Weak current pipeline settlement monitoring system based on multi-source data fusion

Abstract

The invention provides a weak current pipeline settlement monitoring system based on multi-source data fusion. The system comprises a ground sensor array which comprises a plurality of fiber bragg grating static level gauges, a strain sensing optical cable and a plurality of MEMS triaxial accelerometers and is used for collecting horizontal displacement, deformation stress and vertical settlement in sequence; the satellite remote sensing module comprises a synthetic aperture radar module and a GNSS module and is sequentially used for acquiring earth surface deformation data and elevation data of a monitoring area; and the data analysis platform is used for carrying out feature extraction on the data acquired by the ground sensor array, carrying out multi-source data fusion on the extracted features and the satellite remote sensing data acquired by the satellite remote sensing module by adopting a multi-source data fusion algorithm, and carrying out settlement monitoring and early warning based on a fusion result. According to the scheme, the problems that traditional single monitoring precision is insufficient and response lags are solved, the pipeline settlement early warning reliability can be remarkably improved, and the pipeline breakage risk is effectively prevented.

Description

Technical Field

[0001] The present application relates to a weak current pipeline settlement monitoring system based on multi-source data fusion, belonging to the technical field of building engineering safety monitoring. Background Art

[0002] In the application scenario of the weak current pipeline inlet section of a building, the mechanical stress borne by the optical cable often exceeds the limit due to foundation settlement, resulting in cable fracture. Therefore, it is necessary to monitor the pipeline settlement situation in order to detect abnormal conditions in a timely manner.

[0003] Traditional monitoring means, such as level instruments, total stations, etc., rely on manual operation and cannot achieve continuous monitoring for 24 hours a day, and the monitoring efficiency is relatively low. When only using the fiber optic sensing monitoring method, a conventional fiber Bragg grating system can only support a limited number of monitoring points, making it difficult to meet the requirements for the number of monitoring points of an ultra-long pipeline. When using satellite monitoring means, taking the InSAR technology as an example, although large-scale deformation data can be obtained, due to the lack of verification of ground measured data, the false alarm rate is relatively high. Summary of the Invention

[0004] The present application provides a foundation settlement monitoring device for building engineering, aiming to solve the problems of single existing settlement monitoring technology, insufficient accuracy, and response lag.

[0005] In a first aspect, an embodiment of the present application provides a weak current pipeline settlement monitoring system based on multi-source data fusion, including: A ground sensor array, including a plurality of fiber Bragg grating static level instruments, strain sensing optical cables, and a plurality of MEMS triaxial accelerometers, which are used to collect horizontal displacement, deformation stress, and vertical settlement amount in sequence; A satellite remote sensing module, including a synthetic aperture radar module and a GNSS module, which are used to obtain surface deformation data and elevation data of the monitoring area in sequence; A data analysis platform, which is used to extract features from the data collected by the ground sensor array, perform multi-source data fusion on the extracted features and the satellite remote sensing data obtained by the satellite remote sensing module using a multi-source data fusion algorithm, and perform settlement monitoring and early warning based on the fusion result; Wherein, the ground sensor array is distributed in a three-dimensional grid shape along the weak current pipeline inlet, is buried in multiple different depths below the ground surface in a vertical direction in layers, and is arranged in a radiation pattern outward from the pipeline inlet in a horizontal direction within a set range, and a group of sensor nodes is set at every set distance; The synthetic aperture radar module periodically obtains surface deformation data of the monitoring area and generates a settlement rate map through differential interferometry; the GNSS module obtains elevation data of the monitoring area in real time; The data analysis platform includes edge computing nodes, cloud servers, and warning terminals. The edge computing nodes are deployed at the monitoring site, equipped with lightweight LSTM models, and are used to process the data collected by the ground sensor array in real time and extract settlement features. The cloud server obtains satellite remote sensing data, constructs a spatio-temporal unified coordinate system, and uses a weighted Kalman filtering algorithm for multi-source data fitting to generate a comprehensive settlement risk map. The warning terminal stores risk thresholds for different pipeline materials. When it is determined based on the comprehensive settlement risk map and the risk threshold that the settlement amount meets the set warning conditions, an alarm is automatically triggered and the location information of the warning area is sent to the operation and maintenance personnel.

