A deformation monitoring method and system

Abstract

The present invention provides a deformation monitoring method and system, including: initially calculating the three-dimensional displacement change amount of a monitoring object at a monitoring station; performing deformation trend analysis based on the initial calculation results at each time point to obtain deformation trend information; judging whether it is necessary to trigger an alarm mechanism according to the initial calculation results and the deformation trend information; if the alarm mechanism is triggered, the data center starts high-precision calculation, performs high-precision calculation through the variational Bayesian method to obtain high-precision calculation results, and performs satellite integrity monitoring and interference detection through RAIM; judging whether it is necessary to continue triggering the alarm mechanism according to the value of the high-precision calculation results and the deformation trend information. The present invention realizes a rapid response to the deformation situation of the monitoring object through real-time initial calculation and deformation trend analysis at the monitoring station; combined with high-precision calculation in the data center, the variational Bayesian method is used to improve the calculation accuracy, ensuring the real-time performance, accuracy and reliability of deformation monitoring.

Description

Technical Field

[0001] The present invention relates to the technical field of deformation monitoring, and particularly relates to a deformation monitoring method and system. Background Art

[0002] The application of deformation monitoring technology is becoming more and more extensive in various fields, such as building structure safety monitoring, geological disaster early warning, bridge health monitoring, etc. The core of deformation monitoring technology lies in accurately and real-time obtaining the displacement change information of the monitoring object, so as to timely discover and warn potential safety risks.

[0003] Traditional deformation monitoring methods, such as using professional monitoring equipment or manual inspections, although can meet the requirements of deformation monitoring to a certain extent, have many limitations. Especially in high-precision calculation, traditional technologies face many challenges.

[0004] First of all, traditional deformation monitoring methods often rely on ground monitoring equipment. Although these equipment can collect deformation data, they have deficiencies in high-precision calculation. The data collected by ground monitoring equipment may be affected by factors such as environmental interference and equipment accuracy limitations, resulting in errors in the calculation results.

[0005] Secondly, traditional deformation monitoring methods often transmit all data to the data center or server for unified processing, which will lead to large data transmission volume and high processing delay in large-scale monitoring scenarios. Especially when the number of monitoring stations is large, the processing pressure on the data center will increase significantly, thus affecting the real-time and accuracy of monitoring.

[0006] In addition, traditional deformation monitoring methods usually only focus on a single deformation result and lack in-depth analysis of the deformation trend. This results in the system being unable to early warn potential deformation risks and can only react after the deformation occurs, missing the best intervention opportunity. Summary of the Invention

[0007] Based on this, the purpose of the present invention is to propose a deformation monitoring method and system to solve the above-mentioned problems.

[0008] According to a deformation monitoring method proposed by the present invention, the method includes:

[0009] Based on the original observation data set X collected by the reference station and the preliminary observation data set Y collected by the monitoring station within the time interval T, the three-dimensional displacement change amount of the monitoring object is preliminarily calculated at the monitoring station end to obtain a preliminary calculation result ΔY;

[0010] Based on the preliminary calculation results at each time point at the monitoring station end, deformation trend analysis is carried out to obtain deformation trend information;

[0011] At the monitoring station end, based on the preliminary solution result ΔY and the deformation trend information, determine whether it is necessary to trigger the alarm mechanism;

[0012] If the alarm mechanism is triggered, start high-precision solution through the data center. Combine the original observation data set X and the preliminary observation data set Y, and perform high-precision solution through the variational Bayesian method to obtain the high-precision solution result ΔY*. During high-precision solution, judge the health status of the satellite through RAIM satellite integrity monitoring, and judge whether the satellite signal is interfered through interference detection to exclude abnormal positioning accuracy caused by satellite failures or signal interference;

[0013] Based on the value of the high-precision solution result ΔY* and the deformation trend information, judge whether it is necessary to continue to trigger the alarm mechanism.

[0014] Furthermore, before the step of performing a preliminary solution on the three-dimensional displacement change amount of the monitoring object at the monitoring station end based on the original observation data set X collected by the reference station and the preliminary observation data set Y collected by the monitoring station within the time interval T to obtain the preliminary solution result ΔY, the following steps are also included:

[0015] Collect the original observation data through the reference station receiver at a preset frequency;

[0016] Send the original observation data of the reference station to the data center to form the original observation data set X, and forward it to the monitoring station receiver through the data center;

[0017] Receive the original observation data set X through the monitoring station receiver, collect the preliminary observation data at a preset frequency, and save it in the memory as the original observation data set Y.

[0018] Furthermore, the step of performing a preliminary solution on the three-dimensional displacement change amount of the monitoring object at the monitoring station end to obtain the preliminary solution result ΔY includes:

[0019] Establish the observation equation as:

[0020] ,

[0021] where x i and y i are the original observation data and the preliminary observation data of the reference station and the monitoring station at time i respectively, f is the observation model, is the observation noise, ΔY = [ΔY x , ΔY y , ΔY z is the preliminary solution result of the three-dimensional displacement change of the monitoring object;

[0022] Linearize the nonlinear model to obtain the linear observation equation as:

[0023] ,

[0024] where A i is the design matrix and b i is the constant term;

[0025] Construct the least - squares objective function J(ΔY) as:

[0026] ,

[0027] Solve for the preliminary solution result ΔY that minimizes J(ΔY):

[0028] ,

[0029] where A is the stack of the design matrix, A T is the transpose of the design matrix A, B is the stack of the constant terms, and Y is the stack of the preliminary observation data.

[0030] Furthermore, the step of performing deformation trend analysis based on the preliminary solution result at each time point to obtain deformation trend information includes:

[0031] Perform a difference calculation on the preliminary solution result ΔY of the three - dimensional displacement change at each time point k k with respect to time to obtain the displacement change rate ΔY' at each time point k , and the calculation formula is:

[0032] , where T is the time interval;

[0033] Calculate the mean value and the standard deviation ;

[0034] According to the displacement change rate ΔY' at each time point k , the mean value of the displacement change rate and the standard deviation , judge the degree of abnormal deformation trend;

[0035] If , then it is determined that the deformation trend is normal;

[0036] If , then it is determined that there is a slight abnormal deformation trend;

[0037] If , then it is determined that there is a significant abnormal deformation trend;

[0038] If , then it is determined that there is a serious abnormal deformation trend;

[0039] Among them, θ1, θ2, and θ3 respectively represent the first abnormal deformation trend threshold, the second abnormal deformation trend threshold, and the third abnormal deformation trend threshold, and θ1 < θ2 < θ3.

[0040] Furthermore, the step of judging whether to trigger the alarm mechanism according to the preliminary calculation result ΔY and the deformation trend information includes:

[0041] If the preliminary calculation results ΔY within the time interval T are all within the first threshold range and the deformation trend information does not indicate an abnormal deformation trend, then send the preliminary calculation result ΔY to the data center and store it;

[0042] If any preliminary calculation result ΔY within the time interval T exceeds the first threshold range, or the deformation trend information indicates an abnormal deformation trend, then the monitoring station side no longer performs the preliminary calculation of the three-dimensional displacement, uploads the set of preliminary observation data Y saved in the memory to the data center, uploads the early warning / alarm information according to the threshold, and simultaneously uploads the subsequent preliminary observation data to the data center in real time;

[0043] After the step of judging whether to trigger the alarm mechanism according to the preliminary calculation result ΔY and the deformation trend information, it further includes:

[0044] If the alarm mechanism is not triggered, then receive the preliminary calculation result ΔY through the data center, store the preliminary calculation result ΔY and record the status as normal, and as the time interval accumulates, form a set of preliminary calculation results.

