Method and system for building a seismic monitoring platform based on a fiber optic seismometer

Abstract

The present application relates to the field of optical fiber sensing technology, and particularly to a method and system for building a seismic monitoring platform based on an optical fiber seismometer, a three-dimensional geological model of a monitoring area is constructed based on multi-source geological data of the monitoring area; a grid element in the three-dimensional geological model is taken as a virtual particle, and the position, motion direction and chemotaxis parameter of each virtual particle are initialized; the intensity of a seismic precursor signal of the grid element is determined as the concentration of a chemical attractant of the virtual particle; a phototaxis mechanism is introduced to simulate the group motion behavior of the virtual particle under the concentration gradient of the chemical attractant, and the final distribution density map of the virtual particle is obtained; according to the final distribution density map of the virtual particle, an optimal layout map of the optical fiber seismometer in the monitoring area is determined, and the seismic monitoring platform is built according to the optimal layout map, the present application can accurately identify a potential seismic source area, dynamically adapt to changes in the geological environment, and improve the coverage accuracy and response capability of the seismic monitoring platform.

Description

Technical Field

[0001] This invention relates to the field of fiber optic sensing technology, and in particular to a method and system for building an earthquake monitoring platform based on a fiber optic seismometer. Background Technology

[0002] Earthquake monitoring is a crucial component of geological disaster early warning and mitigation. Traditional earthquake monitoring platforms typically rely on fixed seismograph networks, whose deployment is often based on experience or simple statistical models, making them ill-suited for monitoring needs in complex geological environments. With the development of fiber optic sensing technology, fiber optic seismographs, due to their high sensitivity, resistance to electromagnetic interference, and long-distance monitoring capabilities, have gradually become core equipment for earthquake monitoring. However, existing fiber optic seismograph monitoring systems still suffer from the following problems: first, a lack of deep fusion of multi-source geological data makes it difficult to accurately identify potential seismic source areas; second, deployment strategies rely heavily on human experience, failing to dynamically adapt to changes in the geological environment; and third, uneven resource allocation leads to monitoring blind spots or resource waste. Therefore, this paper aims to develop an intelligent earthquake monitoring platform construction method and system based on fiber optic seismographs to provide more efficient and accurate technical support for earthquake monitoring. Summary of the Invention

[0003] This invention overcomes the shortcomings of the prior art and provides a method and system for building an earthquake monitoring platform based on a fiber optic seismometer.

[0004] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0005] The first aspect of this invention discloses a method for constructing a seismic monitoring platform based on a fiber optic seismometer, comprising the following steps:

[0006] A three-dimensional geological model of the monitoring area was constructed based on multi-source geological data of the monitoring area.

[0007] The grid cells in the 3D geological model are treated as virtual particles, and the position, direction of motion, and chemotaxis parameters of each virtual particle are initialized.

[0008] Based on multi-source geological data, the intensity of earthquake precursor signals in each grid cell is determined as the concentration of chemical attractant for virtual particles;

[0009] A phototaxis mechanism was introduced to simulate the collective motion behavior of virtual particles under a chemical attractant concentration gradient, and the final distribution density map of the virtual particles was obtained.

[0010] Based on the final distribution density map of the virtual particles, the optimal layout of fiber optic seismometers in the monitoring area is determined, and the seismic monitoring platform is built according to the optimal layout map.

[0011] Preferably, a three-dimensional geological model of the monitoring area is constructed based on multi-source geological data of the monitoring area, specifically as follows:

[0012] Acquire multi-source geological data for the monitoring area, including the distribution of historical earthquake events, fault zone locations, crustal stress field distribution, changes in resistivity, radon concentration, temperature changes, geomagnetic anomalies, and groundwater level data;

[0013] Align multi-source geological data according to spatial location and unify the coordinate system to form the basic framework for multi-source data fusion;

[0014] Based on geostatistical methods, the correlation between various geological parameters is analyzed, and a mapping relationship model between the parameters is constructed.

[0015] The monitoring area was divided into multiple grid units using a three-dimensional gridding method, and each unit was assigned a corresponding geological attribute value.

[0016] The gridded data is rendered into a 3D geological model using 3D visualization tools, and the realism of the model is enhanced by lighting and texture.

[0017] The constructed 3D geological model is validated. If the model accuracy does not reach the preset accuracy threshold, the mesh density is adjusted until the model accuracy meets the requirements, thus completing the construction of the 3D geological model.

[0018] Preferably, the grid cells in the three-dimensional geological model are treated as virtual particles, and the position, direction of motion, and chemotaxis parameters of each virtual particle are initialized, specifically as follows:

[0019] Based on the aforementioned three-dimensional geological model, each grid cell is defined as a virtual particle and assigned a unique identifier.

[0020] Based on the geological attribute values ​​of the grid cells, including the rate of change of resistivity, radon concentration gradient and crustal stress intensity, the initial chemotaxis parameters of each virtual particle are determined. If the geological attribute value is higher than the preset attribute threshold, the virtual particle is defined as having high chemotaxis sensitivity; otherwise, it is defined as having low chemotaxis sensitivity.

[0021] Each virtual particle is randomly initialized with a direction of motion, and its initial coordinates are determined based on its spatial position within the grid cell.

[0022] Based on the geological characteristics of the monitoring area, the movement step size and maximum number of iterations of the virtual particles are set; if the grid cell is located in a fault zone, the movement step size is shortened according to the preset amplitude.

