Hydraulic structure settlement monitoring and early warning method for hydraulic engineering

Abstract

The invention relates to the technical field of building settlement monitoring, in particular to a hydraulic structure settlement monitoring and early warning method for a hydraulic engineering, and the method comprises the steps: clustering environment interference data of each dimension, and obtaining an influence direct factor of the environment interference data of each dimension on inclination angle data based on a clustering result of the environment interference data of each dimension; analyzing the anomaly of the correlation between the environmental interference data of any two dimensions under the time corresponding to the inclination angle data, and combining the change degree of the inclination angle data to obtain the environmental interference anomaly degree of the environmental interference data of each dimension at any moment; and further obtaining an SVM model training weight, and performing compensation correction on inclination angle data to complete settlement prediction. By considering the gain influence among various environmental interference data, the model can better process interference in a complex environment, and the robustness of the model in practical application and the accuracy of settlement monitoring are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of building settlement monitoring, and particularly to a method for settlement monitoring and early warning of hydraulic structures for water conservancy projects. Background Art

[0002] With the rapid development of urbanization and building technology, the safety and stability of building structures have received increasing attention. Especially in large-scale, high-rise or long-term used building projects, structural settlement has become an important monitoring index, which is directly related to the safety and service life of the building. The existing methods for settlement early warning of hydraulic structures usually install inclinometer sensors at positions such as the edges and corners of the building to monitor the inclination angle of the building in real time, and unify the monitoring of the angle changes of several settlement monitoring points through the combination of BIM technology and the Internet of Things. However, due to various environmental and weather impacts, it usually leads to affected interference data of hydraulic structures. Therefore, it is usually necessary to use the support vector machine SVM model to compensate the monitoring data of the inclinometer.

[0003] For the support vector machine model that compensates the inclinometer monitoring data, the inclinometer monitoring data and multiple environmental interference data at the same time series are usually used as the training data set and input into the model for training, so as to perform compensation and correction based on the trained model. The conventional training of the support vector machine SVM model is one-to-one training. However, in a more complex environment interference, multiple environmental interference data usually appear simultaneously, and there is a gain performance in the influence of some environmental interferences on the hydraulic structure. This situation will lead to an inaccurate compensation model obtained by the conventional training method. Summary of the Invention

[0004] In order to solve the above technical problems, the purpose of the present invention is to provide a method for settlement monitoring and early warning of hydraulic structures for water conservancy projects.

[0005] According to the first aspect of the embodiments of the present invention, a method for settlement monitoring and early warning of hydraulic structures for water conservancy projects is provided, and the technical solution adopted is specifically as follows: Collect the inclination data and multi-dimensional environmental interference data of the hydraulic structure; Cluster the environmental interference data of each dimension to obtain environmental interference data clusters, analyze the influence uniformity of the environmental interference data clusters on the inclination data, and analyze the distribution of the environmental interference data within the environmental interference data clusters, so as to obtain the direct influence factor of the environmental interference data of each dimension on the inclination data; Analyze the abnormality of the correlation between the environmental interference data in any two dimensions corresponding to the inclination angle data at a specific time, and combine the degree of change between the inclination angle data at any moment and the inclination angle data at its adjacent moment to obtain the degree of environmental interference abnormality of the environmental interference data in each dimension at any moment; According to the influence direct factor and the degree of environmental interference abnormality, obtain the weight of the environmental interference data in each dimension when participating in the training of the support vector machine (SVM) model at any moment, and complete the compensation and correction of the inclination angle data; Based on the compensated and corrected inclination angle data, conduct settlement prediction to complete settlement monitoring.

[0006] In some embodiments of the present invention, after clustering the environmental interference data in each dimension to obtain environmental interference data clusters, the following steps are further included: Analyze the continuity of the time corresponding to the environmental interference data in the environmental interference data clusters to obtain multiple continuous interference environmental data groups; Among them, analyzing the influence uniformity of the environmental interference data clusters on the inclination angle data includes: Analyze the influence uniformity of each continuous interference environmental data group in the environmental interference data clusters on the inclination angle data.