[0006] Based on the above system, optionally, the fiber Bragg grating static level uses a temperature compensation structure, with a PT-100 platinum resistance built-in, and eliminates the interference of ambient temperature on settlement measurement through a dual-parameter demodulation algorithm.

[0007] Based on the above system, optionally, the installation structure of the ground sensor array includes: The fiber Bragg grating static level and the strain sensing optical cable are installed using a thorn-type settlement pipe. The outer side of the settlement pipe body is provided with a barbed structure to enhance the coupling with the soil. Each settlement pipe is 1.5 meters long and is connected through a flange to form a continuous monitoring network. An optical fiber Bragg grating sensor string is embedded in the pipe body, and a monitoring point is set every 0.3 meters to cover the full-depth deformation monitoring. The MEMS triaxial accelerometer module arranges multiple monitoring nodes at preset intervals along the axial direction of the pipeline. Each monitoring node includes a sealed and protected MEMS triaxial accelerometer, a temperature compensation unit, and a wireless transmission module. The accelerometer is vertically fixed above the pipeline.

[0008] Based on the above system, optionally, the monitoring period of the synthetic aperture radar module is 7 days. After the data analysis platform updates the comprehensive settlement map, it automatically compares it with the historical comprehensive settlement map, identifies abnormal deformation areas, and marks them as high-risk areas.

[0009] Based on the above system, optionally, in the satellite remote sensing module, the GNSS module arranges at least one reference station and multiple monitoring stations within the monitoring area to form an observation network. Each station is equipped with a multi-frequency GNSS receiver and an anti-multipath antenna. The monitoring stations are arranged in a mesh pattern along the direction of the weak current pipeline entering the building.

[0010] Based on the above system, optionally, the data analysis platform integrates a BIM model, overlays the monitoring data with the building structure model, and supports three-dimensional visual simulation of settlement trends and pipeline stress simulation analysis.

[0011] Based on the above system, optionally, the cloud server constructs a spatio-temporal unified coordinate system and establishes a conversion model between the WGS84 coordinate system and the local coordinate system:

[0012] In the formula, is the rotation matrix, obtained by solving the baseline vectors of 3 GNSS reference stations, and T is the translation vector, determined by measuring ground control points; 、 and are the three-dimensional coordinates in the local coordinate system, 、 and are the three-dimensional coordinates in the WGS84 coordinate system.

[0013] Based on the above system, optionally, the multi-source data fusion algorithm includes: (1)Construct the state equation

[0014] In the formula, represents the state vector, used to describe the state of the system at time , is the vertical settlement amount, with the unit of mm; is the axial strain of the pipeline, with the unit of ; is the vertical acceleration, with the unit of g; is the satellite-inverted settlement rate, with the unit of mm / month;

[0015] In the formula, represents the observation vector, characterizing the original signal measured by the sensor, which needs to be associated with the state vector through conversion, is the optical fiber wavelength offset, with the unit of pm; is the phase difference of the strain optical cable, with the unit of rad; is the second derivative of the vertical component of the MEMS triaxial accelerometer, with the unit ; is the InSAR interference phase, with the unit of rad; (2)Weight adaptive allocation Calculate the confidence of satellite data:

[0016] In the formula, is the satellite measurement error, with a typical value of 1.2 mm; ​​is the comprehensive error of ground sensors, 0.05mm for the fiber Bragg grating static level and 0.1mm for the MEMS triaxial accelerometer; is the satellite data weight, taking the upper limit when the signal-to-noise ratio > 15dB; is the sensor weight, when the temperature gradient is, force ; (2)Weighted Kalman filter iteration: Prediction stage, calculated according to the following formula:

[0017]

[0018] In the formula, represents the predicted state vector at the th moment; represents the state transition matrix; represents the predicted state vector at the th moment; represents the control input matrix; represents the external control vector; represents the predicted error covariance matrix at the th moment; represents the error covariance matrix at the th moment; represents the transpose matrix of the state transition matrix; represents the process noise matrix, dynamically adjusted according to the pipeline burial depth; Update stage, calculated according to the following formula:

[0019]

[0020]

[0021] In the formula, represents the Kalman gain matrix at the th moment; represents the observation matrix, including the geometric relationship parameters of the sensors and the satellite; represents the transpose matrix of the observation matrix; represents the satellite data weight; represents the ground sensor weight, =1 - ; represents the satellite observation noise covariance matrix; represents the ground sensor observation noise covariance matrix; Denote the state vector updated at the th moment; Denote the observation vector at the th moment; Denote the observed value corresponding to the predicted state, and the difference from the measured value is used as the basis for update; Denote the error covariance matrix updated at the th moment; I represents the identity matrix.