[0023] Subsequently, a random perturbation factor was introduced to simulate the uncertainty in the geological environment, and a random offset was added to the motion direction of each virtual particle to avoid the virtual particles getting trapped in local optima;

[0024] The initialization parameters of all virtual particles are verified. If any parameters are found to be abnormal or exceed the preset range, they are recalculated and adjusted until the initialization parameters of all virtual particles meet the requirements, thus completing the initialization configuration of the virtual particles.

[0025] Preferably, based on multi-source geological data, the intensity of the earthquake precursor signal for each grid cell is determined as the concentration of the chemical attractant for the virtual particles, specifically as follows:

[0026] Data on the rate of change of resistivity and radon concentration in the monitoring area are obtained. The gradient of the rate of change of resistivity for each grid cell is calculated. If the gradient of the rate of change of resistivity is higher than the preset threshold of the rate of change of resistivity, the corresponding grid cell is marked as a high-change area; otherwise, it is marked as a low-change area.

[0027] Calculate the radon concentration gradient for each grid cell. If the radon concentration gradient is higher than the preset radon concentration gradient threshold, mark the relevant grid cell as a high concentration region; otherwise, mark it as a low concentration region.

[0028] If a grid cell is located in both a high-variance region and a high-concentration region, the resistivity change rate gradient and the radon concentration gradient are weighted and fused based on a first preset weight; otherwise, the resistivity change rate gradient and the radon concentration gradient are weighted and fused based on a second preset weight; thus obtaining the earthquake precursor signal intensity value for each grid cell; wherein, the first preset weight is greater than the second preset weight.

[0029] The earthquake precursor signal intensity value of each grid cell is mapped to the chemical attractant concentration of virtual particles.

[0030] Preferably, a phototactic mechanism is introduced to simulate the swarm motion behavior of virtual particles under a chemical attractant concentration gradient, and the final distribution density map of the virtual particles is obtained, specifically as follows:

[0031] Based on the concentration of the chemical attractant in each grid cell, the initial direction of motion of the virtual particles is determined: if the concentration of the chemical attractant in a certain grid cell is higher than a preset concentration threshold, the virtual particles in that grid cell are made to move toward the high concentration region that is closest to them in a straight line; otherwise, the direction of motion is randomly selected.

[0032] A phototaxis mechanism is introduced to simulate the avoidance behavior of virtual particles in local concentration traps. If the virtual particles stay in a local high concentration area for more than a preset value, their movement direction is adjusted by a random perturbation factor to avoid excessive aggregation.

[0033] The position information of the virtual particle is updated according to its movement step size and direction. If the new position exceeds the boundary of the monitoring area, its movement direction is reversed and the step size is shortened by a preset amount.

[0034] The trajectory of the virtual particle is calculated iteratively. If the number of iterations does not reach the preset maximum value, the step size and direction of the particle are adjusted. Otherwise, the iteration is stopped.

[0035] The final position distribution of all virtual particles is statistically analyzed, and the virtual particle density of each grid cell is calculated. If the density value is higher than the preset density threshold, the corresponding grid cell is marked as a high-density region; otherwise, it is marked as a low-density region.

[0036] The final distribution density map of virtual particles is obtained based on the high-density region and the low-density region.

[0037] Preferably, based on the final distribution density map of the virtual particles, the optimal layout map of the fiber optic seismometers in the monitoring area is determined, and the seismic monitoring platform is built according to the optimal layout map, specifically as follows:

[0038] The high-density and low-density areas of the monitoring area are obtained based on the final distribution density.

[0039] Fiber optic seismometers are deployed in high-density areas according to a first preset density, while sparse fiber optic seismometers are deployed in low-density areas according to a second preset density; a fiber optic seismometer deployment scheme is generated; wherein the first preset density is greater than the second preset density.

[0040] A preliminary layout map is generated based on the deployment plan. If there are monitoring blind spots in the preliminary layout map, the density distribution of fiber optic seismometers is readjusted.

[0041] The initial layout diagram is input into the digital twin system for simulation verification. If the simulation results show that the monitoring accuracy does not meet the preset requirements, the optimized layout diagram is returned until the accuracy requirements are met.

[0042] Based on the final determined optimal layout diagram, the fiber optic seismometers were actually deployed.

[0043] The deployed fiber optic seismometers are integrated with the earthquake monitoring platform to acquire seismic wave signals in real time, and the monitoring effect is verified through the data analysis module. If the effect does not meet expectations, the layout is re-optimized to complete the construction of the earthquake monitoring platform.

[0044] The second aspect of this invention discloses a system for building an earthquake monitoring platform based on a fiber optic seismograph. The system includes a memory and a processor. The memory stores a program for building an earthquake monitoring platform based on a fiber optic seismograph. When the processor executes the program for building an earthquake monitoring platform based on a fiber optic seismograph, the following steps are implemented:

[0045] A three-dimensional geological model of the monitoring area was constructed based on multi-source geological data of the monitoring area.

[0046] The grid cells in the 3D geological model are treated as virtual particles, and the position, direction of motion, and chemotaxis parameters of each virtual particle are initialized.

[0047] Based on multi-source geological data, the intensity of earthquake precursor signals in each grid cell is determined as the concentration of chemical attractant for virtual particles;

[0048] A phototaxis mechanism was introduced to simulate the collective motion behavior of virtual particles under a chemical attractant concentration gradient, and the final distribution density map of the virtual particles was obtained.

[0049] Based on the final distribution density map of the virtual particles, the optimal layout of fiber optic seismometers in the monitoring area is determined, and the seismic monitoring platform is built according to the optimal layout map.