[0007] In some embodiments of the present invention, analyzing the influence uniformity of each continuous interference environmental data group in the environmental interference data clusters on the inclination angle data includes: Analyze the dispersion degree of the inclination angle data corresponding to each continuous interference environmental data group in the environmental interference data clusters, and combine the amplitude of the environmental interference data in other dimensions at the corresponding time to obtain the influence uniformity of each continuous interference environmental data group in the environmental interference data clusters on the inclination angle data.

[0008] In some embodiments of the present invention, analyzing the distribution of the environmental interference data in the environmental interference data clusters includes: Calculate the within-cluster sum of squares after normalizing the environmental interference data clusters, and obtain the data volume of any continuous interference environmental data group in the environmental interference data clusters to obtain the distribution of the environmental interference data in the environmental interference data clusters; Among them, analyzing the influence uniformity of the environmental interference data clusters on the inclination angle data and analyzing the distribution of the environmental interference data in the environmental interference data clusters to obtain the influence direct factor of the environmental interference data in each dimension on the inclination angle data includes: Weight the influence uniformity by the data volume, and combine the within-cluster sum of squares to obtain the influence direct factor of the environmental interference data in each dimension on the inclination angle data.

[0009] In some embodiments of the present invention, analyzing the abnormality of the correlation between the environmental interference data of any two dimensions corresponding to the inclination angle data at a corresponding time includes: Analyzing the correlation factor between the environmental interference data of any two dimensions; Defining a time window corresponding to any moment; Obtaining the Pearson correlation coefficient between the environmental interference data of any two dimensions within the time window where any moment is located, and combining with the correlation factor to obtain the abnormality of the correlation between the environmental interference data of any two dimensions within the time window where any moment is located.

[0010] In some embodiments of the present invention, analyzing the correlation factor between the environmental interference data of any two dimensions includes: Segmenting the inclination angle data to obtain inclination angle change segments; Calculating the Pearson correlation coefficient between the environmental interference data of any two dimensions within the time corresponding to the inclination angle change segment, and combining with the amplitude of the inclination angle data within the inclination angle change segment to obtain the correlation factor between the environmental interference data of any two dimensions.

[0011] In some embodiments of the present invention, segmenting the inclination angle data to obtain inclination angle change segments includes: Judging the time series composed of the inclination angle data, and the judgment criterion is whether the inclination angle data is 0; If it is 0, stop and form an inclination angle change segment; If it is not 0, continue to judge the next inclination angle data; Repeat this operation to obtain a plurality of continuous inclination angle change segments.

[0012] In some embodiments of the present invention, the degree of change between the inclination angle data at any moment and the inclination angle data at its adjacent moment includes: Calculating the mean value of the inclination angle data within the time window corresponding to any moment; Performing linear normalization processing on the mean value and the inclination angle data within the inclination angle change segment to obtain normalized inclination angle data, representing the degree of change between the inclination angle data at any moment and the inclination angle data at its adjacent moment.

[0013] In some embodiments of the present invention, collecting the inclination angle data and multi-dimensional environmental interference data of a hydraulic structure includes: Collecting the inclination angle data and multi-dimensional environmental interference data of the hydraulic structure at the current moment, and obtaining the inclination angle data and multi-dimensional environmental interference data within the previous month of the current moment; Performing preprocessing of standardization on the inclination angle data and the multi-dimensional environmental interference data to obtain standardized inclination angle data and standardized multi-dimensional environmental interference data.

[0014] In some embodiments of the present invention, clustering the environmental interference data for each dimension to obtain environmental interference data clusters includes: Performing K-means clustering on the environmental interference data for each dimension, determining the optimal number of clusters by the elbow method, and obtaining the environmental interference data clusters.

