Methods, devices, equipment, media, and products for combined deployment of different salt cavern gas storage well types.

Abstract

This invention provides a method, apparatus, equipment, medium, and product for the combined deployment of different salt cavern gas storage well types. The method includes: generating the center point of at least one candidate salt cavern cavity within the target storage area; selecting a well type unit from a predefined well type unit library as the dominant well type unit applied to the target storage area, and converting the strategic intent into optimization objectives and corresponding constraints as configuration information for the well type deployment strategy; characterizing the well type deployment strategy using a three-layer coding structure based on the center points of each candidate salt cavern cavity, and searching and iterating the three-layer coding structure using a hybrid heuristic search strategy based on the configuration information of the well type deployment strategy to determine the target well type deployment strategy for the target storage area. Using this method, a highly flexible, adaptive, and adaptable combined deployment of salt cavern gas storage well types can be achieved, fully adapting to irregular ground boundaries and maximizing the utilization of underground space.

Description

Technical Field

[0001] This invention relates to the field of underground energy storage technology, and in particular to a method, apparatus, equipment, medium and product for the combined deployment of different salt cavern gas storage well types. Background Technology

[0002] Salt cavern gas storage is a critical infrastructure for ensuring energy security. An ideal site requires thick, pure layers of salt rock underground, along with an open and regular surface to facilitate the deployment of a regular well network. However, in actual site selection, ideal open areas are very limited. Restricted by existing surface obstacles such as highways, railways, rivers, and residential areas, the boundaries of available surface areas for storage are often highly irregular, severely limiting the layout of well cavities and resulting in a large amount of usable underground salt rock space remaining unused due to surface constraints.

[0003] Existing well placement methods for salt cavern gas storage facilities primarily focus on the uniformity and mechanical stability of underground salt layers, generally employing regular well patterns such as equilateral triangles and squares. However, these methods exhibit significant drawbacks when faced with the prevalent irregular surface boundaries in reality: regular well patterns struggle to efficiently fill irregular storage areas, resulting in the waste of substantial underground salt rock space in marginal areas and low utilization of surface land resources.

[0004] Therefore, there is an urgent need for a technical solution that can break through the constraints of regular well layout and can be "customized" for intelligent deployment according to irregular ground boundaries, so as to maximize the utilization of underground space resources in a limited and irregular well construction area. Summary of the Invention

[0005] This invention provides a method, apparatus, equipment, medium, and product for the combined deployment of salt cavern gas storage well types based on different salt cavern gas storage well types. This achieves highly flexible, highly adaptive salt cavern gas storage well type combined deployment that can fully adapt to irregular ground boundaries and maximize the utilization of underground space.

[0006] Firstly, this embodiment provides a combined deployment method based on different salt cavern gas storage well types, the method comprising:

[0007] Generate the center point of at least one candidate salt cavern cavity within the target reservoir construction area;

[0008] Select a well type unit from the predefined well type unit library as the dominant well type unit applied to the target reservoir construction area, and convert the strategy intent into optimization objectives and corresponding constraints as configuration information for the well type deployment strategy. The optimization objective is to maximize the proportion of the number of salt caverns controlled by the dominant well type unit to the total number of salt caverns in the target reservoir construction area.

[0009] Based on the center point of each candidate salt cavern cavity, a three-layer coding structure is used to characterize the well deployment strategy. Based on the configuration information of the well deployment strategy, a hybrid heuristic search strategy is used to search and iterate the three-layer coding structure to determine the target well deployment strategy for the target reservoir area.

[0010] Secondly, this embodiment provides a combined deployment device based on different salt cavern gas storage well types, the device comprising:

[0011] The cavity determination module is used to generate the center point of at least one candidate salt cavern cavity within the target reservoir construction area;

[0012] The strategy deployment module is used to select a well type unit from a predefined well type unit library as the dominant well type unit applied to the target reservoir construction area, and convert the strategy intent into optimization objectives and corresponding constraints as configuration information for the well type deployment strategy. The optimization objective is to maximize the proportion of the number of salt caverns controlled by the dominant well type unit to the total number of salt caverns in the target reservoir construction area.

[0013] The strategy optimization module is used to characterize the well deployment strategy using a three-layer coding structure based on the center point of each candidate salt cavern cavity, and to search and iterate the three-layer coding structure using a hybrid heuristic search strategy based on the configuration information of the well deployment strategy, so as to determine the target well deployment strategy for the target reservoir area.

[0014] Thirdly, this embodiment provides an electronic device, including:

[0015] At least one processor; and

[0016] A memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to execute the combined deployment method based on different salt cavern gas storage well types according to any embodiment of the present invention.

[0018] Fourthly, this embodiment provides a computer-readable storage medium storing computer instructions that cause a processor to execute and implement the combined deployment method based on different salt cavern gas storage well types as described in any embodiment of the present invention.

[0019] Fifthly, embodiments of the present invention also provide a computer program product, the computer program product including a computer program, which, when executed by a processor, implements the combined deployment method based on different salt cavern gas storage well types as described in any embodiment of the present invention.

[0020] This invention provides a method, apparatus, equipment, medium, and product for the combined deployment of different salt cavern gas storage well types. The method includes: generating the center point of at least one candidate salt cavern cavity within the target storage area; selecting a well type unit from a predefined well type unit library as the dominant well type unit applied to the target storage area, and converting the strategic intent into optimization objectives and corresponding constraints as configuration information for the well type deployment strategy; characterizing the well type deployment strategy using a three-layer coding structure based on the center points of each candidate salt cavern cavity, and searching and iterating the three-layer coding structure using a hybrid heuristic search strategy based on the configuration information of the well type deployment strategy to determine the target well type deployment strategy for the target storage area. This technical solution overcomes the shortcomings of existing salt cavern gas storage well placement schemes, such as rigidity, difficulty in adapting to complex surface boundaries, and low underground space utilization. It provides a highly flexible, adaptable, and efficient salt cavern gas storage well type combined deployment method that can fully adapt to irregular surface boundaries and maximize the utilization of underground space. It elevates the deployment design from the operation of a single cavity to a process of overall optimization and combination of different types of development units. By constructing a modular deployment system for different salt cavern gas storage well types, integrating multi-layer coding and hybrid search mechanisms, and utilizing intelligent optimization algorithms, synchronous and integrated optimization of well location, well type, and well site is achieved. This enables adaptive matching and collaborative optimization of well layout under complex surface constraints, thereby improving the utilization rate of salt rock space within the storage area and significantly enhancing the efficiency of well placement scheme design.

[0021] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a flowchart illustrating a combined deployment method for different salt cavern gas storage well types provided in Embodiment 1 of the present invention.

[0024] Figure 2A schematic diagram of a single-well, single-cavity well and its surface projection;

[0025] Figure 3 This is a schematic diagram of a convection cavity well and its ground projection.

[0026] Figure 4 A schematic diagram of a three-cavity cluster well and its ground projection;

[0027] Figure 5 This is a flowchart illustrating another method for combined deployment of different salt cavern gas storage well types provided in Embodiment 2 of the present invention.

