Underground pipeline risk early warning system and method based on muon flux anomaly

Abstract

The invention belongs to the technical field of underground engineering safety monitoring, and provides an underground pipeline risk early warning system and method based on muon flux abnormity, and the technical scheme is that the system comprises a sensing layer which is used for collecting muon flux data and environmental parameters in real time; the edge calculation layer is used for performing data preprocessing and dynamic reference correction on the muon flux data and the environmental parameters which are acquired in real time, and calculating to obtain a flux anomaly index; the network transmission layer is used for constructing a data communication channel and performing data transmission and remote control on the data of the sensing layer and the data of the edge computing layer by adopting a layered protocol stack; and the cloud platform is used for extracting multi-dimensional features reflecting the state of the underground pipeline based on the data after dynamic reference correction, performing risk assessment and classification based on the extracted multi-dimensional features reflecting the state of the underground pipeline, and generating a multi-stage early warning response strategy according to a risk assessment and classification result. The problem of early recognition of risks such as pipeline leakage and cavities in a complex urban environment is solved.

Description

Technical Field

[0001] This invention belongs to the field of underground engineering safety monitoring technology, and in particular relates to an underground pipeline risk early warning system and method based on muon flux anomalies. Background Technology

[0002] The statements in this section are merely background information related to the present invention and do not necessarily constitute prior art.

[0003] With the acceleration of urbanization, the scale of underground pipelines is constantly expanding, posing serious challenges to their safe operation. Traditional monitoring technologies such as ground-penetrating radar (GPR), infrared thermal imaging, and acoustic detection suffer from insufficient penetration, poor real-time performance, and high false alarm rates. GPR typically penetrates no more than 3 meters into highly conductive strata and is susceptible to electromagnetic interference; infrared thermal imaging can only identify near-surface anomalies and is significantly affected by ambient temperature; while acoustic detection requires contact-mounted sensors, making it difficult to achieve large-scale continuous monitoring. These limitations make it difficult for existing technologies to meet the needs of deep risk identification for urban underground pipelines.

[0004] In recent years, cosmic ray muon imaging technology has demonstrated unique advantages in fields such as geological exploration and nuclear facility monitoring due to its extremely strong penetrating power and non-contact characteristics. Muons, as secondary particles resulting from the interaction of high-energy protons with the atmosphere, can penetrate hundreds of meters of rock layers. Their flux attenuation is closely related to the density of the medium, and they have been successfully applied to the detection of volcanic internal structures and the archaeological study of pyramids. However, existing muon imaging devices are generally bulky, have complex data processing algorithms, and are primarily geared towards geology and archaeology. A dedicated monitoring method for urban underground pipeline risks has not yet been developed. Particularly in the area of ​​pipeline-specific monitoring, a systematic solution lacking lightweight detector design, real-time risk identification algorithms, and multi-level early warning mechanisms is still lacking. Summary of the Invention

[0005] To address at least one of the technical problems mentioned above, this invention provides a method and system for early warning of underground pipeline risks based on muon flux anomalies. It develops a novel monitoring system that integrates high-sensitivity detection, intelligent risk analysis, and rapid early warning response to meet the urgent needs of urban underground space safety management and effectively solve the problem of early identification of risks such as pipeline leakage and cavities in complex urban environments.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: The first aspect of the present invention provides an underground pipeline risk early warning system based on muon flux anomalies, comprising: The sensing layer is used to collect muon flux data and environmental parameters in real time. The edge computing layer is used to preprocess and dynamically correct the real-time collected muon flux data and environmental parameters, and to calculate the flux anomaly index. The network transport layer is used to build data communication channels and uses a layered protocol stack to transmit data from the sensing layer and remotely control the edge computing layer. The cloud platform is used to extract multi-dimensional features reflecting the status of underground pipelines based on data after dynamic benchmark correction. Risk assessment and classification are performed based on the extracted multi-dimensional features reflecting the status of underground pipelines, and multi-level early warning and response strategies are generated based on the risk assessment and classification results.

[0007] Furthermore, in the sensing layer, muon flux data and environmental parameters are collected in real time based on the constructed monitoring network infrastructure; the construction of the monitoring network infrastructure includes: Muon detector nodes are deployed at set intervals along the underground pipeline to be monitored to ensure that the detector array is parallel to the pipeline direction; each monitoring node is equipped with a three-layer orthogonally arranged array of detectors and silicon photomultiplier tube sensors.

