A heating well layout optimization method and device based on genetic algorithm

Abstract

The present invention discloses a method and device for optimizing the layout of heating wells based on a genetic algorithm. The method comprises: obtaining the shape and area of ​​a target area, dividing the target area into multiple regular blocks according to a segmentation rule; evenly distributing k heating wells as an initial population P(0) on each regular block according to the layout rule; setting an evolutionary algebra counter t=0 and a maximum evolutionary algebra T; assuming that the k heating wells have a probability of p of moving randomly in a direction around them in each cycle; calculating the coverage area of ​​the new positions of P(t)k heating wells after the movement, and taking the solution with the largest coverage area as the next generation solution P(t+1); when t=T, the current corresponding solution is the relatively optimal layout solution. The method optimizes the layout of heating wells in the thermal enhancement (SVE) process, reduces the overlap of the heating wells' effective ranges, and maximizes the effective area covered by the heating wells, thereby achieving the purpose of reducing energy waste and controlling greenhouse gas emissions.

Description

Technical Field

[0001] The present invention relates to the technical field of gas phase extraction, and in particular to a method and device for optimizing the layout of heating wells based on a genetic algorithm. Background Art

[0002] Vapor phase extraction (SVE) is a widely used in-situ soil remediation technology. It works by heating the surrounding soil with a heating well and then pumping large amounts of gas into or extracting it from the soil, creating a gas flow within the soil. This method effectively removes volatile and semi-volatile organic compounds (VOCs) from the soil.

[0003] However, my country's SVE technology started late and has lagged behind in development, remaining largely confined to single-factor experiments, shallow-layer mechanism, and kinetic model research. The late start of related technologies and lagging independent R&D capabilities have made it difficult to achieve economies of scale. In particular, research on the layout of meteorological extraction heating wells is scarce.

[0004] The traditional meteorological extraction process often requires heating the soil temperature to five or six hundred degrees. This process will consume a lot of energy and also produce some greenhouse gases.

[0005] How to reasonably arrange the layout of heating wells in an area so that fewer heating wells can cover a larger effective area, improve fuel utilization efficiency and heating efficiency, and reduce fuel consumption and greenhouse gas emissions has become an urgent problem to be solved. Summary of the Invention

[0006] The purpose of the present invention is to address the shortcomings of the above-mentioned existing technologies and propose a heating well layout optimization method and device based on genetic algorithm. This method optimizes the layout of heating wells in the thermal enhancement SVE process, reduces the overlap of the heating well action range, and maximizes the effective area covered by the heating wells, thereby achieving the purpose of reducing energy waste and controlling greenhouse gas emissions.

[0007] To achieve the above object, the technical solution adopted by the present invention is:

[0008] In a first aspect, an embodiment of the present invention provides a method for optimizing heater well layout based on a genetic algorithm, comprising:

[0009] S1. Obtain the shape and area of ​​the target area, and divide the target area into multiple regular blocks according to a segmentation rule;

[0010] S2. Distribute k heating wells uniformly on each regular block as the initial population P(0) according to the layout rule; set the evolution generation counter t=0 and the maximum evolution generation T;

[0011] S3. Assume that k heating wells have a probability of p to move in a random direction around them in each cycle;

[0012] S4. Calculate the coverage area of ​​the new positions of the P(t)k heating wells after they are moved, and use the solution with the largest coverage area as the next generation solution P(t+1);

[0013] S5. When t=T, the current corresponding solution is a relatively optimal layout solution.

[0014] Furthermore, the step S1 includes:

[0015] S11. Obtain the shape and area of ​​the target area. Starting from the boundary of the target area, delineate the area of ​​one or more heating wells as a valid block, and the remaining areas as redundant blocks; multiple heating wells are adjacent heating wells; calculate the percentage of heating well coverage area;

[0016] S12, combining the redundant blocks with the valid blocks according to the principle of proximity to complete the outer boundary of the irregular complex figure; calculating the new heating well coverage area percentage, and subtracting the percentage in step S11 as the reward for the selected state;

[0017] S13. Assuming that each step is the optimal decision, the state with the largest reward is selected as the next state, thereby dividing the target area into multiple regular blocks.

