Whale optimization algorithm-based seismic source positioning method, device, equipment and medium

Abstract

This application provides a source location method, device, equipment, and medium based on the whale optimization algorithm, belonging to the field of signal processing technology. The method includes: performing Latin hypercube sampling on the three-dimensional spatial data of the microseismic monitoring target area to obtain a predetermined number of whale population individual position vector data; constructing a fitness function based on the microseismic time difference positioning principle, substituting the whale population individual position vector data into the fitness function for calculation to obtain the current optimal solution individual data; performing iterative processing based on the current optimal solution individual data until the maximum number of iterations is reached, and extracting the coordinates of the final optimal solution individual data to obtain the microseismic source location result data. The source location method, device, equipment, and medium based on the whale optimization algorithm provided in this application can improve the positioning accuracy of microseismic sources.

Description

Technical Field

[0001] This application belongs to the field of signal processing technology, and more specifically, relates to a source localization method, device, equipment, and medium based on the whale optimization algorithm. Background Technology

[0002] In recent years, with the continuous expansion of underground engineering projects such as mines, tunnels, and hydropower projects, the application of microseismic monitoring technology in rock mass stability evaluation and disaster early warning has become increasingly widespread. Microseismic source location is a key issue in microseismic monitoring and rock mass stability analysis, and its results directly affect disaster early warning and safety assessment. Traditional source location methods, such as the Geiger algorithm and Newton's iteration method, typically rely on iterative solutions, are sensitive to initial values, and are prone to slow convergence or getting trapped in local optima under complex geological conditions, making it difficult to guarantee location accuracy and stability. Therefore, it is urgent to optimize existing source location methods to improve their accuracy and stability. Summary of the Invention

[0003] The purpose of this application is to provide a source localization method, apparatus, device, and medium based on the whale optimization algorithm that can improve the localization accuracy of microseismic sources. To achieve the above objective, the technical solution provided by this application is as follows: Firstly, a source localization method based on the whale optimization algorithm is provided, including: Latin hypercube sampling was performed on the three-dimensional spatial data of the microseismic monitoring target area to obtain a set number of whale population individual location vector data. A fitness function is constructed based on the principle of microseismic time difference positioning. The individual position vector data of the whale population is substituted into the fitness function for calculation and processing to obtain the current optimal solution individual data. Based on the current optimal solution individual data, perform iterative processing until the maximum number of iterations is reached. Then, perform coordinate extraction processing on the optimal solution individual data of the final iteration to obtain the microseismic source location result data. The process of one iteration is as follows: The current optimal solution individual data is perturbed by an adversarial learning strategy to obtain new candidate individual data; the new candidate individual data and the original optimal whale individual data are merged to obtain merged population data; the merged population data is then re-substituted into the fitness function for calculation to obtain updated global optimal solution individual data. The optimized convergence factor data is determined based on the hyperbolic form. The optimized convergence factor data is then subjected to parameter extrapolation to obtain the coefficient vector data and distance vector parameter data of the whale optimization algorithm. The updated global optimal solution individual data and the coefficient vector data and distance vector parameter data of the whale optimization algorithm are processed by target predation mechanism to obtain the updated whale population individual position vector data; The updated whale population individual location vector data is substituted into the fitness function to calculate and select the optimal solution individual data for the current iteration; the optimal solution individual data for the current iteration is used as the current optimal solution individual data for the next iteration.

[0004] Secondly, a source localization device based on the whale optimization algorithm is provided, comprising: The sampling and processing module is used to perform Latin hypercube sampling on the three-dimensional spatial data of the microseismic monitoring target area to obtain a set number of whale population individual location vector data. The optimal solution individual data calculation module is used to construct a fitness function based on the microseismic time difference positioning principle, and to substitute the individual position vector data of the whale population into the fitness function for calculation to obtain the current optimal solution individual data; The source location determination module is used to perform iterative processing based on the current optimal solution individual data until the maximum number of iterations is reached, and to perform coordinate extraction processing on the optimal solution individual data of the final iteration to obtain the microseismic source location result data. The process of one iteration is as follows: The current optimal solution individual data is perturbed by an adversarial learning strategy to obtain new candidate individual data; the new candidate individual data and the original optimal whale individual data are merged to obtain merged population data; the merged population data is then re-substituted into the fitness function for calculation to obtain updated global optimal solution individual data. The optimized convergence factor data is determined based on the hyperbolic form. The optimized convergence factor data is then subjected to parameter extrapolation to obtain the coefficient vector data and distance vector parameter data of the whale optimization algorithm. The updated global optimal solution individual data and the coefficient vector data and distance vector parameter data of the whale optimization algorithm are processed by target predation mechanism to obtain the updated whale population individual position vector data; The updated whale population individual location vector data is substituted into the fitness function to calculate and select the optimal solution individual data for the current iteration; the optimal solution individual data for the current iteration is used as the current optimal solution individual data for the next iteration.

[0005] Thirdly, embodiments of this application also provide an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the source localization method based on the whale optimization algorithm provided in any possible implementation of the first aspect.

[0006] Fourthly, embodiments of this application also provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the source localization method based on the whale optimization algorithm provided by any possible implementation of the first aspect.

[0007] The beneficial effects of the technical solution provided in this application are as follows: This application employs the Latin hypercube sampling method to initialize the whale population. Compared to traditional random initialization methods, this ensures the uniformity and diversity of the population's distribution in the three-dimensional solution space of the microseismic monitoring target area, laying a solid foundation for global search. Furthermore, this application introduces an adversarial learning strategy to perturb the current optimal solution and generate new candidate individuals. By merging the population and re-evaluating fitness, it effectively escapes the local optimum trap, avoids the positioning results falling into biased regions, and significantly improves the algorithm's global optimization capability.