[0015] Compared with the prior art, the method for settlement monitoring and early warning of hydraulic structures for water conservancy projects provided by the present invention has the following beneficial effects: After clustering and analyzing the environmental interference data for each dimension, the present invention obtains the direct influence factors of the environmental interference data for each dimension on the current hydraulic structure based on the clustering results; then obtains the change section based on the inclination data, combines the actual swaying situation of the hydraulic structure to obtain the correlation factors between the environmental interference data, and further obtains the authenticity and abnormality evaluation of the environmental interference data for each dimension according to the performance of the correlation coefficients between the environmental interference data items; finally, places it in the SVM model to optimize the compensation model and improve the compensation accuracy. By considering the gain effect between various environmental interference data, the model can better handle the interference in a complex environment and improve the robustness of the model in practical applications; by analyzing the correlation between the environmental interference data and the inclination data, and considering the authenticity and abnormality of the environmental interference data, the SVM model is optimized and the accuracy of settlement monitoring is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0017] Figure 1 It is a schematic flowchart of the basic process of a method for settlement monitoring and early warning of a hydraulic structure for water conservancy projects provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0018] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following, in combination with the drawings and preferred embodiments, details the specific implementation manners, structures, features, and effects of the method for settlement monitoring and early warning of a hydraulic structure for water conservancy projects proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the technical field to which this invention belongs. Terms such as "including", "comprising" or any other variant thereof are intended to cover non-exclusive inclusion, such that a circuit structure, article or device including a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such article or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the article or device including the element.

[0020] The following specifically describes the specific scheme of a method for settlement monitoring and early warning of hydraulic structures for water conservancy projects provided by the present invention in conjunction with the accompanying drawings.

[0021] Please refer to Figure 1 , which shows the basic process of a method for settlement monitoring and early warning of hydraulic structures for water conservancy projects provided by an embodiment of the present invention.

[0022] As Figure 1 shown, a method for settlement monitoring and early warning of hydraulic structures for water conservancy projects provided by an embodiment of the present invention specifically includes: S100: Collect the inclination data and multi-dimensional environmental interference data of the hydraulic structure.

[0023] According to information such as the structure of the hydraulic structure to be monitored, select the monitoring points, install inclinometers at each monitoring point, and preset the zero value (this implementation is prior art and will not be elaborated here). Obtain the continuous real-time monitoring results of the inclinometers at multiple monitoring points to obtain the inclination data of the hydraulic structure. At the same time, obtain the multi-dimensional environmental interference data such as wind speed and local vibration within the local range of each monitoring point. Finally, each inclination data corresponds to a set of environmental interference data.

[0024] And obtain the inclination data and multi-dimensional environmental interference data within the previous month before the current moment as the reference data set.

[0025] Furthermore, perform standardized preprocessing on the inclination data and multi-dimensional environmental interference data to obtain standardized inclination data and standardized multi-dimensional environmental interference data. It should be noted that unless otherwise specified hereinafter, the inclination data and multi-dimensional environmental interference data both refer to the standardized inclination data and standardized multi-dimensional environmental interference data.

[0026] S200: Cluster the environmental interference data for each dimension to obtain environmental interference data clusters, analyze the degree of influence of the environmental interference data clusters on the inclination data, and analyze the distribution of the environmental interference data within the environmental interference data clusters to obtain the direct influence factor of the environmental interference data for each dimension on the inclination data.

[0027] For the settlement monitoring of hydraulic structures, environmental factors usually have a great interference on the settlement monitoring results. For example, due to reasons such as water flow impact and too high wind speed, these interferences usually cause immediate changes, rather than long-term changes caused by soil deposition, etc. Moreover, they are not noise, but actually affect the monitoring results of the inclinometer. Environmental interference will greatly affect the effect of the support vector machine (SVM) for compensating inclinometer data.

[0028] The occurrence of environmental interference has seasonality and regularity. Therefore, first, for different environmental interference data, it is necessary to first analyze based on the occurrence pattern of a certain environmental interference data in the current area, and then preset the sensitivity of each environmental interference data to the monitoring data of the inclinometer.

