Method, device and equipment for configuring aviation resource sites on offshore platforms

Abstract

The present application relates to a method, device and equipment for configuring aviation resource sites on an offshore platform. The method includes taking the resource type and quantity of the cabin-installed resource sites as decision variables, obtaining the upper-level constraints that the decision variables must satisfy based on the resource type of the resource site, the parking space set and the cabin set, and constructing a resource site configuration layer based on the upper-level constraints with the lowest cabin occupancy percentage as the upper-level goal; constructing a flight support planning layer based on the process flow constraints, process support resource constraints and transfer timing constraints with the shortest fleet support completion time as the lower-level goal; constructing a resource configuration-support planning model based on the resource site configuration layer and the flight support planning layer, solving the resource configuration-support planning model and obtaining the aviation resource site configuration result. The present method can reasonably plan the number and type of fixed resource sites configured in each cabin, meet the one-stop support requirements of each support parking space, and shorten the support cycle.

Description

Technical Field

[0001] The present application relates to the technical field of resource configuration, and in particular to a method, device and equipment for configuring aviation resource sites on an offshore platform. Background Art

[0002] One-stop support is the development trend of the design and use of aviation support systems for new offshore platforms. The key to designing a one-stop support parking space is to ensure that each parking space can provide all kinds of resources required for aircraft support. In response to this problem, some foreign offshore platforms have configured power modules and refueling support modules around the parking spaces, so that the aircraft can complete various support operations before dispatching in situ, and then taxi to the take-off position for lift-off operations. In order to achieve one-stop support for aircraft, the offshore platform has made many improvements, one of which is to optimize the layout of the offshore platform, so that there is more space for the layout of support modules.

[0003] Compared with foreign offshore platforms, the current domestic offshore platforms are smaller in area. In addition, the length of domestic aircraft is longer, and a larger support area is required to achieve normal aircraft mooring and dispatching. Therefore, if an independent support module is set up at each support position in accordance with foreign countries, it will inevitably occupy a large area around the parking position of the offshore platform, and the number of support positions will also decrease, which will reduce the efficiency of the use of the aviation support system of the offshore platform, affect the maximum number of waves / continuous dispatch of aircraft, and is not conducive to the performance of the offshore platform's operational capabilities. On the other hand, before the aircraft is dispatched, it is necessary to complete a series of pre-flight preparations on the offshore platform. The configuration of fixed aviation support resource sites has an important impact on operational efficiency and dispatch rate. However, the resource site configuration is determined at the design stage of the offshore platform and is almost never modified according to needs. Therefore, based on the existing offshore platform layout, to achieve one-stop aircraft support, it is necessary to reasonably plan the configuration of various fixed resource sites on the offshore platform to ensure that each parking position can provide various resources required in the aircraft dispatching support operation. Summary of the invention

[0004] Based on this, it is necessary to provide an aviation resource site configuration method, device, computer equipment and storage medium for an offshore platform in response to the above technical problems.

[0005] A method for configuring an aviation resource site of an offshore platform, the method comprising:

[0006] According to the preset aviation resource site configuration task, the resource type of the resource site, the parking space set corresponding to the parking space, and the cabin set corresponding to the cabin are obtained; the cabin can be installed with a resource site of any resource type;

[0007] The resource type and quantity of the cabin installation resource site are used as decision variables, and the upper-level constraints to be satisfied by the decision variables are obtained according to the resource type of the resource site, the parking space set and the cabin set. According to the upper-level constraints, the resource site configuration layer is constructed with the lowest cabin occupancy percentage as the upper-level target; the upper-level constraints include guarantee scope constraints, one-stop guarantee constraints and resource reachability constraints;

[0008] According to the pre-set process flow constraints, process support resource constraints and transfer timing constraints, the flight support planning layer is constructed with the shortest fleet support completion time as the lower-level goal;

[0009] According to the resource site configuration layer and the flight support planning layer, a resource configuration-support planning model is constructed, and the resource configuration-support planning model is solved to obtain an aviation resource site configuration result.

[0010] An aviation resource site configuration device for an offshore platform, the device comprising:

[0011] A configuration task acquisition module is used to obtain the resource type of the resource site, the parking space set corresponding to the parking space, and the cabin set corresponding to the cabin according to the preset aviation resource site configuration tasks; the cabin can be installed with a resource site of any resource type;

[0012] An upper-layer constraint construction module is used to take the resource type and quantity of the cabin installation resource site as decision variables, obtain the upper-layer constraint conditions to be satisfied by the decision variables according to the resource type of the resource site, the parking space set and the cabin set, and construct the resource site configuration layer according to the upper-layer constraint conditions with the lowest cabin occupancy percentage as the upper-layer target; the upper-layer constraint conditions include guarantee scope constraint, one-stop guarantee constraint and resource reachability constraint;

[0013] An upper model construction module is used to obtain the cabin occupancy percentage according to the decision variables and the number of cabins of the configurable resource site, and to construct a resource site configuration layer according to the upper constraint conditions and with the lowest cabin occupancy percentage as the upper target; the cabin occupancy percentage is a function of the decision variables;

[0014] The lower-level model building module is used to build the flight support planning layer based on the pre-set process flow constraints, process support resource constraints and transfer timing constraints, with the shortest fleet support completion time as the lower-level goal;

[0015] The configuration result output module is used to construct a resource configuration-guarantee planning model according to the resource site configuration layer and the flight guarantee planning layer, solve the resource configuration-guarantee planning model, and obtain the aviation resource site configuration result.

[0016] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0017] According to the preset aviation resource site configuration task, the resource type of the resource site, the parking space set corresponding to the parking space, and the cabin set corresponding to the cabin are obtained; the cabin can be installed with a resource site of any resource type;

[0018] The resource type and quantity of the cabin installation resource site are used as decision variables, and the upper-level constraints to be satisfied by the decision variables are obtained according to the resource type of the resource site, the parking space set and the cabin set. According to the upper-level constraints, the resource site configuration layer is constructed with the lowest cabin occupancy percentage as the upper-level target; the upper-level constraints include guarantee scope constraints, one-stop guarantee constraints and resource reachability constraints;

[0019] According to the pre-set process flow constraints, process support resource constraints and transfer timing constraints, the flight support planning layer is constructed with the shortest fleet support completion time as the lower-level goal;

[0020] According to the resource site configuration layer and the flight support planning layer, a resource configuration-support planning model is constructed, and the resource configuration-support planning model is solved to obtain an aviation resource site configuration result.

[0021] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the following steps:

[0022] According to the preset aviation resource site configuration task, the resource type of the resource site, the parking space set corresponding to the parking space, and the cabin set corresponding to the cabin are obtained; the cabin can be installed with a resource site of any resource type;

[0023] The resource type and quantity of the cabin installation resource site are used as decision variables, and the upper-level constraints to be satisfied by the decision variables are obtained according to the resource type of the resource site, the parking space set and the cabin set. According to the upper-level constraints, the resource site configuration layer is constructed with the lowest cabin occupancy percentage as the upper-level target; the upper-level constraints include guarantee scope constraints, one-stop guarantee constraints and resource reachability constraints;

[0024] According to the pre-set process flow constraints, process support resource constraints and transfer timing constraints, the flight support planning layer is constructed with the shortest fleet support completion time as the lower-level goal;

[0025] According to the resource site configuration layer and the flight support planning layer, a resource configuration-support planning model is constructed, and the resource configuration-support planning model is solved to obtain an aviation resource site configuration result.