[0008] The embodiments of this application adopt a hyperbolic form to dynamically adjust the convergence factor, replacing the linear convergence mechanism of the prior art. By combining the maximum number of iterations and the current number of iterations to deduce the algorithm parameters in real time, a dynamic balance between convergence speed and search accuracy is achieved. This ensures the convergence speed in the later stages of iteration while maintaining the global exploration capability in the early stages of the algorithm, effectively alleviating the problem of premature convergence of the algorithm.

[0009] This application's embodiments update the population location based on a target predation mechanism. By combining optimized coefficients and distance parameters, it accurately simulates whale predation behavior, making the individual location iteration more closely match the actual seismic source search patterns. After multiple rounds of iterative convergence, the final extracted coordinate results possess higher accuracy and stability, meeting the stringent requirements for high-precision microseismic monitoring in underground engineering projects such as mines and tunnels, and providing reliable technical support for rock mass disaster early warning. Attached Figure Description

[0010] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments of this application will be briefly introduced below.

[0011] Figure 1 A flowchart illustrating the source localization method based on the whale optimization algorithm provided in this application embodiment; Figure 2 A flowchart of the whale optimization algorithm provided in the embodiments of this application; Figure 3 A structural block diagram of a seismic source location device based on the whale optimization algorithm provided in this application embodiment; Figure 4 A schematic block diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0012] The embodiments of this application are described below with reference to the accompanying drawings. It should be understood that the embodiments described below with reference to the accompanying drawings are exemplary descriptions for explaining the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions of the embodiments of this application.

[0013] Those skilled in the art will understand that, unless specifically stated otherwise, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. It should be further understood that the terms “comprising” and “including” as used in embodiments of this application mean that the corresponding feature can be implemented as the presented feature, information, data, step, operation, element, and / or component, but do not exclude implementation as other features, information, data, step, operation, element, component, and / or combinations thereof supported by the art. It should be understood that when we say that an element is “connected” or “coupled” to another element, the one element can be directly connected or coupled to the other element, or it can mean that the one element and the other element establish a connection relationship through an intermediate element. Furthermore, “connected” or “coupled” as used herein can include wireless connection or wireless coupling. The term “and / or” as used herein indicates at least one of the items defined by the term; for example, “A and / or B” can be implemented as “A,” or as “B,” or as “A and B.” When describing multiple (two or more) items, if the relationship between the multiple items is not explicitly defined, the multiple items can refer to one, several or all of the multiple items. For example, the description of "parameter A includes A1, A2, A3" can be implemented as parameter A includes A1 or A2 or A3, or it can be implemented as parameter A includes at least two of the three items A1, A2 and A3.

[0014] It is understood that in the embodiments of this application, data such as user information are involved. When the embodiments of this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of related data must comply with relevant laws, regulations and standards.

[0015] To make the objectives, technical solutions, and advantages of this application clearer, the following description will be provided in conjunction with the accompanying drawings and specific embodiments.

[0016] This application provides a source localization method based on the whale optimization algorithm, which can be executed by electronic devices, such as... Figure 1As shown, the method may include: S101: Perform Latin hypercube sampling on the three-dimensional spatial data of the microseismic monitoring target area to obtain a set number of whale population individual location vector data.

[0017] In this embodiment, the three-dimensional spatial data of the microseismic monitoring target area is the three-dimensional coordinate space related data of the microseismic monitoring target area, such as the three-dimensional coordinate range data of the tunnel engineering monitoring area; the Latin hypercube sampling processing is a layered random sampling numerical simulation processing method, such as a processing method that randomly samples and maps the value interval after stratifying the value interval; the set quantity is the total number of whale population individuals set in advance, such as 100; the whale population individual position vector data is vector data representing the position of each individual in the whale population in three-dimensional space, such as vector data composed of three-dimensional coordinate values.

[0018] Latin hypercube sampling is employed because traditional random sampling can easily lead to uneven distribution of the initial population in the solution space. The stratified nature of this sampling method can ensure the uniformity of population distribution, improve population diversity, and lay the foundation for the global search of the algorithm. The number of samples is set to balance the sufficiency of the algorithm's optimization and computational efficiency. Too few samples may lead to blind spots in the search, while too many samples will increase computational redundancy. The sampling results are converted into location vector data because the whale optimization algorithm uses individual location vectors to represent candidate solutions for earthquake source locations. This needs to match the core requirement of three-dimensional localization of microseismic sources and provide suitable initial data for subsequent fitness calculations.

[0019] In this embodiment, firstly, three-dimensional spatial data of the microseismic monitoring target area is acquired. The upper and lower limits of each dimension of the three-dimensional coordinates of the area are determined through engineering surveys, clarifying the spatial range of sampling. A predetermined number of individual whales in the population is set, with specific values ​​determined according to the calculation requirements of microseismic positioning. The value intervals for each dimension of the three-dimensional spatial data of the microseismic monitoring target area are divided equally, with the number of sub-intervals consistent with the predetermined number. Within each sub-interval, a sample value is randomly selected, and the uniformly distributed sample value is mapped to the sample value of each dimension using the inverse distribution function, achieving spatial coordinate transformation of the sample value. The interval numbers for each dimension are randomly arranged to eliminate sampling correlation between dimensions. Three-dimensional sample points are constructed by combining the random arrangement of interval numbers with the sample values ​​of each dimension, and each sample point is converted into a corresponding vector form. A single vector represents the location vector data of a single individual whale in the population. Finally, all constructed vector data are integrated to form a predetermined number of whale population location vector data, completing the Latin hypercube sampling processing of the three-dimensional spatial data of the microseismic monitoring target area.

[0020] In this embodiment, the whale population is initialized by Latin hypercube sampling, which makes the distribution of individual whales in three-dimensional space more uniform, effectively improving the diversity of the initial population and avoiding the problem of concentrated population distribution caused by traditional sampling methods.