[0008] Furthermore, in the edge computing layer, when performing dynamic benchmark correction on the preprocessed muon flux data, a sliding time window algorithm is used to dynamically update the background flux reference value, and a stable background flux is obtained through median filtering.

[0009] Furthermore, in the cloud platform, the data extraction based on dynamic benchmark correction reflects multi-dimensional characteristics of the underground pipeline status, including: Spatial correlation analysis was performed on the muon flux data, and the flux spatial gradient was obtained based on the results of the spatial correlation analysis. Time series feature mining was performed on muon flux data to calculate flux change rate and energy spectrum characteristics; A multi-dimensional feature vector is constructed based on flux spatial gradient, flux change rate, energy spectrum characteristics, and flux anomaly index.

[0010] Furthermore, spatial correlation analysis of the muon flux data includes calculating the flux spatial gradient for a monitoring unit consisting of three adjacent nodes. Represented as: , in, This represents the flux difference between node 1 and node 2. This represents the actual physical distance between node 1 and node 3. This represents the flux difference between node 2 and node 3. This represents the actual physical distance between node 2 and node 3.

[0011] Furthermore, in the cloud platform, risk assessment and classification are performed based on the extracted multi-dimensional features reflecting the status of underground pipelines. This includes: inputting the multi-dimensional features into a pre-trained XGBoost evaluation model, and basing the assessment on the output medium density change rate. pore volume Weighted fusion yields a comprehensive risk score .

[0012] Furthermore, the cloud platform generates multi-level early warning and response strategies based on the risk assessment and classification results, including: When the risk score is slightly abnormal within the first range, the adjacent node review scan is automatically initiated and a preliminary report is generated; When the risk score is moderately abnormal in the second range, in addition to enhanced monitoring, a mobile muon detector carried by a drone is also used for verification. When the risk score is in the third range of severe anomalies, the emergency management system is directly triggered and the pipeline automatic shutdown protocol is initiated, forming a complete emergency response closed loop.

[0013] A second aspect of the present invention provides a method for early warning of underground pipeline risks based on muon flux anomalies, comprising the following steps: Real-time acquisition of muon flux data and environmental parameters; Data preprocessing and dynamic benchmark correction are performed on the real-time collected muon flux data and environmental parameters, and the flux anomaly index is calculated. Construct a data communication channel and adopt a layered protocol stack for data transmission and remote control between the sensing layer and the edge computing layer; Based on the data after dynamic benchmark correction, multi-dimensional features reflecting the status of underground pipelines are extracted. Risk assessment and classification are performed based on the extracted multi-dimensional features reflecting the status of underground pipelines. Multi-level early warning and response strategies are generated based on the risk assessment and classification results.

[0014] A third aspect of the present invention provides a computer-readable storage medium.

[0015] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the underground pipeline risk early warning method based on muon flux anomalies as described above.

[0016] A fourth aspect of the present invention provides a computer device.

[0017] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the underground pipeline risk early warning method based on muon flux anomalies as described above.

[0018] Compared with the prior art, the beneficial effects of the present invention are: This invention leverages the inherent strong penetrating properties of cosmic ray muons, combined with a "flux-density-deformation" coupling algorithm, to achieve high-precision (5mm resolution) monitoring of deep pipelines (10-30m) that traditional ground-penetrating radar (penetration ≤3m) cannot reach. The lightweight XGBoost model deployed at the edge computing layer significantly improves the risk identification speed compared to traditional methods, and the dynamic benchmark correction technology reduces the false alarm rate and lowers the operation and maintenance costs.

[0019] Advantages of additional aspects of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0020] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an improper limitation of the invention.