[0028] Figure 6 This is a deployment diagram illustrating the combined deployment method of different salt cavern gas storage well types using this scheme;

[0029] Figure 7 This is a deployment diagram of a traditional regular well layout scheme;

[0030] Figure 8 This is a schematic diagram of a combined deployment device based on different salt cavern gas storage well types provided in Embodiment 3 of the present invention;

[0031] Figure 9 This is a schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention. Detailed Implementation

[0032] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0033] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0034] Example 1

[0035] Figure 1 This is a flowchart illustrating a combined deployment method for salt cavern gas storage well types based on different salt cavern morphologies, provided in Embodiment 1 of the present invention. This method is applicable to the combined deployment of salt cavern gas storage well types based on different salt cavern morphologies. This method can be executed by a combined deployment device based on different salt cavern gas storage well types. This combined deployment device based on different salt cavern gas storage well types can be implemented in hardware and / or software and is generally integrated into electronic equipment.

[0036] like Figure 1 As shown, the combined deployment method based on different salt cavern gas storage well types provided in this embodiment may specifically include the following steps:

[0037] S101. Generate the center point of at least one candidate salt cavern cavity within the target reservoir area.

[0038] Specifically, the target storage area can be understood as the region where a salt cavern gas storage facility will be built. In this embodiment, the irregular ground boundary of the target storage area, as well as the locations and safety buffer zones of all ground obstacles within the target storage area, are obtained and converted into computer-recognizable boundary constraints. Within the defined boundary constraints, a series of candidate salt cavern center points that meet the basic distribution requirements are generated.

[0039] S102. Select a well type unit from the predefined well type unit library as the dominant well type unit applied to the target reservoir construction area, and convert the strategy intent into optimization objectives and corresponding constraints as configuration information for the well type deployment strategy. The optimization objective is to maximize the proportion of the number of salt caverns controlled by the dominant well type unit to the total number of salt caverns in the target reservoir construction area.

[0040] To address the significant problem of existing regular well placement methods being unable to adapt to irregular surface boundaries and resulting in low utilization of salt rock space, this embodiment abandons the traditional design approach centered on fixed regular well networks and proposes a new intelligent deployment paradigm "based on modular combination and dynamic strategy configuration." The core of this paradigm lies in introducing the concepts of "differentiated spacing constraints" and "development units," elevating deployment design from the operation of individual cavities to a process of overall optimization and combination of different types of development units. It allows designers to proactively select and execute corresponding well deployment strategies based on specific project priorities (such as maximum land intensity, minimum initial investment, and strongest operational flexibility), thereby generating globally optimal or near-optimal solutions.

[0041] In this embodiment, a modular deployment system combining cluster wells, convection cavities, and single-well single-cavity configurations is constructed, and intelligent optimization algorithms are integrated to achieve adaptive matching and collaborative optimization of well layout under complex ground constraints. It is an organic whole composed of various types of development units as basic building blocks, collaboratively combined within the same irregular ground boundary. It employs diverse development units, with various structures predefined in the well unit library. The structure consists of at least three types of development units:

[0042] Cluster well unit: This refers to a development module consisting of multiple directional wells drilled from a centralized surface well site, each connected to multiple underground salt cavern cavities. The multiple cavities within this module are considered a collaboratively designed whole, with fixed relative positions and meeting the cavity spacing requirement P1 / D, set at 0.8–1.5, forming a highly compact internal geometric configuration (such as an equilateral triangle with arcs, a quadrilateral, etc.). Convection cavity unit: This refers to the joint development of a salt cavern cavity by two wells, typically one for injection and one for production. Single-well single-cavity unit: This refers to injection and production operations on a single salt cavern cavity using only one well. It should be noted that well unit types include, but are not limited to, the three types mentioned above.

[0043] Spatially Adaptable Unit Layout: The projected positions of the aforementioned development units on the ground do not follow a regular geometric grid, but are precisely configured to adapt to the irregular boundaries of the construction area formed by ground obstacles such as highways, railways, rivers, and residential areas. These units tightly fill the available planar area.

[0044] For example, Figure 2 This is a schematic diagram of a single-well, single-cavity well and its surface projection. Figure 3 This is a schematic diagram of a convection cavity well and its ground projection. Figure 4 The figure shows a schematic diagram of a three-cavity cluster well type and its ground projection. 1 represents a single well single-cavity unit, 2 represents the well site, 3 represents the convection cavity unit, 4 represents the cluster well group unit, 5 represents the width of the pillar between cavities, and 12 represents the cavity diameter.

[0045] Before optimizing the algorithm, it is necessary to first clarify the well deployment strategy, which includes at least three elements: the dominant well unit, the optimization objective, and the constraints, serving as the configuration information for the well deployment strategy. Dominant Well Unit: This specifies the well unit that should be preferentially applied on a large scale under the current design objectives. This dominant well unit can be flexibly selected from a predefined well unit library. Typical strategies include using slave well cluster units as the dominant unit, convection cavity units as the dominant unit, or single-well single-cavity units as the dominant unit. This embodiment is not limited to the above typical units and can be extended to other well units that may be defined in the future. The core is to specify a unit type that needs to be globally maximized. Specifically, a well unit is selected from the predefined well unit library as the dominant well unit applied in the target reservoir construction area.

[0046] The optimization objective refers to quantifying the strategic intent into an algorithm's objective function. This function is directly related to the selection of the dominant well unit. For example, when a slave well cluster unit is dominant, the objective function can be defined as maximizing the proportion of salt caverns controlled by the slave well cluster unit to the total number of salt caverns; when a convection cavity unit is dominant, the objective function can be defined as maximizing the proportion of salt caverns controlled by the convection cavity unit; when a single-well single-cavity unit is dominant, the objective function can be defined as maximizing the proportion of salt caverns controlled by the single-well single-cavity unit; if other well units are introduced as dominant, the corresponding quantification objective is defined accordingly.

[0047] Constraints refer to the hard boundaries set for the algorithm, and the core constraints include cell spacing requirements, land use requirements for each cell well site, and other constraints such as obstacle avoidance buffer zones.

[0048] Preferably, the constraints include: internal constraints of the unit, external constraints of the unit, and other constraints. The other constraints include at least that all well sites meet the minimum working area requirement and that the ground projection of any salt cavern cavity must not intrude into the safety buffer zone.

[0049] In this embodiment, a hierarchical safety spacing system is adopted. The key to this structure lies in the hierarchical spacing constraints: Internal unit spacing: Within a cluster well group unit, the cavities adhere to a tight cavity spacing requirement P1 / D. External unit spacing: Between different development units, such as between one cluster well group unit and another, or between a cluster well group unit and a single-well single-cavity unit, a more stringent unit spacing requirement P2 / D is followed, set to 1.5–2.5, to ensure long-term overall stability between different units.

[0050] S103. Based on the center point of each candidate salt cavern cavity, a three-layer coding structure is used to characterize the well deployment strategy. Based on the configuration information of the well deployment strategy, a hybrid heuristic search strategy is used to search and iterate the three-layer coding structure to determine the target well deployment strategy for the target reservoir area.