[0029] Based on the above analysis, in the embodiment of the present invention, by clustering the environmental interference data of each dimension, environmental interference data clusters are obtained, the influence uniformity of the environmental interference data clusters on the inclinometer data is analyzed, and the distribution of the environmental interference data within the environmental interference data clusters is analyzed to obtain the direct influence factor of the environmental interference data of each dimension on the inclinometer data. Further, it includes: First, cluster the environmental interference data of each dimension to obtain environmental interference data clusters. The specific implementation method is: perform K-means clustering on the environmental interference data of each dimension, and determine the optimal number of clusters by the elbow method to obtain the number of environmental interference data clusters of the environmental interference data of each dimension. Multiple environmental interference data clusters represent multiple amplitude ranges in which the environmental interference data of this dimension appears relatively frequently within a month. The inclinometer data at multiple moments corresponding to the environmental interference data within the environmental interference data cluster reflects the degree of influence on the inclinometer data when this environmental interference occurs.

[0030] Then, analyze the continuity of the moments corresponding to the environmental interference data in the environmental interference data clusters to obtain multiple groups of continuous interference environmental data. The specific implementation method is: for each environmental interference data in the th environmental interference data cluster, judge the adjacent moments. If the moments corresponding to the environmental interference data adjacent to this environmental interference data are adjacent, it is determined as a group of continuous interference environmental data. After traversing all the environmental interference data in this environmental interference data cluster, the Multiple groups of continuous interference environment data groups of an environmental interference data cluster class; at the same time, for environmental interference data where there are no adjacent moments corresponding to adjacent environmental interference data, the environmental interference data at the adjacent moments on the left and right of the moment corresponding to the interference environmental data (i.e., environmental interference data not in the same environmental interference data cluster class) is combined with the interference environmental data to form a continuous interference environment data group; through the above two methods, each environmental interference data in the environmental interference data cluster class is divided into multiple continuous interference environment data groups, and finally each continuous interference environment data group has at least two environmental interference data.

[0031] Then, analyze the degree of uniformity of the influence of the environmental interference data cluster class on the inclination data. Further, analyze the degree of uniformity of the influence of each continuous interference environment data group in the environmental interference data cluster class on the inclination data. The specific implementation method is: analyze the dispersion degree of the inclination data corresponding to each continuous interference environment data group in the environmental interference data cluster class, and combine the amplitudes of the environmental interference data in other dimensions at the corresponding moments to obtain the degree of uniformity of the influence of each continuous interference environment data group in the environmental interference data cluster class on the inclination data. Construct the th th environmental interference data cluster class of the th continuous interference environment data group in the In the formula, represents the degree of uniformity of the influence of the th continuous interference environment data group in the th environmental interference data cluster class of the th dimension environmental interference data on the inclination data; represents the amplitude of the inclination data corresponding to the th interference environmental data in the th continuous interference environment data group in the th environmental interference data cluster class of the th dimension environmental interference data; represents the average value of the amplitudes of the inclination data corresponding to all interference environmental data in the th continuous interference environment data group in the th environmental interference data cluster class of the th dimension environmental interference data; represents the th continuous interference environment data group in the th environmental interference data cluster class of the th dimension environmental interference data; represents the remaining dimensional environmental interference data except the current th dimension environmental interference data; Indicates the th environmental interference data of the th environmental interference data cluster class, and the th continuous interference environment data group, and the th interference environment data corresponding to the amplitude of the Indicates a preset hyperparameter, set here as , which can be adjusted by yourself; Indicates the exponential function with the natural constant as the base.

[0032] Indicates the difference between the amplitude of the inclination data corresponding to the th continuous interference environment data group in the environmental interference data cluster class and the mean value of the amplitudes of the inclination data corresponding to the th continuous interference environment data group in the environmental interference data cluster class, indicating the dispersion degree of the inclination data corresponding to the th continuous interference environment data group in the environmental interference data cluster class. The smaller this value is, the closer the actual change of the inclinometer in this continuous interference environment data group is. In order to mainly obtain whether the change of the monitoring data of the inclinometer corresponding to the th continuous interference environment data group above is mainly caused by the th dimensional environmental interference data, so here it is necessary to adjust the weight based on the amplitude size of the environmental interference data of the remaining dimensions at the same time, that is, through weight , and normalize the th dimensional environmental interference data. The closer the amplitude is to 1, the smaller the allocated weight. The exponential normalization has a faster change speed and can better expand the gap between larger values and smaller values, and further expand the gap through the preset hyperparameter.

