A landslide three-dimensional deformation field monitoring method and system based on physical information neural network model

Abstract

The present invention discloses a method and system for monitoring the three-dimensional deformation field of a landslide based on a physical information neural network model. The method comprises: using three-dimensional laser scanning to acquire multi-period point cloud data of the landslide body, and combining limited inclinometer and GNSS monitoring data to acquire time-series deformation data of the landslide body's internal and external appearance; using an improved ICP algorithm to solve the point cloud data to obtain the surface deformation field of the landslide body; constructing a physical information neural network model, training it based on monitoring data, and optimizing model parameters to predict displacement along and perpendicular to the slope; and deducing the three-dimensional overall time-series deformation field of the landslide based on the trained model to achieve real-time monitoring. The advantages of the present invention are: it can provide high-precision landslide deformation monitoring with real-time and accuracy, and can effectively warn of landslide disasters.

Description

Technical Field

[0001] The present invention relates to the field of geological engineering technology, and in particular to a landslide three-dimensional deformation field monitoring method and system based on a physical information neural network model. Background Art

[0002] In recent years, landslides have become increasingly frequent worldwide, causing significant economic losses and casualties. These disasters not only threaten the safety of people and property but also disrupt the normal operation of infrastructure. Therefore, landslide monitoring and early warning have become crucial components of landslide disaster prevention and mitigation. However, traditional landslide monitoring methods still face challenges and limitations, necessitating the urgent need for more efficient and accurate technical systems to enhance landslide monitoring and early warning capabilities.

[0003] Existing landslide monitoring methods are mainly divided into point deformation monitoring methods and surface deformation monitoring methods based on remote sensing technology. Point deformation monitoring methods usually monitor the local deformation of the landslide body by deploying GNSS (Global Navigation Satellite System), multi-point displacement meters and inclinometers on the landslide body. Although this method can provide certain monitoring data, its limitations are also very obvious: first, point monitoring can only provide deformation information of local areas and cannot fully reflect the deformation of the entire landslide body; second, this method relies on the deployment and maintenance of a large number of equipment, and is easily affected by factors such as equipment failure, local collapse, and dissolution, resulting in data anomalies and false alarms. In addition, the point monitoring method is generally applicable to gravity-traction landslides, and is not applicable to rainfall-type landslides or landslides with step-like deformation characteristics.

[0004] Surface deformation monitoring methods based on remote sensing technology, such as InSAR (Synthetic Aperture Radar Interferometry) and three-dimensional laser scanning technology, can obtain deformation information on the landslide surface over a large area. InSAR technology uses the phase difference of electromagnetic wave signals to calculate the deformation of the landslide surface, while three-dimensional laser scanning obtains deformation data by analyzing multi-period point cloud data. However, these methods mainly provide surface deformation information and cannot penetrate deep into the interior of the landslide body, lacking a comprehensive understanding of the deformation and instability process within the landslide body. In addition, the InSAR solution method may lead to large errors when it is significantly interfered by factors such as surrounding vegetation and terrain. The three-dimensional laser scanning method has problems such as large computational complexity and discontinuous data when processing large amounts of point cloud data, making it difficult to achieve real-time monitoring of landslide disasters.

[0005] There are also some landslide monitoring methods that set thresholds based on rock and soil parameters (such as acoustic emission, rainfall, deformation rate, etc.). Although they can determine landslide instability and provide disaster warnings to a certain extent, the strong spatial variability of rock and soil parameters leads to large differences between different landslide cases. Thresholds based on historical experience and statistical data are often not universal, so these methods are difficult to be widely applied to all types of landslide disasters.

[0006] In summary, existing technologies are still unable to provide a comprehensive and accurate landslide monitoring and early warning system, especially the lack of real-time monitoring and prediction methods for the three-dimensional deformation of landslide bodies. Summary of the Invention

[0007] In view of the defects of the prior art, the present invention provides a landslide three-dimensional deformation field monitoring method and system based on a physical information neural network model.

