between the fixed-wing unmanned aerial vehicle in the jth candidate address and the ith target inspection equipment, and Y ij is a Boolean variable, P fail is the probability of failure of the multi-rotor unmanned aerial vehicle nest, Z ij is the corresponding relationship between the multi-rotor unmanned aerial vehicle in the jth candidate address and the ith target inspection equipment, and Z ij is a Boolean variable, β is the penalty cost per unit distance of manual inspection when the multi-rotor unmanned aerial vehicle nest fails, is the penalty distance when the ith target inspection equipment is not covered by the multi-rotor unmanned aerial vehicle nest.

[0027] In a possible implementation, the types of unmanned aerial vehicles include fixed-wing unmanned aerial vehicles and multi-rotor unmanned aerial vehicles; the second constraint condition is specifically represented as:

[0028]

[0029] wherein, J * is a set of candidate addresses for building nests, I is a set of all target inspection devices in the inspection area, d ij is the flight distance between the i-th target inspection device and the j-th candidate address, Y ij is the correspondence between the fixed-wing unmanned aerial vehicle in the j-th candidate address and the i-th target inspection device, and Y ij is a Boolean variable, Z ij is the correspondence between the multi-rotor unmanned aerial vehicle in the j-th candidate address and the i-th target inspection device, and Z ij is a Boolean variable, y j is the result of building a fixed-wing unmanned aerial vehicle nest in the j-th candidate address, and y j is a Boolean variable, z j is the result of building a multi-rotor unmanned aerial vehicle nest in the j-th candidate address, and z j is a Boolean variable, R is the maximum service radius of the candidate address, N1 is the maximum number of fixed-wing unmanned aerial vehicle candidate addresses, and N0 is the maximum number of multi-rotor unmanned aerial vehicle candidate addresses.

[0030] In a possible implementation, based on the second objective function and the second constraint condition, an optimization iteration is performed in the candidate address set by using a meta-heuristic optimization algorithm to obtain a target nest position set corresponding to each type of unmanned aerial vehicle, and the optimization iteration specifically includes:

[0031] Based on the model operator for changing the unmanned aerial vehicle type of the candidate address, the unmanned aerial vehicle type of the candidate address in the candidate address set is changed to perform an optimization iteration to obtain a first optimization set;

[0032] Based on the first optimization set, the unmanned aerial vehicle type of the candidate address and / or the correspondence between the candidate address and the target inspection device is changed by using a relationship operator and a hybrid operator to perform an optimization iteration to obtain a second optimization set, wherein the relationship operator is used to adjust the correspondence between the candidate address and the target inspection device, and the hybrid operator includes the model operator and the relationship operator;

[0033] Based on the relationship operator, the correspondence between the candidate address and the target inspection device in the second optimization set is adjusted to perform an optimization iteration to obtain the target nest position set.

[0034] In a possible implementation, based on the first optimization set, the unmanned aerial vehicle type of the candidate address and / or the correspondence between the candidate address and the target inspection device is changed by using a relationship operator and a hybrid operator to perform an optimization iteration to obtain a second optimization set, and the optimization iteration specifically includes:

[0035] A comparison result is obtained by comparing the random number with a preset optimization threshold;

[0036] determine an operator corresponding to the comparison result, and optimize the first optimization set based on the operator corresponding to the comparison result;

[0037] If the number of iterations reaches a preset second iteration threshold, a second optimization set is obtained.

[0038] In a possible implementation, based on the relationship operator, the correspondence between the candidate address and the target inspection device in the second optimization set is adjusted, and optimization iteration is performed to obtain a target nest position set, specifically including:

[0039] The correspondence between the candidate address and the target inspection device is adjusted through the mth iteration of the second optimization set, and an iteration result set Q is obtained m , wherein m is a positive integer and m is greater than 1;

[0040] According to Q m , a second target function value corresponding to Q m-1 , and a difference between the second target function value corresponding to Q m,sa , a current optimal result set is determined and an iteration parameter T corresponding to the iteration result set is updated.

[0041] When T m,sa is greater than a preset temperature threshold or m is greater than a preset maximum iteration threshold, the current optimal result set is taken as the target nest position set.

[0042] The application further discloses a multi-type unmanned aerial vehicle nest site selection device based on an inspection task allocation, comprising:

[0043] A first condition construction module is configured to give a first target function corresponding to the number of unmanned aerial vehicle nests and a first constraint condition corresponding to the position of the unmanned aerial vehicle nests based on the inspection task.

[0044] A candidate address determination module is configured to obtain a candidate address set based on the first target function and the first constraint condition.

