A method and apparatus for predicting dam deformation

Abstract

The application provides a method and device for predicting dam deformation, and belongs to the technical field of deformation prediction. The method fits the monitoring displacement of multiple measuring points in a measuring area of a dam in a historical time period to obtain fitting displacement of the multiple measuring points; and obtains displacement residuals of the multiple measuring points through the monitoring displacement and the fitting displacement of the multiple measuring points; further optimizes the displacement residuals of the multiple measuring points to obtain optimized displacement residuals of the multiple measuring points; and predicts the displacement of the multiple measuring points in a future time period according to the fitting displacement and the optimized displacement residuals of the multiple measuring points in the future time period. The method can more accurately predict the displacement residuals of each measuring point of the dam in the future time period, thereby predicting the displacement of each measuring point in the dam deformation process based on the displacement residuals, and improving the prediction accuracy of the dam deformation.

Description

Technical Field

[0001] This invention relates to the field of deformation prediction technology, and in particular to a method and apparatus for predicting dam deformation. Background Technology

[0002] Dams, as concrete structures, are typically built in terrains such as rivers and canyons to block water flow and form reservoirs. Dams may deform due to various factors. Currently, by deploying monitoring equipment at various points along the dam to obtain the dam's displacement at each point, and then using the displacement of each point to predict the displacement of the dam's internal structure in the future, timely maintenance or reinforcement measures can be taken to prevent dam failure accidents.

[0003] However, due to the complex operating environment of dams (e.g., diverse geological structures), it is difficult to analyze the factors that cause deformation of the internal structure of dams. Therefore, existing prediction methods do not have high accuracy in predicting dam deformation. Summary of the Invention

[0004] This invention proposes a method and apparatus for predicting dam deformation. In the process of predicting dam deformation, the displacement residuals of various measuring points of the dam in the future time period can be predicted more accurately. Thus, based on the displacement residuals, the displacement of each measuring point during the dam deformation process can be predicted, thereby improving the prediction accuracy of dam deformation.

[0005] To achieve the above objectives, the present invention adopts the following technical solution:

[0006] In a first aspect, the present invention provides a method for dam deformation, comprising: fitting the monitored displacements of multiple measuring points within a survey area of ​​the dam during a first historical time period and the monitored displacements of multiple measuring points during a second historical time period to obtain fitted displacements of multiple measuring points during the second historical time period. The multiple measuring points within the survey area exhibit the same deformation pattern; the first historical time period precedes the second historical time period. Next, based on the monitored displacements and fitted displacements of the multiple measuring points during the second historical time period, the displacement residuals of the multiple measuring points within the survey area are determined. Then, the displacement residuals of the multiple measuring points within the survey area are optimized to obtain optimized displacement residuals for the multiple measuring points. Finally, based on the fitted displacements of the multiple measuring points in a future time period and the optimized displacement residuals of the multiple measuring points, the displacements of the multiple measuring points in the future time period are determined; the fitted displacements of the multiple measuring points in the future time period are obtained by fitting data from the monitored displacements of the multiple measuring points within the survey area during the historical time period.

[0007] The method for predicting dam deformation provided by this invention can more accurately predict the displacement residuals of each measuring point of the dam in the future time period by optimizing the residuals of multiple measuring points after optimization processing during the determination of prediction residuals. Thus, based on the displacement residuals, the displacement of each measuring point during the dam deformation process can be predicted, thereby improving the prediction accuracy of dam deformation.

[0008] In one implementation of the first and second aspects, any one of the multiple measuring points within the measurement area is taken as the target measuring point, and the optimized displacement residual of the target measuring point is determined. This includes: decomposing the displacement residual of each of the multiple measuring points based on the displacement residual of the target measuring point to obtain multiple modal residuals corresponding to the multiple measuring points; wherein each measuring point corresponds to at least one modal residual. Multiple relevant modal residuals are selected from the multiple modal residuals corresponding to the multiple measuring points; the correlation coefficients between the displacement residual of the target measuring point and the multiple relevant modal residuals are all greater than a preset threshold. From the multiple modal residual groups, the target modal residual group with the strongest correlation to the displacement residual of the target measuring point is selected; the multiple modal residual groups are obtained by combining multiple relevant modal residuals, and each modal residual group includes N relevant modal residuals. The relevant modal residuals in the target modal residual group are weighted and summed to obtain the optimized displacement residual of the target measuring point.

[0009] As can be seen from the above, the process of optimizing the displacement residual of the target measuring point can be divided into three steps.

[0010] The first step is to decompose the displacement residuals of multiple measuring points in the measurement area based on the modal number of the target measuring point, and obtain the modal residuals corresponding to multiple measuring points. This provides more effective information that is closer to the deformation trend of the internal structure of the dam for the optimization of the displacement residuals of the target measuring point.

[0011] The second step is to filter the modal residuals corresponding to multiple measuring points to obtain the target modal residual set. This process removes noise information and selects the target modal residual set containing as much effective information as possible for the optimization of the displacement residuals of the target measuring points.

[0012] The third step is to reconstruct the target modal residual group to obtain the optimized residual, so that the optimized residual obtained by reconstruction conforms as closely as possible to the variation law of the displacement residual of the target measuring point.

[0013] In summary, the optimized residuals obtained through optimization contain more limited information and are closer to the variation law of the displacement residuals of the target measuring point, which can make the prediction accuracy of the displacement of the target measuring point in the future time period predicted by the optimized residuals higher.

[0014] In one implementation of the first aspect, based on the displacement residual of the target measuring point, the displacement residual of each of the multiple measuring points is decomposed to obtain multiple modal residuals corresponding to the multiple measuring points. This includes: determining the number of modes of the displacement residual based on the center frequency of the displacement residual of the target measuring point; and using variational modal decomposition to decompose the displacement residual of each of the multiple measuring points to obtain multiple modal residuals corresponding to the multiple measuring points; wherein the number of modal residuals corresponding to each measuring point is equal to the number of modes.

[0015] As is well known, variational mode decomposition (VMD) can extract effective information from displacement residuals. Therefore, when multiple measuring points within a survey area exhibit the same deformation patterns, decomposing the displacement residual of the target measuring point using the mode number of the target point's displacement residual can extract effective information. Furthermore, decomposing the displacement residuals of other measuring points within the survey area using the mode number of the target point's displacement residual can extract effective information from the displacement residuals of other measuring points that is similar to and / or related to the target measuring point's displacement residual. Therefore, when the complex operating environment of a dam makes it difficult to analyze the factors causing deformation of the dam's internal structure, the above processing can provide more effective information that more closely reflects the deformation trend of the dam's internal structure for optimizing the displacement residual of the target measuring point. Based on this effective information, the optimized displacement residual can predict the displacement of the target measuring point in the future time period with higher prediction accuracy.

