Online monitoring system for vacuum preloading treatment of soft soil foundation area

Abstract

The invention relates to the technical field of data abnormal value identification, and provides an on-line monitoring system for vacuum preloading treatment of a soft soil foundation area, which comprises the following steps: acquiring void water pressure, horizontal displacement and displacement direction; determining a horizontal displacement initial abnormal value of the horizontal displacement; determining an initial displacement direction abnormal value and a horizontal displacement first abnormal value at the acquisition moment; and determining the data correlation degree of the sampling points and a third initial abnormal value of the pore water pressure at the acquisition moment, determining a corrected abnormal value of the horizontal displacement of the sampling points acquired at the acquisition moment in combination with the first abnormal value of the horizontal displacement, and obtaining a horizontal displacement monitoring result of vacuum preloading treatment of the soft soil foundation area according to the corrected abnormal value. According to the invention, the accuracy of lateral deformation abnormity monitoring can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data outlier identification, and particularly relates to an online monitoring system for soft soil foundation area vacuum preloading treatment. BACKGROUND

[0002] The soft soil foundation area vacuum preloading treatment is a soft soil foundation reinforcement method, which can make free water and part of combined water and air in the soil pores continuously discharge from the drainage channel under the action of pressure difference, so that the soil particles recombine, the void ratio decreases, and the foundation consolidates and the strength increases. During the soft soil foundation area vacuum preloading treatment, the foundation soil of soft soil is prone to lateral deformation, which may induce serious engineering accidents such as landslides and foundation instability.

[0003] The horizontal displacement can be abnormally detected during the soft soil foundation area vacuum preloading treatment process to avoid safety accidents caused by lateral deformation, but the existing LOF abnormal detection algorithm does not consider the time dependence and trend change of the horizontal displacement during the abnormal detection of the lateral deformation, which often leads to inaccurate lateral deformation monitoring. SUMMARY

[0004] The present application provides an online monitoring system for soft soil foundation area vacuum preloading treatment to solve the problem that the time dependence and trend change of the time series data of the horizontal displacement are not considered during the abnormal monitoring of the lateral deformation, resulting in inaccurate monitoring results. The technical solution adopted is as follows: An embodiment of the present application provides an online monitoring system for soft soil foundation area vacuum preloading treatment, which comprises the following modules: A data acquisition module is configured to acquire the void water pressure, horizontal displacement and displacement direction of each sampling point at different collection times and different depths. A horizontal displacement initial abnormal value determination module is configured to take any collection time as a target collection time, and determine the horizontal displacement initial abnormal value of the horizontal displacement according to the difference of the horizontal displacement of all sampling points at the same depth at the collection time, and the change trend and difference of the horizontal displacement of adjacent collection times. A horizontal displacement first abnormal value determination module is configured to determine the initial displacement direction abnormal value of the target collection time according to the difference of the displacement direction of the sampling point at the same depth at adjacent collection times, and the difference between the displacement directions of the sampling point at different depths, determine the first abnormal value of the horizontal displacement at the collection time according to the abnormal detection result of the fluctuation degree of the difference value of the displacement direction of different sampling points at adjacent collection times, and the initial displacement direction abnormal value and the horizontal displacement initial abnormal value. The monitoring result determining module is configured to determine a data correlation degree of each sampling point, a third initial abnormal value of the pore water pressure at each collection time, and a corrected abnormal value of the horizontal displacement collected at each collection time at each sampling point by combining the horizontal displacement first abnormal value, and obtain a result of the horizontal displacement monitoring of the soft soil foundation area vacuum preloading treatment according to the corrected abnormal value.

[0005] Further, the method for determining the horizontal displacement initial abnormal value of the horizontal displacement is as follows: performing abnormality detection on the horizontal displacement of all sampling points at the same depth at the same collection time, obtaining the LOF value of the horizontal displacement of each sampling point at each depth, and denoting the LOF value as the horizontal displacement first initial abnormal value; determining the initial deviation value and the predicted deviation value of the horizontal displacement according to the change trend and the difference of the horizontal displacement at the target collection time and at each adjacent collection time before the target collection time; and denoting the normalized value of the difference between the initial deviation value and the predicted deviation value of the horizontal displacement at the target collection time as the second initial abnormal value of the horizontal displacement at the target collection time; denoting the average value of the first initial abnormal value and the second initial abnormal value of the horizontal displacement at the target collection time as the horizontal displacement initial abnormal value of the horizontal displacement at the target collection time.