[0022] Based on the above system, optionally, the calculation formula for the risk threshold is:

[0023] In the formula, is the basic threshold, 2.5 mm / month for PVC pipes and 3.5 mm / month for steel pipes; = 0.05 / m, is the burial depth correction coefficient, and d is the burial depth; is the material coefficient, 0 for PVC pipes and 0.2 for steel pipes.

[0024] The weak current pipeline settlement monitoring system based on multi-source data fusion provided by this application has the following beneficial effects: 1. This application adopts a three-dimensional grid layout of vertical stratification combined with horizontal radiation for sensor layout, combined with synchronous monitoring of different depths, to accurately capture the compression deformation characteristics of soil in different depth layers. The strain sensing optical cable is closely attached along the weak current pipeline route, breaking through the limitations of traditional discrete point monitoring, and realizing continuous linear stress distribution measurement. Improve the comprehensiveness and accuracy of monitoring.

[0025] 2. This application uses multi-source data fusion technology to fuse the high-precision real-time data provided by the ground sensor array with the large-scale macroscopic deformation covered by satellite remote sensing, improving the reliability of monitoring.

[0026] 3. This application sets up an early warning mechanism. When the settlement risk threshold is exceeded, it will remind the operation and maintenance personnel. After receiving the alarm information, the operation and maintenance personnel can take corresponding measures (such as starting the backup optical cable route) to minimize the impact caused by pipeline settlement. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The drawings here are incorporated into the specification and constitute a part of this specification, showing embodiments consistent with this application, and are used together with the specification to explain the principles of this application. In addition, these drawings and text descriptions are not intended to limit the scope of the concept of this application in any way, but to illustrate the concept of this application to those skilled in the art by referring to specific embodiments.

[0028] Figure 1 It is a schematic structural diagram of a weak current pipeline settlement monitoring system based on multi-source data fusion provided by an embodiment of this application; Figure 2 Schematic diagram of the installation structure of the fiber Bragg grating static level and the strain sensing optical cable provided by an embodiment of the present application; Figure 3 Schematic diagram of the installation structure of the MEMS triaxial accelerometer provided by an embodiment of the present application; Figure 4 Schematic diagram of the ground station layout of the GNSS module provided by an embodiment of the present application. Detailed implementation manners

[0029] To make the objectives, technical solutions and advantages of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application. Without conflict, the following embodiments and the features in the embodiments may be combined with each other.

[0030] The embodiment of the present invention provides a weak current pipeline settlement monitoring system based on multi-source data fusion, aiming to solve the problems of single existing settlement monitoring technology, insufficient accuracy and lagging response. This system can significantly improve the reliability of pipeline settlement early warning, effectively prevent the risk of pipeline fracture, ensure the stability of the campus network, and guarantee the smooth development of higher education teaching.

[0031] Referring to Figure 1 , a weak current pipeline settlement monitoring system based on multi-source data fusion provided by the embodiment of the present invention. This system mainly includes: a ground sensor array, a satellite remote sensing module and a data analysis platform.

[0032] Among them, the ground sensor array includes a plurality of fiber Bragg grating (Weak - reflection Fiber Bragg Grating, WFBG) static level meters, strain sensing optical cables and a plurality of MEMS (Micro-Electro-Mechanical System) triaxial accelerometers, which are used to collect horizontal displacement, deformation stress and vertical settlement amount in sequence.

[0033] The satellite remote sensing module includes a synthetic aperture radar (SAR) module and a GNSS (Global Navigation Satellite System) module, which are used to obtain surface deformation data and elevation data of the monitoring area in sequence.

[0034] A data analysis platform is used to extract features from the data collected by the ground sensor array, and a multi-source data fusion algorithm is adopted to perform multi-source data fusion on the extracted features and the satellite remote sensing data obtained by the satellite remote sensing module, and settlement monitoring and early warning are carried out based on the fusion result.

