A lateral deformation prediction system and method based on deep foundation pit walls

Abstract

The present invention relates to the field of deformation prediction technology, specifically a lateral deformation prediction system and method based on deep foundation pit walls. The system includes: a deformation data acquisition module, which collects surface settlement monitoring values and lateral displacement monitoring values of corresponding measuring points on the deep foundation pit walls, performs time-series alignment processing on the data points and eliminates abnormal monitoring values, and establishes calibrated deformation sequence data. In the present invention, by real-time acquisition and strict execution of data time-series alignment processing, the consistency of surface settlement data and wall lateral displacement data is ensured, and abnormal monitoring data is effectively eliminated, thereby improving data accuracy and consistency; in the spatial interpolation process, the width measurement of the settlement area is introduced to determine the width characteristics of the settlement trough, and the deformation index is used to capture the surface deformation trend; the maximum lateral displacement of each time section of the monitoring profile is extracted, and a dynamic corresponding relationship between the maximum displacement and the settlement trough width is established to identify the regular influence of changes in the construction process on the lateral deformation.

Description

Technical Field

[0001] The present invention relates to the technical field of deformation prediction, and in particular to a lateral deformation prediction system and method based on a deep foundation pit wall. Background Art

[0002] The field of deformation prediction technology is a crucial component of civil engineering safety monitoring, primarily focusing on civil structures such as bridges, high-rise buildings, slopes, tunnels, and deep foundation pits. This field uses sensors to collect real-time deformation data, such as settlement, tilt, and displacement, of structures. Using data analysis, trend prediction, and risk assessment, potential risks are identified and early warnings are issued to ensure structural safety during construction and operational phases.

[0003] Existing technologies primarily rely on average interpolation of data across the entire region, without precise measurement and analysis of key settlement areas. This results in monitoring results that fail to capture important trends in local deformation. Furthermore, insufficient research on the relationship between maximum wall displacement and process evolution leads to a crude analysis of wall deformation trends, making it difficult to identify key risk points during construction. Therefore, improvements are needed. Summary of the Invention

[0004] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a lateral deformation prediction system and method based on deep foundation pit walls.

[0005] In order to achieve the above-mentioned purpose, the present invention adopts the following technical solution: A lateral deformation prediction system based on a deep foundation pit wall comprises:

[0006] The deformation data acquisition module collects surface settlement monitoring values and lateral displacement monitoring values of corresponding measuring points on the deep foundation pit wall, performs time sequence alignment processing on the data points and eliminates abnormal monitoring values to establish calibrated deformation sequence data;

[0007] a surface pattern recognition module that generates surface settlement contour lines through spatial interpolation based on the surface settlement monitoring values in the calibration deformation sequence data, obtains a surface settlement contour map, measures the width of the settlement trough formed in the key settlement area based on the surface settlement contour map, and establishes a settlement trough width feature;

[0008] A wall response association module extracts the maximum lateral displacement value of each monitoring section at the same time section based on the wall lateral displacement monitoring values in the calibration deformation sequence data to obtain the maximum wall displacement value. Based on the maximum wall displacement value, the corresponding relationship between the evolution of the wall with the excavation process and the change of the settlement trough width characteristics is analyzed to establish the surface wall evolution association rules;

[0009] The deformation trend prediction module, based on the width characteristics of the settlement trough, queries the wall behavior pattern corresponding to the width characteristics in the surface wall evolution association rules to obtain the expected wall response pattern. Based on the expected wall response pattern and combined with the deformation state of the current deep foundation pit wall, the lateral deformation value of the deep foundation pit wall in the next time window is predicted to obtain the wall lateral deformation prediction result.

[0010] Preferably, the step of obtaining the calibration deformation sequence data is:

[0011] Collect surface settlement monitoring values and lateral displacement monitoring values of corresponding measuring points on the deep foundation pit wall, match them one by one according to the collection time, mark and remove the unmatched monitoring values, and generate surface settlement monitoring values and lateral displacement monitoring values of corresponding measuring points on the deep foundation pit wall after time series alignment and outlier removal;

[0012] Based on the surface settlement monitoring values and the lateral displacement monitoring values of the corresponding measuring points of the deep foundation pit wall after time series alignment and outlier removal, the surface settlement monitoring values and the lateral displacement monitoring values of the corresponding measuring points of the deep foundation pit wall are grouped according to the measuring point number. The data integrity within each group is checked to eliminate incomplete data groups, and data pairs are generated that are grouped according to the measuring point number and have guaranteed integrity.

[0013] Based on the data pairs grouped by measuring point numbers and ensuring integrity, the surface settlement monitoring values of each data pair and the lateral displacement monitoring values of the corresponding measuring points of the deep foundation pit wall are sorted to form calibrated deformation sequence data.

[0014] Preferably, the steps for obtaining the surface subsidence contour map are:

[0015] Based on the surface settlement monitoring values in the calibration deformation sequence data, the surface settlement monitoring values are distributed and sorted according to the spatial coordinates of the measuring points, and the surface settlement monitoring value differences between adjacent measuring points and the distances of each measuring point are calculated to generate settlement difference and distance data of adjacent measuring points;

[0016] Calculating the interpolation factor of the surface settlement contour line based on the settlement difference of adjacent measuring points and the distance measurement data;

[0017] Based on the surface settlement contour interpolation factor, the surface settlement monitoring values are gridded and distributed by spatial interpolation. During the gridding process, the interpolation density of each grid unit is adjusted according to the surface settlement contour interpolation factor to form a surface settlement contour map.

[0018] Preferably, the steps for obtaining the width feature of the sedimentation tank are:

[0019] Based on the surface settlement contour map, identifying the area with the densest settlement contour lines in the surface settlement contour map, and marking the outer edge coordinate points of the area to obtain the outer edge coordinate points of the key settlement area;

[0020] Based on the outer edge coordinate points of the key settlement area, the horizontal distance between the outer edge coordinate points is measured, and representative distances are selected according to the principle of maximum horizontal spacing to obtain the maximum horizontal width of the key settlement area;

[0021] Based on the maximum horizontal width of the key settlement area, the maximum horizontal width is used as a characteristic indicator of the settlement tank, and the width value is recorded as the settlement tank width feature to form the settlement tank width feature.

[0022] Preferably, the steps for obtaining the maximum displacement value of the wall are:

[0023] Based on the wall lateral displacement monitoring values in the calibration deformation sequence data, the wall lateral displacement monitoring values are grouped according to the monitoring section number, and all observation values of the same time section are extracted for the wall lateral displacement monitoring values in each group of monitoring sections. By comparing the timestamps, the valid observation values in the time section are selected to obtain the valid lateral displacement monitoring values of each monitoring section at the same time section;

[0024] Based on the effective lateral displacement monitoring values of each monitoring section at the same time section, each group of data is traversed in turn and the sizes of the observation values in the group are compared. The lateral displacement monitoring value with the largest value in each group is selected, and the corresponding monitoring section number and observation time are recorded at the same time to obtain the maximum lateral displacement value set of each monitoring section;

[0025] Based on the maximum lateral displacement value set of each monitoring section, the sizes of all the maximum lateral displacement values in the set are compared, and the highest group is selected as the representative value. At the same time, the monitoring section number and observation time of the representative value are marked to form the maximum displacement value of the wall.

[0026] Preferably, the steps for obtaining the surface wall evolution association rules are:

[0027] Based on the maximum wall displacement value, the maximum wall displacement values are aggregated according to the time sequence of the excavation process, and a one-to-one correspondence is established between the settlement trough width characteristics corresponding to each process and the maximum wall displacement value, thereby obtaining combined data of the excavation process, the maximum wall displacement value, and the settlement trough width characteristics;

[0028] Calculating a comprehensive factor of wall settlement evolution based on the combined data of the excavation process, the maximum displacement value of the wall, and the width characteristics of the settlement trough;

[0029] Based on the comprehensive factor of wall settlement evolution, the comprehensive factor of wall settlement evolution is correlated with the excavation process number, the maximum displacement value of the wall, and the width characteristics of the settlement trough. The combination representing the relationship between wall deformation and settlement trough change is extracted to form the surface wall evolution association rules.

[0030] Preferably, the steps of obtaining the expected wall response mode are:

[0031] Based on the settlement trough width feature, the settlement trough width feature is matched with the historical width feature recorded in the surface wall evolution association rule. The settlement trough width range of each historical record is checked one by one to see whether it covers the current settlement trough width feature. The historical records that meet the matching conditions are selected, and the corresponding historical excavation process number, settlement trough width range and associated wall behavior description are extracted to generate a historical association record set.

[0032] Based on the set of historical association records, the wall behavior descriptions in each historical association record are parsed one by one, and the wall displacement change trends, displacement change rates, and key deformation nodes associated with the descriptions are extracted. Records of similar wall displacement change trends, displacement change rates, and key deformation nodes are grouped together, and the most frequently occurring wall behavior descriptions in each group are summarized to obtain the main wall behavior pattern groups.

