Building deformation monitoring method and device based on Beidou GNSS and three-axis tilt sensor

Abstract

The invention discloses a method and device for monitoring building deformation based on Beidou GNSS and a three-axis tilt sensor, comprising: obtaining building information of a building to be tested, analyzing the deformation direction of the building to be tested according to building geometry; deploying a Beidou GNSS monitoring station at the building outline along the deformation direction; deploying a Beidou GNSS reference station outside the building to be tested; deploying a three-axis tilt sensor at the geometric center of the building to be tested according to the building geometry; collecting Beidou GNSS data of the building to be tested in the deformation direction; extracting significant change features in the deformation direction; classifying Beidou GNSS data into stable data and unstable data according to the significant change features; obtaining expected complex deformation data of unstable data through a first neural network model; calculating and obtaining general simple deformation data of stable data; obtaining comprehensive building deformation of expected complex deformation data and general simple deformation data through a second neural network model; and verifying the comprehensive building deformation through the three-axis tilt data of the three-axis tilt sensor.

Description

Technical Field

[0001] The present invention relates to the field of building and geological surveying technology, and in particular to a building deformation monitoring method, device, equipment and storage medium based on Beidou GNSS and a three-axis tilt sensor. Background Art

[0002] The collapse of buildings, especially high-rise buildings, seriously endangers people's public safety. Especially when buildings are hit by accidents such as fire, the probability of building collapse increases significantly. For firefighters who are in the building to evacuate people and provide first aid, it is impossible to predict whether the burning building will collapse, let alone when it will collapse. Usually, firefighters can only perceive and judge based on experience and observation of the on-site conditions. In this way, there is no safety warning guarantee for people in dangerous buildings. Usually, buildings will undergo different degrees of deformation before they collapse, and the most important characteristic parameter of deformation is displacement. Others such as deflection, tilt, and settlement are essentially displacement. To a certain extent, by measuring the displacement of building components or the whole, the deformation of the building in the spatial dimension can be obtained. Measuring within a continuous time range can obtain the real-time deformation of the building in the time dimension. However, due to the large volume of buildings, especially high-rise buildings, small deformation, and deformation caused by different external forces in different deformation directions, it is impossible to directly accept the data of the acquisition equipment. It is difficult for current measurement equipment to achieve high-reliability and accurate monitoring of building deformation. Summary of the invention

[0003] Based on this, the first aspect of an embodiment of the present invention discloses a building deformation monitoring method based on Beidou GNSS and a three-axis tilt sensor.

[0004] The monitoring method comprises the following steps: obtaining architectural information of a building to be measured, wherein the architectural information comprises an architectural outline and architectural geometry of the building to be measured; analyzing one or more deformation directions in which the building to be measured may deform according to the architectural geometry; deploying one or more Beidou GNSS monitoring stations at the building outline along the deformation direction; deploying a Beidou GNSS reference station outside the building to be measured; deploying a three-axis tilt sensor at the geometric center of the building to be measured according to the architectural geometry; collecting Beidou GNSS data of the building to be measured in multiple deformation directions within a monitoring period, wherein the GNSS data is obtained according to the measurement of the Beidou GNSS monitoring station relative to the GNSS reference station in the deformation direction; and extracting the Beidou GNSS data of each building to be measured. The method comprises the following steps: determining a significant change feature of the deformation direction within the monitoring time; classifying at least one of the Beidou GNSS data as stable data and at least one of the Beidou GNSS data as unstable data according to the significant change feature; selecting a first neural network model corresponding to the unstable data, and obtaining expected complex deformation data of the unstable data through monitoring the first neural network model; calculating general simple deformation data of the stable data; selecting a second neural network model, and obtaining a comprehensive building deformation of at least one of the expected complex deformation data and at least one of the general simple deformation data through monitoring the second neural network model; and verifying the comprehensive building deformation through the three-axis tilt data of the three-axis tilt sensor.

[0005] In the embodiments of the present invention, the deformation direction is horizontal displacement, vertical displacement, vertical displacement, flexure or torsion.

[0006] In the disclosed embodiment of the present invention, the significant change feature includes the distance signal change of the Beidou GNSS monitoring station relative to the GNSS reference station; extracting the significant change feature includes performing a fast Fourier transform on the Beidou GNSS data within the monitoring time to obtain frequency domain data; selecting at least one main frequency whose amplitude of the frequency domain data is greater than a threshold; and determining the distance signal change based on all the main frequencies.

