Complex environment information acquisition method based on sensor network

Abstract

The invention discloses a complex environment information collection method based on a sensor network, and relates to the technical field of information processing, and the method comprises the steps: collecting multi-dimensional geological data in real time, constructing a multilayer coupling model, and calculating a signal transmission path and path loss between sensor nodes; when a plurality of geological data meet at the relay node, opportunistic aggregation is carried out to form an aggregated data packet; dynamically adjusting a data compression strategy according to the current network bandwidth and the environment state based on the aggregated data packet and the signal transmission path to obtain a compressed data packet; constructing a panoramic model of an underground environment by using the decompressed geological data and combining geological changes and historical data monitored in real time, and predicting a future geological trend; through opportunistic data aggregation and a dynamic compression strategy, the data packet can be efficiently compressed according to the current network bandwidth and the environment state, so that the waste of the bandwidth is avoided, and the integrity of key data is ensured.

Description

Technical Field

[0001] The present invention relates to the field of information processing technology, and in particular to a complex environment information collection method based on a sensor network. Background Art

[0002] With the development of sensor networks and information processing technology, real-time acquisition and analysis of geological data has gradually become a key link in the fields of geological monitoring and earthquake early warning. Current technologies usually use distributed sensors to collect geological data of a single or small number of dimensions, such as temperature, pressure or displacement. However, the transmission and processing of these data have great limitations. On the one hand, the large number of sensor nodes and their wide distribution range lead to complex data transmission paths, which are easily affected by the environment and cause signal attenuation. On the other hand, the existing multi-node data transmission method lacks effective data aggregation and compression strategies, resulting in low network bandwidth utilization and difficulty in improving data transmission efficiency.

[0003] The main deficiencies of the existing technology in the deployment and data transmission of sensor networks are reflected in the following two points: First, the existing sensor node layout method fails to fully consider the attenuation characteristics of the signal in a complex geological environment, resulting in low communication efficiency between nodes and affecting the reliability of data transmission; second, for data collected by multiple nodes, the existing technology lacks dynamic adjustment means in data compression and transmission strategies, which easily causes bandwidth waste or data loss, thus affecting the overall monitoring effect. Our invention effectively solves these problems through the construction of a multi-layer coupling model, opportunistic aggregation and dynamic data compression strategy, and significantly improves the efficiency and accuracy of data transmission. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a complex environment information acquisition method based on a sensor network to solve the problems of complex signal transmission paths, large transmission losses and low data compression efficiency of geological data in complex environments.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: In a first aspect, the present invention provides a complex environment information collection method based on a sensor network, which includes collecting multi-dimensional geological data in real time, and constructing a multi-layer coupling model to calculate the signal transmission path and path loss between each sensor node; According to the signal transmission path, a multi-layer repeater network is arranged to transmit the geological data layer by layer to the control center; When multiple geological data meet at a repeater node, they are opportunistically aggregated to form an aggregated data packet; Based on the aggregated data packets and signal transmission paths, the data compression strategy is dynamically adjusted according to the current network bandwidth and environmental status to obtain compressed data packets; The compressed data packets are transmitted to the surface control center through a multi-layer repeater network for decompression and restoration to the original multi-dimensional geological data; By using the decompressed geological data, combined with real-time monitoring of geological changes and historical data, a panoramic model of the underground environment is constructed to predict future geological trends.

[0007] As a preferred solution of the complex environment information collection method based on the sensor network of the present invention, wherein: the multi-dimensional geological data includes rock layer density, temperature, pressure and fluid flow; the collected multi-dimensional geological data is cleaned and formatted; The construction of the multi-layer coupling model comprises the following steps: According to the geological structure of the underground environment and the monitoring requirements of the target area, the sensor nodes are distributed at different depths and crack areas; According to the depth of sensor node deployment and geological characteristics, the geological structure is divided into the first layer, the second layer and the third layer, and the physical parameters corresponding to each layer are initialized; Through the parameters corresponding to each layer, the coupling relationship between layers is determined to obtain geological models of different depths and different characteristics.

