Underground pipe gallery deformation monitoring method and system combined with muon imaging and medium

Abstract

The invention discloses an underground pipe gallery deformation monitoring method and system combined with muon imaging and a medium, and relates to the related technical field of underground pipe gallery deformation monitoring, and the method comprises the steps: arranging a plurality of muon detectors to form a muon detection network; collecting muon flux data of a standard structure, and reconstructing to obtain a reference three-dimensional density image; acquiring muon detection network acquisition data of an operation monitoring period, and reconstructing to obtain a monitored three-dimensional density image; performing difference calculation on the monitoring three-dimensional density image and the reference three-dimensional density image to generate a density change difference image; evaluating the deformation of the underground pipe gallery according to the difference of the abnormal area, judging whether the underground pipe gallery deforms or not, and sending a deformation feedback result; the technical problems that in the prior art, pipe gallery deformation monitoring is not comprehensive in coverage range, low in data accuracy and difficult to achieve continuous monitoring are solved. All-area monitoring of the pipe gallery is achieved, the data accuracy is improved, and the technical effect of continuous monitoring is achieved.

Description

Technical Field

[0001] This invention relates to the technical field of underground utility tunnel deformation monitoring, specifically to a method, system, and medium for underground utility tunnel deformation monitoring combined with muon imaging. Background Technology

[0002] Underground utility tunnels are the core of urban infrastructure, carrying power, communication, water supply, and drainage pipelines. Their structural stability is directly related to the safety of urban operations. With increasing service life and the impact of surrounding soil settlement and construction disturbances, utility tunnels are prone to deformation and cracking. If not monitored in time, this can lead to pipeline leaks, collapses, and other accidents. Currently, deformation monitoring of underground utility tunnels mainly relies on traditional sensor monitoring and conventional non-destructive testing (NDT) techniques. Traditional sensor monitoring requires the deployment of numerous hardware devices inside the tunnel, enabling only localized monitoring of the sensor locations. This results in limited monitoring range, susceptibility to electromagnetic interference within the tunnel affecting data accuracy, and difficulty in simultaneously monitoring the deformation of the surrounding soil, failing to comprehensively reflect the collaborative deformation risks between the tunnel and its environment. While conventional NDT techniques can achieve non-contact monitoring within a certain range, they are limited by detection depth, resolution, and environmental adaptability. In complex geological conditions, they are prone to detection blind spots or data distortion. Furthermore, these techniques require interrupting normal tunnel operation for periodic inspections, making it difficult to meet the needs of long-term continuous monitoring of utility tunnels.

[0003] Therefore, existing technologies suffer from limitations in the range of traditional sensor monitoring of utility tunnels, susceptibility to electromagnetic interference, and the fact that conventional non-destructive testing is subject to geological constraints, resulting in blind spots and difficulty in continuous monitoring. These issues lead to incomplete coverage, low data accuracy, and difficulty in achieving continuous monitoring of utility tunnel deformation. Summary of the Invention

[0004] This invention provides a method, system, and medium for monitoring the deformation of underground utility tunnels using muon imaging. It addresses the technical problems of existing technologies, such as the limited range and susceptibility to electromagnetic interference with traditional sensor monitoring, and the limitations of conventional non-destructive testing due to geological constraints leading to blind spots and difficulties in continuous monitoring. These issues result in incomplete coverage, low data accuracy, and the inability to achieve continuous monitoring. By deploying a muon detection network to collect data, reconstructing a baseline and monitoring a three-dimensional density image, and differentially identifying abnormal areas, the invention evaluates the deformation of the utility tunnel. This achieves comprehensive monitoring of the utility tunnel and surrounding soil, avoids electromagnetic interference and geological blind spots, improves data accuracy, and enables continuous monitoring.

[0005] In view of the above problems, the present invention adopts the following technical solution: In a first aspect, the present invention provides a method for monitoring the deformation of underground utility tunnels using muon imaging, comprising: deploying multiple muon detectors along the extension direction of the underground utility tunnel to form a muon detection network; collecting muon flux data of a standard structure based on the muon detection network and reconstructing a baseline three-dimensional density image of the utility tunnel and its surrounding soil; acquiring muon detection network data collected during the operation monitoring cycle and reconstructing a monitoring three-dimensional density image; performing differential calculation between the monitoring three-dimensional density image and the baseline three-dimensional density image to generate a density change differential image, and using a preset density change threshold to traverse and identify abnormal areas; evaluating the deformation of the underground utility tunnel based on the differential of the abnormal areas, determining whether the underground utility tunnel has deformed, and sending deformation feedback results.

[0006] Secondly, the present invention also provides an underground utility tunnel deformation monitoring system combined with muon imaging, comprising: a muon detection network deployment module, used to deploy multiple muon detectors along the extension direction of the underground utility tunnel to form a muon detection network; a reference three-dimensional density image reconstruction module, used to collect muon flux data of a standard structure based on the muon detection network and reconstruct a reference three-dimensional density image of the utility tunnel and its surrounding soil; a monitoring three-dimensional density image acquisition module, used to acquire data collected by the muon detection network during the operation monitoring cycle and reconstruct a monitoring three-dimensional density image; an abnormal area identification module, used to perform differential calculation between the monitoring three-dimensional density image and the reference three-dimensional density image to generate a density change differential image, and to traverse and identify abnormal areas using a preset density change threshold; and a deformation evaluation and feedback module, used to evaluate the deformation of the underground utility tunnel based on the differential of the abnormal areas, determine whether the underground utility tunnel has deformed, and send deformation feedback results.

