Design method and system of earthquake observation system, computer device and storage medium
Through the design method based on genetic algorithms, the problem of how to design high -density three -dimensional seismic observation systems in coal field earthquake exploration, realize the collection of high -quality seismic data in meeting various constraints, and reduce the cost of exploration.
Patent Information
- Application Number
- CN202111116467.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-09-23
- Publication Date
- 2025-01-28
- Estimated Expiration
- Not applicable · inactive patent
Smart Images
Figure CN113836717B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of coalfield seismic exploration, and in particular to a design method for a seismic observation system and a system applying the method, and also to a computer device and a storage medium for implementing the method. Background Art
[0002] Seismic exploration is a method of using seismic information to explore oil and coal fields. Since seismic information can reflect the changing trends of reservoir parameters, this method can be used to predict reservoir parameters and structures.
[0003] An ideal seismic observation system requires spending as little manpower and material resources as possible to collect seismic data of the highest quality possible. In addition to requiring a high signal-to-noise ratio, the imaging capability of the observation system, especially the resolution, is an important criterion for evaluating the quality of the observation system.
[0004] In addition, the main factors affecting the resolution of the seismic acquisition observation system include: array length, trace spacing (or spatial sampling rate), wavelet main frequency (or bandwidth), target point location, etc.
[0005] Therefore, the primary issue to be addressed is how to design a feasible high-density three-dimensional seismic observation system based on geophysical constraints, instrument and equipment constraints, and economic cost constraints. Summary of the invention
[0006] The first object of the present invention is to provide a design method for a high-density three-dimensional seismic observation system for coal fields based on geophysical constraints, instrument and equipment constraints, and economic cost constraints.
[0007] The second object of the present invention is to provide a high-density three-dimensional seismic observation system applied to the above-mentioned design method.
[0008] The third object of the present invention is to provide a computer device capable of implementing the above-mentioned design method of the earthquake observation system.
[0009] A fourth object of the present invention is to provide a storage medium that, when read and executed by a processor, can implement the above-mentioned design method of the earthquake observation system.
[0010] In order to achieve the above-mentioned main purpose, the present invention provides a design method for a seismic observation system, including establishing a genetic algorithm model; generating a seismic-constrained coalfield seismic observation system objective function; setting seismic exploration economic cost constraints; based on the genetic algorithm model, determining a feasible solution set of observation system parameters according to the objective function and the economic cost constraints; wherein different feasible solution sets are set, the optimal solution from multiple feasible solution sets is calculated, multiple interval optimal solutions are compared, and the optimal combination of observation system parameters is output to establish a high-density three-dimensional seismic observation system for coalfields.
[0011] In a further scheme, after setting the economic cost constraint conditions, the following is also performed: based on the genetic algorithm model, genetic operator parameters are determined; wherein, an option set of GA evolution parameters is provided according to the confirmed programming goals, and the GA evolution parameters include genetic algorithm control parameters, population type, population size, generation, migration score, number of elites, mating ratio, creation operator, selection operator, crossover operator and mutation operator.
[0012] In a further scheme, the establishment of the genetic algorithm model includes: binary encoding: representing the solution data of the solution space as genotype string structure data of the genetic space, different points are constituted by different combinations of the string structure data, and an initial group is randomly formed, wherein the solution data in the solution space serves as the phenotype form of the genetic algorithm; generation of the initial group: randomly generating N initial string structure data, each string structure data is called an individual, and N individuals constitute a group; fitness value evaluation detection: defining a fitness function, and indicating the quality of an individual or a solution through the fitness function; selection: applying a selection operator to a population; crossover: applying a crossover operator to a population; mutation: applying a mutation operator to a population; termination condition judgment: when the termination condition is met, the individual with the maximum fitness obtained in the evolution process is output as the optimal solution, and the operation is terminated.
[0013] In a further embodiment, the objective function of generating seismic constraints includes: establishing targets using acoustic detection and raw two-dimensional data; planning costs and geophysical constraints; running a constraint algorithm and introducing evolutionary parameters, application data and model constraints to generate the objective function.