[0006] Further, the method for determining the initial deviation value and the predicted deviation value is as follows: establishing a first historical horizontal displacement sequence of the sampling point at the target collection time according to the horizontal displacement of the sampling point at the same depth at the first preset number of adjacent collection times before the target collection time; denoting the average value of all horizontal displacements contained in the first historical horizontal displacement sequence of the sampling point at the target collection time as a first horizontal average displacement of the sampling point at the target collection time; denoting a sequence formed by the difference between all horizontal displacements in the first historical horizontal displacement sequence of the sampling point at the target collection time and the first horizontal average displacement as a first average deviation difference value sequence of the sampling point at the target collection time; obtaining the LOF value corresponding to each difference value in the first average deviation difference value sequence, and denoting the LOF value corresponding to the difference value as the initial deviation value of the horizontal displacement corresponding to the difference value; According to the first historical horizontal displacement sequence of the target acquisition time, a predicted value of the horizontal displacement of the target acquisition time is obtained, and a second historical horizontal displacement sequence of the sampling point at the target acquisition time is established according to the horizontal displacement of the same depth at the adjacent first preset number of acquisition times before the target acquisition time and the predicted value of the horizontal displacement of the target acquisition time; the average value of all horizontal displacements contained in the second historical horizontal displacement sequence of the sampling point at the target acquisition time is recorded as the second horizontal average displacement of the sampling point at the target acquisition time; the sequence formed by the difference between all horizontal displacements in the second historical horizontal displacement sequence of the sampling point at the target acquisition time and the second horizontal average displacement is recorded as the second average deviation value sequence of the sampling point at the target acquisition time; the LOF value corresponding to each difference value in the second average deviation value sequence is obtained and recorded as the predicted deviation value of the horizontal displacement corresponding to the difference value.

[0007] Further, the method for determining the initial displacement direction abnormal value of the target acquisition time is: The displacement direction of the same sampling point at the same depth and at the adjacent first preset number of acquisition times before the target acquisition time is detected for abnormality, the LOF value of each displacement direction is obtained, and recorded as the displacement direction first abnormal value of the displacement direction; The displacement direction of all different depths of the same sampling point collected at the same acquisition time is detected for abnormality, the LOF value of each displacement direction is obtained, and recorded as the displacement direction second abnormal value of the displacement direction; The average of the displacement direction first abnormal value and the displacement direction second abnormal value of the displacement direction of the target acquisition time is recorded as the initial displacement direction abnormal value of the target acquisition time.

[0008] Further, the specific determination method of the horizontal displacement first abnormal value of the acquisition time is: The normalized value of the variance of the difference value of the displacement direction of the two different sampling points at the target acquisition time and the adjacent first preset number of acquisition times before the target acquisition time and at the same depth is recorded as the displacement direction difference degree of the two different sampling points at the target acquisition time and at the same depth; according to the displacement direction difference degree, the corresponding sample points to be analyzed are screened; According to the results of abnormality detection of the difference value of the displacement direction of all corresponding sample points to be analyzed at the target acquisition time and at each adjacent acquisition time before the target acquisition time, and the initial displacement direction abnormal value of the target acquisition time, the third abnormal value of the displacement direction of the target acquisition time is determined; The average of the horizontal displacement initial abnormal value of the horizontal displacement collected at the target acquisition time and the third abnormal value of the displacement direction of the target acquisition time is recorded as the horizontal displacement first abnormal value of the horizontal displacement collected at the target acquisition time.

[0009] Further, the determination method of the third abnormal value of the displacement direction is: performing abnormality detection on the difference value of the displacement direction of two corresponding to-be-analyzed sampling points at the target acquisition time and the first preset number of acquisition times adjacent to the target acquisition time, and obtaining an abnormal value of the difference value of the displacement direction; taking the average value of the abnormal values of the difference values of the displacement direction of all to-be-analyzed sampling points as the first horizontal direction abnormal value of the target acquisition time; and taking the average value of the initial displacement direction abnormal value of the target acquisition time and the first horizontal direction abnormal value as the third abnormal value of the displacement direction of the target acquisition time.

[0010] Further, the determination method of the data correlation degree is: establishing a same-depth void water pressure sequence at the same depth of the same acquisition time according to the void water pressure at the same depth of all sampling points at the same acquisition time; establishing a same-depth horizontal displacement sequence at the same depth of the same acquisition time according to the horizontal displacement at the same depth of all sampling points at the same acquisition time; taking the absolute value of the Pearson correlation coefficient of the same-depth horizontal displacement sequence and the same-depth void water pressure sequence at the same acquisition time and at the same depth as the data correlation degree of the same sampling point at the same acquisition time and at the same depth.

[0011] Further, the acquisition method of the third initial abnormal value is: determining the initial deviation value and the predicted deviation value of the pore water pressure of the target acquisition time according to the change trend and difference of the pore water pressure of the target acquisition time and each adjacent acquisition time before the target acquisition time; taking the normalized value of the difference value of the initial deviation value and the predicted deviation value of the pore water pressure of the target acquisition time as the third initial abnormal value of the pore water pressure of the target acquisition time.

[0012] Further, the calculation formula of the corrected abnormal value of the horizontal displacement is: wherein, represents the corrected abnormal value of the horizontal displacement of the sampling point collected at the target acquisition time; represents the data correlation degree of the depth of the horizontal displacement of the sampling point collected at the target acquisition time; represents the first abnormal value of the horizontal displacement of the horizontal displacement of the sampling point collected at the target acquisition time; represents the third initial abnormal value of the pore water pressure collected at the depth of the horizontal displacement of the sampling point collected at the target acquisition time.