[0007] On the other hand, the present invention also provides a computer-readable storage medium, comprising: a computer program stored thereon, which, when executed by a processor, implements a method for monitoring the deformation of underground utility tunnels in conjunction with muon imaging.

[0008] One or more technical solutions provided in this invention have at least the following technical effects or advantages: This invention discloses the deployment of multiple muon detectors along the extension direction of an underground utility tunnel to form a muon detection network. Based on this network, muon flux data of a standard structure is collected, and a baseline three-dimensional density image of the tunnel and its surrounding soil is reconstructed. Data collected by the muon detection network during the operational monitoring cycle is acquired, and a monitoring three-dimensional density image is reconstructed. The monitoring three-dimensional density image and the baseline three-dimensional density image are compared using differential calculations to generate a density change differential image. Anomalies are identified by traversing the network using a preset density change threshold. The deformation of the underground utility tunnel is evaluated based on the differential values ​​of the anomalies, determining whether deformation has occurred and sending deformation feedback results. This achieves comprehensive monitoring of the utility tunnel and its surrounding soil, avoids electromagnetic interference and geological blind spots, improves data accuracy, and enables continuous monitoring. Attached Figure Description

[0009] Figure 1 This is a flowchart illustrating the underground utility tunnel deformation monitoring method based on muon imaging, as described in this invention.

[0010] Figure 2 This is a schematic diagram of the underground utility tunnel deformation monitoring system based on muon imaging, as described in this invention.

[0011] Figure labeling: Muon detection network deployment module 11, baseline 3D density image reconstruction module 12, monitoring 3D density image acquisition module 13, anomaly region identification module 14, deformation evaluation and feedback module 15. Detailed Implementation

[0012] This invention provides a method, system, and medium for monitoring the deformation of underground utility tunnels using muon imaging. It addresses the technical problems of existing technologies, such as the limited range and susceptibility to electromagnetic interference with traditional sensor monitoring, and the limitations of conventional non-destructive testing due to geological constraints leading to blind spots and difficulties in continuous monitoring. These issues result in incomplete coverage, low data accuracy, and the inability to achieve continuous monitoring. By deploying a muon detection network to collect data, reconstructing a baseline and monitoring a three-dimensional density image, and differentially identifying abnormal areas, the invention evaluates the deformation of the utility tunnel. This achieves comprehensive monitoring of the utility tunnel and surrounding soil, avoids electromagnetic interference and geological blind spots, improves data accuracy, and enables continuous monitoring.

[0013] like Figure 1 As shown, this invention provides a method for monitoring the deformation of underground utility tunnels using muon imaging, the method comprising: S100: Multiple muon detectors are deployed along the extended direction of the underground utility tunnel to form a muon detection network.

[0014] Specifically, this involves pre-planning monitoring points on the inner wall or perimeter of the utility tunnel according to its actual extension path, and installing multiple muon detectors at certain intervals. This creates a monitoring network covering the entire utility tunnel and surrounding key soil areas. Pre-planned monitoring points refer to the installation locations predetermined before deploying the muon detectors, taking into account the structural characteristics of the underground utility tunnel, key areas of the surrounding soil, and monitoring accuracy requirements. This ensures that the detectors can fully cover the utility tunnel and the surrounding areas requiring focused monitoring, laying the foundation for subsequent data collection. The structural characteristics of the underground utility tunnel include bends and interface sections. The specific spacing needs to be determined based on both the monitoring accuracy and the length of the utility tunnel.

[0015] S200: Based on the muon detection network, collect muon flux data of the standard structure and reconstruct a baseline three-dimensional density image of the pipe gallery and its surrounding soil.

[0016] Specifically, when the underground utility tunnel is in a stable initial state, a synchronization clock unit is used to synchronize the time of all detectors in the muon detection network, controlling the detectors to continuously collect muon flux data for a predetermined period of time. This data serves as the muon flux data for the standard structure. An iterative reconstruction algorithm is then used to process this data, discretizing the three-dimensional space of the tunnel and its surroundings into a voxel matrix and iteratively correcting the density. Finally, a baseline three-dimensional density image reflecting the initial density distribution of the tunnel and its surrounding soil is generated. The muon flux data for the standard structure refers to the muon flux data collected by the muon detection network when the tunnel is in a stable, undeformed state, reflecting the initial density characteristics of the tunnel and its surrounding soil. The baseline three-dimensional density image is generated using the muon flux data of the standard structure through an iterative reconstruction algorithm, presenting the initial three-dimensional density distribution of the tunnel and its surrounding soil.

[0017] S300: Acquires muon detection network data during the operational monitoring cycle and reconstructs the monitoring three-dimensional density image.

[0018] Specifically, this involves continuously collecting muon flux data of the utility tunnel and surrounding soil using a pre-deployed muon detection network according to a set monitoring cycle. Then, using the same data processing method as for generating the baseline 3D density image, the data collected during this cycle is analyzed and processed to ultimately construct a 3D density image of the utility tunnel and surrounding soil for the corresponding operational phase. The set monitoring cycle can be monthly or yearly. The muon flux data collected by the operational monitoring network during the operation cycle refers to the muon flux data collected by the network within the preset monitoring cycle during the utility tunnel's operation, reflecting the real-time density status of the utility tunnel and surrounding soil within that cycle. The monitoring 3D density image is an image generated using the muon flux data collected during the operational monitoring cycle, showing the 3D density distribution of the utility tunnel and surrounding soil for the corresponding cycle. This image is used to compare with the baseline 3D density image to identify density changes.