[0008] In order to achieve the above object of the invention, the technical solution adopted by the present invention is as follows:

[0009] A method for monitoring a landslide's three-dimensional deformation field based on a physical information neural network model comprises the following steps:

[0010] Step 1: Use 3D laser scanning to obtain multi-period point cloud data of the landslide body, and combine limited inclinometers and GNSS monitoring to obtain limited internal and external time-series deformation monitoring data of the landslide body;

[0011] Step 2: Use the improved ICP algorithm to solve the multi-period point cloud data to obtain the surface deformation field of the landslide body; the improved ICP algorithm is used to identify the corresponding point pairs between the source point cloud and the target point cloud, and construct the rotation and translation matrices based on these point pairs to ensure that the error function is minimized.

[0012] Step 3: Construct a physical information neural network model and train the model based on the limited internal and external time-series deformation monitoring data of the landslide to obtain the optimal parameters. The input of the model is (x, y, z, t), where (x, y, z) is the three-dimensional spatial coordinates of the monitoring point, t is the monitoring time, and the output is the displacement u along the slope and the displacement v perpendicular to the slope. The loss of the physical information neural network model includes traditional loss and physical information loss. The traditional loss is the mean square error loss, and the physical information loss is used to express the physical laws of the internal and external mechanical deformation of the landslide.

[0013] Step 4: Based on the optimized network parameters, the trained physical information neural network model is used to deduce the three-dimensional overall time-series deformation field of the landslide to achieve real-time monitoring of the three-dimensional deformation field of the landslide.

[0014] Furthermore, the improved ICP algorithm described in step 2 includes the following steps:

[0015] Identify the corresponding point pairs between the source point cloud and the target point cloud, and construct the rotation matrix and spatial translation vector based on these point pairs. The specific formula is as follows:

[0016] Q=MP+t

[0017]

[0018] Among them, P is the source point cloud, Q is the target point cloud, M is the spatial rotation matrix, and t is the spatial translation vector; t y represents the translation along the Y axis, t z Represents the translation along the Z axis, r ij Where i, j = 1, 2, 3 represents a component of the rotation matrix, which is used to rotate the coordinates of the point cloud.

[0019] The error function is estimated using the rotation matrix M and the spatial translation vector t, and the error function is minimized by iteratively optimizing the transformation. The expression of the error function J is:

[0020] J=Σ||q i -(M*p i +t)|| 2

[0021] Among them, q i is the i-th point in the target point cloud, p i is the i-th point in the source point cloud;

[0022] In each iteration, a new rotation matrix M is calculated n and the translation vector t n , so that the sum of the error functions is minimized. The specific calculation formula is:

[0023]

[0024] Among them, p i n-1 is the point cloud of the last iteration, q i is the point of the target point cloud, k is the total number of points in the point cloud;

[0025] When the maximum number of iterations n is met max When the error threshold δ is reached, the iteration is stopped and the calculation is completed.

[0026] Furthermore, for the nth iteration, the nth point cloud P n Expressed as:

[0027] P n =M n P n-1 +t n

[0028] Corresponding point cloud P nThe average distance between and Q is expressed as follows:

[0029]

[0030] When n>n max or d≤δ, the iteration of the calculation stops, is the position of the i-th point in the source point cloud after the n-th iteration.

[0031] Furthermore, the architecture of the physical information neural network model is any one of an artificial neural network, a recurrent neural network, a long short-term memory neural network or a Transformer attention mechanism.

[0032] Furthermore, the traditional loss is the mean square error loss, and the formula is:

[0033]

[0034] Among them, u i and v i is the measured deformation along and perpendicular to the slope, and is the deformation along and perpendicular to the slope predicted by the model;

[0035] Furthermore, the physical information neural network model uses a ReLU activation function, and the expression of the ReLU activation function is:

[0036]

[0037] Furthermore, the boundary conditions of the physical information neural network model include the landslide deformation boundary, and at the monitoring time t=0, the landslide body has no deformation; at the monitoring time t=∞, the landslide deformation converges to the maximum value U max and V max .

