Vertical take-off and landing field site selection method based on fuzzy multi-objective optimization model

Abstract

The invention discloses a vertical take-off and landing field site selection method based on a fuzzy multi-objective optimization model, and relates to the technical field of low-altitude traffic, and the method comprises the steps: constructing a fuzzy number of a travel demand, and converting the fuzzy number into a deterministic interval; constructing a multi-target site selection model according to the deterministic interval; constructing a solving algorithm of the multi-target site selection model; searching a Pareto optimal solution set of the multi-target site selection model by using a solution algorithm; and determining the site selection of the vertical take-off and landing field according to the Pareto optimal solution set. According to the method, fuzzy parameters and operation uncertainty are considered, so that the multi-target site selection model still has relatively high stability in different scenes, and the scientificity, the practical feasibility and the long-term robustness of a vertical take-off and landing field site selection scheme can be improved by solving the multi-target site selection model.

Description

Technical Field

[0001] This application relates to the field of low-altitude transportation technology, and in particular to a method for selecting vertical take-off and landing sites based on a fuzzy multi-objective optimization model. Background Technology

[0002] With the gradual advancement of electric vertical takeoff and landing (VTOL) aircraft technology, low-altitude aeronautical charts, and urban low-altitude airspace policies, urban air transportation is considered a key component of the future integrated urban transportation system. As a critical infrastructure of the urban air transportation system, the layout of VTOL fields directly affects the system's service level, cost efficiency, and network robustness. However, the selection of VTOL field locations faces various problems and challenges in reality:

[0003] (1) Urban air traffic demand is volatile and uncertain: Due to various uncertainties in the actual urban environment, such as future demand forecasting errors, uncertainties in facility operation reliability, and cost fluctuations, traditional deterministic models cannot effectively capture these uncertainties, limiting the stability and practical applicability of site selection schemes. (2) The site selection of vertical take-off and landing (VTOL) fields needs to consider multiple objectives: the government values ​​the fairness of public services, enterprises focus on the cost of construction and operation, and users are concerned about operational efficiency. (3) The site layout of VTOL fields needs to be compatible with the existing urban space: land scarcity, high building density, and airport noise control limit the freedom of VTOL field layout. Therefore, traditional single-objective, deterministic optimization models alone are insufficient to meet the actual needs of VTOL field site selection. Summary of the Invention

[0004] In view of this, the embodiments of this application provide a vertical take-off and landing field site selection method based on a fuzzy multi-objective optimization model, so as to provide a comprehensive optimization scheme that can simultaneously handle multi-objective trade-offs and fuzzy uncertainties, thereby improving the scientificity, practical feasibility and long-term robustness of the site selection scheme.

[0005] One aspect of this application provides a method for selecting vertical takeoff and landing sites based on a fuzzy multi-objective optimization model, the method comprising the following steps:

[0006] Construct fuzzy numbers of travel demand and convert the fuzzy numbers into deterministic intervals;

[0007] Construct a multi-objective location selection model based on the deterministic interval;

[0008] Construct a solution algorithm for the multi-objective location selection model;

[0009] The solution algorithm described above is used to search for the Pareto optimal solution set of the multi-objective location model;

[0010] The location of the vertical take-off and landing field is determined based on the Pareto optimal solution set.

[0011] In some embodiments, constructing a fuzzy number of travel demand includes the following steps:

[0012] The fuzzy number used to construct the travel demand is as follows:

[0013]

[0014] in, This represents the fuzzy number. These represent the minimum travel demand, the most likely travel demand, and the maximum travel demand under conservative estimates, respectively.

[0015] The process of converting the fuzzy number into a deterministic interval includes the following steps:

[0016] The fuzzy number is converted into the deterministic interval as follows:

[0017]

[0018] in, Let α represent the deterministic interval, and let α represent the satisfaction level.