[0016] In one implementation of the first aspect, a weighted summation is performed on multiple relevant modal residuals in the target modal residual set to obtain the optimized displacement residual of the target measuring point. This includes: calculating multiple weighted summations of the relevant modal residuals in the target modal residual set under multiple residual weight coefficients; wherein each set of residual weight coefficients corresponds to one weighted summation value. The weighted summation value with the strongest correlation to the displacement residual of the target measuring point is taken as the optimized displacement residual of the target measuring point.

[0017] As can be seen from the above, the above processing procedure simulates various scenarios for reconstructing the residuals of the target modal residual set by adjusting the weighting coefficients of multiple related modal residuals in the target modal residual set. Furthermore, the correlation between multiple weighted sums (corresponding to multiple sets of weighting coefficients) and the displacement residuals of the target measuring point indicates the similarity between the reconstructed residuals of the target modal residual set and the displacement residual variation patterns of the target measuring point (the stronger the correlation between the weighted sum and the displacement residuals of the target measuring point, the higher the similarity between the reconstructed residuals of the target modal residual set and the displacement residual variation patterns of the target measuring point). Based on this, selecting the weighted sum with the strongest correlation to the displacement residuals of the target measuring point as the optimized displacement residual for the target measuring point yields the optimized residual that most closely resembles the variation pattern of the displacement residuals of the target measuring point.

[0018] In one implementation of the first aspect, any one of multiple measuring points within the survey area is taken as the target measuring point, and the displacement of the target measuring point in the future time period is determined. This includes: processing the optimized displacement residual of the target measuring point using an autoregressive integral moving average model to predict the displacement residual of the target measuring point in the future time period; and superimposing the fitted displacement and displacement residual of the target measuring point in the future time period to obtain the displacement of the target measuring point in the future time period.

[0019] As can be seen from the above, the optimized displacement residual of the measuring point obtained by the above optimization process is based on the displacement of the measuring point in the second historical time period. This optimized displacement residual can more accurately reflect the change of displacement residual in the second historical time period. Based on this, in the above prediction process, further analysis and processing of the optimized displacement residual can more reasonably and accurately predict the displacement residual of the measuring point in the future time period, which helps to more accurately predict the displacement of the measuring point in the future time period.

[0020] In one implementation of the first aspect, the method further includes classifying all the measuring points deployed in the dam to obtain multiple measuring zones.

[0021] Secondly, the present invention provides an apparatus for predicting dam deformation, comprising a fitting module, a determination module, an optimization module, and a prediction module.

[0022] The fitting module is used to fit the monitored displacements of multiple measuring points in a survey area of ​​the dam during a first historical time period and the monitored displacements of multiple measuring points during a second historical time period to obtain the fitted displacements of multiple measuring points during the second historical time period; wherein, multiple measuring points in the survey area have the same deformation pattern; the first historical time period is before the second historical time period.

[0023] The determination module is used to determine the displacement residuals of multiple measuring points within the measurement area based on the monitored displacements and fitted displacements of multiple measuring points during the second historical time period.

[0024] The optimization module is used to optimize the displacement residuals of multiple measuring points within the survey area to obtain optimized displacement residuals for multiple measuring points.

[0025] The prediction module is used to determine the displacement of multiple measuring points in the future time period based on the fitted displacement of multiple measuring points and the optimized displacement residual of multiple measuring points. The fitted displacement of multiple measuring points in the future time period is obtained by fitting the monitoring displacement of multiple measuring points in the measurement area in the historical time period.

[0026] In one implementation of the second aspect, any one of the multiple measuring points within the measurement area is taken as the target measuring point. The aforementioned optimization module is specifically used for: decomposing the displacement residual of each of the multiple measuring points based on the displacement residual of the target measuring point to obtain multiple modal residuals corresponding to the multiple measuring points; wherein each measuring point corresponds to at least one modal residual. Multiple relevant modal residuals are selected from the multiple modal residuals corresponding to the multiple measuring points; the correlation coefficients between the displacement residual of the target measuring point and the multiple relevant modal residuals are all greater than a preset threshold. From the multiple modal residual groups, the target modal residual group with the strongest correlation to the displacement residual of the target measuring point is selected; the multiple modal residual groups are obtained by combining multiple relevant modal residuals, and each modal residual group includes N relevant modal residuals.

[0027] In one implementation of the second aspect, the prediction module is specifically used to: process the optimized displacement residual of the target measuring point using an autoregressive integral moving average model to predict the displacement residual of the target measuring point in the future time period; and then superimpose the fitted displacement and displacement residual of the target measuring point in the future time period to obtain the displacement of the target measuring point in the future time period.

[0028] In one implementation of the second aspect, the device further includes a classification module. The classification module is used to classify all measuring points deployed in the dam to obtain multiple measuring zones.

[0029] In one implementation of the first aspect, the aforementioned optimization module is further specifically used for: decomposing the displacement residual of each of the multiple measuring points based on the displacement residual of the target measuring point to obtain multiple modal residuals corresponding to the multiple measuring points, including: determining the number of modes of the displacement residual based on the center frequency of the displacement residual of the target measuring point. The variational modal decomposition method is used to decompose the displacement residual of each of the multiple measuring points to obtain multiple modal residuals corresponding to the multiple measuring points; wherein the number of modal residuals corresponding to each measuring point is equal to the number of modes.

[0030] In one implementation of the second aspect, the optimization module is further specifically used to: calculate multiple weighted sums of the relevant modal residuals in the target modal residual group under multiple sets of residual weight coefficients; wherein, each set of residual weight coefficients corresponds to one weighted sum. The weighted sum with the strongest correlation to the displacement residual of the target measuring point among the multiple weighted sums is taken as the optimized displacement residual of the target measuring point.

[0031] In one implementation of the second aspect, the prediction module is specifically used to: process the optimized displacement residual of the target measuring point using an autoregressive integral moving average model to predict the displacement residual of the target measuring point in the future time period; and then superimpose the fitted displacement and displacement residual of the target measuring point in the future time period to obtain the displacement of the target measuring point in the future time period.

[0032] In one implementation of the first and second aspects, N equals the number of modes.

[0033] Thirdly, the present invention provides an electronic device including a processor and a memory coupled to the processor; the memory is used to store computer instructions, and when the electronic device is running, the processor executes the computer instructions stored in the memory to cause the electronic device to perform the method described in the first aspect above or any implementation thereof.