[0045] A second condition construction module is configured to construct a second target function and a second constraint condition based on the unmanned aerial vehicle type decision and the inspection task according to the inspection cost, the inspection range and the inspection area of each type of unmanned aerial vehicle.

[0046] A target position determination module is configured to perform optimization in the candidate address set based on the second target function and the second constraint condition through a meta-heuristic optimization algorithm to obtain a target nest position set corresponding to each type of unmanned aerial vehicle.

[0047] The multi-type unmanned aerial vehicle nest site selection method based on the inspection task allocation provided by the application has at least the following beneficial effects:

[0048] By establishing a two-stage multi-type unmanned aerial vehicle nest site selection method based on inspection task allocation, a target nest position set with minimum total cost is determined, and the target nest position set includes the deployment position of the nest, the type of the unmanned aerial vehicle of the nest and the allocation of the target inspection equipment between the nests; in the first stage, by analyzing the inspection task, the number of unmanned aerial vehicle nests is limited and a candidate address set is obtained, in the second stage, the inspection cost, the inspection range and the inspection area of each type of unmanned aerial vehicle are further limited in the economic level, a meta-heuristic optimization algorithm is used to optimize the candidate address set, and a target nest position set is obtained, so that the fixed-wing unmanned aerial vehicle nest and the multi-rotor unmanned aerial vehicle nest are reasonably set, the fixed-wing unmanned aerial vehicle and the multi-rotor unmanned aerial vehicle are combined for use in the power inspection process, the advantages of each are fully utilized, and efficient unmanned aerial vehicle inspection is ensured. BRIEF DESCRIPTION OF DRAWINGS

[0049] Figure 1 The flow chart of the multi-type unmanned aerial vehicle nest site selection method based on inspection task allocation provided by the embodiment of the application is provided.

[0050] Figure 2 The flow chart of the meta-heuristic optimization algorithm provided by the embodiment of the application is provided.

[0051] Figure 3 The operation schematic diagram of the model operator provided by the embodiment of the application is provided.

[0052] Figure 4 The operation schematic diagram of the relationship operator provided by the embodiment of the application is provided.

[0053] Figure 5 The structural schematic diagram of the inspection area provided by the embodiment of the application is provided.

[0054] Figure 6 The structural schematic diagram of the candidate address set provided by the embodiment of the application is provided.

[0055] Figure 7 The structural schematic diagram of the target nest position set provided by the embodiment of the application is provided.

[0056] Figure 8 The structural diagram of the multi-type unmanned aerial vehicle nest site selection device based on inspection task allocation provided by the embodiment of the application is provided.

[0057] Among them, 201, the first condition construction module; 202, the candidate address determination module; 203, the second condition construction module; 204, the target position determination module. DETAILED DESCRIPTION

[0058] In order to better understand the above technical solutions, the above technical solutions will be described in detail below in combination with the drawings of the specification and specific embodiments. Obviously, the described embodiments are only part of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor are within the scope of protection of the present application.

[0059] The terms used in the embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to limit the present application. The singular forms "a", "said" and "the" used in the embodiments of the present application and the appended claims are also intended to include the plural forms, unless the context clearly indicates otherwise. "Multiple" generally includes at least two.

[0060] It should also be noted that the terms "include", "contain" or any other variants thereof are intended to cover non-exclusive inclusion, so that the goods or devices including a series of elements not only include those elements, but also include other elements not explicitly listed, or include elements inherent to such goods or devices. Without more limitation, the element defined by the sentence "including a…" does not exclude the presence of other identical elements in the goods or devices including the element.

[0061] There are several target inspection devices to be inspected in the inspection area, including extra-high voltage transmission line towers, transmission lines, power towers, substations and distribution facilities, etc. In order to improve the automation level of power inspection, further improve the inspection efficiency and reduce the cost, it is necessary to deploy unmanned aerial vehicle nests in the inspection area to realize automatic unmanned aerial vehicle power inspection. Each unmanned aerial vehicle nest is paired with an unmanned aerial vehicle, which is responsible for the inspection of several target inspection devices within the coverage of the nest. When performing each inspection task, the unmanned aerial vehicle departs from the nest after the nest is fully charged, goes to the target inspection device to be inspected, and returns to the nest for charging after the inspection task is completed and waits for the next task.

[0062] The nest site selection needs to consider many factors such as terrain, climate, power facility distribution, etc. to ensure the safe take-off and landing and efficient inspection of the unmanned aerial vehicle. The allocation of inspection tasks needs to consider the performance characteristics of the unmanned aerial vehicle, the inspection target and its priority, etc. to optimize the inspection efficiency and quality.