[0033] Based on the main wall behavior pattern group, the main wall behavior pattern group corresponding to the current settlement trough width characteristics is matched and verified with the real-time monitoring data. By comparing the displacement change trend, displacement change rate and key deformation nodes for consistency, the behavior description that meets the current working conditions is screened and the expected wall response pattern is generated.

[0034] Preferably, the steps for obtaining the wall lateral deformation prediction result are:

[0035] Based on the expected wall response pattern, the expected wall response pattern is matched with the deformation state of the current deep foundation pit wall, the displacement increment, acceleration and time change rate of the current deep foundation pit wall are extracted, and a parameter set required for the current deep foundation pit wall prediction is generated;

[0036] Calculating a predicted value of the lateral deformation of the deep foundation pit wall within a next time window according to the set of parameters required for the current deep foundation pit wall prediction;

[0037] Based on the predicted value of the lateral deformation of the deep foundation pit wall in the next time window, the predicted value is compared with the historical deformation threshold, the real-time monitoring data and the expected wall response mode item by item to obtain the wall lateral deformation prediction result.

[0038] The present invention provides a method for predicting lateral deformation of a deep foundation pit wall, comprising the following steps:

[0039] Collect surface settlement monitoring values and lateral displacement monitoring values of corresponding measuring points on the deep foundation pit wall, perform time series alignment processing on the data points and eliminate abnormal monitoring values to establish calibrated deformation sequence data;

[0040] Based on the surface settlement monitoring values in the calibration deformation sequence data, surface settlement contour lines are generated by spatial interpolation to obtain a surface settlement contour map; based on the surface settlement contour map, the width of the settlement trough formed in the key settlement area is measured to establish the settlement trough width feature;

[0041] Based on the wall lateral displacement monitoring values in the calibration deformation sequence data, the maximum lateral displacement value of each monitoring section at the same time section is extracted to obtain the maximum wall displacement value. Based on the maximum wall displacement value, the corresponding relationship between the evolution with the excavation process and the change of the settlement trough width characteristics is analyzed to establish the surface wall evolution association rules;

[0042] Based on the width characteristics of the settlement trough, the wall behavior pattern corresponding to the width characteristics is queried in the surface wall evolution association rules to obtain an expected wall response pattern. Based on the expected wall response pattern and combined with the current deformation state of the deep foundation pit wall, the lateral deformation value of the deep foundation pit wall in the next time window is predicted to obtain the wall lateral deformation prediction result.

[0043] Compared with the prior art, the advantages and positive effects of the present invention are:

[0044] In the present invention, by real-time acquisition and strict execution of data time series alignment processing, the consistency of surface settlement data and wall lateral displacement data is ensured, and abnormal monitoring data is effectively eliminated to improve data accuracy and consistency; in the spatial interpolation process, the width measurement of the settlement area is introduced to determine the width characteristics of the settlement trough, and the surface deformation trend is captured by deformation indicators; the maximum lateral displacement of each time section of the monitoring profile is extracted, and a dynamic correspondence between the maximum displacement and the width of the settlement trough is established to identify the regular influence of changes in the construction process on the lateral deformation; by matching the width characteristics of the settlement trough with the wall response mode, the accuracy and adaptability of the lateral deformation prediction value are dynamically ensured to be improved; combined with the current deformation state and the prediction mode for comparative analysis, real-time correction and accurate prediction results are given, so that the early perception of deformation trends and the risk prevention and control capabilities are enhanced, thereby reducing the risk hazards in the construction stage. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 It is a system flow chart of the present invention. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0047] See also Figure 1 The present invention provides a technical solution: a lateral deformation prediction system based on a deep foundation pit wall comprises:

[0048] The deformation data acquisition module collects surface settlement monitoring values and lateral displacement monitoring values of corresponding measuring points on the deep foundation pit wall, performs time sequence alignment processing on the data points and eliminates abnormal monitoring values to establish calibrated deformation sequence data;

[0049] The surface pattern recognition module generates surface settlement contour lines through spatial interpolation based on the surface settlement monitoring values in the calibration deformation sequence data, and obtains a surface settlement contour map. Based on the surface settlement contour map, the width of the settlement trough formed in the key settlement area is measured and the settlement trough width characteristics are established;

[0050] The wall response association module extracts the maximum lateral displacement value of each monitoring section at the same time section based on the wall lateral displacement monitoring values in the calibrated deformation sequence data to obtain the maximum wall displacement value. Based on the maximum wall displacement value, the corresponding relationship between the evolution of the wall with the excavation process and the change of the settlement trough width characteristics is analyzed to establish the surface wall evolution association rules;

[0051] The deformation trend prediction module, based on the width characteristics of the settlement trough, queries the wall behavior pattern corresponding to the width characteristics in the surface wall evolution association rules to obtain the expected wall response pattern. Based on the expected wall response pattern and combined with the current deformation state of the deep foundation pit wall, the lateral deformation value of the deep foundation pit wall in the next time window is predicted to obtain the wall lateral deformation prediction result.

[0052] The steps for obtaining the calibration deformation sequence data are:

[0053] Collect surface settlement monitoring values and lateral displacement monitoring values of corresponding measuring points on the deep foundation pit wall, match them one by one according to the collection time, mark and remove the unmatched monitoring values, and generate surface settlement monitoring values and lateral displacement monitoring values of corresponding measuring points on the deep foundation pit wall after time series alignment and outlier removal;

[0054] Based on the surface settlement monitoring values and the lateral displacement monitoring values of the corresponding measuring points of the deep foundation pit wall after time series alignment and outlier removal, the surface settlement monitoring values and the lateral displacement monitoring values of the corresponding measuring points of the deep foundation pit wall are grouped according to the measuring point number. The data integrity within each group is checked to eliminate incomplete data groups, and data pairs are generated that are grouped according to the measuring point number and have guaranteed integrity.

[0055] Based on the data pairs grouped by measuring point numbers and ensuring integrity, the surface settlement monitoring values of each data pair and the lateral displacement monitoring values of the corresponding measuring points of the deep foundation pit wall are sorted to form calibrated deformation sequence data.

[0056] Specifically, the surface settlement monitoring values and the lateral displacement monitoring values of the corresponding measuring points of the deep foundation pit wall are collected. First, the two types of monitoring data are matched one by one according to the collection time. The specific operation is to traverse each surface settlement monitoring value, record its collection timestamp, and then search for records with the same timestamp in the lateral displacement monitoring values of the corresponding measuring points of the deep foundation pit wall. Considering the possible slight time asynchrony in actual monitoring, a time matching tolerance is set, for example Seconds, that is, if the acquisition time difference of two monitoring values is within this tolerance range, it is considered a successful match, and the monitoring values that cannot find a corresponding timestamp match within this tolerance will be marked, for example, adding a "unmatched" label, and then all monitoring data points marked as "unmatched" will be removed from their respective data sets. Next, the abnormal monitoring values of the time-aligned data pairs that have been successfully matched are removed. The abnormal values here mainly refer to the abnormalities of the data values themselves. The method based on the interquartile range (IQR) is used for judgment. For the surface settlement monitoring value sequence, the first quartile (Q1) and the third quartile (Q3) are first calculated to obtain the interquartile range , set the limit parameters for outlier judgment The value is 1.5, which is a common statistical standard used to identify moderate outliers. For example, if the Q1 of a batch of surface settlement monitoring values is 5 mm and Q3 is 12 mm, the IQR is 7 mm, so the effective data range is mm to Any surface settlement monitoring value (and its paired wall lateral displacement value) outside this range will be considered abnormal and eliminated. Similarly, the same abnormal value elimination process is performed on the lateral displacement monitoring value sequence of the corresponding measuring point of the deep foundation pit wall to calculate its interquartile range. , and using the same bounds parameters =1.5 (this parameter can be adjusted according to specific project experience and data characteristics. For example, it can be appropriately relaxed to 2.0 for data with large fluctuations). Set the normal range. For example, if the Q1 of a batch of wall lateral displacement monitoring values is 3 mm and Q3 is 10 mm, then the IQR is 7 mm. The effective data range is mm to Millimeters. The lateral displacement monitoring values of the wall (and their paired surface settlement values) that are beyond this range are also eliminated. After the above-mentioned time matching and bidirectional numerical outlier elimination, the surface settlement monitoring values and the lateral displacement monitoring values of the corresponding measuring points of the deep foundation pit wall are generated after time series alignment and outlier elimination.

