Auxiliary monitoring method and device for settlement displacement of deep foundation pit

Abstract

The invention relates to the technical field of settlement displacement auxiliary monitoring, in particular to a settlement displacement auxiliary monitoring method and device for a deep foundation pit, and the method comprises the steps: collecting each kind of monitoring data of each monitoring point in the deep foundation pit, and the characteristic value difference between different monitoring points under the same kind of monitoring data, measuring distances between different monitoring points under the same kind of monitoring data are obtained, clustering division is carried out on all the monitoring points under the same kind of monitoring data, modal decomposition is carried out, and the characteristic coefficient of each modal component of the monitoring data at each monitoring point in each cluster under the same kind of monitoring data is obtained; the method comprises the following steps: firstly, monitoring data of a deep foundation pit is obtained, interference adjustment values of monitoring data at all monitoring points in each cluster in each modal component under the same type of monitoring data are obtained, filtering processing is carried out, all modal components are reconstructed and restored, each type of monitoring data is predicted, and auxiliary monitoring is carried out on settlement displacement of the deep foundation pit. The auxiliary monitoring precision of settlement displacement of the deep foundation pit can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of settlement and displacement auxiliary monitoring, and in particular to a settlement and displacement auxiliary monitoring method and device for a deep foundation pit. Background Art

[0002] Deep foundation pit projects are widely used in projects such as subways, underground shopping malls, and high-rise basements. Due to the deep excavation depths, complex geological conditions, and sensitive surrounding environments, soil deformation and support structure displacement can lead to serious consequences such as ground subsidence, building tilt, and even collapse. Therefore, through real-time, accurate auxiliary monitoring, deformation trends of the foundation pit and surrounding soil can be monitored in a timely manner, providing data support for engineering design and construction plan optimization, effectively preventing safety accidents, ensuring construction safety and surrounding environmental stability, and also helping to improve the overall quality and management level of deep foundation pit projects.

[0003] However, the current process of assisting deep foundation pit settlement and displacement monitoring, from data collection to prediction, still faces numerous challenges. In actual monitoring, the complex monitoring environment leads to significant differences in interference effects across different regions. For example, variations in water content and temperature can cause interference effects of varying frequencies to appear in the actual monitoring results. Traditional filtering methods, when monitoring multiple monitoring points for deep foundation pit settlement and displacement, fail to fully account for the varying influences of different interference frequencies in the complex environment of actual monitoring. This results in poor data processing quality, impacting the accuracy of subsequent settlement and displacement prediction analysis, and making it difficult to meet the demands of deep foundation pit projects for precise settlement and displacement monitoring and early warning. Summary of the Invention

[0004] In order to solve the above technical problems, the purpose of this application is to provide a method and device for auxiliary monitoring of settlement and displacement of deep foundation pits. The technical solutions adopted are as follows: The present invention provides a method for auxiliary monitoring of the settlement and displacement of a deep foundation pit, comprising the following steps: Collect each type of monitoring data at each monitoring point in the deep foundation pit; According to the fluctuation characteristics of each monitoring data at different monitoring points, a sample set of each monitoring data is obtained. By comparing the differences in characteristic values ​​between different monitoring points in each monitoring data sample set and combining the differences in monitoring data between different monitoring points under the same monitoring data, the metric distance between different monitoring points under the same monitoring data is obtained, and then all monitoring points under the same monitoring data are clustered. By analyzing the differences between the modal components of the monitoring data at different monitoring points in each cluster under the same monitoring data under modal decomposition in the same frequency band, the characteristic coefficient of the monitoring data at each monitoring point in each cluster in each modal component is obtained, and combined with the discrete range of the corresponding modal component data, the interference adjustment value of the monitoring data at all monitoring points in each cluster in each modal component is obtained, and then each modal component of the monitoring data at each monitoring point in each cluster under each type of monitoring data is filtered; All modal components of the monitoring data at each monitoring point after filtering are reconstructed and restored to predict each type of monitoring data, thereby assisting in monitoring the settlement and displacement of the deep foundation pit.