[0008] As a preferred solution of the complex environment information collection method based on sensor network of the present invention, wherein: the calculation of the signal transmission path between each sensor node and the determination of the path loss comprises the following steps: According to the comprehensive geological characteristics of each area output by the coupling model, a signal attenuation model is established to calculate the signal transmission path between each sensor node. The expression is: ; in, is the received power, is the transmission power, is the signal wavelength, is the transmission distance, is the signal attenuation coefficient; Based on the signal transmission path, the signal loss in different paths is calculated, and the expression is: ; in, is the path loss.

[0009] As a preferred solution of the complex environment information collection method based on the sensor network of the present invention, wherein: according to the signal transmission path, a multi-layer repeater network is arranged to transmit the geological data layer by layer to the control center, including the following steps: Divide the repeater network into three layers, each layer is responsible for signal relay in a fixed depth area; The optimal repeater location is selected by coupling the geological characteristics output from the model; Deploy the main repeater node and backup repeater node at each repeater location, and use a combination of directional antennas and omnidirectional antennas to enable the main repeater node to receive signals from the lower sensor nodes and transmit the signals upward to the upper repeater and the surface control center; When the main repeater node fails, the backup repeater node starts to take over signal transmission.

[0010] As a preferred solution of the complex environment information collection method based on sensor network described in the present invention, when multiple geological data meet at a repeater node, opportunistic aggregation is performed to form an aggregated data packet, including the following steps: The sensor nodes continuously collect geological data in their respective areas of responsibility and send data packets to the nearest repeater node; Each repeater node maintains an aggregation window, receives data packets from multiple sensor nodes and aggregates them within the aggregation window to obtain aggregated data packets; The repeater node performs semantic analysis on the aggregated data packets, removes redundant information, and transmits the aggregated data packets to the upper-layer repeater nodes through a multi-layer repeater network; The upper layer repeater nodes receive aggregated data packets from multiple lower layer nodes, aggregate these data packets, and transmit the data packets to the cluster head node through the multi-layer repeater network; The cluster head node aggregates all received data packets and transmits them to the surface control center through the signal transmission path.

[0011] As a preferred solution of the complex environment information collection method based on sensor network described in the present invention, wherein: based on the aggregated data packet and signal transmission path, dynamically adjusting the data compression strategy according to the current network bandwidth and environmental status, obtaining the compressed data packet includes the following steps: Real-time geological environment data is obtained through sensor nodes distributed at different depths. Each sensor node sends the monitored environmental data and geological data to the nearest repeater node; The repeater node performs a preliminary analysis of the received environmental data to determine the current environmental status; When the environment is stable, the aggregated data packets are compressed using a lossy compression method with a high compression ratio; When the environment changes drastically, a lossless compression method with a low compression ratio is used to compress the aggregated data packets; Mark the key data in each data packet and set priorities based on the importance of the data; Real-time detection of current network bandwidth, and calculation of bandwidth occupancy rate based on data size at different compression rates; Dynamically adjust data compression strategy based on bandwidth usage and data packet priority.

[0012] As a preferred solution of the complex environment information collection method based on sensor network described in the present invention, the compressed data packet is transmitted to the surface control center through a multi-layer repeater network for decompression, and the original multi-dimensional geological data is restored, including the following steps: During transmission, the integrity of the data packet is monitored using a periodic checksum mechanism; The surface control center receives the compressed data packet and identifies the compression type used in the data packet; Decompress the data packet according to the identified compression type and restore it to the original multi-dimensional geological data; The decompressed data is integrity checked and stored in a hierarchical structure.