[0033] Then, analyze the distribution of the environmental interference data within the environmental interference data cluster class. For each environmental interference data cluster class, the larger the within-cluster sum of squares and the larger the number of data within the cluster class, the higher the frequency and the more concentrated the degree of the occurrence of this environmental interference data within the amplitude range corresponding to this environmental interference data cluster class in the current water conservancy project building environment. Therefore, the specific implementation method is: calculate the within-cluster sum of squares after normalizing the environmental interference data cluster class, that is, for the th dimensional environmental interference data of the After linearly normalizing each environmental interference data cluster class and obtaining the centroid position of the environmental interference data cluster class, calculate the within-cluster sum of squares SSE (SSE is an index to measure the difference between the sample points within the cluster and its centroid. The smaller the SSE value, the closer the sample points within the cluster are and the better the clustering effect) of the normalized environmental interference data cluster class. This feature is a known technology; in addition, obtain the data volume of any continuous interference environmental data group within the environmental interference data cluster class to obtain the distribution of the environmental interference data within the environmental interference data cluster class.

[0034] Finally, based on the degree of uniformity of the influence of the environmental interference data cluster class on the inclination data and the distribution of the environmental interference data within the environmental interference data cluster class, obtain the direct influence factor of the environmental interference data in each dimension on the inclination data. Further, weight the degree of uniformity by the data volume and combine it with the within-cluster sum of squares to obtain the direct influence factor of the environmental interference data in each dimension on the inclination data. Construct the formula for calculating the direct influence factor of the environmental interference data in the In the formula, represents the direct influence factor of the environmental interference data in the th dimension on the inclination data; represents the degree of uniformity of the influence of the th continuous interference environmental data group in the th environmental interference data cluster class of the environmental interference data in the th dimension on the inclination data; represents the data volume of the th continuous interference environmental data group in the th environmental interference data cluster class of the environmental interference data in the th dimension; represents the within-cluster sum of squares of the th environmental interference data cluster class of the environmental interference data in the th dimension after normalization; represents the number of continuous interference environmental data groups in the th environmental interference data cluster class of the environmental interference data in the th dimension; represents the number of environmental interference data cluster classes of the environmental interference data in the th dimension; represents the activation function.

[0035] Since the structures of hydraulic engineering generally do not shake easily, short-term disturbances usually should not show obvious interference. For such sensors used to detect environmental parameters, due to the relatively harsh environment, they are vulnerable to interference, resulting in noisy data. Therefore, according to the data volume in the th consecutive interference environment data group in the cluster The larger it is, the longer the continuous interference duration. Therefore, by performing weighting on , The larger the value, the relatively higher the corresponding weight; The larger the value, it indicates that the current environmental interference data cluster is higher than the other environmental interference data clusters in both quantity and aggregation effect. Further, it indicates that the current environmental interference data appears relatively frequently within the amplitude range corresponding to this environmental interference data cluster and has a more direct impact on the monitored building. Therefore, the direct influence factor of the environmental interference data in this dimension on the inclination data is relatively large.

[0036] S300: Analyze the abnormality of the correlation between the environmental interference data of any two dimensions corresponding to the inclination data at a specific time, and combine the change degree between the inclination data at any moment and the inclination data at its adjacent moment to obtain the environmental interference abnormality degree of the environmental interference data of each dimension at any moment.