[0063] The location of the nest is not easily changed once selected, and due to the limitations of power supply, signal, network and security factors, the unmanned aerial vehicle nest can only be deployed near the ultra-high voltage transmission line. In actual operation, the unmanned aerial vehicle nest may fail due to weather, mechanical failure and other reasons, thereby causing a more serious impact on power inspection. Due to different requirements of ultra-high voltage transmission line inspection tasks, different qualities and maintenance inputs of unmanned aerial vehicle nests, the unmanned aerial vehicle nest is usually divided into fixed-wing unmanned aerial vehicle nests and multi-rotor unmanned aerial vehicle nests. The fixed-wing unmanned aerial vehicle nest is generally deployed in a dedicated area near the ultra-high voltage transmission line, and has a large volume, a high construction cost and needs to invest sufficient operation and maintenance cost. The application considers that the fixed-wing unmanned aerial vehicle nest always maintains normal work within the task cycle, and the fixed-wing unmanned aerial vehicle has a long endurance time. The multi-rotor unmanned aerial vehicle nest is generally directly deployed on the ultra-high voltage transmission tower. It has a small volume, a low construction cost but has a certain probability of failure and cannot work normally. Once the multi-rotor unmanned aerial vehicle nest fails, the corresponding inspection task needs to be completed by manual replacement, thereby generating additional manual inspection cost. In the actual nest inspection problem, the construction nest cost accounts for a large proportion in the total cost, so the decision maker usually first wants to use the least number of nests to complete the full coverage of all target inspection equipment to be inspected in the inspection area. Next, the nest type used and the inspection task allocation scheme are selected according to the inspection frequency of the ultra-high voltage transmission line, the distance between the transmission tower and the nest, the reliability of the nest and the manual cost and other factors.

[0064] The application provides a multi-type unmanned aerial vehicle nest site selection method based on inspection task allocation, which determines the deployment position, type and allocation of the demand points to be inspected among the nests of the fixed-wing unmanned aerial vehicle nest and the multi-rotor unmanned aerial vehicle nest, determines the nest site selection and the type of the unmanned aerial vehicle corresponding to the nest position, realizes the inspection task of all target inspection equipment in the inspection area on the basis of reducing the cost, improves the efficiency and quality of power inspection, and provides a strong guarantee for the safe operation of power facilities.

[0065] As shown in Figure 1 The application provides a multi-type unmanned aerial vehicle nest site selection method based on inspection task allocation, and the specific steps are as follows:

[0066] S101: Based on the inspection task, a first target function corresponding to the number of unmanned aerial vehicle nests and a first constraint condition corresponding to the position of the unmanned aerial vehicle nest are given.

[0067] Specifically, the first target function is specifically represented as:

[0068]

[0069] The first constraint condition is specifically represented as:

[0070]

[0071] wherein x j is the result of establishing a nest at the jth pending address, and x j is a Boolean variable, if x j = 0, it means that no nest is established at the jth pending address, if x j = 1, it means that a nest is established at the jth pending address, J is a set of pending addresses in the inspection area, X ij is the relationship between the distance between the jth pending address and the ith target inspection device and the inspection range of the unmanned aerial vehicle, and X ij is a Boolean variable, if X ij = 0, it means that the distance between the jth pending address and the ith target inspection device is not within the inspection range of the unmanned aerial vehicle, if X ij = 1, it means that the distance between the jth pending address and the ith target inspection device is within the inspection range of the unmanned aerial vehicle, I is a set of all target inspection devices in the inspection area.

[0072] The first objective function is used to minimize the number of unmanned aerial vehicle nest construction points, that is, to establish the least number of nests to achieve the inspection task of all target inspection devices in the inspection area. The first formula in the first constraint condition indicates that for any one target inspection device i∈I, it is at least within the coverage range of one unmanned aerial vehicle nest j∈J. The second formula in the first constraint condition indicates that only when a nest is established at the pending address j∈J, the unmanned aerial vehicle can start from the pending address j to inspect the target inspection device i∈I.

[0073] S102: Obtain a candidate address set based on the first objective function and the first constraint condition.

[0074] Specifically, based on the first objective function and the first constraint condition, a set of pending addresses is obtained. Based on the set of pending addresses, each target inspection device in the inspection area is respectively associated with the nearest pending address to obtain a candidate address set.

[0075] In a specific embodiment, the set of pending addresses described above can be obtained by inputting the first objective function and the first constraint condition into a gurobi solver to obtain a candidate address set, or other optimization algorithms can be used, which are not limited.