[0013] As a preferred solution of the complex environment information collection method based on sensor network described in the present invention, the following steps are included: using the decompressed geological data, combined with the real-time monitoring of geological changes and historical data, to build a panoramic model of the underground environment and predict future geological trends: The real-time monitored geological data are integrated with the multi-dimensional geological data recovered after decompression to construct a geological data set; A variable resolution partitioning strategy is used to divide the underground environment into three-dimensional spatial grids; Each data point in the geological data set is mapped to the corresponding three-dimensional grid unit to construct a three-dimensional grid model of the underground environment. The expression is: Among them, M grid (x, y, z) represents the physical parameter distribution of the position coordinate (x, y, z) in the grid cell in the three-dimensional grid model, x represents the position coordinate in the east-west direction in the three-dimensional space, y represents the position coordinate in the north-south direction in the three-dimensional space, z represents the position coordinate in the depth direction in the three-dimensional space, h represents the depth, ρ(x, y, z) represents the density of the grid cell, v(x, y, z) represents the fluid velocity of the grid cell, P(x, y, z) represents the pressure of the grid cell, and β represents the attenuation coefficient related to the depth; Based on the current physical parameter distribution and historical data, combined with real-time monitoring data, the future geological change trend is predicted, and the expression is: Among them, T fut (x, y, z, t) represents the future geological change trend of the position coordinates (x, y, z) in the grid cell at time t, M grid (x, y, z, t-τ) represents the physical parameter distribution of the position coordinates (x, y, z) in the grid cell at the past time t-τ, γ represents the attenuation coefficient of the historical data, represents the real-time monitoring data of the position coordinates (x, y, z) of the i-th sensor in the grid unit at time t, λ i represents the coupling coefficient between real-time data and flow velocity, t represents the time variable, τ represents the time difference, i represents the sensor index variable, n represents the total number of sensors, and v i (x, y, z, t) represents the fluid velocity of the position coordinate (x, y, z) of the i-th sensor in the grid cell at time t; By analyzing the predicted results of future geological change trends, abnormal geological changes are identified and graded according to the severity of the anomalies; According to the anomaly detection and classification results, the corresponding early warning mechanism is triggered.

[0014] In a second aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the complex environment information collection method based on a sensor network as described in the first aspect of the present invention is implemented.

[0015] In a third aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the complex environment information collection method based on a sensor network as described in the first aspect of the present invention.

[0016] The beneficial effects of the present invention are as follows: by constructing a multi-layer coupling model, the problem of difficulty in determining the signal transmission path in a complex geological environment is effectively solved. The signal attenuation characteristics of each sensor node are calculated through the output of the coupling model, and a multi-layer repeater network is arranged accordingly, so that the signal transmission path is optimized and the path loss is reduced. In addition, through opportunistic data aggregation and dynamic compression strategies, data packets can be efficiently compressed according to the current network bandwidth and environmental status, which not only avoids bandwidth waste, but also ensures the integrity of key data. Finally, the compressed data is transmitted layer by layer to the surface control center, ensuring efficient transmission of the data and integrity after decompression. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0018] Figure 1 This is a flow chart of the complex environment information collection method based on sensor network in Example 1.

[0019] Figure 2 This is a schematic diagram of abnormal classification in Example 1. DETAILED DESCRIPTION

[0020] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0021] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0022] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0023] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, and provides a complex environment information collection method based on a sensor network, comprising the following steps: S1. Collect multi-dimensional geological data in real time, build a multi-layer coupling model, and calculate the signal transmission path and path loss between each sensor node.

[0024] S1.1. Multi-dimensional geological data include rock density, temperature, pressure and fluid flow; the collected multi-dimensional geological data are cleaned and formatted.

[0025] S1.2, building a multi-layer coupling model includes the following steps: According to the geological structure of the underground environment and the monitoring requirements of the target area, the sensor nodes are distributed at different depths and fracture areas; according to the depth of the sensor node arrangement and the geological characteristics, the geological structure is divided into the first layer, the second layer and the third layer, and the physical parameters corresponding to each layer are initialized; through the parameters corresponding to each layer, the coupling relationship between the layers is determined to obtain geological models of different depths and different characteristics.

[0026] Specifically, the geological structure is divided as follows: The first layer: mainly includes the density, temperature and humidity of shallow rocks; the second layer: the distribution, expansion rate and fluid flow rate of cracks; the third layer: the pressure distribution and rock density of deep layers.

[0027] The specific operations of parameter initialization are as follows: The formation density is calculated based on the seismic wave reflection information collected by the sensor. The expression is: ; in, is the formation density, is the longitudinal wave velocity, is the shear wave velocity; The crack expansion rate is calculated by the crack change measured by the sensor, and the expression is: ; in, is the crack expansion rate, is the change in crack length, is the time interval; The fluid velocity is measured by the Doppler effect and is expressed as: ; in, is the fluid flow rate, is the transmitting signal frequency, is the received signal frequency, is the speed of sound; The geological pressure is obtained by the pressure sensor, and the expression is: ; in, is the geological pressure, is the acceleration due to gravity, For depth.