[0018] Furthermore, the arrangement rule in step S2 is:

[0019] K heating wells are evenly distributed on each regular block; the effective coverage area diameter of each heating well is d; the total coverage area of ​​the k heating wells reaches 1.3 times the area of ​​each regular block pattern.

[0020] Furthermore, the step S4 includes:

[0021] S41, calculating the coverage area of ​​the new positions of P(t)k heating wells after the movement;

[0022] S42, when the coverage area increases, setting the evolution generation counter t to 0;

[0023] S43. When the coverage area does not increase, the evolution generation counter t is incremented by 1, and step S3 is executed.

[0024] In a second aspect, an embodiment of the present invention further provides a heating well layout optimization device based on a genetic algorithm, comprising:

[0025] An acquisition and division module is used to acquire the shape and area of ​​the target area and divide the target area into a plurality of regular blocks according to a segmentation rule;

[0026] Initialization module, used to evenly distribute k heating wells as the initial population P(0) on each regular block according to the layout rule; set the evolution generation counter t=0 and set the maximum evolution generation T;

[0027] Select the crossover and mutation module to assume that the k heating wells have a probability of p to move in a random direction around them in each cycle;

[0028] The update module is used to calculate the coverage area of ​​the new positions of the P(t)k heating wells after they are moved, and the solution with the largest coverage area is used as the next generation solution P(t+1);

[0029] The termination judgment module is used to determine that when t=T, the current corresponding solution is a relatively optimal layout solution.

[0030] Furthermore, the acquisition and division module includes:

[0031] The acquisition submodule is used to obtain the shape and area of ​​the target area. Starting from the boundary of the target area, the area of ​​one or more heating wells is circled as a valid block, and the remaining areas are regarded as redundant blocks. Multiple heating wells are considered adjacent heating wells. The percentage of heating well coverage is calculated.

[0032] A combination selection submodule is used to combine the redundant blocks with the valid blocks according to the principle of proximity to complete the outer boundary of the irregular complex figure; calculate the new heating well coverage area percentage, and subtract the percentage in step S11 as the reward for the selected state;

[0033] The selection division submodule is used to assume that each step is the optimal decision, and then select the state with the largest reward as the next state, so as to divide the target area into multiple regular blocks.

[0034] Furthermore, the arrangement rules in the initialization module are:

[0035] K heating wells are evenly distributed on each regular block; the effective coverage area diameter of each heating well is d; the total coverage area of ​​the k heating wells reaches 1.3 times the area of ​​each regular block pattern.

[0036] Furthermore, the update module includes:

[0037] The calculation submodule is used to calculate the coverage area of ​​the new positions of the P(t)k heating wells after they are moved;

[0038] A first judgment submodule, configured to set the evolutionary generation counter t to 0 when the coverage area increases;

[0039] The second judgment submodule is configured to increase the evolutionary generation counter t by 1 when the coverage area has not increased, and notify the selection crossover and mutation module to perform an operation.

[0040] Compared with the prior art, the present invention has the following beneficial effects:

[0041] The embodiment of the present invention provides a heating well layout optimization method based on a genetic algorithm, including: obtaining the shape and area of ​​a target area, dividing the target area into multiple regular blocks according to a segmentation rule; evenly distributing k heating wells as an initial population P(0) on each regular block according to a layout rule; setting an evolutionary generation counter t=0 and a maximum evolutionary generation T; assuming that the k heating wells have a probability of p of moving in a random direction around them in each cycle; calculating the coverage area of ​​the new positions of P(t)k heating wells after movement, and taking the solution with the largest coverage area as the next generation solution P(t+1); when t=T, the current corresponding solution is the relatively optimal layout solution. This method optimizes the layout of heating wells in the thermal enhancement (SVE) process, reduces the overlap of the heating wells' range of action, and maximizes the effective area covered by the heating wells, thereby achieving the purpose of reducing energy waste and controlling greenhouse gas emissions. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 A flow chart of a method for optimizing heating well layout based on a genetic algorithm is provided in an embodiment of the present invention.