[0045] Furthermore, the step of performing high-precision calculation through the variational Bayesian method by combining the cached original observation data set X and the received preliminary observation data set Y to obtain the high-precision calculation result ΔY* includes:

[0046] Construct a hierarchical probability model for representing the relationship between the original observation data X, the preliminary observation data Y, and the three-dimensional displacement change, so as to decompose the three-dimensional displacement change into a combination of different components;

[0047] Specify a prior distribution for each component respectively and perform joint inference;

[0048] Calculate the lower bound of the marginal likelihood according to the variational distribution and the observation data;

[0049] Adjust the parameters of the variational distribution through an optimization algorithm to maximize the lower bound of the marginal likelihood. During the optimization process, continuously update the variational distribution to make it gradually approach the true posterior distribution;

[0050] Repeat calculating the lower bound of the marginal likelihood and optimizing the variational distribution until the lower bound of the marginal likelihood converges, and extract the parameters of the variational distribution as the optimal high-precision calculation result ΔY*.

[0051] Further, the step of combining the original observation data set X and the preliminary observation data set Y and performing high-precision calculation through the variational Bayesian method to obtain the high-precision calculation result ΔY* further includes:

[0052] During the high-precision calculation process, a DRL optimization calculation strategy is introduced to dynamically adjust the original observation data upload time interval ΔT and the calculation time interval T_calc according to the current observation data, calculation result, deformation trend, and alarm level through the DRL model. At the same time, through continuous learning and optimization of the DRL model, it adapts to the dynamic changes of deformation monitoring.

[0053] Further, the step of dynamically adjusting the original observation data upload time interval ΔT and the calculation time interval T_calc includes:

[0054] Define the state space, including the current original observation data, preliminary observation data, high-precision calculation result solved by the variational Bayesian method, deformation trend, and alarm level;

[0055] Define the action space, including adjusting the original observation data upload time interval ΔT and the calculation time interval T_calc;

[0056] Select the optimal action according to the current state through the reinforcement learning model, obtain the reward according to the result after executing the action, and update the model parameters according to the reward. The results include calculation accuracy and real-time performance;

[0057] Through continuous interaction with the deformation monitoring system by the reinforcement learning model, learn to select the optimal action according to the current state and gradually optimize its strategy to adapt to the dynamic changes of deformation monitoring;

[0058] According to the output of the reinforcement learning model, dynamically adjust the original observation data upload time interval ΔT and the calculation time interval T_calc, so that when the deformation trend is stable, the deformation monitoring system appropriately extends ΔT and T_calc to reduce the data transmission and processing burden, or when the deformation trend is abnormal or the alarm level is high, appropriately shorten ΔT and T_calc to improve the monitoring accuracy and real-time performance.

[0059] Further, the step of judging whether it is necessary to continue to trigger the alarm mechanism according to the value of the high-precision calculation result ΔY* and the deformation trend information includes:

[0060] If the high-precision calculation result ΔY* is within the first threshold range and the deformation trend information does not indicate an abnormal deformation trend, store the high-precision calculation result ΔY* and record the state as normal. At the same time, feedback the normal state to the monitoring station side so that the monitoring station side stops uploading the warning / alarm signal and continues to obtain the preliminary observation data from the monitoring station;

[0061] If the high-precision calculation result ΔY* exceeds the first threshold range but does not reach the second threshold range, or the deformation trend information indicates a slight abnormal deformation trend, a low-risk early warning reminder is sent to the security personnel, and at the same time, high-precision calculation continues to track the deformation situation;

[0062] If the high-precision calculation result ΔY* exceeds the second threshold range but does not reach the third threshold range, or the deformation trend information indicates a significant abnormal deformation trend, a medium-risk alarm reminder is sent to the security personnel, and at the same time, high-precision calculation continues;

[0063] If the high-precision calculation result ΔY* exceeds the third threshold range, or the deformation trend information indicates a severe abnormal deformation trend, a high-risk alarm reminder is sent to the security personnel, and at the same time, high-precision calculation continues to obtain more detailed deformation information.

[0064] The present invention also proposes a deformation monitoring system for implementing the above deformation monitoring method, and the system includes:

[0065] The preliminary calculation module: used to perform preliminary calculation on the three-dimensional displacement change of the monitoring object at the monitoring station end based on the original observation data set X collected by the reference station and the preliminary observation data set Y collected by the monitoring station within the time interval T, and obtain the preliminary calculation result ΔY;

[0066] The deformation trend analysis module: used to perform deformation trend analysis at the monitoring station end based on the preliminary calculation results at each time point to obtain deformation trend information;

[0067] The first alarm mechanism module: used to judge whether it is necessary to trigger the alarm mechanism at the monitoring station end according to the preliminary calculation result ΔY and the deformation trend information;

[0068] The high-precision calculation module: used to, if the alarm mechanism is triggered, start high-precision calculation through the data center, combine the original observation data set X and the preliminary observation data set Y, perform high-precision calculation through the variational Bayesian method to obtain the high-precision calculation result ΔY*, and during high-precision calculation, judge the health status of the satellite through RAIM satellite integrity monitoring and judge whether the satellite signal is interfered through interference detection to eliminate abnormal positioning accuracy caused by satellite failures or signal interference;

[0069] The second alarm mechanism module: used to judge whether it is necessary to continue to trigger the alarm mechanism according to the value of the high-precision calculation result ΔY* and the deformation trend information.

[0070] In summary, for the deformation monitoring method of the present invention, first, the monitoring station terminal performs a preliminary calculation of the three-dimensional displacement change amount on the collected preliminary observation data to quickly obtain the preliminary calculation result, providing a real-time preliminary judgment for deformation monitoring. Then, based on the preliminary calculation results at each time point, a deformation trend analysis is carried out, which can timely detect the deformation trend of the monitoring object and provide a basis for subsequent alarm judgment. At the monitoring station terminal, it also determines whether to trigger the alarm mechanism according to the preliminary calculation results and deformation trend information, realizing the real-time monitoring and early warning of the deformation situation.

[0071] When the alarm mechanism is triggered, the data center starts high-precision calculation, combines the original observation data and the preliminary observation data for in-depth analysis, and uses the variational Bayesian method to obtain the high-precision calculation result. This not only improves the accuracy of deformation monitoring, but also effectively eliminates the abnormal positioning accuracy caused by satellite failures or signal interference through RAIM satellite integrity monitoring and interference detection, ensuring the reliability of the high-precision calculation results.

[0072] Finally, according to the high-precision calculation results and deformation trend information, it is determined again whether to continue to trigger the alarm mechanism, realizing the continuous monitoring and accurate early warning of the deformation situation.

[0073] The deformation monitoring method proposed by the present invention realizes a rapid response to the deformation situation of the monitoring object through the real-time preliminary calculation and deformation trend analysis at the monitoring station terminal; combined with the high-precision calculation of the data center, the variational Bayesian method is used to improve the calculation accuracy, and at the same time, satellite failures or signal interference are excluded, which can ensure the real-time, accuracy and reliability of the deformation monitoring results, providing strong technical support for related fields such as engineering safety monitoring and geological disaster early warning.

[0074] The additional aspects and advantages of the present invention will be partially given in the following description, partially become obvious from the following description, or be understood through the embodiments of the present invention. Description of the Drawings

[0075] The above and / or additional aspects and advantages of the present invention will become obvious and easy to understand from the description of the embodiments in conjunction with the following drawings, where:

[0076] Figure 1 is a flowchart of a deformation monitoring method according to Embodiment 1 of the present invention;

[0077] Figure 2 is a system block diagram of a deformation monitoring system according to Embodiment 2 of the present invention. Detailed Embodiments

[0078] To facilitate the understanding of the present invention, the present invention will be described more comprehensively below with reference to the relevant drawings. Several embodiments of the present invention are shown in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, these embodiments are provided to make the disclosure of the present invention more thorough and comprehensive.