[0005] Preferably, each monitoring data sample set further includes: The three characteristic values ​​of the monitoring time series of each type of monitoring data in each monitoring point are used as the X-axis, Y-axis, and Z-axis coordinate values ​​to establish a three-dimensional rectangular coordinate system. One three-dimensional rectangular coordinate system corresponds to one type of monitoring data. The mapping result of each three-dimensional rectangular coordinate system is used as the monitoring sample set of each type of monitoring data, that is, each monitoring data sample set.

[0006] Preferably, the three characteristic values ​​of the monitoring time series of each type of monitoring data at each monitoring point are: Arrange each monitoring data of each monitoring point according to the collection time sequence to obtain the monitoring time sequence of each monitoring data at each monitoring point; The three characteristic values ​​are: the variance, range and trend statistics of the monitoring time series of each type of monitoring data in each monitoring point.

[0007] Preferably, the method for calculating the metric distance between different monitoring points under the same monitoring data is: ; Where, For the same monitoring data Monitoring points and The measured distance between monitoring points; For each monitoring data sample set Monitoring points and The Euclidean distance of the characteristic values ​​between the monitoring points; Indicates the same monitoring data Monitoring points and The DTW distance of the monitoring time series between the monitoring points.

[0008] Preferably, clustering all monitoring points under the same type of monitoring data further includes: For each monitoring point, the metric distance between different monitoring points under the same monitoring data is used as the cluster distance for clustering division.

[0009] Preferably, obtaining the characteristic coefficient of each modal component of the monitoring data at each monitoring point in each cluster includes: The DTW distances of modal components in similar frequency bands between monitoring data at different monitoring points in each cluster under the same monitoring data are counted, and the mean of all DTW distances is used as the characteristic coefficient of each modal component of the monitoring data at each monitoring point in each cluster under the same monitoring data.

[0010] Preferably, the method for obtaining the modal components of the similar frequency bands is: The modal components of the same frequency band in the monitoring data at different monitoring points under the same monitoring data are regarded as the modal components of similar frequency bands.

[0011] Preferably, the interference adjustment value of each modal component of the monitoring data at all monitoring points in each cluster is calculated as follows: ; Where, The monitoring data of all monitoring points in each cluster under the same monitoring data are The interference adjustment value of each modal component; is the first cluster in each cluster under the same monitoring data The monitoring data at the monitoring point The standard deviation of the data corresponding to each modal component; is the first cluster in each cluster under the same monitoring data The monitoring data at the monitoring point Characteristic coefficients of modal components; is the first monitoring data of all monitoring points in each cluster under the same monitoring data. The sum of the characteristic coefficients of the modal components; n is the total number of monitoring points in each cluster.

[0012] Preferably, the filtering process for each modal component of the monitoring data at each monitoring point in each cluster under each type of monitoring data further includes: The standard deviation of the data corresponding to each modal component of the monitoring data at each monitoring point in each cluster under each type of monitoring data, as well as the mean of the interference adjustment value of each modal component of the monitoring data at all monitoring points in each cluster under the same type of monitoring data, are used as the standard deviation parameters of the filter, and then each modal component of the monitoring data at each monitoring point in each cluster under each type of monitoring data is filtered.

[0013] An embodiment of the present application also provides an auxiliary monitoring device for settlement and displacement of a deep foundation pit, wherein a computer program is stored in the device, and when the computer program is executed by a processor, the steps of any one of the above-mentioned auxiliary monitoring methods for settlement and displacement of a deep foundation pit are implemented.