[0043] Figure 2 A schematic diagram provided for an embodiment of the present invention assuming that heating wells are arranged on a regular rectangle.

[0044] Figure 3 A schematic diagram of the arrangement of k heating wells provided in an embodiment of the present invention when the total area reaches 1.3 times the area of ​​the graphic.

[0045] Figure 4 for Figure 3 Schematic diagram of the heating well after the heating area is moved.

[0046] Figure 5 A schematic diagram of the execution principle of the heating well layout optimization method based on genetic algorithm provided in an embodiment of the present invention.

[0047] Figure 6 A block diagram of a heating well layout optimization device based on a genetic algorithm provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0048] In order to make the technical means, creative features, objectives and effects achieved by the present invention easier to understand, the present invention is further described below in conjunction with specific implementation methods.

[0049] In the description of the present invention, it should be noted that the terms "upper," "lower," "inner," "outer," "front end," "rear end," "both ends," "one end," "the other end," and the like, indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings and are intended solely to facilitate and simplify the description of the present invention. They are not intended to indicate or imply that the devices or components referred to must have, be constructed, or operate in a specific orientation, and therefore should not be construed as limiting the present invention. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0050] In the description of the present invention, it should be noted that, unless otherwise expressly specified or limited, the terms "installed," "provided with," "connected," etc., should be understood in a broad sense. For example, "connected" may refer to a fixed connection, a detachable connection, or an integral connection; it may refer to a mechanical connection or an electrical connection; it may refer to a direct connection or an indirect connection through an intermediate medium; it may refer to internal communication between two components. Those skilled in the art will be able to understand the specific meanings of the above terms in the present invention based on the specific circumstances.

[0051] Reference Figure 1 As shown, an embodiment of the present invention provides a method for optimizing the layout of heating wells based on a genetic algorithm, comprising:

[0052] S1. Obtain the shape and area of ​​the target area, and divide the target area into multiple regular blocks according to a segmentation rule;

[0053] S2. Distribute k heating wells uniformly on each regular block as the initial population P(0) according to the layout rule; set the evolution generation counter t=0 and the maximum evolution generation T;

[0054] S3. Assume that k heating wells have a probability of p to move in a random direction around them in each cycle;

[0055] S4. Calculate the coverage area of ​​the new positions of the P(t)k heating wells after they are moved, and use the solution with the largest coverage area as the next generation solution P(t+1);

[0056] S5. When t=T, the current corresponding solution is a relatively optimal layout solution.

[0057] This method uses genetic algorithms to optimize the layout of heating wells, as shown below:

[0058] (1) Initialization: Set the evolution generation counter t = 0, set the maximum evolution generation T = 50, and k heating wells as the initial population P(0).

[0059] (2) Group evaluation: the coverage area of ​​k heating wells.

[0060] (3) Select crossover and mutation: For each heating well, there is a probability of p that it moves a small distance in a random direction around it in each cycle. In order to reduce the amount of calculation and reduce the calculation time, this operation is repeated for all wells in each step, and a limited number of attempts are made to select the optimal method.

[0061] (4) Value update: Calculate the coverage area of ​​P(t)k heating wells after they are in their new positions, including the current solution, and take the solution with the largest coverage area as the next generation solution P(t+1).

[0062] (5) Termination condition judgment: If t = T, it is considered that the current group can no longer be optimized and the current solution is the relatively optimal solution.

[0063] In this embodiment, the method optimizes the layout of the heating wells in the thermal enhancement SVE process to obtain the optimal layout plan, which can reduce the overlap of the heating wells' range of action and maximize the effective area covered by the heating wells, thereby achieving the purpose of reducing energy waste and controlling greenhouse gas emissions.

[0064] In one embodiment, step S1 includes:

[0065] S11. Obtain the shape and area of ​​the target area. Starting from the boundary of the target area, delineate the area of ​​one or more heating wells as a valid block, and the remaining areas as redundant blocks; multiple heating wells are adjacent heating wells; calculate the percentage of heating well coverage area;

[0066] S12, combining the redundant blocks with the valid blocks according to the principle of proximity to complete the outer boundary of the irregular complex figure; calculating the new heating well coverage area percentage, and subtracting the percentage in step S11 as the reward for the selected state;

[0067] S13. Assuming that each step is the optimal decision, the state with the largest reward is selected as the next state, thereby dividing the target area into multiple regular blocks.