[0007] In the disclosed embodiment of the present invention, determining the distance signal change includes averaging all the main frequencies as the distance signal change.

[0008] In the disclosed embodiment of the present invention, classifying the unstable data includes selecting the Beidou GNSS data corresponding to the distance signal change greater than or equal to a frequency threshold as unstable data.

[0009] In the disclosed embodiment of the present invention, classifying the stable data includes selecting the Beidou GNSS data corresponding to the distance signal change less than the frequency threshold as stable data.

[0010] In the embodiments of the present invention, the first neural network model is a BP neural network model; the second neural network model is a RBF neural network model.

[0011] A second aspect of an embodiment of the present invention discloses a building deformation monitoring device based on Beidou GNSS and a three-axis tilt sensor, comprising:

[0012] Beidou GNSS monitoring station, Beidou GNSS reference station, three-axis tilt sensor and server;

[0013] The server obtains building information of the building to be measured, wherein the building information includes the building outline and building geometry of the building to be measured; one or more deformation directions in which the building to be measured may be deformed are analyzed according to the building geometry; one or more Beidou GNSS monitoring stations are deployed along the building outline in the deformation direction; the Beidou GNSS reference station is deployed outside the building to be measured; the three-axis tilt sensor is deployed at the geometric center of the building to be measured according to the building geometry; the server collects Beidou GNSS data of the building to be measured in multiple deformation directions within a monitoring time, wherein the GNSS data source is obtained according to the measurement of the Beidou GNSS monitoring station relative to the GNSS reference station in the deformation direction. ; Extract the significant change characteristics of each deformation direction within the monitoring time; classify at least one of the Beidou GNSS data as stable data and at least one of the Beidou GNSS data as unstable data according to the significant change characteristics; select a first neural network model corresponding to the unstable data, and obtain the expected complex deformation data of the unstable data through the first neural network model; calculate the general simple deformation data of the stable data; select a second neural network model, and obtain the comprehensive building deformation of at least one of the expected complex deformation data and at least one of the general simple deformation data through the second neural network model; verify the comprehensive building deformation through the three-axis tilt data of the three-axis tilt sensor.

[0014] The third aspect of an embodiment of the present invention discloses at least one computer device, which includes a processor and a memory: the memory is used to store a computer program and transmit the computer program to the processor; the processor is used to execute the building deformation monitoring method based on Beidou GNSS and a three-axis tilt sensor according to the instructions in the computer program.

[0015] The fourth aspect of an embodiment of the present invention discloses at least one computer-readable storage medium, which is used to store a computer program. When the computer program is executed by a processor, it is used to implement the building deformation monitoring method based on Beidou GNSS and a three-axis tilt sensor.

[0016] In view of the above-mentioned solution, the present invention describes the disclosed exemplary embodiments in detail below with reference to the accompanying drawings, so that other features and advantages of the embodiments of the present invention are also made clear. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0018] Figure 1 A schematic diagram of the process of the building deformation monitoring method based on Beidou GNSS and a three-axis tilt sensor in this embodiment is shown;

[0019] Figure 2 A schematic diagram of the structure of a building deformation monitoring device based on Beidou GNSS and a three-axis tilt sensor in this embodiment is shown;

[0020] Figure 3 A schematic diagram showing the structure of the computer device of this embodiment is shown. DETAILED DESCRIPTION

[0021] In order to facilitate the understanding of the present application, the present application will be described more fully below with reference to the relevant drawings. The drawings provide embodiments of the present application. However, the present application can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present application more thorough and comprehensive.

[0022] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application.

[0023] It is understood that spatial relational terms such as "under", "beneath", "below", "under", "above", "above", etc., may be used herein to describe the relationship of one element and / or feature to other elements and / or features shown in the figures. It should be understood that the spatial relational terms also include different orientations of the device in use and operation in addition to the orientations shown in the figures. For example, if the device in the figures is turned over, the elements and / or features described as "under other elements" and / or "beneath" and / or "beneath" will be oriented "above" the other elements and / or features. Therefore, the exemplary terms "under" and "under" can include both the above and below orientations. In addition, the device can also include additional orientations (e.g., rotated 90 degrees and / or other orientations), and the spatial descriptors used herein are interpreted accordingly.