[0019] In some embodiments, constructing a multi-objective location model based on the deterministic interval includes the following steps:

[0020] The multi-objective location selection model is constructed based on the deterministic interval; the multi-objective location selection model includes minimizing total cost, minimizing travel time, and maximizing spatial fairness;

[0021] The objective function for minimizing the total cost is:

[0022]

[0023] Among them, y j Indicates whether a vertical takeoff and landing field j is constructed, variable w ij q represents the number of trips i that are satisfied through vertical takeoff and landing field j. i This indicates that urban air mobility has failed to meet travel demand; Fix j The fixed construction cost of the vertical takeoff and landing field j, c w The unit cost of operating urban air mobility services. The cost of unit fines for unmet travel demand;

[0024] The objective function for minimizing travel time is:

[0025]

[0026] Among them, t ijThe travel time required for travel demand i to be met through the vertical take-off and landing field j;

[0027] The objective function for maximizing spatial fairness is:

[0028]

[0029]

[0030] Among them, W i W represents the fairness ratio indicator. i It is defined as the proportion of demand met by urban air transport to the proportion of total demand at each demand point.

[0031] In some embodiments, the algorithm for constructing the multi-objective location selection model includes the following steps:

[0032] The NSGA-III algorithm is constructed as the solution algorithm for the multi-objective location model.

[0033] In some embodiments, the step of searching for the Pareto optimal solution set of the multi-objective location model using the solution algorithm includes the following steps:

[0034] Determine the satisfaction level; set the population size, maximum number of generations, crossover probability, and mutation probability in the NSGA-III algorithm; generate reference points uniformly distributed on the normalized hyperplane;

[0035] The population is initialized according to the population size; wherein each individual in the population represents the function value of each optimization objective in the multi-objective location selection model;

[0036] Calculate the function values ​​of each optimization objective in the multi-objective location selection model for all individuals in the current parent and offspring populations at the current satisfaction level;

[0037] Merge the parent and offspring populations into a joint population; perform a non-dominated sort on all individuals in the joint population;

[0038] Construct a new population based on the joint population after the non-dominated sorting;

[0039] Based on the reference point, individuals are selected from the new population to generate a new offspring population;

[0040] The new offspring population is selected, crossovered, and mutated. The steps of calculating the function values ​​of each optimization objective in the multi-objective location model for all individuals in the current parent and offspring populations at the current satisfaction level are returned until the maximum number of generations is satisfied. The final population is then output as the Pareto optimal solution set.

[0041] Another aspect of this application embodiment provides a vertical takeoff and landing field location device based on a fuzzy multi-objective optimization model, the device comprising:

[0042] A fuzzy modeling unit is used to construct fuzzy numbers of travel demand and convert the fuzzy numbers into deterministic intervals;

[0043] A multi-objective location selection model construction unit is used to construct a multi-objective location selection model based on the deterministic interval;

[0044] An algorithm construction unit is used to construct the solution algorithm for the multi-objective location selection model;

[0045] The model solving unit is used to search for the Pareto optimal solution set of the multi-objective location model using the solving algorithm;

[0046] The location selection unit is used to determine the location of the vertical take-off and landing field based on the Pareto optimal solution set.

[0047] Another aspect of this application embodiment provides an electronic device, including a processor and a memory;

[0048] The memory is used to store programs;

[0049] The processor executes the program to implement any of the methods described above.

[0050] Another aspect of this application provides a computer-readable storage medium storing a program that is executed by a processor to implement the method described in any of the above embodiments.

[0051] This application includes at least the following beneficial effects:

[0052] This application constructs fuzzy numbers representing travel demand and converts them into deterministic intervals; it then constructs a multi-objective site selection model based on these intervals; it develops an algorithm for solving the multi-objective site selection model; it uses this algorithm to search for the Pareto optimal solution set of the multi-objective site selection model; and finally, it determines the site selection for vertical take-off and landing (VTOL) fields based on the Pareto optimal solution set. This application considers fuzzy parameters and operational uncertainties, ensuring the multi-objective site selection model maintains strong stability under different scenarios. Solving this multi-objective site selection model improves the scientific rigor, practical feasibility, and long-term robustness of VTOL field site selection schemes. Attached Figure Description

[0053] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0054] Figure 1 A flowchart illustrating a vertical take-off and landing field location method based on a fuzzy multi-objective optimization model provided in this application embodiment;

[0055] Figure 2 This is a structural block diagram of a vertical take-off and landing field location device based on a fuzzy multi-objective optimization model, provided in an embodiment of this application. Detailed Implementation

[0056] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0057] Before providing a detailed description of the embodiments of this application, some related technologies involved in the embodiments of this application will be described first, as follows:

[0058] Most methods for initially determining the location of vertical takeoff and landing (VTOL) sites employ clustering and improved algorithms, treating urban air traffic demand as point data. However, given that these methods only consider distance or data similarity, they are most often used to identify candidate facility locations, rather than the final facility location.