[0051] To implement the above strategy, this embodiment constructs a general intelligent optimization algorithm engine. Through deep fusion of multi-layer coding, multi-objective evaluation, and hybrid search, it achieves synchronous and integrated optimization of well location, well type, and well site. In this embodiment, multi-layer coding is implemented using a three-layer chromosome coding structure (i.e., a three-layer coding structure) to achieve a complete and structured description of the deployment scheme. The three-layer coding structure includes a well type allocation layer, a unit topology layer, and a well site-trajectory association layer. The well type allocation layer identifies the well type of each candidate cavity. The unit topology layer, for cluster well groups, defines the unit number to which it belongs and the fixed topological relationships between internal cavities, such as standard geometric configurations. The well site-trajectory association layer, through a sparse association matrix, encodes the geographical coordinates of the well site and the set of wellheads it serves. Based on the location and quantity of the well site and the anti-collision relationship of the well trajectory, it achieves collaborative coding and integrated optimization of surface facilities and underground well locations.

[0052] In this embodiment, a hybrid heuristic search strategy, namely a hybrid optimization framework combining global exploration using genetic algorithms, local enhancement using simulated annealing, and tabu search memory guidance, is employed to search and iterate over the three-layer coding structure. This achieves efficient and stable searching of complex solution spaces, exhibiting fast solution speed and good convergence. Once the algorithm converges, the optimal chromosome is decoded, outputting the final optimized deployment scheme as the target well type deployment strategy. This is equivalent to decoding the optimal three-layer coding structure. Since the three-layer coding structure includes a well type allocation layer, a unit topology layer, and a well site-trajectory association layer, decoding it allows us to obtain the well type of each candidate cavity; for cluster well groups, it obtains the unit number to which it belongs and the fixed topological relationships between internal cavities; as well as the geographical coordinates of the well site and the set of wellheads it serves. From this, the location, number, and collision avoidance relationships of the well site's trajectory can be deduced. These can serve as the final target well type deployment strategy for subsequent combined deployment of salt cavern gas storage well types.

[0053] In this embodiment, by constructing a complete design system of "modular combination - strategic deployment - intelligent optimization," an upgrade from traditional experience-based well placement to a customizable, computable, and globally optimized intelligent decision-making mode is achieved. This method decomposes the complex well placement problem into two levels: modular unit design and global collaborative optimization. It allows designers to flexibly select the dominant well type strategy according to engineering objectives and drives intelligent algorithms to automatically find the optimal solution.

[0054] The aforementioned technical solution overcomes the shortcomings of existing salt cavern gas storage well placement schemes, such as rigidity, difficulty in adapting to complex surface boundaries, and low underground space utilization. It provides a highly flexible, adaptive method for combining and deploying salt cavern gas storage well types, fully adapting to irregular surface boundaries and maximizing underground space utilization. The deployment design is elevated from operating on individual cavities to a process of overall optimization and combination of different types of development units. By constructing a unitized deployment system for different salt cavern gas storage well types, integrating multi-layer coding and hybrid search mechanisms, and utilizing intelligent optimization algorithms, synchronous and integrated optimization of well location, well type, and well site is achieved. This enables adaptive matching and collaborative optimization of well layout under complex surface constraints, thereby improving the utilization rate of salt rock space within the storage area and significantly enhancing the efficiency of well placement scheme design.

[0055] Example 2

[0056] Figure 5 This is a flowchart illustrating another method for combined deployment of different salt cavern gas storage well types provided in Embodiment 2 of the present invention. This embodiment is a further optimization of the above embodiment. In this embodiment, the following optimizations are made: "generating the center point of at least one candidate salt cavern cavity within the target storage area", "characterizing the well type deployment scheme using a three-layer coding structure based on the center point of each candidate salt cavern cavity", and "searching and iterating the three-layer coding structure using a hybrid heuristic search strategy based on the configuration information of the well type deployment strategy to determine the target well type deployment strategy for the target storage area".

[0057] like Figure 5 As shown in the figure, this embodiment 2 provides a combined deployment method based on different salt cavern gas storage well types, which specifically includes the following steps:

[0058] S201. Determine the geometric constraints corresponding to the target reservoir construction area based on the ground boundary of the target reservoir construction area, the location of all ground obstacles in the target reservoir construction area, and the reserved safety buffer zone.

[0059] In this embodiment, the irregular ground boundary of the target reservoir construction area, as well as the location and safety buffer range of all ground obstacles within the target reservoir construction area, are obtained and converted into geometric constraints that can be recognized by a computer.

[0060] S202. Based on the geometric constraints corresponding to the target reservoir area, generate the center points of multiple candidate salt cavern cavities that meet the distribution requirements.

[0061] In this embodiment, within the geometric constraints defined in the above steps, i.e., the boundary constraints, a series of candidate salt cavern center points that meet the basic distribution requirements are generated.

[0062] S203. Select a well type unit from the predefined well type unit library as the dominant well type unit applied to the target reservoir construction area, and convert the strategy intent into optimization objectives and corresponding constraints as configuration information for the well type deployment strategy. The optimization objective is to maximize the proportion of the number of salt caverns controlled by the dominant well type unit to the total number of salt caverns in the target reservoir construction area.

[0063] S204. Construct a vector in which each element represents the well-shaped unit to which each candidate salt cavern cavity corresponding to the center point is allocated, as the well-shaped allocation layer.

[0064] In this embodiment, the three-layer coding structure includes a well type allocation layer, a unit topology layer, and a well field-trajectory association layer. First, the well type allocation layer identifies the well type of each candidate cavity. Let the set of candidate cavities be... The three-layer coding structure is as follows:

[0065]

[0066]

[0067] in: Assign layers to well types, indicating the well type to which each candidate cavity belongs; For the first The well type codes for each candidate cavity are as follows: 0 indicates a single well with a single cavity, 1 indicates a convection cavity, and 2 indicates a cluster well.

[0068] S205. Record the multiple candidate salt cavern cavities contained in each cluster well unit as the unit topology layer.

[0069] The second layer is the unit topology layer, which defines the unit number and fixed topological relationships between internal cavities of a cluster well group, such as the standard geometric configuration. For the unit topology layer, define the internal cavity relationships of the cluster well group unit.

[0070] S206. Construct a well site-trajectory association layer with rows representing well sites, columns representing wells, and each element representing the association matrix of a well site providing drilling services to a well.

[0071] Finally, there is the well site-trajectory association layer, which encodes the geographical coordinates of the well site and the set of wellheads it serves through a sparse association matrix, realizing the collaborative coding and integrated optimization of surface facilities and underground well locations. This is the well site-trajectory association layer, used to encode the topology of the well site, well trajectory, and service relationships. It is represented by a matrix, with elements... Indicates well From the well site Drilling is carried out, from which the location and number of well sites and the collision prevention relationship of the well trajectory can be deduced.

[0072] S207. Individuals that satisfy the constraints are randomly generated according to the three-layer coding structure to form an initial population as the current population.

[0073] Specifically, a number of individuals satisfying the basic constraints are randomly generated according to the three-layer coding structure to form an initial population, which is then used as the current population. Each individual corresponds to a well-shaped deployment strategy. For example, 150 individuals satisfying the basic constraints are randomly generated according to the above coding structure to form the initial population.

[0074] S208. Determine the fitness value of each individual in the current population according to the pre-constructed multi-objective dynamic fitness evaluation function, wherein the multi-objective dynamic fitness evaluation function is determined based on the optimization objective in the configuration information of the well-shaped deployment strategy.