[0014] As can be seen from the above, the settlement and displacement auxiliary monitoring method and device for deep foundation pits provided in this application have at least the following beneficial effects: This application fully considers the impact characteristics of regional interference in different frequency bands under the monitoring mode of multiple monitoring points, and accurately pre-processes the settlement monitoring data, thereby improving the accuracy of deep foundation pit settlement displacement in prediction analysis, and improving the accuracy of deep foundation pit engineering in settlement displacement accurate monitoring and early warning. In the process of deep foundation pit settlement displacement monitoring, due to the complex environment of the deep foundation pit, there are significant differences in the interference effects on different monitoring points during the monitoring process, which in turn causes the monitoring data of each monitoring point to be affected by interference factors in different frequency ranges. Combined with the multi-monitoring point monitoring strategy, all monitoring points under the same monitoring data are divided by the characteristic values ​​between different monitoring points under the same monitoring data, and then the data deviations caused by interference effects at different monitoring points in similar frequency bands are analyzed. By analyzing the interference influence characteristics of different monitoring points in different frequency bands under the same monitoring data, the processing process of each collected monitoring data is optimized and adjusted. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present application or the prior art, the following is a brief introduction to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0016] Figure 1 A flowchart of the steps of a settlement displacement auxiliary monitoring method for a deep foundation pit provided in this application; Figure 2 This is a flowchart of the steps of the method for obtaining the measured distance provided by this application. DETAILED DESCRIPTION

[0017] In order to further illustrate the technical means and effects adopted by this application to achieve the predetermined invention purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, describes in detail the specific implementation method, structure, features and effects of a deep foundation pit settlement displacement auxiliary monitoring method and device proposed in this application. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0018] Unless otherwise specified and limited, terms such as "comprises", "includes" or any other variants thereof are intended to cover non-exclusive inclusion, so that a circuit structure, article or device comprising a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the presence of other identical elements in the article or device comprising the element. In addition, the term "and\or" used herein includes any and all combinations of one or more related listed items. All technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs.

[0019] The specific scheme of the settlement and displacement auxiliary monitoring method and device for deep foundation pit provided by the present application is described in detail below with reference to the accompanying drawings.

[0020] See also Figure 1 , which shows a flowchart of a method for auxiliary monitoring of settlement displacement of a deep foundation pit provided by an embodiment of the present application, including the following steps: Step 1: Collect each monitoring data at each monitoring point in the deep foundation pit.

[0021] In the auxiliary monitoring of settlement and displacement of deep foundation pits, the reasonable layout of monitoring points is the basis for obtaining effective data. Specifically, based on the design drawings of the foundation pit, the geological survey report and the surrounding environmental conditions, monitoring points are arranged at certain intervals at the key parts of the support structure of the foundation pit and the surrounding soil along the edge of the foundation pit. For the foundation pit support structure, a monitoring point is arranged at the top of each supporting pile and the crown beam at intervals of a first preset distance; and the monitoring point positions are arranged at intervals of a second preset distance in the soil around the foundation pit along the edge of the foundation pit. Among them, the key parts include but are not limited to the pile tops, crown beams and support nodes. The value range of the first preset distance is 10-15 meters, and the value range of the second preset distance is 5-10 meters. Preferably, in this embodiment, the first preset distance is set to 5 meters, and the second preset distance is set to 10 meters.

[0022] Monitoring equipment will be deployed at each monitoring point. For settlement monitoring, a high-precision level or a static leveling system is used; for tilt and displacement monitoring, a total station and a displacement sensor are used. At the same time, a sampling frequency is set on the monitoring equipment, and monitoring data is collected once an hour during the active construction period, and a preset number of monitoring data is collected every day during the stable construction period, and the monitoring time and equipment number parameters are recorded. The collected monitoring data include settlement, horizontal displacement and inclination, and after the collection is completed, the data is transmitted to the data processing center in real time via the 4G or 5G wireless network. The preset number of times ranges from 2 to 4 times, and in this embodiment, the preset number of times is set to 3 times.

[0023] Step 2: According to the fluctuation characteristics of each monitoring data at different monitoring points, obtain a sample set of each monitoring data. Through the difference in characteristic values ​​between different monitoring points in each monitoring data sample set, combined with the difference in monitoring data between different monitoring points under the same monitoring data, obtain the metric distance between different monitoring points under the same monitoring data, and then cluster all monitoring points under the same monitoring data.