[0076] It can be understood that the candidate addresses in the candidate address set obtained according to the first constraint condition and the first target function do not have a corresponding relationship with the target inspection equipment, and only need to meet the condition that the target inspection equipment is at least in the coverage range of one candidate address. There can be a case that multiple candidate addresses cover the same target inspection equipment. Based on this, the application establishes a corresponding relationship between each target inspection equipment and the nearest undetermined address in the undetermined address set by using a greedy algorithm to obtain the candidate address set. The candidate address set is used as an initial solution in the solving process based on the second target function and the second constraint condition. In a specific example, since the construction cost of the multi-rotor unmanned aerial vehicle nest is lower than the construction cost of the fixed-wing unmanned aerial vehicle nest, the unmanned aerial vehicle type of all candidate addresses in the candidate address set is set to the multi-rotor unmanned aerial vehicle. In other embodiments, the unmanned aerial vehicle type in the initial solution can be set to other unmanned aerial vehicle types, which is not limited.

[0077] S103: According to the inspection cost, the inspection range and the inspection area of each type of unmanned aerial vehicle, a second target function and a second constraint condition based on the unmanned aerial vehicle type decision and the inspection task are constructed.

[0078] Specifically, the inspection cost includes the construction cost, the flight cost and the penalty cost. The construction cost, the flight cost and the penalty cost of each type of unmanned aerial vehicle are obtained, the corresponding relationship between each type of unmanned aerial vehicle and the target inspection equipment and the flight distance are combined, the probability of failure of each type of unmanned aerial vehicle nest is analyzed, and the second target function is constructed. The inspection range of each type of unmanned aerial vehicle, the flight distance of each type of unmanned aerial vehicle and the target inspection equipment, the corresponding relationship between each type of unmanned aerial vehicle and the target inspection equipment, and the number of each type of unmanned aerial vehicle are combined to construct the second constraint condition.

[0079] Further, the second target function is specifically represented as:

[0080]

[0081] wherein J * is the candidate address set for constructing the nest, I is the set of all target inspection equipment in the inspection area, c1 is the construction cost of the fixed-wing unmanned aerial vehicle nest, y j is the result of constructing the fixed-wing unmanned aerial vehicle nest at the jth candidate address, and y j is a Boolean variable, if y j = 0, it indicates that the fixed-wing unmanned aerial vehicle nest is not constructed at the jth candidate address, if y j = 1, it indicates that the fixed-wing unmanned aerial vehicle nest is constructed at the jth candidate address, c0 is the construction cost of the multi-rotor unmanned aerial vehicle nest, z j is the result of constructing the multi-rotor unmanned aerial vehicle nest at the jth candidate address, and z j is a Boolean variable, if zj = 0, it means that the multi-rotor drone nest is not built on the jth candidate address, and if z j = 1, it means that the multi-rotor drone nest is built on the jth candidate address, T is the total running time of the inspection system including various types of drones, f i is the inspection service demand frequency of the ith target inspection equipment, a is the flight cost of the drone per unit distance, d ij is the flight distance between the ith target inspection equipment and the jth candidate address, Y ij is the correspondence between the fixed-wing drone in the jth candidate address and the ith target inspection equipment, and Y ij is a Boolean variable, if Y ij = 0, it means that there is no correspondence between the fixed-wing drone in the jth candidate address and the ith target inspection equipment, and if Y ij = 1, it means that there is correspondence between the fixed-wing drone in the jth candidate address and the ith target inspection equipment, P fail is the probability of failure of the multi-rotor drone nest, Z ij is the correspondence between the multi-rotor drone in the jth candidate address and the ith target inspection equipment, and Z ij is a Boolean variable, if Z ij = 0, it means that there is no correspondence between the multi-rotor drone in the jth candidate address and the ith target inspection equipment, and if Z ij = 1, it means that there is correspondence between the multi-rotor drone in the jth candidate address and the ith target inspection equipment, β is the punishment cost of manual inspection per unit distance when the multi-rotor drone nest fails, is the punishment distance when the ith target inspection equipment is not covered by the multi-rotor drone nest.

[0082] It can be understood that the second objective function is to minimize the total cost, including the construction cost of the two nests, the total cost of the fixed-wing drone inspection, and the total cost of the multi-rotor drone inspection, wherein the total cost of the multi-rotor drone inspection includes the total cost of the normal inspection of the multi-rotor drone and the total cost of the manual supplementary inspection of the multi-rotor drone in the case of nest failure.