[0021] Figure 1 This is a schematic diagram of an underground pipeline risk early warning system based on muon flux anomalies provided in an embodiment of the present invention; Figure 2 This is a flowchart of an underground pipeline risk early warning method based on muon flux anomaly provided in an embodiment of the present invention; Figure 3 This is a structural example diagram of the electronic device provided in an embodiment of the present invention. Detailed Implementation

[0022] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0023] It should be noted that the following detailed description is illustrative and intended to provide further explanation of the invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0024] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of exemplary embodiments according to the invention. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Furthermore, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0025] like Figure 1 As shown, this embodiment provides an underground pipeline risk early warning system based on muon flux anomalies, including: The sensing layer is used to collect muon flux data and environmental parameters in real time. The edge computing layer is used to preprocess and dynamically correct the real-time collected muon flux data and environmental parameters, and to calculate the flux anomaly index. The network transport layer is used to build data communication channels and uses a layered protocol stack to transmit data from the sensing layer and remotely control the edge computing layer. The cloud platform is used to extract multi-dimensional features reflecting the status of underground pipelines based on data after dynamic benchmark correction. Risk assessment and classification are performed based on the extracted multi-dimensional features reflecting the status of underground pipelines, and multi-level early warning and response strategies are generated based on the risk assessment and classification results.

[0026] The sensing layer consists of distributed muon detection nodes, which are specifically deployed at intervals of 20-30 meters along the underground pipeline to be monitored, ensuring that the detector array is parallel to the pipeline direction.

[0027] Each node contains a muon detector: a three-layer orthogonal detection unit consisting of a plastic scintillator and a silicon photomultiplier tube (SiPM) array, used to capture muon trajectories. Specifically, each monitoring node is configured with a three-layer orthogonally arranged plastic scintillator detector and silicon photomultiplier tube (SiPM) sensor array, with the overall size controlled within a compact range of 60×40×20cm³.

[0028] Data acquisition unit: High-precision time-to-digital converter with a time resolution of <100ps, used to record the arrival time and position of muons.

[0029] Environmental monitoring module: integrates a barometer and temperature sensor to correct the impact of environmental factors on muon flux.

[0030] Power management module: Supports hybrid power supply of solar energy and lithium battery to ensure long-term unattended operation.

[0031] After node deployment, connect to the edge computing gateway and configure the LoRa wireless transmission module to establish a stable communication link with the cloud analytics platform. Before the system goes live, conduct 72 hours of continuous baseline data collection and establish baseline throughput values ​​for each node through statistical analysis. .

[0032] When collecting muon flux data and environmental parameters in real time, each detector node continuously records the three-dimensional position information, incident angle and energy characteristics of the muon passing through at a sampling frequency of 1Hz.

[0033] Furthermore, in the edge computing layer, data preprocessing of the real-time collected muon flux data and environmental parameters includes: The 3σ criterion is applied to automatically remove anomalous events such as cosmic ray bursts to ensure data quality. The specific filtering formula is as follows: , in, The filtered flux value is used to retain the original value if it falls within the range of mean ± 3 standard deviations; otherwise, it is considered an outlier. (Not a Number) is used instead to indicate that the data point has been removed. The original muon flux value measured at time t. This represents the absolute deviation of the current flux value from the mean. This represents the mean of the most recent 60 samples. It represents the standard deviation of the most recent 60 samples.

[0034] Achieve spatiotemporal synchronization of multi-node data through precise timestamp alignment; Calculate the average flux per minute Then, normalization is performed, and it is expressed as: , Where W is the sliding window size (1 minute), Δt is the sampling interval (1 second), and k is the summation index variable, ranging from 0 to W. An integer of 1, used to iterate through all data points within the sliding window.

[0035] Edge computing nodes synchronously perform multi-level data preprocessing. The preprocessed feature data is packaged and transmitted to the cloud analysis platform every 10 minutes, ensuring data timeliness while effectively reducing communication load.

[0036] Furthermore, in the edge computing layer, dynamic benchmark correction is performed on the preprocessed muon flux data and environmental parameters to obtain the flux anomaly index; In this embodiment, when performing dynamic baseline correction on the preprocessed muon flux data, a sliding time window algorithm is used to dynamically update the background flux reference value. The window length is set to 24 hours, covering the complete daily cycle variation. Stable background flux is obtained through median filtering. This effectively suppresses short-term fluctuations, as shown in the following: , in, In time The baseline flux at that location, The total length of the sliding window. The window start time, The window ends.

[0037] Furthermore, a standardized flux anomaly index is generated. , is represented as: , in, The index represents the standard deviation of historical fluctuations, accurately reflecting the degree of deviation from the baseline level.