[0037] In relatively complex environmental interferences, usually multiple dimensions of environmental interference data appear simultaneously, and there is a gain effect between some environmental interferences on the hydraulic structure, that is, one plus one is greater than two. Therefore, by analyzing the abnormality of the correlation between the environmental interference data of any two dimensions corresponding to the inclination data at a specific time, and combining the change degree between the inclination data at any moment and the inclination data at its adjacent moment, the environmental interference abnormality degree of the environmental interference data of each dimension at any moment is obtained. Further, it includes: First, analyze the correlation factors between the environmental interference data of any two dimensions. The specific implementation method is as follows: Segment the inclination data to obtain inclination change segments; the segmentation method can be to judge the time series sequence composed of inclination data, and the judgment criterion is whether the inclination data is 0; if it is 0, stop and form an inclination change segment; if it is not 0, continue to judge the next inclination data; repeat this operation to obtain multiple consecutive inclination change segments, and each inclination change segment corresponds to the actual shaking situation of its hydraulic structure. Calculate the Pearson correlation coefficient between the environmental interference data of any two dimensions within the time corresponding to the inclination change segment, and combine the amplitude of the inclination data within the inclination change segment to obtain the correlation factors between the environmental interference data of any two dimensions. Construct the calculation formula for the correlation factors between the environmental interference data of the th dimension as: In the formula, represents the correlation factor between the environmental interference data of the th dimension; represents the Pearson coefficient between the environmental interference data of the th dimension in the th inclination change segment; represents the amplitude mean value of all inclination data in the th inclination change segment; represents the total number of inclination change segments; represents the linear normalization function.

[0038] When calculating the correlation factor between environmental interference data, the larger the inclination data corresponding to the current inclination change segment, the more obvious the corresponding interference, and further, the Pearson coefficient obtained at this time will be more real. Therefore, by weighting , and the larger it is, the greater the weight.

[0039] The correlation factor analysis logic is as follows: Since the current environmental interference is to obtain the influence of different parameters on the gain of hydraulic structures, the correlation analysis cannot be completely based on the environmental interference data in the entire historical data, but on the environmental interference data corresponding to the change of inclination data.

[0040] Then, define the time window corresponding to any moment. Specifically, for the th moment of the environmental interference data, obtain the environmental interference data of the previous and next adjacent moments for five minutes each (since the sampling frequency of environmental interference data is usually not high, and such interference usually lasts for a long time, it is necessary to select in minutes).

[0041] Then, obtain the Pearson correlation coefficient between the environmental interference data of any two dimensions within the time window where any moment is located, and combine the correlation factor to obtain the abnormality of the correlation between the environmental interference data of any two dimensions within the time window where any moment is located.

[0042] Finally, the abnormality of the correlation between the environmental interference data of any two dimensions corresponding to the inclination data, combined with the change degree between the inclination data of any moment and the inclination data of its adjacent moment, obtains the environmental interference abnormality degree of the environmental interference data of each dimension at any moment. Among them, the change degree between the inclination data of any moment and the inclination data of its adjacent moment includes: calculating the mean value of the inclination data within the time window corresponding to any moment; performing linear normalization processing on the mean value and the inclination data within the inclination change segment to obtain the normalized inclination data, which represents the change degree between the inclination data of any moment and the inclination data of its adjacent moment.

[0043] Construct the environmental interference data of the th dimension within the time window where the th moment is located and the correlation abnormality between the environmental interference data of the In the formula, represents the correlation abnormality between the environmental interference data of the th dimension within the time window where the th moment is located and the environmental interference data of the th dimension; represents the Pearson coefficient between the environmental interference data of the th dimension within the time window where the th moment is located and the environmental interference data of the th dimension; represents the correlation factor between the environmental interference data of the th dimension; represents the mean value of the inclination angle data of the environmental interference data of the th dimension within the time window corresponding to the th moment and the inclination angle data within the foregoing multiple (more than 3) inclination angle change segments are linearly normalized to obtain the normalized inclination angle data, representing the change degree between the inclination angle data of the th moment and the inclination angle data of its adjacent moment; represents the number of dimensions of the environmental interference data, represents taking the absolute value.

[0044] represents the difference between the Pearson coefficient between the environmental interference data of the th dimension within the time window corresponding to the th moment and the correlation factor between the environmental interference data of these two dimensions. The greater this difference is, the greater the deviation between the two items of environmental interference data in the current time window and the performance shown in the long time series, and there may be untrustworthy components in the corresponding data; the more obvious the shaking of the hydraulic structure is, the more appropriate the gain combination performance should be between the environmental interferences in the corresponding current time window. Therefore, based on this effect, the degree of authenticity obtained at this time is enlarged by the difference, that is The larger the

[0045] S400: According to the direct influencing factors and the degree of abnormal environmental interference, the weight of each dimension of environmental interference data participating in the support vector machine SVM model training at any time is obtained to complete the compensation correction of the inclination data.