[0083] Further, the second constraint condition is specifically represented as:

[0084]

[0085] wherein J * is the set of candidate addresses for building nests, I is the set of all target inspection equipment in the inspection area, d ij is the flight distance between the ith target inspection equipment and the jth candidate address, Y ijis a Boolean variable, and Y ij is a Boolean variable, and Z ij is a Boolean variable, and Y ij is a Boolean variable, and Z j is a Boolean variable, and Y j is a Boolean variable, and Z j is a Boolean variable, and Z j is a Boolean variable, R is the maximum service radius of the candidate address, N1 is the maximum number of fixed-wing UAV candidate addresses, and N0 is the maximum number of multi-rotor UAV candidate addresses.

[0086] It can be understood that the second constraint condition limits the number of fixed-wing UAV nests, the number of multi-rotor UAV nests, the correspondence between the target inspection equipment and the candidate address, and the service radius of the candidate address.

[0087] S104: Based on the second objective function and the second constraint condition, an optimization is performed in the candidate address set by using a meta-heuristic optimization algorithm to obtain a target nest position set corresponding to each type of UAV.

[0088] Specifically, with reference to Figure 2 , a model operator is used to change the UAV type of the candidate address in the candidate address set, and optimization iteration is performed. If the number of iterations reaches a preset first iteration threshold, a first optimization set is obtained. Based on the first optimization set, a relationship operator and a hybrid operator are combined to change the UAV type of the candidate address and / or adjust the correspondence between the candidate address and the target inspection equipment, and optimization iteration is performed to obtain a second optimization set. The relationship operator is used to adjust the correspondence between the candidate address and the target inspection equipment, and the hybrid operator includes the model operator and the relationship operator. Based on the relationship operator, the correspondence between the candidate address and the target inspection equipment in the second optimization set is adjusted, and optimization iteration is performed to obtain the target nest position set.

[0089] Further, a comparison result is obtained by comparing the random number with a preset optimization threshold. An operator corresponding to the comparison result is determined, and the first optimization set is optimized based on the operator corresponding to the comparison result. If the number of iterations reaches a preset second iteration threshold, a second optimization set is obtained.

[0090] Further, the second optimization set is iterated for the mth time, the correspondence between the candidate address and the target inspection equipment is adjusted, and an iteration result set Q m is obtained, where m is a positive integer and m is greater than 1. According to Q mThe corresponding second objective function value and Q m-1 The difference between the corresponding second objective function values ​​is used to determine the current optimal result set and update the iteration parameter T corresponding to the iteration result set. m,sa When T m,sa If the temperature exceeds the preset threshold or m exceeds the preset maximum iteration threshold, the current optimal result set will be used as the target nest location set.

[0091] T m,sa Let T be the iteration parameter for the m-th iteration. The initial value of the above iteration parameter is set according to the actual situation. At the same time, the iteration coefficient γ of the iteration parameter is set. After each iteration, the iteration parameter T is updated according to the iteration coefficient. m,sa =T m-1,sa ×γ。 Q m The corresponding second objective function value is obtained through the iterative result set Q. m The second objective function is obtained by solving it.

[0092] In one specific implementation, this invention proposes an Iterated Local Search (ILS)-Simulated Annealing (SA) algorithm. This algorithm sets up a set of neighborhoods, each representing a new set of solutions obtained by performing a specific operation on the current solution. By iteratively selecting neighborhoods and combining them with the acceptance criteria of simulated annealing, the quality of the solutions is continuously improved.

[0093] The aforementioned domain includes aircraft type operators, relational operators, and hybrid operators. The aircraft type operator is used to change the drone type corresponding to a candidate address. The specific process is as follows: a candidate address is randomly selected from the candidate address set. If the drone type of the current candidate address is a fixed-wing drone, it is replaced with a multi-rotor drone; conversely, if the drone type of the current candidate address is a multi-rotor drone, it is replaced with a fixed-wing drone. (See reference...) Figure 3 In this context, squares represent one type of drone at a candidate address, and triangles represent another type of drone at a candidate address. Changing a square to a triangle changes the drone type. A relational operator is used to change the correspondence between candidate addresses and target inspection devices. Specifically, the process is as follows: Select target inspection devices from the inspection area that fall within the coverage area of ​​two or more candidate addresses, denoted as set I', where the number of elements in the set is represented by |I'|. Randomly generate a natural number Num ∈ [1, |I'|], and randomly select Num target inspection devices from I'. These target devices are then randomly reassigned to candidate addresses that meet the coverage requirements. (Refer to...) Figure 4The target inspection device in the intersection of any two dashed circles is added to the set I', and the target inspection device connected with the triangle is adjusted to the target inspection device connected with the square, so as to change the correspondence between the candidate address and the target inspection device. The hybrid operator is a combination of the machine type operator and the relationship operator, and the hybrid operator contains the operation of the machine type operator and the operation of the relationship operator.