[0038] Atmospheric pressure data is collected in real time, and the flux measurement values ​​are compensated according to a correction factor of 0.12% / hPa to eliminate systematic errors caused by changes in the atmospheric environment. , in, This represents the corrected flux anomaly index. This represents the atmospheric pressure correction factor. This represents the atmospheric pressure measurement at the current moment. This indicates the reference atmospheric pressure.

[0039] Furthermore, in the network transport layer, a reliable data communication channel is constructed, and a layered protocol stack is used to achieve efficient transmission and remote control of monitoring data, supporting adaptive switching of multiple network standards.

[0040] In the construction of the data communication channel, multiple redundancy mechanisms are used to ensure reliability: critical instructions are guaranteed to arrive using the TCP protocol; sensor data uses UDP+MQTT QoS 1 to balance efficiency and reliability; forward error correction codes (such as Hamming codes) are embedded to correct bit errors in real time; each node is equipped with a 4G and LoRa dual-mode module and forms a mesh network, which automatically switches or is relayed through adjacent nodes when the main link is interrupted, eliminating single points of failure from the protocol to the hardware.

[0041] The system employs a layered protocol stack to achieve efficient transmission and remote control of monitoring data. Specifically, the application layer uses an MQTT publish / subscribe model, distributing and compressing data by topic to achieve decoupling and efficient distribution. The transport layer features intelligent traffic splitting: UDP transmits high-frequency sensor data, while TCP transmits critical commands. The network layer uses IPv6 and 6LoWPAN header compression to adapt to narrowband networks. The link layer dynamically adjusts physical parameters (such as LoRa spreading factor) based on the real-time signal-to-noise ratio. Control commands are precisely delivered through topics, and node responses confirm the delivery, forming a closed loop. At a scale of hundreds of nodes, the end-to-end latency is <200ms.

[0042] Specifically, the conditions for multi-network adaptive handover include: The handover is automatically decided by the edge gateway based on a weighted algorithm. Key evaluation parameters include: real-time link quality (signal-to-noise ratio, packet loss rate, weight 40%), cost and energy consumption (weight 45%), and service priority (weight 15%). The handover is triggered when the overall score falls below the current network threshold and the backup network's estimated score is higher. For example, when the 4G signal is weak or non-critical data is being transmitted, a switch to low-power LoRa may occur. The handover process is smooth, ensuring uninterrupted data flow.

[0043] The cloud platform centrally processes and analyzes global monitoring data, and uses a distributed computing architecture to achieve throughput reconstruction, risk assessment, and 3D visualization, providing decision support and early warning management functions.

[0044] Specifically, the data used for extracting multi-dimensional features reflecting the status of underground pipelines based on dynamically corrected benchmarks includes: Spatial correlation analysis was performed on the muon flux data, and the flux spatial gradient was obtained based on the results of the spatial correlation analysis. Specifically, through spatial correlation analysis, the flux spatial gradient is calculated for a monitoring unit consisting of three adjacent nodes. Represented as: , in, This represents the flux difference between node 1 and node 2. This represents the actual physical distance between node 1 and node 3. This represents the flux difference between node 2 and node 3. This is the actual physical distance between node 2 and node 3. This parameter can effectively locate the spatial position of the abnormal area.

[0045] Time series feature mining was performed on muon flux data to calculate flux change rate and energy spectrum characteristics; In this embodiment, the flux change rate dΦ / dt is calculated using a 6-hour sliding window, and wavelet transform is used to extract the energy spectrum features E in the 1-5Hz frequency band.

[0046] A multi-dimensional feature vector is constructed based on flux spatial gradient, flux change rate, energy spectrum characteristics, and flux anomaly index. By using multi-dimensional feature vectors to jointly reflect the pipeline status, a comprehensive basis is provided for subsequent risk assessment.

[0047] Furthermore, the cloud platform performs risk assessment and classification based on extracted multi-dimensional features reflecting the status of underground pipelines, including: Input the feature vectors into the pre-trained XGBoost evaluation model The XGBoost evaluation model, trained on labeled samples, has a 7-layer tree depth structure. The final model output includes three key indicators: the rate of change of medium density ρ, the void volume V, and a comprehensive risk score; among which, the rate of change of medium density... pore volume These are the two core physical quantities that influence the score; specifically, the comprehensive risk score. It is the core decision indicator output by the model, which is the rate of change of medium density. and void volume The scalar value obtained by weighted fusion.