[0059] Some other related approaches treat the VTOL site selection problem as a facility location problem, and urban air traffic demand as origin-destination demand. This is a classic operations research problem, aiming to optimize facility locations to meet demand while considering cost constraints. However, they mainly employ classic models from facility location problems, such as the maximum coverage model, the p-median model, or the cost minimization model. These methods generally assume that system parameters are fixed and the objective is singular, such as minimizing total cost or maximizing demand coverage.

[0060] Reference Figure 1 This application provides a method for selecting a vertical takeoff and landing field based on a fuzzy multi-objective optimization model, specifically including the following steps S100 to S140:

[0061] S100: Construct a fuzzy number of travel demand and convert the fuzzy number into a deterministic interval;

[0062] S110: Construct a multi-objective location selection model based on the deterministic interval;

[0063] S120: Construct the solution algorithm for the multi-objective location selection model;

[0064] S130: Use the solution algorithm to search for the Pareto optimal solution set of the multi-objective location model;

[0065] S140: Determine the location of the vertical take-off and landing field based on the Pareto optimal solution set.

[0066] Optionally, constructing the fuzzy number of travel demand includes the following steps:

[0067] The fuzzy number used to construct the travel demand is as follows:

[0068]

[0069] in, This represents the fuzzy number. These represent the minimum travel demand, the most likely travel demand, and the maximum travel demand under conservative estimates, respectively.

[0070] The process of converting the fuzzy number into a deterministic interval includes the following steps:

[0071] The fuzzy number is converted into the deterministic interval as follows:

[0072]

[0073] in, Let α represent the deterministic interval, and let α represent the satisfaction level.

[0074] Optionally, constructing a multi-objective location selection model based on the deterministic interval includes the following steps:

[0075] The multi-objective location selection model is constructed based on the deterministic interval; the multi-objective location selection model includes minimizing total cost, minimizing travel time, and maximizing spatial fairness;

[0076] The objective function for minimizing the total cost is:

[0077]

[0078] Among them, y j Indicates whether a vertical takeoff and landing field j is constructed, variable w ij q represents the number of trips i that are satisfied through vertical takeoff and landing field j. i This indicates that urban air mobility has failed to meet travel demand; Fix j The fixed construction cost of the vertical takeoff and landing field j, c w The unit cost of operating urban air mobility services. The cost of unit fines for unmet travel demand;

[0079] The objective function for minimizing travel time is:

[0080]

[0081] Among them, t ij The travel time required for travel demand i to be met through the vertical take-off and landing field j;

[0082] The objective function for maximizing spatial fairness is:

[0083]

[0084] Among them, W i W represents the fairness ratio indicator. i It is defined as the proportion of demand met by urban air transport to the proportion of total demand at each demand point.

[0085] Optionally, the algorithm for constructing the multi-objective location selection model includes the following steps:

[0086] The NSGA-III algorithm is constructed as the solution algorithm for the multi-objective location model.

[0087] Optionally, the step of using the solution algorithm to search for the Pareto optimal solution set of the multi-objective location model includes the following steps:

[0088] Determine the satisfaction level; set the population size, maximum number of generations, crossover probability, and mutation probability in the NSGA-III algorithm; generate reference points uniformly distributed on the normalized hyperplane;

[0089] The population is initialized according to the population size; wherein each individual in the population represents the function value of each optimization objective in the multi-objective location selection model;

[0090] Calculate the function values ​​of each optimization objective in the multi-objective location selection model for all individuals in the current parent and offspring populations at the current satisfaction level;

[0091] Merge the parent and offspring populations into a joint population; perform a non-dominated sort on all individuals in the joint population;

[0092] Construct a new population based on the joint population after the non-dominated sorting;

[0093] Based on the reference point, individuals are selected from the new population to generate a new offspring population;

[0094] The new offspring population is selected, crossovered, and mutated. The steps of calculating the function values ​​of each optimization objective in the multi-objective location model for all individuals in the current parent and offspring populations at the current satisfaction level are returned until the maximum number of generations is satisfied. The final population is then output as the Pareto optimal solution set.