[0013] Further, the result of the horizontal displacement monitoring of the soft soil foundation area vacuum preloading treatment according to the modified abnormal value comprises the following specific steps: When the modified abnormal value is greater than the second preset threshold value, it is determined that the sampling point corresponding to the modified abnormal value has abnormal horizontal displacement at the corresponding collection time.

[0014] The beneficial effects of the present application are: First, considering that the horizontal displacement of different sampling points at different depths may differ in the process of soft soil foundation area vacuum preloading treatment, but the values of the horizontal displacement of different sampling points at different depths are similar, the horizontal displacement initial abnormal value of the horizontal displacement is determined according to the difference of the horizontal displacement of all sampling points at the same depth at the collection time, and the change trend and difference of the horizontal displacement of each adjacent collection time before the target collection time, the greater the horizontal displacement initial abnormal value, the more obvious the characteristics of the horizontal displacement deviating from the change trend of the horizontal displacement, and the greater the possibility of abnormal value of the horizontal displacement; since the greater the difference between the displacement directions of the same sampling point at different depths and different collection times, the greater the possibility of abnormal displacement direction, the initial displacement direction abnormal value of the target collection time is determined according to the difference of the displacement direction of the same depth of the sampling point at the target collection time and each adjacent collection time before the target collection time, and the difference between the displacement directions of different sampling points, further, combined with the physical characteristics analysis of the central region in the vacuum state in the process of soft soil foundation area vacuum preloading treatment, the displacement direction of each sampling point tends to the center of the soft soil foundation area, and the difference between the displacement directions of different sampling points should fluctuate within a small range, the horizontal displacement first abnormal value of the horizontal displacement is determined, and when the horizontal displacement first abnormal value of the horizontal displacement is greater, the possibility of abnormal horizontal displacement and displacement direction collected at the target collection time is greater; finally, combined with the characteristics that when the horizontal displacement and displacement direction are abnormal, the void water pressure at the collection time corresponding to the horizontal displacement and displacement direction will also be abnormal, the modified abnormal value of the horizontal displacement collected by each sampling point at each collection time is determined, and the result of the horizontal displacement monitoring of the soft soil foundation area vacuum preloading treatment according to the modified abnormal value is obtained, solving the problem that the time dependence and trend change of the time series data of the horizontal displacement are not considered in the process of monitoring the lateral deformation abnormality, resulting in inaccurate monitoring results. BRIEF DESCRIPTION OF DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and those skilled in the art can also obtain other drawings according to these drawings without creative labor.

[0016] Figure 1 This is a schematic diagram of the structure of an online monitoring system for vacuum preloading treatment in soft soil foundation areas, provided in one embodiment of the present invention. Figure 2 This is a schematic diagram of an online monitoring system for vacuum preloading treatment in soft soil foundation areas, provided as an embodiment of the present invention. Detailed Implementation

[0017] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] Please see Figure 1 The diagram illustrates a schematic of an online monitoring system for vacuum preloading treatment in soft soil subgrade areas, provided by an embodiment of the present invention. The system includes: a data acquisition module, a module for determining initial anomalies in horizontal displacement, a module for determining first anomalies in horizontal displacement, and a module for determining monitoring results. Figure 2 A schematic flowchart of an online monitoring system for vacuum preloading treatment in soft soil foundation areas, provided by an embodiment of the present invention, is shown.

[0019] The data acquisition module collects the pore water pressure, horizontal displacement, and displacement direction at each sampling point at different times and depths.

[0020] Multiple sampling points were set at equal intervals at the edge of the vacuum preloading treatment in the soft soil foundation area. At each sampling point, an inclinometer and a pore water pressure gauge were set up. The inclinometer was used to collect the horizontal displacement and displacement direction, and the pore water pressure was collected by the pore water pressure gauge.

[0021] This embodiment sets up 10 sampling points. Each inclinometer collects horizontal displacement and displacement direction at 5 different depths at each sampling time, and the pore water pressure gauge collects pore water pressure at 5 different depths at each sampling time. Horizontal displacement, displacement direction, and pore water pressure are collected every 1 hour. In practical applications, as other implementation methods, implementers can decide the number of inclinometers, the sampling frequency of horizontal displacement, displacement direction, and pore water pressure, and the number of different depths collected according to the actual situation. This application does not impose any special restrictions.

[0022] Here, it can be understood that horizontal displacement is the distance moved along the direction of displacement.

[0023] Up to now, the void water pressure, the horizontal displacement and the displacement direction at different collection time and different depth are obtained.

[0024] The horizontal displacement initial abnormal value determination module, any one collection time is recorded as a target collection time, according to the difference of the horizontal displacement of all sampling points at the same depth of the collection time, and the change trend and difference of the horizontal displacement of the target collection time and each adjacent collection time before the target collection time, the horizontal displacement initial abnormal value of the horizontal displacement is determined.

