Landslide displacement monitoring method, system and equipment and storage medium

Abstract

The embodiment of the invention discloses a landslide displacement monitoring method, system and device, and a storage medium, and aims at minimizing the total mean square error, and can adaptively find an optimal weighting factor corresponding to each piece of landslide displacement data, so that the fused data value is optimal. According to the optimization method, the error difference between the landslide displacement data can be fully considered, so that a more accurate and reliable data fusion result is obtained, and therefore, the first weighting factor of each landslide displacement data is utilized to carry out weighted fusion on all the landslide displacement data to obtain the landslide displacement deformation data of the landslide displacement monitoring point; the landslide displacement deformation data can comprehensively and effectively judge the landslide deformation stage, and the landslide deformation stage is closer to the real condition of landslide deformation.

Description

[Technical field]

[0001] The present invention relates to the technical field of landslide prediction, and in particular to a method, system, equipment and storage medium for monitoring landslide displacement. [Background technology]

[0002] In geological disaster monitoring and analysis, the most important thing is to discriminate the deformation stage of landslides. However, in practical applications, simply comparing and analyzing the data collected at each monitoring point cannot fully utilize the information of these data, and thus cannot realize the monitoring of the real situation of landslides. [Summary of the invention]

[0003] In view of this, the present invention provides a landslide displacement monitoring method, system, device and storage medium.

[0004] The specific technical scheme of the first embodiment of the present invention is: a method for monitoring landslide displacement, the method comprising: obtaining landslide monitoring data of a landslide displacement monitoring point; the landslide monitoring data comprises landslide displacement data obtained by monitoring the landslide displacement monitoring point with different displacement sensors; obtaining a total mean square error of all landslide displacement data; obtaining a first weighting factor of each landslide displacement data with the goal of minimizing the total mean square error; performing weighted fusion on all landslide displacement data using the first weighting factor of each landslide displacement data to obtain landslide displacement deformation data of the landslide displacement monitoring point; the landslide displacement deformation data comprises displacement data after fusion of landslide displacement data of different time periods; obtaining landslide displacement deformation data of different time periods; and performing landslide displacement monitoring on the landslide displacement monitoring point based on the landslide displacement deformation data of the different time periods.

[0005] Preferably, the method of obtaining the total mean square error of all landslide displacement data includes: obtaining the variance of each landslide displacement data and a second weighting factor of each landslide displacement data; the second weighting factor is a preset weighting factor; and obtaining the total mean square error based on the variance of each landslide displacement data and the second weighting factor.

[0006] Preferably, the total mean square error is obtained using the following formula:

[0007]

[0008] Among them, σ 2 is the total mean square error, n is the number of landslide displacement data, W p is the second weighting factor of the pth landslide displacement data, is the variance of the pth landslide displacement data.

[0009] Preferably, obtaining the variance of each landslide monitoring data includes: obtaining the variance of the first landslide displacement data based on the mutual correlation coefficient between the first landslide displacement data and the second landslide displacement data, and the autocorrelation coefficient of the first landslide displacement data; the first landslide displacement data and the second landslide displacement data are any one of the landslide displacement data in the landslide monitoring data.

[0010] Preferably, the difference between the mutual correlation coefficient and the autocorrelation coefficient is the variance of the first landslide displacement data.

[0011] Preferably, the first weighting factor is obtained using the following formula:

[0012]

[0013] in, is the first weighting factor of the pth landslide displacement data, is the variance of the p-th landslide displacement data, is the variance of the displacement data of the ith landslide.

[0014] Preferably, after obtaining the landslide monitoring data of the landslide displacement monitoring point, it also includes: performing data missing interpolation processing and data smoothing and denoising processing on the landslide monitoring data to obtain optimized landslide monitoring data; using the optimized landslide monitoring data as the landslide monitoring data, and returning to the step of obtaining the total mean square error of all landslide displacement data.

[0015] The specific technical scheme of the second embodiment of the present invention is: a monitoring system for landslide displacement, the system comprising: a first data acquisition module, a total mean square error acquisition module, a target optimization module, a data fusion module, a second data acquisition module and a monitoring module; the first data acquisition module is used to acquire landslide monitoring data of a landslide displacement monitoring point; the landslide monitoring data includes landslide displacement data obtained by different displacement sensors monitoring the landslide displacement monitoring point; the total mean square error acquisition module is used to acquire the total mean square error of all landslide displacement data; the target optimization module is used to acquire a first weighting factor of each landslide displacement data with the minimum total mean square error as the goal; the data fusion module is used to perform weighted fusion on all landslide displacement data using the first weighting factor of each landslide displacement data to obtain landslide displacement deformation data of the landslide displacement monitoring point; the landslide displacement deformation data includes displacement data after fusion of landslide displacement data of different time periods; the second data acquisition module is used to acquire landslide displacement deformation data of different time periods; the monitoring module is used to perform landslide displacement monitoring on the landslide displacement monitoring point based on the landslide displacement deformation data of the different time periods.