[0095] The following section will provide a detailed introduction and explanation of the solutions in the embodiments of this application, using specific application examples.

[0096] 1. Fuzzy number processing and equivalent model construction.

[0097] In the early planning stages of urban air mobility systems, many input parameters (such as demand, cost, facility reliability, and user response behavior) often cannot be accurately obtained from historical data and can only rely on expert experience or rough estimates. These data are inherently "uncertain but bounded," making them difficult to model using traditional probabilistic models. Therefore, fuzzy mathematics becomes an effective means of modeling uncertainty.

[0098] Fuzzy numbers are a class of mathematical objects widely used to express uncertain information, with triangular fuzzy numbers and trapezoidal fuzzy numbers being the most commonly used. This embodiment models key parameters in urban vertical take-off and landing field site selection as fuzzy numbers. For each demand point i, its potential urban air traffic travel demand is represented by a triangular fuzzy number:

[0099]

[0100] in, These represent the minimum demand (pessimistic value), the most likely demand value, and the maximum expected demand (optimistic value) under conservative estimates, respectively. This fuzzy expression can fully consider the uncertain impact of factors such as user acceptance and urban growth rate.

[0101] In fuzzy optimization, this embodiment typically uses fuzzy satisfaction theory to transform fuzzy objectives or constraints into deterministic problems. The basic idea is to introduce a satisfaction level α ∈ [0,1] and require the objective value to reach a certain degree of "possible satisfaction." Ultimately, given the satisfaction level α, the travel demand for urban air transportation is transformed into a deterministic interval:

[0102]

[0103] This transformation not only preserves the fuzzy robustness of the original problem but also ensures the solvability of the model. Compared to traditional interval optimization models, this approach offers greater finesse and flexibility, effectively supporting site selection decisions by policymakers under varying risk preferences, and is widely applicable to urban infrastructure planning scenarios with fuzzy and conflicting objectives.

[0104] 2. Construction of a multi-objective optimization model.

[0105] To comprehensively consider system economy and service performance, the location selection model constructed in this embodiment simultaneously optimizes the following three objective functions.

[0106] Objective 1 is to minimize total cost, which includes facility construction costs and operating costs:

[0107]

[0108] Among them, y j Indicates whether a vertical takeoff and landing field (J) is to be constructed, w ij q represents the number of trips i that are satisfied through vertical takeoff and landing field j. i This indicates that urban air transport has failed to meet travel demand. j The fixed construction cost of the vertical takeoff and landing field j, c w The unit cost of operating urban air mobility services. The cost of unit fines for unmet travel demand.

[0109] Objective 2 is to minimize travel time:

[0110]

[0111] Among them, t ij The travel time required for travel demand i to be met through a vertical take-off and landing field j.

[0112] The concept of equity has received considerable attention in urban planning. Spatial equity plays a crucial role in achieving long-term sustainable profits. This embodiment uses the equity ratio indicator W. i Defined as the proportion of demand met by urban air transport relative to the proportion of total demand at each demand point. This refers to the vague requirement described above.

[0113]

[0114] Therefore, objective 3 of this embodiment is to maximize spatial fairness, as follows:

[0115]

[0116] 3. Design of the solution algorithm.

[0117] In multi-objective optimization theory, since there are often conflicts between multiple objectives, it is impossible to find a single optimal solution. Therefore, a Pareto optimal solution set must be used as the output. For the multi-objective location selection model (f1, f2, f3) after the fuzzy satisfaction transformation established above, this embodiment adopts the NSGA-III (Non-dominated Sorting Genetic Algorithm III) algorithm, which is an evolutionary algorithm for solving high-dimensional multi-objective optimization problems.

