An intelligent detection method and system for deformation of deep foundation pits in pipe corridors

Abstract

The present invention relates to the field of signal data processing technology, and specifically to an intelligent detection method and system for deformation of a deep foundation pit of a pipe gallery, comprising: collecting vibration signals and IMF component signals within each short-time window; obtaining a vibration propagation sequence and a first-stage signal corresponding to each IMF; obtaining a first-stage correction coefficient based on the similarity between the IMF component signal and the corresponding vibration signal, combined with the similarity between the first-stage signals corresponding to adjacent IMFs; obtaining a second-stage signal and a second-stage correction coefficient corresponding to each IMF based on the vibration propagation sequence and the IMF component signal; correcting the signal in the vibration propagation sequence, and obtaining a vibration source signal segment corresponding to each monitoring point based on the correction result and the similarity between the IMF component signals of each vibration signal within each short-time window; and obtaining deformation monitoring results of the deep foundation pit of the pipe gallery. The present invention achieves precise separation and positioning of independent vibration sources.

Description

Technical Field

[0001] The present invention relates to the technical field of signal data processing, and in particular to an intelligent detection method and system for deformation of a deep foundation pit of a pipe gallery. Background Art

[0002] With the development of urbanization, underground pipeline corridors are widely constructed as important infrastructure. However, due to the complex geological conditions, changing surrounding environment, and uncertainties involved in deep foundation pit construction, deformation of pipeline corridor deep foundation pits is a common occurrence. To ensure the stability of the foundation pit and the safety of surrounding buildings and underground facilities, timely monitoring of foundation pit deformation is crucial.

[0003] The existing method installs sensors at various monitoring points to collect vibration data from deep tunnel pits, then uses array sensor technology to estimate the locations of deformation and vibration sources. However, given the complex internal environment of deep tunnel pits, the sources of vibration are also complex, and vibrations can generate echoes in the tunnel. This method has difficulty separating signals from different vibration sources, and the boundaries between vibration signal segments from a single vibration source are unclear. This makes it impossible to directly use the original vibration signal to estimate the location of the vibration source, affecting the results of deformation detection in deep tunnel pits. Summary of the Invention

[0004] In order to solve the technical problem that existing methods have difficulty in separating different vibration source signals and the original vibration signals cannot be directly used to estimate the location of the vibration source, the purpose of the present invention is to provide an intelligent detection method and system for deformation of deep foundation pits in pipe corridors. The technical solutions adopted are as follows:

[0005] In a first aspect, the present invention provides an intelligent detection method for deformation of a deep foundation pit of a pipe gallery, comprising:

[0006] Obtain the vibration signal at each monitoring point in the deep foundation pit of the pipeline corridor, perform signal feature decomposition on the vibration signal of each monitoring point to obtain the IMF component signal of each vibration signal in each short-time window;

[0007] According to the changing trend of each IMF component signal of each vibration signal in each short-time window, the mutation signal point is analyzed to obtain the vibration propagation sequence of each vibration signal in each short-time window and the first-stage signal corresponding to each IMF;

[0008] The first-stage correction coefficient is obtained based on the similarity between the IMF component signal and the corresponding vibration signal in each short-time window of each vibration signal, combined with the similarity between the first-stage signals corresponding to adjacent IMFs in the short-time window;

[0009] Obtain a second-stage signal corresponding to each IMF according to the vibration propagation sequence and the IMF component signal of each vibration signal in each short-time window; and obtain a second-stage correction coefficient according to a signal correlation relationship between the first-stage signal and the second-stage signal;

[0010] The signals in the vibration propagation sequence are corrected using the first-stage correction coefficients and the second-stage correction coefficients, and the vibration source signal segment corresponding to each monitoring point is obtained based on the correction results and the similarity between the IMF component signals of each vibration signal in each short-time window;

[0011] According to the vibration signal segment corresponding to each monitoring point and combined with the point cloud data inside the deep foundation pit of the pipeline corridor, the deformation monitoring results of the deep foundation pit of the pipeline corridor are obtained.