[0035] Among them, as Figures 2-4 shown, the ground sensor array is distributed in a three-dimensional grid shape along the entrance of the weak current pipeline into the building, and is buried vertically in multiple different depths (such as 0.5m, 1m, 1.5m) below the ground surface. Horizontally, with the entrance of the pipeline into the building as the center, it is radiated and arranged within a set range (such as a radius of 10 meters), and a group of sensor nodes is set at every set distance (such as 2m).

[0036] In some embodiments, the strain sensing optical cable is laid along the pipeline direction, and a monitoring point (a strain sensor is set at the monitoring point) is set at every certain distance (such as 1m), which is used to capture horizontal displacement and deformation stress. In addition, the MEMS triaxial accelerometer module is arranged along the section of the weak current pipeline entering the building at intervals of 5-8 meters, which is used to capture the vertical settlement amount.

[0037] Furthermore, in some embodiments, the installation structure of the ground sensor array includes: The fiber Bragg grating hydrostatic level is installed with the strain sensing optical cable by using a barbed settlement pipe. The outer side of the settlement pipe body is provided with a barbed structure to enhance the coupling with the soil; the length of each settlement pipe is 1.5 meters, and a continuous monitoring network is formed by connecting through flange plates; a string of fiber Bragg grating sensors is embedded in the pipe body, and a monitoring point is set at every interval of 0.3 meters to cover the full-depth deformation monitoring.

[0038] The MEMS triaxial accelerometer module arranges a plurality of monitoring nodes along the pipeline axis at a preset interval. Each monitoring node includes a sealed and protected MEMS triaxial accelerometer, a temperature compensation unit and a wireless transmission module; the accelerometer is vertically fixed above the pipeline.

[0039] In some embodiments, the fiber Bragg grating hydrostatic level adopts a temperature compensation structure, and a PT-100 platinum resistance is built in, and the interference of environmental temperature on settlement measurement is eliminated through a dual-parameter demodulation algorithm.

[0040] The synthetic aperture radar module periodically obtains the surface deformation data of the monitoring area, and generates a settlement rate map through differential interferometric synthetic aperture radar (D-InSAR) technology. In some embodiments, a satellite carrying a synthetic aperture radar periodically obtains the surface deformation data of the monitoring area, and generates a settlement rate map through differential interferometric synthetic aperture radar technology, and the spatial resolution is better than 5 millimeters.

[0041] The GNSS module obtains elevation data of the monitoring area in real time. Specifically, the GNSS module includes a GNSS reference network, which can obtain elevation data of a large area in real time. In some embodiments, within the monitoring area, at least one reference station and multiple monitoring stations are arranged to form an observation network, and each station is equipped with a multi-frequency GNSS receiver and an anti-multipath antenna; the monitoring stations are arranged in a mesh pattern along the direction of the weak current pipeline into the building.

[0042] The data analysis platform includes an edge computing node, a cloud server, and an early warning terminal.

[0043] The edge computing node is deployed at the monitoring site and is equipped with a lightweight LSTM model (with 32 hidden layer neurons), which processes the data collected by the ground sensor array in real time and extracts settlement features. Since the edge computing node is deployed at the monitoring site, the processing efficiency can be improved, and at the same time, the amount of data transmitted to the cloud server can be reduced.

[0044] The cloud server obtains satellite remote sensing data, constructs a spatio-temporal unified coordinate system, and uses the weighted Kalman filtering algorithm for multi-source data fitting to generate a comprehensive settlement risk map.

[0045] The early warning terminal stores risk thresholds for different pipeline materials. When it is determined based on the comprehensive settlement risk map and the risk threshold that the settlement amount meets the set early warning conditions, an alarm is automatically triggered and the positioning information of the early warning area is sent to the operation and maintenance personnel.

[0046] In some embodiments, the monitoring period of the synthetic aperture radar module is 7 days; after the data analysis platform updates the comprehensive settlement map, it automatically compares it with the historical comprehensive settlement map, identifies the abnormal deformation area and marks it as a high-risk area. In this way, it is convenient for subsequent viewing.

[0047] In some embodiments, the data analysis platform integrates a BIM (Building Information Modeling) model, superimposes the monitoring data on the building structure model for display, and supports three-dimensional visualization of settlement trend simulation and pipeline stress simulation analysis.