[0075] The multi-objective dynamic fitness function integrates multiple engineering objectives and constraints, such as the proportion of dominant well types, estimated cost per unit reservoir capacity, well site concentration index, and spacing penalty, to drive the algorithm search. The proportion of dominant well types is equivalent to the optimization objective in the configuration information of well type deployment strategies included in the multi-objective dynamic fitness function. Specifically, for each individual in the current population, i.e., each well type deployment strategy, it is substituted into the multi-objective dynamic fitness function to calculate its fitness value and comprehensively evaluate its merits.

[0076] S209. Determine whether the current population iteration termination condition is met. The population iteration termination condition includes the number of iterations reaching a threshold or the change in fitness value not exceeding a set fitness threshold.

[0077] The iteration threshold and fitness threshold can be set according to actual conditions. Convergence is determined by checking whether the current iteration count has reached the threshold or whether the change in fitness exceeds the set fitness threshold. For example, the iteration count can be set to 500-1000 generations, or termination can occur when the optimal solution no longer significantly improves over several consecutive generations.

[0078] S210. If not satisfied, a hybrid heuristic search strategy is used to search and iterate the contemporary population, and then the process returns to continue executing the pre-constructed multi-objective dynamic fitness evaluation function to determine the fitness value of each individual in the contemporary population.

[0079] In this embodiment, if the current population iteration termination condition is not met, a hybrid heuristic search strategy is used to search and iterate the current population, and steps S208 and S209 are repeated for iterative optimization.

[0080] As a specific implementation method, the steps of searching and iterating the contemporary population using a hybrid heuristic search strategy can be optimized, including:

[0081] a1) Using a genetic algorithm as a global framework, the current population is evolved through selection, crossover, and mutation operations.

[0082] In this embodiment, a hybrid heuristic search is performed. A genetic algorithm (GA) is used as the global framework, and the population evolves through selection, crossover, and mutation operations. Its adaptive mutation probability is:

[0083]

[0084] in: In the first The actual probability of mutation at generation time; Basic mutation probability; For the first The diversity entropy value of a population is used to measure the degree of difference between individuals in the population. This represents the theoretical maximum value of population diversity entropy; The adjustment coefficient controls the strength of the influence of diversity on the probability of variation.

[0085] b1) After each generation of genetic operations, perform simulated annealing local search on the top 100 elite individuals with the highest fitness values.

[0086] Furthermore, the Simulated Annealing (SA) algorithm is embedded, and a local search is performed on the top-ranked elite individuals in each generation. The probability of them accepting inferior solutions follows the annealing criterion:

[0087]

[0088] in, To accept a poor new solution The probability of; This represents the difference in fitness values ​​between the new and old solutions. For the first The temperature during the local search decreases as the search progresses, and the decrease formula is: .

[0089] c1) Establish a taboo list to avoid duplicate searches, which records well-shaped deployment strategies that have been frequently adjusted in historical iterations but have not brought about improvement.

[0090] Finally, a tabu search (TS) mechanism is used to avoid redundant searches, thus enabling efficient computation. The tabu search mechanism involves creating a tabu list that records well-shaped deployment strategies that have been frequently adjusted recently (e.g., within the past 20 generations) without bringing improvement. In subsequent generations, the algorithm is prohibited from trying these strategies again, effectively escaping local optima traps.

[0091] S211. If satisfied, the well type deployment strategy with the highest fitness value is obtained as the target well type deployment strategy.

[0092] Specifically, if the current population iteration termination condition is met, the well type deployment strategy with the highest fitness value is obtained as the target well type deployment strategy, meaning the algorithm eventually converges to the well type deployment scheme with the highest fitness. After the algorithm converges, the optimal chromosome (i.e., an individual, corresponding to a well type deployment strategy) is decoded, and the final optimized deployment scheme is output as the target well type deployment strategy. This is equivalent to decoding the optimal three-layer coding structure. Since the three-layer coding structure includes a well type allocation layer, a unit topology layer, and a well site-trajectory association layer, decoding it can obtain the well type of each candidate cavity; for cluster well groups, it can obtain the unit number to which it belongs and the fixed topological relationship between the internal cavities; and it can decode the geographical coordinates of the well site, the set of wellheads it serves, etc. From this, the location, number, and anti-collision relationship of the well trajectory can be derived. These can be used as the final target well type deployment strategy for the subsequent combined deployment of salt cavern gas storage well types.

[0093] It should be noted that this embodiment deeply integrates computer-aided design and intelligent optimization algorithms, forming a computable and iterative automatic deployment method. The core of this method lies in employing a multi-layered coding mechanism, a multi-objective dynamic fitness evaluation function, and a hybrid heuristic search strategy. It is worth noting that the optimization algorithm is not limited to a specific type; its core lies in its ability to handle combinatorial optimization problems and accommodate multi-objective constraints, all of which are within the scope of this embodiment.

[0094] The aforementioned technical solution deeply integrates a three-layer coding mechanism, multi-objective dynamic fitness evaluation, and a hybrid heuristic search strategy. By constructing a coding structure that associates well type allocation, unit topology, and well site-trajectory relationships, a dynamic evaluation function integrating the proportion of dominant well types, economic efficiency, and intensification is established. A hybrid optimization framework of "global exploration using genetic algorithm + local enhancement using simulated annealing + tabu search memory guidance" is employed, achieving efficient and stable search of complex solution spaces with fast solution speed and good convergence. It can automatically generate optimized deployment schemes highly adapted to irregular surface reservoir areas. Through the synergistic optimization of the extreme deployment of available reservoir areas and well site locations, it achieves intensive layout of surface space and efficient utilization of salt rock resources. The algorithm-based automatic optimization effectively reduces reliance on human experience, significantly reduces trial-and-error costs and workload in scheme design, and significantly improves design efficiency.

[0095] As an optional embodiment of the present invention, based on the above embodiments, the construction steps of the multi-objective dynamic fitness evaluation function can be optimized, including:

[0096] a2) Determine the optimization objective function value based on the proportion of dominant well types, estimated cost per unit reservoir capacity, well site concentration index, and corresponding dynamic weight coefficients.

[0097] In this embodiment, the dominant well type proportion is used to maximize the proportion of salt cavern cavities controlled by the dominant well type, the unit reservoir capacity estimated cost is used for economic optimization, and the well site concentration index is used to characterize the surface concentration. The optimization objective function value is obtained by summing the results of multiplying the dominant well type proportion, the unit reservoir capacity estimated cost, and the well site concentration index by their respective dynamic weighting coefficients.

[0098] As a specific implementation method, the objective function value can be optimized based on the proportion of dominant well types, estimated cost per unit reservoir capacity, well site concentration index, and corresponding dynamic weighting coefficients. This includes:

[0099] a21) Determine the proportion of the dominant well type based on the number of salt caverns controlled by the dominant well type and the total number of salt caverns in the target reservoir area.

[0100] In this embodiment, the proportion of dominant well types can be expressed as: ,in: The number of salt caverns controlled by the dominant well unit; This represents the total number of salt caverns.

[0101] a22) Determine the estimated cost per unit capacity based on the total designed reservoir capacity of all salt caverns, the total number of wells, the length of surface injection and production pipelines, and the area occupied by the well site.