[0028] S2, calculating the signal transmission path between each sensor node and determining the path loss includes the following steps: According to the comprehensive geological characteristics of each area output by the coupling model, a signal attenuation model is established to calculate the signal transmission path between each sensor node. The expression is: ; in, is the received power, is the transmission power, is the signal wavelength, is the transmission distance, is the signal attenuation coefficient; Based on the signal transmission path, the signal loss in different paths is calculated, and the expression is: ; in, is the path loss.

[0029] S3. Arrange a multi-layer repeater network according to the signal transmission path to transmit the geological data layer by layer to the control center, including the following steps: The repeater network is divided into three layers, each of which is responsible for signal relay in a fixed depth area; the optimal repeater location is selected by coupling the geological characteristics output in the model; the main repeater node and the backup repeater node are deployed at each repeater location, and a combination of directional antennas and omnidirectional antennas is used to enable the main repeater node to receive signals from the lower-level sensor nodes respectively, and transmit the signals upward to the upper-level repeaters and the surface control center; when the main repeater node fails, the backup repeater node begins to take over the signal transmission.

[0030] Specifically, the division results of the repeater network are as follows: The first layer of repeaters: arranged 10 to 50 meters below the surface, responsible for signal transmission between shallow sensor nodes and the surface control center.

[0031] The second layer of repeaters: arranged at 50 to 200 meters, responsible for signal transmission of deep sensor nodes, mainly covering cracks and fluid flow areas.

[0032] The third layer of repeaters are arranged below 200 meters and are responsible for signal transmission in very deep geological areas, ensuring that data from deep sensor nodes can be transmitted smoothly.

[0033] S4. When multiple geological data meet at a repeater node, opportunistic aggregation is performed to form an aggregated data packet, including the following steps: The sensor nodes continuously collect geological data in their respective areas of responsibility and send data packets to the nearest repeater node; each repeater node maintains an aggregation window, receives data packets from multiple sensor nodes and aggregates them within the aggregation window to obtain aggregated data packets; the repeater node performs semantic analysis on the aggregated data packets, removes redundant information, and transmits the aggregated data packets to the upper-level repeater node through a multi-layer repeater network; the upper-level repeater node receives aggregated data packets from multiple lower-level nodes, aggregates these data packets, and transmits the data packets to the cluster head node through a multi-layer repeater network; the cluster head node finally aggregates all received data packets and transmits them to the surface control center through a signal transmission path.

[0034] Specifically, the aggregation formula for the data packets received by the repeater node within the aggregation window is: Among them, D agg Denotes the aggregated data packet, D m represents the mth data packet, m represents the data packet index, N represents the total number of data packets, and t i represents the timestamp of the mth packet, and σ represents the standard deviation of the time window.

[0035] S5. Based on the aggregated data packet and signal transmission path, dynamically adjust the data compression strategy according to the current network bandwidth and environment status to obtain the compressed data packet, including the following steps: Real-time geological environment data is obtained through sensor nodes distributed at different depths. Each sensor node sends the monitored environmental data and geological data to the nearest repeater node; The repeater node performs a preliminary analysis of the received environmental data to determine the current environmental status; When the environment is stable, the aggregated data packets are compressed using a lossy compression method with a high compression ratio; When the environment changes drastically, a lossless compression method with a low compression ratio is used to compress the aggregated data packets; Mark the key data in each data packet and set priorities based on the importance of the data; Real-time detection of current network bandwidth, and calculation of bandwidth occupancy rate based on data size at different compression rates; Dynamically adjust data compression strategy based on bandwidth usage and data packet priority.

[0036] In high bandwidth situations, the system will give priority to transmitting data packets with higher integrity (lower compression ratio).

[0037] In low bandwidth situations, the system will give priority to transmitting highly compressed data packets to reduce bandwidth usage.

[0038] Specifically, the expression of bandwidth occupancy is: Where B represents the bandwidth utilization rate, S m Indicates the size of the mth data packet, F total Indicates the total time of the transfer.