[0118] 3.1 Parameter settings.

[0119] (1) Determine the satisfaction level α value (fixed or as an external input).

[0120] (2) Set the NSGA-III parameters: population size N, maximum number of generations G max Crossover probability p c mutation probability p m .

[0121] (3) Generate a set of reference points: In the three-dimensional target space (f1, f2, f3), generate a set of reference points {z} uniformly distributed on the normalized hyperplane. 1 ,z 2 ,…,z H The number of reference points H is usually slightly larger than the population size N.

[0122] 3.2 Initialize the population P0.

[0123] (1) Randomly generate an initial population of size N. Each individual is a binary vector x = (x1, x2, ..., xn). J ), representing a site selection option ("0 / 1" indicates whether to build a vertical take-off and landing field).

[0124] (2) Ensure that individuals in the initial population meet all constraints of the site selection model (such as the number of vertical take-off and landing sites and construction budget constraints). If not, they need to be repaired or regenerated.

[0125] 3.3 Fitness assessment.

[0126] For the current parent population P g and offspring population Q g (Q is generated from P0 in the first iteration) o For all individuals x in α, calculate their three objective function values ​​(f1, f2, f3) at the current α level.

[0127] 3.4 Non-dominated sorting.

[0128] (1) Parent generation P g and offspring Q g Merge into a joint population R of size 2N g =P g ∪Q g .

[0129] (2) For R g Perform a non-dominated sort of all individuals: First Front F1: Find R g The first front is the group of individuals not dominated by any other individual (i.e., Pareto optimal solutions). The second front, F2, is the group of individuals remaining after removing F1 that are not dominated by any other individual. This process continues until all individuals are assigned to a front F. k .

[0130] 3.5 Constructing a new population P g+1 .

[0131] (1) Individuals are added to the new population P in order of increasing frontier hierarchy (F1, F2, F3, ...). g+1 .

[0132] (2) When it is necessary to make a certain frontier F k When joining, if P is joined... g+1 If the size of the value is equal to N, then stop.

[0133] (3) If F is added k Afterwards, P g+1 If the size exceeds N, then it needs to be from F. k Select a subset of individuals to join.

[0134] 3.6. Selection based on reference point (when P) g+1 (If necessary to supplement).

[0135] (1) Normalized objective value: for R g All individuals in the target space are normalized (finding the minimum ideal point and the maximum extreme point of each target) and mapped to the interval [0,1].

[0136] (2) Correlated reference point: for the frontier F k For each individual in the dataset, calculate its normalized target vector to each reference point z. h The perpendicular distance of the direction line (vector). Associating this individual with the nearest reference point.

[0137] (3) Calculate niche counts: Count the frontier F associated with each reference point. k Number of individuals in a microhabitat (ρ) h ).

[0138] (4) Select individuals: Under the condition that P is satisfied g+1 Given the capacity requirement, the priority should be given to: the number of habitats associated with ρ. h Individuals with reference points equal to 0 (i.e., those in uncovered reference point directions) are selected. If there are still vacancies or the number of associated individuals exceeds the demand, then among the individuals associated with the same reference point, individuals associated with reference points having lower niche counts are selected, or individuals closer to their associated reference points (with better convergence) are selected. This ensures the population's wide distribution (covering all reference point directions) and uniformity in the target space.

[0139] 3.7 Generate offspring population Q g+1 .

[0140] (1) From P g+1 Choose an individual as the parent.

[0141] (2) Selection: Binary tournament selection is usually used (based on non-dominance level and crowding / reference point distance).

[0142] (3) Crossover: Perform a crossover operation on the selected parent individuals to generate offspring. Commonly used binary crossover methods include single-point crossover, multi-point crossover, and uniform crossover, which are especially suitable for binary encoding.

[0143] (4) Mutation: Perform mutation operations on offspring individuals (maintain probability p) m Lower). Common bit-flip mutations (in p) m The probability of flipping x j (The value of ). Mutation is key to introducing new genes and avoiding getting trapped in local optima.

[0144] (5) Ensure that the generated offspring meet the constraints.

[0145] 3.8 Output Results.