[0025] In the process of soft soil foundation area vacuum preloading treatment, the horizontal displacement of different sampling points at different depths may be different, but the values of the horizontal displacement of different sampling points at different depths are similar.

[0026] According to the difference of the horizontal displacement of all sampling points at the same depth of the collection time, the first initial abnormal value of the horizontal displacement is determined.

[0027] Arranging the horizontal displacement of all sampling points at the same depth of the same collection time according to the order set by the sampling point, obtaining the same depth horizontal displacement sequence of the same depth of the same collection time, using LOF anomaly detection algorithm for anomaly detection on the same depth horizontal displacement sequence, obtaining the LOF value of the horizontal displacement of each sampling point at each depth, and recording it as the first initial abnormal value of the horizontal displacement.

[0028] Wherein, using LOF anomaly detection algorithm to obtain the LOF value of the data is a known technology, which will not be repeated.

[0029] Since the horizontal displacement is time series data that changes with the progress of vacuum preloading, it is necessary to evaluate whether the horizontal displacement is abnormal according to the time series change characteristics of the horizontal displacement.

[0030] Any one collection time is recorded as a target collection time, according to the change trend and difference of the horizontal displacement of the target collection time and each adjacent collection time before the target collection time, the initial deviation value and the predicted deviation value of the horizontal displacement are determined respectively.

[0031] The first history horizontal displacement sequence of the sampling point at the target acquisition time is obtained by arranging the horizontal displacements of the same depth of the first preset number of acquisition times adjacent to the target acquisition time in the order of the acquisition times; the first horizontal average displacement of the sampling point at the target acquisition time is recorded as the average value of all the horizontal displacements contained in the first history horizontal displacement sequence of the sampling point at the target acquisition time; the first average deviation value sequence of the sampling point at the target acquisition time is recorded as the sequence formed by the difference values of all the horizontal displacements in the first history horizontal displacement sequence of the sampling point at the target acquisition time minus the first horizontal average displacement; the LOF value corresponding to each difference value in the first average deviation value sequence is obtained by using the LOF anomaly detection algorithm to perform anomaly detection on the first average deviation value sequence, and the LOF value corresponding to the difference value is recorded as the initial deviation value of the horizontal displacement corresponding to the difference value.

[0032] In the embodiment, the value of the first preset number is set to 20; the prediction value of the data obtained according to the historical data is a known technology, and will not be described herein again; in the embodiment, an autoregressive moving average model is selected to obtain the prediction value of the horizontal displacement at the target acquisition time according to the first history horizontal displacement sequence at the target acquisition time.

[0033] The prediction value of the horizontal displacement at the target acquisition time is obtained according to the first history horizontal displacement sequence at the target acquisition time; the second history horizontal displacement sequence of the sampling point at the target acquisition time is obtained by arranging the horizontal displacements of the same depth of the first preset number of acquisition times adjacent to the target acquisition time and the prediction value of the horizontal displacement at the target acquisition time in the order of the acquisition times; the second horizontal average displacement of the sampling point at the target acquisition time is recorded as the average value of all the horizontal displacements contained in the second history horizontal displacement sequence of the sampling point at the target acquisition time; the second average deviation value sequence of the sampling point at the target acquisition time is recorded as the sequence formed by the difference values of all the horizontal displacements in the second history horizontal displacement sequence of the sampling point at the target acquisition time minus the second horizontal average displacement; the LOF value corresponding to each difference value in the second average deviation value sequence is obtained by using the LOF anomaly detection algorithm to perform anomaly detection on the second average deviation value sequence, and the LOF value corresponding to the difference value is recorded as the prediction deviation value of the horizontal displacement corresponding to the difference value.

[0034] The horizontal displacement initial abnormal value of the horizontal displacement is determined according to the first initial abnormal value, the initial deviation value and the prediction deviation value of the horizontal displacement.

[0035] The second initial abnormal value of the horizontal displacement at the target acquisition time is recorded as the normalized value of the difference value between the initial deviation value and the prediction deviation value of the horizontal displacement at the target acquisition time; the horizontal displacement initial abnormal value of the horizontal displacement at the target acquisition time is recorded as the average value of the first initial abnormal value and the second initial abnormal value of the horizontal displacement at the target acquisition time.

[0036] It should be noted that the embodiment uses the Z-Score standard normalization method to calculate the normalized value, and in actual application, the implementer can use other methods such as the maximum and minimum value normalization method, sigmoid function, and other prior art methods to calculate the normalized value, which is not limited herein.

[0037] The greater the difference between the initial deviation value of the horizontal displacement and the predicted deviation value, the more significant the feature of the horizontal displacement deviating from the change trend of the horizontal displacement, and the greater the possibility of abnormality of the value of the horizontal displacement. At this time, the initial abnormal value of the horizontal displacement is greater.

[0038] It can be understood that the horizontal displacement collected at the target collection time can determine the depth corresponding to the horizontal displacement, that is, for each sampling point, each depth at each collection time can determine a corresponding initial abnormal value of the horizontal displacement.