[0021] For example, the specific process of this embodiment can be as follows: First, sampling is performed in three-dimensional space, with N whale samples, where N is set to 100. Let the random variable... It is one of the dimensions One of the elements, with the distribution function is The inverse distribution function is ;in, For whale random variables, The probability that X is less than or equal to x; These are uniformly distributed random numbers, typically taking values ​​within the interval [0, 1]. It is the probability that x is greater than or equal to u.

[0022] Then, the value interval [0, 1] is divided into N sub-intervals, that is... Randomly select one within each sub-interval. The sampled value, i.e. These uniformly distributed samples are mapped to random variables using the inverse distribution function. The N sampled values, i.e. .in, This represents the sub-interval number. ; As a dimension, ; For the range of sub-intervals, for The first dimension within A value randomly selected from each sub-interval represents the probability, ranging from 0 to 1.

[0023] Finally, for each dimension Generate a random permutation of interval numbers. , ; by random arrangement Construct sample points .in, For interval numbering, for The first in One element, For the first One sample point, From 1 to N, For the first Weizhongdi Each sample value.

[0024] S102: Based on the principle of microseismic time difference positioning, a fitness function is constructed. The individual position vector data of the whale population is substituted into the fitness function for calculation and processing to obtain the current optimal solution individual data.

[0025] In this embodiment, a fitness function is constructed based on the microseismic time difference positioning principle, including: Based on the microseismic wave velocity, the arrival time of the microseismic signal received by the sensor, the occurrence time of the microseismic source, and the correspondence between the location of the microseismic source and the sensor coordinates, a microseismic source localization expression is constructed. The microseismic source localization expression is then transformed to obtain the fitness function.

[0026] In this embodiment, the microseismic time difference positioning principle is based on the fundamental principle of inverting the microseismic source location based on the time difference of microseismic waves propagating to different sensors. For example, it can be the principle of calculating the spatial distance from the source to the sensor using wave velocity and time difference. The fitness function is a function that measures the quality of candidate solutions of the algorithm. For example, it can be a function that characterizes the deviation between the candidate solution for the source location and the actual location. The microseismic wave velocity is the propagation speed of the microseismic wave in the rock mass of the monitoring area. For example, it can be the measured longitudinal wave propagation speed of the rock mass. The microseismic source occurrence time is the actual time of the microseismic event. The sensor coordinates are the three-dimensional spatial coordinates of the sensors arranged in the monitoring area. The microseismic source positioning expression is a mathematical expression constructed based on the relevant parameters of microseismic positioning. The transformation processing is a method of formally transforming the mathematical expression. The current optimal solution individual data is the optimal whale population individual location vector data selected after the initial calculation of the algorithm.

[0027] The fitness function is constructed based on the principle of microseismic time difference positioning because this principle is the core engineering principle of microseismic source positioning. This ensures that the function fits the actual positioning requirements and avoids the algorithm's optimization from deviating from engineering practice. The microseismic source positioning expression is constructed and then transformed to transform the actual positioning problem into an optimization problem solvable by the whale optimization algorithm, thus achieving the adaptation between the engineering problem and the algorithm. Substituting the individual position vector data of the whale population into the fitness function to calculate and select the optimal solution provides the initial optimal reference for subsequent algorithm iterations, clarifies the initial direction of the algorithm's optimization, and improves the efficiency and targeting of subsequent iterations.

[0028] In this embodiment, the microseismic wave velocity of the monitoring area is first obtained through a combination of engineering geological survey and on-site measurement. During the sensor installation phase, the three-dimensional spatial coordinates of each sensor are accurately calibrated and recorded. Microseismic signals are acquired in real time by the sensors, and the arrival time of the received microseismic signals is extracted. Simultaneously, the relevant calculation benchmarks for the occurrence time of the microseismic source are determined. Based on the principle of microseismic time difference positioning, and combining the correspondence between microseismic wave velocity, sensor arrival time, microseismic source occurrence time, microseismic source location, and sensor coordinates, a microseismic source positioning expression is constructed. This expression is then transformed into a fitness function that can measure the merits of candidate solutions. The obtained whale population individual location vector data are substituted one by one into the constructed fitness function, and the fitness function value for each individual is calculated sequentially. The function calculation results for all whale population individuals are summarized, and the individual with the optimal function value is selected. The relevant data corresponding to this individual is the current optimal solution individual data.

[0029] For example, the specific process of this embodiment can be as follows: Based on the time-difference localization principle of microseismic sources, the localization expression for microseismic sources is as follows:

[0030] in, For microseismic wave velocity; For the first The arrival time of the micro-vibration signal received by the sensor; The moment of occurrence of the microseismic source; The location of the microseismic source. For the first The coordinates of sensor number W are given. The fitness function for microseismic source localization is obtained by transforming the expression for microseismic source localization, as shown below:

[0031] Substitute the location vectors of all whale population individuals into the fitness function to calculate the corresponding fitness function values, and select the whale individual with the smallest fitness function value as the current optimal solution individual data.

[0032] S103: Based on the current optimal solution individual data, perform iterative processing until the maximum number of iterations is reached. Then, perform coordinate extraction processing on the optimal solution individual data of the final iteration to obtain the microseismic source location result data. The process of one iteration is as follows: The current optimal solution individual data is perturbed by an adversarial learning strategy to obtain new candidate individual data; the new candidate individual data and the original optimal whale individual data are merged to obtain merged population data; the merged population data is re-substituted into the fitness function for calculation to obtain the updated global optimal solution individual data. The optimized convergence factor data is determined based on the hyperbolic form. The optimized convergence factor data is then subjected to parameter extrapolation to obtain the coefficient vector data and distance vector parameter data of the whale optimization algorithm. The updated global optimal solution individual data and the coefficient vector data and distance vector parameter data of the whale optimization algorithm are processed by target predation mechanism to obtain the updated whale population individual position vector data; The updated whale population individual location vector data is substituted into the fitness function to calculate and select the optimal solution individual data for the current iteration; the optimal solution individual data for the current iteration is used as the current optimal solution individual data for the next iteration.