[0024] When used herein, the singular forms "a", "an" and " / the" may also include the plural forms, unless the context clearly indicates otherwise. It should also be understood that the terms "include / comprise" and / or "have" etc. specify the presence of stated features, wholes, steps, operations, components, parts and / or combinations thereof, but do not exclude the possibility of the presence and / or addition of one and / or more other features, wholes, steps, operations, components, parts and / or combinations thereof.

[0025] This embodiment discloses a building deformation monitoring method based on Beidou GNSS and a three-axis tilt sensor.

[0026] The monitoring method is used to monitor the architectural deformation of the building to be tested. Architectural deformation refers to various deformation phenomena that occur in the use of the building, mainly including elastic deformation and plastic deformation. Elastic deformation refers to the deformation that occurs under the action of external force, which can return to its original state when the external force is removed; while plastic deformation refers to the deformation that occurs under the action of external force, which cannot return to its original state once the external force is removed. The causes of building deformation include factors such as structure, soil and environment, as well as the influence of natural factors. For example, high-rise buildings will undergo bending deformation and shear deformation under wind loads and earthquakes. These deformation forms are closely related to the stiffness and stress conditions of the building structure. This embodiment uses the idea of ​​ensemble learning to fully consider the complex and difficult-to-observe deformations caused by complex and continuous external forces on the building during the deformation process. ‌‌

[0027] Figure 1 A schematic flow chart of the building deformation monitoring method based on Beidou GNSS and a three-axis tilt sensor in this embodiment is shown.

[0028] Figure 1 It is shown that the monitoring method comprises the following steps.

[0029] 10. Obtain the building information of the building to be tested.

[0030] The building information includes the building outline and building geometry of the building to be measured.

[0031] ‌Architectural outline refers to the outer contour line of the horizontal projection of the building's exterior wall. This is the boundary line of the building's appearance, used to describe the overall shape and size of the building. ‌Architectural geometry‌ refers to a method of applying geometric principles to architectural design, creating beautiful and practical architectural forms through the arrangement and combination of geometric figures and spatial construction. The application of geometry in architecture is not limited to simple shape design, but also includes more complex geometric transformations and spatial relationship processing.

[0032] 20 Analyze one or more deformation directions in which the building to be tested may deform according to the building geometry.

[0033] The analysis of the possible deformation direction of the building through architectural geometry refers to analyzing the geometric form of the building, and analyzing the direction or angle of the building's easy deformation when subjected to external forces based on the building's geometric form. These directions or angles of the building's easy deformation are important bases for monitoring the deformation of the building to be tested.

[0034] 30. Deploy one or more Beidou GNSS monitoring stations on the building outline along the deformation direction, and deploy a Beidou GNSS reference station outside the building to be measured.

[0035] Beidou GNSS monitoring stations and Beidou GNSS reference stations are devices used to monitor the Global Navigation Satellite System (GNSS). These satellite systems transmit signals for receivers to use to calculate information such as position, speed and time. Beidou GNSS monitoring stations receive satellite signals, record information such as time, position and signal strength, measure satellite orbits and clock errors, and provide high-precision position and time information. Beidou GNSS monitoring stations deployed along the deformation direction will be able to obtain possible future deformations of the building to be measured in the deformation direction or angle. The changes in the coordinates of the Beidou GNSS monitoring station and the Beidou GNSS reference station are calculated through the relative signal distance between the two, that is, the deformation of the building in the deformation direction.

[0036] 40 The building geometry deploys a three-axis tilt sensor at the geometric center of the building to be measured.

[0037] The three-axis tilt sensor is deployed at the geometric center of the building to be tested, and can obtain relatively stable data on the overall displacement of the building to be tested.

[0038] 50 collecting Beidou GNSS data of the building to be tested in multiple deformation directions within a monitoring period,

[0039] 60 Extract the significant change characteristics of each Beidou GNSS data during the monitoring time.

[0040] Among them, the significant change features include the distance signal change. Extracting the distance signal change includes performing a fast Fourier transform on a continuous section of Beidou GNSS data within the monitoring time to obtain the frequency domain data of the Beidou GNSS data. Sort the frequency components in the frequency domain data according to the amplitude. Select a threshold, and only retain the frequency components greater than the amplitude threshold as the main frequency of the Beidou GNSS data. The distance signal change is calculated based on all the selected main frequencies.

[0041] Preferably, when selecting the main frequency, the frequency components arranged in front of a certain number can be directly selected as the main frequency.

[0042] Preferably, the mean of all main frequencies is calculated as the distance signal variation.