[0016] The specific technical solution of the third embodiment of the present invention is: a landslide displacement monitoring device, including a memory and a processor, the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the method described in any one of the first embodiments of the present application.

[0017] The specific technical solution of the fourth embodiment of the present invention is: a computer-readable storage medium storing a computer program, which, when executed by a processor, enables the processor to perform the steps of the method described in any one of the first embodiments of the present application.

[0018] Implementing the embodiments of the present invention will have the following beneficial effects:

[0019] The present invention obtains landslide monitoring data of a landslide displacement monitoring point; obtains a total mean square error of all landslide displacement data; obtains a first weighting factor of each landslide displacement data with the goal of minimizing the total mean square error; performs weighted fusion of all landslide displacement data using the first weighting factor of each landslide displacement data to obtain landslide displacement deformation data of the landslide displacement monitoring point; obtains landslide displacement deformation data of different time periods; and performs landslide displacement monitoring on the landslide displacement monitoring point based on the landslide displacement deformation data of different time periods.

[0020] By taking the minimum total mean square error as the goal, the optimal weighting factor corresponding to each landslide displacement data can be adaptively found to make the fused data value optimal. This optimization method can fully consider the error differences between each landslide displacement data, thereby obtaining a more accurate and reliable data fusion result. Therefore, the first weighting factor of each landslide displacement data is used to perform weighted fusion on all landslide displacement data to obtain the landslide displacement deformation data of the landslide displacement monitoring point, so that the landslide displacement deformation data can comprehensively and effectively identify the landslide deformation stage and be closer to the actual situation of landslide deformation.

Brief Description of the Drawings

[0021] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0022] Figure 1 A flow chart of the steps of the landslide displacement monitoring method;

[0023] Figure 2 It is a schematic diagram of landslide displacement data at different time periods;

[0024] Figure 3The schematic diagram of the landslide displacement data after fusion in different periods;

[0025] Figure 4 It is the structural diagram of the monitoring system of landslide displacement;

[0026] Figure 5 A diagram of the internal structure of a computer device;

[0027] Among them, 201, a first data acquisition module; 202, a total mean square error acquisition module; 203, a target optimization module; 204, a data fusion module; 205, a second data acquisition module; 206, a monitoring module. [Specific implementation method]

[0028] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0029] The terms "first", "second", etc. in the specification, claims and drawings of this application are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or modules is not limited to the listed steps or modules, but optionally includes steps or modules that are not listed, or optionally includes other steps or modules that are inherent to these processes, methods, products or devices.

[0030] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0031] In order to more effectively utilize deformation monitoring data of various types and points, these data can be fused. Currently, the commonly used landslide monitoring data-level fusion algorithms include Kalman filtering, wavelet transformation, and weighted fusion. This application is based on the landslide displacement deformation data collected by GNSS monitoring technology and displacement meters, and adopts a weighted fusion method to perform data-level fusion processing on the displacement change obtained by landslide body monitoring.

[0032] (1) In areas where landslides and other geological disasters are prone to occur in power transmission line projects, multiple landslide monitoring displacement sensors are installed to monitor the displacement changes of landslide bodies that may cause landslides.

[0033] (2) Monitoring data preprocessing:

[0034] When monitoring landslides, the monitoring instrument itself and the external environment will have more or less impact on the monitoring data, reducing the quality of the monitoring data. By preprocessing the monitoring data such as removing irrelevant information (gross errors), interpolating and completing data, smoothing and denoising data, we can obtain a high-quality monitoring sequence and further improve the accuracy and reliability of data-level fusion results and applications.