[0033] In this embodiment, the adversarial learning strategy is as follows:

[0034] in, For the first The position of the whale individual after sensor t+1 iterations, i.e., the data of the new candidate individuals; is a random number; a is the lower bound vector of the individual whale's coordinate range; b is the upper bound vector of the individual whale's coordinate range. For the first The position of the optimal solution individual after t iterations of sensor number 1, i.e., the current optimal solution individual data.

[0035] In this embodiment, the optimized convergence factor data is determined based on a hyperbolic form, including: Based on the preset maximum number of iterations and the current number of iterations of the whale optimization algorithm, a hyperbolic convergence factor optimization expression is constructed. The current number of iterations of the whale optimization algorithm is substituted into the convergence factor optimization expression for calculation to obtain the optimized convergence factor data. The convergence factor optimization expression is as follows:

[0036] in, For the optimized convergence factor data, The preset maximum number of iterations, This represents the current iteration number of the whale optimization algorithm.

[0037] In this embodiment, the optimized convergence factor data is subjected to parameter extrapolation processing to obtain the coefficient vector data and distance vector parameter data of the whale optimization algorithm, including: The coefficient vector data is calculated based on the optimized convergence factor data and the control parameters of the whale optimization algorithm. Distance vector parameter data is calculated based on coefficient vector data, updated global optimal solution individual data, and random whale individual position vector data.

[0038] In this embodiment, iterative processing refers to repeatedly executing the same computational process to optimize the solution, such as repeatedly executing perturbation, parameter update, and position optimization computational processes; the maximum number of iterations is a pre-set total number of iterations, such as 100 times; adversarial learning strategy perturbation processing is a processing method that perturbs the optimal solution based on an adversarial learning strategy to generate a new solution. The original optimal whale individual data is the initial optimal whale individual position vector data before iteration; merging processing is a processing method that integrates different individual data; the hyperbolic form is a dynamic adjustment form of the convergence factor; the control parameter is a fixed adjustment parameter preset by the algorithm, such as 0.5; random whale individual position vector data is individual position vector data randomly selected from the whale population; coordinate extraction processing is a processing method that extracts three-dimensional coordinates from the optimal solution individual data; and microseismic source location result data is coordinate data characterizing the actual three-dimensional position of the microseismic source.

[0039] Iterative processing is employed to gradually approximate the actual location of the microseismic source through multiple optimizations. The maximum number of iterations balances optimization sufficiency with computational efficiency. Adversarial learning perturbation breaks the limitations of local optima, increasing the diversity of solutions. Merging the population and recalculating fitness selects a better global solution from the old and new optima, ensuring the effectiveness of the optimization. Optimizing the convergence factor using a hyperbolic form dynamically balances the algorithm's global search and local exploitation capabilities. Parameter extrapolation provides suitable computational parameters for the predation mechanism, which is the core method for optimizing the population location. Continuous iterative updates of the optimal solution ultimately lead to high-precision positioning results.

[0040] In this embodiment, the current optimal solution individual data is used as the initial data for iteration. Iterative processing is initiated, firstly by performing adversarial learning strategy perturbation processing. Random numbers within a preset interval are selected to determine the lower and upper bound vectors of the whale individual's coordinate range. Combined with the current optimal solution individual data, new candidate individual data is generated according to the adversarial learning strategy. The new candidate individual data is merged with the original optimal whale individual data to obtain merged population data. This merged population data is then substituted into the fitness function for recalculation, and updated global optimal solution individual data is obtained. A maximum number of iterations is preset. Combined with the current iteration count of the whale optimization algorithm, a hyperbolic convergence factor optimization expression is constructed. This expression is then substituted into the current iteration count to calculate the optimized convergence factor data. Pre-set control parameters are selected, and coefficient vector data is derived from the optimized convergence factor data. Then, random individuals are selected from the whale population to obtain random whale individual position vector data. Combined with the coefficient vector data and the updated global optimal solution individual data, distance vector parameter data is derived. The updated global optimal solution individual data is processed by target predation mechanism calculation with the above coefficient and distance vector parameter data to obtain updated whale population individual position vector data. This data is then substituted into the fitness function to calculate and select the optimal solution individual data for the current iteration. This data is used as the current optimal solution individual data for the next iteration. The above process is repeated until the number of iterations reaches the preset maximum number of iterations. Finally, the coordinates of the optimal solution individual data in the final iteration are extracted to obtain the microseismic source location results data.

[0041] For example, the specific process of this embodiment can be as follows: To improve the solution performance of the whale optimization algorithm, an adversarial learning strategy is introduced, as shown in the following expression:

[0042] in, For the first The position of the whale individual after sensor t+1 iterations, i.e., the data of the new candidate individuals; The result is a random number, with a range of [0,1]. In this embodiment, we can take... 0.3, 0.5, 0.7, 1; a is the lower limit vector of the individual whale's coordinate range; b is the upper limit vector of the individual whale's coordinate range; For the first The position of the optimal solution individual after t iterations of the sensor, i.e., the current optimal solution individual data. When t=1, it indicates the position of the optimal solution individual after the first iteration.

[0043] In each iteration, after obtaining the current optimal solution, a new candidate individual is generated by adversarially perturbing the optimal position. Subsequently, the new individual is added to the population along with the original optimal individual, the fitness function is recalculated, and the global optimal solution is updated and selected based on this.

[0044] Then, a hyperbolic form is established to optimize the convergence factor, as shown in the following expression:

[0045] in, For the optimized convergence factor data, The preset maximum number of iterations, This represents the current iteration number of the whale optimization algorithm.

[0046] This embodiment uses a hyperbolic form so that the convergence is slower in the early stage, focusing on global search; and faster in the later stage, focusing on local search.

[0047] The coefficient vector data are A and C, and their expressions are as follows:

[0048]

[0049] in, The control parameters for the whale optimization algorithm are in the range [0,1], and can be taken as follows: It is 0.5.