[0034] Fourthly, the present invention provides a computer-readable storage medium including computer program instructions that, when executed by a computer, cause the computer to perform the method described in the first aspect above or any implementation thereof.

[0035] Fifthly, the present invention provides a computer program product, including computer program instructions, which, when executed on a computer, cause the computer to perform the method described in the first aspect above or any implementation thereof.

[0036] The technical effects corresponding to the second to fifth aspects and their possible implementations can be referred to the above description of the technical effects of the first aspect and its possible implementations, and will not be repeated here. Attached Figure Description

[0037] Figure 1 This is one of the schematic diagrams of a method for predicting dam deformation provided in the embodiments of this application;

[0038] Figure 2 This is a schematic diagram of the clustering results of all measuring points deployed in the dam provided in the embodiments of this application;

[0039] Figure 3 This is a schematic diagram illustrating the change of the monitored displacement of four measuring points in the first measuring area over time, provided in an embodiment of this application.

[0040] Figure 4 This is a schematic diagram of the monitored displacement, fitted displacement, and displacement residual of measuring point LS1 in the second historical time period provided in the embodiments of this application;

[0041] Figure 5 This is a second schematic diagram of a method for predicting dam deformation provided in an embodiment of this application;

[0042] Figure 6 This is the third schematic diagram of a method for predicting dam deformation provided in the embodiments of this application;

[0043] Figure 7 This is a schematic diagram of multiple modal residuals corresponding to four measuring points in the first measuring area provided in the embodiments of this application;

[0044] Figure 8 This is the fourth schematic diagram of a method for predicting dam deformation provided in the embodiments of this application;

[0045] Figure 9 This is the fifth schematic diagram of a method for predicting dam deformation provided in the embodiments of this application;

[0046] Figure 10 This is one of the structural schematic diagrams of a device for predicting dam deformation provided in the embodiments of this application;

[0047] Figure 11 This is the second structural schematic diagram of a device for predicting dam deformation provided in the embodiments of this application. Detailed Implementation

[0048] In the specification and claims of this invention, the terms "first" and "second," etc., are used to distinguish different objects, rather than to describe a specific order of objects.

[0049] In the embodiments of this application, "and / or" indicates the relationship between objects. For example, similar and / or related valid information can represent the following three situations: similar valid information exists alone, related valid information exists alone, and similar valid information and related valid information exist simultaneously.

[0050] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design that is described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design. Specifically, the use of the terms "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0051] In the description of this invention, unless otherwise stated, "multiple" means two or more. For example, multiple measuring points within a measuring area refers to two or more measuring points belonging to one measuring area.

[0052] The method and apparatus provided in this application can be used to predict the displacement caused by dam deformation. Specifically, by using the displacement data of multiple measuring points deployed on the dam over a historical period, the displacement data of the aforementioned multiple measuring points over a future period can be predicted.

[0053] Understandably, dams are important water-control structures for reservoirs, rivers, and other bodies of water, with primary functions including flood control, power generation, irrigation, water supply, and navigation. As dams age, they deform due to geological conditions and natural disasters, specifically manifesting as displacement at certain points along the dam. In this embodiment, predicting dam deformation involves predicting the displacement of various measuring points on the dam. Based on this prediction, repair or reinforcement measures can be taken to prevent dam failure.

[0054] To address the issue of low prediction accuracy for dam deformation in the prior art, this application provides a method and apparatus for predicting dam deformation. In this solution, the monitored displacements of multiple measuring points within a measurement area of ​​the dam are fitted over a first and second historical time period to obtain the fitted displacements of the multiple measuring points in the second historical time period. Displacement residuals are then obtained by comparing the monitored displacements with the fitted displacements in the second historical time period. Further, these residuals are optimized to obtain optimized residuals. Finally, based on the fitted displacements and optimized residuals of the multiple measuring points in future time periods, the displacements of the multiple measuring points in future time periods are predicted. This solution can more accurately predict the displacement residuals of each measuring point on the dam in future time periods, thereby improving the prediction accuracy of dam deformation by predicting the displacements of each measuring point during dam deformation based on these residuals.

[0055] For example, the method for predicting dam deformation provided in this embodiment of the invention can be executed by an electronic device with processing capabilities, such as a computer or server. Taking a computer as an example, the hardware components of the computer may include: a processor, memory, a network interface, a user interface, a communication bus, etc.

[0056] The processor controls the electronic equipment to perform related processing and calculation tasks, such as determining the fitted displacement, displacement residual, optimized displacement residual, and displacement of multiple measurement points over a future time period for multiple measurement points. The processor may include a central processing unit (CPU) or other processors, and may be single-core or multi-core; for example, the processor may include multiple CPUs.

[0057] Memory is used to store computer instructions and related data, such as storing monitored displacements, fitted displacements, displacement residuals, and optimized displacement residuals at multiple measurement points. Memory can be random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical storage, magnetic disk storage media, or other magnetic storage devices, or any other medium capable of storing program code or data accessible by a computer. Optionally, memory can be integrated into the processor, or it can be independent of the processor.

[0058] A network interface is used for communication between a computer and other devices or communication networks. A network interface can be a transceiver with transmit and receive capabilities. Optionally, a network interface may include standard wired interfaces or wireless interfaces (such as Wi-Fi interfaces, Bluetooth interfaces, and 5G interfaces).

[0059] The communication bus is used to enable communication between different components. For example, the processor, memory, network interface and user interface mentioned above can be interconnected through the communication bus.

[0060] The user interface may include a display screen and an input unit (such as a keyboard). Optionally, the user interface may also include a standard wired interface or a wireless interface.

[0061] Those skilled in the art will understand that the computer described above may include more or fewer components, or combine certain components, or have different component arrangements; the embodiments of this application do not limit this.

[0062] like Figure 1 As shown, the method for predicting dam deformation provided in this application includes S101-S105.

[0063] S101. All measuring points deployed in the dam are classified to obtain multiple measuring areas.

[0064] Understandably, during the long-term operation of a dam, the displacement of various measuring points deployed within the dam (hereinafter referred to as monitored displacement) can be monitored, and dam deformation can be predicted based on the monitored displacement of each measuring point. Based on this, the patterns of displacement at each measuring point can be analyzed, i.e., the deformation patterns of the measuring points. Measuring points with the same deformation patterns among all the measuring points deployed within the dam can be grouped into one category (i.e., assigned to a single measuring area), resulting in multiple measuring areas.

[0065] Optionally, Ward's hierarchical clustering method can be used to cluster all the measuring points deployed in the dam, thereby dividing the deployed measuring points into multiple measuring zones of the dam. The specific steps of the above clustering process are as follows.