[0019] S400: Perform differential calculation between the monitored three-dimensional density image and the reference three-dimensional density image to generate a density change differential image, and use a preset density change threshold to traverse and identify abnormal areas.

[0020] Specifically, in the operation and monitoring of underground utility tunnels, a baseline 3D density image generated during the tunnel's stable period is used as a reference. For monitoring 3D density images acquired during the operation and monitoring cycle, the density difference between the two images is calculated pixel by pixel according to the same spatial coordinate correspondence. This is the difference between the monitored density value and the baseline density value. Through this global differential operation, a density change differential image is generated that intuitively reflects the density changes at various locations within the tunnel and surrounding soil. Subsequently, based on the characteristics of the tunnel's structural materials, surrounding geological conditions, and engineering safety monitoring standards, a reasonable density change threshold is pre-set. Using this threshold as a judgment standard, all voxels in the density change differential image are comprehensively screened. Continuous areas formed by voxels whose density change values ​​exceed this threshold are identified as abnormal areas that may pose a deformation risk. The density change differential image is an image generated by the differential operation of the corresponding voxel density values ​​between the monitoring 3D density image and the baseline 3D density image. It can visually present the density changes of the tunnel and surrounding soil during the operation cycle, clearly marking the specific spatial locations and magnitudes of density increases or decreases, providing a direct data carrier for subsequent abnormal area identification. The preset density change threshold refers to the critical value of density change determined in advance by combining the design parameters of the utility tunnel, the physical properties of the materials, the geological environment parameters and the engineering safety requirements. It is a quantitative standard to distinguish between normal density fluctuations and abnormal density changes, ensuring that only areas of density change that exceed the reasonable range are identified as abnormal, and avoiding misjudgment or omission.

[0021] S500: Evaluate the deformation of the underground utility tunnel based on the differential evaluation of the abnormal area, determine whether the underground utility tunnel has deformed, and send the deformation feedback result.

[0022] Specifically, the process begins by using density change differential data corresponding to identified abnormal areas, such as the specific values ​​and coverage of density changes, to correlate with the deformation of the utility tunnel using a pre-defined analysis method. The resulting deformation is then calculated. Next, the calculated deformation is compared with the allowable deformation range for normal operation of the utility tunnel to determine if it has exceeded the normal range. Finally, if deformation is determined, key information such as the deformation amount and the location of the abnormal area is integrated to form a deformation feedback result. If no deformation is determined, the monitoring data and the conclusion of no deformation are combined to form a feedback result, which is then sent to the relevant monitoring or management platform to provide data support for the safe operation of the utility tunnel.

[0023] Furthermore, the present invention also discloses a method for differentially evaluating the deformation of underground utility tunnels based on the abnormal area, determining whether the underground utility tunnel has deformed, and sending deformation feedback results, including: acquiring monitoring data from traditional sensors deployed in the underground utility tunnel during the same time period, wherein the traditional sensors include one or more of strain sensors, settlement sensors, and crack sensors; performing spatiotemporal correlation and fusion analysis on the spatial location information of the abnormal area and the monitoring data of the traditional sensors to conduct a deformation risk assessment of the abnormal area and generate a deformation risk assessment result; when the deformation risk assessment result indicates that deformation has occurred, generating deformation early warning information based on the deformation amount and spatial location of the abnormal area; when the deformation risk assessment result indicates that no deformation has occurred, generating the deformation feedback result from the monitoring data and the conclusion of no deformation.

[0024] Specifically, after evaluating the deformation of the underground utility tunnel based on the differential assessment of the abnormal area, a multi-step operation is then performed to determine whether the tunnel is deformed and to send feedback results. First, data from traditional sensors installed in the underground utility tunnel are collected during the same period as the muon detection network monitoring. These traditional sensors can be selected from strain sensors, settlement sensors, and crack sensors, ensuring that the data is synchronized with the muon detection data in time, providing matching traditional monitoring basis for subsequent analysis. Next, the spatial location information of the identified abnormal areas, such as the specific segment of the abnormal area in the utility tunnel and its three-dimensional coordinate range, is spatiotemporally correlated and fused with the collected traditional sensor monitoring data to assess whether there is deformation risk in the abnormal area and how much risk there is, generating a deformation risk assessment result. Then, the deformation risk assessment result is processed according to different situations. If the result shows that the utility tunnel has deformed, the deformation amount obtained from the previous assessment and the spatial location information of the abnormal area are combined to generate deformation warning information including specific deformation details, such as deformation size and risk location. If the result shows that the utility tunnel has not deformed, the muon detection data, traditional sensor monitoring data, and the conclusion that the utility tunnel has not deformed generated during this monitoring process are integrated to form a complete deformation feedback result and sent out. Spatiotemporal correlation refers to accurately matching the spatial location of anomaly areas, such as specific segments and three-dimensional coordinates within the utility tunnel, with monitoring data from traditional sensors during the same monitoring period. This ensures a one-to-one correspondence between the anomaly information and sensor data used in the analysis, preventing deviations in the assessment of anomaly deformation due to spatiotemporal misalignment. Fusion analysis involves comprehensively integrating and cross-validating information related to anomalies identified by muon imaging technology, such as density variation characteristics and size, with data on strain, settlement, and cracks in the utility tunnel monitored by traditional sensors. This overcomes the limitations of single monitoring technologies, such as the insufficient perception of subtle local deformations by muon imaging and the limited monitoring range of traditional sensors. This allows for a comprehensive analysis of anomaly deformation and more accurate assessments. Deformation risk assessment results, derived from spatiotemporal correlation and fusion analysis of anomalies, provide a clear conclusion regarding whether the area will cause utility tunnel deformation and the level of deformation risk (e.g., no risk, low risk, high risk). This conclusion serves as the basis for deciding whether to generate deformation warning information or conventional deformation feedback results. Deformation early warning information refers to the warning information generated when deformation of the utility tunnel is determined, based on the amount of deformation and the spatial location of the abnormal area. This information clarifies the degree and location of the deformation, providing guidance for timely response. Deformation feedback results refer to the complete feedback formed by integrating muon detection data, traditional sensor data, and the conclusion of no deformation when the utility tunnel is determined to be undeformed. This feedback is used to inform the utility tunnel of its current safety status.