[0035] See also Figure 1 , is a flow chart of the steps of a landslide displacement monitoring method in the first embodiment of the present application, so that the landslide displacement deformation data can comprehensively and effectively determine the landslide deformation stage and be closer to the actual situation of the landslide deformation. The method includes:

[0036] Step 101, acquiring landslide monitoring data of a landslide displacement monitoring point; the landslide monitoring data includes landslide displacement data obtained by different displacement sensors monitoring the landslide displacement monitoring point;

[0037] Step 102, obtaining the total mean square error of all landslide displacement data;

[0038] Step 103, obtaining a first weighting factor for each landslide displacement data with the goal of minimizing the total mean square error;

[0039] Step 104: weighted fusion of all landslide displacement data using the first weighting factor of each landslide displacement data to obtain landslide displacement deformation data of the landslide displacement monitoring point; the landslide displacement deformation data includes displacement data after fusion of landslide displacement data in different time periods;

[0040] Step 105, obtaining landslide displacement deformation data in different time periods;

[0041] Step 106: Perform landslide displacement monitoring on the landslide displacement monitoring points based on the landslide displacement deformation data in different time periods.

[0042] Specifically, a plurality of displacement sensors are used to monitor the landslide displacement monitoring points, and the landslide displacement data of the landslide displacement monitoring points are obtained; the total mean square error can reflect the difference between the landslide displacement data and the actual displacement data, and the first weighting factor of each landslide displacement data is obtained with the goal of minimizing the total mean square error, and the landslide displacement data is weightedly fused using the first weighting factor of each landslide displacement data, so that the difference between the fused landslide displacement deformation data and the actual displacement data can be minimized.

[0043] The method in this embodiment can adaptively find the optimal weighting factor corresponding to each landslide displacement data by taking the minimum total mean square error as the goal, so that the fused data value reaches the optimal value. This optimization method can fully consider the error difference between each landslide displacement data, so as to obtain a more accurate and reliable data fusion result. Therefore, the first weighting factor of each landslide displacement data is used to perform weighted fusion on all landslide displacement data to obtain the landslide displacement deformation data of the landslide displacement monitoring point, so that the landslide displacement deformation data can comprehensively and effectively judge the landslide deformation stage and be closer to the actual situation of landslide deformation.

[0044] In a specific embodiment, the total mean square error of all landslide displacement data is obtained, including: obtaining the variance of each landslide displacement data and a second weighting factor of each landslide displacement data; the second weighting factor is a preset weighting factor; and the total mean square error is obtained based on the variance of each landslide displacement data and the second weighting factor.

[0045] Specifically, suppose the variances of n displacement monitoring sensors are The true value to be estimated is X. The data obtained by one sensor corresponds to one true value, and the number of measured values ​​is the same; the measured values ​​of each displacement sensor are X1, X2, ..., X n ; The first weighting factors preset for each group of measured values ​​are W1, W2, ..., W n , then the initial true value X obtained by fusing multiple measured values * The value satisfies the following expression:

[0046]

[0047]

[0048] In a specific embodiment, the total mean square error is obtained using the following formula:

[0049]

[0050] Among them, σ 2 is the total mean square error, n is the number of landslide displacement data, W p is the second weighting factor of the pth landslide displacement data, is the variance of the pth landslide displacement data.

[0051] In a specific embodiment, the first weighting factor is obtained using the following formula:

[0052]

[0053] in, is the first weighting factor of the pth landslide displacement data, is the variance of the p-th landslide displacement data, is the variance of the i-th landslide displacement data. Specifically, the number of the second weighting factors is the same as the number of the measured values, that is, each measured value has a corresponding weighting factor.

[0054] In a specific embodiment, obtaining the variance of each landslide monitoring data includes: obtaining the variance of the first landslide displacement data based on the correlation coefficient between the first landslide displacement data and the second landslide displacement data, and the autocorrelation coefficient of the first landslide displacement data; the first landslide displacement data and the second landslide displacement data are any one of the landslide displacement data in the landslide monitoring data.

[0055] Specifically, the displacement values ​​collected by the two independent displacement monitoring sensors are Xp and Xq, and the corresponding measurement errors are Vp and Vq, that is:

[0056] X p =X+V p X q =X+V q

[0057] The variance of the displacement monitoring sensor p is:

[0058]

[0059] The mutual correlation coefficient R of Xp and Xq pq for:

[0060] R pq =E[X p X q ]=E[X 2

[0061] Autocorrelation coefficient R of Xp pp for:

[0062]

[0063] In a specific embodiment, the difference between the mutual correlation coefficient and the autocorrelation coefficient is the variance of the first landslide displacement data. Specifically, the variance of the landslide displacement data is obtained using the following formula:

[0064] In a specific embodiment, after obtaining the landslide monitoring data of the landslide displacement monitoring point, it also includes: performing data missing interpolation processing and data smoothing and denoising processing on the landslide monitoring data to obtain optimized landslide monitoring data; using the optimized landslide monitoring data as the landslide monitoring data, and returning to the step of obtaining the total mean square error of all landslide displacement data.