[0068] In this embodiment, for irregular shaped areas, it is desired to divide them into regular graphic blocks, and the following division method is used:

[0069] 1. Starting from the boundary position, circle the area (as a valid block) that can just accommodate one or several heating wells (the heating wells mentioned here must be adjacent). The remaining area is used as redundant blocks. Here, it is necessary to ensure that the valid blocks do not overlap. Calculate the percentage of heating well coverage area.

[0070] 2. Combine redundant blocks with valid blocks based on proximity, and complete the outer boundaries of irregular, complex shapes. If a redundant block is adjacent to two valid blocks, divide it into two parts based on the distance from each point on it to the two valid blocks. This results in three states: both blocks are divided into valid block A or valid block B, or both blocks are divided into blocks A and B based on proximity (no blocks are divided into groups of non-adjacent valid blocks). Complete the outer boundaries (make each valid block a rectangle or a combination of non-overlapping rectangles), and calculate the new percentage of heating well coverage for each of these three states. Subtract the previous percentage as the reward for selecting this state.

[0071] 3. Assuming that each step is the optimal decision, the state with the largest reward is selected as the next state.

[0072] 4. Train several times to get different solutions, and then choose a relatively suitable segmentation solution.

[0073] In one embodiment, the arrangement rule in step S2 is:

[0074] K heating wells are evenly distributed on each regular block; the effective coverage area diameter of each heating well is d; the total coverage area of ​​the k heating wells reaches 1.3 times the area of ​​each regular block pattern.

[0075] Step S4 includes:

[0076] S41, calculating the coverage area of ​​the new positions of P(t)k heating wells after the movement;

[0077] S42, when the coverage area increases, setting the evolution generation counter t to 0;

[0078] S43. When the coverage area does not increase, the evolution generation counter t is incremented by 1, and step S3 is executed.

[0079] The technical solution of the embodiment of the present invention is described below through specific examples:

[0080] ① Assume that the diameter of each effective coverage area of ​​k heating wells is d, and they are evenly distributed on a regular rectangle (such as an n*m rectangle, where n and m are both integer multiples of d). In this case, the k heating wells cover π / 4 of the total area of ​​the rectangle, that is, 0.78; Figure 2 shown.

[0081] Calculation process: For example, if a rectangle is divided into multiple d*d squares, the area of ​​the circle in each square is d 2π / 4, which is 0.78 of the total area covered by the heating wells. If the length and width of the rectangle are not integer multiples of d, the number of heating wells can be rounded up. This process can be regarded as stretching the length or width of the rectangle to fill it with heating wells, thereby ensuring that the coverage area of ​​the heating wells must be greater than or equal to 0.78.

[0082] ② Take k heating wells so that their total area reaches 1.3 times the area of ​​the pattern (round up to leave enough margin, from 1-π / 4=0.22, 1.3*0.78=1). Then, through reasonable layout, k heating wells should be able to cover more than 95% of the regular pattern; Figure 3 shown.

[0083] ③ Such as Figure 4 As shown in the figure, assuming that the k heating wells have a probability of p to move a small distance in a random direction around them in each cycle (the new position can be observed), a single-step calculation is performed on the positions of the k heating wells to calculate the coverage area of ​​the k heating wells after they are in the new position.

[0084] ④ Design a counter. If the coverage area increases, set the counter to zero and replace the original position of the heating well with the new position. If the coverage area does not increase, add one to the counter and jump to step ③.

[0085] ⑤ If the counter reading is greater than or equal to T (which can be set according to actual needs, generally tens to hundreds of times, the more times and the longer the training time, the better the result may be), it means that the coverage area cannot be increased by changing the position of the heating well within the limited number of cycles, that is, it is considered that the distribution of the heating wells in the current graph cannot be optimized.

[0086] ⑥ If the target graph is a complex graph, then the Markov decision process is used to divide the complex graph area into multiple regular graph areas, while ensuring that the segmented graph can accommodate one or n heating wells, and the above process is repeated.