[0025] Furthermore, the present invention also discloses a method for collecting muon flux data of a standard structure based on the muon detection network and reconstructing a baseline three-dimensional density image of the utility tunnel and its surrounding soil, including: synchronizing the muon detectors using a synchronization clock unit; controlling the muon detection network to continuously collect muon flux data for a first predetermined time during the stable period of the utility tunnel structure, as a baseline dataset; and processing the baseline dataset using an iterative reconstruction algorithm to generate a baseline three-dimensional density image of the utility tunnel and its surrounding soil.

[0026] Specifically, when using a muon detection network to acquire muon flux data for a standard structure and reconstruct a baseline 3D density image, the first step is to synchronize the time of all muon detectors in the network using a synchronization clock unit. This ensures that the time dimension of the data collected by each detector remains consistent, preventing deviations in subsequent data integration and analysis due to time asynchrony. Then, a stage in the structural stability period of the underground utility tunnel is selected, such as when the tunnel is newly built and not yet operational, or during operation when testing confirms no deformation and a stable structural state. During this period, the muon detection network is controlled to continuously collect muon flux data for a first predetermined time period according to preset parameters. This data, reflecting the density characteristics of the utility tunnel and surrounding soil under stable conditions, serves as the baseline dataset.

[0027] After collecting the baseline dataset, an iterative reconstruction algorithm is used to process it. The algorithm calculates, analyzes, and models the muon flux information in the baseline dataset, gradually constructing a three-dimensional image that clearly shows the spatial density distribution of the underground utility tunnel and its surrounding soil—that is, a baseline three-dimensional density image of the tunnel and its surrounding soil. This image records the original density distribution characteristics of the tunnel and its surrounding soil under stable conditions. It serves as an important reference for subsequent operational monitoring, comparing the image with the three-dimensional density image generated during the monitoring phase to identify density changes and determine whether the tunnel is deformed.

[0028] Furthermore, this invention also discloses an iterative reconstruction algorithm for processing the benchmark dataset to generate a benchmark three-dimensional density image of the underground utility tunnel and its surrounding soil, comprising: Step 1: Discretizing the three-dimensional space to be detected in the underground utility tunnel and its surrounding area into a voxel matrix, and assigning an initial density estimate to each voxel to obtain a voxel density matrix; Step 2: Calculating the expected muon flux theoretically input to each muon detector based on the voxel density matrix; Step 3: Comparing the expected muon flux with the actual measured value of the monitored muon flux data, and calculating the difference residual; Step 4: Back-projecting the difference residual to the three-dimensional voxel space, and combining it with prior information constraints to generate a density correction factor matrix for updating the voxel density matrix; Repeating steps 2 to 4 iteratively until the difference residual is less than a predetermined threshold or reaches a predetermined number of iterations, the resulting voxel density matrix serves as the benchmark three-dimensional density image, used to reflect the monitored three-dimensional density distribution.