[0065] Specifically, when monitoring a landslide, the monitoring instrument itself and the external environment will have more or less impact on the monitoring data, reducing the quality of the monitoring data. By preprocessing the monitoring data such as removing irrelevant information (gross errors), interpolating and completing data, and smoothing and denoising data, we hope to obtain a high-quality monitoring sequence, and further improve the accuracy and reliability of data-level fusion results and applications. In practical applications, there is a common phenomenon of missing data in surface displacement monitoring data, and the missing data are mainly distributed in the uniform deformation stage and the accelerated deformation stage. Lagrange interpolation is used to interpolate the missing data of landslide monitoring data, providing a high-quality data set for multi-source landslide data fusion. The three-dimensional displacement change data in the uniform deformation stage of the landslide monitoring data is selected, such as Figure 2 As shown. The "peaks and burrs" in the monitoring sequence are smoothed, and the effective characteristic information of the displacement change is retained, making the displacement change trend clearer. Combined with the characteristics of the landslide deformation stage, the least squares method and the weighted moving average method are selected for data smoothing and denoising. In the presence of data noise, the least squares method can still give reasonable fitting results. It has little impact on outliers and can handle outliers better, which makes it more reliable when dealing with data containing noise or outliers. The weighted moving average method can better handle trend changes in the data by assigning different weights to observations in different periods, thereby providing more accurate prediction results.

[0066] In a specific embodiment, geological disasters such as landslides often show a suddenness due to geological environment reasons. It can be seen from the cumulative displacement deformation that the time experienced by the accelerated deformation stage of loess landslide is very short. Therefore, in order to analyze the accelerated deformation stage more accurately and reliably, the interval during equal interval processing should be reduced, and the number of samples in the observation sequence of the accelerated deformation stage should be increased. In this application, the accelerated deformation stage is spaced at intervals of two hours, and the other two stages are spaced at intervals of days. The data is averaged to obtain an equally spaced observation sequence. Therefore, the monitoring sequence is divided into two stages, Stage I (initial deformation stage + uniform deformation stage) and Stage II (accelerated deformation stage). The data of Stage I after weighted fusion is fused with the data of Stage II after weighted fusion. The fused data can be found in Figure 3 shown.

[0067] from Figure 3In the comparative analysis, it is found that the analysis results of the fused data are more stable than those of the actual monitoring data, and the deformation curve is smoother and more complete, which is conducive to more accurate information capture when distinguishing the stages of landslides. In order to further analyze and evaluate the results of adaptive weighted fusion, the results are analyzed and compared with the data before fusion. The fused data and the monitoring data are processed separately, and the improved tangent angle is used as an example for comparative analysis. Here, the displacement data and fused data collected by each sensor are mainly calculated, and the statistics are calculated before and after the improved tangent angle reaches 80°, as shown in Table 1 below.

[0068]

[0069] Table 1 Improved tangent intersection comparison analysis

[0070] The related technology uses the mathematical method of improved tangent angle to further divide the acceleration stage of landslide deformation into three sub-stages, namely: when the improved tangent angle > 45°, the landslide is in the initial acceleration deformation stage; when the improved tangent angle > 80°, the landslide is in the middle acceleration deformation stage; when the improved tangent angle > 85°, the landslide is in the pre-slip stage. According to the above table, it can be seen from the monitoring point DCF11 that the landslide entered the medium acceleration stage on 2019-9-20 and the accelerated stage on 2019-9-27; from the monitoring point HF07, it can be seen that the landslide entered the medium acceleration stage on 2019-10-4; from the monitoring points DCF14 and HF06, it can be seen that the landslide entered the medium acceleration stage on 2019-9-30 and the accelerated stage on 2019-10-1; from the monitoring point DCF15 and the adaptive weighted fusion results, it can be seen that the landslide entered the medium acceleration stage on 2019-10-1 and the accelerated stage on 2019-10-2.

[0071] In summary, the results show that adaptive weighting can effectively fuse the five sets of deformation data, and the fused data can comprehensively and effectively identify the landslide deformation stage and is closer to the actual situation of landslide deformation. The fused data analysis curve is relatively smooth and complete, which can better reflect and capture the overall deformation characteristics of the landslide. The fused analysis results are better than the analysis results of a single landslide deformation monitoring point data.