[0014] In a further embodiment, the objective function is expressed as formula (1):
[0015]
[0016] Among them, x max is the maximum offset, x mi n is the minimum offset, fold deed is the number of times the deeper target layer is covered, fold shallow is the number of first-arrival formation coverages, nc is the total number of received channels, RLI is the receiving line spacing, SLI is the shot row spacing, and x r is the maximum longitudinal offset, x s is the maximum lateral offset.
[0017] In a further scheme, the setting of economic cost constraints includes: taking the total cost of the seismic observation system per square kilometer as the optimization target, constructing a cost objective function, wherein the cost objective function includes measurement, layout and picking, drilling holes and explosives, recording data, and logistics processes.
[0018] In a further embodiment, the optimal solution in the plurality of feasible solution sets is calculated, and the optimal solution parameters include: track spacing, number of receiving lines / number of detectors per line, shot / receiving line spacing SLI / RLI, longitudinal / lateral coverage times, average coverage times of the first target layer / second target layer, maximum closest shot offset, maximum longitudinal / lateral shot offset, maximum shot offset, total number of detectors required, lateral roll, economic cost per square kilometer, and cumulative error; the optimal observation system parameter combination includes: observation system parameters, receiving line spacing, receiving track spacing, excitation point spacing, excitation line spacing, number of receiving tracks, bin size, coverage times, beam roll, and aspect ratio; the numerical set of decision variables of the feasible solution set includes RI a 、SI a , nr, ns, NRL, NL; among them, RI a is the numerical set of receiving point distances, SI a is the numerical set of shot point distances, nr is the set of the number of detectors between two adjacent shot lines, ns is the set of the number of shot points between two adjacent detection lines, NRL is the set of the number of receiving lines, and NL is the set of the number of detectors on each receiving line.
[0019] In order to achieve the above second objective, the present invention provides a high-density three-dimensional seismic observation system, which is a seismic observation system constructed using the above-mentioned design method for the seismic observation system.
[0020] It can be seen that compared with the prior art, the present invention uses an improved genetic algorithm to perform correlation analysis on seismic data based on geophysical constraints, instrument and equipment constraints, and economic cost constraints, and designs an optimal high-density three-dimensional seismic observation system, which can avoid falling into local optimal solutions and obtain the global optimal seismic attribute combination, thereby reducing exploration costs while ensuring exploration quality.
[0021] In order to achieve the third objective mentioned above, the computer device provided by the present invention includes a processor, and the processor is used to implement each step of the above-mentioned seismic observation system design method when executing a computer program stored in a memory.
[0022] In order to achieve the fourth objective mentioned above, a computer program is stored on the storage medium provided by the present invention, and when the computer program is executed by a processor, each step of the design method of the above-mentioned earthquake observation system is implemented.
[0023] It can be seen that the present invention provides a computer device and a storage medium, which includes: one or more memories, and one or more processors. The memory is used to store program codes and intermediate data generated during program execution, storage of model output results, and storage of models and model parameters; the processor is used for processor resources occupied by code execution and multiple processor resources occupied when training models. BRIEF DESCRIPTION OF THE DRAWINGS
[0024] Figure 1 It is a flow chart of an embodiment of a design method for a seismic observation system of the present invention.
[0025] Figure 2 It is a schematic diagram of the process of establishing a genetic algorithm model in an embodiment of a design method for a seismic observation system of the present invention.
[0026] Figure 3 It is a schematic diagram of a process for generating an objective function in an embodiment of a design method for a seismic observation system of the present invention.
[0027] Figure 4 It is a principle diagram of the proportion of the cost of each process in the acquisition link in an embodiment of a design method for a seismic observation system of the present invention.
[0028] Figure 5 It is a comparison diagram of the uniformity of the shot distance distribution of Design 1 and Design 2 in an embodiment of a design method for a seismic observation system of the present invention.
[0029] Figure 6 It is a comparison diagram of the uniformity index of the shot distance distribution of Design 1 and Design 2 in an embodiment of a design method for a seismic observation system of the present invention.