[0029] Specifically, an iterative reconstruction algorithm is used to process the benchmark dataset to generate a benchmark 3D density image of the underground utility tunnel and its surrounding soil. Step 1: First, the 3D space to be detected in the underground utility tunnel and its surrounding area is decomposed into numerous uniformly sized cubic units, i.e., voxels. These voxels are arranged in an orderly manner according to their actual positions in 3D space, forming a structured voxel matrix. Simultaneously, based on basic information such as the material properties of the utility tunnel and the common density range of the surrounding soil, an initial density estimate is assigned to each voxel, establishing the initial data framework for iterative calculation. Step 2: Next, using the constructed voxel density matrix as the core basis, and leveraging the physical laws and mathematical models of muon propagation, the expected muon flux that each muon detector should theoretically receive is calculated. Step 3: Subsequently, the obtained expected muon flux is compared point-by-point with the actual muon flux data monitored in the benchmark dataset. By calculating the numerical difference between the two, a residual reflecting the deviation between theory and reality is obtained. This residual will serve as the key basis for subsequent correction of voxel density. Step 4: Then, the calculated difference residuals are back-mapped to the 3D voxel space to clarify the contribution of each voxel to the residuals. Simultaneously, prior information constraints are introduced to ensure that the correction direction conforms to the actual structure and density patterns of the pipe gallery and surrounding soil. Based on this, a density correction factor matrix is ​​generated, where each element corresponds to the density adjustment coefficient of a voxel, used to specifically update the current voxel density matrix. Finally, steps 2 to 4 are repeated. After each update of the voxel density matrix, the expected muon flux and difference residuals are recalculated, and a new correction factor matrix is ​​generated based on the residuals to continue updating until the difference residuals are less than a pre-set threshold or the number of iterations reaches a predetermined upper limit. The resulting voxel density matrix is ​​used as the baseline 3D density image, reflecting the true density distribution of the pipe gallery and surrounding soil. The voxel matrix is ​​a structured data carrier formed by discretizing the 3D space to be detected in the pipe gallery and surrounding area. It consists of a large number of regular cubic voxels arranged according to their spatial positions. It transforms the continuous 3D space into quantifiable discrete units, providing a basic framework for subsequent density calculations and image reconstruction. The initial density estimate is a pre-assigned density value to each voxel in the voxel matrix before the iterative reconstruction begins. This value is determined by basic information such as the known density of the reference tunnel's building materials and the typical density range of the surrounding soil layers. It serves as the starting reference value for iterative calculations, providing an initial basis for subsequent gradual density corrections to approximate the true value. The voxel density matrix records the current density information of each voxel. Initially, it consists of the initial density estimate and is continuously updated during iteration based on the difference residuals and the density correction factor matrix, persisting throughout the entire iterative reconstruction process and ultimately being directly transformed into a baseline 3D density image. The density correction factor matrix is ​​a coefficient matrix generated by combining the difference residuals and prior information constraints, used to adjust the voxel density.Each element in the matrix corresponds to a voxel, and its value and sign depend on the contribution of the voxel to the difference residual and the constraints of prior information. By multiplying or adding the correction factor with the current voxel density, the voxel density is adjusted in a targeted manner, and the voxel density matrix is ​​gradually made closer to the true density distribution.

[0030] Furthermore, the present invention also discloses that the prior information constraints include: the dimensions, spatial location, and material density information of the underground utility tunnel structure.

[0031] Specifically, prior information constraints are known objective information introduced during the iterative reconstruction process to regulate the direction and range of density correction, preventing calculation results from deviating from the actual physical scenario. The dimensions of the utility tunnel structure include the cross-sectional size and length, while its spatial location includes the tunnel's burial depth and its relative position to the surrounding soil.

[0032] Furthermore, the present invention also discloses a method for differentially evaluating the deformation of underground utility tunnels based on the abnormal area, including: establishing a relationship model between density change and deformation; and substituting the density change statistics of the abnormal area into the relationship model to obtain the deformation.

[0033] Specifically, when evaluating the deformation of underground utility tunnels based on differential density changes in anomaly areas, the model first establishes the inherent correlation between density changes and structural deformation in the tunnel and surrounding soil. This is done by combining fundamental information such as the physical properties of the tunnel materials and the mechanical parameters of the surrounding soil. A model of the relationship between density change and deformation is then constructed, and this relationship is quantified to clarify the correspondence between the two. For example, the model determines the magnitude of settlement, displacement, and other deformations that the tunnel may experience under different density variation amplitudes, ensuring that the model accurately reflects the impact of density changes on deformation and providing a theoretical framework for subsequent calculations. The physical properties of the tunnel materials include elastic modulus and compressive strength; the mechanical parameters of the surrounding soil include porosity and compressibility coefficient. After completing the model construction, key statistical information is extracted from the density variation differences in the anomaly area to form density variation statistics, including the average value, maximum variation, and standard deviation of density variation within the anomaly area, which comprehensively reflects the density variation characteristics of the anomaly area. Subsequently, these density change statistics are substituted into the established relational model. Through the model's operational logic, the deformation of the underground utility tunnel corresponding to the abnormal area is calculated, thereby achieving a quantitative assessment of the degree of tunnel deformation and providing core data support for subsequent judgment on whether the tunnel has deformed. The model's operational logic includes formula calculation and data mapping.

[0034] Furthermore, the present invention also discloses a method for spatiotemporal correlation and fusion analysis of the spatial location information of the abnormal region with the monitoring data of the traditional sensor, to conduct a deformation risk assessment of the abnormal region and generate a deformation risk assessment result, including: A spatiotemporal mapping relationship between the anomalous region and adjacent traditional sensor data is established, and a multidimensional risk assessment feature vector is constructed. The multidimensional risk assessment feature vector includes a first feature group from muon imaging and a second feature group from traditional sensors. The first feature group includes the average density change value of the anomalous region, the volume of the anomalous region, and the shortest distance between the centroid of the anomalous region and the outer wall of the pipe gallery. The second feature group includes the maximum micro-strain value and change rate of strain sensors within a set range around the anomalous region, the cumulative settlement amount and settlement rate of settlement sensors, and the crack width increment of crack sensors. The multidimensional risk assessment feature vector is input into a risk assessment model to obtain the deformation risk assessment result of the anomalous region. The risk assessment model is a gradient boosting decision tree model that learns and converges through a training sample set. It is used to perform fusion identification and analysis based on the input feature vectors of muon imaging and traditional sensors, and output the corresponding deformation risk assessment value.

[0035] Specifically, when performing spatiotemporal correlation and fusion analysis between the spatial location information of anomaly areas and traditional sensor monitoring data to complete the deformation risk assessment of anomaly areas and generate results, it is necessary to first establish the spatiotemporal mapping relationship between the anomaly area and the adjacent traditional sensor data, clarify the adjacent traditional sensors corresponding to the anomaly area in space, and ensure that the correlated data is sensor data that is completely consistent with the monitoring period of the anomaly area, so as to avoid data mismatch due to spatiotemporal misalignment, and lay an accurate spatiotemporal correspondence foundation for subsequent analysis.