[0066] Step 1: Treat each measuring point deployed in the dam as a class. At this point, the hierarchy of all classes is: 1 .

[0067] Step 2: Calculate the sum of squared errors between the monitored displacement of each class and the monitored displacement of other classes (hereinafter referred to as the sum of squared errors).

[0068] The above sum of squared errors ESS(C) satisfies: Where x is the monitored displacement of this class, and μ(C) is the average monitored displacement of other classes.

[0069] Step 3: For each class in all classes, enumerate all binomial classes of that class (i.e., combinations of that class with another class in all classes except that class), merge the binomial classes with the smallest sum of squared errors, and reduce the number of classes by 1 after merging.

[0070] In this embodiment of the application, for the i-th class, the i-th class is combined with the j-th class from other classes to form a binomial class, and the sum of squared errors of this binomial class (denoted as ΔESS) ij )satisfy:

[0071] ΔESS ij =ESS(C t )-ESS(C i )-ESS(C j ),

[0072] Among them, ESS(C t Let ESS(C) be the sum of squared errors of the class resulting from merging the i-th class and the j-th class. i Let ) be the sum of squared errors for the i-th class, ESS(C j ) represents the sum of squared errors for the j-th class.

[0073] Step 4: Increment the hierarchy of the class obtained from merging in Step 3 by 1.

[0074] Repeat steps 2 through 4 until the number of classes corresponding to the highest level is 1. This indicates that convergence of all classes (corresponding to all measurement points deployed in the dam) has been completed, and the resulting classes corresponding to all levels are the clustering results of Ward's aggregate hierarchical clustering method. Then, based on the actual situation, select certain levels of classes as measurement areas, with each measurement area containing multiple measurement points.

[0075] Figure 2 The diagram illustrates the clustering results of the above clustering method, based on... Figure 2 As can be seen, this clustering method divides a certain number of measuring points (denoted as LS) deployed in the dam into six measuring regions (corresponding to six clusters). The first measuring region includes LS1, LS2, LS3, and LS4; the second measuring region includes LS20, LS22, LS23, LS21, LS24, LS25, and LS26; the third measuring region includes LS8, LS9, LS10, and LS11; the fourth measuring region includes LS5, LS6, and LS7; the fifth measuring region includes LS18, LS19, LS27, and LS28; and the sixth measuring region includes LS13, LS15, LS14, LS16, and LS17.

[0076] The following section uses a test area of ​​a dam as an example to describe in detail the process of predicting dam deformation.

[0077] S102. Based on the monitored displacements of multiple measuring points within a measuring area of ​​the dam during the first historical time period and the monitored displacements of multiple measuring points during the second historical time period, the fitted displacements of multiple measuring points during the second historical time period are obtained.

[0078] Among them, multiple measuring points in the survey area have the same deformation pattern, and the first historical time period is before the second historical time period.

[0079] In this embodiment of the application, the displacement of the dam in one of the historical time periods can be obtained by combining the monitored displacements of the dam in multiple historical time periods (referred to as the fitted displacement). For example, the fitted displacement of the dam in the second historical time period can be fitted based on the monitored displacements of multiple measuring points (which belong to a measuring area) of the dam in the first and second historical time periods.

[0080] As one approach, the fitted displacement of the dam can also be directly fitted based on the monitored displacement of the dam during a specific historical period. For example, the fitted displacement of multiple measuring points within a measuring area of ​​the dam during a second historical period can be fitted based on the monitored displacement of those points.

[0081] The aforementioned deformation pattern refers to the pattern of displacement change over time. Figure 3 It indicated Figure 2 The clustering results show the time-varying patterns of the monitored displacements of the four measuring points (LS1, LS2, LS3, LS4) within the first measuring area. Figure 3 It can be seen that the changing trends of the monitored displacements at the four measuring points are almost the same. Therefore, the deformation patterns of the four measuring points in the first measuring area are the same.

[0082] In this embodiment, the Firefly-Random Forest algorithm can be used to fit displacements to obtain the fitted displacements of multiple measuring points in the second historical time period. Specifically, the parameters of the Random Forest (RF) are first optimized using the Firefly Algorithm (FA), and then the optimized RF is used to fit the monitored displacements of multiple measuring points in a measuring area within the first and second historical time periods to obtain the fitted displacements of multiple measuring points in the second historical time period. Since the Firefly-Random Forest algorithm is a common algorithm in this technical field, this embodiment will not elaborate further on the above process.

[0083] In one scenario, the Firefly algorithm optimizes the parameters of the random forest, such as the number of variables selected (Mtry) and the number of trees in operation (Ntree). The optimized Mtry is 3 and Ntree is 100.

[0084] Alternatively, other fitting algorithms can be used to fit the displacements of multiple measuring points in the second historical time period, and this application does not limit the specific algorithms used.

[0085] S103. Based on the monitored displacement and fitted displacement of multiple measuring points in the second historical time period, determine the displacement residuals of multiple measuring points in the measurement area.

[0086] The displacement residuals of multiple measuring points within the measurement area during the second historical time period are the differences between the monitored displacements and fitted displacements of these multiple measuring points during the second historical time period. Figure 2 Taking measuring point LS1 in the first measuring area as an example, Figure 4 The diagram illustrates the monitored displacement, fitted displacement, and displacement residual of measuring point LS1 during the second historical time period.

[0087] S104. Optimize the displacement residuals of multiple measuring points in the test area to obtain optimized displacement residuals of multiple measuring points.

[0088] In this embodiment, the optimization method for the displacement residual of each of the multiple measuring points is the same, combined with... Figure 1 ,like Figure 5 As shown, for ease of description, any one of the multiple measuring points in the survey area is taken as the target measuring point. The following describes the process of optimizing the displacement residual of the target measuring point to obtain the optimized displacement residual of the target measuring point through S1041-S1044.

[0089] S1041. Based on the displacement residual of the target measuring point, decompose the displacement residual of each of the multiple measuring points to obtain multiple modal residuals corresponding to the multiple measuring points; wherein, each measuring point corresponds to at least one modal residual.

[0090] Optionally, combined Figure 5 ,like Figure 6 As shown, S1041 includes S1041A-S1041B.

[0091] S1041A. Determine the number of modes of the displacement residual based on the center frequency of the displacement residual at the target measuring point.

[0092] In one implementation, the number of bit modes is set to an integer range of 2 to 10, and the displacement residual is modally decomposed in ascending order of the number of modes. After each decomposition, the center frequency of each modal residual is obtained. When the center frequencies of adjacent modal residuals are similar, the modal decomposition is considered to be an over-decomposition of the signal, and the modal number corresponding to this decomposition - 1 is determined as the modal number of the displacement residual.