[0050] The distance vector data are D1 and D2, and their expressions are as follows:

[0051]

[0052] in, This represents the individual location of a random whale.

[0053] Finally, the updated whale population individual location vector data is substituted into the fitness function to calculate and select the whale with the smallest fitness function value, and its corresponding whale is taken as the current optimal individual. The algorithm proceeds to the next iteration before the maximum number of iterations is reached and the number of whales does not exceed a set range. This process is repeated until the maximum number of iterations is reached. The final output of the optimal whale is the location result, and its corresponding coordinates are the location of the microseismic source. The flowchart of the whale optimization algorithm is as follows: Figure 2 As shown.

[0054] As can be seen from the above, the embodiment of this application uses the Latin hypercube sampling method to initialize the whale population. Compared with the traditional random initialization method, this ensures the uniformity and diversity of the population distribution in the three-dimensional solution space, laying a solid foundation for global search. Furthermore, this embodiment introduces an adversarial learning strategy to perturb the current optimal solution and generate new candidate individuals. By merging the population and re-evaluating fitness, it effectively escapes the local optimum trap, avoids the localization results falling into biased regions, and significantly improves the algorithm's global optimization capability.

[0055] The embodiments of this application adopt a hyperbolic form to dynamically adjust the convergence factor, replacing the linear convergence mechanism of the prior art. By combining the maximum number of iterations and the current number of iterations to deduce the algorithm parameters in real time, a dynamic balance between convergence speed and search accuracy is achieved. This ensures the convergence speed in the later stages of iteration while maintaining the global exploration capability in the early stages of the algorithm, effectively alleviating the problem of premature convergence of the algorithm.

[0056] This application's embodiments update the population location based on a target predation mechanism. By combining optimized coefficients and distance parameters, it accurately simulates whale predation behavior, making the individual location iteration more closely match the actual seismic source search patterns. After multiple rounds of iterative convergence, the final extracted coordinate results possess higher accuracy and stability, meeting the stringent requirements for high-precision microseismic monitoring in underground engineering projects such as mines and tunnels, and providing reliable technical support for rock mass disaster early warning.

[0057] In one embodiment of this application, the seismic source localization method based on the whale optimization algorithm further includes: Select random numbers from a preset range; The target predation mechanism is determined based on coefficient vector data of random numbers and whale optimization algorithm.

[0058] In this embodiment, the target predation mechanism includes a spiral bubble net attack mechanism, a prey encirclement mechanism, and a prey search mechanism. The target predation mechanism is determined based on random numbers and the coefficient vector data of the whale optimization algorithm, including: If the random number is greater than or equal to the first preset value, the spiral bubble net attack mechanism will be determined as the target predation mechanism. If the random number is less than the first preset value and the absolute value of the coefficient vector data of the whale optimization algorithm is less than the second preset value, then the hunting mechanism is determined as the target predation mechanism. If the random number is less than the first preset value and the absolute value of the coefficient vector data of the whale optimization algorithm is greater than or equal to the second preset value, then the prey search mechanism is determined as the target predation mechanism.

[0059] In this embodiment, the preset interval is a pre-defined range of random numbers, such as a range of 0 to 1; the first preset value is the first value used to determine the target predation mechanism, such as 0.5; the second preset value is the second value used to determine the target predation mechanism, such as 1; the spiral bubble net attack mechanism is an algorithm that simulates a whale spiraling towards its prey; the prey encirclement mechanism is an algorithm that simulates a whale group encircling and approaching the optimal solution; and the prey search mechanism is an algorithm that simulates a whale searching for prey over a wide area.

[0060] Selecting random numbers from a preset range ensures the choice of predation mechanism is random, preventing the algorithm from becoming monotonous and limiting its optimization capabilities due to fixed mechanisms. The dual-determination mechanism using both random numbers and coefficient vector data ensures that mechanism selection balances randomness with the algorithm's real-time optimization state, matching the needs of different stages of the algorithm. The spiral rotation and encirclement mechanisms are suitable for fine-grained local optimization, while the search mechanism is suitable for large-scale global optimization. Through layered determination using dual preset values, the algorithm can dynamically switch predation mechanisms, balancing global search and local exploitation capabilities, and avoiding insufficient optimization or getting trapped in local optima caused by a single mechanism. In this embodiment, using random numbers to determine the target predation mechanism broadens the search range and reduces the likelihood of getting trapped in local optima.

[0061] In this embodiment, a preset interval for random numbers is first defined and fixed. Random numbers meeting the algorithm requirements are selected from this preset interval using a random number generation method. Simultaneously, based on the algorithm requirements for microseismic source localization, a first preset value and a second preset value are preset and fixed. The coefficient vector data of the whale optimization algorithm, obtained through parameter extrapolation during the current iteration, is acquired, and its absolute value is calculated numerically. The selected random number is compared with the first preset value. If the random number is greater than or equal to the first preset value, the spiral bubble net attack mechanism is directly identified as the current target predation mechanism. If the random number is less than the first preset value, the absolute value of the coefficient vector data is further compared with the second preset value. If the absolute value is less than the second preset value, the prey-hunting mechanism is identified as the target predation mechanism; if the absolute value is greater than or equal to the second preset value, the prey-searching mechanism is identified as the target predation mechanism. After the determination, the identified target predation mechanism is used as the sole basis for subsequent whale population individual position vector calculations.