[0050] This invention addresses the technical deficiencies in the prior art and offers the following advantages: It constructs a three-dimensional geological model of the monitoring area based on multi-source geological data; it treats each grid cell in the three-dimensional geological model as a virtual particle, initializing the position, direction of motion, and chemotactic parameters of each virtual particle; it determines the intensity of the earthquake precursor signal in each grid cell based on the multi-source geological data, using it as the chemotactic concentration of the virtual particle; it introduces a phototactic mechanism to simulate the collective motion behavior of the virtual particle under a chemotactic concentration gradient, obtaining the final distribution density map of the virtual particle; based on the final distribution density map of the virtual particle, it determines the optimal layout of fiber optic seismometers in the monitoring area, and constructs an earthquake monitoring platform according to the optimal layout map. This invention can accurately identify potential seismic source areas, dynamically adapt to changes in the geological environment, and improve the coverage accuracy and response capability of the earthquake monitoring platform. Attached Figure Description

[0051] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other embodiments can be obtained from these drawings without creative effort.

[0052] Figure 1 This is a flowchart illustrating the overall methodology for building a seismic monitoring platform based on a fiber optic seismometer.

[0053] Figure 2 This is a partial flowchart of the method for building an earthquake monitoring platform based on a fiber optic seismometer;

[0054] Figure 3 This is a system block diagram of the earthquake monitoring platform based on fiber optic seismometer. Detailed Implementation

[0055] To better understand the above-mentioned objectives, features, and advantages of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in these embodiments can be combined with each other.

[0056] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and therefore the scope of protection of the invention is not limited to the specific embodiments disclosed below.

[0057] like Figure 1 As shown, the first aspect of this invention discloses a method for building an earthquake monitoring platform based on a fiber optic seismometer, comprising the following steps:

[0058] S102. Construct a three-dimensional geological model of the monitoring area based on multi-source geological data of the monitoring area;

[0059] S104. Treat the mesh cells in the three-dimensional geological model as virtual particles, and initialize the position, direction of motion, and chemotaxis parameters of each virtual particle;

[0060] S106. Based on multi-source geological data, determine the intensity of earthquake precursor signals for each grid cell, which serves as the concentration of chemical attractant for virtual particles.

[0061] S108. Introduce a phototaxis mechanism to simulate the collective motion behavior of virtual particles under a chemical attractant concentration gradient, and obtain the final distribution density map of virtual particles.

[0062] S110. Based on the final distribution density map of the virtual particles, determine the optimal layout map of the fiber optic seismometers in the monitoring area, and build the seismic monitoring platform according to the optimal layout map.

[0063] It should be noted that by constructing a three-dimensional geological model using multi-source geological data and combining it with the simulation of the collective motion behavior of virtual particles, the optimal layout scheme of the fiber optic seismometer is scientifically determined, achieving efficient coverage and optimized resource allocation of the monitoring area; it can accurately identify potential seismic source areas, dynamically adapt to changes in the geological environment, and improve the coverage accuracy and response capability of the earthquake monitoring platform.

[0064] Preferably, a three-dimensional geological model of the monitoring area is constructed based on multi-source geological data of the monitoring area, specifically as follows:

[0065] Acquire multi-source geological data for the monitoring area, including the distribution of historical earthquake events, fault zone locations, crustal stress field distribution, changes in resistivity, radon concentration, temperature changes, geomagnetic anomalies, and groundwater level data;

[0066] Align multi-source geological data according to spatial location and unify the coordinate system to form the basic framework for multi-source data fusion;

[0067] Based on geostatistical methods, the correlation between various geological parameters is analyzed, and a mapping relationship model between the parameters is constructed.

[0068] It should be noted that multi-source geological data of the monitoring area were collected, including the distribution of historical earthquake events, fault zone locations, crustal stress field distribution, changes in resistivity, radon concentration, temperature changes, geomagnetic anomalies, and groundwater level data. The data was preprocessed to remove noise and outliers. Next, the preprocessed data were aligned according to spatial location and a unified coordinate system was established, forming the basic framework for multi-source data fusion. Then, Pearson correlation coefficient and principal component analysis were used to calculate the correlation between various geological parameters. If the correlation coefficient was higher than a preset threshold, it was marked as a strongly correlated parameter; otherwise, it was marked as a weakly correlated parameter. Further, based on the strongly correlated parameters, a multiple linear regression model was constructed, and the mapping relationship between the parameters was fitted using the least squares method. Finally, the constructed mapping relationship model was applied to calculate the attribute values ​​of the three-dimensional geological model, completing the analysis of the correlation of geological parameters and the construction of the mapping relationship model.

[0069] The monitoring area was divided into multiple grid units using a three-dimensional gridding method, and each unit was assigned a corresponding geological attribute value.

[0070] It should be noted that the precision of the 3D grid division is determined based on the spatial extent of the monitoring area. The monitoring area is uniformly divided into multiple cubic grid cells along the longitude, latitude, and depth directions, and each cell is assigned a unique identifier. Then, based on multi-source geological data, the center point of each grid cell is calculated, and the corresponding geological attribute values ​​are extracted. These geological attribute values ​​are quantitative indicators describing the geological characteristics and physical parameters of each grid cell within the monitoring area, including but not limited to crustal stress intensity, resistivity variation rate, radon concentration gradient, temperature variation amplitude, geomagnetic anomaly, groundwater level fluctuation, and historical earthquake event density. These attribute values ​​are obtained through the fusion and calculation of multi-source geological data and can reflect the geological activity state and potential seismic source risk of the grid cell.