[0048] The warning levels are divided into three levels based on the risk score: Low-risk status ( <0.3) for logging only; medium risk (0.3≤ <0.7) triggers a yellow alert; high risk ( If the value is ≥0.7, a red alert will be immediately activated to achieve tiered risk management.

[0049] Furthermore, the cloud platform generates multi-level early warning and response strategies based on risk assessment and classification results. These multi-level early warning and response mechanisms ensure accurate and effective risk management, including: When the risk score is in the first range, such as 3-5 For minor anomalies, the system automatically initiates a verification scan of adjacent nodes and generates a preliminary report; When the risk score is in the second range, such as 5-8 In cases of moderate anomalies, in addition to enhanced monitoring, a mobile muon detector carried by a drone is also used for verification. When the risk score is in the third range, such as exceeding 8 The severe anomaly directly triggered the emergency management system and initiated the pipeline automatic shutdown protocol, forming a complete emergency response closed loop.

[0050] like Figure 2 As shown in the figure, this embodiment provides a method for early warning of underground pipeline risks based on muon flux anomalies, including the following steps: Step 1: Collect muon flux data and environmental parameters in real time based on the constructed monitoring network infrastructure; In this embodiment, the construction of the monitoring network infrastructure includes: Muon detector nodes are deployed along the underground pipeline to be monitored at intervals of 20-30 meters, ensuring that the detector array is parallel to the pipeline's direction. Each monitoring node is equipped with a three-layer orthogonally arranged plastic scintillator detector and a silicon photomultiplier tube (SiPM) sensor array, with the overall size controlled within a compact range of 60×40×20cm³. After the nodes are deployed, they are connected to an edge computing gateway and configured with a LoRa wireless transmission module to establish a stable communication link with the cloud analysis platform. Before the system officially goes into operation, continuous baseline data collection for 72 hours is conducted, and baseline flux values ​​for each node are established through statistical analysis. .

[0051] When collecting muon flux data and environmental parameters in real time, each detector node continuously records the three-dimensional position information, incident angle and energy characteristics of the muon passing through at a sampling frequency of 1Hz.

[0052] Step 2: Perform data preprocessing on the real-time collected muon flux data and environmental parameters; Edge computing nodes synchronously perform multi-level data preprocessing. The preprocessed feature data is packaged and transmitted to the cloud analysis platform every 10 minutes, ensuring data timeliness while effectively reducing communication load.

[0053] In this embodiment, multi-level data preprocessing is performed, specifically including: The 3σ criterion is applied to automatically eliminate anomalous events such as cosmic ray bursts to ensure data quality; Achieve spatiotemporal synchronization of multi-node data through precise timestamp alignment; Calculate the average flux per minute And then normalize it.

[0054] Step 3: Perform dynamic baseline correction on the preprocessed muon flux data and environmental parameters to obtain the flux anomaly index; In this embodiment, when performing dynamic baseline correction on the preprocessed muon flux data, a sliding time window algorithm is used to dynamically update the background flux reference value. The window length is set to 24 hours, covering the complete daily cycle variation. Stable background flux is obtained through median filtering. This effectively suppresses short-term fluctuations, as shown in the following: , in, Here is the baseline flux value at time t, where T is the total length of the sliding window, and t is the baseline value. T / 2 is the start time of the window, and t+T / 2 is the end time of the window.

[0055] Atmospheric pressure data is collected in real time, and the flux measurement values ​​are compensated according to a correction factor of 0.12% / hPa to eliminate systematic errors caused by changes in the atmospheric environment. , in, This represents the corrected flux anomaly index. This represents the original flux anomaly index. This represents the atmospheric pressure correction factor. This represents the atmospheric pressure measurement at the current moment. This indicates the reference atmospheric pressure.

[0056] Step 4: Extract multi-dimensional features reflecting the status of underground pipelines based on the data after dynamic benchmark correction; In this embodiment, the multi-dimensional feature extraction process for underground pipelines specifically includes the following steps: Step 401: Perform spatial correlation analysis on the muon flux data and obtain the flux spatial gradient based on the results of the spatial correlation analysis; Specifically, through spatial correlation analysis, the flux spatial gradient is calculated for a monitoring unit consisting of three adjacent nodes. Represented as: , in, This represents the flux difference between node 1 and node 2. This represents the actual physical distance between node 1 and node 3. This represents the flux difference between node 2 and node 3. This is the actual physical distance between node 2 and node 3. This parameter can effectively locate the spatial position of the abnormal area.