[0038] Furthermore, the landslide body is divided into several strips by the strip division method, and the angle between the strip and the horizontal plane is θ i The relationship between the deformation u along the slope and the deformation v perpendicular to the slope and the monitoring time t is as follows:

[0039]

[0040] Furthermore, the total loss L of the physical information neural network model is composed of the traditional loss L data and physical information loss L physics The superposition composition is expressed as:

[0041] L=L data +L physics .

[0042] The present invention also discloses a landslide three-dimensional deformation field monitoring system, which can be used to implement the above-mentioned landslide three-dimensional deformation field monitoring method, specifically including:

[0043] 3D laser scanning device, used to obtain multi-period point cloud data of the landslide;

[0044] A limited inclinometer device is used to obtain time-series deformation monitoring data of the internal and external appearance of the landslide body;

[0045] GNSS monitoring device, used to obtain time-series deformation data of the landslide;

[0046] A data processing module is used to solve multi-period point cloud data using an improved ICP algorithm to obtain the surface deformation field of the landslide body. The improved ICP algorithm is used to identify corresponding point pairs between the source point cloud and the target point cloud, and to construct rotation and translation matrices based on these point pairs to ensure that the error function is minimized;

[0047] A physical information neural network model construction module is used to train the physical information neural network model based on limited internal and external time-series deformation monitoring data of the landslide to obtain optimal parameters. The input of the physical information neural network model is (x, y, z, t), where (x, y, z) is the three-dimensional spatial coordinates of the monitoring point and t is the monitoring time. The output is the displacement u along the slope and the displacement v perpendicular to the slope. The loss of the physical information neural network model includes traditional loss and physical information loss. The traditional loss is mean square error loss, and the physical information loss is used to express the physical laws of the internal and external mechanical deformation of the landslide body.

[0048] The real-time monitoring module is used to deduce the three-dimensional overall time-series deformation field of the landslide based on the optimized network parameters and the trained physical information neural network model, thereby realizing real-time monitoring of the three-dimensional deformation field of the landslide.

[0049] The present invention also discloses a computer device, comprising a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the program, the above-mentioned landslide three-dimensional deformation field monitoring method is implemented.

[0050] The present invention also discloses a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the above-mentioned landslide three-dimensional deformation field monitoring method is realized.

[0051] Compared with the prior art, the advantages of the present invention are:

[0052] 1. This invention utilizes a 3D landslide deformation field monitoring technology based on a physical information neural network. This technology overcomes the limitations of traditional point-based deformation monitoring methods, moving beyond localized deformation monitoring to comprehensive 3D landslide deformation monitoring. This enhanced dimensionality allows for comprehensive visualization of the entire landslide, including both surface and deep deformation, providing more accurate and comprehensive landslide deformation information than traditional methods.

[0053] 2. This invention utilizes multiple monitoring technologies, including 3D laser scanning, limited inclinometers, and GNSS, combined with a physical information neural network model to achieve real-time monitoring and prediction of landslide deformation. This enables more timely and accurate landslide warnings, providing strong support for disaster prevention and control and emergency decision-making.

[0054] 3. Traditional landslide monitoring methods, relying on experience and thresholds, are often inadequate for different landslide types. In contrast, the present invention, through training a physical information neural network, can adapt to the varying deformation characteristics of landslides. This method is not only applicable to gravity-induced landslides, but can also be widely applied to monitoring other types of landslide disasters, such as rainfall-induced landslides and reservoir landslides.

[0055] 4. This invention combines the advantages of physical mechanics and neural networks. By eliminating physical information in the loss function, it ensures that the displacement predictions output by the model conform to the physical laws of the landslide. By continuously optimizing the parameters of the neural network model, the predicted displacement values ​​are more consistent with the measured data, effectively reducing errors and improving prediction accuracy.

[0056] 5. Using a variety of neural network architectures (such as artificial neural networks, long short-term memory neural networks, and the Transformer attention mechanism), selecting the optimal network structure based on actual needs helps improve the model's learning ability and computational efficiency. In addition, by setting appropriate activation functions and boundary conditions, the model's computational process is further optimized, ensuring efficient and accurate results.