[0093] S1041B. The displacement residual of each of the multiple measuring points is decomposed using the variational mode decomposition method to obtain multiple modal residuals corresponding to the multiple measuring points. The number of modal residuals corresponding to each measuring point is equal to the number of modes (the number of modes is greater than or equal to 1, therefore, each measuring point corresponds to at least one modal residual).

[0094] The Variational Mode Decomposition (VMD) method described above is a signal processing method that can decompose a multimodal signal (in this embodiment, the multimodal signal is the displacement residual of each measuring point) into a set of single-mode components (IMFs) of different modes (i.e., the modal residuals corresponding to each measuring point).

[0095] In one implementation, for each of multiple measuring points, the displacement residual is decomposed using variational mode decomposition (VMD) based on the mode number K of the displacement residual, yielding K modal residuals corresponding to the measuring point. Specifically, VMD decomposes the displacement residual by minimizing the following objective function.

[0096] The objective function is:

[0097] Among them, u k (t) represents the k-th modal residual in the modal residual corresponding to the measurement point, ω k Let x(t) represent the center frequency of the k-th displacement residual, and let x(t) represent the monitored displacement of the measuring point in the second historical time period. This represents the difference between the k-th modal residual corresponding to the measuring point and the monitored displacement of the measuring point in the second historical time period. Indicates that u k (t) and ω k The smallest value in the middle is taken as u k (t) Substitute The calculation results obtained later; This represents a smoothness constraint term used to adjust the smoothness of the modal residuals.

[0098] Still with Figure 2 Taking measuring point LS1 in the first measurement area as an example, if the modal number K of the displacement residual is determined to be 4 based on the center frequency of the displacement residual of measuring point LS1, then according to the modal number K, the displacement residuals of measuring points LS1, LS2, LS3, and LS4 in the first measurement area are decomposed into 4 IMFs respectively using the variational modal decomposition method, resulting in 16 IMFs. For example, the displacement residual of LS1 is decomposed into IMF1 to IMF4, the displacement residual of LS2 is decomposed into IMF5 to IMF8, the displacement residual of LS3 is decomposed into IMF9 to IMF12, and the displacement residual of LS4 is decomposed into IMF13 to IMF16. Figure 7It illustrates how the 16 IMFs have changed over time.

[0099] As can be seen from the above, S1041 decomposes the displacement residuals of multiple measuring points in the measuring area where the target measuring point is located based on the modal number of the displacement residuals of the target measuring point. Subsequently, the multiple modal residuals corresponding to the multiple measuring points obtained by decomposition are used as optimization conditions for the displacement residuals of the target measuring point to optimize the displacement residuals of the target measuring point.

[0100] As is well known, variational mode decomposition (VMD) can extract effective information from displacement residuals. Therefore, when multiple measuring points within a survey area exhibit the same deformation patterns, decomposing the displacement residual of the target measuring point using the mode number of the target point's displacement residual can extract effective information. Furthermore, decomposing the displacement residuals of other measuring points within the survey area using the mode number of the target point's displacement residual can extract effective information from the displacement residuals of other measuring points that is similar to and / or related to the target measuring point's displacement residual. Therefore, when the complex operating environment of a dam makes it difficult to analyze the factors causing deformation of the dam's internal structure, S1041 can provide more effective information that more closely reflects the deformation trend of the dam's internal structure for optimizing the displacement residual of the target measuring point. Based on this effective information, the optimized displacement residual can predict the displacement of the target measuring point in the future time period with higher prediction accuracy.

[0101] S1042. Select multiple related modal residuals from multiple modal residuals corresponding to multiple measuring points; the correlation coefficients between the displacement residual of the target measuring point and the multiple related modal residuals are all greater than the preset threshold.

[0102] In one implementation, the correlation coefficient between the displacement residual of the target measuring point and the modal residuals corresponding to multiple measuring points is the Pearson correlation coefficient. For example, the preset threshold can be set to 0.3174. Since the calculation method of the Pearson correlation coefficient is a common method in this technical field, it will not be elaborated upon here.

[0103] Continue with Figure 2 Taking measuring point LS1 in the first measuring area as an example, the Pearson correlation coefficient between each modal residual (IMF) in IMF1 to IMF16 and the displacement residual of measuring point LS1 is calculated. When the Pearson correlation coefficient between a certain modal residual and the displacement residual of measuring point LS1 is greater than 0.3174, the modal residual is taken as the relevant modal residual.

[0104] Optionally, the correlation coefficient between the displacement residual of the target measuring point and the modal residuals corresponding to multiple measuring points can also be the Spearman rank correlation coefficient or the Kendall rank correlation coefficient, etc. The above-mentioned preset threshold can also be other values ​​between 0 and 1 that meet the requirements. This application embodiment does not limit it.

[0105] As can be seen from the above, S1042 calculates the correlation coefficient between the displacement residual of the target measuring point and the multiple modal residuals corresponding to multiple measuring points. Modal residuals with correlation coefficients less than or equal to a preset threshold are identified as noise information in the displacement residuals and are filtered out. Modal residuals with correlation coefficients greater than the preset threshold are identified as relevant modal residuals containing valid information. The relevant modal residuals are used to optimize the displacement residuals of the target measuring point, which can improve the optimization effect of the displacement residuals of the target measuring point and make the displacement residuals of the target measuring point more accurate.

[0106] S1043. From multiple modal residual groups, select the target modal residual group that has the strongest correlation with the displacement residual of the target measuring point; multiple modal residual groups are obtained by combining multiple related modal residuals, and each modal residual group includes N related modal residuals.

[0107] As can be seen from S1041 above, the number N of relevant modal residuals in each modal residual group is equal to the number of modes K mentioned above.

[0108] In one implementation, the correlation between the modal residual set and the displacement residual of the target measurement point satisfies:

[0109]

[0110] Where f1 represents the correlation coefficient between the modal residual set and the displacement residual of the target measurement point, r i This represents the correlation coefficient between the i-th correlated modal residual in the modal residual set and the displacement residual of the target measurement point. This represents the sum of the correlation coefficients between each relevant modal residual in the modal residual group and the displacement residual of the target measuring point.

[0111] by Figure 2 Taking the measuring point LS1 in the first measuring area as an example, the number of modes K=4. After screening and obtaining multiple related modal residuals (e.g., IMF2, IMF4, IMF9, IMF10, IMF13), four related modal residuals are selected from the above multiple related modal residuals and combined to obtain a total of five modal residual groups. Then, the correlation coefficient between each modal residual group and the displacement residual of the target measuring point is calculated. The modal residual group with the largest correlation coefficient (i.e. the strongest correlation) is taken as the target modal residual group (e.g., {IMF2, IMF9, IMF10, IMF13}).