[0072] In the specific embodiments, see Figure 4, is a structural schematic diagram of a landslide displacement monitoring system in the second embodiment of the present application, the system comprising: a first data acquisition module 201, a total mean square error acquisition module 202, a target optimization module 203, a data fusion module 204, a second data acquisition module 205 and a monitoring module 206; the first data acquisition module 201 is used to acquire landslide monitoring data of a landslide displacement monitoring point; the landslide monitoring data includes landslide displacement data obtained by different displacement sensors monitoring the landslide displacement monitoring point; the total mean square error acquisition module 202 is used to acquire the total mean square error of all landslide displacement data; the target optimization module 20 3 is used to obtain the first weighting factor of each landslide displacement data with the goal of minimizing the total mean square error; the data fusion module 204 is used to use the first weighting factor of each landslide displacement data to perform weighted fusion on all landslide displacement data to obtain the landslide displacement deformation data of the landslide displacement monitoring point; the landslide displacement deformation data includes the displacement data after the landslide displacement data of different time periods are fused; the second data acquisition module 205 is used to obtain the landslide displacement deformation data of different time periods; the monitoring module 206 is used to perform landslide displacement monitoring on the landslide displacement monitoring point based on the landslide displacement deformation data of different time periods.

[0073] Specifically, the system in the embodiment of the present application uses multiple displacement sensors to monitor the landslide displacement monitoring points and obtain the landslide displacement data of the landslide displacement monitoring points; the total mean square error can reflect the difference between the landslide displacement data and the actual displacement data, and the first weighting factor of each landslide displacement data is obtained with the goal of minimizing the total mean square error, and the landslide displacement data is weightedly fused using the first weighting factor of each landslide displacement data, so that the difference between the fused landslide displacement deformation data and the actual displacement data can be minimized.

[0074] The system in this embodiment can adaptively find the optimal weighting factor corresponding to each landslide displacement data by taking the minimum total mean square error as the goal, so that the fused data value reaches the optimal value. This optimization method can fully consider the error difference between each landslide displacement data, so as to obtain a more accurate and reliable data fusion result. Therefore, the first weighting factor of each landslide displacement data is used to perform weighted fusion on all landslide displacement data to obtain the landslide displacement deformation data of the landslide displacement monitoring point, so that the landslide displacement deformation data can comprehensively and effectively judge the landslide deformation stage and be closer to the actual situation of landslide deformation.

[0075] In a specific embodiment, the third embodiment of the present application provides a monitoring device for landslide displacement, including a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the method described in any one of the first embodiments of the present application. The monitoring device in this embodiment can adaptively find the optimal weighting factor corresponding to each landslide displacement data by taking the minimum total mean square error as the goal, so that the fused data value reaches the optimal value. This optimization method can fully consider the error difference between each landslide displacement data, so as to obtain a more accurate and reliable data fusion result. Therefore, the first weighting factor of each landslide displacement data is used to perform weighted fusion on all landslide displacement data to obtain the landslide displacement deformation data of the landslide displacement monitoring point, so that the landslide displacement deformation data can comprehensively and effectively distinguish the landslide deformation stage and be closer to the actual situation of the landslide deformation.

[0076] In a specific embodiment, the fourth embodiment of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the processor executes the steps of the method described in any one of the first embodiments of the present application. The storage medium in this embodiment can adaptively find the optimal weighting factor corresponding to each landslide displacement data by taking the minimum total mean square error as the goal, so that the fused data value reaches the optimal. This optimization method can fully consider the error difference between each landslide displacement data, so as to obtain a more accurate and reliable data fusion result. Therefore, the first weighting factor of each landslide displacement data is used to perform weighted fusion on all landslide displacement data to obtain the landslide displacement deformation data of the landslide displacement monitoring point, so that the landslide displacement deformation data can comprehensively and effectively distinguish the landslide deformation stage and be closer to the actual situation of the landslide deformation.