[0057] 6. Compared to traditional point-based monitoring methods, this method reduces reliance on numerous sensors and monitoring equipment, lowering the risk of data anomalies and false alarms due to factors such as equipment failure or local collapse. Furthermore, by combining 3D laser scanning and GNSS data, reliance on a single device can be further reduced, improving the robustness and reliability of the monitoring system. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 Schematic diagram of joint slope monitoring based on 3D laser scanning, limited inclinometer measurement, and GNSS according to an embodiment of the present invention;

[0059] Figure 2Figure 1 is a diagram of the physical information neural network architecture of an embodiment of the present invention. In the figure, (ab) are diagrams of the improved ICP algorithm for calculating the landslide surface deformation field; (ce) are schematic diagrams of the physical and mechanical mechanism of landslide instability; (fg) are diagrams of the physical information neural network architecture; and (h) are diagrams of different network structures, including long short-term memory neural networks, recurrent neural networks, and Transformer attention mechanisms.

[0060] Figure 3 Schematic diagram of the landslide surface deformation field calculated by three-dimensional laser scanning according to an embodiment of the present invention; in the figure, (a) is the deformation u of the landslide along the slope direction in the middle stage of development; (b) is the deformation u along the slope direction in the late stage of development of the landslide; (c) is the deformation v perpendicular to the slope direction in the middle stage of development of the landslide; and (d) is the deformation v perpendicular to the slope direction in the late stage of development of the landslide.

[0061] Figure 4 This is a schematic diagram of a landslide 3D deformation field constructed based on a physical information neural network according to an embodiment of the present invention. (a) shows the model training and parameter optimization process; (b) shows the result of constructing the 3D landslide deformation field. DETAILED DESCRIPTION

[0062] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below with reference to the accompanying drawings and examples.

[0063] The present invention provides a method for monitoring a landslide three-dimensional deformation field based on a physical information neural network model, comprising the following steps:

[0064] Step 1: Use 3D laser scanning to obtain multi-period point cloud data of the landslide body, and use limited inclinometers and GNSS monitoring to obtain limited internal and external time series deformation monitoring data of the landslide body. The monitoring diagram is shown in the figure below. Figure 1 As shown;

[0065] Step 2: The multi-period point cloud data is solved using an improved ICP algorithm to obtain the surface deformation field of the landslide. This algorithm identifies corresponding point pairs between the source and target point clouds, constructs rotation and translation matrices based on these pairs, and uses these matrices to estimate the error function. The algorithm iteratively optimizes the transformation to ensure that the error function meets predefined criteria, as described below:

[0066] Q=MP+t (1)

[0067]

[0068] Where P is the source point cloud, Q is the target point cloud, M is the spatial rotation matrix, and t is the spatial translation vector. The total error J is expressed as follows:

[0069] J=Σ||q i -(M*p i+t)|| 2 (3)

[0070] Among them, the minimum value of J should be calculated, M0 and t0 are defined as the initial rotation matrix and initial translation vector. The maximum number of iterations is defined as n max The sum threshold of the squared Euclidean distance is set to δ. The nth iteration is calculated as follows:

[0071]

[0072] For the nth iteration, the nth point cloud P n It can be expressed as:

[0073] P n =M n P n-1 +t n (5)

[0074] Corresponding point cloud P n The average distance between and Q can be expressed as follows:

[0075]

[0076] When n>n max or d≤δ, the calculation iteration stops, at which point the ICP calculation process is complete. The landslide surface deformation field solution process and result examples are as follows: Figure 2 As shown in (ab), in order to ensure the accuracy of the calculation, the target point cloud is divided into blocks and calculated separately.