[0062] For example, the method for determining the target predation mechanism can be as follows: (1) p is a random number in [0,1] in the whale optimization algorithm. When p is greater than or equal to 0.5, the spiral bubble net attack mechanism is selected. is the distance between the optimal position and the current position; b is the coefficient defining the spiral curve, set to 0.1; A random number in the range [-1, 1], with a value of 0.5. The expression for the spiral bubble web attack mechanism is as follows:

[0063]

[0064] (2) p is less than 0.5 When the time comes, select the hunt-and-hunt mechanism. The expression for the hunt-and-hunt mechanism is as follows:

[0065] (3) p is less than 0.5 When selecting the prey search mechanism, the expression for the prey search mechanism is as follows:

[0066] This embodiment can select random numbers from a preset range, allowing the selection of the target predation mechanism to break free from a fixed pattern and improve the flexibility of the algorithm's optimization. By combining the hierarchical judgment rules of random numbers and coefficient vector data, precise adaptation between the predation mechanism and the algorithm's real-time optimization state is achieved. The dynamic switching of the three predation mechanisms effectively balances the algorithm's global search and local exploitation capabilities, ensuring that the algorithm can search for microseismic source candidate solutions over a wide range while also performing fine-grained optimization within the optimal solution region, avoiding the algorithm from getting trapped in local optima, and laying the foundation for subsequent precise updates to the population location vector.

[0067] Figure 2 The flowchart of the whale optimization algorithm provided in this application embodiment is as follows: This application embodiment initializes individual whales through Latin hypercube sampling, that is, it initializes the whale population through Latin hypercube sampling to obtain a set number of whale population individual location vector data; it calculates the fitness function of individual whales, that is, it constructs a fitness function based on the microseismic time difference positioning principle, and substitutes the whale population individual location vector data into the fitness function for calculation to obtain the current optimal solution individual data; it adds an adversarial learning strategy, that is, it applies an adversarial learning strategy perturbation to the current optimal solution individual data to obtain new candidate individual data; it calculates the nonlinear convergence factor, that is, it determines the optimized convergence factor data based on hyperbolic form, and performs parameter extrapolation processing on the optimized convergence factor data to obtain the coefficient vector data and distance vector parameter data of the whale optimization algorithm; it updates the parameters and performs... The condition judgment, when it is not satisfied When the optimal solution is met, output the optimal solution; when the optimal solution is met, output the optimal solution. Continue to judge When not satisfied When t=t+1, repeat the step of adding the adversarial learning strategy; when the condition is met... Continue to judge When not satisfied When the conditions are met, the spiral bubble net attack mechanism is selected as the target predation mechanism; when the conditions are met... Continue to judge When not satisfied When the prey-hunting mechanism is selected as the target-prey mechanism, and the conditions are met... At that time, the prey-hunting mechanism is selected as the target predation mechanism.

[0068] Based on the same principle as the source location method based on the whale optimization algorithm provided in the embodiments of this application, the embodiments of this application also provide a source location device based on the whale optimization algorithm, such as... Figure 3 As shown, the source location device 20 based on the whale optimization algorithm may specifically include: a sampling processing module 21, an optimal solution individual data calculation module 22, and a source location determination module 23. The sampling processing module 21 is used to perform Latin hypercube sampling processing on the three-dimensional spatial data of the microseismic monitoring target area to obtain a set number of whale population individual location vector data. The optimal solution individual data calculation module 22 is used to construct a fitness function based on the microseismic time difference positioning principle, and to substitute the individual position vector data of the whale population into the fitness function for calculation and processing to obtain the current optimal solution individual data. The source location determination module 23 is used to perform iterative processing based on the current optimal solution individual data until the maximum number of iterations is reached, and to perform coordinate extraction processing on the optimal solution individual data of the final iteration to obtain the microseismic source location result data. The process of one iteration is as follows: The current optimal solution individual data is perturbed by an adversarial learning strategy to obtain new candidate individual data; the new candidate individual data and the original optimal whale individual data are merged to obtain merged population data; the merged population data is re-substituted into the fitness function for calculation to obtain the updated global optimal solution individual data. The optimized convergence factor data is determined based on the hyperbolic form. The optimized convergence factor data is then subjected to parameter extrapolation to obtain the coefficient vector data and distance vector parameter data of the whale optimization algorithm. The updated global optimal solution individual data and the coefficient vector data and distance vector parameter data of the whale optimization algorithm are processed by target predation mechanism to obtain the updated whale population individual position vector data; The updated whale population individual location vector data is substituted into the fitness function to calculate and select the optimal solution individual data for the current iteration; the optimal solution individual data for the current iteration is used as the current optimal solution individual data for the next iteration.

[0069] In one embodiment of this application, the optimal solution individual data calculation module 22 is specifically used to construct a microseismic source location expression based on the microseismic wave velocity, the arrival time of the microseismic signal received by the sensor, the occurrence time of the microseismic source, and the correspondence between the microseismic source location and the sensor coordinates, and to transform the microseismic source location expression to obtain the fitness function.

[0070] In one embodiment of this application, the adversarial learning strategy is:

[0071] in, For the first The position of the whale individual after sensor t+1 iterations, i.e., the data of the new candidate individuals; is a random number; a is the lower bound vector of the individual whale's coordinate range; b is the upper bound vector of the individual whale's coordinate range. For the first The position of the optimal solution individual after t iterations of sensor number 1, i.e., the current optimal solution individual data.

[0072] In one embodiment of this application, the source location determination module 23 is specifically used to construct a hyperbola-shaped convergence factor optimization expression based on the preset maximum number of iterations and the current number of iterations of the whale optimization algorithm, and to calculate the optimized convergence factor data by substituting the current number of iterations of the whale optimization algorithm into the convergence factor optimization expression. The convergence factor optimization expression is as follows:

[0073] in, For the optimized convergence factor data, The preset maximum number of iterations, This represents the current iteration number of the whale optimization algorithm.

[0074] In one embodiment of this application, the source location determination module 23 is specifically used to calculate coefficient vector data based on the optimized convergence factor data and the control parameters of the whale optimization algorithm; Distance vector parameter data is calculated based on coefficient vector data, updated global optimal solution individual data, and random whale individual position vector data.

[0075] In one embodiment of this application, the source location device 20 based on the whale optimization algorithm further includes: a target predation mechanism determination module, used to select random numbers from a preset interval; The target predation mechanism is determined based on coefficient vector data of random numbers and whale optimization algorithm.