[0012] Preferably, the step of analyzing the mutation signal points according to the change trend of each IMF component signal of each vibration signal in each short-time window, and obtaining the vibration propagation sequence of each vibration signal in each short-time window and the first-stage signal corresponding to each IMF specifically includes:

[0013] For any short-time window of any vibration signal;

[0014] Obtain the second-order difference value of each IMF component signal respectively, record the moment when the second-order difference value is greater than the preset threshold as the mutation point, and record the signal corresponding to the first mutation point in each IMF component signal as the initial mutation signal;

[0015] The initial mutation signals of all IMF component signals in the short-time window constitute the vibration propagation sequence of the vibration signal in the short-time window; the signal segment corresponding to the time period corresponding to the initial mutation signal in the vibration propagation sequence is obtained on each IMF component signal in the short-time window as the first-stage signal corresponding to each IMF in the short-time window.

[0016] Preferably, the first-stage correction coefficient is obtained based on the similarity between the IMF component signal and the corresponding vibration signal of each vibration signal in each short-time window, combined with the similarity between the first-stage signals corresponding to adjacent IMFs in the short-time window, and specifically includes:

[0017] For any short-time window of any vibration signal, any IMF component signal is recorded as the target component signal;

[0018] Determining a first characteristic factor based on a similarity between the first-stage signal corresponding to the target component signal and the original vibration signal;

[0019] Obtaining the number of repetitions between all frequency components in the target component signal and all frequency components in the next adjacent IMF component signal as the second characteristic factor;

[0020] A first-stage correction coefficient of the target component signal is determined based on a negative correlation coefficient of a ratio between the first characteristic factor and the second characteristic factor.

[0021] Preferably, obtaining the second-stage signal corresponding to each IMF according to the vibration propagation sequence and the IMF component signal of each vibration signal in each short-time window specifically includes:

[0022] The time period after obtaining the last initial mutation point of all IMF component signals in the short-time window is recorded as the second stage;

[0023] The signal corresponding to each IMF component signal in the short-time window in the second stage is used as the second-stage signal corresponding to each IMF in the short-time window.

[0024] Preferably, obtaining the second-stage correction coefficient according to the signal correlation between the first-stage signal and the second-stage signal specifically includes:

[0025] For any short-time window of any vibration signal;

[0026] Obtain the first-stage signal function and the second-stage signal function corresponding to each IMF; calculate the product between each first-stage signal function and the second-stage signal function within the short-time window, and the integral value at the corresponding time as the cross-correlation eigenvalue between each first-stage signal and each second-stage signal;

[0027] Record any IMF component signal as a selected component signal, obtain the maximum value of the cross-correlation eigenvalue between the selected component signal and each first-stage signal and record it as the maximum eigenvalue of the selected component signal;

[0028] The time length between the first stage signal corresponding to the maximum eigenvalue of the selected component signal and the second stage signal corresponding to the selected component signal is obtained, and the ratio of the time length to the maximum eigenvalue is normalized to obtain the second stage correction coefficient of the selected component signal in the short time window.

[0029] Preferably, the correction of the signal in the vibration propagation sequence using the first-stage correction coefficient and the second-stage correction coefficient specifically includes:

[0030] For any short-time window of any vibration signal;

[0031] Obtain the time interval between the initial mutation point of each IMF component signal and the initial mutation point of the next adjacent IMF component signal in the vibration propagation sequence, and obtain the characteristic time length of each IMF component signal;

[0032] Calculating the product of the mean value between the first-stage correction coefficient and the second-stage correction coefficient of each IMF component signal and the characteristic time length to obtain the moving time length of each IMF component signal;

[0033] The initial mutation point of each IMF component signal corresponding to the vibration propagation sequence is shifted to the right by the shift time length to obtain a shift signal which is recorded as a modified propagation signal of each IMF component signal;

[0034] A sequence composed of the corrected propagation signals of all IMF component signals within a short-time window is used as a corrected propagation sequence, and the corrected propagation sequence is a correction result.