[0094] In a specific example, since the construction cost of the nest accounts for a large proportion of the total cost, the machine type operator is applied in the early iteration, that is, when the iteration number is less than 10% of the maximum iteration number (i.e., the first iteration threshold), the machine type operator is used to generate a new solution to obtain a first optimized set. The relationship operator and the hybrid operator are applied in the middle iteration, that is, when the iteration number is less than 50% of the maximum iteration number (i.e., the second iteration threshold), by comparing the random number generated by the random function with the preset optimization threshold, the relationship operator and the hybrid operator are randomly used to expand the search space and improve the quality of the solution. The relationship operator is applied in the late iteration, that is, when the iteration number is less than the maximum iteration number, the relationship operator is used continuously to optimize the matching relationship between the candidate address and the target inspection device. In other embodiments, the use stage and the use proportion of the machine type operator, the relationship operator and the hybrid operator are adjusted according to actual needs, and the adjustment is not limited.

[0095] Since the ILS algorithm can only accept a better solution than the current optimal solution, it is easy to fall into a local minimum value at this time, so the acceptance criterion of simulated annealing is used. The specific process includes: when the iteration solution s t is better than the current optimal solution s * , s * is updated to s t , otherwise, the acceptance criterion accepts the worse iteration solution s t with a certain probability, and s * is updated to s t . For example, when the current optimal solution s * is better than the iteration solution s t , the probability that the iteration solution s t is the optimal solution is compared by using a random function, and whether to receive the worse iteration solution s t is selected according to the comparison result, where ΔQ is the difference between the corresponding second objective function value Q m and the corresponding second objective function value Q m-1 . If the random number obtained by the random function is less than the probability that the iteration solution s t is the optimal solution, the worse iteration solution s t is received, that is, s * is updated to s t .

[0096] In one specific example, referring to Figure 5 , a transmission tower area of about 400 square kilometers is selected as the inspection area for algorithm verification and scenario comparison.

[0097] The present application considers establishing several unmanned aerial vehicle nests in the above-mentioned inspection area to serve 2062 power equipment that need to be inspected, i.e., target inspection equipment. Each unmanned aerial vehicle nest can serve all the to-be-inspected towers within a radius of 3 km. The goal is to select the minimum number of towers to establish unmanned aerial vehicle nests at their locations so that all to-be-inspected towers can be covered by at least one unmanned aerial vehicle nest, thereby achieving the lowest construction cost. Referring to Figure 6 , through the solution of the Gurobi optimizer, 17 optimal nest site points, i.e., a candidate address set, are obtained. Among them, the towers to be inspected, i.e., the target inspection equipment, are represented by points, and the nest site points, i.e., the candidate addresses, are represented by crosses, and there are a total of 17 candidate addresses.

[0098] Referring to Figure 7 , a set of optimal unmanned aerial vehicle nest deployment and task allocation schemes are obtained by the present application. Figure 7 The types of unmanned aerial vehicles of each unmanned aerial vehicle nest and its service area are shown. Different numbers of points and lines represent different nests and their covered target inspection equipment, in which the fixed-wing unmanned aerial vehicle nests and their corresponding task points are identified by squares, and the multi-rotor unmanned aerial vehicle nests are identified by triangles, Figure 7 contains 13 fixed-wing unmanned aerial vehicle nests and 4 multi-rotor unmanned aerial vehicle nests, and the cost of this scheme is 1,684,373 yuan. Through analysis Figure 7 , it can be found that the position distribution of the unmanned aerial vehicle nests is relatively uniform, and the task allocation scheme effectively covers all the task points.

[0099] The performance comparison of the present application scheme and the greedy algorithm in solving the unmanned aerial vehicle nest site selection and task allocation problem is shown in Table 1, and the main indicators for comparison include the total cost, the number of nests used, and the proportion of fixed-wing nests.

[0100] Table 1 Comparison results of ILS-SA and greedy algorithm

[0101]

[0102] Referring to Figure 8 , the embodiment of the present application provides a multi-type unmanned aerial vehicle nest site selection device based on inspection task allocation, which comprises:

[0103] The first condition construction module 201 is used to give a first target function corresponding to the number of unmanned aerial vehicle nests and a first constraint condition corresponding to the position of the unmanned aerial vehicle nest based on the inspection task.