[0079] It should be noted that when an element is referred to as being "fixedly provided on" another element, it can be directly on the other element or there can also be an intermediate element. When an element is considered to be "connected" to another element, it can be directly connected to the other element or there may be an intermediate element at the same time. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are only for illustrative purposes.

[0080] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs. The terms used in the specification of the present invention herein are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0081] Embodiment 1: Please refer to Figure 1 , the present invention provides a deformation monitoring method, which includes steps S101 to S105:

[0082] S101, based on the set X of original observation data collected by the reference station and the set Y of preliminary observation data collected by the monitoring station within the time interval T, perform a preliminary calculation on the three-dimensional displacement change amount of the monitoring object at the monitoring station end to obtain a preliminary calculation result ΔY.

[0083] It should be noted that the preliminary calculation of this embodiment is performed at the monitoring station end. At the monitoring station end, based on the set X of original observation data collected by the reference station and the set Y of preliminary observation data collected by the monitoring station within the time interval T, a preliminary calculation is performed on the three-dimensional displacement change amount of the monitoring object to obtain a preliminary calculation result ΔY. The preliminary calculation result ΔY reflects the three-dimensional displacement change of the monitoring station within the time interval T. However, the accuracy of this result is affected by various factors, such as the accuracy of the observation data, the accuracy of the observation model, the noise level, etc. Therefore, the accuracy may not be sufficient, but it can be used for daily data monitoring in the case of no deformation, avoiding a large waste of computing power and resources. And the preliminary calculation result is the basis for subsequent deformation trend analysis and alarm mechanism triggering. It provides a preliminary estimate of the deformation state of the monitoring station and provides important input data for subsequent steps.

[0084] Before the preliminary calculation in this embodiment, the timely transmission and sharing of data among the reference station, the monitoring station, and the data center can be achieved through the following steps, providing a real-time data basis for deformation monitoring and analysis:

[0085] The reference station receiver acquires the original observation data x1, x2,..., x at a preset frequency. n The preset frequency is set according to the requirements of deformation monitoring and the performance of the equipment to ensure that sufficient deformation information can be captured. The acquired original observation data can include various types such as pseudorange and carrier phase.

[0086] The reference station sends the original observation data to the data center, forming the original observation data set X at the data center. At the same time, the data center forwards the original observation data set X to the monitoring station receiver, ensuring the timely transmission and sharing of data.

[0087] The monitoring station receiver receives the original observation data set X and acquires the preliminary observation data y1, y2,..., y at the same preset frequency as the reference station receiver. n And saves it as the original observation data set Y in the memory. These data reflect the deformation state of the monitoring station at the current moment.

[0088] Further optionally, the step of performing a preliminary calculation on the three-dimensional displacement change amount of the monitoring object at the monitoring station end to obtain the preliminary calculation result ΔY includes:

[0089] Establish the observation equation as:

[0090] ,

[0091] where x i and y i are the original observation data and the preliminary observation data of the reference station and the monitoring station at time i respectively, f is the observation model, is the observation noise, and ΔY = [ΔY x , ΔY y , ΔY z is the preliminary calculation result of the three-dimensional displacement change of the monitoring object;

[0092] Linearize the nonlinear model to obtain the linear observation equation as:

[0093] ,

[0094] where A i is the design matrix and b i is the constant term;

[0095] Construct the least squares objective function J(ΔY) as:

[0096] ,

[0097] Solve for the preliminary solution result ΔY that minimizes J(ΔY):

[0098] ,

[0099] where A is the stack of the design matrix, A T is the transpose of the design matrix A, B is the stack of constant terms, and Y is the stack of preliminary observation data.

[0100] It is understandable that by establishing the observation equation, linearizing the non-linear model, constructing the least squares objective function and solving it, the preliminary solution of the three-dimensional displacement change of the monitoring station is realized, enabling the monitoring station to accurately estimate the three-dimensional displacement change of the monitored object by using the preliminary observation data of the reference station and the monitoring station, facilitating the daily monitoring under the condition of no abnormal deformation, and also providing a basis for subsequent deformation trend analysis and triggering of the alarm mechanism.

[0101] where ΔY = [ΔY x , ΔY y , ΔY z in which ΔY x is the displacement change amount of the monitoring station in the X-axis direction, ΔY y is the displacement change amount of the monitoring station in the Y-axis direction, and ΔY z is the displacement change amount of the monitoring station in the Z-axis direction.

[0102] S102. At the monitoring station end, based on the preliminary solution results at each time point, perform deformation trend analysis to obtain deformation trend information.

[0103] It should be noted that the deformation trend can be identified by analyzing the change of the three-dimensional displacement change amount of the monitored object over time, and then it can be judged whether there is an abnormal deformation trend of the monitored object.

[0104] Further optionally, the step of performing deformation trend analysis based on the preliminary solution results at each time point to obtain deformation trend information includes:

[0105] Perform difference calculation on the change of the preliminary solution result ΔY k of the three-dimensional displacement change amount at each time point k over time to obtain the displacement change rate ΔY' k , and the calculation formula is:

[0106] , where T is the time interval;

[0107] Calculate the mean value and the standard deviation ;

[0108] According to the displacement change rate ΔY' at each time point k , the mean value of the displacement change rate and the standard deviation , judge the degree of the abnormal deformation trend;

[0109] If , it is determined that the deformation trend is normal;

[0110] If , it is determined that there is a slight abnormal deformation trend;

[0111] If , it is determined that there is a significant abnormal deformation trend;

[0112] If , it is determined that there is a serious abnormal deformation trend;

[0113] Among them, θ1, θ2, and θ3 respectively represent the first abnormal deformation trend threshold, the second abnormal deformation trend threshold, and the third abnormal deformation trend threshold, and θ1 < θ2 < θ3.

[0114] It can be understood that by performing differential calculation on the three-dimensional displacement change amount at each time point, the displacement change rate is obtained, thereby identifying the deformation trend of the monitoring object over time, which helps to understand the deformation law of the monitoring object in space and time. By calculating the difference between the displacement change rate at each time point and the mean value and comparing it with the standard deviation, it is judged whether the deformation trend is abnormal and the degree of abnormality according to the size of the difference. Through deformation trend analysis and abnormal deformation judgment, it provides a scientific basis for subsequent decisions such as whether to trigger the alarm mechanism and whether to perform high-precision calculation, which helps to make timely and accurate judgments during the deformation monitoring process and ultimately ensure the safety and stability of the monitoring object.

[0115] The mean value μ of the displacement change rate ΔY' and the standard deviation σ ΔY' are calculated as follows:

[0116] ,

[0117] ,

[0118] Among them, n is the number of time points within the time interval T.

[0119] S103. At the monitoring station end, judge whether it is necessary to trigger the alarm mechanism according to the preliminary calculation result ΔY and the deformation trend information.

[0120] It should be noted that, based on the preliminary calculation results ΔY and the deformation trend information, the monitoring station determines whether to trigger the alarm mechanism. If no abnormal deformation or abnormal deformation trend is found, the preliminary calculation results can be used as the final calculation results of the three-dimensional displacement change of the monitoring station, without triggering the alarm mechanism, thus avoiding the subsequent high-precision calculation process. This can not only ensure the calculation efficiency under normal circumstances but also reduce the dependence on the data center.