[0026] The above-mentioned aviation resource site configuration method, device, computer equipment and storage medium of the offshore platform can obtain the resource type of the resource site, the parking space set corresponding to the parking space and the cabin set corresponding to the cabin, and use the resource type and quantity of the cabin installation resource site as decision variables to obtain the upper-level constraints. According to the upper-level constraints, the resource site configuration layer is constructed with the lowest cabin occupancy percentage as the upper-level goal. According to the pre-set process flow constraints, process guarantee resource constraints and transfer timing constraints, the flight guarantee planning layer is constructed with the shortest fleet guarantee completion time as the lower-level goal. According to the resource site configuration layer and the flight guarantee planning layer, a resource configuration-guarantee planning model is constructed, and the resource configuration-guarantee planning model is solved to obtain the aviation resource site configuration result. The embodiment of the present invention can reasonably plan the number of cabins and the installation type of fixed resource sites, so that each guarantee parking space meets the one-stop guarantee requirements and shortens the fleet guarantee cycle. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 A flow diagram of a method for configuring an aviation resource site of an offshore platform in one embodiment;

[0028] Figure 2 A schematic diagram of the IVNS algorithm flow in one embodiment;

[0029] Figure 3 A conceptual diagram of a TODFFO model in one embodiment;

[0030] Figure 4 A conceptual diagram of a VNS algorithm in another embodiment;

[0031] Figure 5 A schematic diagram of the simulation results of the IVNS algorithm in another embodiment;

[0032] Figure 6 A schematic diagram of the configuration of an offshore platform aviation resource site in another embodiment;

[0033] Figure 7 A schematic diagram of a simulation result of a VNS algorithm in another embodiment;

[0034] Figure 8 It is a structural block diagram of an aviation resource site configuration device of an offshore platform in one embodiment;

[0035] Fig. 9 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0036] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0037] In one embodiment, Figure 1 As shown, a method for configuring an aviation resource site of an offshore platform is provided, comprising the following steps:

[0038] Step 102, according to the preset aviation resource site configuration task, obtain the resource type of the resource site, the parking stand set corresponding to the parking stand, and the cabin set corresponding to the cabin.

[0039] The cabin can be installed with resource stations of any resource type. The aviation resource station is set on the offshore platform. The offshore platform is also equipped with cabins, aircraft support parking spaces, buildings, etc. The aviation resource station configuration task includes the resource type to be configured, the number of parking spaces on the offshore platform and the number of cabins. Resources refer to supply resources. Aviation resource stations refer to fixed resource stations near each support parking space, which can provide the supply resources required for the support of each aircraft. In the embodiment of the method of the present invention, the supply resources include fuel, power supply, oxygen, nitrogen and hydraulic oil. The fixed resource station is fixedly installed in the cabin. A fixed resource station that can provide one-stop support for aircraft at the support parking space can provide a stable support environment to the maximum extent, avoid the risk of accidental collision of mobile support vehicles due to external forces, and a stable support environment can improve work efficiency. Fixed resource stations near the one-stop support parking space are sufficient to provide the supply resources required for the support of each aircraft. There is no need to configure various types of mobile support vehicles, eliminating the risk of collision between the mobile support vehicle and the aircraft during the transfer of the offshore platform, and also reducing the maintenance and use costs of the offshore platform throughout its life cycle.

[0040] Step 104, taking the resource type and quantity of the cabin installation resource site as decision variables, obtaining the upper-level constraints that the decision variables must satisfy based on the resource type of the resource site, the parking space set and the cabin set, and constructing the resource site configuration layer based on the upper-level constraints and taking the lowest cabin occupancy percentage as the upper-level goal.

[0041] The upper-level constraints include support scope constraints, one-stop support constraints, and resource reachability constraints. Pipelines refer to the pipelines that transmit working fluids in hydraulic systems. Fixed resource sites of different resource types have different pipeline lengths. Therefore, it is necessary to optimize the configuration method of fixed resource sites so that all types of fixed resource sites cover every parking space and can complete all flight support operations in one parking space, thereby improving the efficiency of support operations. The cabin occupancy percentage is a function of the decision variable. The decision variable is found according to the factors to be achieved by the configuration of the aviation resource site. The objective function is determined by the functional relationship between the decision variable and the purpose to be achieved. The constraints to be satisfied by the decision variable are determined by the restrictions on the decision variable, thereby constructing the resource site configuration layer.

[0042] Step 106, based on the pre-set process flow constraints, process guarantee resource constraints and transfer timing constraints, the flight guarantee planning layer is constructed with the shortest fleet guarantee completion time as the lower-level goal.

[0043] Process support resources include maintenance support personnel, service support equipment, workstation space and supply resources. There are two assumptions in the flight support planning layer: Assumption 1: Each support position meets the one-stop support conditions, and each aircraft can complete all process support tasks in situ; Assumption 2: There is a zero-delay end-start connection relationship between processes, and the process cannot be interrupted during execution.

[0044] Step 108, constructing a resource configuration-guarantee planning model according to the resource site configuration layer and the flight support planning layer, solving the resource configuration-guarantee planning model, and obtaining the aviation resource site configuration result.

[0045] By establishing a two-tier optimization decision-making framework for fixed resource configuration and operations scheduling (TODFFO), namely the resource configuration-security planning model, the fixed resource site configuration scheme for offshore platforms that meets the one-stop security operation mode is designed and optimized. The conceptual diagram of the TODFFO model is shown in the figure. Figure 3As shown in the figure, the upper layer is the resource site configuration layer, which is used to formulate the layout plan of the fixed resource sites in each cabin and pass the resource site layout plan to the lower layer. The lower layer is the flight support planning layer, which is used to receive the resource site layout plan of the upper layer, perform scheduling optimization, generate an efficient operation scheduling plan, and pass the optimization result to the upper layer as a reference for the upper layer's decision-making optimization. Through the coupling relationship between the upper and lower layer models, one-stop support for each support parking space is jointly achieved. Since the fixed resource station provides replenishment resources for the pre-flight support operations of the aircraft, the configuration of the aviation resource site of the offshore platform has a strong correlation with the pre-flight support operations of the aircraft. Therefore, by jointly optimizing the configuration of the aviation resource site and the scheduling of the aircraft flight support operations, a two-layer optimization decision framework is formulated, and the model is solved to obtain the aviation resource site configuration results that can meet the needs of the aircraft flight mission. The one-stop support parking space has sufficient resource coverage, and the aircraft can complete a series of flight support operations such as filling and hanging in situ. There is no towing and mooring link of the aircraft during the support process, which not only improves the operation efficiency but also reduces the operation risk.

[0046] In the above-mentioned method for configuring aviation resource sites of offshore platforms, by obtaining the resource type of the resource site, the parking space set corresponding to the parking space, and the cabin set corresponding to the cabin, the resource type and quantity of the cabin installation resource site are used as decision variables, and the upper-level constraints can be obtained. According to the decision variables and the number of cabins of the configurable resource site, the cabin occupancy percentage is obtained. According to the upper-level constraints, the lowest cabin occupancy percentage is taken as the upper-level goal to construct the resource site configuration layer. According to the pre-set process flow constraints, process guarantee resource constraints and transfer timing constraints, the shortest fleet guarantee completion time is taken as the lower-level goal to construct the flight guarantee planning layer. According to the resource site configuration layer and the flight guarantee planning layer, a resource configuration-guarantee planning model is constructed, and the resource configuration-guarantee planning model is solved to obtain the aviation resource site configuration result. In the embodiment of the present invention, the number of cabins and the installation type of fixed resource sites can be reasonably planned and used, so that each guarantee parking space meets the one-stop guarantee requirements and shortens the fleet guarantee cycle.

[0047] In one embodiment, the resource type and quantity of the resource site installed in the cabin are used as decision variables. According to the resource type of the resource site, the parking space set and the cabin set, the upper-level constraints to be satisfied by the decision variables are obtained, including: calculating the distance between the cabin in the cabin set and the parking space in the parking space set, and according to the distance not exceeding the pipeline length of the resource site type installed in the cabin, obtaining the protection range constraint as follows:

[0048]

[0049] Among them, the position coordinates of the pth parking space are The position coordinates of the jth cabin are L k represents the pipeline length of the k-th resource site, k∈Ke, Ke represents the resource type set, p∈P S , P S is the parking stand set, P S ={1,2,…,|P S |},|P S | is the number of parking spaces, j∈C S , C S C is the cabin collection S ={1,2,…,|C S |},|C S | represents the number of cabins at the configurable resource site, ρ pjk =1 means that if the jth cabin is equipped with the kth resource station, the protection range of the kth resource station can cover the pth guaranteed parking space; the resource type and quantity of the resource station installed in the cabin are taken as decision variables, and the decision variables are constrained according to the protection range of each parking space in all resource station types, and the one-stop protection constraint is obtained as follows:

[0050]

[0051] The decision variables are:

[0052] X jk ∈{0,1} (3)

[0053]

[0054] Among them, X jk =1 means that the kth resource station is installed in the jth cabin, represents the number of resource sites that can be installed in the cabin; according to the resource type of the resource site installed in the cabin, the set of resource sites with the same resource type installed is obtained. According to the guarantee scope constraint, decision variables and the set of resource sites with the same resource type installed, the resource accessibility constraint is obtained as follows:

[0055]

[0056]

[0057] in, is the resource accessibility variable, ρ pjk is a resource type variable, X jk is the upper-level decision variable, Le k is the k-th resource site set, l is the resource site number in the k-th resource site set, l∈Le k , |Le k| represents the number of resource sites of the kth category, It means that the protection range of the lth resource site of the kth category can cover the pth guaranteed parking space.