[0039] S6, transmitting the compressed data packet to the surface control center through a multi-layer repeater network for decompression, and restoring it to the original multi-dimensional geological data includes the following steps: During transmission, the integrity of the data packet is monitored using a periodic checksum mechanism; The surface control center receives the compressed data packet and identifies the compression type used in the data packet; Decompress the data packet according to the identified compression type and restore it to the original multi-dimensional geological data; The decompressed data is integrity checked and stored in a hierarchical structure.

[0040] S7. Using the decompressed geological data, combined with real-time monitoring of geological changes and historical data, a panoramic model of the underground environment is constructed to predict future geological trends, including the following steps: The real-time monitored geological data are integrated with the multi-dimensional geological data recovered after decompression to construct a geological data set; A variable resolution partitioning strategy is used to divide the underground environment into three-dimensional spatial grids; Each data point in the geological data set is mapped to the corresponding three-dimensional grid unit to construct a three-dimensional grid model of the underground environment. The expression is: Among them, M grid (x, y, z) represents the physical parameter distribution of the position coordinate (x, y, z) in the grid cell in the three-dimensional grid model, x represents the position coordinate in the east-west direction in the three-dimensional space, y represents the position coordinate in the north-south direction in the three-dimensional space, z represents the position coordinate in the depth direction in the three-dimensional space, h represents the depth, ρ(x, y, z) represents the density of the grid cell, v(x, y, z) represents the fluid velocity of the grid cell, P(x, y, z) represents the pressure of the grid cell, and β represents the attenuation coefficient related to the depth; Based on the current physical parameter distribution and historical data, combined with real-time monitoring data, the future geological change trend is predicted, and the expression is: Among them, T fut(x, y, z, t) represents the future geological change trend of the position coordinates (x, y, z) in the grid cell at time t, M grid (x, y, z, t-τ) represents the physical parameter distribution of the position coordinates (x, y, z) in the grid unit at the past time r-τ, γ represents the attenuation coefficient of the historical data, represents the real-time monitoring data of the position coordinates (x, y, z) of the i-th sensor in the grid unit at time t, λ i represents the coupling coefficient between real-time data and flow velocity, t represents the time variable, τ represents the time difference, i represents the sensor index variable, n represents the total number of sensors, and v i (x, y, z, t) represents the fluid velocity of the position coordinate (x, y, z) of the i-th sensor in the grid cell at time t; By analyzing the predicted results of future geological change trends, abnormal geological changes are identified and graded according to the severity of the anomalies; According to the anomaly detection and classification results, the corresponding early warning mechanism is triggered.

[0041] Specifically, when a geological parameter of a grid cell exceeds a preset safety threshold, the cell is marked as abnormal.

[0042] The abnormal classification standards are as follows: Set the abnormal deviation threshold, Level 1 anomaly: The anomaly area is small (e.g., less than 5 grid cells) and the anomaly value deviation is not large. Secondary anomaly: medium-sized anomaly area (5-20 grid cells) with large deviation of anomaly values. Level 3 anomaly: large-scale anomaly area (more than 20 grid cells) and the outlier value significantly deviates from the threshold.

[0043] Specifically, the early warning mechanism rules are set as follows: Level 1 warning: When a level 1 anomaly is detected, the operator is notified through a prompt warning, but no automatic action is taken.

[0044] Level 2 warning: When a level 2 anomaly is detected, a higher level warning is issued, and the relevant person in charge is notified and recommended to take preventive measures.

[0045] Level 3 warning: When a level 3 abnormality is detected, the highest level of warning is triggered and automatic emergency measures are taken immediately (such as suspending oil and gas production, initiating emergency response, etc.).

[0046] This embodiment also provides a computer device, which is suitable for the case of a complex environment information collection method based on a sensor network, including: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the complex environment information collection method based on a sensor network as proposed in the above embodiment.