[0077] Step 3: Construct a physical information neural network model and train the model based on the limited internal and external time series deformation monitoring data of the landslide to obtain the optimal parameters. Figure 2 As shown in (ce), the input of the neural network model is (x, y, z, t), where (x, y, z) is the three-dimensional spatial coordinate of the monitoring point, t is the monitoring time, and the output of the neural network model is the displacement u along the slope and the displacement v perpendicular to the slope. The architecture of the physical information neural network model is shown in Figure 2 As shown in (fg), depending on the situation, you can choose artificial neural network, recurrent neural network, long short-term memory neural network or Transformer attention mechanism architecture, such as Figure 2 (h). The loss of the physical information neural network model includes traditional loss (root mean square error loss) and physical information loss. The traditional loss is the mean square error loss or other forms of traditional loss. The mean square error loss is shown in formula (7):

[0078]

[0079] In formula (7), ui and v i is the measured deformation along and perpendicular to the slope, and is the deformation along the slope and perpendicular to the slope predicted by the model. Using ReLU activation function or other activation function types, the expression of ReLU activation function is shown in formula (8):

[0080]

[0081]

[0082] The boundary conditions of the model are shown in Equations (9), (10) and (11). When the monitoring time t = 0, it is the initial state and the landslide body has not deformed. When the monitoring time t = ∞, as the time scale is infinitely extended, the landslide deformation will not increase infinitely. At the maximum value U max and V max In addition, when the position (x, y, z) is located at Figure 2 Outside the deformation boundary shown in d, the deformation value is also 0. Figure 2 In e, the slope is divided into a number of strips by the strip division method. The total number of strips is i, and the angle between strip i and the horizontal plane is θ i Therefore, on the sliding surface of the landslide, the relationship between the deformation u along the slope, the deformation v perpendicular to the slope and the monitoring time t is as follows:

[0083]

[0084] The total loss L of the physical information neural network model is the superposition of the traditional loss of the model and the physical information loss, as shown in formula (13):

[0085] L = L data + L physics (13)

[0086] Step 4: Based on the optimized network parameters, use the trained physical information neural network model to deduce the three-dimensional overall time-series deformation field of the landslide, realize real-time monitoring of the three-dimensional deformation field of the landslide, and upgrade from local deformation monitoring to three-dimensional overall deformation monitoring.

[0087] This embodiment is first applied to the three-dimensional overall deformation field monitoring of a small landslide model.

[0088] (1) Based on three-dimensional laser scanning, multi-period point cloud data of the slope surface are obtained, and based on limited inclinometer measurement, the time-series deformation monitoring data of the slope's internal and external appearance are obtained.

[0089] (2) Use three-dimensional laser scanning to obtain multi-period point cloud data on the slope surface, and use the average field vector algorithm to solve the point cloud data to obtain the surface deformation field of the slope, such as Figure 3 shown.

[0090] (3) Based on the deformation time series data of the surface deformation field and the slope limited inclinometer monitoring, the physical information neural network model is trained to obtain the optimal parameters. Using the physical information neural network, the three-dimensional overall deformation field of the landslide is deduced, such as Figure 4 shown.

[0091] In another embodiment of the present invention, a landslide three-dimensional deformation field monitoring system is provided. The system can be used to implement the above-mentioned landslide three-dimensional deformation field monitoring method, specifically comprising:

[0092] 3D laser scanning device, used to obtain multi-period point cloud data of the landslide;

[0093] A limited inclinometer device is used to obtain time-series deformation monitoring data of the internal and external appearance of the landslide body;

[0094] GNSS monitoring device, used to obtain time-series deformation data of the landslide;

[0095] A data processing module is used to solve multi-period point cloud data using an improved ICP algorithm to obtain the surface deformation field of the landslide body. The improved ICP algorithm is used to identify corresponding point pairs between the source point cloud and the target point cloud, and to construct rotation and translation matrices based on these point pairs to ensure that the error function is minimized;

[0096] A physical information neural network model construction module is used to train the physical information neural network model based on limited internal and external time-series deformation monitoring data of the landslide to obtain optimal parameters. The input of the physical information neural network model is (x, y, z, t), where (x, y, z) is the three-dimensional spatial coordinates of the monitoring point and t is the monitoring time. The output is the displacement u along the slope and the displacement v perpendicular to the slope. The loss of the physical information neural network model includes traditional loss and physical information loss. The traditional loss is mean square error loss, and the physical information loss is used to express the physical laws of the internal and external mechanical deformation of the landslide body.