[0058] In this embodiment, the distance between the parking position and the cabin is obtained by a pre-constructed offshore platform coordinate system. The left rear vertex of the offshore platform envelope is taken as the coordinate origin, the direction from the tail of the offshore platform to the bow of the offshore platform is taken as the x-axis, and the direction from the left to the right is taken as the y-axis to establish a plane rectangular coordinate system. The parking position set is denoted as P S ={1,2,…,|P S |}, the cabin set is C S ={1,2,…,|C S |}, the position coordinates of the pth parking space are The position coordinates of the jth cabin are Where p∈P S , j∈C S , according to the parking position coordinates and the cabin position coordinates, the distance between the parking position and the cabin is obtained. The cabin numbering rule is: number each cabin from small to large in a counterclockwise direction. For multiple cabins on the same longitudinal axis perpendicular to the bow direction of the offshore platform, they are numbered in order from right to left. The resource type and number of the resource station installed in the cabin are used as decision variables. Due to the limitation of the cabin space size, each cabin can only install at most 1 fixed resource station. The decision variable is a 0-1 decision variable, which means that the j-th cabin is installed with a k-th fixed resource station and the j-th cabin is not installed with a fixed resource station. The k-th (k∈Ke)-th fixed resource station is numbered in order from small to large according to the cabin number 1~|Le k |. is a 0-1 variable. The resource site layout plan passed from the upper layer to the lower layer can be used by Le k and express.

[0059] The purpose of TODFFO decision optimization is to build a one-stop parking space for offshore platforms, thereby achieving efficient flight support operation scheduling and improving aircraft dispatch rate. Therefore, the first optimization goal of the TODFFO two-layer decision framework is to minimize the completion time of fleet support:

[0060] min f1=C max

[0061] The more resource sites are configured, the more sufficient the support resources are, and the shorter the fleet support completion time is. However, too many resource sites will occupy a large number of idle cabins, which will reduce the number of available cabins for other operating systems of the offshore platform, which is not conducive to the comprehensive use efficiency of the offshore platform. In order to balance the cabin occupancy relationship between the aviation support system and other systems, the second optimization goal of the TODFFO model is set to minimize the cabin occupancy percentage:

[0062]

[0063] Through the above analysis of the upper-level offshore platform fixed resource allocation decision model and the relationship between the upper and lower coupling variables, combined with the one-stop offshore platform flight support planning layer, the TODFFO model is established as follows:

[0064] min F=(f1,f2) T

[0065]

[0066] Among them, Constraints (1) to (6) represent upper-level constraints, and Constraints (7) to (20) represent lower-level constraints. The decision variables of the flight support planning layer are defined as shown in Table 1:

[0067] Table 1 Decision variables at the one-stop offshore platform flight support planning level

[0068]

[0069] The one-stop flight support operation scheduling problem can be described by the following mixed integer programming model:

[0070] min C max (7)

[0071]

[0072]

[0073]

[0074]

[0075]

[0076]

[0077]

[0078]

[0079]

[0080]

[0081]

[0082]

[0083]

[0084] Among them, the earliest start time of the aircraft i support mission is when the aircraft is tied to the parking position p i Completion timeEx i , p i is the parking stand number corresponding to aircraft i, i∈I, I is the set of aircraft to be protected, I={1,2,…,n}, i is the number of the aircraft in the set of aircraft to be protected, A it is the process that aircraft i performs simultaneously at time t, J is the set of fleet support processes, J i is a series of support procedures with process constraints that constitute the aircraft support mission, J = {(i,j)|i∈I,j∈J i}, (i,j) is the process, d ij is the duration of the process, W ij is the support station of the process, Kp is the set of maintenance support personnel, Ke is the set of service support equipment, Ks is the set of station space, Kw is the set of supply resources, and the process (i, j) should be in the set of its immediate predecessor process P ij After all the processes are completed, the guarantee starts. The starting time of the process guarantee is the earliest time when all the resources required by it can meet the guarantee requirements at the same time. Each process involves at most four types of guarantee resources. The lower-level constraints include process flow constraints, process guarantee resource constraints and transfer timing constraints. The process guarantee resource constraints include maintenance support personnel constraints, service support equipment constraints, workstation space constraints and supply resource constraints. The specific constraints are as follows:

[0085] Maintenance support personnel constraints: The support scope of each support personnel covers the entire aircraft fleet, and the set of the kth (k∈Kp) type of support personnel is Lp k ={1,2,…,|Lp k |}, the number of support personnel required for the kth category in process (i,j) is rp ijk , personnel from the current security workstation W ij Transfer to the next security station W eg The transfer time required is

[0086] Service support equipment constraints: The set of the kth (k∈Ke) type of support equipment is Le k ={1,2,…,|Lek |}, the protection equipment can only provide protection for aircraft within the coverage area of ​​its pipeline. k ) support equipment can cover parking position p, then otherwise The number of equipment required by process (i, j) for the kth (k∈Ke) type is re ijk Each aircraft body usually has only one support equipment interface. If the support process has a demand for support equipment, the required quantity is only 1, that is, Ensure that the equipment is from the current working position W ij Transfer to the next workstation W eg The time required is The shared device type set is Ke s , the exclusive device type set is Ke u , Ke=Ke s ∪Ke u ;

[0087] Workstation space constraints: Considering the limitation of workstation space on the number of maintenance personnel, some maintenance workstations can only accommodate a certain number of personnel to work at the same time due to limited space. For example, the aircraft cockpit can only accommodate one maintenance personnel to work. If the process (i, j) has a demand for the kth (k∈Ks) type of workstation space, let rs ijk =1, otherwise rs ijk = 0, the maximum capacity of maintenance personnel in the kth (k∈Ks) type of workstation space of aircraft i is ns ik ;

[0088] Supply resource constraints: Limited by the supply of supply resources on offshore platforms, the maximum number of processes that the kth (k∈Kw) supply resource can provide at the same time is Lw k , rw ijk =1 indicates that process (i,j) has demand for the kth (k∈Kw)th supply resource, otherwise rw ijk =0;

[0089] In the mixed integer programming model, formula (7) indicates that the objective function is to minimize the completion time of the fleet support, and formulas (8) to (20) are lower-level constraints. Formula (8) indicates that the start time of a single aircraft support operation shall not be earlier than the time when the aircraft arrives at the support parking position and is moored. Formula (9) indicates the process flow constraint of the support operation. Formula (10) indicates the supply resource constraint. At any time, the total number of aircraft supported by each supply resource cannot exceed the maximum supply of the resource. Formula (11) indicates the workstation space constraint. At any time, the number of maintenance personnel accommodated by the workstation space of a single aircraft support process cannot exceed the rated number. Formula (12) is the coverage constraint of the service support equipment. Formula (13) indicates the same The transfer timing constraints when maintenance personnel continuously perform multiple maintenance processes, where BM is a sufficiently large positive number. Formula (14) limits the transfer timing relationship between exclusive maintenance equipment and shared equipment that do not support the same aircraft between adjacent maintenance processes. Formula (15) is for shared equipment, ensuring that different processes that require the same shared equipment for a single aircraft at the same time are allocated to the same equipment to avoid multiple shared support equipment supporting a single aircraft at the same time. Formulas (16) and (17) indicate that the allocation and demand of maintenance personnel and service support equipment are equal. Formulas (18) and (19) represent the relationship between decision variables. Formula (20) is the attribute constraint of 0-1 decision variables.