[0076] In one embodiment of this application, the target predation mechanism includes a spiral bubble net attack mechanism, a prey encirclement mechanism, and a prey search mechanism; the target predation mechanism determination module is specifically used to determine the spiral bubble net attack mechanism as the target predation mechanism if the random number is greater than or equal to a first preset value. If the random number is less than the first preset value and the absolute value of the coefficient vector data of the whale optimization algorithm is less than the second preset value, then the hunting mechanism is determined as the target predation mechanism. If the random number is less than the first preset value and the absolute value of the coefficient vector data of the whale optimization algorithm is greater than or equal to the second preset value, then the prey search mechanism is determined as the target predation mechanism.

[0077] The apparatus in this application embodiment can execute the method provided in this application embodiment, and the implementation principle is similar. The actions performed by each module in the apparatus of each embodiment of this application correspond to the steps in the method of each embodiment of this application. For detailed functional descriptions of each module of the apparatus, please refer to the descriptions in the corresponding methods shown above, which will not be repeated here.

[0078] Figure 4 A schematic diagram of the structure of an electronic device to which this application embodiment applies is shown, such as... Figure 4 As shown, the electronic device can be used to implement the methods provided in any embodiment of this application.

[0079] like Figure 4 As shown, the electronic device 300 may primarily include at least one processor 301. Figure 4 The diagram shows components such as a memory 302, a communication module 303, and an input / output interface 304. Optionally, these components can be connected and communicate with each other via a bus 305. It should be noted that... Figure 4 The structure of the electronic device 300 shown is merely illustrative and does not constitute a limitation on the electronic devices to which the methods provided in the embodiments of this application are applicable.

[0080] The memory 302 can be used to store operating systems and applications, etc. The applications can include computer programs that implement the methods shown in the embodiments of this application when invoked by the processor 301, and can also include programs for implementing other functions or services. The memory 302 can be ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, RAM (Random Access Memory) or other types of dynamic storage devices that can store information and computer programs, or it can be EEPROM (Electrically Erasable Programmable Read Only Memory), CD-ROM (Compact Disc Read Only Memory) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer, but is not limited thereto.

[0081] Processor 301 is connected to memory 302 via bus 305 and implements corresponding functions by calling the application programs stored in memory 302. Processor 301 can be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 301 can also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0082] Electronic device 300 can connect to a network via communication module 303 (which may include, but is not limited to, components such as a network interface) to communicate with other devices (such as user terminals or servers) through the network and achieve data interaction, such as sending data to or receiving data from other devices. Communication module 303 may include wired network interfaces and / or wireless network interfaces, meaning the communication module may include at least one of wired or wireless communication modules.

[0083] The electronic device 300 can connect to necessary input / output devices, such as a keyboard and display device, via the input / output interface 304. The electronic device 300 itself may have a display device, and other display devices can also be connected externally via the interface 304. Optionally, a storage device, such as a hard drive, can also be connected via the interface 304 to store data from the electronic device 300, retrieve data from the storage device, or store data from the storage device in the memory 302. It is understood that the input / output interface 304 can be a wired interface or a wireless interface. Depending on the actual application scenario, the device connected to the input / output interface 304 can be a component of the electronic device 300 or an external device connected to the electronic device 300 when needed.

[0084] The bus 305 used to connect the components may include a path for transmitting information between the components. The bus 305 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Depending on its function, the bus 305 may be divided into an address bus, a data bus, a control bus, etc.

[0085] Optionally, for the solution provided in the embodiments of this application, the memory 302 can be used to store a computer program that executes the solution of this application, and the processor 301 runs the computer program. When the processor 301 runs the computer program, it implements the operation of the method or apparatus provided in the embodiments of this application.

[0086] Based on the same principle as the method provided in the embodiments of this application, the embodiments of this application provide a computer-readable storage medium storing a computer program, which, when executed by a processor, can implement the corresponding content of the aforementioned method embodiments.

[0087] It should be noted that the terms "first," "second," "third," "fourth," "1," "2," etc. (if present) in the specification, claims, and accompanying drawings of this application 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 this application described herein can be implemented in a sequence other than that shown in the figures or text.

[0088] In the embodiments of this application, the terms "module" or "unit" refer to a computer program or part of a computer program that has a predetermined function and works with other related parts to achieve a predetermined goal, and can be implemented wholly or partially using software, hardware (such as processing circuitry or memory), or a combination thereof. Similarly, a processor (or multiple processors or memory) can be used to implement one or more modules or units. Furthermore, each module or unit can be part of an overall module or unit that includes the functionality of that module or unit.

[0089] It should be understood that although arrows indicate various operation steps in the flowcharts of this application's embodiments, the order in which these steps are implemented is not limited to the order indicated by the arrows. Unless explicitly stated herein, in some implementation scenarios of this application's embodiments, the implementation steps in each flowchart can be executed in other orders as required. Furthermore, some or all steps in each flowchart, based on the actual implementation scenario, may include multiple sub-steps or multiple stages. Some or all of these sub-steps or stages can be executed at the same time, and each sub-step or stage can also be executed at different times. In scenarios where execution times differ, the execution order of these sub-steps or stages can be flexibly configured according to requirements, and this application's embodiments do not limit this.

[0090] The above description is only an optional implementation method for some implementation scenarios of this application. It should be noted that for those skilled in the art, other similar implementation methods based on the technical concept of this application without departing from the technical concept of this application also fall within the protection scope of the embodiments of this application.