[0097] The real-time monitoring module is used to deduce the three-dimensional overall time-series deformation field of the landslide based on the optimized network parameters and the trained physical information neural network model, thereby realizing real-time monitoring of the three-dimensional deformation field of the landslide.

[0098] In another embodiment of the present invention, a terminal device is provided, comprising a processor and a memory, wherein the memory is configured to store a computer program, wherein the computer program includes program instructions, and the processor is configured to execute the program instructions stored in the computer storage medium. The processor may be a central processing unit (CPU), or may be another general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic device, discrete gate or transistor logic device, discrete hardware component, etc. It is the computing core and control core of the terminal, and is suitable for implementing one or more instructions, specifically for loading and executing one or more instructions to implement a corresponding method flow or corresponding function. The processor described in this embodiment of the present invention can be used to operate a landslide three-dimensional deformation field monitoring method.

[0099] In another embodiment of the present invention, a storage medium is provided, specifically a computer-readable storage medium (Memory), which is a memory device in a terminal device for storing programs and data. It can be understood that the computer-readable storage medium here can include both the built-in storage medium in the terminal device and, of course, the extended storage medium supported by the terminal device. The computer-readable storage medium provides a storage space, which stores the operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by the processor are also stored in the storage space. These instructions can be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk memory.

[0100] The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement the corresponding steps of the landslide three-dimensional deformation field monitoring method in the above embodiment; the processor can load and execute one or more instructions in the computer-readable storage medium.

[0101] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0102] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0103] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0104] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0105] Those skilled in the art will appreciate that the embodiments described herein are intended to help readers understand the implementation methods of the present invention, and it should be understood that the scope of protection of the present invention is not limited to such specific descriptions and embodiments. Those skilled in the art can make various other specific variations and combinations based on the technical teachings disclosed in the present invention without departing from the essence of the present invention, and such variations and combinations are still within the scope of protection of the present invention.

Claims

1. A method for monitoring the three-dimensional deformation field of landslides based on a physical information neural network model, characterized by: The following steps are involved: Step 1: Use 3D laser scanning to obtain multi-period point cloud data of the landslide body, and combine limited inclinometers and GNSS monitoring to obtain limited internal and external time-series deformation monitoring data of the landslide body; Step 2: Using an improved ICP algorithm to solve the multi-period point cloud data to obtain the surface deformation field of the landslide body; the improved ICP algorithm is used to identify corresponding point pairs between the source point cloud and the target point cloud, and to construct rotation and translation matrices based on these point pairs to ensure that the error function is minimized; The improved ICP algorithm comprises the following steps: Identify the corresponding point pairs between the source point cloud and the target point cloud, and construct the rotation matrix and spatial translation vector based on these point pairs. The specific formula is as follows: Q=MP+t Among them, P is the source point cloud, Q is the target point cloud, M is the spatial rotation matrix, and t is the spatial translation vector; t y represents the translation along the Y axis, t z Represents the translation along the Z axis, r ij Where i, j = 1, 2, 3 represents a component of the rotation matrix, which is used to rotate the coordinates of the point cloud; The error function is estimated using the rotation matrix M and the spatial translation vector t, and the error function is minimized by iteratively optimizing the transformation. The expression of the error function J is: J=Σ||q i -(M*p i +t)|| 2 Among them, q i is the i-th point in the target point cloud, p i is the i-th point in the source point cloud; In each iteration, a new rotation matrix M is calculated n and the translation vector t n , so that the sum of the error functions is minimized. The specific calculation formula is: Among them, p i n-1 is the point cloud of the last iteration, q i is the point of the target point cloud, k is the total number of points in the point cloud; When the maximum number of iterations n is met max Or when the error threshold δ is reached, the iteration is stopped and the calculation is completed; Step 3: Construct a physical information neural network model and train the model based on the limited internal and external deformation monitoring data of the landslide to obtain the optimal parameters. The landslide body is divided into several strips by the strip division method, and the angle between the strip and the horizontal plane is θ i The relationship between the deformation u along the slope and the deformation v perpendicular to the slope and the monitoring time t is as follows: The boundary conditions of the physical information neural network model include the landslide deformation boundary, and at the monitoring time t=0, the landslide body has no deformation; at the monitoring time t=∞, the landslide deformation converges to the maximum value U max and V max； The landslide body is divided into several strips by the strip division method, and the angle between the strip and the horizontal plane is θ i The relationship between the deformation u along the slope and the deformation v perpendicular to the slope and the monitoring time t is as follows: The input of the model is (x, y, z, t), where (x, y, z) is the three-dimensional spatial coordinate of the monitoring point, t is the monitoring time, and the output is the displacement u along the slope and the displacement v perpendicular to the slope. The total loss L of the physical information neural network model includes the traditional loss L data and physical information loss L physics , the expression is: L=L data +L physics The total loss L of the physical information neural network model is used to express the physical laws of the internal and external mechanical deformation of the landslide body; Step 4: Based on the optimized network parameters, the trained physical information neural network model is used to deduce the three-dimensional overall time-series deformation field of the landslide, thereby realizing real-time monitoring of the three-dimensional deformation field of the landslide.