[0090] By building TODFFO, the resource site configuration optimization problem that satisfies the one-stop guarantee conditions for each guaranteed parking space is solved, and the variable neighborhood search algorithm (VNS) is widely used in a large number of optimization problems. Figure 4 As shown in FIG. 1 , a conceptual diagram of a VNS algorithm is provided. The basic idea of ​​the VNS algorithm is to design a variety of neighborhood structures with different search ranges. Starting from a solution to the problem, neighborhood solutions of the current solution are generated in different neighborhood structures, and then individual evaluation is performed to obtain the local optimal solution. If a better solution can be obtained in the current neighborhood, the solution is retained and returned to the first neighborhood for re-searching. Otherwise, the neighborhood solution is abandoned and the next neighborhood is entered for local search. The VNS algorithm is mostly used for single-objective optimization solutions. The key step in its search mechanism is that if the neighborhood solution is inferior to the current solution, the neighborhood solution will be directly abandoned, and the next neighborhood structure with a larger search range will be turned to obtain a better solution. In multi-objective optimization problems, the neighborhood solution obtained by a neighborhood transformation may not guarantee that all objective functions are better than the current solution, that is, the neighborhood solution and the current solution do not dominate each other, or the two objective functions of the neighborhood solution are slightly inferior to the current solution. In this case, if the neighborhood solution is directly abandoned, the number of feasible solutions in the final result will be reduced. The present invention adopts an improved variable neighborhood search algorithm (IVNS) to solve the optimization problem.

[0091] In one embodiment, Figure 2 As shown, a schematic diagram of the IVNS algorithm flow is provided to solve the resource allocation-security planning model and obtain the aviation resource site configuration results, including:

[0092] S10: Calculate the initial solution of the resource allocation-security planning model, obtain the upper objective function value and the lower objective function value of the initial solution according to the initial solution, store the initial solution in the non-dominated solution set (Archive), and initialize k=1.

[0093] S12: Search the feasible neighborhood solutions of the initial solution in the pre-constructed insert neighborhood, delete neighborhood, exchange neighborhood and reset neighborhood in sequence. If the current solution can generate a feasible neighborhood solution in the kth neighborhood structure, then a feasible neighborhood solution is obtained. When a feasible neighborhood solution cannot be generated, let k = k + 1, determine the next neighborhood structure, and Figure 2 In, N k represents the kth neighborhood structure, x′ is a feasible neighborhood solution, x′=N k (x).

[0094] S14: Calculate the upper objective function value and the lower objective function value of the feasible neighborhood solution. When the feasible neighborhood solution and the current solution do not dominate each other, update the current solution to the feasible neighborhood solution, store the feasible neighborhood solution in the non-dominated solution set, and return to step S12.

[0095] S16: When the feasible neighborhood solution and the initial solution dominate each other, the acceptance probability of the simulated annealing algorithm (SA) is obtained according to the upper objective function value and the lower objective function value of the initial solution and the upper objective function value and the lower objective function value of the feasible neighborhood solution. When the generated random number is less than the acceptance probability, the current solution is updated to the feasible neighborhood solution, and iterative operations are performed. After reaching the maximum number of iterations, set k=k+1 to determine the next neighborhood structure.

[0096] S18: If k>k max , then continue to determine whether the algorithm has reached the maximum number of iterations. If so, terminate the algorithm and output the aviation resource site configuration result. Otherwise, set k = 1 and return to step S12. If k ≤ k max , then directly return to step S12, k max is the number of neighbors, iter max The maximum number of iterations of the VNS-SA algorithm.

[0097] In step S14, the feasible neighborhood solution and the current solution do not dominate each other, that is, The conditions for establishment are:

[0098]

[0099] Among them, f1(x′) represents the upper objective function value of the feasible neighborhood solution, and f2(x′) represents the lower objective function value of the feasible neighborhood solution.

[0100] In step S16, the acceptance probability is:

[0101]

[0102]

[0103] Where T is the annealing temperature, and its value decreases with the increase of the number of iterations.

[0104] In this embodiment, the IVNS algorithm accepts the current degraded neighborhood solution based on the acceptance mechanism of SA, and generates a new neighborhood solution in other neighborhood structures based on the degraded neighborhood solution. If the neighborhood solution is better than the current solution or the two do not dominate each other, it means that the current neighborhood structure is helpful for the algorithm to find the best solution. Then IVNS continues to search in the current neighborhood structure, which can reduce the degree of damage to the structure of the current solution and prevent the phenomenon of random search due to excessive conversion of the neighborhood search range, which leads to the inability of the neighborhood solution to make good use of the heuristic information of the current solution.

[0105] Before the IVNS algorithm seeks the best solution, it first gives the encoding scheme for the solution x. In the IVNS algorithm, the solution x is a vector with a length of |C S | is the row vector of The value of each code is x j ∈Ke∪{0},j=1,2,…,|C S |, if x j = k, it means that the kth type of fixed resource station is installed in the jth cabin. If x j = 0, it means that the jth cabin does not install any fixed resource station. From the structure of the solution x, it can be seen that not all lengths |C S |The row vectors can all satisfy the upper constraints of TODFFO. If the initial solution is generated randomly and then the infeasible solutions are deleted according to the constraints, a lot of computing resources will be wasted.

[0106] In one embodiment, the step of calculating the initial solution of the resource configuration-security planning model includes:

[0107] S20: Initialize the solution of the resource allocation-security planning model as Let i=1, i is the parking position number.

[0108] S22: Let k=1, k∈Ke, k is the resource type number, Ke is the resource type.

[0109] S24: When k≤|Ke|, if the i-th parking space is not covered by the k-th resource site, a cabin without a resource site installed (i.e., x j_select = 0), install the k-th resource site (i.e., let x j_select = k), and the protection range of the cabin without resource site installation after the k-th resource site is installed can cover the i-th parking space. If the i-th parking space is covered by the k-th resource site, let k = k + 1, return to step S24 and iterate again. When k> | Ke |, let i = i + 1. If i> | P S |, then proceed to step S26, otherwise proceed to step S22, where i represents the parking space number and k represents the resource type number.

[0110] S26: When all parking spaces can meet the one-stop guarantee requirements, a random number rand is generated. When the random number is less than the resource increase probability P add When the resource station is not installed, it will be randomly selected as a cabin j_idle Install a resource site, that is, x j_idle =randi(|Ke|), and the minimum resource configuration coding scheme of the solution is obtained. The minimum resource configuration coding scheme can meet the one-stop guarantee condition for each parking position, where the function randi(y) represents the generation of a random integer between 1 and y.

[0111] S28: Output the initial solution of the resource allocation-security planning model according to the minimum resource allocation coding scheme.

[0112] In this embodiment, an initial solution can be obtained by generating a minimum resource configuration code that can meet the one-stop guarantee conditions of each parking position, and then increasing the resource site configuration according to the resource increase probability.

[0113] In one embodiment, the steps of calculating the upper layer objective function value and the lower layer objective function value include: obtaining, according to the minimum resource configuration coding scheme, a resource site set corresponding to each resource type and a resource accessibility variable between each resource site and each parking space, and obtaining a resource site layout scheme according to the resource site set and the accessibility variable that install the same resource type; the resource site configuration layer transmits the resource site layout scheme to the flight support planning layer, uses the scheduling algorithm to solve the first goal, obtains the fleet support completion time, and solves the second goal according to the number of resource sites installed with the same resource type and the number of cabins that can configure the resource sites, and obtains the cabin occupancy percentage:

[0114]

[0115] Where k represents the resource type number, k∈Ke, Ke represents the resource type, |Le k| represents the number of resource sites of the kth category, |C S | represents the number of cabins of configurable resource sites; the lower objective function value is obtained according to the completion time of the fleet support, and the upper objective function value is obtained according to the cabin occupancy percentage. In this embodiment, when optimizing the lower model, the scheduling algorithm used is the existing technology, specifically a dual-population genetic algorithm combined with a serial schedule generation mechanism (Serial Schedule Generation Scheme, SSGS). In Su Xichao, Han Wei, Zhang Yong, et al., Scheduling Algorithm for Aircraft Deck Maintenance Service Support Considering Human-Machine Matching Mode [J]. Acta Aeronautica Sinica, 2018, 39(12): 222314, the implementation process of the scheduling algorithm has been made public. Through the coupling relationship between the upper and lower layers of the TODFFO model, the function value of the objective function is obtained, thereby obtaining the aviation resource configuration result that meets the one-stop support.