[0048] In some embodiments, the cloud server constructs a spatio-temporal unified coordinate system and establishes a conversion model between the WGS84 coordinate system (earth-centered coordinate system) and the local coordinate system:

[0049] In the formula, is the rotation matrix, which is calculated by solving the baseline vectors of three GNSS reference stations. It is used to describe the rotation relationship between the two coordinate systems and eliminate the effects of earth curvature, azimuth deviation, etc.; T is the translation vector, which is determined by measuring ground control points (measured points with known precise coordinates) and is used to adjust the origin offset of the coordinate system to ensure absolute matching of spatial positions; 、 and is the three-dimensional coordinate in the local coordinate system, 、 and It is the three-dimensional coordinate in the WGS84 coordinate system.

[0050] Obtaining the rotation matrix R: Utilize at least three GNSS reference stations (arranged in a triangulated network) to calculate the coordinates of each station in the WGS84 coordinate system by receiving satellite signals. Then, based on the baseline vectors (vector direction and length) between the stations, calculate the coordinate system rotation parameters to ensure that the coordinate axis direction of the local coordinate system is consistent with the actual geographic orientation (such as true north).

[0051] Determination of translation vector T: Several ground control points (such as fixed building corners and measurement landmarks) are selected within the monitoring area. Their local coordinate system coordinates are measured using a total station or other equipment, and the WGS84 coordinates measured by GNSS are simultaneously obtained. The offset between the two sets of coordinates is calculated using the least squares method to obtain the translation vector T.

[0052] By accurately calculating the rotation matrix and translation vector, the spatial position of sensor data (such as fiber Bragg grating settlement and strain values) and satellite images (InSAR settlement rate maps and GNSS elevation data) can be unified. The error can be controlled at the millimeter level, providing a reliable spatial reference for the subsequent weighted Kalman filter algorithm.

[0053] In addition, after unifying the coordinate system, the monitoring data can be superimposed on the BIM model to intuitively display the settlement trend in three-dimensional space (such as the spatial distribution of pipeline vertical settlement and horizontal displacement), and predict the pipeline deformation risk through stress simulation analysis, assisting operation and maintenance personnel to quickly locate high-risk areas.

[0054] In some embodiments, the multi-source data fusion algorithm includes: (1) Constructing the equation of state

[0055] In the formula, Represents the state vector, which is used to describe the system at time Status; is the vertical settlement, with the unit of mm, reflecting the vertical deformation of the soil or pipeline; is the axial strain of the pipeline, with the unit of , used to monitor the tensile or compressive stress generated by the settlement of the pipeline; is the vertical acceleration, with the unit of g, which can be converted into settlement velocity or displacement through integration; is the satellite-inverted settlement rate, with the unit of mm / month, providing the macroscopic trend of large-scale surface deformation.

[0056]

[0057] In the formula, represents the observation vector, characterizing the original signal measured by the sensor, which needs to be associated with the state vector through conversion; is the optical fiber wavelength offset, with the unit of pm. According to the fiber Bragg grating principle, the wavelength offset has a linear relationship with the settlement; is the phase difference of the strain optical cable, with the unit of rad, used to calculate the distribution of the axial strain of the pipeline; is the second derivative of the vertical component of the MEMS triaxial accelerometer, with the unit , reflecting the change rate of the settlement acceleration; is the InSAR interference phase, with the unit of rad, which can be converted into the surface deformation displacement through phase unwrapping; (2) Weight adaptive allocation Calculate the confidence of satellite data:

[0058] In the formula, is the satellite measurement error, with a typical value of 1.2 mm, affected by factors such as atmospheric delay and radar resolution; is the comprehensive error of ground sensors. For the fiber optic grating static level, it is 0.05 mm, and for the MEMS triaxial accelerometer, it is 0.1 mm, reflecting the accuracy of local single-point monitoring; is the weight of satellite data, taking the upper limit when the signal-to-noise ratio > 15 dB; is the weight of the sensor. When the temperature gradient , force .

[0059] Among them, the weight logic is: When the satellite data error is smaller, The larger it is (with an upper limit of 0.8), the higher the credibility of the satellite data; Conversely, when the ground sensor error is smaller or the temperature gradient forces the sensor weight = 1 - = 0.9, reducing the impact of satellite data (to avoid misjudgment caused by temperature interference).