[0077] Figure 5 The internal structure of a computer device in one embodiment is shown. The computer device can be a terminal or a server. Figure 5 The computer device includes a processor, a memory, etc. connected via a system bus. The memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system and may also store a computer program. When the computer program is executed by the processor, the processor can implement the method in this embodiment. The internal memory may also store a computer program. When the computer program is executed by the processor, the processor can implement the method in this embodiment. Those skilled in the art can understand that Figure 5The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0078] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

[0079] The above description is only a preferred embodiment of the present invention and does not limit the present invention in other forms. Any technician familiar with the profession may use the technical content disclosed above to change or modify it into an equivalent embodiment with equivalent changes and apply it to other fields. However, any simple modification, equivalent change and modification made to the above embodiment based on the technical essence of the present invention without departing from the content of the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A method for monitoring landslide displacement, characterized in that: The method comprises: Acquiring landslide monitoring data of a landslide displacement monitoring point; the landslide monitoring data includes landslide displacement data obtained by different displacement sensors monitoring the landslide displacement monitoring point; Obtain the total mean square error of all landslide displacement data; Obtaining a first weighting factor for each landslide displacement data with the goal of minimizing the total mean square error; Using the first weighting factor of each landslide displacement data, all the landslide displacement data are weightedly fused to obtain the landslide displacement deformation data of the landslide displacement monitoring point; the landslide displacement deformation data includes the displacement data after the landslide displacement data of different time periods are fused; Obtain landslide displacement and deformation data at different time periods; The landslide displacement monitoring point is subjected to landslide displacement monitoring based on the landslide displacement deformation data in different time periods.

2. The method for monitoring landslide displacement according to claim 1, characterized in that: The total mean square error of all landslide displacement data is obtained, including: Obtaining the variance of each landslide displacement data and a second weighting factor of each landslide displacement data; the second weighting factor is a preset weighting factor; The total mean square error is obtained based on the variance of each landslide displacement data and the second weighting factor.

3. The method for monitoring landslide displacement according to claim 2, characterized in that: The total mean square error is obtained using the following formula: Among them, σ 2 is the total mean square error, n is the number of landslide displacement data, W p is the second weighting factor of the pth landslide displacement data, is the variance of the pth landslide displacement data.

4. The method for monitoring landslide displacement according to claim 2, characterized in that: The obtaining of the variance of each landslide monitoring data comprises: The variance of the first landslide displacement data is obtained according to the correlation coefficient between the first landslide displacement data and the second landslide displacement data and the autocorrelation coefficient of the first landslide displacement data; the first landslide displacement data and the second landslide displacement data are any one of the landslide displacement data in the landslide monitoring data.

5. The method for monitoring landslide displacement according to claim 4, characterized in that: The difference between the mutual correlation coefficient and the autocorrelation coefficient is the variance of the first landslide displacement data.

6. The method for monitoring landslide displacement according to claim 1, characterized in that: The first weighting factor is obtained by using the following formula: in, is the first weighting factor of the pth landslide displacement data, is the variance of the p-th landslide displacement data, is the variance of the displacement data of the ith landslide.

7. The method for monitoring landslide displacement according to claim 1, characterized in that: After acquiring the landslide monitoring data of the landslide displacement monitoring point, the method further includes: Performing data missing interpolation processing and data smoothing and denoising processing on the landslide monitoring data to obtain optimized landslide monitoring data; The optimized landslide monitoring data is used as the landslide monitoring data, and the step of obtaining the total mean square error of all landslide displacement data is returned.

8. A landslide displacement monitoring system, characterized in that: The system comprises: a first data acquisition module, a total mean square error acquisition module, a target optimization module, a data fusion module, a second data acquisition module and a monitoring module; The first data acquisition module is used to acquire landslide monitoring data of a landslide displacement monitoring point; the landslide monitoring data includes landslide displacement data obtained by different displacement sensors monitoring the landslide displacement monitoring point; The total mean square error acquisition module is used to acquire the total mean square error of all landslide displacement data; The target optimization module is used to obtain a first weighting factor for each landslide displacement data with the minimum total mean square error as the target; The data fusion module is used to perform weighted fusion on all the landslide displacement data using the first weighting factor of each landslide displacement data to obtain the landslide displacement deformation data of the landslide displacement monitoring point; the landslide displacement deformation data includes the displacement data after the landslide displacement data of different time periods are fused; The second data acquisition module is used to acquire landslide displacement and deformation data in different time periods; The monitoring module is used to perform landslide displacement monitoring on the landslide displacement monitoring point based on the landslide displacement deformation data in different time periods.

9. A landslide displacement monitoring device, comprising a memory and a processor, characterized in that: The memory stores a computer program, and when the computer program is executed by the processor, the processor is caused to perform the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the processor is caused to perform the steps of the method according to any one of claims 1 to 7.

Images