[0030] The present invention is further described below in conjunction with the accompanying drawings and embodiments. DETAILED DESCRIPTION
[0031] In order to make the purpose, technical solution and advantages of the embodiment of the present invention clearer, the technical solution of the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings of the embodiment of the present invention. Obviously, the described embodiment is a part of the embodiment of the present invention, not all of the embodiments. Based on the described embodiment of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0032] See also Figures 1 to 3 A design method of a seismic observation system of the present invention comprises the following steps:
[0033] Step S1, establishing a genetic algorithm model.
[0034] Step S2: Generate an earthquake-constrained coalfield seismic observation system objective function.
[0035] Step S3: setting economic cost constraints for seismic exploration.
[0036] Step S4: Based on the genetic algorithm model, a feasible solution set of observation system parameters is determined according to the objective function and economic cost constraints.
[0037] Among them, in the above step S4, different feasible solution sets are set, the optimal solution among multiple feasible solution sets is calculated, multiple interval optimal solutions are compared, the optimal observation system parameter combination is output, and a high-density three-dimensional seismic observation system for coalfields is established.
[0038] In the above step S3, after setting the economic cost constraint condition, the following is further performed: determining genetic operator parameters based on the genetic algorithm model.
[0039] Among them, an option set of GA evolution parameters is provided according to the confirmed programming goals, and the GA evolution parameters include genetic algorithm control parameters, population type, population size, generation, migration score, number of elites, mating ratio, creation operator, selection operator, crossover operator and mutation operator.
[0040] In the above step S1, a genetic algorithm model is established, which specifically includes:
[0041] Binary coding: The solution data in the solution space is represented as genotype string structure data in the genetic space, different points are formed by different combinations of the string structure data, and an initial population is randomly formed, wherein the solution data in the solution space serves as the phenotype form of the genetic algorithm.
[0042] Generation of the initial group: N initial string structure data are randomly generated, each string structure data is called an individual, and N individuals constitute a group.
[0043] Fitness value evaluation test: define the fitness function, and use the fitness function to indicate the quality of individuals or solutions.
[0044] Selection: Apply the selection operator to the population.
[0045] Crossover: Apply the crossover operator to the population.
[0046] Mutation: Apply the mutation operator to the population.
[0047] Termination condition judgment: When the termination condition is met, the individual with the maximum fitness obtained in the evolution process is output as the optimal solution and the operation is terminated.
[0048] In the above step S2, the objective function of seismic constraints is generated, which specifically includes: establishing targets using acoustic wave detection and original two-dimensional data; planning costs and geophysical constraints; running the constraint algorithm, and introducing evolutionary parameters, application data and model constraints, and then generating the objective function.
[0049] The objective function is expressed as formula (1):
[0050]
[0051] Among them, x max is the maximum offset, x mi n is the minimum offset, fold deed is the number of times the deeper target layer is covered, fold shallow is the number of first-arrival formation coverages, nc is the total number of received channels, RLI is the receiving line spacing, SLI is the shot row spacing, and x r is the maximum longitudinal offset, x s is the maximum lateral offset.
[0052] In the above step S3, economic cost constraints are set, specifically including: taking the total cost of the seismic observation system per square kilometer as the optimization target, constructing a cost objective function, wherein the cost objective function includes measurement, layout and picking, drilling blastholes and explosives, recording data, and logistics processes.
[0053] In the above step S4, the optimal solution parameters include: track spacing, number of receiving lines / number of detectors per line, shot / receiving line spacing SLI / RLI, longitudinal / lateral coverage times, average coverage times of the first target layer / second target layer, maximum closest shot offset, maximum longitudinal / lateral shot offset, maximum shot offset, total number of detectors required, lateral roll, economic cost per square kilometer, and accumulated error.
[0054] The optimal observation system parameter combination includes: observation system parameters, receiving line spacing, receiving track spacing, excitation point spacing, excitation line spacing, number of receiving tracks, facet size, number of coverage times, beam spacing roll, and aspect ratio.