[0043] 70 Classify at least one Beidou GNSS data as stable data and at least one Beidou GNSS data as unstable data according to the significant change characteristics.

[0044] Among them, Beidou GNSS data corresponding to a distance signal change greater than or equal to a frequency threshold is selected as unstable data; Beidou GNSS data corresponding to a distance signal change less than the frequency threshold is selected as stable data.

[0045] 80 A first neural network model corresponding to the unstable data is selected, and expected complex deformation data of the unstable data is obtained by monitoring the first neural network model.

[0046] Among them, the first neural network model is the BP neural network model. The BP neural network is a multi-layer feedforward neural network based on error back propagation training. The BP neural network model consists of an input layer, several hidden layers and an output layer. The input layer of the BP neural network model contains several input neurons, and the input neurons are used to input the input features of stable data. The BP neural network model has 1 hidden layer, and the hidden layer includes 3 to 5 hidden neurons. The output layer of the BP neural network model has 1 output neuron, and the output of the output neuron can characterize the complex deformation changes corresponding to the stable data, that is, the expected complex deformation data. The BP neural network model uses an S-type transfer function, ; By back-propagating the error function, ; Where Ti is the expected output, Oi is the calculated output of the network, the network weights and thresholds are adjusted to minimize the error function E, and the S-type tangent function tansig is selected as the excitation of the hidden neurons.

[0047] Preferably, before the unstable data is used as the input of the BP neural network model, the time domain characteristics and frequency domain characteristics of the unstable data are extracted, which are peak value, margin, skewness, kurtosis, center frequency domain, frequency standard deviation, root mean square frequency and frequency concentration.

[0048] The extracted time domain features and frequency domain features are normalized, that is, , , are the minimum and maximum values ​​of the normalized results. The normalized results are used as the input of the BP neural network model.

[0049] 90 General simple deformation data for which stable data are calculated.

[0050] The calculation of the general simple deformation data refers to filtering the stable data, and then calculating the deformation of the building to be measured corresponding to the stable data within the monitoring time by superposition and summation, that is, the general simple deformation data.

[0051] 100 A second neural network model is selected, and a comprehensive deformation of the building to be measured, which is obtained by monitoring at least one expected complex deformation data and at least one general simple deformation data, is obtained through the second neural network model.

[0052] Among them, the second neural network model is the RBF neural network model. The RBF neural network model is the radial basis neural network model. The RBF neural network model includes an input layer, a hidden layer and an output layer. The input layer has m input neurons, each input neuron corresponds to a Beidou GNSS data, the input corresponds to the expected complex deformation data of the unstable data, and the input corresponds to the general simple deformation data of the stable data. The number of hidden neurons in the hidden layer is m, and the radial basis function of each hidden neuron adopts a Gaussian function, that is, , where j is a natural number and is less than or equal to m, is the Gaussian function center of the jth neuron in the hidden layer; is the width of the Gaussian function; exist Take the maximum value and Negatively correlated, The value is greater than or equal to 0. Preferably, the Gaussian function center (i.e., cluster center) of each initial hidden neuron can be obtained randomly, or the output layer has m output neurons obtained by clustering multiple samples used to train the RBF neural network model by K-means, which respectively represent the deformation of the building to be tested after the monitoring time, so as to represent the comprehensive deformation of the building to be tested. The output neuron is determined as follows: is the weight from the jth hidden neuron in the hidden layer to the kth output neuron in the output layer, and W is the number of hidden neurons.

[0053] Preferably, the second neural network model can also be configured as a BP neural network model.

[0054] 110 verifies the comprehensive building deformation through the three-axis tilt data of the three-axis tilt sensor.

[0055] The deformation ratio of the comprehensive building deformation and the three-axis tilt data in each deformation direction should be kept within a controllable range. If the deformation ratio of the comprehensive building deformation and the three-axis tilt data is inconsistent, it is considered that the building deformation in at least one deformation direction is unreliable, and 30 pairs of unstable data are returned for reclassification.

[0056] Based on this, the monitoring method of this embodiment first extracts each Beidou GNSS data, and then classifies the signal frequency of the Beidou GNSS data to determine whether stable data or unstable data is obtained. Stable data refers to the displacement data of one or more directions of Beidou GNSS that are reliable during the monitoring time, and unstable data refers to the displacement data of one or more directions of Beidou GNSS that are unreliable during the monitoring time. The monitoring method uses an integrated learning method to monitor the unreliable Beidou GNSS data through a first neural network model to obtain the expected complex deformation data; and obtains general simple deformation data by directly calculating the reliable Beidou GNSS data. Finally, the monitoring method monitors multiple expected complex deformation data and / or general simple deformation data through a second neural network model to obtain a comprehensive building deformation that characterizes the deformation of the building to be tested in various directions.