[0102] In this embodiment, the estimated cost per unit storage capacity can be expressed as:

[0103] , This represents the total design capacity of all salt caverns in the well-type deployment strategy; , This is the cost conversion factor; This refers to the total number of wells in the well deployment strategy; Estimate the length of the surface injection and production pipeline; The area occupied by the well site.

[0104] a23) Determine the well site concentration index based on the variance of the number of service wells in each well site.

[0105] In this embodiment, the well site concentration index can be expressed as: ,in, The variance of the number of wells serving each well site is represented by a smaller value, indicating a more uniform distribution of wells serving each well site and a higher degree of concentration.

[0106] (a24) The sum of the results of multiplying the dominant well type proportion, the estimated cost per unit reservoir capacity, and the well site concentration index by their respective dynamic weight coefficients is used to obtain the value of the optimization objective function.

[0107] In this embodiment, the objective function value can be expressed as: ,in, For the first The dynamic weight coefficients of each objective at the t-th iteration; To optimize the objective function value, factors include the proportion of dominant well types, estimated cost per unit reservoir capacity, and well site concentration index.

[0108] It should be noted that the weighting coefficients of the above indicators... It is not fixed, but rather adaptively adjusted according to the iteration process, realizing the transition of the optimization focus from quickly forming the dominant well layout to a more refined balance between economy and safety:

[0109]

[0110] in, For learning rate, For the target item in the most recent The amount of improvement within a generation.

[0111] b2) Determine the penalty function value based on the spacing penalty, land use penalty, buffer intrusion penalty, and the corresponding fixed weight coefficient.

[0112] In this embodiment, the penalty function value is determined by summing the results of multiplying the spacing penalty, land use penalty, and buffer intrusion penalty by their respective fixed weight coefficients.

[0113] As a specific implementation method, the step of determining the penalty function value based on the spacing penalty, land use penalty, buffer intrusion penalty, and corresponding fixed weight coefficients can be optimized, including:

[0114] b21) Determine the spacing penalty based on the actual distance between the two well-type units and the minimum allowable distance.

[0115] In this embodiment, the spacing penalty can be expressed as: ,in, For the first The and the first The actual distance between the edges of each well-shaped unit; This is the minimum allowable distance between elements calculated based on the element spacing requirement P2 / D.

[0116] b22) Determine the land use penalty based on the minimum footprint required by the well site according to the design and the available area at the actual planned location of the well site.

[0117] In this embodiment, the land use penalty can be expressed as: ,in, For well site Based on the minimum footprint required by the design; For well site The usable area at the actual planned location.

[0118] b23) Determine the buffer intrusion penalty based on the depth of the cavity projection of the candidate salt cavern into the safety buffer and the width of the safety buffer.

[0119] In this embodiment, the buffer intrusion penalty can be expressed as: ,in, The depth to which the candidate salt cavern cavity projection intrudes into the safety buffer zone; The width of the safety buffer.

[0120] (b24) The penalty function value is determined by summing the results of multiplying the spacing penalty, the land use penalty, and the buffer intrusion penalty by their respective fixed weight coefficients.

[0121] In this embodiment, the penalty function value can be expressed as: , For the first Fixed weighting coefficients for each penalty item; The penalties include spacing penalties, land use penalties, and buffer zone intrusion penalties.

[0122] c2) Subtract the penalty function value from the optimization objective function value to obtain the multi-objective dynamic fitness evaluation function.

[0123] In this embodiment, the multi-objective dynamic fitness evaluation function can be expressed as:

[0124]

[0125] in: This is the overall fitness value of the deployment plan; a higher value indicates a better plan. For the first The goal in iteration number 1 Dynamic weighting coefficients for each generation; To optimize the objective function value, factors include the proportion of dominant well types, estimated cost per unit reservoir capacity, and well site concentration index; For the first Fixed weighting coefficients for each penalty item; The penalties include spacing penalties, land use penalties, and buffer zone intrusion penalties.

[0126] The above technical solution specifies the steps for determining the multi-objective dynamic fitness evaluation function, establishes a dynamic evaluation function that integrates the proportion of dominant well types, economy and intensity, and allows designers to actively select and execute the corresponding well type deployment strategy according to the specific priorities of the project, such as the highest land intensity, the lowest initial investment, and the strongest operational flexibility, thereby generating a globally optimal or near-optimal solution.

[0127] To more clearly illustrate the combined deployment method based on different salt cavern gas storage well types provided in this embodiment of the invention, a practical application scenario of a combined deployment based on different salt cavern gas storage well types will be used as an example. For instance, only cluster well group unit 4 is selected as the dominant example among multiple well types for detailed explanation of the invention. This embodiment aims to demonstrate how to use this invention to generate the optimal deployment scheme when the project objective is to maximize surface intensification and overall development efficiency.

[0128] Figure 6 The diagram shows the deployment of this scheme based on the combined deployment method of different salt cavern gas storage well types. 1 represents a single well single cavity unit, 2 represents the well site, 3 represents the convection cavity unit, 4 represents the cluster well group unit, 6 represents the irregular surface storage area, 7 represents the residential area, 8 represents the highway, 9 represents the residential area buffer zone, 10 represents the highway buffer zone, 11 represents the width of the pillar between units, and 12 represents the cavity diameter.

[0129] In a specific application scenario, the target storage area is an irregular ground area 6, which contains several residential areas 7 and a highway 8, forming surface obstacles. These obstacles are surrounded by residential area buffer zones 9 and highway buffer zones 10, which together constitute the areas that must be avoided during deployment.

[0130] The deployment strategy and parameter configuration for this embodiment are as follows:

[0131] 1. Dominant Well Type Unit: Set as a standard three-chamber cluster well group unit 4. That is, during subsequent well location deployment optimization, the algorithm will prioritize the formation and application of this type of unit.

[0132] 2. Optimization Objective: Under the premise of adapting to the irregular ground reservoir area 6, after removing the unusable areas corresponding to the residential area buffer zone 9 and the highway buffer zone 10, within the finally determined usable reservoir construction area, maximize the proportion of salt cavern cavities controlled by all cluster well group units 4 to the total number of cavities. This objective function will directly drive the search direction of the algorithm.

[0133] 3. Constraints:

[0134] 1) Internal constraints of the unit: The predefined standard three-cavity cluster well group unit 4 is used as the basic module. The ratio (P1 / D) of the width of the pillar between the cavities 5 to the diameter of the cavity 12 inside the module is fixed at 1.0, forming a stable approximately equilateral triangle geometric configuration with a circular arc.

[0135] 2) External constraints of the unit: Between any two independent development units, including between cluster well group units 4, between cluster well group unit 4 and single well single cavity unit 1, and between cluster well group unit 4 and convection cavity unit 3, the ratio of the pillar width 11 to the cavity diameter 12 (P2 / D) between the units must not be less than 2.0.

[0136] 3) Other constraints: All well sites 2 must meet the minimum operating area requirements; the ground projection of any cavity must not intrude into the safety buffer zone.

[0137] The algorithm execution and scheme generation in this embodiment are as follows:

[0138] The deployment scheme is optimized and searched using a genetic algorithm. The specific process is as follows:

[0139] 1. Problem coding and population initialization:

[0140] A three-layer coding structure is used to characterize the deployment scheme. Assume that m candidate cavity center points are generated within an irregular ground storage area 6, and the set is [formula missing]. .