[0112] As can be seen from the above, S1043 combines multiple related modal residuals according to the number of modes K to obtain multiple modal residual groups containing K related modal residuals. Among them, the modal residual group with the strongest correlation to the displacement residual of the target measuring point contains the most effective information. The modal residual group containing the most effective information is taken as the target modal residual group. This target modal residual group can provide more effective information that is closer to the deformation trend of the internal structure of the dam for the optimization of the displacement residual of the target measuring point.

[0113] S1044. The relevant modal residuals in the target modal residual group are weighted and summed to obtain the optimized displacement residual of the target measuring point.

[0114] Optionally, combined Figure 6 ,like Figure 8 As shown, S1044 includes S1044A-S1044B.

[0115] S1044A. Calculate multiple weighted sums of relevant modal residuals in the target modal residual group under multiple residual weight coefficients; wherein, one set of residual weight coefficients corresponds to one weighted sum.

[0116] The sum of the residual weight coefficients in the above multiple sets of residual weight coefficients is 1. Assume that for a set of residual weight coefficients (a1, a2, ... a... K ), where a1 represents the weight of the first relevant mode residual x1, a2 represents the weight of the second relevant mode residual x2, and a K Let x represent the residual of the Kth related mode. K The weights, the above weighted summation value satisfies

[0117] S1044B: Among multiple weighted sums, the weighted sum with the strongest correlation to the displacement residual of the target measuring point is taken as the optimized displacement residual of the target measuring point.

[0118] In this embodiment, the correlation coefficients between multiple weighted sums and the displacement residuals of the target measuring point are calculated. The largest correlation coefficient indicates the strongest correlation. The correlation coefficient with the displacement residual of the target measuring point satisfies:

[0119]

[0120] Among them, R 2 Represents the weighted sum value The correlation coefficient between the displacement residual of the target measuring point and the target measuring point, a i Let x represent the weight of the residual of the i-th relevant mode. i Represents the residual of the i-th related mode. This represents the average value of the K related modal residuals corresponding to the target measurement point.

[0121] by Figure 2 Taking measuring point LS1 in the first measuring area as an example, after obtaining the target modal residual set (e.g., {IMF2, IMF9, IMF10, IMF13}), the target modal residual set is weighted and summed based on multiple sets of residual weight coefficients to obtain multiple weighted sum values. For example, among the multiple sets of residual weight coefficients, the weighted sum value corresponding to the weighted residual coefficients (0.1, 0.2, 0.3, 0.4) (i.e., 0.1×IMF2+0.2×IMF9+0.3×IMF10+0.4×IMF13) has the largest correlation coefficient with the optimized displacement residual of the target measuring point.

[0122] As can be seen from the above, S1044 simulates various scenarios for reconstructing the residuals of the target modal residual group by adjusting the weighting coefficients of multiple related modal residuals in the target modal residual group; and indicates the similarity between the residuals reconstructed by the target modal residual group and the displacement residuals of the target measuring point by the correlation between multiple weighted sums (corresponding to multiple sets of weighting coefficients) and the displacement residuals of the target measuring point (the stronger the correlation between the weighted sum and the displacement residuals of the target measuring point, the higher the similarity between the residuals reconstructed by the target modal residual group and the displacement residuals of the target measuring point). Based on this, selecting the weighted sum with the strongest correlation to the displacement residuals of the target measuring point as the optimized displacement residual of the target measuring point can yield the optimized residual that is most similar to the displacement residual variation pattern of the target measuring point.

[0123] In summary, the process of optimizing the displacement residuals of the target measurement points using S104 can be divided into three steps.

[0124] The first step is to decompose the displacement residuals of multiple measuring points in the measurement area based on the modal number of the target measuring point, and obtain the modal residuals corresponding to multiple measuring points. The first step corresponds to S1041, which provides more effective information that is closer to the deformation trend of the internal structure of the dam for the optimization of the displacement residuals of the target measuring point.

[0125] The second step is to filter the modal residuals corresponding to multiple measuring points to obtain the target modal residual group; the second step corresponds to S1042-S1043, which is to remove noise information and filter out the target modal residual group containing as much effective information as possible for the optimization processing of the displacement residuals of the target measuring points.

[0126] The third step is to reconstruct the optimized residuals through the target modal residual group; the third step corresponds to S1044, so that the optimized residuals obtained by reconstruction are as consistent as possible with the variation law of the displacement residuals of the target measuring point.

[0127] In summary, the optimized residual obtained through S104 optimization contains more limited information and is closer to the variation law of the displacement residual of the target measuring point, which can make the prediction accuracy of the displacement of the target measuring point in the future time period predicted by the optimized residual higher.

[0128] S105. Based on the fitted displacements of multiple measuring points in the future time period and the optimized displacement residuals of multiple measuring points, determine the displacements of multiple measuring points in the future time period.

[0129] The fitted displacements of multiple measuring points in the future time period are obtained by fitting the monitored displacements of multiple measuring points in the measurement area during historical time periods. For details on the data fitting process, please refer to the relevant description of data fitting in S102, which will not be elaborated upon here.

[0130] For example, in combination Figure 8 ,like Figure 9 As shown, S105 includes S1051-S1052.

[0131] S1051. An autoregressive integral moving average model is used to process the optimized displacement residuals of the target measuring point, and the displacement residuals of the target measuring point in the future time period are predicted.

[0132] It should be understood that the aforementioned Autoregressive Integrated Moving Average (ARIMA) model is a classic statistical model used for time series data forecasting. The basic form of the ARIMA model can be represented as ARIMA(p,d,q). Here, p is the order of the autoregressive term (AR), representing the number of lagged observations used in the model; d is the differencing order, representing the number of differencing operations performed to make the time series stationary; and q is the order of the moving average term (MA), representing the number of lagged values ​​of past prediction errors used in the prediction error.