[0057] This embodiment discloses a building deformation monitoring device based on Beidou GNSS and a three-axis tilt sensor.

[0058] Figure 2 The schematic diagram of the structure of the building deformation monitoring device based on Beidou GNSS and three-axis tilt sensor is shown.

[0059] Figure 2The monitoring device is shown to include a Beidou GNSS monitoring station, a Beidou GNSS reference station, a three-axis tilt sensor and a server. The server obtains the building information of the building to be measured, wherein the building information includes the building outline and building geometry of the building to be measured; one or more deformation directions in which the building to be measured may be deformed are analyzed according to the building geometry; one or more Beidou GNSS monitoring stations are deployed along the deformation direction at the building outline; the Beidou GNSS reference station is deployed outside the building to be measured; the three-axis tilt sensor is deployed at the geometric center of the building to be measured according to the building geometry; the server collects Beidou GNSS data of the building to be measured in multiple deformation directions within a monitoring period, wherein the GNSS data source is obtained according to the measurement of the Beidou GNSS monitoring station relative to the GNSS reference station in the deformation direction. ; Extract the significant change characteristics of each deformation direction within the monitoring time; classify at least one of the Beidou GNSS data as stable data and at least one of the Beidou GNSS data as unstable data according to the significant change characteristics; select a first neural network model corresponding to the unstable data, and obtain the expected complex deformation data of the unstable data through the first neural network model; calculate the general simple deformation data of the stable data; select a second neural network model, and obtain the comprehensive building deformation of at least one of the expected complex deformation data and at least one of the general simple deformation data through the second neural network model; verify the comprehensive building deformation through the three-axis tilt data of the three-axis tilt sensor.

[0060] This embodiment discloses a computer device.

[0061] Figure 3 A schematic diagram of the structure of a computer device.

[0062] Figure 3 The computer device is shown to include: at least one processor, at least one memory, a power supply, a communication interface, an input / output interface, and a communication bus. The memory is used to store a computer program, and the computer program is loaded and executed by the processor to implement the relevant steps in the monitoring method disclosed in any of the above embodiments.

[0063] In this embodiment, the power supply is used to provide working voltage for each hardware device on the electronic device; the communication interface can create a data transmission channel between the electronic device and the external device, and the communication protocol it follows is any communication protocol that can be applied to the technical solution of this application, and is not specifically limited here; the input and output interface is used to obtain external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs, and is not specifically limited here. The memory, as a carrier for resource storage, can be a read-only memory, a random access memory, a disk or an optical disk, etc. The resources stored thereon can include an operating system, a computer program, etc., and the storage method can be short-term storage or permanent storage. The operating system is used to manage and control various hardware devices and computer programs on the electronic device, which can be Windows Server, Netware, Unix, Linux, etc. In addition to including a computer program that can be used to complete the monitoring method performed by the electronic device disclosed in any of the aforementioned embodiments, the computer program can further include a computer program that can be used to complete other specific tasks.

[0064] This embodiment discloses a computer-readable storage medium. The storage medium is used to store a computer program; wherein, when the computer program is executed by a processor, the aforementioned disclosed monitoring method is implemented. For the specific steps of the monitoring method, reference may be made to the corresponding contents disclosed in the aforementioned embodiment, and no further description will be given here.

[0065] Through the above description of the implementation method, technical personnel in the relevant field can clearly understand that the present invention can be implemented with the help of software and necessary general-purpose hardware, and of course can also be implemented through hardware, but in many cases the former is a better implementation method.