[0035] Preferably, obtaining the vibration source signal segment corresponding to each monitoring point based on the correction result and the similarity between the IMF component signals of each vibration signal in each short-time window specifically includes:

[0036] The average phases corresponding to all IMF component signals in the short-time window are arranged in ascending order to form a propagation phase sequence;

[0037] According to the time length between the vibration propagation signals of two adjacent IMF component signals in each short-time window, combined with the difference between the two adjacent average phases in the propagation phase sequence and the time series length of the vibration propagation sequence, the similarity index between each short-time window and the modified propagation sequence is obtained;

[0038] According to the change of the similarity index between each short-time window of each vibration signal and the modified propagation sequence, the vibration source signal segment of the monitoring point corresponding to each vibration signal is obtained.

[0039] Preferably, the calculation formula for the similarity index between each short-time window and the modified propagation sequence is:

[0040]

[0041] in, It represents the similarity index between the u-th short-time window of any vibration signal and the modified propagation sequence, It represents the time interval between the initial mutation point of the i-th IMF component signal and the initial mutation point of the next adjacent IMF component signal in the modified propagation sequence within the u-th short-time window. Indicates the total number of IMF component signals contained in the short-time window, represents the time length of the modified propagation sequence, The absolute value of the average phase difference between the i-th IMF component signal and the adjacent next IMF component signal in the propagation phase sequence of the u-th short-time window of the vibration signal, that is, the phase delay, Represents the maximum value of all phase delays in the u-th short-time window of the vibration signal, represents the exponential function with the natural constant e as the base, is the normalization function.

[0042] Preferably, obtaining the vibration source signal segment of the monitoring point corresponding to each vibration signal according to the change of the similarity index between each short-time window of each vibration signal and the modified propagation sequence specifically includes:

[0043] For any vibration signal, calculate the first-order difference value of the similarity index corresponding to each short-time window in the vibration signal, and take the previous short-time window adjacent to the short-time window corresponding to the minimum value of all first-order difference values ​​as the first vibration source signal segment;

[0044] According to the same method as the first vibration source signal segment, the mutation point is re-acquired within the short time window after the vibration source signal segment, and the second vibration source signal segment is determined. And so on, all vibration source signal segments corresponding to the monitoring points of the vibration signal are obtained.

[0045] In the second aspect, the present invention provides an intelligent detection system for deformation of deep foundation pits in pipeline corridors, comprising a memory, a processor, and a computer program stored in the memory and running on the processor. When the computer program is executed by the processor, it implements the steps of an intelligent detection method for deformation of deep foundation pits in pipeline corridors.

[0046] The embodiments of the present invention have at least the following beneficial effects:

[0047] The present invention first collects vibration signals at different monitoring points and performs data preprocessing to obtain signal decomposition results, providing a data basis for subsequent feature analysis. Then, in the first aspect, considering the signal propagation characteristics of the independent vibration source in the first stage, the mutation in the IMF component signal is analyzed to determine the initial vibration propagation sequence and the first stage signal in the corresponding propagation characteristics. Then, the similarity between the first stage signal and the original signal is analyzed to quantify whether the current IMF component signal has the signal propagation characteristics of the first stage, and obtain the first stage correction coefficient. Secondly, in the second aspect, considering the signal propagation characteristics of the independent vibration source in the second stage, the second stage signal is determined, and based on the correlation between the first stage signal and the second stage signal, the current IMF component is quantified to determine whether it meets the signal propagation characteristics of the second stage to obtain the second stage correction coefficient. Further, combining the correction feature analysis results of these two aspects, the initial vibration propagation sequence is corrected, and then by analyzing the similarity between the corrected vibration propagation situation and the IMF signal components in each short-time window, the vibration signal that best meets the vibration source propagation characteristics can be determined to screen out the vibration source signal segment and finally obtain the deformation monitoring results of the deep foundation pit of the pipe gallery. The present invention solves the problem of locating vibration sources in complex environments such as corridor foundation pits, and realizes the precise separation and positioning of independent vibration sources. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0049] Figure 1 This is a flowchart of the steps of an intelligent detection method for deformation of a deep foundation pit of a pipe gallery provided by the present invention;