[0121] If an abnormal deformation or abnormal deformation trend is found, the monitoring station will trigger the alarm mechanism and notify the data center to start high-precision calculation through this mechanism. This process realizes the joint analysis and calculation of data between the monitoring station and the data center. Real-time preliminary calculation, deformation trend analysis, and early warning judgment are carried out at the monitoring station end, while the data center is responsible for high-precision calculation to track the deformation situation in real time after receiving the alarm to ensure the accuracy of the calculation results. This mechanism improves the sensitivity and accuracy of deformation monitoring, optimizes resource utilization, and ensures that high-precision calculation of the data center is only carried out when necessary, thus improving the overall calculation and deformation monitoring efficiency.

[0122] Further optionally, the step of determining whether to trigger the alarm mechanism according to the preliminary calculation results ΔY and the deformation trend information includes:

[0123] If the preliminary calculation results ΔY within the time interval T are all within the first threshold range and the deformation trend information does not indicate an abnormal deformation trend, the preliminary calculation results ΔY are sent to the data center for storage.

[0124] If any of the preliminary calculation results ΔY within the time interval T exceeds the first threshold range, or the deformation trend information indicates an abnormal deformation trend, the monitoring station will no longer perform the preliminary calculation of the three-dimensional displacement, upload the set of preliminary observation data Y saved in the memory to the data center, upload the warning / alarm information according to the threshold, and simultaneously upload the subsequent preliminary observation data to the data center in real time.

[0125] It can be understood that if the preliminary calculation results ΔY within the time interval T are all within the first threshold range and the deformation trend information does not indicate an abnormal deformation trend, that is, when the deformation of the monitoring object is normal or the deformation trend is normal, the preliminary calculation results ΔY are sent to the data center for storage as a record of the three-dimensional displacement change of the monitoring object during this time period. In this case, there is no need to trigger the alarm mechanism, thus avoiding the subsequent high-precision calculation process. This can not only ensure the calculation efficiency under normal circumstances but also reduce the dependence on the data center.

[0126] If any preliminary solution result ΔY within the time interval T exceeds the first threshold range, or the deformation trend information indicates an abnormal deformation trend, that is, when the monitored object shows abnormal deformation or an abnormal deformation trend (i.e., there is a potential deformation risk), the alarm mechanism is triggered in a timely manner. The monitoring station stops performing the preliminary solution of the three-dimensional displacement and uploads the set of preliminary observation data Y saved in the memory to the data center, providing data support for subsequent high-precision solutions. And according to the threshold, warning / alarm information is uploaded to the data center to remind the data center that the monitored object has abnormal deformation, and the subsequent preliminary observation data Y of the monitoring station a+1 ,Y a+2 ,…,Y a+n are also uploaded to the data center in real time, so that the data center can continuously perform high-precision solutions to track the deformation situation in real time, ensuring the sensitivity, accuracy, and continuity of deformation monitoring.

[0127] Further optionally, after the step of judging whether to trigger the alarm mechanism according to the preliminary solution result ΔY and the deformation trend information, it further includes:

[0128] If the alarm mechanism is not triggered, the preliminary solution result ΔY is received through the data center, the preliminary solution result ΔY is stored and the status is recorded as normal. As the time interval accumulates, a set of preliminary solution results is formed.

[0129] It can be understood that at the data center end, if the data center receives the preliminary solution result ΔY, it means that the alarm mechanism has not been triggered, that is, there is no abnormal deformation or abnormal deformation trend. The data center will store the preliminary solution result ΔY and record the status as normal. As the time interval accumulates, a set of preliminary solution results is formed, such as ΔY T1 ,ΔY T2 ,…,ΔY Tn 。At this time, the preliminary solution result can be used as the daily monitoring data of the three-dimensional displacement change of the monitored object, and high-precision solution is not required, which helps to optimize the monitoring process, improve the monitoring efficiency, and reduce unnecessary resource and computing power consumption.

[0130] S104, if the alarm mechanism is triggered, the data center starts high-precision solution. Combining the original observation data set X and the preliminary observation data set Y, high-precision solution is performed by the variational Bayesian method to obtain the high-precision solution result ΔY*. During high-precision solution, the health status of the satellite is judged by RAIM satellite integrity monitoring, and whether the satellite signal is interfered is judged by interference detection to exclude abnormal positioning accuracy caused by satellite faults or signal interference.

[0131] It should be noted that the preliminary solution result ΔY and the deformation trend information jointly determine whether to trigger the alarm mechanism. If the preliminary solution result shows that the deformation may exceed the first threshold range, or the deformation trend information indicates an abnormal deformation trend, the alarm mechanism is triggered. Once the alarm mechanism is triggered, the early warning / alarm information sent by the monitoring station will remind the data center to start the high-precision solution algorithm. Then, by combining the cached original observation data set X and the received preliminary observation data set, more refined data processing and higher-precision solution are carried out through the variational Bayesian method to obtain the high-precision solution result ΔY*, that is, the accurate three-dimensional displacement change amount, providing a more reliable result for deformation monitoring. The variational Bayesian method of this embodiment can approximate the complex posterior distribution by finding the optimal approximate probability distribution, which not only ensures the calculation efficiency but also improves the accuracy of the solution result as much as possible. Since this method can handle the uncertainty of parameters and latent variables and provides a more robust and reliable solution result through the modeling of uncertainty.

[0132] Before the high-precision solution, the cached original observation data set X and the received preliminary observation data set Y can be processed by the Kalman filter algorithm to reduce data noise.

[0133] At the same time, during the high-precision solution process, the RAIM technology is used to judge the health status of the satellites. RAIM is a technology for detecting anomalies in satellite navigation systems, which can identify and exclude the signals of faulty satellites, thereby improving the accuracy and reliability of positioning. Interference detection is also carried out to judge whether the satellite signals are affected by external interference. When performing high-precision solution, combining the RAIM and interference detection technologies can exclude the abnormal positioning accuracy caused by satellite failures or signal interference, thereby improving the accuracy and reliability of data processing.

[0134] Further optionally, the steps of combining the cached original observation data set X and the received preliminary observation data set Y and performing high-precision solution through the variational Bayesian method to obtain the high-precision solution result ΔY* include:

[0135] Construct a hierarchical probability model for representing the relationship between the original observation data X, the preliminary observation data Y, and the three-dimensional displacement change, so as to decompose the three-dimensional displacement change into a combination of different components;

[0136] Specify the prior distribution for each component respectively and perform joint inference;

[0137] Calculate the lower bound of the marginal likelihood according to the variational distribution and the observation data;

[0138] Adjust the parameters of the variational distribution through an optimization algorithm to maximize the lower bound of the marginal likelihood. During the optimization process, continuously update the variational distribution to make it gradually approach the true posterior distribution;

[0139] Repeatedly calculate the lower bound of the marginal likelihood and optimize the variational distribution until the lower bound of the marginal likelihood converges, and extract the parameters of the variational distribution as the optimal high-precision solution result ΔY*.

[0140] It can be understood that by constructing a hierarchical probability model representing the relationship between the original observed data X, the preliminary observed data Y, and the three-dimensional displacement change, the complex three-dimensional displacement change can be decomposed into a combination of different components (such as trend terms, periodic terms, noise terms). This decomposition helps to more clearly understand the source and characteristics of the displacement change.

[0141] Specify prior distributions for each component and perform joint inference, which can simultaneously consider the influence of all components on the observed data, that is, comprehensively consider all factors that may affect the observed data, thereby improving the accuracy and reliability of the solution.

[0142] According to the variational distribution and the observed data, calculate the lower bound of the marginal likelihood as the objective function for optimization. Adjust the parameters of the variational distribution through optimization algorithms (such as gradient descent, coordinate ascent, etc.) to maximize the lower bound of the marginal likelihood. This process continuously optimizes the variational distribution to gradually approach the true posterior distribution, thereby improving the accuracy of the solution. Repeatedly calculate the lower bound of the marginal likelihood and optimize the variational distribution until the lower bound of the marginal likelihood converges, and then extract the parameters of the variational distribution as the optimal high-precision solution result ΔY*, thus realizing a high-precision and high-efficiency solution process and ensuring the accuracy and reliability of the solution result.