[0060] (2) Weighted Kalman filter iteration: 1. Prediction stage, calculated according to the following formula: 1.1 State prediction formula:

[0061] In the formula, : The predicted state vector at the th moment (including predicted values of parameters such as settlement and strain); : The state transition matrix, describing the variation law of the system state over time (such as the time transfer relationship of the settlement rate); : The predicted state vector at the th moment; : The control input matrix (if there is no external control in the system, this value can be regarded as 0); : The external control vector (usually 0, representing no active intervention).

[0062] 1.2 Error covariance prediction formula:

[0063] In the formula, : The predicted error covariance matrix at the th moment, measuring the uncertainty of the predicted state; : The error covariance matrix at the th moment; : The transpose matrix of the state transition matrix; : The process noise matrix, dynamically adjusted according to the pipeline burial depth (the greater the burial depth, the more complex the soil disturbance, and the higher the noise weight), reflecting the uncertainty in the system dynamic process.

[0064] 2. Update stage, calculated according to the following formula: 2.1 Kalman gain calculation formula:

[0065] In the formula, : The Kalman gain matrix at the moment, which is used to balance the weights of the predicted value and the observed value; : The observation matrix, which contains the geometric relationship parameters between the sensor and the satellite (such as coordinate conversion coefficients, measurement angles, etc.), and maps the state vector to the observation space; : The transpose matrix of the observation matrix; : The satellite data weight (range 0.2 - 0.8, take 0.8 when the signal-to-noise ratio > 15 dB); : The ground sensor weight ( = 1 - ), and it is forced to be 0.9 when the temperature gradient > 5℃ / m); : The satellite observation noise covariance matrix, which is determined by the satellite measurement error (1.2 mm); : The ground sensor observation noise covariance matrix, which is determined by the accuracy of the fiber Bragg grating (0.05 mm) and MEMS (0.1 mm).

[0066] 2.2 State update formula:

[0067] In the formula, : The updated state vector at the moment (the optimal estimate after fusing the observation data); : The observation vector at the moment (including the original signals such as the fiber optic wavelength shift, InSAR phase, etc.); : The observed value corresponding to the predicted state, and the difference from the measured value is used as the basis for updating.

[0068] 2.3 Error covariance update formula:

[0069] In the formula, : The updated error covariance matrix at the moment, which reflects the uncertainty of the fused state; I: The identity matrix, which ensures the consistency of the matrix operation dimensions.

[0070] Based on the above algorithm, through the state transition matrix and the observation matrix , establish the mathematical correlation of multi-source data, and use the weight Dynamically balance the credibility of satellites and ground sensors, and finally obtain the optimal settlement estimate through iterative calculation.

[0071] In some embodiments, the calculation formula for the risk threshold is:

[0072] In the formula, is the basic threshold, 2.5 mm / month for PVC pipes and 3.5 mm / month for steel pipes; = 0.05 / m, which is the burial depth correction coefficient (the greater the burial depth, the more complex the soil stress distribution, and the threshold needs to be adjusted downwards), and d is the burial depth; is the material coefficient, 0 for PVC pipes and 0.2 for steel pipes (due to the higher stiffness of the steel pipe material, a certain degree of settlement compensation is allowed (the threshold can be increased by 0.2 times), and there is no correction for PVC pipes).

[0073] In addition, in some embodiments, a multi-level alarm form is adopted: Yellow warning: Triggered when the single-point settlement > 2 mm / month and lasts for 2 weeks; Red warning: Average settlement > 3 mm / month and deformation gradient > 0.5 mm / m.

[0074] Among them, the deformation gradient refers to the settlement difference within a unit length (such as the settlement difference between the two ends of a 1-meter pipeline > 0.5 mm), which reflects the non-uniformity of settlement and is a key indicator for pipeline fracture.

[0075] The above solutions set the basic safety boundary in combination with engineering characteristics such as material and burial depth, and achieve hierarchical early warning through the dual indicators of "single-point settlement rate + deformation gradient" to avoid false alarms and missed alarms.

[0076] The weak current pipeline settlement monitoring system based on multi-source data fusion provided by this application has the following beneficial effects: 1. This application adopts a three-dimensional grid layout of vertical stratification and horizontal radiation for sensor layout, combined with synchronous monitoring of different depths, to accurately capture the compression deformation characteristics of soil in different depth layers. The strain sensing optical cable is closely attached along the weak current pipeline route, breaking through the limitations of traditional discrete point monitoring, and realizing continuous linear stress distribution measurement. Improve the comprehensiveness and accuracy of monitoring.