[0116] The IVNS algorithm proposed in this paper designs four types of neighborhood structures, namely k max =4, in the order of the neighborhood search range from small to large, they are Insert neighborhood, Delete neighborhood, Swap neighborhood and Reassign neighborhood.

[0117] In one embodiment, the step of constructing the insertion neighborhood includes: obtaining a resource type with a minimum resource redundancy ratio according to a resource redundancy ratio of each resource type; the expression of the resource redundancy ratio is:

[0118]

[0119] Among them, γ k represents the redundancy ratio of the k-th resource, represents the resource margin of the k-th resource at the p-th parking space, ρ pjk is a resource type variable, X jk is the upper-level decision variable, β k represents the resource redundancy weight coefficient of the k-th resource site, P S is the parking stand set, P S ={1,2,…,|P S |},|P S | is the number of parking spaces, C S For the cabin assembly, C S ={1,2,…,|C S |},|C S| represents the number of cabins that can be configured with resource sites, j is the cabin number; according to the minimum resource surplus ratio resource type of each parking position, the minimum resource surplus parking position is obtained, and a free cabin that can cover the minimum resource surplus parking position is randomly selected, and the resource site with the minimum resource surplus ratio resource type is configured in the free cabin; when there are no free cabins around the minimum resource surplus parking position, the current solution cannot generate a feasible neighborhood solution in the insertion neighborhood, and the current solution is transferred to the next neighborhood.

[0120] In this embodiment, β k The value is related to the use time of this type of fixed resource station in the single-machine support operation. The Insert neighborhood solution is constructed by inserting a fixed resource station on the idle cabin of the current solution x. Generally speaking, since solution x has met the one-stop support requirements after initialization, any fixed resource station can be inserted into any idle cabin of solution x to generate a neighborhood solution. However, this insertion method is not targeted, and new resource stations may be configured near parking spaces with abundant resources, while resource stations around parking spaces with scarce resources cannot be supplemented, resulting in uneven resource distribution. To this end, the present invention proposes an Insert neighborhood based on the minimum resource redundancy ratio, and the mechanism of action is: Among them, k 0 is the resource type with the minimum resource redundancy ratio, and j_insert is the number of the free cabin that can cover the parking space with the minimum resource redundancy ratio.

[0121] In one embodiment, the step of constructing a deletion neighborhood includes: randomly selecting a resource type to obtain the resource type to be deleted; obtaining the cabins in the current solution that have installed the resource site of the resource type to be deleted, and when the resource margins of all parking spaces that can be guaranteed by each cabin are greater than 1, it means that the resource site of the resource type to be deleted installed in the cabin can be deleted, and the resource site number of the resource site is recorded; randomly selecting a cabin from the cabins where all resource sites that can be deleted are located, and deleting the resource site installed in the cabin; when there are no resource sites that can be deleted for all resource types, the current solution cannot generate a feasible neighborhood solution in the deletion neighborhood, and the current solution is transferred to the next neighborhood. In this embodiment, the construction method of the Delete neighborhood solution is to randomly delete one of the configured fixed resource sites of the current solution x. In order to ensure that each parking space after deleting the fixed resource site can still meet the one-stop guarantee conditions, when deleting the resource site, it is necessary to determine whether each parking space is covered by other similar resource sites. The working mechanism of the Delete neighborhood solution is as follows: Among them, j_delete is the resource site ID of the resource type to be deleted that can be deleted.

[0122] In one embodiment, the step of constructing an exchange neighborhood includes: randomly selecting two resource types, selecting a cabin number corresponding to a resource site that can be deleted from each of the two resource types, and exchanging the cabin numbers; when there is no cabin to exchange, the current solution cannot produce a feasible neighborhood solution in the exchange neighborhood, and the current solution is transferred to the next neighborhood. In this embodiment, the Swap neighborhood solution is constructed by randomly selecting the cabin numbers of two exchangeable fixed resource sites, and then exchanging the corresponding numbers. Exchanging the cabin numbers of the deletable fixed resource sites can ensure that after the resource sites are exchanged, each support parking space can meet the one-stop support requirements. The working mechanism of the Swap neighborhood solution is Among them, j_swap1 and j_swap2 are the cabin numbers of the exchangeable fixed resource sites.

[0123] In one embodiment, the step of constructing a reset neighborhood includes: obtaining the cabin number corresponding to the resource site that can be deleted in each type of resource, deleting the resource site of the cabin corresponding to the cabin number, and re-searching the deletable cabin number after each deletion of the resource site; randomly selecting a resource type, deleting the resource site of the resource type in the current solution, reconfiguring the resource site for all parking spaces, and increasing the resource site configuration according to the probability of resource increase, and outputting a feasible neighborhood solution. In this embodiment, the Reassign neighborhood solution is constructed by deleting the surplus resource sites of each parking space, and then randomly selecting a type of resource to reconfigure the resource sites for all parking spaces. Deleting the surplus resource sites can prevent the situation where there are no free cabins when the resource sites are subsequently reconfigured for the parking spaces. The working mechanism of the Reassign neighborhood solution is: Initialization means initialization.

[0124] In a specific embodiment, Figure 5 As shown in Figure 1, a schematic diagram of the simulation results of the IVNS algorithm is provided. The simulation experiment considers five types of fixed equipment stations (i.e., Ke = {1, 2, 3, 4, 5}), namely, fueling station, power station, oxygen station, nitrogen station and hydraulic station. The corresponding pipeline lengths of various resource stations are (Unit: m), during the flight support operation, the use time of the power supply station is relatively long, so the redundancy weight coefficients of various resources are taken exist Figure 5In the results, the IVNS algorithm has a good distribution. With the increase of cabin occupancy percentage (the increase of the number of fixed resource site configurations), the average value of the support completion time of the three types of support tasks gradually decreases, that is, the two objective function values ​​of the TODFFO model are negatively correlated. The rate of decrease of the average value of the support completion time is different under different cabin occupancy percentages. Under the condition of the minimum fixed resource configuration that meets the one-stop support conditions, the increase of the cabin occupancy percentage will cause a significant decrease in the fleet support completion time. When the cabin occupancy percentage increases to a certain extent, the increase in the number of fixed resource site configurations has little effect on speeding up the support operation process. The number of fixed resource site configurations is no longer the main constraint on the scheduling plan for maintenance service support operations. Figure 5 Point A in the figure is the demarcation point where the average rate of decrease of the guarantee completion time changes significantly. Therefore, under the requirement of meeting the time limit of the fleet dispatch, the cabin occupancy percentage should be controlled within a reasonable range. A significant increase in the number of fixed resource station configurations will not only make it difficult to improve the guarantee efficiency, but will also occupy a large number of vacant cabins, making the operating resources of other systems on the offshore platform even scarcer.

[0125] Figure 5 The layout plan of the fixed resource site of the offshore platform shown at point A is as follows Figure 6 As shown, Figure 6 A schematic diagram of the configuration of aviation resource stations on an offshore platform is provided. A1 to A12 represent parking bay numbers. There are 12 parking bays and 48 cabins, with a cabin occupancy rate of 63.64%. The number of various fixed resource stations is 5 gas stations, 7 power stations, 5 oxygen stations, 8 nitrogen stations, and 4 hydraulic stations. Figure 7 As shown in the figure, a schematic diagram of the simulation results of the VNS algorithm is provided. The IVNS algorithm has obvious advantages in the number of feasible solutions and the distribution of non-dominated solution sets, while the number of feasible solutions obtained by the VNS algorithm is small, and most of them are concentrated in the area with a large cabin occupancy percentage, and the distribution of solutions is poor. This is because the VNS algorithm does not accept degraded neighborhood solutions, and when the neighborhood solution is better than the current solution, the VNS algorithm will return to the first Insert neighborhood to continue searching, resulting in new resource sites being inserted into the current solution, so that the cabin occupancy percentage is always at a high value. Even though the VNS algorithm mainly iteratively searches in the solution space where the cabin occupancy percentage is high, the average value of the guarantee completion time has not been greatly reduced. Under the same cabin occupancy percentage, the difference between the average value of the guarantee completion time obtained by the IVNS algorithm and the VNS algorithm is very small, which also shows that when the cabin occupancy percentage increases to a certain extent, the further increase in the number of fixed resource site configurations has little effect on accelerating the guarantee operation process.