[0143] Further optionally, the step of combining the original observed data set X and the preliminary observed data set Y and performing high-precision solution through the variational Bayesian method to obtain the high-precision solution result ΔY* further includes:

[0144] During the high-precision solution process, introduce a DRL optimization solution strategy to dynamically adjust the original observed data upload time interval ΔT and the solution time interval T_calc according to the current observed data, solution result, deformation trend, and alarm level through the DRL model. At the same time, through the continuous learning and optimization of the DRL model, adapt to the dynamic changes of deformation monitoring.

[0145] It can be understood that once the alarm mechanism is triggered, the data center will start the high-precision solution process, perform high-precision solution through the variational Bayesian method to obtain the high-precision solution result ΔY*, make full use of the existing observed data, improve the accuracy of the solution, and provide a more reliable result for deformation monitoring.

[0146] Meanwhile, during the high-precision solution process, DRL (Deep Reinforcement Learning) is introduced to optimize the solution strategy. The DRL model can dynamically adjust the upload time interval ΔT of the original observation data and the solution time interval T_calc according to the current observation data, the high-precision solution results obtained by the variational Bayesian method, the deformation trend, and the alarm level. This dynamic adjustment mechanism enables the system to flexibly adjust the time intervals of data transmission and processing according to the real-time requirements of deformation monitoring, thereby improving the real-time performance of the system while ensuring the accuracy of the solution.

[0147] Further optionally, the steps of dynamically adjusting the upload time interval ΔT of the original observation data and the solution time interval T_calc include:

[0148] Define the state space, including the current original observation data, preliminary observation data, high-precision solution results obtained by the variational Bayesian method, deformation trend, and alarm level, etc.;

[0149] Define the action space, including adjusting the upload time interval ΔT of the original observation data and the solution time interval T_calc;

[0150] Through the reinforcement learning model, select the optimal action according to the current state, obtain the reward according to the result after executing the action, and update the model parameters according to the reward. The results include the solution accuracy and real-time performance;

[0151] Through continuous interaction with the deformation monitoring system by the reinforcement learning model, learn to select the optimal action according to the current state, and gradually optimize its strategy to adapt to the dynamic changes of deformation monitoring;

[0152] According to the output of the reinforcement learning model, dynamically adjust the upload time interval ΔT of the original observation data and the solution time interval T_calc, so that the deformation monitoring system appropriately extends ΔT and T_calc when the deformation trend is stable to reduce the data transmission and processing burden, or appropriately shortens ΔT and T_calc when the deformation trend is abnormal or the alarm level is high to improve the monitoring accuracy and real-time performance.

[0153] It can be understood that during the high-precision solution process, DRL is introduced to optimize the solution strategy. The DRL model can dynamically adjust the upload time interval ΔT of the original observation data and the solution time interval T_calc according to the current observation data, the high-precision solution results obtained by the variational Bayesian method, the deformation trend, and the alarm level. This dynamic adjustment mechanism enables the system to flexibly adjust the time intervals of data transmission and processing according to the real-time requirements of deformation monitoring, thereby improving the real-time performance of the system while ensuring the accuracy of the solution.

[0154] Through the dynamic adjustment of the DRL model, when the deformation trend is stable, the system can appropriately extend the upload time interval and calculation time interval of the original observation data, reduce the data transmission and processing burden, and improve the system efficiency. When the deformation trend is abnormal or the alarm level is high, the system can shorten the time interval, obtain and process the observation data in a timely manner, improve the accuracy and real-time performance of the calculation, and ensure the timeliness and reliability of deformation monitoring.

[0155] Since the DRL model has the ability to continuously learn and optimize. Through continuous interaction with the deformation monitoring system, the DRL model can gradually optimize its decision-making strategy to adapt to the dynamic changes of deformation monitoring. This learning and optimization mechanism enables the system to better handle various complex and changing deformation monitoring scenarios, improve the robustness and adaptability of the system, and ensure that the system can work stably and accurately in different environments.

[0156] S105. According to the value of the high-precision calculation result ΔY* and the deformation trend information, determine whether it is necessary to continue to trigger the alarm mechanism.

[0157] It should be noted that after high-precision calculation is performed in the data center to obtain the high-precision calculation result, more accurate deformation trend analysis is carried out based on the high-precision calculation result ΔY* to obtain the deformation trend information, and according to the value of the high-precision calculation result ΔY* and the deformation trend information, determine whether it is necessary to continue to trigger the alarm mechanism. Specifically, according to different deformation degrees or different degrees of abnormal deformation trends, early warning or alarm reminders can be automatically sent to ensure that security personnel can take measures in a timely manner. Regardless of the deformation degree, the system continues to perform high-precision calculation to obtain more accurate deformation information and trends.

[0158] Further optionally, the step of determining whether it is necessary to continue to trigger the alarm mechanism according to the value of the high-precision calculation result ΔY* and the deformation trend information includes:

[0159] If the high-precision calculation result ΔY* is within the first threshold range and the deformation trend information does not indicate an abnormal deformation trend, store the high-precision calculation result ΔY* and record the status as normal, and at the same time feedback the normal status to the monitoring station terminal, so that the monitoring station terminal stops uploading the early warning / alarm signal and continues to obtain the preliminary observation data from the monitoring station;

[0160] If the high-precision calculation result ΔY* exceeds the first threshold range but does not reach the second threshold range, or the deformation trend information indicates a slight abnormal deformation trend, send a low-risk early warning reminder to the security personnel, and at the same time continue to perform high-precision calculation to track the deformation situation;

[0161] If the high-precision solution result ΔY* exceeds the second threshold range but does not reach the third threshold range, or the deformation trend information indicates a significant abnormal deformation trend, a medium-risk alarm reminder is sent to the security personnel, and high-precision calculation continues;

[0162] If the high-precision solution result ΔY* exceeds the third threshold range, or the deformation trend information indicates a severe abnormal deformation trend, a high-risk alarm reminder is sent to the security personnel, and high-precision calculation continues to obtain more detailed deformation information.

[0163] The following is a specific implementation of a deformation monitoring method of the present invention, which is as follows:

[0164] The reference station receiver acquires the original observation data x1, x2,..., x at a preset frequency n ;

[0165] The original observation data of the reference station is sent to the data center to form an original observation data set X = {x1, x2,..., x n}, and is forwarded to the monitoring station receiver through the data center;

[0166] The monitoring station receiver receives the original observation data set X and acquires the preliminary observation data y1, y2,..., y at a preset frequency n , and stores it in the memory as the original observation data set Y = {y1, y2,..., y n};

[0167] Based on the original observation data set X collected by the reference station and the preliminary observation data set Y collected by the monitoring station within the time interval T, the three-dimensional displacement change of the monitoring object is preliminarily calculated at the monitoring station end to obtain a preliminary calculation result ΔY;

[0168] Based on the preliminary calculation results at each time point, deformation trend analysis is performed to obtain deformation trend information;

[0169] Combined with the deformation trend information and the preset threshold range, it is judged whether to trigger the alarm mechanism:

[0170] If the preliminary calculation result ΔY within the time interval T is within the first threshold range and the deformation trend information does not indicate an abnormal deformation trend, the preliminary calculation result ΔY is sent to the data center for storage;

[0171] If any preliminary calculation result ΔY within the time interval T exceeds the first threshold range, or the deformation trend information indicates an abnormal deformation trend, the monitoring station end no longer performs the preliminary calculation of three-dimensional displacement, uploads the preliminary observation data set Y saved in the memory to the data center, and uploads the early warning / alarm information according to the threshold. At the same time, the subsequent preliminary observation data Y a+1, Y a+2 , …, Y a+n are also uploaded to the data center in real time;