[0055] The numerical set of decision variables of the feasible solution set includes RI a 、SI a , nr, ns, NRL, NL; among them, RI a is the numerical set of receiving point spacing, SIa is the numerical set of shot point spacing, nr is the set of the number of detectors between two adjacent shot lines, ns is the set of the number of shot points between two adjacent detection lines, NRL is the set of the number of receiving lines, and NL is the set of the number of detectors on each receiving line.
[0056] Therefore, the present invention is based on intelligent evolutionary algorithm-genetic algorithm. When combining geological tasks and various constraints, an algorithm model is established to generate an objective function. Given a feasible solution set of observation system parameters, the parameters of the genetic operator are first self-optimized, the parameters are binary-encoded, an initial population is generated, and the generation-by-generation evolution of the biological population is simulated. In each generation of evolution, elite, selection, crossover, and mutation operators are applied to the encoded parameters, and then the objective function evaluation and detection are performed. When the termination conditions are met, the most suitable high-density three-dimensional seismic observation system design scheme is globally optimized from the feasible solution set.
[0057] In practical applications, the operation process of establishing a genetic algorithm model includes:
[0058] Encoding: The solution data x in the solution space is used as the phenotype of the genetic algorithm. The mapping from phenotype to genotype is called encoding. Before searching, the genetic algorithm first represents the solution data in the solution space as genotype string structure data in the genetic space. Different combinations of these string structure data constitute different points.
[0059] Generation of the initial population: Randomly generate N initial string structure data, each string structure data is called an individual, and N individuals constitute a population. The genetic algorithm starts iteration with these N string structures as the initial point. Set the evolutionary algebra counter t←0; set the maximum evolutionary algebra T; randomly generate M individuals as the initial population P(O).
[0060] Fitness value evaluation test: The fitness function indicates the quality of an individual or solution. The fitness function is defined differently for different problems. According to the specific problem, the fitness of each individual in the population P(t) is calculated.
[0061] Selection: Apply the selection operator to the population. The purpose of selection is to select excellent individuals from the current population so that they have the opportunity to serve as parents to reproduce offspring for the next generation. According to the fitness value of each individual, some excellent individuals are selected from the previous generation group according to certain rules or methods to be inherited to the next generation group. The genetic algorithm embodies this idea through the selection operation. The principle of selection is that individuals with strong adaptability have a high probability of contributing one or more offspring to the next generation, which reflects Darwin's principle of survival of the fittest.
[0062] Crossover: Apply the crossover operator to the population. The crossover operation is the most important genetic operation in the genetic algorithm. Through the crossover operation, a new generation of individuals can be obtained, and the new individuals combine the characteristics of the parent individuals. The individuals in the population are randomly paired, and for each individual, part of their chromosomes are exchanged with a certain probability (called the crossover rate). Crossover embodies the idea of information exchange.
[0063] Mutation: Apply the mutation operator to the population. The mutation operation first randomly selects an individual in the population, and randomly changes the value of a string in the string structure data with a certain probability for the selected individual, that is, for each individual in the population, the gene value on one or some loci is changed to other alleles with a certain probability (called mutation rate). As in the biological world, the probability of mutation in genetic algorithms is very low. Mutation provides an opportunity for the generation of new individuals.
[0064] Among them, the population P(t) is obtained after selection, crossover and mutation operations to obtain the next generation population P(t+1).
[0065] Termination condition judgment: If t<=T, then t=t+1, and go to step (2); if t>T, the individual with the maximum fitness obtained in the evolution process is output as the optimal solution and the operation is terminated.
[0066] From the genetic algorithm operation process, we can see that the evolutionary operation process is simple and easy to understand, which provides a basic framework for various other genetic algorithms.