[0071] The gridded data is rendered into a 3D geological model using 3D visualization tools, and the realism of the model is enhanced by lighting and texture.

[0072] Among them, 3D visualization tools include, but are not limited to, Petrel, GOCAD, and Leapfrog.

[0073] The constructed 3D geological model is validated. If the model accuracy does not reach the preset accuracy threshold, the mesh density is adjusted until the model accuracy meets the requirements, thus completing the construction of the 3D geological model.

[0074] In summary, this method, by fusing multi-source geological data and constructing a high-precision three-dimensional geological model, can comprehensively and intuitively reflect the geological structure and earthquake precursor characteristics of the monitored area. This provides accurate data support for the subsequent intelligent deployment of fiber optic seismometers, thereby improving the coverage efficiency and response capability of the earthquake monitoring platform.

[0075] Preferably, the grid cells in the three-dimensional geological model are treated as virtual particles, and the position, direction of motion, and chemotaxis parameters of each virtual particle are initialized, specifically as follows:

[0076] Based on the aforementioned three-dimensional geological model, each grid cell is defined as a virtual particle and assigned a unique identifier.

[0077] Based on the geological attribute values ​​of the grid cells, including the rate of change of resistivity, radon concentration gradient and crustal stress intensity, the initial chemotaxis parameters of each virtual particle are determined. If the geological attribute value is higher than the preset attribute threshold, the virtual particle is defined as having high chemotaxis sensitivity; otherwise, it is defined as having low chemotaxis sensitivity.

[0078] Each virtual particle is randomly initialized with a direction of motion, and its initial coordinates are determined based on its spatial position within the grid cell.

[0079] Based on the geological characteristics of the monitoring area, the movement step size and maximum number of iterations of the virtual particles are set; if the grid cell is located in a fault zone, the movement step size is shortened according to the preset amplitude.

[0080] It should be noted that during implementation, based on the geological characteristics of the monitoring area, including fault zone distribution, crustal stress field intensity, and historical seismic event density, the initial movement step size and maximum number of iterations for the virtual particles are set. Specifically, if the grid cell is located in a fault zone, the movement step size of the virtual particles is shortened by a preset amount, for example, reduced to 50% of the original value, according to the width and activity of the fault zone, to enhance the local search accuracy in the fault zone area; if the grid cell is located in a non-fault zone area, the default movement step size is maintained to accelerate the global exploration speed. Simultaneously, the maximum number of iterations for the virtual particles is set according to the geological complexity of the monitoring area, for example, 100 iterations in fault zone areas and 50 iterations in non-fault zone areas, to ensure that the virtual particles can fully cover potential seismic source areas.

[0081] Subsequently, a random perturbation factor was introduced to simulate the uncertainty in the geological environment, and a random offset was added to the motion direction of each virtual particle to avoid the virtual particles getting trapped in local optima;

[0082] It should be noted that, based on the geological complexity and historical seismic event distribution of the monitoring area, the intensity range of the random perturbation factor is determined. Next, a random angle offset value is generated for the motion direction of each virtual particle, with the offset value uniformly distributed within a preset perturbation intensity range. Then, the random angle offset value is applied to the current motion direction of the virtual particle to calculate its new motion direction. If the new direction exceeds the boundary of the monitoring area, the offset value is regenerated. The perturbation intensity is dynamically adjusted according to the chemotaxis parameters of the virtual particles. If the virtual particle is located in a highly chemotactic sensitive area, the perturbation intensity is reduced to enhance local search capabilities; otherwise, the perturbation intensity is increased to improve global exploration efficiency. Finally, the motion direction offset results of all virtual particles are verified. If an abnormal offset direction is found or does not conform to geological characteristics, the random perturbation factor is regenerated until the offset direction is reasonable, thus completing the introduction of the random perturbation factor and the adjustment of the motion direction offset.

[0083] The initialization parameters of all virtual particles are verified. If any parameters are found to be abnormal or exceed the preset range, they are recalculated and adjusted until the initialization parameters of all virtual particles meet the requirements, thus completing the initialization configuration of the virtual particles.

[0084] In summary, this method, by abstracting the grid cells in the 3D geological model into virtual particles and initializing their position, direction of motion, and chemotaxis parameters in conjunction with geological attribute values, can accurately simulate dynamic changes in the geological environment, effectively simulate the uncertainty and complexity of the geological environment, and improve the accuracy and robustness of virtual particle initialization.

[0085] Preferably, based on multi-source geological data, the intensity of the earthquake precursor signal in each grid cell is determined as the concentration of the chemical attractant for the virtual particles, such as... Figure 2 As shown, specifically:

[0086] S202. Obtain the data on the rate of change of resistivity and radon concentration in the monitoring area, calculate the gradient of the rate of change of resistivity for each grid cell, and mark the corresponding grid cell as a high-change area if the gradient of the rate of change of resistivity is higher than the preset threshold of the rate of change of resistivity; otherwise, mark it as a low-change area.

[0087] S204. Calculate the radon concentration gradient of each grid cell. If the radon concentration gradient is higher than the preset radon concentration gradient threshold, mark the relevant grid cell as a high concentration region; otherwise, mark it as a low concentration region.

[0088] S206. If a grid cell is located in both a high-variance region and a high-concentration region, the resistivity change rate gradient and the radon concentration gradient are weighted and fused based on the first preset weight; otherwise, the resistivity change rate gradient and the radon concentration gradient are weighted and fused based on the second preset weight; thus obtaining the earthquake precursor signal intensity value for each grid cell; wherein, the first preset weight is greater than the second preset weight.