[0050] Figure 2 This is a schematic diagram of three-dimensional point cloud data of a pipe gallery foundation pit without laying pipes provided by the present invention;

[0051] Figure 3 Schematic diagram of the ITD decomposition result corresponding to the short-time window provided by the present invention;

[0052] Figure 4 It is a schematic diagram of the signal structure of the vibration propagation chain within a short time window provided by the present invention;

[0053] Figure 5 It is a flowchart of the steps of the method for obtaining the correction coefficient in the first stage provided by the present invention;

[0054] Figure 6is a flowchart of the steps of the method for obtaining the second-stage correction coefficient provided by the present invention;

[0055] Figure 7 It is a flowchart of the steps of the method for obtaining the vibration source signal segment corresponding to the monitoring point provided by the present invention. DETAILED DESCRIPTION

[0056] To further illustrate the technical means and effectiveness of the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, describes in detail the specific implementation, structure, features, and effectiveness of an intelligent detection method and system for pipe gallery deep foundation pit deformation proposed by the present invention. In the following description, different references to "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0057] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0058] The specific scheme of the intelligent detection method and system for deformation of a deep foundation pit of a pipe gallery provided by the present invention is described in detail below with reference to the accompanying drawings.

[0059] See also Figure 1 , which shows a flowchart of the steps of an intelligent detection method for deformation of a deep foundation pit of a pipe gallery provided by one embodiment of the present invention, the method comprising the following steps:

[0060] Step S100: Acquire the vibration signal at each monitoring point in the deep foundation pit of the pipe gallery, perform signal feature decomposition on the vibration signal of each monitoring point to obtain the IMF component signal of each vibration signal in each short-time window.

[0061] In this embodiment, a number of monitoring points are set at equal intervals along the length of the corridor at the bottom of the foundation pit, and vibration sensors are installed at the corresponding monitoring points to monitor the vibration data of the bottom of the corridor.

[0062] Furthermore, in order to detect the deformation of the foundation pit based on the vibration source signal, it is also necessary to obtain the three-dimensional point cloud data of the corridor foundation pit, such as Figure 2 Specifically, a three-dimensional laser scan is performed on the foundation pit. This is achieved through grid scanning, typically using laser pulse ranging, to obtain point cloud data within the corridor foundation pit. This method is well known and will not be further described here.

[0063] Before deformation occurs within the corridor's foundation pit, vibrations also occur. Vibration sensors can collect real-time signal data from these vibrations. However, deformation within the corridor's foundation pit can occur at random locations, and vibration sensors used to monitor vibrations can only be installed at a limited number of fixed locations, failing to cover all vibration sources.

[0064] The vibration signal generated by the vibration source may be affected by different positions, different paths, and different structural layers during its propagation toward the vibration sensor. These position differences make the spatiotemporal dimensions of the data collected by the vibration sensor more complex, making it difficult to fuse the vibration data and the point cloud data. That is, the positions of the vibration source and the deformation area cannot correspond, and an accurate foundation pit deformation model cannot be obtained. In order to accurately locate the deformation source, it is necessary to perform temporal and spatial calibration of the vibration data in the point cloud data.

[0065] When certain structural layers in the deep foundation pit of the tunnel experience deformation phenomena such as cracking, collapse, bulging, and displacement, the vibration signal at the time of the abnormality can be collected by vibration sensors. However, it is difficult to determine the more accurate location of the deformation source from the monitoring data, especially since the vibration signals generated in the deep foundation pit are multi-segment and superimposed. It is difficult to independently segment the vibration signals of each independent vibration source to determine whether each independent vibration source may have deformation.

[0066] Based on this, this embodiment first performs characteristic signal decomposition on the vibration signals collected by the vibration sensors at each monitoring point, providing a data foundation for subsequent analysis of the signal source information contained in each decomposed characteristic signal. This embodiment employs intrinsic time decomposition (ITD) decomposition and Fourier transform to perform characteristic signal decomposition.