[0024] Due to the complex construction environment of deep foundation pits and their susceptibility to factors such as geological changes caused by the environment, the actual data collection process is affected by complex interference factors, resulting in large differences in the interference effects of different monitoring points. Consequently, after preprocessing each type of monitoring data collected at each monitoring point, each type of monitoring data has significant differences. Based on the above analysis, under the monitoring strategy of multiple monitoring points, each type of monitoring data collected is comprehensively compared, and each type of monitoring data with similar change characteristics during the monitoring process is divided. The interference influence characteristics of each monitoring point in different frequency ranges are then determined to optimize the preprocessing effect of each type of monitoring data during the monitoring process, achieving accurate auxiliary monitoring of deep foundation pit settlement and displacement.

[0025] Specifically, in the auxiliary monitoring process of deep foundation pit settlement and displacement, due to factors such as rainfall, changes in water content, and surrounding construction, interference from different frequency ranges may occur in the monitoring area, which in turn leads to large errors in each type of monitoring data. This deviation in actual monitoring data caused by environmental interference will affect the accuracy of auxiliary monitoring of deep foundation pit settlement and displacement. Therefore, based on the monitoring strategy characteristics of multiple monitoring points, for each monitoring point, each type of monitoring data of each monitoring point is arranged according to the collection time sequence to obtain a monitoring time series sequence for each type of monitoring data in each monitoring point; and the variance, range and trend statistics of the monitoring time series sequence of each type of monitoring data are calculated to form the characteristic values ​​of the monitoring time series sequence of each type of monitoring data, so as to respectively reflect the degree of fluctuation change, range of change and trend change characteristics of different monitoring data in each monitoring point. Preferably, in this embodiment, the trend statistics are obtained by the MK trend verification algorithm, and the specific process will not be repeated.

[0026] Furthermore, we consider that changing environmental factors may also cause each monitoring data point to exhibit interference characteristics and abnormal changes in different frequency ranges. For example, vibrations from surrounding construction or heavy vehicles can cause small, high-frequency fluctuations in the data. By analyzing the degree of fluctuation, range, and trend characteristics of different monitoring data points at each monitoring point, we can comprehensively compare the differences between different monitoring points.

[0027] Therefore, the variance, range and trend statistics in the characteristic values ​​of the monitoring time series of each monitoring data in each monitoring point are calculated, and used as the X-axis, Y-axis and Z-axis coordinate values ​​respectively to establish a three-dimensional rectangular coordinate system; then all monitoring points are mapped to the three-dimensional rectangular coordinate system according to the characteristic values ​​of the monitoring time series of each monitoring data. One three-dimensional rectangular coordinate system corresponds to one type of monitoring data, and the coordinates in the three-dimensional rectangular coordinate system are the characteristic values ​​of each monitoring data at different monitoring points. The mapping result is used as the monitoring sample set of each monitoring data, that is, each monitoring data sample set, so as to accurately divide the monitoring points with similar monitoring data, and then accurately compare the interference impact characteristics in different frequency ranges.

[0028] Through the above analysis, based on the differences in the characteristic values ​​of different monitoring points in each monitoring data sample set, and combined with the differences in the monitoring time series between different monitoring points under the same monitoring data, the metric distance between different monitoring points under the same monitoring data is calculated. In this embodiment, the specific calculation formula is as follows: ; Where, For the same monitoring data Monitoring points and The measured distance between monitoring points; For each monitoring data sample set Monitoring points and The Euclidean distance of the characteristic values ​​between the monitoring points; Indicates the same monitoring data Monitoring points and The DTW distance of the monitoring time series between the monitoring points.

[0029] in, The larger the value is, the greater the difference in the characteristics of each monitoring data caused by interference during the actual monitoring process; The larger the value, the greater the difference between different monitoring points under the same monitoring data. Figure 2 shown.

[0030] In order to highlight the data deviation characteristics caused by interference factors in different frequency ranges during the monitoring process, the DBSCAN algorithm is used to obtain clustering results for all monitoring points under the same monitoring data, combined with the metric distance between different monitoring points under the same monitoring data. Preferably, in this embodiment, the DBSCAN algorithm is a well-known technology, and the specific process is not repeated here.