[0104] The candidate address determination module 202 is configured to obtain a candidate address set based on the first target function and the first constraint condition;

[0105] The second condition construction module 203 is configured to construct a second target function and a second constraint condition based on the unmanned aerial vehicle type decision and the inspection task according to the inspection cost, the inspection range and the inspection area of each type of unmanned aerial vehicle.

[0106] The target position determination module 204 is configured to perform optimization in the candidate address set based on the second target function and the second constraint condition by using a meta-heuristic optimization algorithm to obtain a target nest position set corresponding to each type of unmanned aerial vehicle.

[0107] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the described modules can refer to the corresponding process in the foregoing method embodiments, which will not be described herein.

[0108] Although the preferred embodiments of the present application have been described, those skilled in the art can make further changes and modifications to these embodiments once they know the basic inventive concept. Therefore, the appended claims are intended to be interpreted as including all the preferred embodiments and all the changes and modifications falling within the scope of the present application. Obviously, those skilled in the art can make various modifications and changes to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and changes of the present application fall within the scope of the claims of the present application and their equivalent technologies, the present application also intends to include these modifications and changes.

Claims

1. A method for selecting nest locations for multiple types of unmanned aerial vehicles (UAVs) based on inspection task allocation, characterized in that, include: Based on the inspection task, the first objective function corresponding to the number of UAV nests and the first constraint condition corresponding to the location of the UAV nests are given respectively. The first objective function is specifically expressed as follows: ； The first constraint condition is specifically expressed as follows: ； in, In the first The result of establishing a nest at a pending address, and For Boolean variables, The set of undetermined addresses in the inspection area. For the first The pending address and the first The relationship between the distance to the target inspection equipment and the inspection range of the drone, and For Boolean variables, The collection of all target inspection equipment within the inspection area; Based on the first objective function and the first constraint condition, a set of candidate addresses is obtained; The construction cost, flight cost, and penalty cost of various types of UAVs are obtained. Combined with the correspondence between each type of UAV and the target inspection equipment and the flight distance, the probability of UAV nest failure for each type is analyzed, and a second objective function is constructed. The types of UAVs include fixed-wing UAVs and multi-rotor UAVs. The second objective function is specifically expressed as follows: ； Obtain the inspection range of each type of drone and the flight distance between each type of drone and the target inspection equipment. Analyze the correspondence between each type of drone and the target inspection equipment. Combined with the number of each type of drone, construct the second constraint, specifically expressed as follows: ； in, The set of candidate addresses for building the nest, The construction cost of fixed-wing UAV nests, For the first The results of constructing fixed-wing UAV nests at candidate sites, and For Boolean variables, The construction cost of multi-rotor drone nests, For the first The results of constructing multi-rotor UAV nests at candidate locations, and For Boolean variables, This refers to the total uptime of the inspection system, which includes all types of drones. For the first Frequency of inspection service requirements for each target inspection equipment. The cost per unit distance for drone flights, For the first The target inspection equipment and the first Flight distance of each candidate address For the first Fixed-wing UAVs among the candidate addresses and the first The correspondence between the target inspection equipment and the corresponding relationship, and For Boolean variables, The probability of nest failure for multi-rotor drones. For the first Multirotor drones and the candidate addresses in the first candidate address The correspondence between the target inspection equipment and the corresponding relationship, and For Boolean variables, The penalty cost per unit distance for manual inspection when a multi-rotor drone nest fails. For the first Penalty distance when the target inspection equipment is not covered by the nest of a multi-rotor drone. The maximum service radius of the candidate address. This represents the maximum number of candidate addresses for fixed-wing UAVs. This represents the maximum number of candidate addresses for a multi-rotor drone. Based on the second objective function and the second constraint, a metaheuristic optimization algorithm is used to optimize the candidate address set to obtain the target nest location set for each type of UAV.

2. The multi-type UAV nesting method based on inspection task allocation as described in claim 1, characterized in that, Based on the first objective function and the first constraint, the candidate address set is obtained, including: Based on the first objective function and the first constraint condition, the set of addresses to be determined is obtained; Based on the set of undetermined addresses, a correspondence is established between each target inspection device in the inspection area and the nearest undetermined address to obtain a set of candidate addresses.

3. The multi-type UAV nesting method based on inspection task allocation as described in claim 1, characterized in that, Based on the second objective function and the second constraint, a metaheuristic optimization algorithm is used to optimize the candidate address set to obtain the target nest location set for each type of UAV, specifically including: Based on the drone type operator that changes the drone type of the candidate address, the drone type of the candidate address in the candidate address set is changed, and optimization iteration is performed to obtain the first optimized set; Based on the first optimization set, by combining relation operators and hybrid operators, the drone type of the candidate address is changed and / or the correspondence between the candidate address and the target inspection equipment is adjusted, and optimization iteration is performed to obtain the second optimization set. The relation operators are used to adjust the correspondence between the candidate address and the target inspection equipment, and the hybrid operators include the drone type operator and the relation operator. Based on the relation operator, the correspondence between candidate addresses and target inspection equipment in the second optimization set is adjusted, and optimization iteration is performed to obtain the target nest location set.