[0057] Step 402: Perform time series feature mining on muon flux data to calculate flux change rate and energy spectrum characteristics; In this embodiment, the flux change rate dΦ / dt is calculated using a 6-hour sliding window, and wavelet transform is used to extract the energy spectrum features E in the 1-5Hz frequency band.

[0058] Step 403: Construct a multi-dimensional feature vector based on flux spatial gradient, flux change rate, energy spectrum characteristics, and flux anomaly index; By using multi-dimensional feature vectors to jointly reflect the pipeline status, a comprehensive basis is provided for subsequent risk assessment.

[0059] Step 5: Conduct risk assessment and classification based on the extracted multi-dimensional features reflecting the status of underground pipelines; In this embodiment, the feature vector is input into the pre-trained XGBoost evaluation model. The XGBoost evaluation model, trained on labeled samples, has a 7-layer tree depth structure. The final model output includes three key indicators: the rate of change of medium density ρ, the void volume V, and a comprehensive risk score; among which, the rate of change of medium density... pore volume These are the two core physical quantities that influence the score; specifically, the comprehensive risk score. It is the core decision indicator output by the model, which is the rate of change of medium density. and void volume The scalar value obtained by weighted fusion.

[0060] Step 6: Generate a multi-level early warning and response strategy based on the risk assessment and classification results; the multi-level early warning and response mechanism can ensure the accuracy and effectiveness of risk management.

[0061] When the risk score is in the first range, such as 3-5 For minor anomalies, the system automatically initiates a verification scan of adjacent nodes and generates a preliminary report; When the risk score is in the second range, such as 5-8 In cases of moderate anomalies, in addition to enhanced monitoring, a mobile muon detector carried by a drone is also used for verification. When the risk score is in the third range, such as exceeding 8 The severe anomaly directly triggered the emergency management system and initiated the pipeline automatic shutdown protocol, forming a complete emergency response closed loop.

[0062] Step 7: System self-optimization; The system automatically performs online model updates monthly, incorporating new monitoring data into the training set through incremental learning algorithms to continuously improve model adaptability. Furthermore, hardware calibration and maintenance are performed quarterly, including SiPM gain calibration and time synchronization calibration, to ensure the system maintains optimal operating condition.

[0063] Please see Figure 3 , Figure 3 This is a schematic diagram of the structure of a computer device provided in an optional embodiment of the present invention, such as... Figure 3As shown, the computer device includes one or more processors 10, memory 20, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components communicate with each other via different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on external input / output devices (such as display devices coupled to the interfaces). In some alternative implementations, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 3 Take a processor 10 as an example.

[0064] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GDA), or any combination thereof.

[0065] The memory 20 stores instructions executable by at least one processor 10 to cause the at least one processor 10 to perform the method shown in the above embodiments.

[0066] The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the computer device. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0067] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0068] The computer device also includes an input device 30 and an output device 40. The processor 10, memory 20, input device 30, and output device 40 can be connected via a bus or other means. Figure 3 Taking the example of a connection between China and Israel via a bus.

[0069] Input device 30 can receive input numerical or character information, and generate key signal inputs related to user settings and function control of the computer device, such as a touchscreen, keypad, mouse, trackpad, touchpad, joystick, one or more mouse buttons, trackball, joystick, etc. Output device 40 may include display devices, auxiliary lighting devices (e.g., LEDs), and haptic feedback devices (e.g., vibration motors). The aforementioned display devices include, but are not limited to, liquid crystal displays, light-emitting diodes, displays, and plasma displays. In some alternative embodiments, the display device may be a touchscreen.

[0070] The computer device also includes a communication interface 30 for communicating with other devices or communication networks.

[0071] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as recordable on a storage medium, or implemented as computer code originally stored on a remote storage medium or a non-transitory machine-readable storage medium and subsequently stored on a local storage medium after being downloaded via a network. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium may also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code, which, when accessed and executed by the computer, processor, or hardware, implements the methods shown in the above embodiments.