[0067] Specifically, each monitoring point corresponds to a set of vibration signals, and ITD decomposition is performed on each set of vibration signals. It should be noted that the ITD algorithm is more adaptable to irregular data. During the decomposition process, short-term windows of varying lengths, called intrinsic short-term windows, are first separated. Within each short-term window, different component signals are then individually segmented. Each intrinsic short-term window in the ITD decomposition result is used directly as a short-term window. A short-time Fourier transform is performed on each component signal of the vibration signal to obtain the amplitude and phase spectrum of each IMF component signal within each short-term window.

[0068] It can be understood that each group of vibration signals corresponds to multiple short-time windows, and each short-time window contains a fixed number of IMF component signals, and each IMF component signal represents a type of signal component in the vibration signal. Figure 3As shown, the ITD decomposition result corresponding to a short-time window in this embodiment includes a total of 5 IMF component signals. Figure 3 The order from top to bottom is IMF1, IMF2, IMF3, IMF4 and IMF5.

[0069] The purpose of short-time series processing is to determine the starting and ending positions of a single vibration signal source through local signal analysis. However, since the energy of the vibration signal attenuates during the propagation process, the amplitude of the vibration signal will show a decreasing trend, and the attenuation rates of different component signal components of the same vibration source signal are also different. Therefore, the ITD decomposition algorithm can only separate the aliasing components of the signal, and further feature analysis is required for the decomposition results.

[0070] Step S200 , analyzing the mutation signal points according to the change trend of each IMF component signal of each vibration signal in each short-time window, and obtaining the vibration propagation sequence of each vibration signal in each short-time window and the first-stage signal corresponding to each IMF.

[0071] In the corridor foundation pit, large, instantaneous stress changes cause deformation, which is typically reflected in the vibration signal as sudden changes. Because ITD decomposition can retain components at different time scales, each IMF component signal can generally exhibit dynamic changes from gentle to sudden changes. Based on this, characteristic analysis can be performed on the signal change trends of each IMF component signal to filter out data points with sudden changes in each IMF component signal, thereby preliminarily extracting the time series signal characteristics of vibration propagation.

[0072] Specifically, this embodiment takes the five IMF component signals in any short-time window in any vibration signal as an example to illustrate, obtain the second-order difference value of each IMF component signal respectively, record the moment when the second-order difference value is greater than the preset threshold as the mutation point, and record the signal corresponding to the first mutation point in each IMF component signal as the initial mutation signal.

[0073] Among them, in each IMF component signal, except for the first and second moments, where the second-order difference value cannot be calculated, the second-order difference value of each moment can be calculated and obtained. For any IMF component signal, the mean of all second-order difference values ​​is used as the preset threshold corresponding to the IMF component signal. That is, under the IMF component signal, when the second-order difference value is greater than the mean of the corresponding second-order difference value, the moment corresponding to the second-order difference value is recorded as the mutation point under the IMF component signal, and the signal corresponding to the mutation point is the initial mutation signal. It can be understood that the second-order difference method is very sensitive to the relationship between smooth signals and mutation signals, which facilitates the detection of the moment when the signal undergoes a mutation phenomenon.

[0074] Furthermore, the initial mutation signals of all IMF component signals in the short-time window constitute the vibration propagation sequence of the vibration signal in the short-time window; and the signal segment corresponding to the time period corresponding to the initial mutation signal in the vibration propagation sequence is obtained on each IMF component signal in the short-time window as the first-stage signal corresponding to each IMF in the short-time window.

[0075] It can be understood that the initial mutation signal in the vibration propagation sequence within the short time window has a certain time sequence, such as Figure 4 As shown in the figure, after re-sorting the IMF component signals according to the time sequence of the initial mutation signals, the performance of the vibration propagation chain can be more intuitively displayed using straight line connections. According to the order of realization, the IMF component signals corresponding to the vibration propagation chain are IMF3, IMF4, IMF5, IMF2 and IMF1.

[0076] The vibration propagation chain represents an estimate of the order in which all components of a vibration signal generated by a vibration source are transmitted to each monitoring point, based on the signal mutations within each IMF component signal. In other words, each initial mutation signal in the vibration propagation chain represents the position of each IMF component signal within the short-term window corresponding to the current monitoring point for that vibration source.