[0077] 2. This application uses multi-source data fusion technology to fuse the high-precision real-time data provided by the ground sensor array with the large-scale macroscopic deformation covered by satellite remote sensing, improving the reliability of monitoring.

[0078] 3. This application sets up an early warning mechanism. When the settlement risk threshold is exceeded, it will remind the operation and maintenance personnel. After receiving the alarm information, the operation and maintenance personnel can take corresponding measures (such as starting the backup optical cable route) to minimize the impact caused by pipeline settlement.

[0079] It can be understood that the same or similar parts in the above embodiments can be referred to each other, and for the content not detailed in some embodiments, reference can be made to the same or similar content in other embodiments.

[0080] It should be noted that in the description of the present invention, the terms "first", "second", etc. are only used for descriptive purposes and cannot be construed as indicating or implying relative importance. In addition, in the description of the present invention, unless otherwise specified, the meaning of "a plurality of" refers to at least two.

[0081] It should be understood that each part of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.

[0082] Those of ordinary skill in the art in the technical field of the present invention can understand that all or part of the steps carried by the methods for implementing the above embodiments can be completed by instructing relevant hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiments.

[0083] In addition, each functional unit in various embodiments of the present invention can be integrated into a processing module, or each unit can exist physically alone, or two or more units can be integrated into one module. The above integrated module can be implemented in the form of hardware or in the form of a software functional module. When the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. The above-mentioned storage medium can be a read-only memory, a magnetic disk or an optical disc, etc.

[0084] In the description of this specification, the description with reference to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples.

[0085] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention.

Claims

1. A weak current pipeline settlement monitoring system based on multi-source data fusion, characterized in that, Including: A ground sensor array, including multiple fiber Bragg grating hydrostatic level gauges, strain sensing optical cables, and multiple MEMS triaxial accelerometers, which are used to collect horizontal displacement, deformation stress, and vertical settlement respectively; A satellite remote sensing module, including a synthetic aperture radar module and a GNSS module, which are used to obtain surface deformation data and elevation data of the monitoring area respectively; A data analysis platform, which is used to extract features from the data collected by the ground sensor array, perform multi-source data fusion on the extracted features and the satellite remote sensing data obtained by the satellite remote sensing module using a multi-source data fusion algorithm, and perform settlement monitoring and early warning based on the fusion result; Among them, the ground sensor array is distributed in a three-dimensional grid shape along the entrance of the weak current pipeline into the building, buried vertically in multiple different depths below the ground surface, and radiated outward in a horizontal direction centered on the pipeline entrance into the building within a set range, and a group of sensor nodes is set at every set distance; The synthetic aperture radar module periodically obtains surface deformation data of the monitoring area and generates a settlement rate map through differential interferometry; the GNSS module obtains elevation data of the monitoring area in real time; The data analysis platform includes an edge computing node, a cloud server, and an early warning terminal. The edge computing node is deployed at the monitoring site, equipped with a lightweight LSTM model, and processes the data collected by the ground sensor array in real time and extracts settlement features; The cloud server obtains satellite remote sensing data, constructs a spatio-temporal unified coordinate system, and performs multi-source data fitting using a weighted Kalman filter algorithm to generate a comprehensive settlement risk map; the early warning terminal stores risk thresholds for different pipeline materials. When it is determined based on the comprehensive settlement risk map and the risk threshold that the settlement amount meets the set early warning conditions, an alarm is automatically triggered and the positioning information of the warning area is sent to the operation and maintenance personnel.

2. The system according to claim 1, wherein The fiber Bragg grating hydrostatic level gauge adopts a temperature compensation structure, with a PT-100 platinum resistance built-in, and eliminates the interference of environmental temperature on settlement measurement through a dual-parameter demodulation algorithm.