[0126] It should be, although Figure 1-4 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 1-4 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0127] In one embodiment, Figure 8 As shown, an aviation resource site configuration device for an offshore platform is provided, comprising: a configuration task acquisition module 802, an upper model construction module 804, a lower model construction module 804 and a configuration result output module 808, wherein:

[0128] The configuration task acquisition module 802 is used to obtain the resource type of the resource site, the parking space set corresponding to the parking space, and the cabin set corresponding to the cabin according to the preset aviation resource site configuration tasks;

[0129] The upper model construction module 804 is used to obtain a resource type variable according to the distance between the parking position and the cabin being no greater than the pipeline length of the resource station corresponding to each resource type, obtain an upper decision variable according to the cabin space restriction and the resource type corresponding to the resource station installed in the cabin, obtain a resource accessibility variable according to the resource type, the decision variable and the cabin number, obtain an upper constraint condition according to the resource accessibility variable, obtain a cabin occupancy percentage according to the decision variable and the number of cabins with configurable resource stations, and construct a resource station configuration layer according to the upper constraint condition and with the lowest cabin occupancy percentage as the upper target;

[0130] The lower model building module 804 is used to build a flight support planning layer according to the pre-set process flow constraints, process support resource constraints and transfer timing constraints, with the shortest fleet support completion time as the lower target;

[0131] The configuration result output module 808 is used to construct a resource configuration-guarantee planning model according to the resource site configuration layer and the flight guarantee planning layer, solve the resource configuration-guarantee planning model, and obtain the aviation resource site configuration result.

[0132] In one of the embodiments, the configuration result output module 808 is also used to calculate the initial solution of the resource configuration-guarantee planning model, and obtain the upper objective function value and the lower objective function value of the initial solution according to the initial solution, and store the initial solution in the non-dominated solution set; sequentially search for the feasible neighborhood solution of the initial solution in the pre-constructed insertion neighborhood, deletion neighborhood, exchange neighborhood and reset neighborhood; calculate the upper objective function value and the lower objective function value of the feasible neighborhood solution, and when the feasible neighborhood solution and the current solution do not dominate each other, update the current solution to the feasible neighborhood solution, store the feasible neighborhood solution in the non-dominated solution set, and iterate the search in the current neighborhood until the iteration termination condition is met, and transfer to the next neighborhood search. When all areas are searched, the aviation resource site configuration result is output; when the feasible neighborhood solution and the initial solution dominate each other, according to the upper objective function value and the lower objective function value of the initial solution and the feasible The upper objective function value and the lower objective function value of the neighborhood solution are used to obtain the acceptance probability of the simulated annealing algorithm. When the generated random number is less than the acceptance probability, the current solution is updated to a feasible neighborhood solution and iterative operation is performed. After the maximum number of iterations is reached, the next neighborhood search is transferred to. When all fields are searched, the aviation resource site configuration result is output; the steps of calculating the initial solution of the resource configuration-guarantee planning model include: initializing the solution of the resource configuration-guarantee planning model, and the solution is a row vector with a length of the number of cabins with configurable resource sites; when the resource type number is not greater than the length of the resource type set corresponding to the resource type, if the p-th parking space is not covered by the k-th resource site, a cabin without a resource site installed is randomly selected, and the k-th resource site is installed, so that the protection range of the cabin without a resource site installed after the k-th resource site is installed can cover the p-th parking space, where p represents the parking position number, k represents the resource type number; when all current parking positions can meet the one-stop guarantee requirements, a random number is generated. When the random number is less than the resource increase probability, a type of resource station is randomly installed for the cabin without a resource station installed, and the minimum resource configuration coding scheme of the solution is obtained; the minimum resource configuration coding scheme can meet the one-stop guarantee conditions for each parking position; according to the minimum resource configuration coding scheme, the initial solution of the resource configuration-guarantee planning model is output.

[0133] In one embodiment, the configuration result output module 808 is further used to obtain, according to the minimum resource configuration coding scheme, a set of resource sites that install the same resource type and a resource accessibility variable between each resource site and each parking position corresponding to each resource type, and obtain a resource site layout scheme according to the set of resource sites that install the same resource type and the accessibility variable; the resource site configuration layer transmits the resource site layout scheme to the flight support planning layer, uses the scheduling algorithm to solve the first goal, obtains the fleet support completion time, and solves the second goal according to the number of resource sites that install the same resource type and the number of cabins that can configure the resource sites, and obtains the cabin occupancy percentage:

[0134]

[0135] Where k represents the resource type number, k∈Ke, Ke represents the resource type, |Le k | represents the number of resource sites of the kth category, |C S | represents the number of cabins at the configurable resource site; the lower objective function value is obtained according to the completion time of the fleet support, and the upper objective function value is obtained according to the cabin occupancy percentage.

[0136] In one embodiment, the configuration result output module 808 is further used to obtain a resource type with a minimum resource redundancy ratio according to a resource redundancy ratio of each resource type; the resource redundancy ratio is:

[0137]

[0138] Among them, γ k represents the redundancy ratio of the k-th resource, represents the resource margin of the k-th resource at the p-th parking space, ρ pjk is a resource type variable, X jk is the upper-level decision variable, β k represents the resource redundancy weight coefficient of the k-th resource site, P S is the parking stand set, P S ={1,2,…,|P S |},|P S | is the number of parking spaces, C S For the cabin assembly, C S ={1,2,…,|C S |},|C S | represents the number of cabins that can be configured with resource sites, j is the cabin number; according to the resource type with the minimum resource surplus ratio of each parking position, the minimum resource surplus parking position is obtained, and a free cabin that can cover the minimum resource surplus parking position is randomly selected, and the resource site with the minimum resource surplus ratio resource type is configured in the free cabin; when there are no free cabins around the minimum resource surplus parking position, the current solution cannot generate a feasible neighborhood solution in the insertion neighborhood, and the current solution is transferred to the next neighborhood.

[0139] In one of the embodiments, the configuration result output module 808 is also used to randomly select a resource type to obtain the resource type to be deleted; obtain the cabin in the current solution where the resource site of the resource type to be deleted is installed, and when the resource redundancy of all parking spaces that can be guaranteed by each cabin is greater than 1, it means that the resource site of the resource type to be deleted installed in the cabin can be deleted, and the resource site number of the resource site is recorded; randomly select a cabin from all the cabins where the resource sites that can be deleted are located, and delete the resource site installed in the cabin; when there are no resource sites that can be deleted for all resource types, the current solution cannot generate a feasible neighborhood solution in the deletion neighborhood, and the current solution is transferred to the next neighborhood.

[0140] In one of the embodiments, the configuration result output module 808 is also used to randomly select two resource types, select a cabin number corresponding to a resource site that can be deleted from the two resource types, and exchange the cabin numbers; when there is no cabin to exchange, the current solution cannot generate a feasible neighborhood solution in the exchange neighborhood, and the current solution is transferred to the next neighborhood.

[0141] In one of the embodiments, the configuration result output module 808 is also used to obtain the cabin number corresponding to the resource site that can be deleted in each type of resource, delete the resource site of the cabin corresponding to the cabin number, and re-search the deletable cabin number after each deletion of the resource site; randomly select the resource type, delete the resource site of the resource type in the current solution, reconfigure the resource site for all parking spaces, and increase the resource site configuration according to the probability of resource increase, and output a feasible neighborhood solution.