[0141] Well-type distribution layer Given a vector of length m ,in , respectively representing the cavity It is assigned as a single-well single-cavity unit 1, a convection cavity unit 3, or a cluster well group unit 4.

[0142] Unit topology layer Used to record the composition of all cluster well units 4. Each unit contains several wells labeled as cluster wells ( The cavity is defined with a predefined fixed spatial topology that satisfies P1 / D=1.0.

[0143] Well Site-Trajectory Association Layer Represented using an incidence matrix. Rows in the matrix represent well sites 2, columns represent wells, and elements... Indicates well site For well By providing drilling services, the location, number, and collision prevention relationships of well site 2 and well trajectory can be deduced.

[0144] Based on the above coding structure, 150 individuals that satisfy the basic constraints are randomly generated to form the initial population.

[0145] 2. Multi-objective dynamic fitness assessment:

[0146] The fitness value is calculated for each individual in the population (i.e., each deployment scheme), and its overall performance is evaluated. The fitness function is designed as follows:

[0147]

[0148] To drive the algorithm to form more cluster well groups 4, the formula is as follows:

[0149]

[0150] To simplify calculations and encourage fewer well sites and shorter surface injection-production pipelines, this embodiment defines:

[0151]

[0152] The well site concentration index is:

[0153]

[0154] Penalties are used to ensure the feasibility of the solution; any violation will reduce fitness. Among them, spacing penalties... The core function is to check the minimum distance between all independent development units, such as between cluster well group units 4, between cluster well group unit 4 and single-well single-cavity unit 1, and between cluster well group unit 4 and convection cavity unit 3. The algorithm calculates the minimum distance between the edges of each pair of units and converts it into a pillar width 11. If the ratio P2 / D of this distance to the cavity diameter 12 is less than the set value of 2.0, a penalty is applied; land use penalty. The main check is whether the actual occupied area of ​​any well site 2 meets the minimum land use requirements for its well type; buffer zone penalty. Used to check whether any cavity ground projection intrudes into residential buffer zone 9 or highway buffer zone 10.

[0155] This embodiment sets the initial weighting coefficient. Every 100 generations of optimization, the weights are automatically fine-tuned based on the improvement of each objective item.

[0156] 3. Hybrid heuristic search and iteration:

[0157] Genetic operations: In each generation, the parent generation is selected using a combination of roulette wheel selection and an elite retention strategy (retaining the top 5 best individuals); single-point crossover is performed with a probability of 0.8; and mutation is performed using an adaptive mutation probability, which increases as the population diversity decreases to avoid premature convergence.

[0158] Simulated Annealing Local Enhancement: After each generation of genetic operations, a local search (SA) is performed on the top 15% of elite individuals based on fitness. The neighborhood operation of SA focuses on fine-tuning: the location of a well site 2 is randomly adjusted within a ±50-meter range; attempts are made to assign a marginal single-well single-cavity unit 1 or convection cavity unit 3 to a neighboring cluster well unit 4. SA operates probabilistically... Accepting inferior solutions, temperature The decay occurs as the local search progresses.

[0159] Tabu Search Guidance: A taboo list is established to record well-shaped cell layout patterns that have been frequently adjusted recently (e.g., within the past 20 generations) without bringing improvement. In subsequent generations, the algorithm is prohibited from trying these patterns again, thus effectively escaping the trap of local optima.

[0160] Iterative convergence: Repeat the above evaluation and search process. Set the maximum number of iterations to 800 generations and monitor the optimal fitness value. If the improvement of the optimal solution is less than 0.1% for 50 consecutive generations, it is considered convergent, and the optimization is terminated.

[0161] 4. Deployment Plan and Results

[0162] The final optimized deployment scheme is as follows: Figure 6As shown, cluster well unit 4 is the dominant well type, occupying all large, continuous open areas within the reservoir area and controlling over 80% of the salt cavern cavities. The few peripheral areas that cannot be incorporated into cluster well unit 4 are automatically assigned to single-well single-cavity unit 1 or convection cavity unit 3, further filling the remaining space in the irregular surface reservoir area 6, while maintaining a strict P2 / D safety distance from the main cluster well unit 4. Simultaneously, the number of well sites 2 is minimized, and the surface injection-production pipeline network is most concentrated, significantly saving land resources and surface engineering costs.

[0163] Compared with the traditional regular well layout using only a single well single cavity unit 1 for the same irregular surface reservoir area 6, the advantages of the present invention can be quantified. Figure 7 This is a deployment diagram of a traditional regular well layout scheme, such as... Figure 7 As shown, 1 represents a single-well, single-cavity unit; 6 represents an irregular surface reservoir area; 7 represents a residential area; 8 represents a highway; 9 represents a residential area buffer zone; 10 represents a highway buffer zone; and 11 represents the width of the pillar between units. The area of ​​the irregular surface reservoir area 6 is 7.524 square kilometers. The diameter of each circular cavity is 80m. The major and minor axes of the ellipse projected by the convection cavity are 60m and 40m, respectively. Under the same surface constraints, the scheme generated by the cluster well group unit 4 as the dominant well type in this invention can deploy 62 wells, with a planar utilization rate of 4.24%. In contrast, the traditional scheme using only the single-well, single-cavity unit 1 with regular well layout can only deploy 43 wells, with a planar utilization rate of 2.87%. The scheme of this invention can increase the effective number of wells by about 44% and the planar utilization rate by about 48%, greatly improving the utilization efficiency of underground salt rock resources. The present invention requires only 24 well sites 2, while the traditional method requires 43 well sites 2, reducing the number of well sites 2 by approximately 44%. This not only significantly saves land resources but also allows for a highly concentrated layout of the surface injection and production pipeline network, significantly reducing the construction cost and complexity of surface engineering. Preliminary estimates suggest that by reducing the number of well sites and pipeline length, the overall surface engineering investment of the present invention can be reduced by approximately 15%-20% compared to the traditional method, demonstrating significant economic benefits. Table 1 compares the traditional method with the present invention, listing the comparison of parameters such as unit spacing, cavity spacing, and number of well sites, which will not be described in detail here.

[0164]

[0165] Example 3

[0166] Figure 8 This is a schematic diagram of a combined deployment device based on different salt cavern gas storage well types provided in Embodiment 3 of the present invention. This device is applicable to the combined deployment of salt cavern gas storage well types based on different salt cavern morphologies. This combined deployment device based on different salt cavern gas storage well types can be implemented in hardware and / or software, and is generally integrated into electronic equipment. For example... Figure 8 As shown, the device includes: a cavity determination module 31, a strategy deployment module 32, and a strategy optimization module 33, wherein,

[0167] The cavity determination module 31 is used to generate the center point of at least one candidate salt cavern cavity within the target reservoir area;

[0168] The strategy deployment module 32 is used to select a well type unit from a predefined well type unit library as the dominant well type unit applied to the target reservoir construction area, and convert the strategy intent into optimization objectives and corresponding constraints as configuration information of the well type deployment strategy. The optimization objective is to maximize the proportion of the number of salt caverns controlled by the dominant well type unit to the total number of salt caverns in the target reservoir construction area.