[0057] Based on the surface settlement monitoring values and lateral displacement monitoring values of the corresponding measuring points of the deep foundation pit wall after time series alignment and outlier removal, these data are grouped according to the measuring point number. In specific implementation, a data structure can be constructed, for example, with the measuring point number as the key, and its value is a dictionary containing a list of all valid (i.e. paired) surface settlement monitoring values and wall lateral displacement monitoring values of the measuring point. All cleaned data points are traversed, and each data point is assigned to a list of corresponding keys according to the measuring point number recorded. After grouping, the data integrity in each group is checked to eliminate incomplete data groups. The data integrity check standard is based on a preset minimum threshold value for the number of valid data point pairs. The threshold is usually set based on the total monitoring time, monitoring frequency and the basic data volume requirements of the analysis model. For example, if the monitoring period of a deep foundation pit project is 60 days and the monitoring equipment automatically collects data 4 times a day (once every 6 hours), then theoretically each measuring point should have data pairs, set a data integrity percentage , for example 70%. This percentage is determined based on engineering experience to ensure that the amount of data used for analysis is sufficient to reflect the statistical characteristics of the deformation trend. Data sequences below this standard may not provide a reliable analysis basis due to too few data points. The minimum threshold for the number of valid data points is During the inspection process, calculate the actual number of data pairs contained in each measurement point number group. ,like , then the data group corresponding to the measurement point number is determined to be an incomplete data group and is removed from the data set for subsequent analysis. For example, measurement point T001 has 180 data pairs ( ), then retain, measuring point T002 has 150 data pairs ( ), it will be marked as incomplete and removed. After this step is completed, data pairs are generated that are grouped according to the measurement point number and ensure integrity.

[0058] Based on the data pairs grouped by measuring point numbers and ensuring integrity, the surface settlement monitoring values and lateral displacement monitoring values of the corresponding measuring points of the deep foundation pit wall in each data pair are then sorted. The core basis for this sorting is the acquisition timestamp of the monitoring data pair. The purpose is to ensure that the data of each measuring point forms a time series arranged in strict chronological order, laying the foundation for subsequent trend analysis and pattern recognition. In specific operations, for each measuring point number group that has passed the integrity check, all the data pairs it contains are extracted (each data pair consists of a surface settlement monitoring value, a wall lateral displacement monitoring value, and a corresponding acquisition timestamp). Then, within each group, a standard sorting algorithm, such as quick sort or merge sort, is applied to sort by the acquisition timestamp. Key, in ascending order, that is, from the earliest monitoring time point to the latest monitoring time point. If there are two data pairs with exactly the same timestamp (although this situation is extremely rare after pre-order processing, it may still occur in some low-precision time records or specific concurrent acquisition scenarios), a secondary sorting rule can be set, such as sorting according to the size of the surface settlement monitoring value or the size of the wall lateral displacement monitoring value, or simply maintaining their relative order in the original data, but the main goal is to ensure strict temporal order. After completing this sorting process, each measuring point number corresponds to one or more time series of surface settlement monitoring values and wall lateral displacement monitoring values. The data points in these sequences are strictly arranged in chronological order, thus forming calibrated deformation sequence data.

[0059] The steps to obtain the surface subsidence contour map are as follows:

[0060] Based on the surface settlement monitoring values in the calibration deformation sequence data, the surface settlement monitoring values are distributed and sorted according to the spatial coordinates of the measuring points, and the surface settlement monitoring value differences between adjacent measuring points and the distance of each measuring point are calculated to generate the settlement difference and distance data of adjacent measuring points;

[0061] According to the settlement difference of adjacent measuring points and the distance data, the interpolation factor of the surface settlement contour line is calculated. The calculation formula is:

[0062] ;

[0063] in, For the Interpolation factor of the surface settlement contour line of the measuring point, For the Surface settlement monitoring value of the measuring point, For the Surface settlement monitoring value of the measuring point, For the Measuring point and The horizontal distance of the measuring point, For the The historical settlement mean of the measuring point, For the The historical settlement mean of the measuring point, is the total number of adjacent measuring points;

[0064] Based on the surface subsidence contour interpolation factor, the surface subsidence monitoring values are gridded and distributed through spatial interpolation. During the gridding process, the interpolation density of each grid unit is adjusted according to the surface subsidence contour interpolation factor to form a surface subsidence contour map.

[0065] Specifically, based on the surface settlement monitoring values in the calibration deformation sequence data, the surface settlement monitoring values are first recorded and organized according to the corresponding three-dimensional coordinates of the measuring point (for example, X, Y, Z coordinates, where X, Y are plane coordinates and Z is elevation) in order to perform spatial proximity analysis. Next, the "adjacent" relationship between the measuring points is determined. A clear method is to generate a spatial proximity relationship for each measuring point. Set a spatial search radius The search radius is determined according to the actual measurement point arrangement density of the construction site. For example, if the average distance between measurement points is 10 meters, you can set 15 meters to ensure that the surrounding measurement points with the most direct impact are included. All measurement points are traversed. For the measurement point currently being processed, , calculate its value with all other measuring points The straight-line distance between ,like and , then the measuring point Considered as a measuring point After the adjacent measuring points are identified, for each pair of adjacent measuring points ( ), calculate the difference in surface subsidence monitoring values between them, that is, ,in and The measuring points are and measuring points The surface settlement monitoring values obtained from the calibration deformation sequence data at the same time section, at the same time, calculate the horizontal distance between the two adjacent measuring points, that is, the distance measurement , these calculated differences and the corresponding horizontal distance And the measurement point pairs involved in the calculation are stored. For example, if the coordinates of measurement point A are (10, 20, 5) and the settlement value is 15 mm, the coordinates of measurement point B are (10, 30, 4.8) and the settlement value is 12 mm, the set If the distance between them is 15 meters, then the space distance between them is about 10.02 meters. If it is less than 15 meters, they are considered adjacent. The settlement difference is mm, horizontal distance is After processing all the measuring point pairs in this way, a set of settlement difference values and corresponding distance measurements of each adjacent measuring point pair is generated, namely, the settlement difference value and distance measurement data of adjacent measuring points.

[0066] formula: The usefulness of the formula is that the surface settlement contour interpolation factor The calculation of takes into account the instantaneous settlement difference between the current monitoring point and its adjacent monitoring points, their spatial distance and the similarity of their historical settlement behaviors, and introduces the square term of the difference between the historical settlement means. And put it in the square root of the denominator, so that the contribution weight of adjacent points with large historical settlement behavior differences to the current interpolation factor is reduced, and conversely, the weight of points with similar behavior is relatively increased. This design can reflect the complexity and difference of local surface deformation, avoid the smoothing effect that may be caused by simple distance or settlement difference weighting, and make the identified settlement change area more accurate. The use of absolute value ensures that all difference contributions are positive, and finally divided by the total number of adjacent points This achieves normalized averaging, making the factors between measurement points with different numbers of neighborhoods comparable, which helps to more accurately adjust the density of subsequent grid interpolation, thereby improving the accuracy and expressiveness of surface subsidence contour maps;

[0067] For the The surface settlement monitoring value of the measuring point is derived from the "calibration deformation sequence data" generated in the previous steps of this application. Specifically, it refers to the surface settlement monitoring value of the measuring point at a specific analysis time. After data cleaning and calibration, the surface settlement readings, for example, at 3:00 PM on May 8, 2025, were obtained by consulting the “calibration deformation sequence data” and the measurement point numbered CP001 (i.e. The surface settlement monitoring value at the 2000-meter measuring point was 22.5 mm;

[0068] For the The surface settlement monitoring value of the measuring point is also obtained from the "calibration deformation sequence data" and represents the surface settlement monitoring value of the measuring point. Adjacent measuring points Surface settlement readings at the same analysis time, measuring point It is a certain measuring point One of the adjacent measuring points, for example, for the above measuring point CP001, one of its adjacent measuring points CP002 (i.e. The surface settlement monitoring value of the measuring points at the same time was 18.0 mm;

[0069] For the Measuring point and The horizontal distance of the measuring point is obtained by calculating the "settlement difference of adjacent measuring points and distance data". and measuring points The plane coordinates (such as X and Y coordinates) in the engineering site coordinate system are calculated using the distance formula between two points. For example, the plane coordinates of measuring point CP001 are (50.5 meters, 100.2 meters), and the plane coordinates of the adjacent measuring point CP002 are (50.5 meters, 110.2 meters). The horizontal distance between them is rice;

[0070] For the The historical settlement mean of the measuring point. This value is the average settlement value of the measuring point. The result of arithmetic averaging of all surface settlement monitoring values in the "calibrated deformation sequence data" since the beginning of monitoring to the current analysis time reflects the average settlement level of the measuring point in a historical period. For example, measuring point CP001 has a total of 180 valid settlement records in the past 90 days, and the total of these records is 2700 mm. The historical settlement average is mm;

[0071] For the The historical settlement mean of the measuring point is obtained in the same way as Exactly the same, but for adjacent measuring points , using measuring points For example, the adjacent measuring point CP002 has 175 valid settlement records in the past 90 days, and the total settlement record is 2100 mm. The average settlement value is mm;

[0072] is the total number of adjacent measuring points. This value is for the measuring points The statistical result when determining adjacent measuring points represents the points that meet the proximity conditions (for example, For example, for measuring point CP001, after proximity judgment, three adjacent measuring points (CP002, CP003, CP004) are found. ;

[0073] Calculation process: Taking the measuring point CP001 as an example, there are three adjacent measuring points CP002, CP003, and CP004, namely The specific values of each parameter are as follows: For CP001 ( ): mm, mm.