[0087] ⑦ Build a complete model to generate the heating well layout for the entire area; Figure 5 As shown in the figure, it is the execution principle diagram of the above steps.

[0088] The genetic algorithm-based heating well layout optimization method provided in the embodiments of the present invention utilizes a genetic algorithm to optimize the layout of heating wells. This method is simple, easy to understand, and readily applicable. It can achieve a larger effective heating area with fewer heating wells, reducing energy consumption and greenhouse gas emissions from fuels. It can also fully utilize areas around heating wells where the temperature is insufficient to reach the specified temperature, thereby improving heating well utilization efficiency by allowing the same area to be covered by different heating wells.

[0089] Furthermore, embodiments of the present invention can optimize existing heating well layouts, adjusting their locations and removing unnecessary ones, thereby reducing management costs and risks. Furthermore, by rationally planning the heating well layout before construction and designing the number and location of heating wells, resources can be efficiently allocated and waste reduced.

[0090] Based on the same inventive concept, an embodiment of the present invention also provides a heating well layout optimization device based on a genetic algorithm. Since the principle of the problem solved by the device is similar to that of the aforementioned heating well layout optimization method based on a genetic algorithm, the implementation of the device can refer to the implementation of the aforementioned method, and the repeated parts will not be repeated.

[0091] Reference Figure 6 As shown, a heating well layout optimization device based on genetic algorithm includes:

[0092] An acquisition and division module is used to acquire the shape and area of ​​the target area and divide the target area into a plurality of regular blocks according to a segmentation rule;

[0093] Initialization module, used to evenly distribute k heating wells as the initial population P(0) on each regular block according to the layout rule; set the evolution generation counter t=0 and set the maximum evolution generation T;

[0094] Select the crossover and mutation module to assume that the k heating wells have a probability of p to move in a random direction around them in each cycle;

[0095] The update module is used to calculate the coverage area of ​​the new positions of the P(t)k heating wells after they are moved, and the solution with the largest coverage area is used as the next generation solution P(t+1);

[0096] The termination judgment module is used to determine that when t=T, the current corresponding solution is a relatively optimal layout solution.

[0097] In one embodiment, the acquisition and division module includes:

[0098] The acquisition submodule is used to obtain the shape and area of ​​the target area. Starting from the boundary of the target area, the area of ​​one or more heating wells is circled as a valid block, and the remaining areas are regarded as redundant blocks. Multiple heating wells are considered adjacent heating wells. The percentage of heating well coverage is calculated.

[0099] A combination selection submodule is used to combine the redundant blocks with the valid blocks according to the principle of proximity to complete the outer boundary of the irregular complex figure; calculate the new heating well coverage area percentage, and subtract the percentage in step S11 as the reward for the selected state;

[0100] The selection division submodule is used to assume that each step is the optimal decision, and then select the state with the largest reward as the next state, so as to divide the target area into multiple regular blocks.

[0101] In one embodiment, the arrangement rules in the initialization module are:

[0102] K heating wells are evenly distributed on each regular block; the effective coverage area diameter of each heating well is d; the total coverage area of ​​the k heating wells reaches 1.3 times the area of ​​each regular block pattern.

[0103] In one embodiment, the update module includes:

[0104] The calculation submodule is used to calculate the coverage area of ​​the new positions of the P(t)k heating wells after they are moved;

[0105] A first judgment submodule, configured to set the evolutionary generation counter t to 0 when the coverage area increases;

[0106] The second judgment submodule is configured to increase the evolutionary generation counter t by 1 when the coverage area has not increased, and notify the selection crossover and mutation module to perform an operation.

[0107] The basic principles, main features, and advantages of the present invention are shown and described above. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions are merely illustrative of the principles of the present invention. Various changes and modifications may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and modifications are intended to fall within the scope of the present invention. The scope of protection claimed in the present invention is defined by the appended claims and their equivalents.