[0172] If the data center receives the preliminary solution result ΔY, it stores the preliminary solution result ΔY and records the status as normal, and forms a set of preliminary solution results containing ΔY with the accumulation of time intervals T1 , ΔY T2 , …, ΔY Tn ;

[0173] If the data center receives a warning / alert message and the set of preliminary observation data Y, it starts high-precision solution through the data center, uses the variational Bayesian algorithm, and combines the original observation data set X and the set of preliminary observation data Y for high-precision solution to obtain the high-precision solution result ΔY*, that is, the accurate three-dimensional displacement change;

[0174] During the high-precision solution process, deep reinforcement learning (DRL) is introduced to optimize the solution strategy. The DRL model dynamically adjusts the time interval ΔT for uploading the original observation data and the solution time interval T_calc according to the current observation data, solution results, deformation trend, and alarm level to improve the accuracy and real-time performance of the solution, and adapts to the dynamic changes of deformation monitoring through continuous learning and optimization to improve the robustness and adaptability of the system;

[0175] And during high-precision solution, it is necessary to judge the health status of the satellite through RAIM satellite integrity monitoring and judge whether the satellite signal is interfered through interference detection to exclude abnormal positioning accuracy caused by satellite faults or signal interference;

[0176] After judging and excluding interference and other situations, more accurate deformation trend analysis is carried out according to the high-precision solution result ΔY*, and deformation trend information is obtained, and whether to continue to trigger the alarm mechanism is judged according to the value of the high-precision solution result ΔY* and the deformation trend information;

[0177] If the high-precision solution result ΔY* is within the first threshold range and the deformation trend information does not indicate an abnormal deformation trend, the data center stores the high-precision solution result ΔY* and records the status as normal, and at the same time feeds back the normal status to the monitoring station end so that the monitoring station end stops uploading warning / alert signals and continues to obtain preliminary observation data from the monitoring station;

[0178] If the high-precision solution result ΔY* exceeds the first threshold range but does not reach the second threshold range, or the deformation trend information indicates a slight abnormal deformation trend, a low-risk warning reminder is sent to the security personnel, and at the same time, high-precision solution continues to track the deformation situation;

[0179] If the high-precision solution result ΔY* exceeds the second threshold range but does not reach the third threshold range, or the deformation trend information indicates a significant abnormal deformation trend, a medium-risk alarm reminder is sent to the security personnel, and the high-precision solution is continued at the same time;

[0180] If the high-precision solution result ΔY* exceeds the third threshold range, or the deformation trend information indicates a serious abnormal deformation trend, a high-risk alarm reminder is sent to the security personnel, and the high-precision solution is continued at the same time to obtain more detailed deformation information.

[0181] In summary, for the deformation monitoring method of the present invention, first, the monitoring station terminal performs a preliminary solution of the three-dimensional displacement change amount on the collected preliminary observation data, quickly obtains the preliminary solution result, and provides a real-time preliminary judgment for deformation monitoring. Then, based on the preliminary solution results at each time point, deformation trend analysis is carried out, which can timely detect the deformation trend of the monitoring object and provide a basis for subsequent alarm judgment. At the monitoring station terminal, it is also determined whether to trigger the alarm mechanism according to the preliminary solution results and deformation trend information, realizing real-time monitoring and early warning of the deformation situation.

[0182] When the alarm mechanism is triggered, high-precision solution is started through the data center, and in-depth analysis is carried out by combining the original observation data and the preliminary observation data. The high-precision solution result is obtained by using the variational Bayesian method. It not only improves the accuracy of deformation monitoring, but also effectively eliminates the abnormal positioning accuracy caused by satellite faults or signal interference through RAIM satellite integrity monitoring and interference detection, ensuring the reliability of the high-precision solution result.

[0183] Finally, according to the high-precision solution result and the deformation trend information, it is determined again whether to continue to trigger the alarm mechanism, realizing continuous monitoring and accurate early warning of the deformation situation.

[0184] The deformation monitoring method proposed by the present invention realizes a rapid response to the deformation situation of the monitoring object through real-time preliminary solution and deformation trend analysis at the monitoring station terminal; combined with the high-precision solution of the data center, the variational Bayesian method is used to improve the solution accuracy, and at the same time satellite faults or signal interference are excluded, which can ensure the real-time, accuracy and reliability of the deformation monitoring results, and provide strong technical support for related fields such as engineering safety monitoring and geological disaster early warning.

[0185] Embodiment 2: Please refer to Figure 2 , a deformation monitoring system proposed by the present invention, the system includes:

[0186] Preliminary solution module: Used to perform a preliminary solution of the three-dimensional displacement change amount of the monitoring object at the monitoring station terminal based on the original observation data set X collected by the reference station and the preliminary observation data set Y collected by the monitoring station within the time interval T, and obtain the preliminary solution result ΔY;

[0187] Deformation trend analysis module: used to perform deformation trend analysis based on the preliminary solution results at each time point to obtain deformation trend information;

[0188] First alarm mechanism module: used to determine whether to trigger the alarm mechanism according to the preliminary solution result ΔY and the deformation trend information;

[0189] High-precision solution module: used to, if the alarm mechanism is triggered, start high-precision solution through the data center, combine the original observation data set X and the preliminary observation data set Y, and perform high-precision solution through the variational Bayesian method to obtain the high-precision solution result ΔY*. During high-precision solution, judge the health status of the satellite through RAIM satellite integrity monitoring, and judge whether the satellite signal is interfered through interference detection to exclude abnormal positioning accuracy caused by satellite failures or signal interference;

[0190] Second alarm mechanism module: used to determine whether to continue to trigger the alarm mechanism according to the value of the high-precision solution result ΔY* and the deformation trend information.

[0191] Further optionally, the preliminary solution module is further used for:

[0192] Collect and obtain the original observation data through the reference station receiver at a preset frequency;

[0193] Send the original observation data of the reference station to the data center to form the original observation data set X, and forward it to the monitoring station receiver through the data center;

[0194] Receive the original observation data set X through the monitoring station receiver, collect and obtain the preliminary observation data at a preset frequency, and save it as the original observation data set Y in the memory.

[0195] Further optionally, the preliminary solution module is further used for:

[0196] Establish the observation equation as:

[0197] ,

[0198] where x i and y i are respectively the original observation data and the preliminary observation data of the reference station and the monitoring station at time i, f is the observation model, is the observation noise, ΔY = [ΔY x , ΔY y , ΔY z is the preliminary solution result of the three-dimensional displacement change of the monitoring object;

[0199] Linearize the nonlinear model to obtain the linear observation equation as:

[0200] ,

[0201] Among them, A i is the design matrix, and b i is the constant term;

[0202] Construct the least squares objective function J(ΔY) as:

[0203] ,

[0204] Solve for the preliminary solution result ΔY that minimizes J(ΔY):

[0205] ,

[0206] Among them, A is the stack of the design matrix, and A T is the transpose of the design matrix A, B is the stack of the constant terms, and Y is the stack of the preliminary observation data.