[0074] Substituting this into the formula, we get 17.78. This result indicates that the interpolation factor of the surface settlement contour line of measuring point CP001 is approximately 17.78. This value comprehensively reflects an average measure of the differences in current settlement, spatial distance, and historical settlement behavior of point CP001 relative to its surrounding points.

[0075] Based on the surface settlement contour interpolation factor, the specific operation is to first define a regular geographic grid covering the entire monitoring area. The initial size of the grid cell is preliminarily set according to the scope of the monitoring area and the required accuracy of the contour map. For example, for an area of 100 meters × 100 meters, a 1 meter × 1 meter grid cell can be preliminarily set. Next, for the center point of each grid cell, a spatial interpolation technique (such as the inverse distance weighted method IDW or Kriging) is used to estimate its surface settlement monitoring value. This interpolation process uses the surface settlement monitoring values in the original calibration deformation sequence data. The key point is that in the gridding process, the interpolation factors of the surface settlement contour lines calculated in the previous step are required. The interpolation density of each grid cell is dynamically adjusted. Specifically, the interpolation density of each measuring point is first adjusted. The value is also interpolated onto the grid to obtain the center point of each grid cell value, then set one or more The threshold interval, for example, defines the low impact area ( ), medium impact area ( ), high impact area ( ), these thresholds are based on the The interpolation density adjustment strategy is different for grid cells in different impact areas, which is set based on the analysis of the statistical characteristics of the value distribution (such as mean and standard deviation) and combined with engineering experience. In the high impact area, that is, Areas with larger values indicate that the settlement changes are complex or the differences are significant. In this case, a higher density interpolation strategy can be adopted. For example, when executing the inverse distance weighted method, the radius of the search for neighboring monitoring points can be reduced (for example, from the default 50 meters to 25 meters) or the number of nearest neighbor points forced to be included in the calculation can be increased (for example, from the default 5 points to 8 points), or the grid in this area can be locally encrypted (for example, the 1 meter × 1 meter unit can be subdivided into 0.5 meter × 0.5 meter units and then interpolated). Conversely, in low-impact areas, a relatively sparse interpolation strategy can be adopted or the initial setting can be maintained. Through this adaptive interpolation density adjustment based on the surface settlement contour interpolation factor, after completing the estimation of the settlement values of all grid cells, the standard contour generation algorithm can be used to draw a surface settlement contour map based on these gridded settlement data.

[0076] The steps to obtain the width characteristics of the sedimentation tank are:

[0077] Based on the surface settlement contour map, identify the area with the densest settlement contour lines in the surface settlement contour map, mark the outer edge coordinate points of the area, and obtain the outer edge coordinate points of the key settlement area;

[0078] Based on the outer edge coordinate points of the key settlement area, the horizontal distance between the outer edge coordinate points is measured, and representative distances are selected according to the principle of maximum horizontal spacing to obtain the maximum horizontal width of the key settlement area;

[0079] Based on the maximum horizontal width of the key settlement area, the maximum horizontal width is used as the characteristic indicator of the settlement tank, and the width value is recorded as the settlement tank width feature to form the settlement tank width feature.

[0080] Specifically, based on the surface settlement contour map, the map must first be digitized and converted into raster data or vector data that can be analyzed by a computer. If it is raster data, each pixel corresponds to a settlement value. To identify the area with the densest settlement contour lines, a specific method is to calculate the numerical value of the surface settlement gradient, that is, to calculate the settlement change rate in the X and Y directions at each grid point, and then synthesize it to obtain the total gradient value of the point. For example, for the grid point The settlement value at , and its X-direction gradient is approximately , the Y-direction gradient is approximately ,in and is the grid spacing, the total gradient , the larger the gradient value, the denser the corresponding contour lines, and set a gradient threshold To define the "most dense" area, this threshold The setting can be based on a statistical analysis of the gradient values of all grid points in the entire monitoring area, such as taking the 90th percentile of all gradient values, or setting it to the average gradient value plus twice the standard deviation. If the calculated regional average gradient is 0.004 m / m and the standard deviation is 0.001 m / m, then Can be set to m / m, all gradient values are greater than or equal to The grid points are initially identified as part of the dense area. Subsequently, these point sets are clustered, and the dense point group connected upward is identified as an independent dense area. If there are multiple such independent dense areas, the area with the largest area or the area containing the maximum settlement value point is selected as the "key settlement area". Once the key settlement area is determined, a boundary extraction algorithm, such as the Moore neighborhood tracking algorithm or the radial scanning algorithm, is used to track and record the plane coordinates (X, Y coordinates) of the grid points that constitute the outermost contour of the area. The set of these coordinate points is the outer edge coordinate points of the key settlement area.

[0081] Based on the outer edge coordinate points of the key settlement area, we first need to clarify the definition of "horizontal", which is usually relative to the excavation direction of the deep foundation pit or the main deformation direction. For example, if the foundation pit is excavated along the north-south direction, then "horizontal" generally refers to the east-west direction. For example, if the horizontal direction is determined to be the X-axis direction of the site coordinate system, the process of measuring the horizontal distance between the outer edge coordinate points and screening the representative distance is as follows: traverse each point in the outer edge coordinate point set of the key settlement area , for each point To find the corresponding point in the "horizontal direction", a scanning line method can be used, that is, along multiple parallel scanning lines perpendicular to the "horizontal direction" (for example, along the Y-axis direction), the key settlement area is cut at a certain interval (for example, set to 0.5 meters according to the measurement point density or the expected accuracy). Each scanning line will generate two or more intersections with the outer edge of the key settlement area. The pair of intersections on each scanning line located at the outermost edge of the area boundary is recorded. and , the horizontal distance between them is the horizontal width of the scan line position , record the calculated horizontal widths on all scan lines, and filter them according to the "maximum horizontal spacing principle", that is, Among them, the one with the largest value is selected as the representative distance. For example, through the above scanning line method, The width is 8.5 meters. The width is 9.2 meters. The width is 9.0 meters at the specified location, and 9.2 meters is the maximum horizontal spacing currently screened out, which gives the maximum horizontal width of the key settlement area.

[0082] Based on the maximum horizontal width of the key settlement area, this specific value is directly used as a key geometric parameter to characterize the current surface settlement trough morphology, that is, the characteristic index of the settlement trough. The maximum horizontal width value of 9.2 meters calculated before is saved together with the corresponding monitoring date, time and identification information of the relevant surface settlement contour map. For example, it is recorded as: "Monitoring date May 8, 2025, surface settlement contour map number SCM-20250508-01, maximum horizontal width of the key settlement area: 9.2 meters". This recording method ensures the traceability and relevance of the data, so that when performing subsequent deformation trend analysis and prediction, the settlement trough width characteristics at a specific time point can be accurately linked to other working conditions parameters at that time (such as excavation depth, wall displacement, etc.). The recorded width value is officially adopted as the settlement trough width characteristic at that moment, forming a data point that can be used for time series analysis or pattern matching, forming a settlement trough width characteristic.

[0083] The steps to obtain the maximum displacement value of the wall are:

[0084] Based on the wall lateral displacement monitoring values in the calibration deformation sequence data, the wall lateral displacement monitoring values are grouped according to the monitoring section number. All observation values of the same time section are extracted from the wall lateral displacement monitoring values in each group of monitoring sections. The valid observation values in the time section are selected by comparing the timestamps to obtain the valid lateral displacement monitoring values of each monitoring section at the same time section.

[0085] Based on the effective lateral displacement monitoring values of each monitoring section at the same time section, each group of data is traversed in turn and the sizes of the observation values in the group are compared. The lateral displacement monitoring value with the largest value in each group is selected, and the corresponding monitoring section number and observation time are recorded at the same time to obtain the maximum lateral displacement value set of each monitoring section;

[0086] Based on the maximum lateral displacement value set of each monitoring section, the sizes of all the maximum lateral displacement values in the set are compared, and the highest group is selected as the representative value. At the same time, the monitoring section number and observation time of the representative value are marked to form the maximum displacement value of the wall.

[0087] Specifically, based on the monitoring values of the lateral displacement of the wall in the calibration deformation sequence data, these monitoring data are first classified and grouped according to the monitoring section numbers to which they belong. For example, all monitoring data with section number PM01 are grouped into one group, PM02 into another group, and so on. After the grouping is completed, for the data in each monitoring section number group, it is necessary to extract all the observation values representing the specific "same time section". The "same time section" here refers to a target analysis time point, for example, it is set to a fixed time of the day, such as 10:00 am. Taking into account the possible slight time deviations in the data collection of each sensor in actual monitoring, an effective time window will be set around this target time. The size of the window is determined according to the synchronization accuracy of the monitoring system and the data collection frequency. For example, if the data is collected once an hour, it can be Set the valid time window to 5 minutes before and after the target time. That is, if the target time is 10:00:00, the time window is 09:55:00 to 10:05:00. Traverse all the wall lateral displacement monitoring values recorded in the specified monitoring section (for example, PM01) within this time window. These values usually correspond to sensor readings at different depths in the section. If there are multiple readings of the same depth sensor within the valid time window, the reading with the timestamp closest to the target time is selected as the valid observation value for that depth. Alternatively, if the readings are very dense and the values are similar, their average can also be taken. However, the single value closest to the target time is usually used as the basis to ensure that each monitoring depth has only one valid lateral displacement monitoring value in this time section. In this way, the valid lateral displacement monitoring value of each monitoring section at the same target time section is obtained.