[0142] In one embodiment, the upper model building module 804 is further used to calculate the distance between the cabin in the cabin set and the parking space in the parking space set, and according to the distance not exceeding the pipeline length of the resource site type installed in the cabin, the protection range constraint is obtained as follows:

[0143]

[0144] Among them, the position coordinates of the pth parking space are The position coordinates of the jth cabin are L k represents the pipeline length of the k-th resource site, k∈Ke, Ke represents the resource type set, p∈P S , P S is the parking stand set, P S ={1,2,…,|P S |},|P S | is the number of parking spaces, j∈C S , C S C is the cabin collection S={1,2,…,|CS|},|C S | represents the number of cabins at the configurable resource site, ρ pjk =1 means that if the jth cabin is equipped with the kth resource station, the protection range of the kth resource station can cover the pth guaranteed parking space; the resource type and quantity of the resource station installed in the cabin are taken as decision variables, and the decision variables are constrained according to the protection range of each parking space in all resource station types, and the one-stop protection constraint is obtained as follows:

[0145]

[0146] The decision variables are:

[0147] X jk ∈{0,1}

[0148]

[0149] Among them, X jk =1 means that the kth resource station is installed in the jth cabin, represents the number of resource sites that can be installed in the cabin; according to the resource type of the resource site installed in the cabin, the set of resource sites with the same resource type installed is obtained. According to the guarantee scope constraint, decision variables and the set of resource sites with the same resource type installed, the resource accessibility constraint is obtained as follows:

[0150]

[0151]

[0152] in, is the resource accessibility variable, ρ pjk is a resource type variable, X jk is the upper-level decision variable, Le k is the k-th resource site set, l is the resource site number in the k-th resource site set, l∈Le k , |Le k | represents the number of resource sites of the kth category, It means that the protection range of the lth resource site of the kth category can cover the pth guaranteed parking space.

[0153] The specific definition of the aviation resource site configuration device for the offshore platform can be found in the definition of the aviation resource site configuration method for the offshore platform mentioned above, which will not be repeated here. Each module in the above-mentioned aviation resource site configuration device for the offshore platform can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0154] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Fig. 9 As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for configuring an aviation resource site of an offshore platform is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0155] Those skilled in the art will understand that Fig. 9 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0156] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method in the above embodiment when executing the computer program.

[0157] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method in the above embodiment are implemented.

[0158] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0159] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0160] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A method for configuring aviation resource sites on an offshore platform, characterized in that: The method comprises: According to the preset aviation resource site configuration task, the resource type of the resource site, the parking space set corresponding to the parking space, and the cabin set corresponding to the cabin are obtained; the cabin can be installed with a resource site of any resource type; The resource type and quantity of the cabin installation resource site are used as decision variables, and the upper-level constraints to be satisfied by the decision variables are obtained according to the resource type of the resource site, the parking space set and the cabin set. According to the upper-level constraints, the resource site configuration layer is constructed with the lowest cabin occupancy percentage as the upper-level target; the upper-level constraints include guarantee scope constraints, one-stop guarantee constraints and resource reachability constraints; According to the pre-set process flow constraints, process support resource constraints and transfer timing constraints, the flight support planning layer is constructed with the shortest fleet support completion time as the lower-level goal; Constructing a resource configuration-security planning model according to the resource site configuration layer and the flight security planning layer, solving the resource configuration-security planning model, and obtaining an aviation resource site configuration result; The resource configuration-security planning model is solved to obtain the aviation resource site configuration result, including: Calculating an initial solution of the resource allocation-security planning model, obtaining an upper objective function value and a lower objective function value of the initial solution according to the initial solution, and storing the initial solution in a non-dominated solution set; Sequentially searching for feasible neighborhood solutions of the initial solution in pre-constructed insert neighborhoods, delete neighborhoods, exchange neighborhoods, and reset neighborhoods; Calculate the upper objective function value and the lower objective function value of the feasible neighborhood solution. When the feasible neighborhood solution and the current solution do not dominate each other, update the current solution to the feasible neighborhood solution, store the feasible neighborhood solution in the non-dominated solution set, and iterate the search in the current neighborhood until the iteration termination condition is met, and transfer to the next neighborhood search. When all areas are searched, output the aviation resource site configuration result; When the feasible neighborhood solution and the initial solution dominate each other, the acceptance probability of the simulated annealing algorithm is obtained according to the upper objective function value and the lower objective function value of the initial solution and the upper objective function value and the lower objective function value of the feasible neighborhood solution. When the generated random number is less than the acceptance probability, the current solution is updated to the feasible neighborhood solution, and iterative operation is performed. After reaching the maximum number of iterations, the search is transferred to the next neighborhood. When all areas are searched, the aviation resource site configuration result is output; The step of calculating the initial solution of the resource allocation-security planning model includes: Initializing a solution of the resource configuration-security planning model, wherein the solution is a row vector having a length equal to the number of cabins of the configurable resource site; When the resource type number is not greater than the length of the resource type set corresponding to the resource type, if the p-th parking position is not covered by the k-th resource site, a cabin without a resource site installed is randomly selected to install the k-th resource site, and the protection range of the cabin without a resource site installed after the k-th resource site is installed can cover the p-th parking position, where p represents the parking position number and k represents the resource type number; When all current parking positions can meet the one-stop guarantee requirements, a random number is generated. When the random number is less than the resource increase probability, a type of resource station is randomly installed for the cabin without a resource station installed, and the minimum resource configuration coding scheme of the solution is obtained; the minimum resource configuration coding scheme can meet the one-stop guarantee conditions for each parking position; Outputting an initial solution of the resource allocation-security planning model according to the minimum resource allocation coding scheme; The calculation steps of the upper layer objective function value and the lower layer objective function value include: According to the minimum resource configuration coding scheme, a set of resource sites for installing the same resource type corresponding to each resource type and a resource accessibility variable between each resource site and each parking space are obtained, and a resource site layout scheme is obtained according to the set of resource sites for installing the same resource type and the accessibility variables; The resource site configuration layer passes the resource site layout plan to the flight support planning layer, uses the scheduling algorithm to solve the first goal, and obtains the fleet support completion time. The second goal is solved according to the number of resource sites installed with the same resource type and the number of cabins that can be configured with resource sites, and the cabin occupancy percentage is obtained as follows: Where k represents the resource type number, k∈Ke, Ke represents the resource type, |Le k | represents the number of resource sites of the kth category, |C S |Indicates the number of cabins at the configurable resource site; A lower objective function value is obtained according to the fleet support completion time, and an upper objective function value is obtained according to the cabin occupancy percentage; The resource type and quantity of the cabin installation resource site are used as decision variables, and the upper-level constraints to be satisfied by the decision variables are obtained according to the resource type of the resource site, the parking space set and the cabin set, including: The distance between the cabin in the cabin set and the parking space in the parking space set is calculated, and according to the distance not exceeding the pipeline length of the resource site type installed in the cabin, the protection range constraint is obtained as follows: Among them, the position coordinates of the pth parking space are The position coordinates of the jth cabin are L k represents the pipeline length of the k-th resource site, k∈Ke, Ke represents the resource type set, p∈P S , P S is the parking stand set, P S ={1,2,…,|P S |},|P S | is the number of parking spaces, j∈C S , C S For the cabin assembly, C S ={1,2,…,|C S |},|C S | represents the number of cabins at the configurable resource site, ρ pjk =1 means that if the jth cabin is equipped with the kth resource station, the protection range of the kth resource station can cover the pth guaranteed parking space; The resource type and quantity of the cabin installation resource site are used as decision variables. According to the protection range of each parking space in all resource site types, the decision variables are constrained, and the one-stop protection constraint is obtained as follows: The decision variables are: X jk ∈{0,1} Among them, X jk =1 means that the kth resource station is installed in the jth cabin, Indicates the limit on the number of resource sites that can be installed in the cabin; According to the resource type of the resource site installed in the cabin, a set of resource sites with the same resource type installed is obtained. According to the guarantee scope constraint, the decision variable and the set of resource sites with the same resource type installed, the resource reachability constraint is obtained as follows: in, is the resource accessibility variable, ρ pjk is a resource type variable, X jk is the upper decision variable, Le k is the k-th resource site set, l is the resource site number in the k-th resource site set, l∈Le k ,|Le k | represents the number of resource sites of the kth category, It means that the protection range of the lth resource site of the kth category can cover the pth guaranteed parking space.