[0039] At this point, the initial abnormal value of the horizontal displacement of each horizontal displacement is obtained.

[0040] The horizontal displacement first abnormal value determination module determines the initial displacement direction abnormal value of the target collection time according to the difference between the displacement directions of the same depth at the target collection time and each adjacent collection time before the target collection time, and the difference between the displacement directions at different depths of the sampling point, determines the horizontal displacement first abnormal value of the collection time according to the abnormality detection result of the fluctuation degree of the difference value of the displacement directions of the adjacent collection times of different sampling points, and the initial displacement direction abnormal value and the initial abnormal value of the horizontal displacement.

[0041] The displacement directions of the same sampling point at different depths and different collection times should be relatively close, and the greater the difference between the displacement directions of the same sampling point at different depths and different collection times, the greater the possibility of abnormality of the displacement direction.

[0042] According to the difference between the displacement directions of the same depth at the target collection time and each adjacent collection time before the target collection time, and the difference between the displacement directions of all different depths collected by the same sampling point at the same collection time, the initial displacement direction abnormal value of the target collection time is determined.

[0043] The displacement direction of the same sampling point at the same depth and at the first preset number of adjacent collection time points before the target collection time is collected, and the LOF anomaly detection algorithm is used for anomaly detection, the LOF value of each displacement direction is obtained, and the displacement direction of the displacement direction is recorded as the first abnormal value of the displacement direction. The displacement direction of the same sampling point at the same collection time is collected at all different depths, and the LOF anomaly detection algorithm is used for anomaly detection, the LOF value of each displacement direction is obtained, and the displacement direction of the displacement direction is recorded as the second abnormal value of the displacement direction. The average of the first abnormal value of the displacement direction of the target collection time and the second abnormal value of the displacement direction is recorded as the initial displacement direction abnormal value of the target collection time.

[0044] When the initial displacement direction abnormal value is larger, the possibility of abnormality of the displacement direction of the collection time corresponding to the initial displacement direction abnormal value is larger.

[0045] In the process of soft soil foundation area vacuum preloading treatment, the central area is in vacuum state, and the edge of the soft soil foundation area will be extruded by the central area, resulting in horizontal displacement, so the displacement direction of each sampling point is towards the center of the soft soil foundation area, and the difference between the displacement directions of different sampling points should fluctuate within a small range.

[0046] According to the fluctuation degree of the difference value of the displacement direction of the target collection time and each adjacent collection time before the target collection time of different sampling points, the corresponding to-be-analyzed sampling point is screened.

[0047] The normalized value of the variance of the difference value of the displacement direction of the same depth of two different sampling points at the target collection time and the first preset number of adjacent collection time points before the target collection time is recorded as the displacement direction difference degree of the two different sampling points at the target collection time and the same depth.

[0048] The smaller the displacement direction difference degree is, the more stable the difference between the displacement directions of different sampling points at different collection time and the same depth is.

[0049] The different sampling points with the displacement direction difference degree greater than the first preset threshold value are recorded as the corresponding to-be-analyzed sampling points. The value of the first preset threshold value in this embodiment is 0.8.

[0050] According to the results of anomaly detection of the difference value of the displacement direction of all corresponding to-be-analyzed sampling points at the target collection time and each adjacent collection time before the target collection time, and the initial displacement direction abnormal value of the target collection time, the third abnormal value of the displacement direction of the target collection time is determined.

[0051] The difference value of the displacement direction at the same depth of two corresponding to-be-analyzed sampling points at the target acquisition moment and the first preset number of acquisition moments adjacent to the target acquisition moment is detected by using the LOF anomaly detection algorithm to obtain the abnormal value of the displacement direction difference value. The average value of all abnormal values of the displacement direction difference value corresponding to all to-be-analyzed sampling points is recorded as the first horizontal direction abnormal value of the target acquisition moment. The average value of the initial displacement direction abnormal value of the target acquisition moment and the first horizontal direction abnormal value is recorded as the third displacement direction abnormal value of the target acquisition moment.

[0052] The average value of the horizontal displacement initial abnormal value of the horizontal displacement collected at the target acquisition moment and the third displacement direction abnormal value of the target acquisition moment is recorded as the first abnormal value of the horizontal displacement of the horizontal displacement collected at the target acquisition moment.

[0053] The greater the first abnormal value of the horizontal displacement of the horizontal displacement, the greater the possibility of abnormality of the horizontal displacement and the displacement direction collected at the target acquisition moment.

[0054] It can be understood that the horizontal displacement collected at the target acquisition moment can determine the depth corresponding to the horizontal displacement, that is, for each sampling point, a corresponding first abnormal value of the horizontal displacement can be determined at each acquisition moment and each depth.

[0055] According to the same method, the first abnormal value of the horizontal displacement of each sampling point at each acquisition moment and each depth can be obtained.

[0056] At this point, the first abnormal value of the horizontal displacement of each sampling point at each acquisition moment and each depth is obtained.