[0047] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0048] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for collecting complex environmental information based on a sensor network as proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0049] In summary, the present invention effectively solves the problem of difficulty in determining the signal transmission path in a complex geological environment by constructing a multi-layer coupling model. The signal attenuation characteristics of each sensor node are calculated through the output of the coupling model, and a multi-layer repeater network is arranged accordingly, so that the signal transmission path is optimized and the path loss is reduced. In addition, through opportunistic data aggregation and dynamic compression strategies, data packets can be efficiently compressed according to the current network bandwidth and environmental status, which not only avoids the waste of bandwidth, but also ensures the integrity of key data. Finally, the compressed data is transmitted layer by layer to the surface control center, ensuring the efficient transmission of the data and the integrity after decompression.

[0050] Example 2, referring to Table 1, is the second example of the present invention. To further verify the technical solution of the present invention, experimental simulation data of a complex environment information collection method based on a sensor network is provided.

[0051] The experiment was conducted in a simulated underground environment. The depth of the experimental area ranged from 50 meters to 300 meters. Sensor nodes were arranged in the fracture area and at different depth levels to collect geological data. Specifically, the experiment divided the sensor nodes into three layers. The number of nodes in each layer varied according to the complexity of the geological structure. The geological data collected by the nodes in real time included rock density, temperature, pressure, and fluid flow.

[0052] The experiment adopted two different transmission schemes: one is the single-layer transmission method in the prior art, in which the sensor nodes directly transmit data upward point by point without data aggregation and compression; the other is the multi-layer coupling model and opportunistic aggregation strategy proposed in the present invention, in which the sensor nodes transmit data layer by layer through a multi-layer repeater network and dynamically adjust the compression strategy according to the signal transmission path.

[0053] In order to verify the advantages of the present invention, six groups of different geological environments and network bandwidth conditions were designed experimentally, and various performance indicators in each group of experiments were compared, including signal transmission path loss, data packet transmission delay, bandwidth utilization, data packet compression rate, data transmission integrity, data aggregation efficiency and accuracy of the prediction model. The network bandwidth in the experimental scenario was adjusted according to the geological conditions and node layout. The experiment lasted for 24 hours, and data was collected every 10 seconds.

[0054] The details are shown in Table 1 below: Table 1 Experimental data comparison table Signal transmission path loss: In all experimental groups, the signal attenuation of the present invention is much lower than that of the prior art. For example, in experimental group 1, the signal path loss of the present invention is 12.3dB, while that of the prior art is 25.7dB, and in experimental group 6, the loss of the present invention is only 11.0dB, while that of the prior art is 23.7dB. This shows that the present invention effectively reduces the attenuation of signals in complex geological environments by constructing a multi-layer coupling model.

[0055] Data packet transmission delay: The transmission delay of the present invention is significantly lower than that of the prior art. In experimental group 1, the transmission delay of the present invention is 45ms, while that of the prior art is 120ms; in experimental group 6, the delay of the present invention is only 38ms, while that of the prior art is as high as 115ms. This is attributed to the fact that the present invention adopts an opportunistic aggregation mechanism, which reduces the number of data packets transmitted, thereby improving transmission efficiency.

[0056] Bandwidth utilization: Experimental data show that the present invention is significantly superior to the prior art in terms of bandwidth utilization. In Experiment Group 1, the bandwidth utilization of the present invention is 85%, while that of the prior art is only 50%; in Experiment Group 6, the bandwidth utilization of the present invention reaches 89%, while that of the prior art is 57%. The dynamic compression strategy of the present invention can adjust the data compression rate according to the environmental status and network bandwidth, thereby greatly improving the effective utilization of bandwidth.

[0057] Data packet compression rate: The present invention uses a dynamic compression strategy to achieve a data packet compression rate between 70% and 76%, while the prior art does not perform compression and has a compression rate of 0%. In Experimental Group 6, the compression rate of the present invention reaches 76%, indicating that in a complex environment, the present invention can significantly reduce the amount of transmitted data and improve transmission efficiency through effective data compression.

[0058] Data transmission integrity: The data transmission integrity of the present invention is close to 100% in all experimental groups, while the data integrity of the prior art fluctuates between 90% and 91%. The present invention ensures that the data packet is not lost or damaged during the transmission process through a periodic verification mechanism, ensuring accurate data recovery.