[0089] For example, during implementation, the grid cells of the monitoring area are first marked. If the gradient of the rate of change of the ground resistivity of a certain grid cell is higher than a preset threshold (e.g., 0.5% / km) and the radon concentration gradient is also higher than a preset threshold (e.g., 10 Bq / m³), then the grid cell is marked. 3 If a grid cell has a resistivity gradient of 0.6% / km and a radon concentration gradient of 12 Bq / m³, then the cell is marked as being located in both a high-variance region and a high-concentration region. For such cells, the resistivity gradient and radon concentration gradient are weighted and fused based on a first preset weight (e.g., 0.7 and 0.3) to calculate the intensity value of the precursor signal. For grid cells that do not meet the above conditions, a second preset weight (e.g., 0.5 and 0.5) is used for weighted fusion. For example, a grid cell has a resistivity gradient of 0.6% / km and a radon concentration gradient of 12 Bq / m³. 3 / km, since it is located in both a high-variance region and a high-concentration region, its earthquake precursor signal intensity value is calculated to be 0.7×0.6+0.3×12=4.02 using the first preset weight; the resistivity change rate gradient of another grid cell is 0.4% / km, and the radon concentration gradient is 8Bq / m 3 / km, since it does not meet the conditions, the intensity value of its earthquake precursor signal is calculated using the second preset weight as 0.5×0.4+0.5×8=4.2.

[0090] S208. Map the earthquake precursor signal intensity value of each grid cell to the chemical attractant concentration of virtual particles.

[0091] The aforementioned precursory signal intensity value refers to a comprehensive index that quantifies the potential seismic risk of each grid cell by integrating multi-source geological data such as the gradient of the rate of change of resistivity and the gradient of radon concentration. A higher value indicates more active geological activity and more pronounced precursory signals in the region, thus providing a scientific basis for the concentration of chemical attractants in virtual particles, guiding the intelligent layout optimization of fiber optic seismometers and the precise construction of seismic monitoring platforms.

[0092] In summary, this method integrates multi-source geological data such as the rate of change of resistivity and radon concentration gradient to obtain the intensity of earthquake precursor signals in each grid cell and maps them to the concentration of chemical attractants for virtual particles, thereby providing a scientific basis for the swarm movement behavior of virtual particles. It can effectively identify high earthquake risk areas, enhance the coverage accuracy of potential seismic source areas, and lay a reliable foundation for the intelligent layout optimization of fiber optic seismometers.

[0093] Preferably, a phototactic mechanism is introduced to simulate the swarm motion behavior of virtual particles under a chemical attractant concentration gradient, and the final distribution density map of the virtual particles is obtained, specifically as follows:

[0094] Based on the concentration of the chemical attractant in each grid cell, the initial direction of motion of the virtual particles is determined: if the concentration of the chemical attractant in a certain grid cell is higher than a preset concentration threshold, the virtual particles in that grid cell are made to move toward the high concentration region that is closest to them in a straight line; otherwise, the direction of motion is randomly selected.

[0095] For example, during implementation, a preset concentration threshold (e.g., 50 units) is set based on the chemisorbent concentration of each grid cell. For grid cells with a chemisorbent concentration higher than this threshold, the initial movement direction of their virtual particles is determined to be towards the nearest high-concentration region in a straight line. For example, if a grid cell has a chemisorbent concentration of 60 units and its nearest high-concentration region is due east, then the initial movement direction of the virtual particles is set to due east. For grid cells with a chemisorbent concentration lower than the preset threshold, the movement direction is randomly selected. For example, if a grid cell has a chemisorbent concentration of 40 units, then the initial movement direction of its virtual particles is randomly set to 30° east of north.

[0096] A phototaxis mechanism is introduced to simulate the avoidance behavior of virtual particles in local concentration traps. If the virtual particles stay in a local high concentration area for more than a preset value, their movement direction is adjusted by a random perturbation factor to avoid excessive aggregation.

[0097] The position information of the virtual particle is updated according to its movement step size and direction. If the new position exceeds the boundary of the monitoring area, its movement direction is reversed and the step size is shortened by a preset amount.

[0098] It should be noted that, based on the current direction of motion of the virtual particle, its new position coordinates are obtained. If the new position is within the boundary of the monitoring area, its position information is directly updated. Next, if the new position exceeds the boundary of the monitoring area, its direction of motion is reversed; for example, if the original direction was due east, it is adjusted to due west, and the step size is shortened by a preset amount (e.g., 80% of the original step size). Then, based on the adjusted direction and step size, the coordinates of the new position are recalculated. If the new position still exceeds the boundary, it is reversed again and the step size is further shortened until the new position is within the monitoring area. The updated position information is stored as the current position of the virtual particle, and its trajectory is recorded. Finally, the position update results of all virtual particles are verified. If any position anomalies or deviations from the motion pattern are found, the direction or step size is readjusted until the position information is reasonable, thus completing the update of the virtual particle position information and the handling of boundary violations.

[0099] The trajectory of the virtual particle is calculated iteratively. If the number of iterations does not reach the preset maximum value, the step size and direction of the particle are adjusted. Otherwise, the iteration is stopped.

[0100] The final position distribution of all virtual particles is statistically analyzed, and the virtual particle density of each grid cell is calculated. If the density value is higher than the preset density threshold, the corresponding grid cell is marked as a high-density region; otherwise, it is marked as a low-density region.

[0101] The final distribution density map of virtual particles is obtained based on the high-density region and the low-density region.