[0072] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A risk early warning system for underground pipelines based on muon flux anomalies, characterized in that, include: The sensing layer is used to collect muon flux data and environmental parameters in real time. The edge computing layer is used to preprocess and dynamically correct the real-time collected muon flux data and environmental parameters, and to calculate the flux anomaly index. The network transport layer is used to build data communication channels and uses a layered protocol stack to transmit data from the sensing layer and remotely control the edge computing layer. The cloud platform is used to extract multi-dimensional features reflecting the status of underground pipelines based on data after dynamic benchmark correction. Risk assessment and classification are performed based on the extracted multi-dimensional features reflecting the status of underground pipelines, and multi-level early warning and response strategies are generated based on the risk assessment and classification results.

2. The underground pipeline risk early warning system based on muon flux anomalies as described in claim 1, characterized in that, In the sensing layer, muon flux data and environmental parameters are collected in real time based on the constructed monitoring network infrastructure. The construction of the monitoring network infrastructure includes: Muon detector nodes are deployed at set intervals along the underground pipeline to be monitored to ensure that the detector array is parallel to the pipeline direction; each monitoring node is equipped with a three-layer orthogonally arranged array of detectors and silicon photomultiplier tube sensors.

3. The underground pipeline risk early warning system based on muon flux anomalies as described in claim 1, characterized in that, In the edge computing layer, when performing dynamic baseline correction on the preprocessed muon flux data, a sliding time window algorithm is used to dynamically update the background flux reference value, and a stable background flux is obtained through median filtering.

4. The underground pipeline risk early warning system based on muon flux anomalies as described in claim 1, characterized in that, In the cloud platform, the data extraction based on dynamic benchmark correction reflects the multi-dimensional characteristics of the underground pipeline status, including: Spatial correlation analysis was performed on the muon flux data, and the flux spatial gradient was obtained based on the results of the spatial correlation analysis. Time series feature mining was performed on muon flux data to calculate flux change rate and energy spectrum characteristics; A multi-dimensional feature vector is constructed based on flux spatial gradient, flux change rate, energy spectrum characteristics, and flux anomaly index.

5. The underground pipeline risk early warning system based on muon flux anomalies as described in claim 1, characterized in that, Spatial correlation analysis of muon flux data includes calculating the spatial gradient of flux for a monitoring unit consisting of three adjacent nodes. Represented as: ， in, This represents the flux difference between node 1 and node 2. This represents the actual physical distance between node 1 and node 3. This represents the flux difference between node 2 and node 3. This represents the actual physical distance between node 2 and node 3.

6. The underground pipeline risk early warning system based on muon flux anomalies as described in claim 1, characterized in that, In the cloud platform, risk assessment and classification are performed based on extracted multi-dimensional features reflecting the status of underground pipelines. This includes: inputting the multi-dimensional features into a pre-trained XGBoost evaluation model, and basing the assessment on the output medium density change rate. pore volume Weighted fusion yields a comprehensive risk score .

7. The underground pipeline risk early warning system based on muon flux anomalies as described in claim 1, characterized in that, The cloud platform generates multi-level early warning and response strategies based on risk assessment and classification results, including: When the risk score is slightly abnormal within the first range, the adjacent node review scan is automatically initiated and a preliminary report is generated; When the risk score is moderately abnormal in the second range, in addition to enhanced monitoring, a mobile muon detector carried by a drone is also used for verification. When the risk score is in the third range of severe anomalies, the emergency management system is directly triggered and the pipeline automatic shutdown protocol is initiated, forming a complete emergency response closed loop.

8. A method for early warning of underground pipeline risks based on muon flux anomalies, characterized in that, Includes the following steps: Real-time acquisition of muon flux data and environmental parameters; Data preprocessing and dynamic benchmark correction are performed on the real-time collected muon flux data and environmental parameters, and the flux anomaly index is calculated. Construct a data communication channel and adopt a layered protocol stack for data transmission and remote control between the sensing layer and the edge computing layer; Based on the data after dynamic benchmark correction, multi-dimensional features reflecting the status of underground pipelines are extracted. Risk assessment and classification are performed based on the extracted multi-dimensional features reflecting the status of underground pipelines. Multi-level early warning and response strategies are generated based on the risk assessment and classification results.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by the processor, the program implements the steps in the underground pipeline risk early warning method based on muon flux anomalies as described in claim 8.

10. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps in the underground pipeline risk early warning method based on muon flux anomaly as described in claim 8.

Images