[0133] In one implementation, the ARIMA model satisfies:

[0134]

[0135] θ(B)=1-θ1B-θ2B 2 -…-θ q B q

[0136] φ(B)=1-φ1B-φ2B 2 -…-φ p B p

[0137] Where B represents the delay operator, Y t This represents the optimized displacement residual of the target measuring point. Let θ(B) represent the displacement residual of the target measurement point over a future time period, θ(B) represent the autoregressive operator (AR) with the retardation operator B introduced, and φ(B) represent the moving average operator (MA) with the retardation operator B introduced. t θ1 represents the first-order autoregressive operator, θ2 represents the second-order autoregressive operator, and B represents the random error. 2 Let θ represent the second-order delay operator. q B represents the q-th order autoregressive operator. q φ1 represents the q-th order delay operator; φ2 represents the first-order moving average operator; φ3 represents the second-order moving average operator; φ4 represents the second-order moving average operator; φ5 represents the first-order moving average operator; φ6 represents the second-order moving average operator; φ7 represents the second-order moving average operator; φ8 represents the second-order moving average operator; φ9 represents the second-order moving average operator; φ1 represents the first-order moving average operator; φ2 represents the second-order moving average operator; φ1 represents the second-order moving average operator; φ2 represents the second-order moving average operator; φ9 represents the second-order moving average operator; φ1 represents the second-order moving average operator; φ2 ... p B represents the p-th order moving average operator. p This represents the p-th order delay operator. In the ARIMA model, θ1, θ2…θ q and φ1, φ2…θ q Let be the quantity to be solved.

[0138] In this embodiment of the application, for the ARIMA model, the values ​​of parameters p, d, and q in ARIMA(p,d,q) are first set, and then θ1, θ2…θ are solved using the above formula. q and φ1, φ2…θ q Then, θ(B) and φ(B) are obtained by solving for them. The displacement residuals of the target measuring point are predicted for future time periods.

[0139] Optionally, the basic form of the ARIMA model can be ARIMA(0, 0, 2), or other forms, and the embodiments of this application do not impose further limitations.

[0140] In this embodiment of the application, the optimized displacement residual of the measuring point obtained in S104 is obtained based on the displacement of the measuring point in the second historical time period. The optimized displacement residual can more accurately reflect the change of displacement residual in the second historical time period. Based on this, in S1051, the optimized displacement residual is further analyzed and processed to more reasonably and accurately predict the displacement residual of the measuring point in the future time period, which helps to more accurately predict the displacement of the measuring point in the future time period.

[0141] S1052. The fitted displacement and displacement residual of the target measuring point in the future time period are superimposed to obtain the displacement of the target measuring point in the future time period.

[0142] Understandably, the above superposition is performed in chronological order, adding the fitted displacement and displacement residual of the target measurement point in the future time period.

[0143] In summary, this embodiment of the application fits the monitored displacements of multiple measuring points within a measurement area of ​​a dam in a first and second historical time period to obtain the fitted displacements of the multiple measuring points in the second historical time period. By comparing the monitored displacements and fitted displacements of the multiple measuring points in the second historical time period, displacement residuals for the multiple measuring points are obtained. These residuals are then optimized to obtain optimized residuals for the multiple measuring points. Based on the fitted displacements and optimized displacement residuals of the multiple measuring points in future time periods, the displacements of the multiple measuring points in future time periods are predicted. In the process of predicting the displacements of multiple measuring points in future time periods, this embodiment of the application optimizes the displacement residuals of the multiple measuring points, making the displacements of the multiple measuring points in future time periods obtained through the optimized displacement residuals more reasonable and accurate in predicting the displacement residuals of the measuring points in future time periods. This helps to more accurately predict the displacements of the measuring points in future time periods, thereby improving the prediction accuracy of dam deformation.

[0144] Accordingly, embodiments of this application provide a device for predicting dam deformation, such as... Figure 10 As shown, it includes a fitting module 901, a determination module 902, an optimization module 903, and a prediction module 904.

[0145] The fitting module 901 is used to fit the monitored displacements of multiple measuring points within a survey area of ​​the dam in a first historical time period and the monitored displacements of multiple measuring points in a second historical time period to obtain the fitted displacements of multiple measuring points in the second historical time period; wherein the multiple measuring points within the survey area have the same deformation pattern; and the first historical time period is before the second historical time period. For example, the fitting module 901 is used to implement S102 of the above-mentioned method for predicting dam deformation.

[0146] The determination module 902 is used to determine the displacement residuals of multiple measuring points within the measurement area based on the monitored displacements and fitted displacements of multiple measuring points during the second historical time period. For example, the determination module 902 is used to implement S103 of the above-mentioned method for predicting dam deformation.

[0147] The optimization module 903 is used to optimize the displacement residuals of multiple measuring points within the survey area to obtain optimized displacement residuals for multiple measuring points. For example, the optimization module 903 is used to implement step S104 of the above-mentioned method for predicting dam deformation.

[0148] The prediction module 904 is used to determine the displacement of multiple measuring points in the future time period based on the fitted displacement of multiple measuring points and the optimized displacement residual of multiple measuring points; the fitted displacement of multiple measuring points in the future time period is obtained by fitting data from the monitored displacement of multiple measuring points in the measurement area in the historical time period. For example, the prediction module 904 is used to implement S105 of the above-mentioned method for predicting dam deformation.

[0149] Optionally, the optimization module 903 is specifically used for: decomposing the displacement residual of each of the multiple measuring points based on the displacement residual of the target measuring point to obtain multiple modal residuals corresponding to the multiple measuring points; wherein each measuring point corresponds to at least one modal residual. Multiple relevant modal residuals are selected from the multiple modal residuals corresponding to the multiple measuring points; the correlation coefficients between the displacement residual of the target measuring point and the multiple relevant modal residuals are all greater than a preset threshold. From the multiple modal residual groups, the target modal residual group with the strongest correlation to the displacement residual of the target measuring point is selected; the multiple modal residual groups are obtained by combining multiple relevant modal residuals, and each modal residual group includes N relevant modal residuals. The relevant modal residuals in the target modal residual group are weighted and summed to obtain the optimized displacement residual of the target measuring point. For example, the optimization module 903 is specifically used to implement S1041-S1044 of the above-mentioned method for predicting dam deformation.

[0150] Optionally, the prediction module 904 is specifically used to: process the optimized displacement residual of the target measuring point using an autoregressive integral moving average model to predict the displacement residual of the target measuring point in the future time period. The fitted displacement and displacement residual of the target measuring point in the future time period are superimposed to obtain the displacement of the target measuring point in the future time period. For example, the prediction module 904 is specifically used to implement S1051-S1052 of the above-mentioned method for predicting dam deformation.

[0151] In one implementation, combined with Figure 10 ,like Figure 11 As shown, the aforementioned device for predicting dam deformation also includes a classification module 905. The classification module 905 is used to classify all measuring points deployed in the dam to obtain multiple measuring zones. For example, the classification module 905 is specifically used to implement step S101 of the aforementioned method for predicting dam deformation.

[0152] The various modules of the above-mentioned device for predicting dam deformation can also be used to perform other steps in the above-mentioned method embodiments. All relevant content involved in the above-mentioned method embodiments can be referred to in the functional description of the corresponding functional module, and will not be repeated here.