[0077] Based on this, the time period from the moment of the first initial mutation point to the moment of the last mutation point in the vibration propagation sequence can be understood as the process of the vibration signal propagating to the current monitoring point, and then the signal of each IMF component signal in the short-time window in this time period constitutes the first-stage signal corresponding to each IMF component signal.

[0078] Step S300 , obtaining a first-stage correction coefficient based on the similarity between the IMF component signal and the corresponding vibration signal in each short-time window of each vibration signal and the similarity between the first-stage signals corresponding to adjacent IMFs in the short-time window.

[0079] Taking into account the existence of echoes in the conduction of vibration in a closed space, the vibration signal collected by the vibration sensor may exhibit modal aliasing and a certain degree of periodicity. By analyzing the characteristics of the vibration signal in these two aspects, the vibration propagation chain of the signal source can be corrected to a certain extent.

[0080] If an independent vibration source exists, the vibration signal generated by this source can be divided into two propagation phases. If the signal segments corresponding to the vibration propagation chain exhibit characteristics that encompass more than just the two propagation phases, the vibration propagation chain needs to be modified based on the distribution of the vibration signal's characteristics. First, the signal characteristics of the first phase exhibited by the independent vibration source are analyzed to quantify the extent to which the vibration propagation chain requires modification in this first phase.

[0081] It's important to note that the first stage specifically represents the signal segment of all different signal components between the first initial mutation point (the earliest initial mutation point) and the last initial mutation point (the latest initial mutation point) in the vibration propagation chain. Because the propagation speeds and propagation paths (due to reflection and refraction) of different signal components may vary, there is no aliasing between the component signals in the first stage.

[0082] In this embodiment, the five IMF component signals of any vibration signal in any short-time window are still used as an example for explanation, and any IMF component signal is recorded as the target component signal. In this embodiment, the nth IMF component signal can be used as the target component signal, such as Figure 5 As shown, the method for obtaining the correction coefficient in the first stage can be implemented by steps S301 to S303.

[0083] Step S301 : determining a first characteristic factor based on the similarity between the first stage signal corresponding to the target component signal and the original vibration signal.

[0084] If the characteristics of each component signal can be observed in the original signal waveform, it means that the different component signals do not overlap with each other and the characteristics of the component signals are not covered. Therefore, the similarity between each IMF component signal and the original vibration signal can be analyzed to quantify the component signal characteristics of each IMF component signal.

[0085] Specifically, in this embodiment, the Pearson correlation coefficient is used to calculate the similarity between two data. More specifically, this embodiment uses the target component signal of any vibration signal within any short-time window as an example for explanation. The signal within the time period corresponding to the first-stage signal of the target component signal is intercepted from the vibration signal and recorded as the original signal segment. The Pearson correlation coefficient between the first-stage signal of the target component signal and the original signal segment is calculated to obtain the first characteristic factor corresponding to the target component signal. The larger the value, the clearer the characteristics of the target component signal.

[0086] Step S302 : obtaining the number of repetitions between all frequency components in the target component signal and all frequency components in the next adjacent IMF component signal as a second characteristic factor.

[0087] In the ITD decomposition results, the fewer repeated signal features between the component signals of two adjacent components, the more independent the characteristic information of each component's component signal is, and the less likely it is to exhibit signal aliasing. Based on this, the number of repeated frequency components between all frequency components in the target component signal and all frequency components in the next adjacent IMF component signal is obtained.

[0088] Specifically, the target component signal is the nth IMF component signal within any short-time window of any vibration signal. The second eigenfactor corresponding to the target component signal, or nth IMF signal component, is calculated by calculating the number of identical frequency values ​​between all different frequency values ​​in the nth IMF component signal and all different frequency values ​​in the (n+1)th IMF signal component. The greater the number of identical frequency values, the greater the likelihood of aliasing between two adjacent component signals of different components.

[0089] It should be noted that, for the last IMF component signal, it is impossible to obtain the next adjacent IMF component signal, and the above calculation is not performed in this embodiment. In other embodiments, the implementer may make settings according to the specific implementation scenario.