2. The method according to claim 1, characterized in that The steps to construct an insertion neighborhood include: According to the resource redundancy ratio of each resource type, the resource type with the minimum resource redundancy ratio is obtained; the expression of the resource redundancy ratio is: Among them, γ k represents the redundancy ratio of the k-th resource, represents the resource margin of the k-th resource at the p-th parking space, ρ pjk is a resource type variable, X jk is the upper-level decision variable, β k represents the resource redundancy weight coefficient of the k-th resource site, P S is the parking stand set, P S ={1,2,…,|P S |},|P S | is the number of parking spaces, C S For the cabin assembly, C S ={1,2,…,|C S |},|C S | represents the number of cabins of configurable resource sites, j is the cabin number; According to the minimum resource redundancy ratio resource type of each parking position, a minimum resource redundancy parking position is obtained, a free cabin that can cover the minimum resource redundancy parking position is randomly selected, and a resource station of the minimum resource redundancy ratio resource type is configured in the free cabin; When there is no free cabin around the minimum resource margin parking space, the current solution cannot generate a feasible neighborhood solution in the insertion neighborhood, and the current solution is transferred to the next neighborhood.

3. The method according to claim 1, characterized in that The steps to build a deletion neighborhood include: Randomly select a resource type to obtain the resource type to be deleted; Obtain the cabins in the current solution where the resource sites of the resource type to be deleted are installed. When the resource margins of all parking spaces that can be guaranteed by each cabin are greater than 1, it means that the resource sites of the resource type to be deleted installed in the cabin can be deleted, and the resource site numbers of the resource sites are recorded. Randomly select a cabin from all cabins where resource sites that can be deleted are located, and delete the resource sites installed in the cabin; When there are no resource sites that can be deleted for all resource types, the current solution cannot generate a feasible neighborhood solution in the deletion neighborhood, and the current solution is transferred to the next neighborhood.

4. The method according to any one of claims 1 or 3, characterized in that: The steps to construct an exchange neighborhood include: Randomly select two resource types, select a cabin number corresponding to a resource site that can be deleted from the two resource types respectively, and exchange the cabin number; When there are no exchangeable cabins, the current solution cannot generate a feasible neighborhood solution in the exchange neighborhood, and the current solution is transferred to the next neighborhood.

5. The method according to any one of claims 1 or 3, characterized in that: The steps to build the reset neighborhood include: Obtain the cabin number corresponding to the resource site that can be deleted in each resource type, delete the resource site of the cabin corresponding to the cabin number, and search for the cabin number that can be deleted again after deleting the resource site each time; Randomly select resource types, delete the resource sites of the resource type described in the current solution, reconfigure resource sites for all parking spaces, increase resource site configurations according to the probability of resource increase, and output feasible neighborhood solutions.

6. An aviation resource site configuration device for an offshore platform, characterized in that: The device comprises: A configuration task acquisition module is used to obtain the resource type of the resource site, the parking space set corresponding to the parking space, and the cabin set corresponding to the cabin according to the preset aviation resource site configuration tasks; the cabin can be installed with a resource site of any resource type; An upper model construction module is used to take the resource type and quantity of the cabin installation resource site as decision variables, obtain the upper constraint conditions to be satisfied by the decision variables according to the resource type of the resource site, the parking space set and the cabin set, and construct the resource site configuration layer according to the upper constraint conditions with the lowest cabin occupancy percentage as the upper target; the upper constraint conditions include guarantee scope constraint, one-stop guarantee constraint and resource reachability constraint; The lower-level model building module is used to build the flight support planning layer based on the pre-set process flow constraints, process support resource constraints and transfer timing constraints, with the shortest fleet support completion time as the lower-level goal; A configuration result output module is used to construct a resource configuration-guarantee planning model according to the resource site configuration layer and the flight guarantee planning layer, solve the resource configuration-guarantee planning model, and obtain the aviation resource site configuration result; The configuration result output module is also used to calculate the initial solution of the resource configuration-security planning model, and obtain the upper objective function value and the lower objective function value of the initial solution according to the initial solution, and store the initial solution in the non-dominated solution set; sequentially search for the feasible neighborhood solution of the initial solution in the pre-constructed insertion neighborhood, deletion neighborhood, exchange neighborhood and reset neighborhood; calculate the upper objective function value and the lower objective function value of the feasible neighborhood solution, and when the feasible neighborhood solution and the current solution do not dominate each other, update the current solution to the feasible neighborhood solution, and store the feasible neighborhood solution in the non-dominated solution. The solution set is selected and iterative search is performed in the current neighborhood until the iteration termination condition is met, and the search is transferred to the next neighborhood. When all areas are searched, the aviation resource site configuration result is output; when the feasible neighborhood solution and the initial solution dominate each other, the acceptance probability of the simulated annealing algorithm is obtained according to the upper objective function value and the lower objective function value of the initial solution and the upper objective function value and the lower objective function value of the feasible neighborhood solution. When the generated random number is less than the acceptance probability, the current solution is updated to a feasible neighborhood solution, and iterative operation is performed. After the maximum number of iterations is reached, the solution is transferred to the next neighborhood. Move to the next neighborhood search, and when all fields are searched, output the aviation resource site configuration result; the step of calculating the initial solution of the resource configuration-security planning model includes: initializing the solution of the resource configuration-security planning model, the solution is a row vector with a length of the number of cabins with configurable resource sites; when the resource type number is not greater than the length of the resource type set corresponding to the resource type, if the p-th parking position is not covered by the k-th resource site, randomly select a cabin without a resource site installed, install the k-th resource site, and make the protection range of the cabin without a resource site installed after the k-th resource site is installed to cover the p-th parking position, where p represents the parking position number and k represents the resource type number; when all current parking positions can meet the one-stop protection requirements, generate a random number, and when the random number is less than the resource increase probability, randomly install a type of resource site for the cabin without a resource site installed, and obtain the minimum resource configuration coding scheme of the solution; the minimum resource configuration coding scheme can meet the one-stop protection conditions of each parking position; according to the minimum resource configuration coding scheme, output the initial solution of the resource configuration-security planning model; The calculation steps of the upper layer objective function value and the lower layer objective function value include: According to the minimum resource configuration coding scheme, a set of resource sites corresponding to each resource type and resource accessibility variables between each resource site and each parking space are obtained. According to the set of resource sites with the same resource type and the accessibility variables, a resource site layout scheme is obtained. The resource site configuration layer transmits the resource site layout scheme to the flight support planning layer, and uses the scheduling algorithm to solve the first goal to obtain the fleet support completion time. According to the number of resource sites with the same resource type and the number of cabins that can be configured with resource sites, the second goal is solved to obtain the cabin occupancy percentage: Where k represents the resource type number, k∈Ke, Ke represents the resource type, |Le k | represents the number of resource sites of the kth category, |C S | represents the number of cabins at the configurable resource site; the lower objective function value is obtained according to the completion time of the fleet guarantee, and the upper objective function value is obtained according to the cabin occupancy percentage; The upper model construction module is further used to calculate the distance between the cabin in the cabin set and the parking space in the parking space set, and according to the distance not exceeding the pipeline length of the resource site type installed in the cabin, the protection range constraint is obtained as follows: Among them, the position coordinates of the pth parking space are The position coordinates of the jth cabin are L k represents the pipeline length of the k-th resource site, k∈Ke, Ke represents the resource type set, p∈P S , P S is the parking stand set, P S ={1,2,…,|P S },|P S | is the number of parking spaces, j∈C S , C S For the cabin collection, C S ={1,2,…,|C S |},|C S | represents the number of cabins at the configurable resource site, ρ pjk =1 means that if the jth cabin is equipped with the kth resource station, the protection range of the kth resource station can cover the pth guaranteed parking space; the resource type and quantity of the resource station installed in the cabin are taken as decision variables, and the decision variables are constrained according to the protection range of each parking space in all resource station types, and the one-stop protection constraint is obtained as follows: The decision variables are: X jk ∈{0,1} Among them, X jk =1 means that the kth resource station is installed in the jth cabin, Indicates the number of resource sites that can be installed in the cabin; according to the resource type of the resource site installed in the cabin, a set of resource sites that install the same resource type is obtained; according to the guarantee scope constraint, the decision variable and the set of resource sites that install the same resource type, the resource reachability constraint is obtained as follows: in, is the resource accessibility variable, ρ pjk is a resource type variable, X jk is the upper decision variable, Le k is the k-th resource site set, l is the resource site number in the k-th resource site set, l∈Le k ,|Le k | represents the number of resource sites of the kth category, It means that the protection range of the lth resource site of the kth category can cover the pth guaranteed parking space.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

Images