[0036] Based on this, a multi-dimensional risk assessment feature vector is constructed. This vector contains a first feature group from muon imaging and a second feature group from traditional sensors. By combining these two feature groups, the density and structural deformation information of the anomalous area can be comprehensively covered. Specifically, the average density change value of the anomalous area reflects the overall density fluctuation of the area; the volume of the anomalous area reflects the size of the anomalous range; the shortest distance between the centroid of the anomalous area and the outer wall of the utility tunnel is used to determine the degree of direct impact of the anomalous area on the utility tunnel; the maximum micro-strain value and rate of change of strain sensors within a set range around the anomalous area are used to monitor the stress and deformation of the utility tunnel structure; the cumulative settlement and settlement rate of settlement sensors are used to analyze the vertical displacement changes of the utility tunnel; and the crack width increment of crack sensors is used to analyze whether the utility tunnel structure has cracked and whether there is a tendency for cracking.

[0037] Finally, the constructed multidimensional risk assessment feature vector is input into the risk assessment model to obtain the deformation risk assessment results for the abnormal area. The risk assessment model is a gradient boosting decision tree model that learns convergence from a training sample set. It can fuse and analyze the input muon imaging features with traditional sensor features, and combine the deformation risk judgment logic learned during training to comprehensively assess the deformation risk of the abnormal area, ultimately outputting the corresponding deformation risk assessment value for the abnormal area. The deformation risk assessment result for the abnormal area is a comprehensive judgment conclusion regarding whether the abnormal area will cause deformation of the utility tunnel and the level of deformation risk, derived through spatiotemporal correlation, feature vector construction, and model analysis. It is directly used to determine whether to generate deformation warning information or routine feedback results, and is the core basis for assessing the deformation risk of the utility tunnel. The deformation risk assessment value is the specific numerical value output by the risk assessment model after analyzing the multidimensional risk assessment feature vector. It quantitatively reflects the possibility and severity of deformation of the utility tunnel caused by the abnormal area; for example, a higher value indicates a greater deformation risk, and it is a key quantitative indicator constituting the deformation risk assessment result for the abnormal area.

[0038] This invention discloses a method for monitoring the deformation of underground utility tunnels using muon imaging. The method includes: deploying multiple muon detectors along the extension direction of the underground utility tunnel to form a muon detection network; collecting muon flux data of a standard structure based on the muon detection network and reconstructing a baseline three-dimensional density image of the utility tunnel and its surrounding soil; acquiring data collected by the muon detection network during the operational monitoring cycle and reconstructing a monitoring three-dimensional density image; performing differential calculations between the monitoring three-dimensional density image and the baseline three-dimensional density image to generate a density change differential image, and using a preset density change threshold to traverse and identify abnormal areas; evaluating the deformation of the underground utility tunnel based on the differential values ​​of the abnormal areas, determining whether deformation has occurred, and sending deformation feedback results. This invention solves the technical problems in existing technologies where traditional sensors for monitoring utility tunnels have limited range and are susceptible to electromagnetic interference, and conventional non-destructive testing is limited by geological conditions, resulting in blind spots and difficulty in continuous monitoring. These problems lead to incomplete coverage, low data accuracy, and difficulty in achieving continuous monitoring. The invention achieves full-area monitoring of the utility tunnel and its surrounding soil, avoids electromagnetic interference and geological blind spots, improves data accuracy, and enables continuous monitoring.

[0039] Based on the same inventive concept as the aforementioned method for monitoring underground utility tunnel deformation using muon imaging, this invention also provides a system for monitoring underground utility tunnel deformation using muon imaging, such as... Figure 2 As shown, the system includes: Muon detection network deployment module 11 is used to deploy multiple muon detectors along the extension direction of the underground utility tunnel to form a muon detection network. The reference three-dimensional density image reconstruction module 12 is used to collect muon flux data of the standard structure based on the muon detection network and reconstruct the reference three-dimensional density image of the pipe gallery and its surrounding soil. The monitoring three-dimensional density image acquisition module 13 is used to acquire the muon detection network data collected during the operation monitoring cycle and reconstruct the monitoring three-dimensional density image; The abnormal region identification module 14 is used to perform differential calculation between the monitored three-dimensional density image and the reference three-dimensional density image to generate a density change differential image, and to traverse and identify abnormal regions using a preset density change threshold. The deformation evaluation and feedback module 15 is used to evaluate the deformation of the underground utility tunnel based on the differential evaluation of the abnormal area, determine whether the underground utility tunnel has deformed, and send the deformation feedback result.

[0040] Furthermore, the present invention also discloses a method for evaluating the deformation of underground utility tunnels based on the differential assessment of the abnormal areas, determining whether the underground utility tunnels have deformed, and sending deformation feedback results, including: The system acquires monitoring data from conventional sensors deployed within the underground utility tunnel during the same time period. These conventional sensors include one or more of strain sensors, settlement sensors, and crack sensors. It then performs spatiotemporal correlation and fusion analysis between the spatial location information of the abnormal area and the monitoring data from the conventional sensors to conduct a deformation risk assessment of the abnormal area, generating a deformation risk assessment result. When the deformation risk assessment result indicates deformation, a deformation early warning message is generated based on the deformation amount and the spatial location of the abnormal area. When the deformation risk assessment result indicates no deformation, the monitoring data and the no-deformation conclusion are used to generate the deformation feedback result.