[0146] (1) Final population It contains the best candidate solution found by the algorithm.

[0147] (2) Pareto front: These solutions are non-dominated (Pareto optimal) on all three objectives (cost f1, efficiency f2 and fairness f3), meaning that any improvement on any one objective will at least harm the other objective.

[0148] (3) Decision-makers can choose the most suitable site selection scheme from this Pareto frontier based on factors such as actual policy needs, budget constraints, risk preferences (α value).

[0149] The solution algorithm in this embodiment is particularly suitable for complex urban infrastructure layout optimization problems with multiple optimization objectives. It can effectively generate a balanced and interpretable Pareto solution set for decision-making reference.

[0150] The beneficial effects of this embodiment include:

[0151] This embodiment transforms the location problem with uncertain parameters into a deterministic multi-objective problem using fuzzy satisfaction theory. Then, it utilizes the NSGA-III algorithm to efficiently search for its Pareto optimal solution set, ultimately providing decision-makers with a set of location schemes that balance system cost, travel efficiency, and fairness while adapting to different risk tolerance levels. This approach offers the following advantages:

[0152] (1) Enhanced robustness: After considering fuzzy parameters and operational uncertainties, the model still has strong stability under different scenarios;

[0153] (2) Reduce risk exposure: The risk of cost surge under extreme scenarios is effectively reduced through the fuzzy satisfaction control mechanism;

[0154] (3) Support for multi-party policy formulation: Support different roles such as government, enterprises and users to set differentiated weights and target preferences;

[0155] (4) It has broad applicability: it can be extended to various city types, enhancing the feasibility of the project.

[0156] Reference Figure 2 This application provides a vertical takeoff and landing field location device based on a fuzzy multi-objective optimization model, comprising:

[0157] A fuzzy modeling unit is used to construct fuzzy numbers of travel demand and convert the fuzzy numbers into deterministic intervals;

[0158] A multi-objective location selection model construction unit is used to construct a multi-objective location selection model based on the deterministic interval;

[0159] An algorithm construction unit is used to construct the solution algorithm for the multi-objective location selection model;

[0160] The model solving unit is used to search for the Pareto optimal solution set of the multi-objective location model using the solving algorithm;

[0161] The location selection unit is used to determine the location of the vertical take-off and landing field based on the Pareto optimal solution set.

[0162] It is understood that the content of the above method embodiments is applicable to the present device embodiments. The specific functions implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0163] In some alternative embodiments, the functions / operations mentioned in the block diagrams may not occur in the order shown in the operation diagrams. For example, depending on the functions / operations involved, two consecutively shown blocks may actually be executed substantially simultaneously, or the blocks may sometimes be executed in reverse order. Furthermore, the embodiments presented and described in the flowcharts of this application are provided by way of example to provide a more comprehensive understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of various operations is changed and sub-operations described as part of a larger operation are executed independently.

[0164] Furthermore, although this application is described in the context of functional modules, it should be understood that, unless otherwise stated, one or more of the described functions and / or features may be integrated into a single physical device and / or software module, or one or more functions and / or features may be implemented in a separate physical device or software module. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding this application. Rather, given the properties, functions, and internal relationships of the various functional modules in the apparatus disclosed herein, the actual implementation of the module will be understood within the scope of conventional technology for an engineer. Therefore, those skilled in the art can implement the application set forth in the claims using ordinary techniques without excessive experimentation. It is also understood that the specific concepts disclosed are merely illustrative and not intended to limit the scope of this application, which is determined by the full scope of the appended claims and their equivalents.

[0165] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0166] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0167] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0168] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0169] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0170] Although embodiments of this application have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of this application, the scope of which is defined by the claims and their equivalents.

[0171] The above is a detailed description of the preferred embodiments of this application, but this application is not limited to the embodiments described. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of this application, and these equivalent modifications or substitutions are all included within the scope defined by the claims of this application.

Claims

1. A vertical take-off and landing site selection method based on a fuzzy multi-objective optimization model, characterized in that, The method comprises the following steps: a fuzzy number of travel demand is constructed, and the fuzzy number is converted into a deterministic interval; a multi-objective site selection model is constructed according to the deterministic interval; a solving algorithm of the multi-objective site selection model is constructed; a Pareto optimal solution set of the multi-objective site selection model is searched by using the solving algorithm; site selection of a vertical take-off and landing field is determined according to the Pareto optimal solution set.