[0207] Further optionally, the deformation trend analysis module is further configured to:

[0208] Perform a difference calculation on the preliminary solution result ΔY of the three-dimensional displacement change at each time point k k with respect to the change over time to obtain the displacement change rate ΔY' at each time point k , and the calculation formula is:

[0209] , where T is the time interval;

[0210] Calculate the mean value of the displacement change rate and the standard deviation ;

[0211] According to the displacement change rate ΔY' at each time point k , the mean value of the displacement change rate and the standard deviation , judge the degree of the abnormal deformation trend;

[0212] If , it is determined that the deformation trend is normal;

[0213] If , it is determined that there is a slight abnormal deformation trend;

[0214] If , it is determined that there is a significant abnormal deformation trend;

[0215] If , it is determined that there is a serious abnormal deformation trend;

[0216] Among them, θ1, θ2, and θ3 respectively represent the first abnormal deformation trend threshold, the second abnormal deformation trend threshold, and the third abnormal deformation trend threshold, and θ1 < θ2 < θ3.

[0217] Further optionally, the first alarm mechanism module is further configured to:

[0218] If the preliminary calculation results ΔY within the time interval T are all within the first threshold range and the deformation trend information does not indicate an abnormal deformation trend, send the preliminary calculation result ΔY to the data center for storage;

[0219] If any preliminary calculation result ΔY within the time interval T exceeds the first threshold range, or the deformation trend information indicates an abnormal deformation trend, the monitoring station side will no longer perform the preliminary calculation of the three-dimensional displacement, upload the preliminary observation data set Y saved in the memory to the data center, upload the warning / alarm information according to the threshold, and simultaneously upload the subsequent preliminary observation data to the data center in real time.

[0220] Further optionally, the first alarm mechanism module is further configured to:

[0221] If the alarm mechanism is not triggered, receive the preliminary calculation result ΔY through the data center, store the preliminary calculation result ΔY and record the status as normal, and form a set of preliminary calculation results as the time interval accumulates.

[0222] Further optionally, the high-precision calculation module is further configured to:

[0223] Construct a hierarchical probability model for representing the relationship between the original observation data X, the preliminary observation data Y, and the three-dimensional displacement change, so as to decompose the three-dimensional displacement change into a combination of different components;

[0224] Specify a prior distribution for each component and perform joint inference;

[0225] Calculate the lower bound of the marginal likelihood according to the variational distribution and the observation data;

[0226] Adjust the parameters of the variational distribution through an optimization algorithm to maximize the lower bound of the marginal likelihood. During the optimization process, continuously update the variational distribution to make it gradually approach the true posterior distribution;

[0227] Repeat calculating the lower bound of the marginal likelihood and optimizing the variational distribution until the lower bound of the marginal likelihood converges, and extract the parameters of the variational distribution as the optimal high-precision calculation result ΔY*.

[0228] Further optionally, the high-precision calculation module is further configured to:

[0229] During the high-precision calculation process, a DRL optimization calculation strategy is introduced to dynamically adjust the original observation data upload time interval ΔT and the calculation time interval T_calc according to the current observation data, calculation results, deformation trend, and alarm level through the DRL model. At the same time, through continuous learning and optimization of the DRL model, it adapts to the dynamic changes of deformation monitoring.

[0230] Further optionally, the high-precision calculation module is further configured to:

[0231] Define the state space, including the current original observation data, preliminary observation data, high-precision calculation results solved by the variational Bayesian method, deformation trend, and alarm level;

[0232] Define the action space, including adjusting the original observation data upload time interval ΔT and the calculation time interval T_calc;

[0233] Select the optimal action according to the current state through the reinforcement learning model, obtain the reward according to the result after executing the action, and update the model parameters according to the reward. The results include calculation accuracy and real-time performance;

[0234] Through continuous interaction with the deformation monitoring system by the reinforcement learning model, learn to select the optimal action according to the current state, and gradually optimize its strategy to adapt to the dynamic changes of deformation monitoring;

[0235] Dynamically adjust the original observation data upload time interval ΔT and the calculation time interval T_calc according to the output of the reinforcement learning model, so that the deformation monitoring system appropriately extends ΔT and T_calc when the deformation trend is stable to reduce the data transmission and processing burden, or appropriately shortens ΔT and T_calc when the deformation trend is abnormal or the alarm level is high to improve the monitoring accuracy and real-time performance.

[0236] Further optionally, the second alarm mechanism module is further configured to:

[0237] If the high-precision calculation result ΔY* is within the first threshold range and the deformation trend information does not indicate an abnormal deformation trend, store the high-precision calculation result ΔY* and record the status as normal. At the same time, feedback the normal status to the monitoring station side so that the monitoring station side stops uploading early warning / alarm signals and continues to obtain preliminary observation data from the monitoring station;

[0238] If the high-precision calculation result ΔY* exceeds the first threshold range but does not reach the second threshold range, or the deformation trend information indicates a slight abnormal deformation trend, send a low-risk early warning reminder to the security personnel, and at the same time continue with the high-precision calculation to track the deformation situation;

[0239] If the high-precision calculation result ΔY* exceeds the second threshold range but does not reach the third threshold range, or the deformation trend information indicates a significant abnormal deformation trend, a medium-risk alarm reminder is sent to the security personnel, and the high-precision calculation continues simultaneously.

[0240] If the high-precision calculation result ΔY* exceeds the third threshold range, or the deformation trend information indicates a severe abnormal deformation trend, a high-risk alarm reminder is sent to the security personnel, and the high-precision calculation continues simultaneously to obtain more detailed deformation information.

[0241] The above-described embodiments merely represent several implementation manners of the present invention. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the scope of the patent for the present invention. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent for the present invention shall be subject to the appended claims.

Claims

1. A deformation monitoring method, characterized in that: The method comprises: Based on the original observation data set X collected by the reference station within the time interval T and the preliminary observation data set Y collected by the monitoring station, the three-dimensional displacement change of the monitored object is preliminarily solved at the monitoring station to obtain a preliminary solution result ΔY; At the monitoring station, deformation trend analysis is performed based on the preliminary solution results at each time point to obtain deformation trend information; At the monitoring station, determine whether the alarm mechanism needs to be triggered based on the preliminary solution result ΔY and deformation trend information; If the alarm mechanism is triggered, high-precision solution is started through the data center. The original observation data set X and the preliminary observation data set Y are combined to perform high-precision solution through the variational Bayesian method to obtain the high-precision solution result ΔY*. During high-precision solution, the satellite health status is judged through RAIM satellite integrity monitoring, and interference detection is used to determine whether the satellite signal is interfered with, so as to eliminate positioning accuracy abnormalities caused by satellite failures or signal interference. A more accurate deformation trend analysis is performed based on the high-precision solution result ΔY* to obtain deformation trend information, and based on the value of the high-precision solution result ΔY* and its deformation trend information, it is determined whether the alarm mechanism needs to be triggered again.

2. The deformation monitoring method according to claim 1, characterized in that: The step of performing a preliminary calculation of the three-dimensional displacement variation of the monitored object at the monitoring station based on the original observation data set X collected by the reference station within the time interval T and the preliminary observation data set Y collected by the monitoring station to obtain the preliminary calculation result ΔY also includes: The original observation data is collected and acquired through the base station receiver at a preset frequency; The original observation data of the reference station is sent to the data center to form the original observation data set X, and then forwarded to the monitoring station receiver through the data center; The original observation data set X is received by the monitoring station receiver, and preliminary observation data is collected and obtained at a preset frequency, and saved in the memory as the original observation data set Y.

3. The deformation monitoring method according to claim 1, characterized in that: The step of performing a preliminary calculation on the three-dimensional displacement variation of the monitored object at the monitoring station to obtain a preliminary calculation result ΔY comprises: The observation equation is established as: ， Among them, x i and i are the original observation data and preliminary observation data of the base station and monitoring station at time i, respectively; f is the observation model, is the observation noise, ΔY=[ΔY x , ΔY y , ΔY z ] is the preliminary solution result of the three-dimensional displacement change of the monitored object; Linearize the nonlinear model and obtain the linear observation equation: ， Among them, A i is the design matrix, b i is a constant term; The least squares objective function J(ΔY) is constructed as: ， Find the preliminary solution ΔY that minimizes J(ΔY): ， where A is the stack of design matrices, A T is the transpose of the design matrix A, B is the stack of constant terms, and Y is the stack of preliminary observations.