Claims

1. A heating well layout optimization method based on genetic algorithm, characterized in that: include: S1. Obtain the shape and area of ​​the target area, and divide the target area into multiple regular blocks according to a segmentation rule; S2. Distribute k heating wells uniformly on each regular block as the initial population P(0) according to the layout rule; set the evolution generation counter t=0 and the maximum evolution generation T; S3. Assume that k heating wells have a probability of p to move in a random direction around them in each cycle; S4. Calculate the coverage area of ​​the new positions of the P(t)k heating wells after they are moved, and use the solution with the largest coverage area as the next generation solution P(t+1); S5. When t=T, the current corresponding solution is the relatively optimal layout solution; Wherein, the step S1 includes: S11. Obtain the shape and area of ​​the target area. Starting from the boundary of the target area, delineate the area of ​​one or more heating wells as a valid block, and the remaining areas as redundant blocks; multiple heating wells are adjacent heating wells; calculate the percentage of heating well coverage area; S12, combining the redundant blocks with the valid blocks according to the principle of proximity to complete the outer boundary of the irregular complex figure; calculating the new heating well coverage area percentage, and subtracting the percentage in step S11 as the reward for the selected state; S13. Assuming that each step is the optimal decision, the state with the largest reward is selected as the next state, thereby dividing the target area into multiple regular blocks.

2. The method for optimizing heating well layout based on genetic algorithm according to claim 1, characterized in that: The arrangement rules in step S2 are: K heating wells are evenly distributed on each regular block; the effective coverage area diameter of each heating well is d; the total coverage area of ​​the k heating wells reaches 1.3 times the area of ​​each regular block pattern.

3. The method for optimizing heating well layout based on genetic algorithm according to claim 2, characterized in that: The step S4 comprises: S41, calculating the coverage area of ​​the new positions of P(t)k heating wells after the movement; S42, when the coverage area increases, setting the evolution generation counter t to 0; S43. When the coverage area does not increase, the evolution generation counter t is incremented by 1, and step S3 is executed.

4. A heating well layout optimization device based on genetic algorithm, characterized in that: include: An acquisition and division module is used to acquire the shape and area of ​​the target area and divide the target area into a plurality of regular blocks according to a segmentation rule; Initialization module, used to evenly distribute k heating wells as the initial population P(0) on each regular block according to the layout rule; set the evolution generation counter t=0 and set the maximum evolution generation T; Select the crossover and mutation module to assume that the k heating wells have a probability of p to move in a random direction around them in each cycle; The update module is used to calculate the coverage area of ​​the new positions of the P(t)k heating wells after they are moved, and the solution with the largest coverage area is used as the next generation solution P(t+1); A termination judgment module is used to determine that the current corresponding solution is the relatively optimal layout solution when t=T; The acquisition and division module includes: The acquisition submodule is used to obtain the shape and area of ​​the target area. Starting from the boundary of the target area, the area of ​​one or more heating wells is circled as a valid block, and the remaining areas are regarded as redundant blocks. Multiple heating wells are considered to be adjacent heating wells. The percentage of the heating well coverage area is calculated. A combination selection submodule is used to combine the redundant blocks with the valid blocks according to the principle of proximity to complete the outer boundary of the irregular complex figure; calculate the new heating well coverage area percentage, and subtract the percentage in step S11 as the reward for the selected state; The selection division submodule is used to assume that each step is the optimal decision, and then select the state with the largest reward as the next state, so as to divide the target area into multiple regular blocks.

5. The heating well layout optimization device based on genetic algorithm according to claim 4, characterized in that: The layout rules in the initialization module are: K heating wells are evenly distributed on each regular block; the effective coverage area diameter of each heating well is d; the total coverage area of ​​the k heating wells reaches 1.3 times the area of ​​each regular block pattern.

6. The heating well layout optimization device based on genetic algorithm according to claim 5, characterized in that: The update module includes: The calculation submodule is used to calculate the coverage area of ​​the new positions of the P(t)k heating wells after they are moved; A first judgment submodule, configured to set the evolutionary generation counter t to 0 when the coverage area increases; The second judgment submodule is configured to increase the evolutionary generation counter t by 1 when the coverage area has not increased, and notify the selection crossover and mutation module to perform an operation.

Images