[0153] This application also provides an electronic device, including: a processor and a memory coupled to the processor; the memory is used to store computer instructions, and when the electronic device is running, the processor executes the computer instructions stored in the memory to cause the electronic device to perform the methods described in the above embodiments. The processor can implement the above-described fitting module 501, determination module 502, optimization module 503, prediction module 504, and classification module 505; the memory can also be used to store monitored displacements, fitted displacements, displacement residuals, and optimized displacement residuals of multiple measurement points.

[0154] This application also provides a computer-readable storage medium including a computer program that, when run on a computer, performs the methods described in the above embodiments.

[0155] This application also provides a computer program product, which includes computer program instructions that, when run on a computer, execute the methods described in the above embodiments.

[0156] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

[0157] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for predicting dam deformation, characterized in that, include: Based on the monitored displacements of multiple measuring points within a survey area of ​​the dam in the first historical time period and the monitored displacements of the same multiple measuring points in the second historical time period, the fitted displacements of the multiple measuring points in the second historical time period are obtained; wherein, the multiple measuring points within the survey area have the same deformation pattern; the first historical time period is before the second historical time period; Based on the monitored displacement and fitted displacement of the multiple measuring points in the second historical time period, determine the displacement residuals of the multiple measuring points in the measuring area; The displacement residuals of multiple measuring points within the survey area are optimized to obtain the optimized displacement residuals of the multiple measuring points; any one of the multiple measuring points within the survey area is taken as the target measuring point, and the optimized displacement residual of the target measuring point is determined, including: Based on the displacement residual of the target measuring point, the displacement residual of each of the plurality of measuring points is decomposed to obtain a plurality of modal residuals corresponding to the plurality of measuring points; wherein, each measuring point corresponds to at least one modal residual; Multiple relevant modal residuals are selected from the multiple modal residuals corresponding to the multiple measuring points; the correlation coefficients between the displacement residual of the target measuring point and the multiple relevant modal residuals are all greater than a preset threshold; From multiple modal residual groups, the target modal residual group with the strongest correlation to the displacement residual of the target measuring point is selected; the multiple modal residual groups are obtained by combining the multiple related modal residuals, and each modal residual group includes N related modal residuals; The weighted summation of the relevant modal residuals in the target modal residual set yields the optimized displacement residual of the target measuring point. The displacements of the multiple measuring points in the future time period are determined based on the fitted displacements of the multiple measuring points and the optimized displacement residuals of the multiple measuring points in the future time period; the fitted displacements of the multiple measuring points in the future time period are obtained by fitting data from the monitored displacements of multiple measuring points in the measurement area in the historical time period.

2. The method as described in claim 1, characterized in that, Based on the displacement residual of the target measuring point, the displacement residual of each of the plurality of measuring points is decomposed to obtain multiple modal residuals corresponding to the plurality of measuring points, including: The number of modes of the displacement residual is determined based on the center frequency of the displacement residual at the target measuring point. The displacement residual of each of the plurality of measuring points is decomposed using the variational mode decomposition method to obtain the modal residuals corresponding to the plurality of measuring points; wherein, the number of modal residuals corresponding to each measuring point is equal to the number of modes.

3. The method as described in claim 1, characterized in that, N equals the number of modes.

4. The method as described in claim 1, characterized in that, The optimized displacement residual of the target measurement point is obtained by weighted summation of multiple related modal residuals in the target modal residual set, including: Calculate multiple weighted sums of the relevant modal residuals in the target modal residual group under multiple residual weight coefficients; wherein, one set of residual weight coefficients corresponds to one weighted sum. The weighted summation value with the strongest correlation to the displacement residual of the target measuring point is taken as the optimized displacement residual of the target measuring point.

5. The method as described in claim 1, characterized in that, Taking any one of the multiple measuring points within the measurement area as the target measuring point, determine the displacement of the target measuring point over a future time period, including: An autoregressive integral moving average model is used to process the optimized displacement residuals of the target measuring point, and the displacement residuals of the target measuring point in the future time period are predicted. The displacement of the target measuring point in the future time period is obtained by superimposing the fitted displacement and displacement residual of the target measuring point in the future time period.

6. The method as described in claim 1, characterized in that, The method further includes: All the measuring points deployed in the dam were classified to obtain multiple measuring areas.

7. A device for predicting dam deformation, characterized in that, It includes a fitting module, a determination module, an optimization module, and a prediction module; The fitting module is used to fit the monitored displacements of multiple measuring points in a survey area of ​​the dam during a first historical time period and the monitored displacements of the same multiple measuring points during a second historical time period to obtain the fitted displacements of the multiple measuring points during the second historical time period; wherein, the multiple measuring points in the survey area have the same deformation pattern; the first historical time period is before the second historical time period; The determining module is used to determine the displacement residuals of multiple measuring points within the measuring area based on the monitored displacements and fitted displacements of the multiple measuring points during the second historical time period. The optimization module is used to optimize the displacement residuals of multiple measuring points within the measurement area to obtain optimized displacement residuals of the multiple measuring points; taking any one of the multiple measuring points within the measurement area as a target measuring point, and determining the optimized displacement residual of the target measuring point, including: decomposing the displacement residual of each of the multiple measuring points based on the displacement residual of the target measuring point to obtain multiple modal residuals corresponding to the multiple measuring points; wherein, each measuring point corresponds to at least one modal residual; selecting multiple related modal residuals from the multiple modal residuals corresponding to the multiple measuring points; the correlation coefficient between the displacement residual of the target measuring point and the multiple related modal residuals is greater than a preset threshold; selecting the target modal residual group with the strongest correlation to the displacement residual of the target measuring point from the multiple modal residual groups; the multiple modal residual groups are obtained by combining the multiple related modal residuals, and each modal residual group includes N related modal residuals; performing a weighted summation of the related modal residuals in the target modal residual group to obtain the optimized displacement residual of the target measuring point; The prediction module is used to determine the displacement of the multiple measuring points in the future time period based on the fitted displacement of the multiple measuring points and the optimized displacement residual of the multiple measuring points in the future time period; the fitted displacement of the multiple measuring points in the future time period is obtained by fitting the data of the monitored displacement of multiple measuring points in the measurement area in the historical time period.

8. An electronic device, characterized in that, The device includes a processor and a memory coupled to the processor; the memory is used to store computer instructions, which, when the electronic device is running, are executed by the processor to cause the electronic device to perform the method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, It includes computer program instructions that, when executed by a computer, cause the computer to perform the method as described in any one of claims 1 to 6.

Images