[0067] The first step in building a genetic model is to select decision variables related to the physical properties of the problem. The range of these decision variables and the required resolution are absolutely proportional to the complexity and scope of the exploration area. It is assumed that the data will be collected by using an orthogonal observation system. The orthogonal observation system is described by 6 independent variable parameters, which can be used to calculate all other variables. The variables are shown in Table 1 below, and finally determine the genetic algorithm structure:
[0068] Table 1 Variable description
[0069]
[0070]
[0071] The fitness function is defined as formula (2):
[0072]
[0073] In step S2, seismic constraints, i.e., geophysical and acquisition equipment constraints, are designed. First, target parameters are designed, as shown in Table 2:
[0074] Table 2 Design target parameters
[0075]
[0076] According to the genetic algorithm model, the objective function is expressed as the above formula (1):
[0077] In step S3, economic cost constraints are set and the solution is designed based on the cost of the economic contract. The total cost of the survey is expected to be no more than 3 million RMB. The study area is about 2 square kilometers, which means that the total cost per square kilometer should not exceed 1.5 million RMB. Several components of 3D seismic acquisition make it difficult to express a cost function that covers all the details. Therefore, a cost simulation is performed to estimate the cost of each part of the process, including measurement, layout and pick-up, drilling blastholes and explosives, recording data, and logistics (clearance and vehicles).
[0078] Among them, the collection cost of each location is shown in Table 3:
[0079] Table 3 Collection costs
[0080]
[0081] Among them, the proportion of each collection process to the total cost is as follows: Figure 4 As shown:
[0082] For example, if the measurement cost of each location (shot point and receiver point) is 3.8￥, the measurement cost per square kilometer should be formula (3):
[0083]
[0084] in, is the receiving channel density per square kilometer, is the density of guns per square kilometer.
[0085] Constrain the cost of placing and picking up receivers: Assuming that the cost of placing and picking up receivers is 8￥, the corresponding cost per square kilometer must be less than the allowed value, as shown in formula (4):
[0086]
[0087] Drilling cost per square kilometer: The cost of each blast hole in this high-density mining area is 85.8￥=7.8m×11￥ / m, the explosive cost of each blast hole is 114.2￥, and the total cost of each blast point is 200￥. Therefore, this constraint can be written as formula (5):
[0088]
[0089] Data recording cost per square kilometer: The data recording cost of each shot point is about 120￥ / S, so the total data recording cost per square kilometer should meet the following constraints, as shown in formula (6):
[0090]
[0091] The total unit price of the compensation and vehicle transportation for the smooth progress of the logistics support project is 250 RMB according to the gun point. The compensation and vehicle transportation per square kilometer unit area meet the following constraints, as shown in formula (7):
[0092]
[0093] In this embodiment, determining the genetic operator parameters specifically includes: after determining the programming goal, it is necessary to specify the evolution parameters. As described above, an upstream algorithm, such as a genetic algorithm, is defined, and its purpose is to provide evolution parameters according to the goal. The upstream algorithm is activated, and an option set of acceptable GA evolution parameters is obtained, as shown in Table 4:
[0094] Table 4 Summary of evolutionary parameters of sequential genetic algorithm
[0095]
[0096] The creation function specifies the function that generates the initial population, such as the Uniform function, which creates a random initial population with uniform distribution.
[0097] The migration operator specifies how individuals (each corresponding to a set of values of the six decision variables) move between subpopulations. When migration occurs with a migration rate of 0.1, the best 10% of individuals in one subpopulation will replace the worst individuals in another subpopulation.
[0098] The number of elites refers to the number of individuals with the best fitness values in the current generation, which are guaranteed to be copied to the next generation. When the number of elites is 4, the four best individuals can be copied from the current generation to the next generation. Setting the number of elites to a higher value may cause the fittest individuals to dominate the population, which may reduce the efficiency of the search.
[0099] The selection operator selects parents for the next generation based on the scaling value of the next generation. Roulette selection selects parents by simulating a roulette wheel where the area of the cross section corresponding to an individual is proportional to its fitness value. Genetic algorithms use random numbers to select segments with probability equal to their area.
[0100] The crossover ratio refers to the proportion of individuals in the next generation (excluding elite children) produced by crossover. The algorithm has a population size of 100, a number of elites of 4, a crossover ratio of 0.8, a crossover number of 77, and the remaining 19 individuals are mutant children.