Claims

1. A source localization method based on the whale optimization algorithm, characterized in that, include: Latin hypercube sampling was performed on the three-dimensional spatial data of the microseismic monitoring target area to obtain a set number of whale population individual location vector data. A fitness function is constructed based on the principle of microseismic time difference positioning. The individual position vector data of the whale population is substituted into the fitness function for calculation and processing to obtain the current optimal solution individual data. Based on the current optimal solution individual data, perform iterative processing until the maximum number of iterations is reached. Then, perform coordinate extraction processing on the optimal solution individual data of the final iteration to obtain the microseismic source location result data. The process of one iteration is as follows: The current optimal solution individual data is perturbed by an adversarial learning strategy to obtain new candidate individual data; the new candidate individual data and the original optimal whale individual data are merged to obtain merged population data; the merged population data is then re-substituted into the fitness function for calculation to obtain updated global optimal solution individual data. The optimized convergence factor data is determined based on the hyperbolic form. The optimized convergence factor data is then subjected to parameter extrapolation to obtain the coefficient vector data and distance vector parameter data of the whale optimization algorithm. The updated global optimal solution individual data and the coefficient vector data and distance vector parameter data of the whale optimization algorithm are processed by target predation mechanism to obtain the updated whale population individual position vector data; The updated whale population individual location vector data is substituted into the fitness function to calculate and select the optimal solution individual data for the current iteration; the optimal solution individual data for the current iteration is used as the current optimal solution individual data for the next iteration.

2. The earthquake source localization method based on the whale optimization algorithm as described in claim 1, characterized in that, The fitness function constructed based on the microseismic time difference positioning principle includes: Based on the microseismic wave velocity, the arrival time of the microseismic signal received by the sensor, the occurrence time of the microseismic source, and the correspondence between the location of the microseismic source and the sensor coordinates, a microseismic source localization expression is constructed. The fitness function is obtained by transforming the microseismic source localization expression.

3. The source localization method based on the whale optimization algorithm as described in claim 1, characterized in that, The adversarial learning strategy is as follows: in, For the first The position of the whale individual after sensor t+1 iterations, i.e., the data of the new candidate individuals; is a random number; a is the lower bound vector of the individual whale's coordinate range; b is the upper bound vector of the individual whale's coordinate range. For the first The position of the optimal solution individual after t iterations of sensor number 1, i.e., the current optimal solution individual data.

4. The source localization method based on the whale optimization algorithm as described in claim 1, characterized in that, The convergence factor data determined based on hyperbolic form includes: Based on the preset maximum number of iterations and the current number of iterations of the whale optimization algorithm, a hyperbolic convergence factor optimization expression is constructed. The current number of iterations of the whale optimization algorithm is substituted into the convergence factor optimization expression for calculation to obtain the optimized convergence factor data. The convergence factor optimization expression is as follows: in, For the optimized convergence factor data, The preset maximum number of iterations, This represents the current iteration number of the whale optimization algorithm.

5. The source localization method based on the whale optimization algorithm as described in claim 1, characterized in that, The parameter extrapolation processing of the optimized convergence factor data yields the coefficient vector data and distance vector parameter data of the whale optimization algorithm, including: The coefficient vector data is calculated based on the optimized convergence factor data and the control parameters of the whale optimization algorithm. The distance vector parameter data is calculated based on the coefficient vector data, the updated global optimal solution individual data, and the random whale individual position vector data.

6. The source localization method based on the whale optimization algorithm as described in claim 1, characterized in that, The source localization method based on the whale optimization algorithm also includes: Select random numbers from a preset range; The target predation mechanism is determined based on the random number and the coefficient vector data of the whale optimization algorithm.

7. The source localization method based on the whale optimization algorithm as described in claim 6, characterized in that, The target predation mechanism includes a spiral bubble web attack mechanism, a prey encirclement mechanism, and a prey search mechanism; the determination of the target predation mechanism based on the coefficient vector data of the random number and the whale optimization algorithm includes: If the random number is greater than or equal to the first preset value, then the spiral bubble net attack mechanism is determined as the target predation mechanism; If the random number is less than the first preset value and the absolute value of the coefficient vector data of the whale optimization algorithm is less than the second preset value, then the hunting mechanism is determined as the target predation mechanism. If the random number is less than the first preset value and the absolute value of the coefficient vector data of the whale optimization algorithm is greater than or equal to the second preset value, then the prey search mechanism is determined as the target predation mechanism.

8. A source location device based on the whale optimization algorithm, characterized in that, include: The sampling and processing module is used to perform Latin hypercube sampling on the three-dimensional spatial data of the microseismic monitoring target area to obtain a set number of whale population individual location vector data. The optimal solution individual data calculation module is used to construct a fitness function based on the microseismic time difference positioning principle, and to substitute the individual position vector data of the whale population into the fitness function for calculation to obtain the current optimal solution individual data; The source location determination module is used to perform iterative processing based on the current optimal solution individual data until the maximum number of iterations is reached, and to perform coordinate extraction processing on the optimal solution individual data of the final iteration to obtain the microseismic source location result data. The process of one iteration is as follows: The current optimal solution individual data is perturbed by an adversarial learning strategy to obtain new candidate individual data; the new candidate individual data and the original optimal whale individual data are merged to obtain merged population data; the merged population data is then re-substituted into the fitness function for calculation to obtain updated global optimal solution individual data. The optimized convergence factor data is determined based on the hyperbolic form. The optimized convergence factor data is then subjected to parameter extrapolation to obtain the coefficient vector data and distance vector parameter data of the whale optimization algorithm. The updated global optimal solution individual data and the coefficient vector data and distance vector parameter data of the whale optimization algorithm are processed by target predation mechanism to obtain the updated whale population individual position vector data; The updated whale population individual location vector data is substituted into the fitness function to calculate and select the optimal solution individual data for the current iteration; the optimal solution individual data for the current iteration is used as the current optimal solution individual data for the next iteration.

9. An electronic device, characterized in that, The electronic device includes a memory and a processor. The memory stores a computer program, and the processor executes the source localization method based on the whale optimization algorithm according to any one of claims 1 to 7 when running the computer program.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the source localization method based on the whale optimization algorithm as described in any one of claims 1 to 7.

Images