4. The deformation monitoring method according to claim 1, characterized in that: The step of performing deformation trend analysis based on the preliminary solution results at each time point to obtain deformation trend information includes: The preliminary solution result ΔY of the three-dimensional displacement change at each time point k k The difference calculation is performed over time to obtain the displacement change rate ΔY' at each time point k , the calculation formula is: , where T is the time interval; Calculate the mean of the displacement change rate and standard deviation ; According to the displacement change rate ΔY' at each time point k , the mean of the displacement change rate and standard deviation , judge the degree of abnormal deformation trend; like , then the deformation trend is judged to be normal; like , it is determined that there is a slight abnormal deformation trend; like , then it is determined that there is a significant abnormal deformation trend; like , it is determined that there is a serious abnormal deformation trend; Among them, θ1, θ2, and θ3 represent the first abnormal deformation trend threshold, the second abnormal deformation trend threshold, and the third abnormal deformation trend threshold, respectively, and θ1<θ2<θ3.

5. The deformation monitoring method according to claim 1, characterized in that: The step of judging whether to trigger the alarm mechanism according to the preliminary solution result ΔY and the deformation trend information includes: If the preliminary solution results ΔY within the time interval T are all within the first threshold range, and the deformation trend information does not indicate an abnormal deformation trend, the preliminary solution results ΔY are sent to the data center and stored; If any preliminary solution result ΔY within the time interval T exceeds the first threshold range, or the deformation trend information indicates an abnormal deformation trend, the monitoring station will no longer perform the preliminary solution of the three-dimensional displacement, upload the preliminary observation data set Y stored in the memory to the data center, and upload the warning / alarm information according to the threshold, and upload the subsequent preliminary observation data to the data center in real time; After the step of judging whether to trigger the alarm mechanism according to the preliminary solution result ΔY and the deformation trend information, the following steps are further included: If the alarm mechanism is not triggered, the preliminary solution result ΔY is received through the data center, and the preliminary solution result ΔY is stored and the status is recorded as normal. As the time interval accumulates, a preliminary solution result set is formed.

6. The deformation monitoring method according to claim 1, characterized in that: The step of combining the original observation data set X and the preliminary observation data set Y and performing high-precision calculation by using the variational Bayesian method to obtain a high-precision calculation result ΔY* comprises: A hierarchical probability model is constructed to represent the relationship between the original observation data X, the preliminary observation data Y and the three-dimensional displacement change, so as to decompose the three-dimensional displacement change into a combination of different components; Specify prior distributions for each component and perform joint inference; Compute a lower bound on the marginal likelihood based on the variational distribution and the observed data; The parameters of the variational distribution are adjusted through the optimization algorithm to maximize the lower bound of the marginal likelihood. During the optimization process, the variational distribution is continuously updated to gradually approach the true posterior distribution. Repeatedly calculate the lower bound of the marginal likelihood and optimize the variational distribution until the lower bound of the marginal likelihood converges, and extract the parameters of the variational distribution as the optimal high-precision solution result ΔY*.

7. The deformation monitoring method according to claim 1, characterized in that: The step of combining the original observation data set X and the preliminary observation data set Y and performing high-precision calculation by using the variational Bayesian method to obtain a high-precision calculation result ΔY* also includes: In the high-precision solution process, the DRL optimization solution strategy is introduced to dynamically adjust the original observation data upload time interval ΔT and the solution time interval T_calc according to the current observation data, solution results, deformation trend and alarm level through the DRL model. At the same time, through the continuous learning and optimization of the DRL model, it can adapt to the dynamic changes of deformation monitoring.

8. The deformation monitoring method according to claim 7, characterized in that: The step of dynamically adjusting the original observation data uploading time interval ΔT and the calculation time interval T_calc comprises: Define the state space, including the current raw observation data, preliminary observation data, high-precision solution results obtained by the variational Bayesian method, deformation trends, and alarm levels; Define the action space, including adjusting the original observation data upload time interval ΔT and the solution time interval T_calc; The reinforcement learning model selects the best action based on the current state, obtains rewards based on the results after executing the action, and updates the model parameters based on the rewards. The results include solution accuracy and real-time performance. Through the continuous interaction with the deformation monitoring system, the reinforcement learning model learns to select the optimal action according to the current state and gradually optimizes its strategy to adapt to the dynamic changes of deformation monitoring. According to the output of the reinforcement learning model, the original observation data upload time interval ΔT and the solution time interval T_calc are dynamically adjusted so that the deformation monitoring system can appropriately extend ΔT and T_calc when the deformation trend is stable to reduce the data transmission and processing burden, or appropriately shorten ΔT and T_calc when the deformation trend is abnormal or the alarm level is high to improve the monitoring accuracy and real-time performance.

9. The deformation monitoring method according to claim 1, characterized in that: The step of performing a more accurate deformation trend analysis based on the high-precision solution result ΔY* to obtain deformation trend information, and judging whether to continue to trigger the alarm mechanism based on the value of the high-precision solution result ΔY* and its deformation trend information includes: If the high-precision solution result ΔY* is within the first threshold range and the deformation trend information does not indicate an abnormal deformation trend, the high-precision solution result ΔY* is stored and the state is recorded as normal, and the normal state is fed back to the monitoring station end, so that the monitoring station end stops uploading the early warning / alarm signal and continues to obtain preliminary observation data from the monitoring station; If the high-precision solution result ΔY* exceeds the first threshold range but does not reach the second threshold range, or the deformation trend information indicates a slight abnormal deformation trend, a low-risk warning reminder is sent to the security personnel, and high-precision solution is continued to track the deformation situation; If the high-precision solution result ΔY* exceeds the second threshold range but does not reach the third threshold range, or the deformation trend information indicates a significant abnormal deformation trend, a medium-risk alarm reminder is sent to the security personnel, and the high-precision solution continues; If the high-precision solution result ΔY* exceeds the third threshold range, or the deformation trend information indicates a serious abnormal deformation trend, a high-risk alarm reminder is sent to the security personnel, and high-precision solution is continued to obtain more detailed deformation information.

10. A deformation monitoring system, used to implement the deformation monitoring method according to any one of claims 1 to 9, characterized in that: The system comprises: Preliminary solution module: used to perform preliminary solution on the three-dimensional displacement change of the monitored object at the monitoring station end based on the original observation data set X collected by the reference station within the time interval T and the preliminary observation data set Y collected by the monitoring station, and obtain the preliminary solution result ΔY; Deformation trend analysis module: used to perform deformation trend analysis based on the preliminary solution results at each time point at the monitoring station to obtain deformation trend information; The first alarm mechanism module is used to determine whether the alarm mechanism needs to be triggered based on the preliminary solution result ΔY and deformation trend information at the monitoring station; High-precision solution module: If the alarm mechanism is triggered, the high-precision solution is started through the data center. The original observation data set X and the preliminary observation data set Y are combined to perform high-precision solution through the variational Bayesian method to obtain the high-precision solution result ΔY*. During the high-precision solution, the satellite health status is judged through RAIM satellite integrity monitoring, and the satellite signal is judged through interference detection to eliminate the positioning accuracy abnormality caused by satellite failure or signal interference. The second alarm mechanism module is used to perform a more accurate deformation trend analysis based on the high-precision solution result ΔY*, obtain deformation trend information, and determine whether it is necessary to continue to trigger the alarm mechanism based on the value of the high-precision solution result ΔY* and its deformation trend information.

Images