[0101] The genetic algorithm uses crossover and mutation functions to generate new individuals in each generation. A scatter crossover function with a crossover ratio of 0.8 was applied. The scatter function creates a random binary vector (or matrix) and selects the bits of the vector that are 1 from the first parent node (or individual) and the bits of the vector that are 0 from the second parent node, and finally combines them to form a new offspring.
[0102] In step S4, a design 1 is provided, and the numerical set of decision variables of the design feasible solution set is shown in Table 5:
[0103] Table 5 Numerical set of decision variables for the feasible solution set of Design 1
[0104]
[0105] The optimal solution parameters of the feasible solution are calculated as shown in Table 6:
[0106] Table 6 Summary of optimized design parameters
[0107]
[0108] In this embodiment, the observation system parameters of the optimal solution of Design 1 are shown in Table 7:
[0109] Table 7 Design 1 observation system parameters
[0110]
[0111]
[0112] Therefore, this observation system is the optimal solution seismic observation system under the geophysical constraints and economic cost constraints.
[0113] Of course, in practical applications, different feasible solution sets can be set according to actual conditions, the optimal solution among multiple feasible solution sets can be calculated, multiple interval optimal solutions can be compared, and the optimal high-density three-dimensional seismic observation system can be selected.
[0114] Specifically, after setting different feasible solution sets, the optimal solution among different multiple feasible solutions will be obtained. For example, in this embodiment, such as Design 1 and Design 2, the numerical sets of decision variables of the two feasible solution sets are set as shown in Table 5 and Table 8 respectively:
[0115] Table 5 Numerical set of decision variables for the feasible solution set of Design 1
[0116]
[0117] The NL value is selected to ensure that the number of longitudinal stacking times is an integer.
[0118] In high-density 3D seismic, the bin size is fixed, so the spacing between receivers and shot points will not change. Therefore, the search space will be reduced to a 4×3 matrix and 43×8 potential solutions, as shown in Table 8:
[0119] Table 8 Numerical set of decision variables for the feasible solution set of Design 2
[0120]
[0121]
[0122] The NL value is selected to ensure that the number of longitudinal stacking times is an integer.
[0123] In this embodiment, the optimal solution parameters of the feasible solution of Design 2 are calculated as shown in Table 9:
[0124] Table 9 Summary of optimized design parameters
[0125]
[0126] Therefore, the observation system parameters of the optimal solution of Design 2 are shown in Table 10:
[0127] Table 10 Design 2 observation system parameters
[0128]
[0129] In high-density 3D seismic, the bin size is fixed, so the receiver and shot spacing does not change. Therefore, the search space is reduced to a 4×3 matrix and 84 potential solutions.
[0130] Thus, two optimal solutions Design 1 and Design 2 are obtained under this feasible solution set, and the parameters are shown in Table 11:
[0131] Table 11 Summary of optimized design parameters of Design 1 and Design 2
[0132]
[0133] Comparing the parameters in the above table, it can be found that the shot line distance and receiving line distance of Design 2 calculated below the feasible solution region 2 are twice that of Design 1. The corresponding number of longitudinal coverage of the surface element is reduced, and the total number of coverage is also reduced to 80 times.
[0134] Therefore, the observation system parameters of Design 1 and Design 2 are shown in Table 12:
[0135] Table 12 Observation system parameters of Design 1 and Design 2
[0136]
[0137]
[0138] By comparing the parameters of the two design schemes in the table above, it is found that the aspect ratio of Design 2 is close to 1, which is closer to omnidirectional.
[0139] Then, the adequacy index value is calculated according to the formula of gun density, channel density and gun channel density, as shown in Table 13:
[0140] Table 13 Channel density values for Design 1 and Design 2
[0141]
[0142] It can be found from the above table that the trace density and shot density of Design 1 are twice that of Design 2, and the shot trace density is also 2 million more than that of Design 2, which means that the observation system of Design 1 has better and more accurate imaging quality for geological targets.