[0102] The phototaxis mechanism refers to an algorithm that guides the movement of virtual particles along a chemical attractant concentration gradient by simulating the biological repulsion behavior towards light sources, thus preventing excessive aggregation in locally high-concentration areas. This mechanism simulates uncertainties in the geological environment by introducing random perturbation factors and dynamically adjusting the movement step size, ensuring that virtual particles effectively avoid local concentration traps while covering high-concentration areas, thereby achieving a balance between global exploration and detailed local investigation of the monitoring area.

[0103] In summary, this method, by introducing a phototactic mechanism, simulates the collective motion behavior of virtual particles under a chemical attractant concentration gradient, effectively avoiding local concentration traps and preventing excessive aggregation of virtual particles. By dynamically adjusting the motion step size and direction of virtual particles and combining iterative calculations, a distribution density map of virtual particles is finally generated.

[0104] Preferably, based on the final distribution density map of the virtual particles, the optimal layout map of the fiber optic seismometers in the monitoring area is determined, and the seismic monitoring platform is built according to the optimal layout map, specifically as follows:

[0105] The high-density and low-density areas of the monitoring area are obtained based on the final distribution density.

[0106] Fiber optic seismometers are deployed in high-density areas according to a first preset density, while sparse fiber optic seismometers are deployed in low-density areas according to a second preset density; a fiber optic seismometer deployment scheme is generated; wherein the first preset density is greater than the second preset density.

[0107] For example, during implementation, the monitoring area is divided into high-density and low-density areas based on the final distribution density map of virtual particles. For high-density areas, fiber optic seismometers are deployed according to a first preset density (e.g., 10 fiber optic seismometers per square kilometer). For instance, if a high-density area is 5 square kilometers, 50 fiber optic seismometers are deployed. For low-density areas, fiber optic seismometers are deployed according to a second preset density (e.g., 2 fiber optic seismometers per square kilometer). For instance, if a low-density area is 10 square kilometers, 20 fiber optic seismometers are deployed. This method generates a fiber optic seismometer deployment scheme, ensuring high-precision monitoring in high-density areas and optimized resource allocation in low-density areas. For example, if a monitoring area has a total area of ​​15 square kilometers, with 5 square kilometers of high-density area and 10 square kilometers of low-density area, the final deployment scheme would be 50 fiber optic seismometers in the high-density area and 20 fiber optic seismometers in the low-density area, totaling 70 fiber optic seismometers, thus completing the deployment scheme generation.

[0108] A preliminary layout map is generated based on the deployment plan. If there are monitoring blind spots in the preliminary layout map, the density distribution of fiber optic seismometers is readjusted.

[0109] The initial layout diagram is input into the digital twin system for simulation verification. If the simulation results show that the monitoring accuracy does not meet the preset requirements, the optimized layout diagram is returned until the accuracy requirements are met.

[0110] Based on the final determined optimal layout diagram, the fiber optic seismometers were actually deployed.

[0111] The deployed fiber optic seismometers are integrated with the earthquake monitoring platform to acquire seismic wave signals in real time, and the monitoring effect is verified through the data analysis module. If the effect does not meet expectations, the layout is re-optimized to complete the construction of the earthquake monitoring platform.

[0112] In summary, this method scientifically determines the optimal layout scheme of fiber optic seismometers through the final distribution density map of virtual particles, ensuring high-precision coverage in high-density areas and optimized resource allocation in low-density areas. Through simulation verification using a digital twin system and dynamic optimization of the layout map, it can effectively eliminate monitoring blind spots, improve monitoring accuracy and resource utilization. The earthquake monitoring platform finally built can acquire seismic wave signals in real time, and the monitoring effect can be verified through a data analysis module, thereby improving the reliability and response capability of earthquake monitoring.

[0113] In this embodiment, the method for building the earthquake monitoring platform may further include the following steps:

[0114] The reflectance spectrum signal of the seismometer node is acquired in real time using fiber optic grating demodulation technology. If the signal intensity is lower than a preset threshold (e.g., -20dB), the node is marked as an abnormal node.

[0115] Based on the virtual particle distribution density map, a backup node is searched for near the abnormal node. If the distance between the backup node and the abnormal node exceeds a preset range (e.g., 500 meters), the drone-assisted deployment mechanism is activated to quickly transport the backup node to the target area.

[0116] The signal quality of the backup node is verified using fiber Bragg grating demodulation technology. If the signal quality does not meet the preset standard, a new backup node is selected.

[0117] Based on the virtual particle distribution density map, the monitoring range of the backup node is dynamically adjusted. If the backup node is located in a high-density area, its monitoring radius is expanded to cover the monitoring blind spot of the abnormal node; otherwise, the default monitoring range is maintained.

[0118] The monitoring data of the backup node is integrated with the earthquake monitoring platform. If the data acquisition frequency or accuracy does not meet the preset requirements, the deployment position of the backup node is readjusted.

[0119] The health status of all nodes is periodically checked. If an abnormal node is found to have failed to switch over in time or the backup node has an abnormal signal, an alarm mechanism is triggered and the switching process is re-executed to ensure the stable operation of the monitoring network.

[0120] It should be noted that this method uses fiber optic grating demodulation technology to monitor the health status of seismometer nodes in real time, and combines virtual particle density maps to dynamically switch backup nodes. This enables rapid response to node failures, eliminates monitoring blind spots, and ensures the continuity and stability of the monitoring network.