[0057] The monitoring result determination module determines the data correlation degree of each sampling point, the third initial abnormal value of the pore water pressure of each acquisition moment, and the corrected abnormal value of the horizontal displacement of each sampling point collected at each acquisition moment according to the similarity of the change trend of the pore water pressure and the horizontal displacement collected at the same acquisition moment and the same depth, and the change trend and difference of the pore water pressure of adjacent acquisition moments, and determines the result of the horizontal displacement monitoring of the soft soil foundation area vacuum preloading treatment according to the corrected abnormal value.

[0058] When the horizontal displacement and the displacement direction are abnormal, the pore water pressure corresponding to the collection time of the horizontal displacement and the displacement direction will also be abnormal. Specifically, during vacuum preloading reinforcement, the vacuum load directly acts on the water vapor fluid of the soil, directly generating negative pore water pressure, resulting in a decrease in pore water pressure. According to the principle of effective stress, the total stress is constant, and the increase in effective stress is the decrease in pore water pressure. The negative pore pressure generated by vacuum preloading causes isotropic stress, resulting in the contraction of the horizontal displacement to the center, and the horizontal displacement changes with the change of the pore water pressure. At the same time, the greater the change rate of the pore water pressure, the greater the horizontal displacement; the smaller the change rate of the pore water pressure, the smaller the horizontal displacement. Whether the horizontal displacement is abnormal can be analyzed according to the change of the pore water pressure.

[0059] According to the similarity degree of the change trend of the pore water pressure and the horizontal displacement collected at the same collection time and the same depth of the same sampling point, the data correlation degree of each sampling point at each collection time and each depth is determined.

[0060] The pore water pressures of all sampling points at the same depth at the same collection time are arranged in the order set by the sampling points, and the same-depth pore water pressure sequence at the same depth at the same collection time is obtained. The absolute value of the Pearson correlation coefficient of the same-depth horizontal displacement sequence and the same-depth pore water pressure sequence at the same collection time and at the same depth is recorded as the data correlation degree of the same sampling point at the same collection time and at the same depth.

[0061] According to the change trend and difference of the pore water pressure of the target collection time and each adjacent collection time before the target collection time, a third initial abnormal value of the pore water pressure of the target collection time is determined.

[0062] The pore water pressures of the same depth of the sampling point at the first preset number of adjacent collection times before the target collection time are arranged in the order of the collection time, and the first historical pore water pressure sequence of the sampling point at the target collection time is obtained. The average value of all pore water pressures contained in the first historical pore water pressure sequence of the sampling point at the target collection time is recorded as the first pore water average pressure of the sampling point at the target collection time. The sequence composed of the difference between all pore water pressures in the first historical pore water pressure sequence of the sampling point at the target collection time and the first pore water average pressure is recorded as the third average deviation value sequence of the sampling point at the target collection time. The LOF anomaly detection algorithm is used for anomaly detection on the third average deviation value sequence, the LOF value corresponding to each difference value in the third average deviation value sequence is obtained, and is recorded as the initial deviation value of the pore water pressure corresponding to the difference value.

[0063] According to the first historical pore water pressure sequence of the target acquisition time, the predicted value of the pore water pressure of the target acquisition time is obtained, the pore water pressure of the same depth of the sampling point at the target acquisition time and the predicted value of the pore water pressure of the target acquisition time are arranged in the order of acquisition time according to the first preset number of adjacent acquisition times before the target acquisition time, and the second historical pore water pressure sequence of the sampling point at the target acquisition time is obtained; The average value of all pore water pressures contained in the second historical pore water pressure sequence of the sampling point at the target acquisition time is recorded as the second pore water average pressure of the sampling point at the target acquisition time; The sequence composed of the difference between all pore water pressures in the second historical pore water pressure sequence of the sampling point at the target acquisition time and the second pore water average pressure is recorded as the fourth average deviation value sequence of the sampling point at the target acquisition time; The LOF anomaly detection algorithm is used for anomaly detection on the fourth average deviation value sequence, the LOF value corresponding to each difference value in the fourth average deviation value sequence is obtained, and is recorded as the predicted deviation value of the pore water pressure corresponding to the difference value.

[0064] The normalized value of the difference between the initial deviation value and the predicted deviation value of the pore water pressure of the target acquisition time is recorded as the third initial anomaly value of the pore water pressure of the target acquisition time.

[0065] It should be noted that the maximum and minimum value normalization method is used to calculate the normalized value of the difference between the initial deviation value and the predicted deviation value in this embodiment, so as to ensure that the third initial anomaly value is greater than or equal to 0 and less than or equal to 1.

[0066] When the third initial anomaly value of the pore water pressure of the target acquisition time is greater, the possibility of the abnormality of the pore water pressure of the target acquisition time is greater, and the possibility of the abnormality of the horizontal displacement and the displacement direction collected at this time is also greater.

[0067] According to the data correlation, the horizontal displacement first anomaly value and the third initial anomaly value, the corrected anomaly value of the horizontal displacement collected by each sampling point at each acquisition time is determined.