[0066] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention is described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A building deformation monitoring method based on Beidou GNSS and three-axis tilt sensor, characterized in that: The monitoring method comprises: Acquire building information of the building to be tested, wherein the building information includes the building outline and building geometry of the building to be tested; Analyzing one or more deformation directions in which the building to be tested may deform according to the building geometry; Deploy one or more Beidou GNSS monitoring stations on the building outline along the deformation direction; Deploy a Beidou GNSS reference station outside the building to be tested; Deploy a three-axis tilt sensor at the geometric center of the building to be tested according to the building geometry; Collecting Beidou GNSS data of the building to be measured in multiple deformation directions within a monitoring time, wherein the GNSS data is obtained according to the measurement of the Beidou GNSS monitoring station relative to the GNSS reference station in the deformation direction; Extracting significant change characteristics of each deformation direction within the monitoring time; Classify at least one of the Beidou GNSS data as stable data and at least one of the Beidou GNSS data as unstable data according to the significant change characteristics; Selecting a first neural network model corresponding to the unstable data, and obtaining expected complex deformation data of the unstable data through monitoring by the first neural network model; Calculate and obtain general simple deformation data of the stable data; Selecting a second neural network model, and obtaining a comprehensive building deformation of at least one of the expected complex deformation data and at least one of the general simple deformation data through monitoring by the second neural network model; The comprehensive building deformation is verified by three-axis tilt data of the three-axis tilt sensor.

2. The building deformation monitoring method based on Beidou GNSS and three-axis tilt sensor according to claim 1 is characterized in that: The deformation direction is horizontal displacement, vertical displacement, vertical displacement, flexure or torsion.

3. The building deformation monitoring method based on Beidou GNSS and three-axis tilt sensor according to claim 2 is characterized in that: The significant change characteristics include a distance signal change of the Beidou GNSS monitoring station relative to the GNSS reference station; Extracting the significant change features includes: Performing a fast Fourier transform on the Beidou GNSS data within the monitoring time to obtain frequency domain data; Selecting at least one main frequency whose amplitude of the frequency domain data is greater than a threshold; The range signal variation is determined based on all of the dominant frequencies.

4. The building deformation monitoring method based on Beidou GNSS and three-axis tilt sensor according to claim 3 is characterized in that: Determining the distance signal change includes, Averaging all of the major frequencies into the distance signal changes.

5. The building deformation monitoring method based on Beidou GNSS and three-axis tilt sensor according to claim 3 is characterized in that: The classification of the non-stable data includes, The Beidou GNSS data corresponding to the distance signal change greater than or equal to a frequency threshold is selected as unstable data.

6. The building deformation monitoring method based on Beidou GNSS and three-axis tilt sensor according to claim 4 is characterized in that: The stability data described in the classification include, The Beidou GNSS data corresponding to the distance signal change that is less than the frequency threshold is selected as stable data.

7. The building deformation monitoring method based on Beidou GNSS and three-axis tilt sensor according to claim 1 is characterized in that: The first neural network model is a BP neural network model; The second neural network model is a RBF neural network model.

8. A building deformation monitoring device based on Beidou GNSS and three-axis tilt sensor, characterized in that: include: Beidou GNSS monitoring station, Beidou GNSS reference station, three-axis tilt sensor and server; The server obtains building information of the building to be tested, wherein the building information includes the building outline and building geometry of the building to be tested; Analyzing one or more deformation directions in which the building to be tested may deform according to the building geometry; One or more Beidou GNSS monitoring stations are deployed along the deformation direction at the building outline; The Beidou GNSS reference station is deployed outside the building to be tested; The three-axis tilt sensor is deployed at the geometric center of the building to be measured according to the building geometry; The server collects Beidou GNSS data of the building to be tested in multiple deformation directions within a monitoring period, wherein the GNSS data source is obtained according to the measurement of the Beidou GNSS monitoring station relative to the GNSS reference station in the deformation direction; Extracting significant change characteristics of each deformation direction within the monitoring time; Classify at least one of the Beidou GNSS data as stable data and at least one of the Beidou GNSS data as unstable data according to the significant change characteristics; select a first neural network model corresponding to the unstable data, and obtain the expected complex deformation data of the unstable data through monitoring by the first neural network model; Calculate and obtain general simple deformation data of the stable data; select a second neural network model, and monitor and obtain the comprehensive building deformation of at least one of the expected complex deformation data and at least one of the general simple deformation data through the second neural network model; verify the comprehensive building deformation through the three-axis tilt data of the three-axis tilt sensor.

9. A computer device, characterized in that: The computer device includes a processor and a memory: the memory is used to store a computer program and transmit the computer program to the processor; the processor is used to execute the building deformation monitoring method based on Beidou GNSS and a three-axis tilt sensor according to any one of claims 1 to 7 according to the instructions in the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium is used to store a computer program, and when the computer program is executed by a processor, it is used to implement the building deformation monitoring method based on Beidou GNSS and a three-axis tilt sensor as described in any one of claims 1 to 7.

Images