[0046] According to the direct influencing factors and the degree of abnormal environmental interference, the weight of each dimension of environmental interference data participating in the support vector machine SVM model training at any time is obtained. The environmental interference data of the dimensions is The weight calculation formula for participating in the support vector machine SVM model training at time is: In the formula, Indicates The environmental interference data of the dimensions is The weight involved in the training of the support vector machine SVM model at time; Indicates The environmental interference data of the dimensions is The time window of the moment The abnormality of the correlation between the environmental interference data of the dimensions; Indicates Direct factors affecting the inclination data from environmental interference data in each dimension; represents the linear normalization function.

[0047] The unusual nature of the correlations between environmental disturbances The larger the value, the smaller its weight is, and the direct factor is affected. The larger the value, the greater its weight. The two correct each other and constrain each other, and after normalization, the interference terms between the environmental interference data of each dimension are obtained. Therefore, it is worth noting that the linear normalization range here is the weight range obtained at each moment for all environmental interference data.

[0048] At this point, the weight of each environmental interference data is directly added as a label to the loss model of the support vector machine SVM, thereby completing the optimization of the compensation model and compensating and correcting the inclination data.

[0049] S500: According to the compensated and corrected inclination data, the settlement amount is predicted and the settlement monitoring is completed.

[0050] Based on the compensated inclination data, data is collected regularly, and the inclination change data is analyzed to determine the inclination trend and degree of the building. According to the inclination change and the known geometric relationship, a mathematical model is established to predict the settlement and complete the settlement monitoring. For example, if the inclinometer is installed on the dam body, the horizontal displacement can be estimated by the inclination change and the height of the dam body, and then the settlement can be calculated.

[0051] It should be noted that: the above order of the embodiments of the present invention is only for description and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0052] The various embodiments in this specification are all described in a progressive manner. For the same or similar parts among the various embodiments, reference can be made to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A method for settlement monitoring and early warning of hydraulic structures for water conservancy projects, characterized in that, The method includes: Collecting the inclination angle data and multi-dimensional environmental interference data of the hydraulic structure; Clustering the environmental interference data of each dimension to obtain environmental interference data cluster classes, analyzing the influence uniformity of the environmental interference data cluster classes on the inclination angle data, and analyzing the distribution of the environmental interference data within the environmental interference data cluster classes to obtain the direct influence factor of the environmental interference data of each dimension on the inclination angle data; Analyzing the abnormality of the correlation between the environmental interference data of any two dimensions corresponding to the inclination angle data at a certain time, and combining the change degree between the inclination angle data at any moment and the inclination angle data at its adjacent moment to obtain the environmental interference abnormality degree of the environmental interference data of each dimension at any moment; According to the direct influence factor and the environmental interference abnormality degree, obtain the weight of the environmental interference data of each dimension when participating in the training of the support vector machine (SVM) model at any moment, and complete the compensation and correction of the inclination angle data; According to the compensated and corrected inclination angle data, conduct settlement prediction to complete settlement monitoring.

2. The method for settlement monitoring and early warning of hydraulic structures for hydraulic engineering according to claim 1, characterized in that After clustering the environmental interference data of each dimension to obtain environmental interference data cluster classes, it further includes: Analyzing the continuity of the corresponding moments of the environmental interference data in the environmental interference data cluster classes to obtain multiple continuous interference environment data groups; Among them, analyzing the influence uniformity of the environmental interference data cluster classes on the inclination angle data includes: Analyzing the influence uniformity of each continuous interference environment data group in the environmental interference data cluster classes on the inclination angle data.

3. The method for settlement monitoring and early warning of hydraulic structures for hydraulic engineering according to claim 2, characterized in that Analyzing the influence uniformity of each continuous interference environment data group in the environmental interference data cluster classes on the inclination angle data includes: Analyzing the dispersion degree of the inclination angle data corresponding to each continuous interference environment data group in the environmental interference data cluster classes, and combining the amplitudes of the environmental interference data of other dimensions at the corresponding moments to obtain the influence uniformity of each continuous interference environment data group in the environmental interference data cluster classes on the inclination angle data.