[0031] Step 3: By analyzing the differences between the modal components in the same frequency band after modal decomposition of the monitoring data at different monitoring points in each cluster under the same monitoring data, the characteristic coefficient of each modal component of the monitoring data at each monitoring point in each cluster is obtained, and combined with the discrete range of the corresponding modal component data, the interference adjustment value of each modal component of the monitoring data at all monitoring points in each cluster is obtained, and then each modal component of the monitoring data at each monitoring point in each cluster under each monitoring data is filtered.

[0032] Furthermore, for each cluster after clustering, the monitoring time series of the monitoring data at all monitoring points in each cluster under the same monitoring data is used as input, and the variational mode decomposition algorithm is used to obtain the modal components of the monitoring time series in the monitoring data at each monitoring point in each cluster under the same monitoring data. The number of modal components is a preset number. In this embodiment, the preset number is set to 5, corresponding to 5 different frequency bands, and then numbered 1, 2, 3, 4, and 5 in sequence according to the decomposition order, corresponding to the monitoring data of the modal components of the monitoring data at each monitoring point under each monitoring data in different frequency bands. Preferably, in this embodiment, the variational mode decomposition algorithm is a well-known technology, and the specific process will not be repeated.

[0033] Based on each monitoring point under each type of monitoring data with similar data fluctuations, combined with the differences in data changes caused by interference in different frequency bands in actual monitoring, the data characteristics of the modal components of the monitoring data at each monitoring point after clustering under the same type of monitoring data in different frequency bands are compared, and the interference adjustment values ​​of the monitoring data at all monitoring points in each cluster cluster under the same type of monitoring data in each modal component are calculated.

[0034] Therefore, the modal components of the same frequency band in different monitoring points under the same monitoring data are regarded as modal components of similar frequency bands, and the DTW distances of modal components of similar frequency bands between the monitoring data at different monitoring points in each cluster under the same monitoring data are calculated. The larger the DTW distance, the greater the data difference in modal components of similar frequency bands between the monitoring data at different monitoring points under the same monitoring data; and the mean of all DTW distances is taken as the characteristic coefficient of each modal component of the monitoring data at each monitoring point in each cluster under the same monitoring data.

[0035] Through the above analysis, according to the characteristic coefficient of each modal component of the monitoring data at each monitoring point in each cluster under the same monitoring data, and combined with the discrete range of the data corresponding to each modal component of the monitoring data at each monitoring point in each cluster under the same monitoring data, the interference adjustment value of each modal component of the monitoring data at all monitoring points in each cluster under the same monitoring data is calculated. In this embodiment, the specific calculation formula is: ; Where, The monitoring data of all monitoring points in each cluster under the same monitoring data are The interference adjustment value of each modal component; is the first cluster in each cluster under the same monitoring data The monitoring data at the monitoring point The standard deviation of the data corresponding to each modal component; is the first cluster in each cluster under the same monitoring data The monitoring data at the monitoring point Characteristic coefficients of modal components; is the first monitoring data of all monitoring points in each cluster under the same monitoring data. The sum of the characteristic coefficients of the modal components; n is the total number of monitoring points in each cluster.

[0036] in, It represents the comparison result of the difference of the modal component data of the monitoring data at different monitoring points in each cluster under the same monitoring data. The larger it is, the more significant the difference of the modal component of the corresponding monitoring data in the similar frequency band caused by the interference effect is. It represents the comparison of modal components of similar frequency bands of monitoring data at all monitoring points in each cluster under the comprehensive monitoring data of the same type. The larger it is, the more significant the interference effect of the monitoring data at each monitoring point in each cluster in the corresponding frequency range under the corresponding monitoring data.

[0037] Furthermore, a Gaussian filter is used to filter each modal component of the monitoring data at each monitoring point in each cluster under each type of monitoring data. Specifically, for each modal component of the monitoring data at each monitoring point in each cluster under each type of monitoring data, the standard deviation of the data corresponding to each modal component and the mean of the interference adjustment values ​​of the monitoring data at all monitoring points in each cluster under the same type of monitoring data at each modal component are used as standard deviation parameters of the Gaussian filter, and then Gaussian filtering is performed on each modal component data. Preferably, in this embodiment, the Gaussian filter is a well-known technology, and the specific process will not be repeated.