[0088] Based on the effective lateral displacement monitoring values of each monitoring section at the same time section, the data inside each monitoring section is processed next. The specific operation is to access a set of effective lateral displacement monitoring values contained in each monitoring section (such as PM01, PM02, etc.) at the specified time section in turn. This set of values represents the lateral displacement of the wall at different depths of the section. For example, for the monitoring section PM01, at the time section at 10:00 am on May 8, 2025, its effective lateral displacement monitoring values are: 5.3 mm at a depth of -2.0 meters, 8.1 mm at a depth of -4.0 meters, 11.5 mm at a depth of -6.0 meters, and 9.2 mm at a depth of -8.0 meters. Compare these values (5.3, 8.1, 11.5, 9.2) to find the maximum value. In this case, the maximum lateral displacement monitoring value of the PM01 profile at this moment is 11.5 mm, which occurs at a depth of -6.0 meters. Record this maximum value, and at the same time record the monitoring profile number to which it belongs (PM01) and the observation time of the time section (10:00 am on May 8, 2025). Perform the same operation on all other monitoring profiles (PM02, PM03, etc.), that is, find the maximum value of all valid lateral displacement monitoring values in each profile and at the same time section, and record the corresponding profile number, maximum displacement value and observation time. After completing the traversal and maximum value extraction of all monitoring profiles, a set containing the maximum lateral displacement values of each monitoring profile at this moment and their related information is obtained, that is, the maximum lateral displacement value set of each monitoring profile.

[0089] Based on the maximum lateral displacement value set of each monitoring section, the set contains the maximum wall lateral displacement readings of each monitoring section at the same specific time section. For example, the set may contain the following data: (monitoring section PM01, maximum displacement 11.5 mm, observation time 2025-05-08 10:00), (monitoring section PM02, maximum displacement 14.2 mm, observation time 2025-05-08 10:00), (monitoring section PM03, maximum displacement 10.8 mm, observation time 2025-05-08 10:00). The processing process is to traverse each record in this set and extract the maximum lateral displacement value of each monitoring section. (i.e. 11.5 mm, 14.2 mm, 10.8 mm), and directly compare these values to screen out the one with the highest value. In this example, 14.2 mm is the highest value among the maximum displacement values of all sections. This 14.2 mm is selected as the representative maximum displacement value of the entire deep foundation pit wall at this time section. At the same time, the information associated with this highest value is fully recorded, including the monitoring section number of its source (PM02 in this case) and the exact observation time (2025-05-08 10:00). The screened highest value, its corresponding monitoring section number and observation time are combined together and recorded as a whole to form the maximum displacement value of the wall.

[0090] The steps for obtaining the association rules of surface wall evolution are as follows:

[0091] Based on the maximum wall displacement value, the maximum wall displacement values are aggregated according to the time sequence of the excavation process, and a one-to-one correspondence is established between the settlement trough width characteristics corresponding to each process and the maximum wall displacement value, thus obtaining the combined data of the excavation process, the maximum wall displacement value and the settlement trough width characteristics;

[0092] Based on the combined data of excavation process, maximum wall displacement value and settlement trough width characteristics, the comprehensive factor of wall settlement evolution is calculated using the following formula:

[0093] ;

[0094] in, For the Comprehensive factors of wall settlement evolution in each process, For the The maximum displacement value of the wall in each process, For the The maximum displacement value of the wall in each process, For the The width characteristics of the sedimentation tank in each process, For the The width characteristics of the sedimentation tank in each process, For the The duration of each process, For the The duration of each process, For the The amount of monitoring data for each process, is the total number of processes;

[0095] Based on the comprehensive factor of wall settlement evolution, the comprehensive factor of wall settlement evolution was correlated with the excavation process number, the maximum displacement value of the wall, and the width characteristics of the settlement trough. The combination representing the relationship between wall deformation and settlement trough change was extracted to form the surface wall evolution association rules.

[0096] Specifically, based on the maximum displacement value of the wall, first obtain a detailed excavation process plan from the project construction management record. The plan should include the unique numbers of all excavation processes planned in the project, the estimated start and end times of each process, and the main contents of the process. For example, process S01 (excavation of the first layer of earthwork) is scheduled to start at 08:00 on May 1, 2025, and end at 17:00 on May 7, 2025; process S02 (excavation of the second layer of earthwork and application of the first support) is scheduled to start at 08:00 on May 8, 2025, and end at 17:00 on May 14, 2025, until the last planned process S Then, the “maximum wall displacement value” data sequence with time stamps obtained by the previous steps and the “settlement trough width feature” data sequence with time stamps are accurately allocated to the time intervals of each completed or ongoing excavation process according to their respective observation times. For each completed excavation process , select the "maximum wall displacement value" observed at the end time of the process (or the time closest to the end time) as the representative maximum wall displacement value of the process, and record it as Similarly, the “sedimentation tank width feature” at the corresponding moment is selected as the representative sedimentation tank width feature of the process, which is recorded as For example, for the completed process S01, if the final maximum wall displacement value determined at its end (May 7, 2025) is 15.0 mm and the corresponding settlement trough width feature is 8.0 m, then the combined data entry of process S01 is (S01, 15.0 mm, 8.0 m). This process continues until all the processes that have occurred have corresponding representative data, forming a combined data of excavation processes, maximum wall displacement values, and settlement trough width features arranged in chronological order.

[0097] formula: The usefulness of the formula is that the comprehensive factor of wall settlement evolution is To quantitatively assess specific The relative evolution intensity and data support of each process in the context of the entire project. The numerator of the formula is constructed by adding the square root of the product of the maximum wall displacement change and the settlement tank width change of all processes (occurring and planned) in the project (and taking into account the regulatory effect of the process duration ratio) to construct an indicator representing the "total potential energy" or "total cumulative change" of the overall deformation of the project. When evaluating each process, if the parameters of the future process are estimated values, then this "total potential energy" also has an estimated component, and the denominator is composed of the total number of project processes. and the current Amount of monitoring data for the process This makes The value will vary depending on the specific process Varies depending on: amount of monitoring data The larger the value, the larger the denominator, which will result in If the monitoring data of a process is less, the risk or uncertainty of the process (expressed as a higher value) is relatively high, or the “weight” or “sensitivity” of this process in the overall project evolution is amplified;

[0098] For the The maximum displacement value of the wall in each process is mainly extracted from the generated "combined data of excavation process, maximum displacement value of the wall and width characteristics of the settlement trough", which represents the maximum displacement value of the wall in the first process. The maximum lateral displacement of the wall observed or determined at the end of each excavation process (or a representative time point determined for the process), in millimeters, for example, process S01 ( ) of the actual maximum wall displacement is 15.0 mm, process S02 ( ) of the actual maximum wall displacement is 25.0 mm, and the planned process S03 ( ) of the estimated maximum wall displacement 32.0 mm;

[0099] For the The maximum displacement value of the wall in each process is obtained in the same way , for the first process (i.e. hour), Represents the initial state before excavation, usually set to 0 mm, for example, when calculating When the item mm, when calculating When the item mm;

[0100] For the The width characteristics of the sedimentation tank in each process are also mainly extracted from the generated combined data, representing the The width of the sedimentation tank at the end of each process (or at a representative time point) is the actual observed value for the completed process and the estimated value for the future process. For example, process S01 ( ) actual width of the sedimentation tank is 8.0 m, process S02 ( ) actual width of the sedimentation tank is 10.5 meters, and the planned process S03 ( ) estimated width of the sedimentation tank 12.5 meters;

[0101] For the The width characteristics of the sedimentation tank in each process are obtained in the same way , for the first process ( hour), The width of the sedimentation tank represents the initial state, which is usually set to 0 meters. For example, when calculating When the item m, when calculating When the item rice;

[0102] For the The duration of each process is obtained from the project construction management records or excavation process plan. The actual duration of a process is calculated by subtracting its start time from the planned or actual end time of the process. For example, the actual duration of process S01 The actual duration of step S02 is 7 days. The estimated duration of process S03 in the plan is 7 days. 6 days;

[0103] For the The duration of each process is obtained in the same way , for the first process ( ) calculation item, to ensure Right now Meaningful, agreed When this ratio The value of is 1, that is, the calculation result of the first process is not adjusted by this item. For example, when calculating When the item Day, when calculating When the item is set ;

[0104] For the The amount of monitoring data for each process refers to the amount of monitoring data for each process in the calculation of the factor The corresponding The total number of observations of the effective “maximum wall displacement value” and “settlement trough width feature” collected and used for analysis during the actual duration of a specific process, for example, in process S02 (here for example ) period, the maximum displacement of the wall and the width of the settlement trough are recorded every day for 7 days. (e.g. one representative observation per day);

[0105] The total number of processes refers to the number of all independent processes planned for the entire deep foundation pit excavation project. For example, if a project is divided into 10 main excavation and support processes, then In this example, the total number of project processes is set to ;

[0106] is the specific process number for which the comprehensive factor of wall settlement evolution is currently being calculated. For example, to calculate the factor of process S02, ;

[0107] Variable comprehensive factor . Known and estimated parameters: mm, Actual process S01( ): mm, rice, Actual process S02 (day ): mm, rice, day, the amount of monitoring data for this process Planned process S03( ): mm, rice, sky;

[0108] Substituting the parameters into the formula, the result is 3.823. This result shows that in the context of a total of three stages planned for the project, when evaluating the second stage (and taking into account the estimated deformation of the third stage), the comprehensive factor of wall settlement evolution is It is approximately 3.823. This value reflects the relative relationship between the cumulative change intensity of the entire project (partly based on estimates) and the amount of monitoring data for the second process, which is used for subsequent association rule establishment.