[0041] Furthermore, this invention also discloses a method for acquiring muon flux data of a standard structure based on the muon detection network, and reconstructing a baseline three-dimensional density image of the pipe gallery and its surrounding soil, including: The muon detectors are synchronized by a synchronous clock unit. During the stable period of the utility tunnel structure, the muon detection network is controlled to continuously collect muon flux data for a first predetermined time as a reference dataset. The reference dataset is then processed by an iterative reconstruction algorithm to generate a reference three-dimensional density image of the utility tunnel and its surrounding soil.

[0042] Furthermore, the present invention also discloses a method for processing the benchmark dataset using an iterative reconstruction algorithm to generate a benchmark three-dimensional density image of the utility tunnel and its surrounding soil, including: Step 1: Discretize the underground utility tunnel and surrounding 3D space to be detected into a voxel matrix, and assign an initial density estimate to each voxel to obtain a voxel density matrix; Step 2: Based on the voxel density matrix, calculate the theoretically expected muon flux for each muon detector; Step 3: Compare the expected muon flux with the actual measured values ​​of the monitored muon flux data, and calculate the difference residual; Step 4: Back-project the difference residual onto the 3D voxel space, and combine it with prior information constraints to generate a density correction factor matrix, which is used to update the voxel density matrix; Repeat steps 2 to 4 iteratively until the difference residual is less than a predetermined threshold or a predetermined number of iterations is reached. The resulting voxel density matrix serves as the baseline 3D density image, used to reflect the monitored 3D density distribution.

[0043] Furthermore, the present invention also discloses that the prior information constraints include: the dimensions, spatial location, and material density information of the underground utility tunnel structure.

[0044] Furthermore, the present invention also discloses a method for differentially evaluating the deformation of underground utility tunnels based on the abnormal regions, including: Establish a relationship model between density change and deformation; substitute the density change statistics of the abnormal region into the relationship model to obtain the deformation.

[0045] Furthermore, the present invention also discloses a method for spatiotemporal correlation and fusion analysis of the spatial location information of the abnormal region and the monitoring data of the traditional sensor, to conduct a deformation risk assessment of the abnormal region and generate a deformation risk assessment result, including: A spatiotemporal mapping relationship between the anomalous region and adjacent traditional sensor data is established, and a multidimensional risk assessment feature vector is constructed. The multidimensional risk assessment feature vector includes a first feature group from muon imaging and a second feature group from traditional sensors. The first feature group includes the average density change value of the anomalous region, the volume of the anomalous region, and the shortest distance between the centroid of the anomalous region and the outer wall of the pipe gallery. The second feature group includes the maximum micro-strain value and change rate of strain sensors within a set range around the anomalous region, the cumulative settlement amount and settlement rate of settlement sensors, and the crack width increment of crack sensors. The multidimensional risk assessment feature vector is input into a risk assessment model to obtain the deformation risk assessment result of the anomalous region. The risk assessment model is a gradient boosting decision tree model that learns and converges through a training sample set. It is used to perform fusion identification and analysis based on the input feature vectors of muon imaging and traditional sensors, and output the corresponding deformation risk assessment value.

[0046] This manual uses a progressive approach, focusing on the differences from other parts. The foregoing... Figure 1The method and specific details of underground utility tunnel deformation monitoring combined with muon imaging are also applicable to the underground utility tunnel deformation monitoring system combined with muon imaging described in this section. Through the foregoing detailed description of the underground utility tunnel deformation monitoring method combined with muon imaging, those skilled in the art can clearly understand the underground utility tunnel deformation monitoring system combined with muon imaging; therefore, for the sake of brevity, it will not be described in detail here. For the disclosed system, since it corresponds to the disclosed method, the description is relatively simple; relevant details can be found in the method section.

[0047] Based on the foregoing, the present invention also discloses a computer-readable storage medium storing a computer program, which, when executed by a processor, enables the implementation of the underground utility tunnel deformation monitoring method combined with muon imaging as described above.

[0048] Although this invention makes various references to certain modules of the system according to the invention, any number of different modules can be used and run on user terminals and / or servers. The various modules included are only divided according to functional logic, but are not limited to the above division. As long as the corresponding functions can be achieved, they are acceptable and are not intended to limit the scope of protection of this invention.

[0049] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0050] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of this invention and its equivalents, this invention also intends to include these modifications and variations.

Claims

1. A method for monitoring the deformation of underground utility tunnels using muon imaging, characterized in that, include: Multiple muon detectors are deployed along the extended direction of the underground utility tunnel to form a muon detection network. Based on the muon detection network, muon flux data of the standard structure are collected, and a baseline three-dimensional density image of the pipe gallery and its surrounding soil is reconstructed. Acquire muon detection network data during the operational monitoring cycle and reconstruct the monitoring three-dimensional density image; The monitored three-dimensional density image and the reference three-dimensional density image are differentially calculated to generate a density change difference image, and an abnormal region is identified by traversing through the data using a preset density change threshold. The deformation of the underground utility tunnel is evaluated based on the differential assessment of the abnormal area to determine whether the underground utility tunnel has deformed, and the deformation feedback result is sent.