[0038] Therefore, in the actual process, when the data of different monitoring points under the same monitoring data deviate due to the influence of interference, the characteristics of each monitoring point under the same monitoring data are analyzed and clustered, and then the influence of interference factors in different frequency ranges on the actual monitoring process of different monitoring points is accurately analyzed, and the parameters of the filtering process of each modal component of the monitoring data at each monitoring point in each cluster under the same monitoring data are adjusted. The more significant the interference effect, the larger the filtering processing parameters of the modal component of the corresponding frequency band, thereby reducing the influence of interference factors on deep basement displacement monitoring.

[0039] Step 4: Reconstruct and restore all modal components of the filtered monitoring data at each monitoring point to predict each type of monitoring data, and then perform auxiliary monitoring of the settlement displacement of the deep foundation pit.

[0040] After the above processing, all modal components after modal decomposition of the filtered monitoring data at each monitoring point in each cluster under the same monitoring data are reconstructed and restored. The reconstructed data is each type of monitoring data after settlement displacement preprocessing at each monitoring point. Preferably, in this embodiment, the reconstruction and restoration process is a well-known technology, and the specific process is not repeated here.

[0041] Based on each monitoring data after pre-processing of the settlement displacement of each monitoring point, the monitoring data of the settlement displacement of the deep foundation pit is predicted using the ARIMAX prediction algorithm. The prediction results are compared and analyzed with the pre-set warning threshold. If each monitoring data of the predicted settlement displacement of each monitoring point exceeds the warning threshold, the system immediately issues a warning signal and notifies relevant personnel through SMS, email, etc., where the specific warning threshold can be set according to the requirements for deep foundation construction during the actual construction process. At the same time, the monitoring data and prediction results are displayed in the form of visual charts such as time-settlement curves and displacement distribution diagrams based on the positions of monitoring points, which intuitively present the changing trend of the settlement displacement of the deep foundation pit, provide accurate data for engineering management personnel to formulate reasonable construction plans and safety protection measures, and realize effective auxiliary monitoring and risk control of the settlement displacement of the deep foundation pit. Preferably, in this embodiment, the ARIMAX prediction algorithm is a well-known technology, and the specific process will not be repeated.

[0042] Based on the same inventive concept as the above method, an embodiment of the present application also provides an auxiliary monitoring device for settlement and displacement of a deep foundation pit, wherein a computer program is stored in the device, and when the computer program is executed by a processor, the steps of any one of the above-mentioned auxiliary monitoring methods for settlement and displacement of a deep foundation pit are implemented.

[0043] It should be understood that the order in which the embodiments of the present application are presented is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. Furthermore, the foregoing descriptions of specific embodiments of this specification are provided. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential sequence shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0044] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

[0045] The above content is only an implementation method of the present application and is not intended to limit the scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the scope of protection of the present application.

Claims

1. A settlement displacement auxiliary monitoring method for a deep foundation pit, characterized in that: The following steps are involved: Collect each type of monitoring data at each monitoring point in the deep foundation pit; According to the fluctuation characteristics of each monitoring data at different monitoring points, a sample set of each monitoring data is obtained. By comparing the differences in characteristic values ​​between different monitoring points in each monitoring data sample set and combining the differences in monitoring data between different monitoring points under the same monitoring data, the metric distance between different monitoring points under the same monitoring data is obtained, and then all monitoring points under the same monitoring data are clustered. By analyzing the differences between the modal components of the monitoring data at different monitoring points in each cluster under the same monitoring data under modal decomposition in the same frequency band, the characteristic coefficient of the monitoring data at each monitoring point in each cluster in each modal component is obtained, and combined with the discrete range of the corresponding modal component data, the interference adjustment value of the monitoring data at all monitoring points in each cluster in each modal component is obtained, and then each modal component of the monitoring data at each monitoring point in each cluster under each type of monitoring data is filtered; All modal components of the monitoring data at each monitoring point after filtering are reconstructed and restored to predict each type of monitoring data, thereby assisting in monitoring the settlement and displacement of the deep foundation pit.