[0109] Based on the comprehensive factors of wall settlement evolution, each completed process Calculated comprehensive factor of wall settlement evolution value, the number of the process, and the maximum displacement of the wall actually observed at the end of the process and actual sedimentation tank width characteristics (These and The actual observation part of the generated "combined data of excavation process, maximum wall displacement value and settlement trough width characteristics" is organized together to form a list containing (process number, , , ) data set, and conduct correlation analysis on this data set in order to explore the potential regular combinations between these parameters that can characterize specific evolutionary behaviors. The analysis method may include first analyzing continuous data (such as , , , and their changes compared to the previous process and ) is divided into levels or discretized, for example, The values are divided into three levels: "low", "medium" and "high" according to their statistical distribution (such as quartiles). For example, if all historical The lower quartile of the value is 1.5 and the upper quartile is 4.0, then is low, For the middle, is high, similarly, the change in wall displacement It can be divided into "small increase" (such as 0-2 mm), "moderate increase" (such as 2-5 mm), and "large increase" (such as greater than 5 mm). These thresholds need to be set comprehensively based on engineering experience, design control standards, and the deformation characteristics of specific projects. For example, the threshold of "large increase" can refer to 30% to 50% of the design deformation warning value. After discretization, an association rule mining algorithm such as Apriori or FP-Growth is applied to find frequently occurring parameter level combinations (frequent item sets) in the data set, and generate association rules with high support and confidence from these frequent item sets. For example, the rule may be found: "If the excavation process type is 'deep earthwork excavation' and its corresponding If the level is 'high', the process The level is 'substantial growth' and The probability of the level being 'significant expansion' is 80%." These verified and screened rule combinations constitute the surface wall evolution association rules.

[0110] The steps to obtain the expected wall response mode are:

[0111] Based on the settlement trough width feature, the settlement trough width feature is matched with the historical width feature recorded in the surface wall evolution association rule. The settlement trough width range of each historical record is checked one by one to see if it covers the current settlement trough width feature. The historical records that meet the matching conditions are selected, and the corresponding historical excavation process number, settlement trough width range, and associated wall behavior description are extracted to generate a historical association record set.

[0112] Based on the historical association record set, the wall behavior descriptions in each historical association record are parsed one by one, and the associated wall displacement change trends, displacement change rates, and key deformation nodes in the descriptions are extracted. Records of similar wall displacement change trends, displacement change rates, and key deformation nodes are grouped together. The most frequently occurring wall behavior descriptions in each group are summarized to obtain the main wall behavior pattern groups.

[0113] Based on the main wall behavior pattern group, the main wall behavior pattern group corresponding to the current settlement trough width characteristics is matched and verified with the real-time monitoring data. By comparing the displacement change trend, displacement change rate and key deformation nodes for consistency, the behavior description that meets the current working conditions is screened and the expected wall response pattern is generated.

[0114] Specifically, based on the settlement trough width feature, which is a specific value calculated in the current monitoring period, such as 9.5 meters, the current settlement trough width feature is matched with each historical record stored in the "surface wall evolution association rule" library formed in the previous step. These historical records contain historical excavation process numbers, historical settlement trough width ranges, and historical wall behavior descriptions associated therewith. The core operation of the matching is to check whether the "settlement trough width range" in the historical records "covers" the current settlement trough width feature. Specifically, if the settlement trough width range defined in a historical record A is [8.0 meters, 10.0 meters], then the current 9.5 meters meets the requirements. , and is therefore considered as an overlay. This historical record A is the record that meets the matching condition. Conversely, if the width range in historical record B is [10.5 meters, 12.0 meters], the current 9.5 meters is not within this range, and record B does not meet the matching condition. The system will filter out all historical records that meet this overlay condition and extract the structured information contained in these records that meet the condition, mainly including the "historical excavation process number" when the record was formed (for example, process S03), the "settlement trough width range" corresponding to the historical record (for example, [8.0 meters, 10.0 meters]), and the most critical "associated wall behavior description" (for example, "the wall deforms uniformly at a rate of 0.3 mm / day in the middle, and the maximum displacement point is concentrated near the depth of -8 meters in the CX-02 section"). All of this extracted information is combined to form a temporary dataset containing multiple matching historical situations, namely the historical association record set.

[0115] Based on the historical association record set, a structured analysis is performed on the "wall behavior description" text contained in each historical record in the set. The analysis process aims to extract three key quantitative or classification indicators from it: wall displacement change trend, displacement change rate and key deformation nodes. The wall displacement change trend is classified into predefined trend types by analyzing keywords in the description, such as "acceleration", "uniform speed", "deceleration", "stabilization", "increase", "decrease", etc., for example, "accelerated increase" (such as the average rate of the current few days increases by more than 20% compared with the average rate of the previous period and the current rate is greater than 0.1 mm / day), "uniform increase" (such as the rate is between 0.1 and 0.5 mm / day and the rate change in the past three days does not exceed ±10%), "decelerated increase" (such as the rate is still increasing but the increase is less than 20% compared with the previous period), "stable" (such as the rate is within ±0.1 mm / day for more than 3 days) or "decrease". The displacement change rate is directly extracted from the text with specific values and units (for example, 0.3 mm / day) and can be classified as "slow speed" (such as 0 to 0 0.2 mm / day), “medium speed” (such as 0.2 to 0.5 mm / day), and “high speed” (such as greater than 0.5 mm / day). These rate classification thresholds are set based on engineering experience and warning levels. For example, “high speed” may correspond to the early warning level. The key deformation nodes are determined based on the location information in the description, such as “top of the wall”, “middle of the wall”, “specific profile number (CX-02)” or “specific depth (-8 meters)”, and are standardized, for example, uniformly classified as “upper”, “middle”, “lower” or specific profile / depth intervals, to complete the classification of all historical deformation nodes. After parsing and extracting features from the historical records, records with the same or similar (according to predetermined classification criteria) wall displacement change trends, displacement change rates of the same level, and similar key deformation node locations are grouped together. For example, all records with a trend of "uniform increase," a rate of "medium speed," and a node in the "middle of the wall" are grouped together. Within each formed group, the frequency of occurrence of each original "wall behavior description" text is counted, and the "wall behavior description" with the highest frequency of occurrence within the group is selected as the representative summary of the group to obtain the main wall behavior pattern groups.

[0116] Based on the main wall behavior pattern group, first, according to the current "settlement trough width characteristics", the matching "main wall behavior pattern group" is screened out, that is, the behavior pattern groups whose historical settlement trough width range covers the current width characteristics are selected. Then, these screened behavior pattern groups are matched and verified with the "real-time monitoring data" of the deep foundation pit wall obtained through the sensor network. This real-time monitoring data needs to undergo similar analysis and processing as the historical data to extract the current actual wall displacement change trend, the current actual displacement change rate and the current key deformation node position. For example, if the real-time data shows that the wall is displacing uniformly at a rate of 0.25 mm / day in the middle, the current trend is "uniform increase", the rate is "medium speed" (for example, 0.25 mm / day falls into the medium speed range), and the node is "middle". The verification process is to compare the trend, rate level and node type defined by each screened "main wall behavior pattern" with the Whether the three features analyzed from the current real-time data are "consistent" is determined by the following criteria: the current trend classification is exactly the same as the trend classification in the pattern, the current rate value belongs to the same rate level as the pattern (for example, the current 0.25 mm / day belongs to "medium speed", which is also defined in the pattern), and the current key deformation node position classification is the same as the node position classification in the pattern. Only when all three features match is the "main wall behavior pattern" considered consistent with the current working condition. From all the consistent behavior patterns, the corresponding original "wall behavior description" text is selected. If multiple behavior patterns are determined to be consistent, they can be sorted according to the total frequency of occurrence of these patterns in the historical data or the confidence of their association rules. The "wall behavior description" text corresponding to the behavior pattern with the highest ranking is selected as the most likely current wall response state to generate the expected wall response pattern.