[0059] Data aggregation efficiency: The efficiency of the opportunistic aggregation strategy of the present invention in each group of experiments is between 77% and 83%, while the efficiency of the prior art is 0% without data aggregation. This shows that the present invention can effectively aggregate data at the repeater node, reduce redundant information, and thus improve transmission efficiency.

[0060] Prediction model accuracy: The present invention is also significantly better than the prior art in terms of accuracy in building a panoramic model and predicting future geological trends. In Experimental Group 1, the prediction accuracy of the present invention was 94.3%, while that of the prior art was 85.1%; in Experimental Group 6, the accuracy of the present invention was further improved to 95.4%, while that of the prior art was 86.0%. This is because the present invention can combine multi-dimensional geological data and historical data to dynamically build a more accurate three-dimensional underground environment model, thereby improving the accuracy of the prediction.

[0061] Through the analysis of experimental data, it can be seen that the present invention has significant innovation and advantages over the existing technology in complex geological environments. The present invention can not only improve the efficiency and integrity of data transmission through the combination of multi-layer coupling model, opportunistic aggregation and dynamic compression strategy, but also more accurately capture the future geological change trend in geological prediction. These advantages make the present invention have great application prospects in the fields of geological monitoring and earthquake early warning.

[0062] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A complex environment information collection method based on a sensor network, characterized in that: include, Collect multi-dimensional geological data in real time, build a multi-layer coupling model, and calculate the signal transmission path and path loss between each sensor node; According to the signal transmission path, a multi-layer repeater network is arranged to transmit the geological data layer by layer to the control center; When multiple geological data meet at a repeater node, they are opportunistically aggregated to form an aggregated data packet; Based on the aggregated data packets and signal transmission paths, the data compression strategy is dynamically adjusted according to the current network bandwidth and environmental status to obtain compressed data packets; The compressed data packets are transmitted to the surface control center through a multi-layer repeater network for decompression and restoration to the original multi-dimensional geological data; By using the decompressed geological data, combined with real-time monitoring of geological changes and historical data, a panoramic model of the underground environment is constructed to predict future geological trends.

2. The complex environment information collection method based on sensor network as claimed in claim 1, characterized in that: The multi-dimensional geological data includes rock layer density, temperature, pressure and fluid flow; the collected multi-dimensional geological data is cleaned and formatted; The construction of the multi-layer coupling model comprises the following steps: According to the geological structure of the underground environment and the monitoring requirements of the target area, the sensor nodes are distributed at different depths and crack areas; According to the depth of sensor node deployment and geological characteristics, the geological structure is divided into the first layer, the second layer and the third layer, and the physical parameters corresponding to each layer are initialized; Through the parameters corresponding to each layer, the coupling relationship between layers is determined to obtain geological models of different depths and different characteristics.

3. The complex environment information collection method based on sensor network as claimed in claim 2, characterized in that: The steps of calculating the signal transmission path between the sensor nodes and determining the path loss include: According to the comprehensive geological characteristics of each area output by the coupling model, a signal attenuation model is established to calculate the signal transmission path between each sensor node. The expression is: ； in, is the received power, is the transmission power, is the signal wavelength, is the transmission distance, is the signal attenuation coefficient; Based on the signal transmission path, the signal loss in different paths is calculated, and the expression is: ； in, is the path loss.

4. The complex environment information collection method based on sensor network as claimed in claim 3, characterized in that: According to the signal transmission path, a multi-layer repeater network is arranged to transmit geological data layer by layer to the control center, including the following steps: Divide the repeater network into three layers, each layer is responsible for signal relay in a fixed depth area; The optimal repeater location is selected by coupling the geological characteristics output from the model; Deploy the main repeater node and backup repeater node at each repeater location, and use a combination of directional antennas and omnidirectional antennas to enable the main repeater node to receive signals from the lower sensor nodes and transmit the signals upward to the upper repeater and the surface control center; When the main repeater node fails, the backup repeater node starts to take over signal transmission.