[0143] Then, the offset distribution uniformity index is compared as shown in Table 14 and Figure 5 As shown:
[0144] Table 14 Comparison of offset distribution uniformity index between design 1 and design 2
[0145]
[0146] Then, the azimuth uniformity index is compared, as shown in Table 15 and Figure 6 As shown:
[0147] Table 15 Statistics of azimuth uniformity index of design 1 and design 2
[0148]
[0149] After comprehensive analysis, two design schemes were obtained using genetic algorithm under two feasible solution sets. In terms of channel density sufficiency, design 1 has a channel density of 200w higher than design 2, and design 1 is better than design 2; in terms of offset uniformity, all indicators of design 1 are better than design 2, but the overall uniformity fluctuation is slightly greater than that of design 1, which can be ignored; in terms of azimuth uniformity, the aspect ratio of design 2 is closer to 1, and the azimuth uniformity index is slightly higher than that of design 1, but the overall azimuth uniformity distribution fluctuation is greater than that of design 1.
[0150] More importantly, although Design 2 meets the target cell size of 5×5m, the number of coverage times is greatly reduced, and the target layer exploration information collected by each gather is less than that of Design 1. Although the cost of Design 2 is half of that of Design 1, it is obviously smaller in shot density and trace density, and no longer meets the requirements of shot density and trace density for high-density 3D seismic acquisition. Therefore, Design 2 cannot be used as an alternative plan for actual high-density acquisition construction.
[0151] It can be seen that compared with the prior art, the present invention uses an improved genetic algorithm to perform correlation analysis on seismic data based on geophysical constraints, instrument and equipment constraints, and economic cost constraints, and designs an optimal high-density three-dimensional seismic observation system, which can avoid falling into local optimal solutions and obtain the global optimal seismic attribute combination, thereby reducing exploration costs while ensuring exploration quality.
[0152] High-density three-dimensional seismic observation system embodiment:
[0153] A high-density three-dimensional seismic observation system provided by the present invention is a seismic observation system constructed by adopting the above-mentioned design method of the seismic observation system.
[0154] Computer device embodiment:
[0155] The computer device of this embodiment includes a processor, and when the processor executes a computer program, the steps in the above-mentioned embodiment of the design method of the earthquake observation system are implemented.
[0156] For example, a computer program may be divided into one or more modules, one or more modules are stored in a memory and executed by a processor to implement the present invention. One or more modules may be a series of computer program instruction segments capable of implementing specific functions, and the instruction segments are used to describe the execution process of the computer program in a computer device.
[0157] The computer device may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that the computer device may include more or fewer components, or a combination of certain components, or different components. For example, the computer device may also include input and output devices, network access devices, buses, etc.
[0158] For example, the processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of a computer device, and uses various interfaces and lines to connect various parts of the entire computer device.
[0159] The memory can be used to store computer programs and / or modules. The processor realizes various functions of the computer device by running or executing the computer programs and / or modules stored in the memory, and calling the data stored in the memory. For example, the memory may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound receiving function, a sound conversion to text function, etc.), etc.; the data storage area may store data created according to the use of the mobile phone (such as audio data, text data, etc.), etc. In addition, the memory may include a high-speed random access memory, and may also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.
[0160] Storage medium embodiment:
[0161] If the module integrated in the terminal device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, it can implement each step of the above-mentioned seismic observation system design method.
[0162] Among them, the computer program includes computer program code, which can be in source code form, object code form, executable file or some intermediate form, etc. Computer readable media may include: any entity or device capable of carrying computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer readable media do not include electric carrier signals and telecommunication signals.
[0163] It can be seen that the present invention provides a computer device and a storage medium, which includes: one or more memories, and one or more processors. The memory is used to store program codes and intermediate data generated during program execution, storage of model output results, and storage of models and model parameters; the processor is used for processor resources occupied by code execution and multiple processor resources occupied when training models.
[0164] It should be noted that the above are only preferred embodiments of the present invention, but the design concept of the invention is not limited thereto, and any non-substantial modifications made to the present invention using this concept also fall within the protection scope of the present invention.