4. The multi-type UAV nesting method based on inspection task allocation as described in claim 3, characterized in that, Based on the first optimization set, and combining relational operators and hybrid operators, the drone type of the candidate addresses is changed and / or the correspondence between candidate addresses and target inspection equipment is adjusted. This process is repeated to obtain the second optimization set, which specifically includes: The random number is compared with the preset optimization threshold to obtain the comparison result; Determine the operator corresponding to the comparison result, and optimize the first optimization set based on the operator corresponding to the comparison result; If the number of iterations reaches the preset second iteration threshold, the second optimized set is obtained.

5. The multi-type UAV nesting method based on inspection task allocation as described in claim 3, characterized in that, Based on relation operators, the correspondence between candidate addresses and target inspection equipment in the second optimization set is adjusted, and optimization iterations are performed to obtain the target nest location set, which specifically includes: The second optimization set is iterated for the mth time, and the correspondence between candidate addresses and target inspection equipment is adjusted to obtain the iterative result set. , where m is a positive integer and m is greater than 1; according to The corresponding second objective function value and The difference between the corresponding second objective function values ​​is used to determine the current optimal result set and update the iteration parameters corresponding to the iteration result set. ; when If the temperature exceeds the preset threshold or m exceeds the preset maximum iteration threshold, the current optimal result set will be used as the target nest location set.

6. A multi-type UAV nesting site selection device based on inspection task allocation, characterized in that, The method for selecting the location of multiple types of UAV nests based on inspection task allocation as described in any one of claims 1-5 includes: The first condition construction module is used to provide a first objective function for the number of drone nests and a first constraint condition for the location of drone nests based on the inspection task. The first objective function is specifically expressed as follows: ； The first constraint condition is specifically expressed as follows: ； in, In the first The result of establishing a nest at a pending address, and For Boolean variables, The set of undetermined addresses in the inspection area. For the first The pending address and the first The relationship between the distance to the target inspection equipment and the inspection range of the drone, and For Boolean variables, The collection of all target inspection equipment within the inspection area; The candidate address determination module is used to obtain a set of candidate addresses based on the first objective function and the first constraint conditions; The second condition construction module is used to obtain the construction cost, flight cost, and penalty cost of each type of UAV. Combining the correspondence between each type of UAV and the target inspection equipment and the flight distance, it analyzes the probability of UAV nest failure for each type and constructs a second objective function. The types of UAVs include fixed-wing UAVs and multi-rotor UAVs. The second objective function is specifically expressed as follows: ； Obtain the inspection range of each type of drone and the flight distance between each type of drone and the target inspection equipment. Analyze the correspondence between each type of drone and the target inspection equipment. Combined with the number of each type of drone, construct the second constraint, specifically expressed as follows: ； in, The set of candidate addresses for building the nest, The construction cost of fixed-wing UAV nests, For the first The results of constructing fixed-wing UAV nests at candidate sites, and For Boolean variables, The construction cost of multi-rotor drone nests, For the first The results of constructing multi-rotor UAV nests at candidate locations, and For Boolean variables, This refers to the total uptime of the inspection system, which includes all types of drones. For the first Frequency of inspection service requirements for each target inspection equipment. The cost per unit distance for drone flights, For the first The target inspection equipment and the first Flight distance of each candidate address For the first Fixed-wing UAVs among the candidate addresses and the first The correspondence between the target inspection equipment and the corresponding relationship, and For Boolean variables, The probability of nest failure for multi-rotor drones. For the first Multirotor drones and the candidate addresses in the first candidate address The correspondence between the target inspection equipment and the corresponding relationship, and For Boolean variables, The penalty cost per unit distance for manual inspection when a multi-rotor drone nest fails. For the first Penalty distance when the target inspection equipment is not covered by the nest of a multi-rotor drone. The maximum service radius of the candidate address. This represents the maximum number of candidate addresses for fixed-wing UAVs. This represents the maximum number of candidate addresses for a multi-rotor drone. The target location determination module is used to optimize the candidate address set based on the second objective function and the second constraint condition, and obtain the target nest location set corresponding to each type of UAV through a metaheuristic optimization algorithm.

Images