[0169] The strategy optimization module 33 is used to characterize the well deployment strategy using a three-layer coding structure based on the center point of each candidate salt cavern cavity, and to search and iterate the three-layer coding structure using a hybrid heuristic search strategy based on the configuration information of the well deployment strategy, so as to determine the target well deployment strategy for the target reservoir area.

[0170] The aforementioned technical solution overcomes the shortcomings of existing salt cavern gas storage well placement schemes, such as rigidity, difficulty in adapting to complex surface boundaries, and low underground space utilization. It provides a highly flexible, adaptive method for combining and deploying salt cavern gas storage well types, fully adapting to irregular surface boundaries and maximizing underground space utilization. The deployment design is elevated from operating on individual cavities to a process of overall optimization and combination of different types of development units. By constructing a unitized deployment system for different salt cavern gas storage well types, integrating multi-layer coding and hybrid search mechanisms, and utilizing intelligent optimization algorithms, synchronous and integrated optimization of well location, well type, and well site is achieved. This enables adaptive matching and collaborative optimization of well layout under complex surface constraints, thereby improving the utilization rate of salt rock space within the storage area and significantly enhancing the efficiency of well placement scheme design.

[0171] Optionally, the cavity determination module 31 is specifically used for:

[0172] Based on the ground boundary of the target reservoir construction area, the location of all ground obstacles within the target reservoir construction area, and the reserved safety buffer zone, determine the geometric constraints corresponding to the target reservoir construction area.

[0173] Based on the geometric constraints corresponding to the target reservoir area, the center points of multiple candidate salt cavern cavities that meet the distribution requirements are generated.

[0174] Optionally, the constraints include: internal constraints of the unit, external constraints of the unit, and other constraints. The other constraints include at least that all well sites meet the minimum working area requirement and that the ground projection of any salt cavern cavity must not intrude into the safety buffer zone.

[0175] Optionally, the strategy optimization module 33 includes a coding construction unit for:

[0176] Construct a vector in which each element represents the well-shaped unit to which each candidate salt cavern cavity corresponding to the center point is assigned, as the well-shaped allocation layer;

[0177] Record the multiple candidate salt cavern cavities contained in each cluster well unit as the unit topology layer;

[0178] Construct a well site-trajectory association layer with rows representing well sites, columns representing wells, and each element representing the association matrix of a well site providing drilling services to a well.

[0179] Optionally, the strategy optimization module 33 includes an iterative optimization unit, specifically used for:

[0180] Individuals that satisfy the constraints are randomly generated according to the three-layer coding structure to form the initial population as the current population;

[0181] The fitness value of each individual in the current population is determined based on a pre-constructed multi-objective dynamic fitness evaluation function, wherein the multi-objective dynamic fitness evaluation function is determined based on the optimization objective in the configuration information of the well-shaped deployment strategy.

[0182] Determine whether the current population iteration termination condition is met. The population iteration termination condition includes the number of iterations reaching a threshold or the change in fitness value not exceeding a set fitness threshold.

[0183] If the conditions are not met, a hybrid heuristic search strategy is used to search and iterate the current population, and then the process is returned to continue executing the pre-constructed multi-objective dynamic fitness evaluation function to determine the fitness value of each individual in the current population.

[0184] If the conditions are met, the well deployment strategy with the highest fitness value is obtained as the target well deployment strategy.

[0185] Optionally, the device also includes a function building module for:

[0186] The optimization objective function value is determined based on the proportion of dominant well types, estimated cost per unit reservoir capacity, well site concentration index, and corresponding dynamic weighting coefficients.

[0187] The penalty function value is determined based on the spacing penalty, land use penalty, buffer intrusion penalty, and the corresponding fixed weight coefficients;

[0188] The value of the optimization objective function is subtracted from the value of the penalty function to obtain the multi-objective dynamic fitness evaluation function.

[0189] Optionally, the function construction module is used to determine the optimization objective function value based on the proportion of dominant well types, estimated cost per unit reservoir capacity, well site concentration index, and corresponding dynamic weighting coefficients, including:

[0190] The proportion of the dominant well type is determined based on the number of salt caverns controlled by the dominant well type and the total number of salt caverns in the target reservoir area;

[0191] The estimated cost per unit capacity is determined based on the total designed capacity of all salt caverns, the total number of wells, the length of surface injection and production pipelines, and the area occupied by the well site.

[0192] The well site concentration index is determined based on the variance of the number of service wells in each well site;

[0193] The optimization objective function value is obtained by summing the results of multiplying the dominant well type proportion, the estimated cost per unit reservoir capacity, and the well site concentration index by their respective dynamic weighting coefficients.

[0194] Optionally, the function construction module is used to determine the penalty function value based on the spacing penalty, land use penalty, buffer intrusion penalty, and corresponding fixed weight coefficients, including:

[0195] The spacing penalty is determined based on the actual distance between the two well-type units and the minimum allowable distance;

[0196] The land penalty is determined based on the minimum footprint required by the well site according to the design and the available area at the actual planned location of the well site;

[0197] The buffer intrusion penalty is determined based on the depth of the cavity projection of the candidate salt cavern into the safety buffer and the width of the safety buffer.

[0198] The penalty function value is determined by summing the results of multiplying the spacing penalty, the land use penalty, and the buffer intrusion penalty by their respective fixed weight coefficients.

[0199] Optionally, the iterative optimization unit is used to perform a search and iteration process on the current population using a hybrid heuristic search strategy, including:

[0200] Using a genetic algorithm as the global framework, the current population is evolved through selection, crossover, and mutation operations.

[0201] After each generation of genetic operations, simulated annealing local search is performed on the top 100 elite individuals with the highest fitness values.

[0202] To avoid duplicate searches, a taboo list is created, which records well-shaped deployment strategies that have been frequently adjusted in historical iterations but have not brought about improvement.

[0203] The combined deployment device based on different salt cavern gas storage well types provided in the embodiments of the present invention can execute the combined deployment method based on different salt cavern gas storage well types provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0204] Example 4

[0205] Figure 9 This is a schematic diagram of an electronic device provided in Embodiment 4 of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0206] like Figure 9 As shown, the electronic device 40 includes at least one processor 41 and a memory, such as a read-only memory (ROM) 42 or a random access memory (RAM) 43, communicatively connected to the at least one processor 41. The memory stores computer programs executable by the at least one processor. The processor 41 can perform various appropriate actions and processes based on the computer program stored in the ROM 42 or loaded from storage unit 48 into the RAM 43. The RAM 43 may also store various programs and data required for the operation of the electronic device 40. The processor 41, ROM 42, and RAM 43 are interconnected via a bus 44. An input / output (I / O) interface 45 is also connected to the bus 44.

[0207] Multiple components in electronic device 40 are connected to I / O interface 45, including: input unit 46, such as keyboard, mouse, etc.; output unit 47, such as various types of monitors, speakers, etc.; storage unit 48, such as disk, optical disk, etc.; and communication unit 49, such as network card, modem, wireless transceiver, etc. Communication unit 49 allows electronic device 40 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0208] Processor 41 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 41 include, but are not limited to, central processing unit (CPU), graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 41 performs the various methods and processes described above, such as combined deployment methods based on different salt cavern gas storage well types.