Claims
1. A design method for an earthquake observation system, characterized in that: include: Establish genetic algorithm model; Generating a seismically constrained coalfield seismic observation system objective function, including establishing objectives using acoustic wave detection and raw two-dimensional data; planning costs and geophysical constraints; running a constraint algorithm and introducing evolutionary parameters, application data and model constraints to generate the objective function; The objective function is expressed as formula (1): Among them, x max is the maximum offset, x min is the minimum offset, fold deed is the number of times the deeper target layer is covered, fold shallow is the number of first-arrival formation coverages, nc is the total number of received channels, RLI is the receiving line spacing, SLI is the shot row spacing, and x r is the maximum longitudinal offset, x s is the maximum lateral offset; Set up economic cost constraints for seismic exploration, including: Taking the total cost of the seismic observation system per square kilometer as the optimization target, a cost objective function is constructed, wherein the cost objective function includes measurement, arrangement and picking, drilling blastholes and explosives, recording data, and logistics processes; Based on the genetic algorithm model, the feasible solution set of observation system parameters is determined according to the objective function and economic cost constraints; Among them, different feasible solution sets are set, the optimal solution among multiple feasible solution sets is calculated, multiple interval optimal solutions are compared, the optimal observation system parameter combination is output, and a high-density three-dimensional seismic observation system for coalfields is established.
2. The design method of the earthquake observation system according to claim 1, characterized in that: After setting the economic cost constraints, also execute: Based on the genetic algorithm model, determine the genetic operator parameters; Among them, an option set of GA evolution parameters is provided according to the confirmed programming goal, and the GA evolution parameters include genetic algorithm control parameters, population type, population size, generation, migration score, number of elites, mating ratio, creation operator, selection operator, crossover operator and mutation operator.
3. The design method of the earthquake observation system according to claim 2, characterized in that: The genetic algorithm model is established, comprising: Binary encoding: The solution data in the solution space is represented as the genotype string structure data in the genetic space, different points are formed by different combinations of the string structure data, and the initial population is randomly formed, wherein the solution data in the solution space is used as the phenotype form of the genetic algorithm; Generation of initial group: Randomly generate N initial string structure data, each string structure data is called an individual, and N individuals constitute a group; Fitness value evaluation and detection: define the fitness function, and use the fitness function to indicate the quality of individuals or solutions; Selection: Apply the selection operator to the population; Crossover: Apply the crossover operator to the population; Mutation: Apply mutation operators to the population; Termination condition judgment: When the termination condition is met, the individual with the maximum fitness obtained in the evolution process is output as the optimal solution and the operation is terminated.
4. The design method of the earthquake observation system according to claim 1, characterized in that: The optimal solution among the plurality of feasible solution sets is calculated, and the optimal solution parameters include: track spacing, number of receiving lines / number of detectors per line, shot / receiving line spacing SLI / RLI, longitudinal / lateral coverage times, average coverage times of the first target layer / second target layer, maximum closest offset, maximum longitudinal / lateral offset, maximum offset, total number of detectors required, lateral roll, economic cost per square kilometer, and cumulative error; The optimal observation system parameter combination includes: observation system parameters, receiving line spacing, receiving track spacing, excitation point spacing, excitation line spacing, number of receiving tracks, bin size, number of coverage times, beam spacing roll, and aspect ratio; The numerical set of decision variables of the feasible solution set includes RI a 、SI a , nr, ns, NRL, NL; Among them, RI a is the numerical set of receiving point distances, SI a is the numerical set of shot point distances, nr is the set of the number of detectors between two adjacent shot lines, ns is the set of the number of shot points between two adjacent detection lines, NRL is the set of the number of receiving lines, and NL is the set of the number of detectors on each receiving line.
5. A high-density three-dimensional seismic observation system, characterized in that: The system is a seismic observation system constructed using the design method for a seismic observation system as described in any one of claims 1 to 4.
6. A computer device, characterized in that: The computer device includes a processor and a memory, and the processor is used to implement the steps of the design method of the seismic observation system as described in any one of claims 1 to 4 when executing the computer program stored in the memory.
7. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for designing a seismic observation system as claimed in any one of claims 1 to 4 are implemented.