2. The method for monitoring the three-dimensional deformation field of a landslide according to claim 1, characterized in that: For the nth iteration, the nth point cloud P n Expressed as: P n =M n P n-1 +t n Corresponding point cloud P n The average distance between and Q is expressed as follows: When n>n max or d≤δ, the iteration of the calculation stops, is the position of the i-th point in the source point cloud after the n-th iteration.

3. The method for monitoring the three-dimensional deformation field of a landslide according to claim 1, characterized in that: The architecture of the physical information neural network model is any one of artificial neural networks, recurrent neural networks, long short-term memory neural networks or Transformer attention mechanism.

4. The method for monitoring the three-dimensional deformation field of a landslide according to claim 1, characterized in that: The traditional loss is the mean square error loss, and the formula is: Among them, u i and v i is the measured deformation along and perpendicular to the slope, and are the deformations predicted by the model along and perpendicular to the slope aspect.

5. The method for monitoring the three-dimensional deformation field of a landslide according to claim 1, characterized in that: The physical information neural network model uses the ReLU activation function, and the expression of the ReLU activation function is:

6. A landslide three-dimensional deformation field monitoring system, characterized by: The system can be used to implement the landslide three-dimensional deformation field monitoring method according to any one of claims 1 to 5, specifically comprising: 3D laser scanning device, used to obtain multi-period point cloud data of the landslide; A limited inclinometer device is used to obtain time-series deformation monitoring data of the internal and external appearance of the landslide body; GNSS monitoring device, used to obtain time-series deformation data of the landslide; A data processing module is used to solve multi-period point cloud data using an improved ICP algorithm to obtain the surface deformation field of the landslide body. The improved ICP algorithm is used to identify corresponding point pairs between the source point cloud and the target point cloud, and to construct rotation and translation matrices based on these point pairs to ensure that the error function is minimized; A physical information neural network model construction module is used to train the physical information neural network model based on limited internal and external time-series deformation monitoring data of the landslide to obtain optimal parameters. The input of the physical information neural network model is (x, y, z, t), where (x, y, z) is the three-dimensional spatial coordinates of the monitoring point and t is the monitoring time. The output is the displacement u along the slope and the displacement v perpendicular to the slope. The loss of the physical information neural network model includes traditional loss and physical information loss. The traditional loss is mean square error loss, and the physical information loss is used to express the physical laws of the internal and external mechanical deformation of the landslide body. The real-time monitoring module is used to deduce the three-dimensional overall time-series deformation field of the landslide based on the optimized network parameters and the trained physical information neural network model, thereby realizing real-time monitoring of the three-dimensional deformation field of the landslide.

Images