2. The settlement displacement auxiliary monitoring method of a deep foundation pit according to claim 1, characterized in that: Each monitoring data sample set further includes: The three characteristic values ​​of the monitoring time series of each type of monitoring data in each monitoring point are used as the X-axis, Y-axis, and Z-axis coordinate values ​​to establish a three-dimensional rectangular coordinate system. One three-dimensional rectangular coordinate system corresponds to one type of monitoring data. The mapping result of each three-dimensional rectangular coordinate system is used as the monitoring sample set of each type of monitoring data, that is, each monitoring data sample set.

3. The settlement displacement auxiliary monitoring method of a deep foundation pit according to claim 2, characterized in that: The three characteristic values ​​of the monitoring time series of each monitoring data at each monitoring point are: Arrange each monitoring data of each monitoring point according to the collection time sequence to obtain the monitoring time sequence of each monitoring data at each monitoring point; The three characteristic values ​​are: the variance, range and trend statistics of the monitoring time series of each type of monitoring data in each monitoring point.

4. The settlement displacement auxiliary monitoring method for a deep foundation pit according to claim 3, characterized in that: The calculation method of the metric distance between different monitoring points under the same monitoring data is: ； Where, For the same monitoring data Monitoring points and The measured distance between monitoring points; For each monitoring data sample set Monitoring points and The Euclidean distance of the characteristic values ​​between the monitoring points; Indicates the same monitoring data Monitoring points and The DTW distance of the monitoring time series between the monitoring points.

5. The settlement displacement auxiliary monitoring method for a deep foundation pit according to claim 1, characterized in that: The clustering of all monitoring points under the same monitoring data further includes: For each monitoring point, the metric distance between different monitoring points under the same monitoring data is used as the cluster distance for clustering division.

6. The settlement displacement auxiliary monitoring method for a deep foundation pit according to claim 1, characterized in that: The method of obtaining the characteristic coefficient of each modal component of the monitoring data at each monitoring point in each cluster includes: The DTW distances of modal components in similar frequency bands between monitoring data at different monitoring points in each cluster under the same monitoring data are counted, and the mean of all DTW distances is used as the characteristic coefficient of each modal component of the monitoring data at each monitoring point in each cluster under the same monitoring data.

7. The settlement displacement auxiliary monitoring method for a deep foundation pit according to claim 6, characterized in that: The method for obtaining the modal components of the similar frequency band is: The modal components of the same frequency band in the monitoring data at different monitoring points under the same monitoring data are regarded as the modal components of similar frequency bands.

8. The settlement displacement auxiliary monitoring method for a deep foundation pit according to claim 1, characterized in that: The calculation method of the interference adjustment value of each modal component of the monitoring data at all monitoring points in each cluster is: ； Where, The monitoring data of all monitoring points in each cluster under the same monitoring data are The interference adjustment value of each modal component; is the first cluster in each cluster under the same monitoring data The monitoring data at the monitoring point The standard deviation of the data corresponding to each modal component; is the first cluster in each cluster under the same monitoring data The monitoring data at the monitoring point Characteristic coefficients of modal components; is the first monitoring data of all monitoring points in each cluster under the same monitoring data. The sum of the characteristic coefficients of the modal components; n is the total number of monitoring points in each cluster.

9. The settlement displacement auxiliary monitoring method for a deep foundation pit according to claim 1, characterized in that: The filtering process for each modal component of the monitoring data at each monitoring point in each cluster under each type of monitoring data further includes: The standard deviation of the data corresponding to each modal component of the monitoring data at each monitoring point in each cluster under each type of monitoring data, as well as the mean of the interference adjustment value of each modal component of the monitoring data at all monitoring points in each cluster under the same type of monitoring data, are used as the standard deviation parameters of the filter, and then each modal component of the monitoring data at each monitoring point in each cluster under each type of monitoring data is filtered.

10. A settlement displacement auxiliary monitoring device for a deep foundation pit, wherein a computer program is stored in the device, characterized in that: When the computer program is executed by a processor, the steps of the settlement and displacement auxiliary monitoring method for a deep foundation pit as described in any one of claims 1 to 9 are implemented.

Images