[0117] The steps for obtaining the wall lateral deformation prediction results are as follows:

[0118] Based on the expected wall response pattern, the expected wall response pattern is matched with the deformation state of the current deep foundation pit wall, the displacement increment, acceleration and time change rate of the current deep foundation pit wall are extracted, and the parameter set required for the current deep foundation pit wall prediction is generated;

[0119] According to the parameter set required for the current deep foundation pit wall prediction, the predicted value of the deep foundation pit wall lateral deformation in the next time window is calculated. The calculation formula is:

[0120] ;

[0121] in, is the duration of the next time window, is the predicted value of the lateral deformation of the deep foundation pit wall in the next time window, For the The displacement increment of each monitoring point, For the The acceleration of each monitoring point, For the The time change rate of each monitoring point, is the reference speed, which is the average lateral speed in the last month. is the expected response complexity parameter of the current process, is the total number of monitoring points;

[0122] Based on the predicted value of the lateral deformation of the deep foundation pit wall in the next time window, the predicted value is compared with the historical deformation threshold, real-time monitoring data and expected wall response mode to obtain the wall lateral deformation prediction result.

[0123] Specifically, based on the expected wall response pattern, which is a textual description of the most likely behavior of the wall under the current working conditions determined in the previous step, for example, "accelerated displacement will occur in the middle of the wall at a rate of about 0.8 mm / day, mainly affecting the CX02 profile", a macro-conformity check is first performed on this expected wall response pattern and the overall deformation state of the current deep foundation pit wall obtained from the real-time monitoring system to confirm that the current actual deformation trend is generally consistent with the expected pattern description. If there is a significant deviation, such as acceleration is expected but deceleration is actually, it may be necessary to re-evaluate the applicability of the expected pattern or mark potential unknown influencing factors. After confirming basic compliance, for each key monitoring point that constitutes the current wall deformation state (for example, all measuring points in the active inclinometer tube), the dynamic parameters required for calculating the next stage of prediction are extracted from its latest "calibrated deformation sequence data". The specific extraction content includes: the dynamic parameters required for calculating the next stage of prediction for each monitoring point in the most recent observation period (for example, the past 24 hours, which is set according to the monitoring frequency and prediction requirements and recorded as ) within the displacement increment , by subtracting the current latest displacement value For example, if the current displacement of a measuring point is 20.5 mm and it was 19.5 mm 24 hours ago, then is 1.0 mm, followed by the current acceleration of each monitoring point , by analyzing the displacement data of the point in at least three consecutive observation periods, for example, if the displacement of a measuring point in the past three 6-hour intervals is 19.0 mm, 19.5 mm, and 20.5 mm, then its acceleration can be calculated based on this, and then the current time change rate of each monitoring point (i.e. instantaneous velocity), usually calculated from the displacement increment of the most recent observation period Divide by the length of the observation period Get, that is , for example, if mm and Heaven, then mm / day, these parameters at all monitoring points ( ) are collected to generate the parameter set required for the current deep foundation pit wall prediction.

[0124] formula: The benefit of the formula is that the prediction model integrates the real-time dynamic parameters (displacement increment, acceleration, velocity) of multiple monitoring points to predict the overall lateral deformation of the next time window, by combining the influence factors of each measuring point ( ) are accumulated and averaged to reflect the overall trend of wall deformation rather than a single most dangerous point. The use of absolute values ensures that the contribution of both acceleration and deceleration deformation is considered as the size of the positive influencing factor. The introduction of normalizes the product of the dynamic parameters of each measuring point, reduces the impact of the speed magnitude difference, and makes it more focused on the relative intensity of the dynamic behavior. The expected response complexity parameter It allows the sensitivity of the prediction to be adjusted according to the current process and the predicted deformation mode, so that the model has a certain engineering adaptability, and finally multiplied by the prediction time Converting rate or acceleration effects into displacement provides a quantitative prediction basis for engineering decisions;

[0125] The duration of the next time window refers to the length of time for which future deformation prediction is required. It is determined by the engineering management requirements and the monitoring feedback cycle. For example, daily prediction may be required during the rapid excavation stage. Set to 1 day, during the maintenance phase when the deformation tends to be stable, it may be adjusted to weekly forecast, then Set to 7 days. This parameter directly affects the size of the predicted displacement. For example, here it is set sky;

[0126] For the The displacement increment of each monitoring point is obtained from the generated "current deep foundation pit wall prediction required parameter set", which represents the displacement increment of the first monitoring point. Monitoring points in the most recent observation period The actual lateral displacement change that occurred within (e.g. 24 hours), for example, for monitoring point k=1, its displacement increment in the past 24 hours is 1.2 mm; for monitoring point k=2, 0.8 mm;

[0127] For the The acceleration of each monitoring point is also obtained from the "current deep foundation pit wall prediction parameter set". The instantaneous lateral acceleration calculated from the most recent series (at least three) of displacement readings at each monitoring point, for example, the acceleration at monitoring point k=1 0.15 mm / day²; acceleration at monitoring point k=2 -0.05 mm / day² (indicating deceleration);

[0128] For the The time change rate of each monitoring point, that is, its current lateral displacement speed, is obtained from the "current deep foundation pit wall prediction parameter set", which is usually the displacement increment of the most recent observation period. Divide by the length of the observation period Get, that is , for example, if is 1 day, then the time change rate of monitoring point k=1 ; The time change rate of monitoring point k=2 ;

[0129] The reference speed represents the average deformation rate of the foundation pit wall over a relatively long period of time. Specifically, the lateral displacement data of all relevant monitoring points in the "calibration deformation sequence data" for the past month (30 days) are retrieved, and the average daily displacement rate of each monitoring point in these 30 days is calculated. Then, these daily average rates of all monitoring points are averaged again. For example, after calculation, the average lateral speed in the past month is 1.0 mm / day;

[0130] The expected response complexity parameter of the current process is an adjustment coefficient set according to the current construction process type and the deformation complexity interpreted from the "expected wall response mode". Its value is obtained by referring to the predefined "process-mode-complexity parameter mapping table". The table is established based on historical engineering data and expert experience. For example, the "shallow excavation-uniform settlement mode" corresponds to is 0.9, and the corresponding is 1.3. For example, the current stage is "main structure construction" and the expected response mode is "wall deformation slows down, local fine-tuning". ;

[0131] The total number of monitoring points participating in this prediction calculation refers to the total number of wall lateral displacement monitoring points deployed in the current deep foundation pit project with valid data. For example, if there are 50 valid wall lateral displacement monitoring points participating in the calculation in the project, then ;

[0132] Calculation process: Setting sky, , mm / day, Monitoring point 1: mm, mm / day², mm / day. Monitoring point 2: mm, mm / day², mm / day.

[0133] Calculate the contribution of each monitoring point :For monitoring point 1( ):

[0134] ;

[0135] For monitoring point 2 ( ):

[0136] ;

[0137] Calculate the summation :

[0138] ;

[0139] Calculate the predicted value of the lateral deformation of the deep foundation pit wall in the next time window :

[0140] ;

[0141] The results show that based on the current monitoring data and the selected parameters, the deep foundation pit wall is expected to undergo a lateral deformation increment of approximately 0.1054 mm (on average) in the next day. This predicted value is a comprehensive average increment, which is used to evaluate the overall deformation trend of the wall in the next time window.

[0142] Based on the predicted value of the lateral deformation of the deep foundation pit wall in the next time window (for example, the calculated mm), add this predicted displacement increment to the current cumulative displacement value of the wall to obtain the estimated total cumulative displacement , and then use this estimated total cumulative displacement and by The calculated average deformation rate in the next time window is compared item by item with the preset "historical deformation threshold". These historical deformation thresholds contain multiple levels, setting the monitoring alarm value, orange warning value, and red warning value of displacement and rate. For example, if the monitoring alarm value is a cumulative displacement of 25 mm, the orange warning value is 30 mm, and the current is 24.9 mm, then mm, which means that the prediction result has triggered the monitoring alarm value. At the same time, the predicted deformation trend (for example, according to The sign and size of the wall are used to judge whether it is continuous deformation, accelerated deformation or slowed deformation) and the current actual deformation trend reflected by the "real-time monitoring data" are checked for consistency, and the deformation behavior described in the "expected wall response mode" obtained in the previous step is checked for consistency. For example, if the expected response mode is "deformation slowing down", but the predicted value is If there is still a significant increase, it is necessary to pay attention to this difference and integrate these comparison results, including whether the predicted value exceeds the limit, the degree of consistency between the predicted trend and the actual and expected patterns, to finally form a comprehensive assessment and description of the wall safety status in the next stage, that is, the wall lateral deformation prediction result.