[0068] Among them, The corrected anomaly value of the horizontal displacement collected by the sampling point at the target acquisition time is represented; The data correlation of the depth of the horizontal displacement collected by the sampling point at the target acquisition time is represented; The horizontal displacement first anomaly value of the horizontal displacement collected by the sampling point at the target acquisition time is represented; The third initial anomaly value of the pore water pressure collected at the depth of the horizontal displacement collected by the sampling point at the target acquisition time is represented.

[0069] When the correction abnormal value is greater than the second preset threshold, it is determined that the horizontal displacement of the sampling point corresponding to the correction abnormal value at the corresponding acquisition time is abnormal.

[0070] In the embodiment, the second preset threshold is 1.

[0071] Thus, the horizontal displacement monitoring of the soft soil foundation area vacuum preloading treatment is realized.

[0072] The above only describes the preferred embodiments of the present application and is not intended to limit the present application. Any modification, equivalent replacement, improvement, etc. within the principles of the present application shall be included in the protection scope of the present application.

Claims

1. An online monitoring system for vacuum preloading treatment in soft soil foundation areas, characterized in that, The system includes the following modules: The data acquisition module is used to collect the pore water pressure, horizontal displacement, and displacement direction at different sampling times and depths for each sampling point; The horizontal displacement initial anomaly determination module is used to record any acquisition time as the target acquisition time, and determine the initial anomaly value of the horizontal displacement based on the difference in horizontal displacement at the same depth of all sampling points at the acquisition time, as well as the trend and difference in the horizontal displacement of adjacent acquisition times. The first anomaly determination module for horizontal displacement is used to determine the initial displacement direction anomaly at the target acquisition time based on the difference in displacement direction of the sampling point at the same depth in adjacent acquisition times, and the difference in displacement direction between sampling points at different depths. Based on the anomaly detection results of the fluctuation degree of the difference in displacement direction of different sampling points in adjacent acquisition times, as well as the initial displacement direction anomaly and the initial horizontal displacement anomaly, the first anomaly of horizontal displacement at the acquisition time is determined. The monitoring result determination module is used to determine the data correlation of each sampling point and the third initial anomaly value of pore water pressure at each sampling time based on the similarity of the variation trends of pore water pressure and horizontal displacement collected at the same sampling point at the same sampling time and the same sampling depth, as well as the variation trends and differences of pore water pressure at adjacent sampling times. Combined with the first anomaly value of horizontal displacement, the module determines the corrected anomaly value of horizontal displacement collected at each sampling point at each sampling time. Based on the corrected anomaly value, the module obtains the monitoring results of horizontal displacement in the vacuum preloading treatment of the soft soil foundation area.

2. The online monitoring system for vacuum preloading treatment in soft soil foundation areas according to claim 1, characterized in that, The method for determining the initial abnormal value of the horizontal displacement is as follows: Anomaly detection is performed on the horizontal displacement of all sampling points at the same depth at the same acquisition time. The LOF value of the horizontal displacement of each sampling point at each depth is obtained and recorded as the first initial anomaly value of the horizontal displacement. Based on the trend and differences in the horizontal displacement between the target acquisition time and each adjacent acquisition time before the target acquisition time, the initial deviation value and the predicted deviation value of the horizontal displacement are determined respectively; the normalized value of the difference between the initial deviation value and the predicted deviation value of the horizontal displacement at the target acquisition time is recorded as the second initial anomaly value of the horizontal displacement at the target acquisition time. The average of the first and second initial anomalies of the horizontal displacement at the target acquisition time is recorded as the initial anomaly of the horizontal displacement at the target acquisition time.

3. The online monitoring system for vacuum preloading treatment in soft soil foundation areas according to claim 2, characterized in that, The method for determining the initial deviation value and the predicted deviation value is as follows: Based on the horizontal displacements at the same depth at the sampling point within a first preset number of sampling times prior to the target sampling time, a first historical horizontal displacement sequence of the sampling point at the target sampling time is established. The average value of all horizontal displacements contained in the first historical horizontal displacement sequence of the sampling point at the target sampling time is denoted as the first average horizontal displacement of the sampling point at the target sampling time. The sequence formed by subtracting the first average horizontal displacement from all horizontal displacements in the first historical horizontal displacement sequence of the sampling point at the target sampling time is denoted as the first average deviation difference sequence of the sampling point at the target sampling time. The LOF value corresponding to each difference in the first average deviation difference sequence is obtained, and the LOF value corresponding to the difference is denoted as the initial deviation value of the horizontal displacement corresponding to the difference. Based on the first historical horizontal displacement sequence at the target acquisition time, the predicted value of the horizontal displacement at the target acquisition time is obtained. Based on the horizontal displacement at the same depth of the sampling point at the first preset number of acquisition times before the target acquisition time and the predicted value of the horizontal displacement at the target acquisition time, a second historical horizontal displacement sequence of the sampling point at the target acquisition time is established. The average value of all horizontal displacements contained in the second historical horizontal displacement sequence of the sampling point at the target acquisition time is recorded as the second average horizontal displacement of the sampling point at the target acquisition time. The sequence formed by subtracting the second average horizontal displacement from all horizontal displacements in the second historical horizontal displacement sequence of the sampling point at the target acquisition time is recorded as the second average deviation difference sequence of the sampling point at the target acquisition time. The LOF value corresponding to each difference in the second average deviation difference sequence is obtained and recorded as the predicted deviation value of the horizontal displacement corresponding to the difference.