5. The complex environment information collection method based on sensor network as claimed in claim 4, characterized in that: When multiple geological data meet at a repeater node, opportunistic aggregation is performed to form an aggregated data packet, including the following steps: The sensor nodes continuously collect geological data in their respective areas of responsibility and send data packets to the nearest repeater node; Each repeater node maintains an aggregation window, receives data packets from multiple sensor nodes and aggregates them within the aggregation window to obtain aggregated data packets; The repeater node performs semantic analysis on the aggregated data packets, removes redundant information, and transmits the aggregated data packets to the upper-layer repeater nodes through a multi-layer repeater network; The upper layer repeater nodes receive aggregated data packets from multiple lower layer nodes, aggregate these data packets, and transmit the data packets to the cluster head node through the multi-layer repeater network; The cluster head node aggregates all received data packets and transmits them to the surface control center through the signal transmission path.

6. The complex environment information collection method based on sensor network as claimed in claim 5, characterized in that: Based on the aggregated data packets and signal transmission paths, the data compression strategy is dynamically adjusted according to the current network bandwidth and environment status to obtain the compressed data packets, including the following steps: Real-time geological environment data is obtained through sensor nodes distributed at different depths. Each sensor node sends the monitored environmental data and geological data to the nearest repeater node; The repeater node performs a preliminary analysis of the received environmental data to determine the current environmental status; When the environment is stable, the aggregated data packets are compressed using a lossy compression method with a high compression ratio; When the environment changes drastically, a lossless compression method with a low compression ratio is used to compress the aggregated data packets; Mark the key data in each data packet and set priorities based on the importance of the data; Real-time detection of current network bandwidth, and calculation of bandwidth occupancy rate based on data size at different compression rates; Dynamically adjust data compression strategy based on bandwidth usage and data packet priority.

7. The complex environment information collection method based on sensor network as claimed in claim 6, characterized in that: The compressed data packets are transmitted to the surface control center through a multi-layer repeater network for decompression and restoration to the original multi-dimensional geological data, including the following steps: During transmission, the integrity of the data packet is monitored using a periodic checksum mechanism; The surface control center receives the compressed data packet and identifies the compression type used in the data packet; Decompress the data packet according to the identified compression type and restore it to the original multi-dimensional geological data; The decompressed data is integrity checked and stored in a hierarchical structure.

8. The complex environment information collection method based on sensor network as claimed in claim 7, characterized in that: Using the decompressed geological data, combined with real-time monitoring of geological changes and historical data, a panoramic model of the underground environment is constructed to predict future geological trends. The following steps are included: The real-time monitored geological data are integrated with the multi-dimensional geological data recovered after decompression to construct a geological data set; A variable resolution partitioning strategy is used to divide the underground environment into three-dimensional spatial grids; Each data point in the geological data set is mapped to the corresponding three-dimensional grid unit to construct a three-dimensional grid model of the underground environment. The expression is: Among them, M grid (x, y, z) represents the physical parameter distribution of the position coordinate (x, y, z) in the grid cell in the three-dimensional grid model, x represents the position coordinate in the east-west direction in the three-dimensional space, y represents the position coordinate in the north-south direction in the three-dimensional space, z represents the position coordinate in the depth direction in the three-dimensional space, h represents the depth, ρ(x, y, z) represents the density of the grid cell, v(x, y, z) represents the fluid velocity of the grid cell, P(x, y, z) represents the pressure of the grid cell, and β represents the attenuation coefficient related to the depth; Based on the current physical parameter distribution and historical data, combined with real-time monitoring data, the future geological change trend is predicted, and the expression is: Among them, T fut (x, y, z, t) represents the future geological change trend of the position coordinates (x, y, z) in the grid cell at time t, M grid (x, y, z, t-τ) represents the physical parameter distribution of the position coordinates (x, y, z) in the grid cell at the past time t-τ, γ represents the attenuation coefficient of the historical data, represents the real-time monitoring data of the position coordinates (x, y, z) of the i-th sensor in the grid unit at time t, λ i represents the coupling coefficient between real-time data and flow velocity, t represents the time variable, τ represents the time difference, i represents the sensor index variable, n represents the total number of sensors, and v i (x, y, z, t) represents the fluid velocity of the position coordinate (x, y, z) of the i-th sensor in the grid cell at time t; By analyzing the predicted results of future geological change trends, abnormal geological changes are identified and graded according to the severity of the anomalies; According to the anomaly detection and classification results, the corresponding early warning mechanism is triggered.

Images