Claims

1. A lateral deformation prediction system based on deep foundation pit walls, characterized in that: The system comprises: The deformation data acquisition module collects surface settlement monitoring values and lateral displacement monitoring values of corresponding measuring points on the deep foundation pit wall, performs time sequence alignment processing on the data points and eliminates abnormal monitoring values to establish calibrated deformation sequence data; a surface pattern recognition module that generates surface settlement contour lines through spatial interpolation based on the surface settlement monitoring values in the calibration deformation sequence data, obtains a surface settlement contour map, measures the width of the settlement trough formed in the key settlement area based on the surface settlement contour map, and establishes a settlement trough width feature; A wall response association module extracts the maximum lateral displacement value of each monitoring section at the same time section based on the wall lateral displacement monitoring values in the calibration deformation sequence data to obtain the maximum wall displacement value. Based on the maximum wall displacement value, the corresponding relationship between the evolution of the wall with the excavation process and the change of the settlement trough width characteristics is analyzed to establish the surface wall evolution association rules; The deformation trend prediction module, based on the width characteristics of the settlement trough, queries the wall behavior pattern corresponding to the width characteristics in the surface wall evolution association rules to obtain the expected wall response pattern. Based on the expected wall response pattern and combined with the deformation state of the current deep foundation pit wall, the lateral deformation value of the deep foundation pit wall in the next time window is predicted to obtain the wall lateral deformation prediction result.

2. The lateral deformation prediction system based on deep foundation pit wall according to claim 1 is characterized in that: The steps for obtaining the calibration deformation sequence data are as follows: Collect surface settlement monitoring values and lateral displacement monitoring values of corresponding measuring points on the deep foundation pit wall, match them one by one according to the collection time, mark and remove the unmatched monitoring values, and generate surface settlement monitoring values and lateral displacement monitoring values of corresponding measuring points on the deep foundation pit wall after time series alignment and outlier removal; Based on the surface settlement monitoring values and the lateral displacement monitoring values of the corresponding measuring points of the deep foundation pit wall after time series alignment and outlier removal, the surface settlement monitoring values and the lateral displacement monitoring values of the corresponding measuring points of the deep foundation pit wall are grouped according to the measuring point number. The data integrity within each group is checked to eliminate incomplete data groups, and data pairs are generated that are grouped according to the measuring point number and have guaranteed integrity. Based on the data pairs grouped by measuring point numbers and ensuring integrity, the surface settlement monitoring values of each data pair and the lateral displacement monitoring values of the corresponding measuring points of the deep foundation pit wall are sorted to form calibrated deformation sequence data.

3. The lateral deformation prediction system based on deep foundation pit wall according to claim 1 is characterized in that: The steps for obtaining the surface subsidence contour map are as follows: Based on the surface settlement monitoring values in the calibration deformation sequence data, the surface settlement monitoring values are distributed and sorted according to the spatial coordinates of the measuring points, and the surface settlement monitoring value differences between adjacent measuring points and the distances of each measuring point are calculated to generate settlement difference and distance data of adjacent measuring points; Calculating the interpolation factor of the surface settlement contour line based on the settlement difference of adjacent measuring points and the distance measurement data; Based on the surface settlement contour interpolation factor, the surface settlement monitoring values are gridded and distributed by spatial interpolation. During the gridding process, the interpolation density of each grid unit is adjusted according to the surface settlement contour interpolation factor to form a surface settlement contour map.

4. The lateral deformation prediction system based on deep foundation pit wall according to claim 1 is characterized in that: The steps for obtaining the width feature of the sedimentation tank are: Based on the surface settlement contour map, identifying the area with the densest settlement contour lines in the surface settlement contour map, and marking the outer edge coordinate points of the area to obtain the outer edge coordinate points of the key settlement area; Based on the outer edge coordinate points of the key settlement area, the horizontal distance between the outer edge coordinate points is measured, and representative distances are selected according to the principle of maximum horizontal spacing to obtain the maximum horizontal width of the key settlement area; Based on the maximum horizontal width of the key settlement area, the maximum horizontal width is used as a characteristic indicator of the settlement tank, and the width value is recorded as the settlement tank width feature to form the settlement tank width feature.

5. The lateral deformation prediction system based on deep foundation pit wall according to claim 1 is characterized in that: The steps for obtaining the maximum displacement value of the wall are: Based on the wall lateral displacement monitoring values in the calibration deformation sequence data, the wall lateral displacement monitoring values are grouped according to the monitoring section number, and all observation values of the same time section are extracted for the wall lateral displacement monitoring values in each group of monitoring sections. By comparing the timestamps, the valid observation values in the time section are selected to obtain the valid lateral displacement monitoring values of each monitoring section at the same time section; Based on the effective lateral displacement monitoring values of each monitoring section at the same time section, each group of data is traversed in turn and the sizes of the observation values in the group are compared. The lateral displacement monitoring value with the largest value in each group is selected, and the corresponding monitoring section number and observation time are recorded at the same time to obtain the maximum lateral displacement value set of each monitoring section; Based on the maximum lateral displacement value set of each monitoring section, the sizes of all the maximum lateral displacement values in the set are compared, and the highest group is selected as the representative value. At the same time, the monitoring section number and observation time of the representative value are marked to form the maximum displacement value of the wall.

6. The lateral deformation prediction system based on deep foundation pit wall according to claim 1 is characterized in that: The steps for obtaining the surface wall evolution association rules are as follows: Based on the maximum wall displacement value, the maximum wall displacement values are aggregated according to the time sequence of the excavation process, and a one-to-one correspondence is established between the settlement trough width characteristics corresponding to each process and the maximum wall displacement value, thereby obtaining combined data of the excavation process, the maximum wall displacement value, and the settlement trough width characteristics; Calculating a comprehensive factor of wall settlement evolution based on the combined data of the excavation process, the maximum displacement value of the wall, and the width characteristics of the settlement trough; Based on the comprehensive factor of wall settlement evolution, the comprehensive factor of wall settlement evolution is correlated with the excavation process number, the maximum displacement value of the wall, and the width characteristics of the settlement trough. The combination representing the relationship between wall deformation and settlement trough change is extracted to form the surface wall evolution association rules.

7. The lateral deformation prediction system based on deep foundation pit wall according to claim 1 is characterized in that: The steps for obtaining the expected wall response mode are: Based on the settlement trough width feature, the settlement trough width feature is matched with the historical width feature recorded in the surface wall evolution association rule. The settlement trough width range of each historical record is checked one by one to see whether it covers the current settlement trough width feature. The historical records that meet the matching conditions are selected, and the corresponding historical excavation process number, settlement trough width range and associated wall behavior description are extracted to generate a historical association record set. Based on the set of historical association records, the wall behavior descriptions in each historical association record are parsed one by one, and the wall displacement change trends, displacement change rates, and key deformation nodes associated with the descriptions are extracted. Records of similar wall displacement change trends, displacement change rates, and key deformation nodes are grouped together, and the most frequently occurring wall behavior descriptions in each group are summarized to obtain the main wall behavior pattern groups. Based on the main wall behavior pattern group, the main wall behavior pattern group corresponding to the current settlement trough width characteristics is matched and verified with the real-time monitoring data. By comparing the displacement change trend, displacement change rate and key deformation nodes for consistency, the behavior description that meets the current working conditions is screened and the expected wall response pattern is generated.

8. The lateral deformation prediction system based on deep foundation pit wall according to claim 1 is characterized in that: The steps for obtaining the wall lateral deformation prediction result are: Based on the expected wall response pattern, the expected wall response pattern is matched with the deformation state of the current deep foundation pit wall, the displacement increment, acceleration and time change rate of the current deep foundation pit wall are extracted, and a parameter set required for the current deep foundation pit wall prediction is generated; Calculating a predicted value of the lateral deformation of the deep foundation pit wall within a next time window according to the set of parameters required for the current deep foundation pit wall prediction; Based on the predicted value of the lateral deformation of the deep foundation pit wall in the next time window, the predicted value is compared with the historical deformation threshold, the real-time monitoring data and the expected wall response mode item by item to obtain the wall lateral deformation prediction result.

9. The method for predicting lateral deformation of a deep foundation pit wall according to any one of claims 1 to 8, wherein: The following steps are involved: Collect surface settlement monitoring values and lateral displacement monitoring values of corresponding measuring points on the deep foundation pit wall, perform time series alignment processing on the data points and eliminate abnormal monitoring values to establish calibrated deformation sequence data; Based on the surface settlement monitoring values in the calibration deformation sequence data, surface settlement contour lines are generated by spatial interpolation to obtain a surface settlement contour map; based on the surface settlement contour map, the width of the settlement trough formed in the key settlement area is measured to establish the settlement trough width feature; Based on the wall lateral displacement monitoring values in the calibration deformation sequence data, the maximum lateral displacement value of each monitoring section at the same time section is extracted to obtain the maximum wall displacement value. Based on the maximum wall displacement value, the corresponding relationship between the evolution with the excavation process and the change of the settlement trough width characteristics is analyzed to establish the surface wall evolution association rules; Based on the width characteristics of the settlement trough, the wall behavior pattern corresponding to the width characteristics is queried in the surface wall evolution association rules to obtain an expected wall response pattern. Based on the expected wall response pattern and combined with the current deformation state of the deep foundation pit wall, the lateral deformation value of the deep foundation pit wall in the next time window is predicted to obtain the wall lateral deformation prediction result.

Images