2. The vertical take-off and landing site selection method based on a fuzzy multi-objective optimization model according to claim 1, characterized in that, The fuzzy number of travel demand is constructed by the following steps: The fuzzy number of the travel demand is constructed as follows: wherein, denotes the fuzzy number, respectively denote the minimum travel demand, the most likely travel demand, the maximum travel demand under conservative estimates; The fuzzy number is converted into the deterministic interval by the following steps: The fuzzy number is converted into the deterministic interval as follows: wherein, denotes the certainty interval, and a denotes the level of satisfaction.

3. The vertical take-off and landing site selection method based on a fuzzy multi-objective optimization model according to claim 1, characterized in that, The multi-objective site selection model is constructed according to the deterministic interval by the following steps: The multi-objective site selection model is constructed according to the deterministic interval; the multi-objective site selection model comprises a minimum total cost, a minimum travel time and a maximum spatial fairness; The target function of the minimum total cost is as follows: where y j represents whether the vertical take-off and landing field j is built, the variable w ij represents the number of travel demands i satisfied by the vertical take-off and landing field j, q i represents the travel demand that the urban air traffic fails to satisfy; Fix j is the fixed construction cost of the vertical take-off and landing field j, c w is the unit cost of the urban air traffic service operation, is the unit penalty cost of the unsatisfied travel demand i. The target function of the minimum travel time is as follows: where t ij is the travel time required for trip demand i to be satisfied by the VTOL field j; The target function of the maximum spatial fairness is as follows: where W i represents the fairness ratio indicator, W i is defined as the proportion of demand satisfied by urban air mobility and the proportion of total demand for each demand point.

4. The vertical take-off and landing site selection method based on a fuzzy multi-objective optimization model according to claim 1, characterized in that, The solving algorithm of the multi-objective site selection model is constructed by the following steps: The NSGA-III algorithm is constructed as the solving algorithm of the multi-objective site selection model.

5. The vertical take-off and landing site selection method based on a fuzzy multi-objective optimization model according to claim 4, characterized in that, The Pareto optimal solution set of the multi-objective site selection model is searched by using the solving algorithm by the following steps: A satisfaction level is determined; the population size, the maximum evolution generation number, the crossover probability and the mutation probability in the NSGA-III algorithm are set; reference points uniformly distributed on a normalized hyperplane are generated; A population is initialized according to the population size; each individual in the population represents a function value of each optimization target in the multi-objective site selection model; Function values of each optimization target in the multi-objective site selection model of all individuals in the current parent population and the child population are calculated under the current satisfaction level; The parent population and the child population are combined into a joint population; all individuals in the joint population are non-dominantly sorted; A new population is constructed according to the non-dominantly sorted joint population; Individuals in the new population are selected according to the reference points to generate a new child population; The new child population is selected, crossed and mutated; the step of calculating function values of each optimization target in the multi-objective site selection model of all individuals in the current parent population and the child population under the current satisfaction level is returned until the maximum evolution generation number is met; and a final population is output as the Pareto optimal solution set.

6. A vertical take-off and landing site selection device based on a fuzzy multi-objective optimization model, characterized by, The device comprises: a fuzzy modeling unit configured to construct a fuzzy number of travel demand and convert the fuzzy number into a deterministic interval; a multi-objective site selection model construction unit configured to construct a multi-objective site selection model according to the deterministic interval; an algorithm construction unit configured to construct a solving algorithm of the multi-objective site selection model; a model solving unit configured to search a Pareto optimal solution set of the multi-objective site selection model by using the solving algorithm; a site selection unit configured to determine site selection of a vertical take-off and landing field according to the Pareto optimal solution set.

7. An electronic device, comprising: The electronic device comprises a processor and a memory; the memory is configured to store a program; The processor executes the program to implement the method in any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The storage medium stores a program, and the program is executed by a processor to implement the method in any one of claims 1-5.

Images