[0209] In some embodiments, the combined deployment method based on different salt cavern gas storage well types can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 48. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 40 via ROM 42 and / or communication unit 49. When the computer program is loaded into RAM 43 and executed by processor 41, one or more steps of the combined deployment method based on different salt cavern gas storage well types described above can be performed. Alternatively, in other embodiments, processor 41 can be configured to perform the combined deployment method based on different salt cavern gas storage well types by any other suitable means (e.g., by means of firmware).

[0210] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0211] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0212] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0213] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0214] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0215] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0216] This invention also provides a computer program product, including a computer program that, when executed by a processor, implements the combined deployment method based on different salt cavern gas storage well types as provided in any embodiment of this invention.

[0217] In implementing a computer program product, computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof. These programming languages ​​include, but are not limited to, object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0218] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0219] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method of combined deployment based on different salt cavern gas storage well types, characterized in that, include: Generate the center point of at least one candidate salt cavern cavity within the target reservoir construction area; Select a well type unit from the predefined well type unit library as the dominant well type unit applied to the target reservoir construction area, and convert the strategy intent into optimization objectives and corresponding constraints as configuration information for the well type deployment strategy. The optimization objective is to maximize the proportion of the number of salt caverns controlled by the dominant well type unit to the total number of salt caverns in the target reservoir construction area. Based on the center point of each candidate salt cavern cavity, a three-layer coding structure is used to characterize the well deployment strategy. Based on the configuration information of the well deployment strategy, a hybrid heuristic search strategy is used to search and iterate the three-layer coding structure to determine the target well deployment strategy for the target reservoir area.

2. The method of claim 1, wherein, The process of generating at least one candidate salt cavern cavity at its center point within the target reservoir area includes: Based on the ground boundary of the target reservoir construction area, the location of all ground obstacles within the target reservoir construction area, and the reserved safety buffer zone, determine the geometric constraints corresponding to the target reservoir construction area. Based on the geometric constraints corresponding to the target reservoir area, the center points of multiple candidate salt cavern cavities that meet the distribution requirements are generated.

3. The method of claim 1, wherein, The constraints include: internal constraints of the unit, external constraints of the unit, and other constraints. The other constraints include at least that all well sites meet the minimum working area requirement and that the ground projection of any salt cavern cavity must not intrude into the safety buffer zone.

4. The method of claim 1, wherein, The step of characterizing the well deployment scheme using a three-layer coding structure based on the center point of each candidate salt cavern cavity includes: Construct a vector in which each element represents the well-shaped unit to which each candidate salt cavern cavity corresponding to the center point is assigned, as the well-shaped allocation layer; Record the multiple candidate salt cavern cavities contained in each cluster well unit as the unit topology layer; Construct a well site-trajectory association layer with rows representing well sites, columns representing wells, and each element representing the association matrix of a well site providing drilling services to a well.

5. The method of claim 1, wherein, The step of determining the target well deployment strategy for the target database area by searching and iterating the three-layer coding structure based on the configuration information of the well deployment strategy includes: Individuals that satisfy the constraints are randomly generated according to the three-layer coding structure to form the initial population as the current population; The fitness value of each individual in the current population is determined based on a pre-constructed multi-objective dynamic fitness evaluation function, wherein the multi-objective dynamic fitness evaluation function is determined based on the optimization objective in the configuration information of the well-shaped deployment strategy. Determine whether the current population iteration termination condition is met. The population iteration termination condition includes the number of iterations reaching a threshold or the change in fitness value not exceeding a set fitness threshold. If the conditions are not met, a hybrid heuristic search strategy is used to search and iterate the current population, and then the process is returned to continue executing the pre-constructed multi-objective dynamic fitness evaluation function to determine the fitness value of each individual in the current population. If the conditions are met, the well deployment strategy with the highest fitness value is obtained as the target well deployment strategy.

6. The method of claim 5, wherein, The construction steps of the multi-objective dynamic fitness evaluation function include: The optimization objective function value is determined based on the proportion of dominant well types, estimated cost per unit reservoir capacity, well site concentration index, and corresponding dynamic weighting coefficients. The penalty function value is determined based on the spacing penalty, land use penalty, buffer intrusion penalty, and the corresponding fixed weight coefficients; The value of the optimization objective function is subtracted from the value of the penalty function to obtain the multi-objective dynamic fitness evaluation function.

7. The method of claim 6, wherein, The process of determining the optimization objective function value based on the proportion of dominant well types, estimated cost per unit reservoir capacity, well site concentration index, and corresponding dynamic weighting coefficients includes: The proportion of the dominant well type is determined based on the number of salt caverns controlled by the dominant well type and the total number of salt caverns in the target reservoir area; The estimated cost per unit capacity is determined based on the total designed reservoir capacity of all salt caverns, the total number of wells, the length of surface injection and production pipelines, and the area occupied by the well site. The well site concentration index is determined based on the variance of the number of service wells in each well site; The optimization objective function value is obtained by summing the results of multiplying the dominant well type proportion, the estimated cost per unit reservoir capacity, and the well site concentration index by their respective dynamic weighting coefficients.

8. The method of claim 6, wherein, The step of determining the penalty function value based on the spacing penalty, land use penalty, buffer zone intrusion penalty, and corresponding fixed weight coefficients includes: The spacing penalty is determined based on the actual distance between the two well-type units and the minimum allowable distance; The land penalty is determined based on the minimum footprint required by the well site according to the design and the available area at the actual planned location of the well site; The buffer intrusion penalty is determined based on the depth of the cavity projection of the candidate salt cavern into the safety buffer and the width of the safety buffer. The penalty function value is determined by summing the results of multiplying the spacing penalty, the land use penalty, and the buffer intrusion penalty by their respective fixed weight coefficients.

9. The method according to claim 5, characterized in that, The method of using a hybrid heuristic search strategy to search and iterate on the contemporary population includes: Using a genetic algorithm as the global framework, the current population is evolved through selection, crossover, and mutation operations. After each generation of genetic operations, simulated annealing local search is performed on the top 100 elite individuals with the highest fitness values. To avoid duplicate searches, a taboo list is created, which records well-shaped deployment strategies that have been frequently adjusted in historical iterations but have not brought about improvement.

10. A combined deployment device based on different salt cavern gas storage well types, characterized in that, include: The cavity determination module is used to generate the center point of at least one candidate salt cavern cavity within the target reservoir construction area; The strategy deployment module is used to select a well type unit from a predefined well type unit library as the dominant well type unit applied to the target reservoir construction area, and convert the strategy intent into optimization objectives and corresponding constraints as configuration information for the well type deployment strategy. The optimization objective is to maximize the proportion of the number of salt caverns controlled by the dominant well type unit to the total number of salt caverns in the target reservoir construction area. The strategy optimization module is used to characterize the well deployment strategy using a three-layer coding structure based on the center point of each candidate salt cavern cavity, and to search and iterate the three-layer coding structure using a hybrid heuristic search strategy based on the configuration information of the well deployment strategy, so as to determine the target well deployment strategy for the target reservoir area.

11. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the combined deployment method based on different salt cavern gas storage well types as described in any one of claims 1-9.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the combined deployment method based on different salt cavern gas storage well types as described in any one of claims 1-9.

13. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the combined deployment method based on different salt cavern gas storage well types as described in any one of claims 1-9.

Images