[0121] In this embodiment, the method for building the earthquake monitoring platform may further include the following steps:

[0122] Acquire InSAR data on surface deformation and geothermal field change data of the monitoring area, align the InSAR data on surface deformation and geothermal field change data in time and space, and construct a spatiotemporal data matrix.

[0123] Convolutional neural networks are constructed by inputting spatiotemporal data matrices into the convolutional neural network and extracting spatiotemporal correlation features of surface deformation and geothermal field changes through convolutional layers. If the feature extraction effect does not reach the preset accuracy, the size of the convolutional kernel is adjusted or the network depth is increased.

[0124] The predicted intensity of earthquake precursor signals is generated through a fully connected layer. If the error between the predicted value and the actual observed value exceeds a preset threshold, the network parameters are optimized.

[0125] The predicted values ​​are mapped to chemical attractant concentration weights. If the weight value is higher than the preset range, normalization is performed.

[0126] The corrected weight values ​​are applied to the chemotaxis parameters of the virtual particles. If the virtual particle distribution density map shows that the prediction accuracy does not meet the requirements, the convolutional neural network is retrained until the prediction accuracy of the earthquake precursor signal intensity meets the expectations, thus completing the dynamic correction of the chemical attractant concentration weights.

[0127] It should be noted that this method, by fusing InSAR data on surface deformation and geothermal field changes, and using a convolutional neural network to construct a spatiotemporal correlation model of earthquake precursor signal intensity, can accurately predict the intensity of earthquake precursor signals in potential seismic source areas and dynamically adjust the concentration weight of chemical attractants. This improves the prediction accuracy and coverage efficiency of virtual particles for high-seismic-risk areas, provides a scientific basis for the intelligent layout optimization of fiber optic seismometers, and enhances the early warning capability and response effect of earthquake monitoring platforms.

[0128] like Figure 3 As shown, the second aspect of the present invention discloses a seismic monitoring platform construction system 6 based on a fiber optic seismometer. The seismic monitoring platform construction system based on a fiber optic seismometer includes a memory 41 and a processor 52. The memory 41 stores a method program for constructing a seismic monitoring platform based on a fiber optic seismometer. When the method program for constructing a seismic monitoring platform based on a fiber optic seismometer is executed by the processor 52, the following steps are implemented:

[0129] A three-dimensional geological model of the monitoring area was constructed based on multi-source geological data of the monitoring area.

[0130] The grid cells in the 3D geological model are treated as virtual particles, and the position, direction of motion, and chemotaxis parameters of each virtual particle are initialized.

[0131] Based on multi-source geological data, the intensity of earthquake precursor signals in each grid cell is determined as the concentration of chemical attractant for virtual particles;

[0132] A phototaxis mechanism was introduced to simulate the collective motion behavior of virtual particles under a chemical attractant concentration gradient, and the final distribution density map of the virtual particles was obtained.

[0133] Based on the final distribution density map of the virtual particles, the optimal layout of fiber optic seismometers in the monitoring area is determined, and the seismic monitoring platform is built according to the optimal layout map.

[0134] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple units or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be electrical, mechanical, or other forms.

[0135] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units. They may be located in one place or distributed across multiple network units. Some or all of the units may be selected to achieve the purpose of this embodiment according to actual needs.

[0136] In addition, in the various embodiments of the present invention, each functional unit can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be implemented in hardware or in the form of hardware plus software functional units.

[0137] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0138] Alternatively, if the integrated units of this invention are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this invention, or the parts that contribute to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROM, RAM, magnetic disks, or optical disks.

[0139] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for building a seismic monitoring platform based on a fiber optic seismometer, characterized in that, The method comprises the following steps: constructing a three-dimensional geological model of the monitoring area based on multi-source geological data of the monitoring area; treating a grid cell in the three-dimensional geological model as a virtual particle, and initializing the position, motion direction and chemotaxis parameter of each virtual particle; determining the intensity of the earthquake precursor signal of each grid cell as the chemical attractant concentration of the virtual particle according to the multi-source geological data; introducing a phototaxis mechanism to simulate the group motion behavior of the virtual particles under the chemical attractant concentration, and obtaining a final distribution density map of the virtual particles; determining an optimal layout map of the fiber seismic meter in the monitoring area according to the final distribution density map of the virtual particles, and building a seismic monitoring platform according to the optimal layout map; further comprising: determining the initial chemotaxis parameter of each virtual particle according to the geological attribute value of the grid cell, including the ground resistivity change rate, the radon concentration gradient and the crustal stress intensity; if the geological attribute value is higher than a preset attribute threshold, the virtual particle is defined as a high chemotaxis sensitivity, otherwise it is defined as a low chemotaxis sensitivity; wherein the phototaxis mechanism is introduced to simulate the group motion behavior of the virtual particles under the chemical attractant concentration, and obtain a final distribution density map of the virtual particles, specifically: determining the initial motion direction of the virtual particle based on the chemical attractant concentration of each grid cell: if the chemical attractant concentration of a certain grid cell is higher than a preset concentration threshold, the virtual particle of the grid cell is made to move towards the high concentration area closest to it in a straight line, otherwise a random motion direction is selected; introducing a phototaxis mechanism to simulate the avoidance behavior of the virtual particles to local concentration traps, if the virtual particle stays in a local high concentration area for more than a preset value, the motion direction is adjusted by a random disturbance factor to avoid excessive aggregation; updating the position information of the virtual particle according to its motion step and direction, if the new position exceeds the boundary of the monitoring area, the motion direction is reversed and the step is shortened by a preset amplitude; iteratively calculating the motion trajectory of the virtual particle, if the number of iterations does not reach a preset maximum value, continue to adjust the motion step and direction, otherwise stop iteration; statistically analyzing the final position distribution of all virtual particles, calculating the virtual particle density of each grid cell, if the density value is higher than a preset density threshold, marking the corresponding grid cell as a high density area, otherwise marking it as a low density area; obtaining a final distribution density map of the virtual particles according to the high density area and the low density area.