4. The online monitoring system for vacuum preloading treatment in soft soil foundation areas according to claim 1, characterized in that, The method for determining the initial displacement direction anomaly value at the target acquisition time is as follows: Anomaly detection is performed on the displacement directions of the same sampling point at the same depth and at the first preset number of sampling times before the target sampling time. The LOF value of each displacement direction is obtained and recorded as the first abnormal value of the displacement direction. Anomaly detection is performed on all displacement directions at different depths collected at the same sampling point at the same acquisition time. The LOF value of each displacement direction is obtained and recorded as the second anomaly value of the displacement direction. The average of the first and second displacement anomalies at the target acquisition time is recorded as the initial displacement anomaly at the target acquisition time.

5. The online monitoring system for vacuum preloading treatment in soft soil foundation areas according to claim 1, characterized in that, The specific method for determining the first outlier value of the horizontal displacement at the time of data acquisition is as follows: The normalized value of the variance of the difference between two different sampling points at the target sampling time and the first preset number of sampling times before the target sampling time, in the same depth direction, is denoted as the displacement direction difference between the two different sampling points at the target sampling time and in the same depth direction; based on the displacement direction difference, the corresponding sampling points to be analyzed are selected. Based on the anomaly detection results of the difference in displacement direction between all corresponding sampling points to be analyzed at the target acquisition time and each adjacent acquisition time before the target acquisition time, and the initial displacement direction anomaly value at the target acquisition time, the third anomaly value of the displacement direction at the target acquisition time is determined. The average of the initial outlier value of the horizontal displacement collected at the target acquisition time and the third outlier value of the displacement direction at the target acquisition time is denoted as the first outlier value of the horizontal displacement collected at the target acquisition time.

6. The online monitoring system for vacuum preloading treatment in soft soil foundation areas according to claim 5, characterized in that, The method for determining the third outlier in the displacement direction is as follows: Anomaly detection is performed on the difference in displacement direction at the same depth between two corresponding sampling points to be analyzed at the target sampling time and the first preset number of sampling times before the target sampling time, and the abnormal value of the difference in displacement direction is obtained. The mean of the outliers of the differences in all displacement directions corresponding to all sampling points to be analyzed is recorded as the first horizontal outlier at the target acquisition time; the mean of the initial displacement outlier at the target acquisition time and the first horizontal outlier is recorded as the third displacement outlier at the target acquisition time.

7. The online monitoring system for vacuum preloading treatment in soft soil foundation areas according to claim 1, characterized in that, The method for determining the data relevance is as follows: Based on the pore water pressure at the same depth at all sampling points at the same sampling time, a sequence of pore water pressure at the same depth at the same sampling time is established. Based on the horizontal displacement of all sampling points at the same depth at the same acquisition time, establish a sequence of horizontal displacements at the same depth at the same acquisition time. The absolute value of the Pearson correlation coefficient between the horizontal displacement sequence and the pore water pressure sequence at the same depth and the same sampling time is denoted as the data correlation of the same sampling point at the same sampling time and at the same depth.

8. The online monitoring system for vacuum preloading treatment in soft soil foundation areas according to claim 1, characterized in that, The method for obtaining the third initial outlier is as follows: Based on the variation trend and differences of pore water pressure at the target acquisition time and each adjacent acquisition time before the target acquisition time, the initial deviation and predicted deviation of pore water pressure at the target acquisition time are determined. The normalized value of the difference between the initial deviation and the predicted deviation of the pore water pressure at the target acquisition time is recorded as the third initial anomaly value of the pore water pressure at the target acquisition time.

9. The online monitoring system for vacuum preloading treatment in soft soil foundation areas according to claim 1, characterized in that, The formula for calculating the corrected outlier value of the horizontal displacement is: in, This represents the corrected outlier value of the horizontal displacement collected at the target acquisition time; This indicates the data correlation of the depth at which the horizontal displacement of the sampling point is located at the target acquisition time; This represents the first outlier value of the horizontal displacement collected at the target acquisition time. This represents the third initial anomaly value of the pore water pressure collected at the depth of the horizontal displacement of the sampling point at the target sampling time.

10. The online monitoring system for vacuum preloading treatment in soft soil foundation areas according to claim 1, characterized in that, The specific steps for obtaining the horizontal displacement monitoring results of vacuum preloading treatment in soft soil subgrade based on corrected outliers are as follows: When the corrected outlier value is greater than the second preset threshold, it is determined that the horizontal displacement of the sampling point corresponding to the corrected outlier value is abnormal at the corresponding sampling time.

Images