4. The method for settlement monitoring and early warning of hydraulic structures for water conservancy projects according to claim 3, characterized in that, Analyzing the distribution of the environmental interference data within the environmental interference data cluster classes includes: Calculating the within-cluster sum of squares after normalizing the environmental interference data cluster classes, and obtaining the data volume of any continuous interference environment data group within the environmental interference data cluster classes to obtain the distribution of the environmental interference data within the environmental interference data cluster classes; Among them, analyzing the influence uniformity of the environmental interference data cluster classes on the inclination angle data, and analyzing the distribution of the environmental interference data within the environmental interference data cluster classes to obtain the direct influence factor of the environmental interference data of each dimension on the inclination angle data includes: Weighting the influence uniformity by the data volume, and combining the within-cluster sum of squares to obtain the direct influence factor of the environmental interference data of each dimension on the inclination angle data.

5. The method for settlement monitoring and early warning of hydraulic structures for water conservancy projects according to claim 1, characterized in that, Analyzing the abnormality of the correlation between the environmental interference data of any two dimensions corresponding to the inclination angle data at a certain time includes: Analyzing the correlation factor between the environmental interference data of any two dimensions; Defining a time window corresponding to any moment; Obtain the Pearson correlation coefficient between the environmental interference data of any two dimensions within the time window at any moment, and combine the correlation factor to obtain the abnormality of the correlation between the environmental interference data of any two dimensions within the time window at any moment.

6. The method for settlement monitoring and early warning of hydraulic structures for water conservancy projects according to claim 5, characterized in that, Analyze the correlation factors between the environmental interference data of any two dimensions, including: Segment the inclination angle data to obtain inclination angle change segments; Calculate the Pearson correlation coefficient between the environmental interference data of any two dimensions within the time corresponding to the inclination angle change segment, and combine the amplitude of the inclination angle data within the inclination angle change segment to obtain the correlation factor between the environmental interference data of any two dimensions.

7. The method for settlement monitoring and early warning of hydraulic structures for water conservancy projects according to claim 6, characterized in that, Segment the inclination angle data to obtain inclination angle change segments, including: Judge the time series sequence composed of the inclination angle data, and the judgment criterion is whether the inclination angle data is 0; If it is 0, stop and form an inclination angle change segment; If it is not 0, continue to judge the next inclination angle data; Repeat this operation to obtain a continuous plurality of inclination angle change segments.

8. The method for settlement monitoring and early warning of hydraulic structures for water conservancy projects according to claim 6, characterized in that, The degree of change between the inclination angle data at any moment and the inclination angle data at its adjacent moment, including: Calculate the mean value of the inclination angle data within the time window corresponding to any moment; Perform linear normalization processing on the mean value and the inclination angle data within the inclination angle change segment to obtain normalized inclination angle data, indicating the degree of change between the inclination angle data at any moment and the inclination angle data at its adjacent moment.

9. The method for settlement monitoring and early warning of hydraulic structures for water conservancy projects according to claim 1, characterized in that, Collect the inclination angle data and multi-dimensional environmental interference data of the hydraulic structure, including: Collect the inclination angle data and multi-dimensional environmental interference data of the hydraulic structure at the current moment, and obtain the inclination angle data and multi-dimensional environmental interference data within the previous month of the current moment; Perform preprocessing of standardization on the inclination angle data and the multi-dimensional environmental interference data to obtain standardized inclination angle data and standardized multi-dimensional environmental interference data.

10. The method for settlement monitoring and early warning of hydraulic structures for water conservancy projects according to claim 1, characterized in that, Cluster the environmental interference data of each dimension to obtain environmental interference data cluster classes, including: Perform K-means clustering on the environmental interference data of each dimension, determine the optimal number of cluster classes by the elbow method, and obtain environmental interference data cluster classes.

Images