2. The method for monitoring underground utility tunnel deformation using muon imaging as described in claim 1, characterized in that, Based on the differential evaluation of the abnormal area, the deformation of the underground utility tunnel is assessed to determine whether deformation has occurred, and deformation feedback results are sent, including: Acquire monitoring data from conventional sensors deployed within the underground utility tunnel during the same time period, wherein the conventional sensors include one or more of strain sensors, settlement sensors, and crack sensors; The spatial location information of the abnormal area is spatiotemporally correlated and fused with the monitoring data of the traditional sensor to conduct a deformation risk assessment of the abnormal area and generate a deformation risk assessment result. When the deformation risk assessment result indicates that deformation has occurred, deformation early warning information is generated based on the deformation amount and spatial location of abnormal areas. When the deformation risk assessment result is that no deformation has occurred, the monitoring data and the conclusion of no deformation will be used to generate the deformation feedback result.

3. The method for monitoring underground utility tunnel deformation using muon imaging as described in claim 2, characterized in that, Based on the muon detection network, muon flux data of the standard structure are collected, and a baseline three-dimensional density image of the utility tunnel and its surrounding soil is reconstructed, including: The muon detector is synchronized by a synchronization clock unit. During the stable period of the tube gallery structure, the muon detection network is controlled to continuously collect muon flux data for a first predetermined time as a reference dataset. The benchmark dataset is processed using an iterative reconstruction algorithm to generate a benchmark three-dimensional density image of the utility tunnel and its surrounding soil.

4. The method for monitoring underground utility tunnel deformation using muon imaging as described in claim 3, characterized in that, The benchmark dataset is processed using an iterative reconstruction algorithm to generate a benchmark three-dimensional density image of the utility tunnel and its surrounding soil, including: Step 1: Discretize the underground utility tunnel and the surrounding three-dimensional space to be explored into a voxel matrix, and assign an initial density estimate to each voxel to obtain the voxel density matrix; Step 2: Based on the voxel density matrix, calculate the theoretically expected muon flux input to each muon detector; Step 3: Compare the expected muon flux with the actual measured values ​​of the monitored muon flux data, and calculate the difference residual; Step 4: Back-project the difference residuals to the three-dimensional voxel space, and combine them with prior information constraints to generate a density correction factor matrix, which is used to update the voxel density matrix; Steps 2 to 4 are repeated iteratively until the difference residual is less than a predetermined threshold or the predetermined number of iterations is reached. The resulting voxel density matrix is ​​used as the reference three-dimensional density image to reflect the monitoring of the three-dimensional density distribution.

5. The method for monitoring underground utility tunnel deformation using muon imaging as described in claim 4, characterized in that, The prior information constraints include: the dimensions, spatial location, and material density information of the underground utility tunnel structure.

6. The method for monitoring underground utility tunnel deformation using muon imaging as described in claim 1, characterized in that, The deformation of the underground utility tunnel is evaluated based on the differential assessment of the abnormal area, including: Establish a model relating density change to deformation. Substituting the density change statistics of the abnormal region into the relational model, the deformation amount is obtained.

7. The method for monitoring underground utility tunnel deformation using muon imaging as described in claim 2, characterized in that, The spatial location information of the abnormal area is spatiotemporally correlated and fused with the monitoring data of the traditional sensor to perform deformation risk assessment on the abnormal area, generating deformation risk assessment results, including: A spatiotemporal mapping relationship between the anomalous area and adjacent traditional sensor data is established, and a multidimensional risk assessment feature vector is constructed. The multidimensional risk assessment feature vector includes a first feature group from muon imaging and a second feature group from traditional sensors. The first feature group includes the average density change value of the anomalous area, the volume of the anomalous area, and the shortest distance between the centroid of the anomalous area and the outer wall of the pipe gallery. The second feature group includes the maximum micro-strain value and change rate of the strain sensor within a set range around the anomalous area, the cumulative settlement amount and settlement rate of the settlement sensor, and the crack width increment of the crack sensor. The multidimensional risk assessment feature vector is input into the risk assessment model to obtain the deformation risk assessment result of the abnormal region. The risk assessment model is a gradient boosting decision tree model that learns and converges through a training sample set. It is used to perform fusion identification and analysis based on the feature vectors of input muon imaging and traditional sensors, and output the corresponding deformation risk assessment value.

8. A deformation monitoring system for underground utility tunnels combined with muon imaging, characterized in that, For performing the underground utility tunnel deformation monitoring method combining muon imaging as described in any one of claims 1 to 7, the system comprises: The muon detection network deployment module is used to deploy multiple muon detectors along the extension direction of the underground utility tunnel to form a muon detection network. The benchmark three-dimensional density image reconstruction module is used to collect muon flux data of the standard structure based on the muon detection network and reconstruct the benchmark three-dimensional density image of the pipe gallery and its surrounding soil. The monitoring three-dimensional density image acquisition module is used to acquire data collected by the muon detection network during the operation monitoring cycle and reconstruct the monitoring three-dimensional density image; An abnormal region identification module is used to perform differential calculation between the monitored three-dimensional density image and the reference three-dimensional density image to generate a density change differential image, and to traverse and identify abnormal regions using a preset density change threshold. The deformation evaluation and feedback module is used to evaluate the deformation of the underground utility tunnel based on the differential evaluation of the abnormal area, determine whether the underground utility tunnel has deformed, and send the deformation feedback result.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by the processor, the program implements the underground utility tunnel deformation monitoring method incorporating muon imaging as described in any one of claims 1 to 7.

Images