3. The system according to claim 1, characterized in that, The installation structure of the ground sensor array includes: The fiber Bragg grating hydrostatic level gauge and the strain sensing optical cable are installed using a thorn-type settlement tube. The outer side of the settlement tube body is provided with a barbed structure to enhance the coupling with the soil; the length of each settlement tube is 1.5 meters, and a continuous monitoring network is formed through flange connection; an optical fiber grating sensor string is embedded in the tube body, and a monitoring point is set every 0.3 meters to cover the full-depth deformation monitoring; The MEMS triaxial accelerometer module arranges multiple monitoring nodes at preset intervals along the axial direction of the pipeline. Each monitoring node includes a sealed and protected MEMS triaxial accelerometer, a temperature compensation unit, and a wireless transmission module; the accelerometer is vertically fixed above the pipeline.

4. The system according to claim 1, characterized in that, The monitoring period of the synthetic aperture radar module is 7 days; after the data analysis platform updates the comprehensive settlement map, it automatically compares it with the historical comprehensive settlement map, identifies abnormal deformation areas and marks them as high-risk areas.

5. The system according to claim 1, wherein Within the monitoring area, at least one reference station and multiple monitoring stations are arranged to form an observation network. Each station is equipped with a multi-frequency GNSS receiver and an anti-multipath antenna; the monitoring stations are arranged in a mesh along the direction of the weak current pipeline into the building.

6. The system according to claim 1, wherein The data analysis platform integrates the BIM model, overlays the monitoring data with the building structure model, and supports three-dimensional visual settlement trend simulation and pipeline stress simulation analysis.

7. The system according to claim 1, wherein The cloud server constructs a spatio-temporally unified coordinate system and establishes a conversion model between the WGS84 coordinate system and the local coordinate system: wherein is a rotation matrix obtained by resolving the baseline vectors of three GNSS reference stations, and T is a translation vector determined by measuring ground control points; , and are three-dimensional coordinates in the local coordinate system. , and are three-dimensional coordinates in the WGS84 coordinate system.

8. The system according to claim 1, wherein The multi-source data fusion algorithm includes: (1) Construct a state equation In the formula, represents the state vector, which is used to describe the state of the system at time . is the vertical settlement, with the unit of mm; is the axial strain of the pipeline, with the unit of ; is the vertical acceleration, with the unit of g; is the settlement rate retrieved by the satellite, with the unit of mm / month; In the formula, represents the observation vector, which characterizes the original signal measured by the sensor and needs to be associated with the state vector through conversion, is the optical fiber wavelength offset, with the unit of pm; is the phase difference of the strain optical cable, with the unit of rad; is the second derivative of the vertical component of the MEMS triaxial accelerometer, with the unit ; is the InSAR interference phase, with the unit of rad; (2) Adaptive weight allocation Calculate the confidence of satellite data: wherein, is the satellite measurement error, with a typical value of 1.2 mm; is the comprehensive error of ground sensors, 0.05mm for the fiber Bragg grating static level and 0.1mm for the MEMS triaxial accelerometer; is the satellite data weight, taking the upper limit when the signal-to-noise ratio > 15 dB; is the sensor weight. When the temperature gradient occurs, force ; (2) Weighted Kalman filter iteration: In the prediction stage, calculate according to the following formula: In the formula, represents the predicted state vector at the th moment; represents the state transition matrix; represents the predicted state vector at the th moment; represents the control input matrix; represents the external control vector; represents the predicted error covariance matrix at the th moment; represents the error covariance matrix at the th moment; represents the transpose matrix of the state transition matrix; represents the process noise matrix, which is dynamically adjusted according to the pipeline burial depth; In the update stage, calculate according to the following formula: Wherein, represents the Kalman gain matrix at the th moment; represents the observation matrix, which contains the geometric relationship parameters between the sensor and the satellite; represents the transpose matrix of the observation matrix; represents the satellite data weight; represents the ground sensor weight, = 1 - ; represents the satellite observation noise covariance matrix; represents the ground sensor observation noise covariance matrix; represents the updated state vector at the th moment; represents the observation vector at the th moment; represents the observed value corresponding to the predicted state, and the difference from the measured value is used as the update basis; represents the updated error covariance matrix at the th moment; I represents the identity matrix.

9. The system according to claim 1, wherein The calculation formula for the risk threshold is: In the formula, is the basic threshold value, 2.5 mm / month for PVC pipes and 3.5 mm / month for steel pipes; = 0.05 / m, which is the burial depth correction coefficient, and d is the burial depth; is the material coefficient, 0 for PVC pipes and 0.2 for steel pipes.

Images