2. The fiber-optic seismometer-based seismic monitoring platform setup method according to claim 1, wherein, Constructing a three-dimensional geological model of the monitoring area based on multi-source geological data of the monitoring area, specifically: obtaining multi-source geological data of the monitoring area, including historical earthquake event distribution, fault zone location, crustal stress field distribution, ground resistivity change, radon concentration, temperature change, geomagnetic anomaly and underground water level data; aligning the multi-source geological data according to the spatial position, and unifying the coordinate system to form a basic framework for multi-source data fusion; analyzing the correlation between each geological parameter based on the method of geological statistics, and constructing a mapping relationship model between the parameters; dividing the monitoring area into multiple grid cells by using a three-dimensional gridding method, and assigning each cell with a corresponding geological attribute value; The gridded data is rendered into a three-dimensional geological model through a three-dimensional visualization tool, and the model is enhanced in reality by using light and texture; The constructed three-dimensional geological model is verified, and if the model precision does not reach the preset precision threshold, the grid division density is adjusted until the model precision meets the requirements, and the construction of the three-dimensional geological model is completed.

3. The fiber-optic seismometer-based seismic monitoring platform setup method according to claim 1, wherein, The grid cells in the three-dimensional geological model are taken as virtual particles, and the position, motion direction and chemotaxis parameters of each virtual particle are initialized, specifically: Based on the three-dimensional geological model, each grid cell is defined as a virtual particle, and a unique identifier is assigned to it; Each virtual particle is randomly initialized in the motion direction, and the initial coordinates are determined based on the spatial position of the grid cell it is located in; According to the geological characteristics of the monitoring area, the motion step and the maximum number of iterations of the virtual particle are set; if the grid cell is located in a fault zone, the motion step is shortened by a preset amplitude; Then, a random disturbance factor is introduced to simulate the uncertainty in the geological environment, and a random offset is added to the motion direction of each virtual particle to avoid the virtual particle falling into a local optimum; The initialization parameters of all virtual particles are checked, and if the parameters are found to be abnormal or exceed the preset range, they are recalculated and adjusted until all virtual particles meet the requirements, and the initialization configuration of the virtual particles is completed.

4. The fiber-optic seismometer-based seismic monitoring platform setup method of claim 1, wherein, According to the multi-source geological data, the seismic precursor signal intensity of each grid cell is determined as the chemical attractant concentration of the virtual particle, specifically: Obtain the geoelectric resistivity change rate and radon concentration data of the monitoring area, calculate the geoelectric resistivity change rate gradient of each grid cell, if the geoelectric resistivity change rate gradient is higher than the preset geoelectric resistivity change rate threshold, mark the corresponding grid cell as a high change area, otherwise mark it as a low change area; Calculate the radon concentration gradient of each grid cell, if the radon concentration gradient is higher than the preset radon concentration gradient threshold, mark the relevant grid cell as a high concentration area, otherwise mark it as a low concentration area; If the grid cell is located in both the high change area and the high concentration area, the geoelectric resistivity change rate gradient and the radon concentration gradient are weighted and fused based on a first preset weight; Otherwise, the geoelectric resistivity change rate gradient and the radon concentration gradient are weighted and fused based on a second preset weight; The seismic precursor signal intensity value of each grid cell is obtained; wherein the first preset weight is greater than the second preset weight; Map the seismic precursor signal intensity value of each grid cell to the chemical attractant concentration of the virtual particle.

5. The fiber-optic seismometer-based seismic monitoring platform setup method according to claim 1, wherein, According to the final distribution density map of the virtual particles, the optimal layout map of the fiber seismometer in the monitoring area is determined, and the seismic monitoring platform is built according to the optimal layout map, specifically: According to the final distribution density, the high-density area and the low-density area of the monitoring area are obtained; In the high-density area, the fiber seismometer is arranged according to a first preset density, and in the low-density area, the sparse fiber seismometer is arranged according to a second preset density; A layout scheme of the fiber seismometer is generated; wherein the first preset density is greater than the second preset density; Based on the layout scheme, a preliminary layout map is generated, and if there is a monitoring blind area in the preliminary layout map, the density distribution of the fiber seismometer is adjusted again; The preliminary layout diagram is input into the digital twin system for simulation verification. If the simulation result shows that the monitoring precision does not meet the preset requirement, the optimized layout diagram is returned until the precision requirement is met. According to the finally determined optimal layout diagram, the optical fiber seismometer is actually laid out; The laid-out optical fiber seismometer is integrated with the seismic monitoring platform, real-time collection of seismic wave signals is performed, and the monitoring effect is verified through a data analysis module. If the effect does not meet the expectation, the layout diagram is re-optimized, and the seismic monitoring platform is built.

6. A system for building a seismic monitoring platform based on a fiber optic seismometer, characterized by, The seismic monitoring platform building system based on the optical fiber seismometer comprises a memory and a processor. The memory stores a seismic monitoring platform building method program based on the optical fiber seismometer. When the seismic monitoring platform building method program based on the optical fiber seismometer is executed by the processor, the seismic monitoring platform building method steps of any one of claims 1 to 5 are realized.

Images