[0090] Step S303 : determining a first-stage correction coefficient of the target component signal based on a negative correlation coefficient of a ratio between the first characteristic factor and the second characteristic factor.

[0091] The first characteristic factor reflects the similarity between the target component signal and the original vibration signal. The larger the value, the clearer the signal characteristic information of the corresponding target component signal. The second characteristic factor reflects the degree of signal repetition between the target component signal and the adjacent component signals. The larger the value, the greater the overlap between the target component signal and other signals, and the greater the possibility of signal aliasing.

[0092] Combining the characteristic performance of the two aspects, the ratio of the first characteristic factor and the second characteristic factor of the target component signal is negatively normalized to obtain the first-stage correction coefficient of the target component signal. The calculation formula can be specifically expressed as , represents the first stage correction coefficient of the target component signal, n represents the nth IMF component signal, represents the first characteristic factor, represents the second characteristic factor, is the normalization function.

[0093] The ratio between the two In the equation, the larger the numerator and the smaller the denominator, the more independent and non-aliased the component signal components are. The corresponding component signal components do not need to be corrected, and the smaller the value of the first-stage correction coefficient is.

[0094] Step S400: obtaining a second-stage signal corresponding to each IMF according to the vibration propagation sequence and the IMF component signal of each vibration signal in each short-time window; and obtaining a second-stage correction coefficient according to the signal correlation relationship between the first-stage signal and the second-stage signal.

[0095] Considering that the vibration signal generated by an independent vibration source is divided into two specific propagation stages, if the signal characteristics of the signal segment corresponding to the vibration propagation chain exceed those of the two propagation stages, the vibration propagation chain needs to be modified based on the characteristic distribution of the vibration signal. Secondly, a two-step analysis is conducted on the signal characteristics of the second stage exhibited by the independent vibration source to quantify the extent to which the vibration propagation chain needs to be modified in this second stage.

[0096] It should be noted that the second stage is specifically represented by all signals after the last initial mutation point (the latest initial mutation point) in the vibration propagation chain, indicating the echo phenomenon that may occur after a single vibration source is fully propagated to the monitoring point, that is, all vibration signals after the last initial mutation point may contain echoes of the signal components in the above-mentioned first stage.

[0097] The first step is to obtain the signal representation of the second stage.

[0098] Specifically, the time period after the last initial mutation point of all IMF component signals within the short-time window is recorded as the second stage; the signal corresponding to each IMF component signal within the short-time window in the second stage is used as the second stage signal corresponding to each IMF within the short-time window. It is understood that the last initial mutation point refers to the last signal point in the time series, that is, the latest initial mutation point.

[0099] The second step is to perform feature analysis on the first and second stages, and quantify the degree to which each component needs to be corrected based on the second stage feature performance. In this embodiment, any short-term window of any vibration signal is used as an example for explanation, such as Figure 6 As shown, the method for obtaining the second stage correction coefficient can be implemented by steps S401 to S403.

[0100] Step S401: Obtain the cross-correlation characteristic value between each first-stage signal and second-stage signal within a short-time window.

[0101] Specifically, firstly, the first-stage signal function and the second-stage signal function corresponding to each IMF are obtained; the product between each first-stage signal function and the second-stage signal function in the short-time window is calculated, and the integral value at the corresponding time is used as the cross-correlation eigenvalue between each first-stage signal and each second-stage signal.

[0102] As a specific example, the calculation formula of the cross-correlation eigenvalue can be expressed as:

[0103]

[0104] in, represents the cross-correlation characteristic value between any first-stage signal and any second-stage signal, t represents the time sequence, represents any first-stage signal function, represents any second-stage signal function.

[0105] It should be noted that the signal function can be obtained by fitting. When calculating the integral value, the signal value corresponding to the stage signal can be actually obtained for calculation. This process is a well-known technology and will not be introduced in detail here.

[0106] Step S402 : record any one IMF component signal as a selected component signal, obtain the maximum value of the cross-correlation eigenvalue between the selected component signal and each first-stage signal, and record it as the maximum eigenvalue of the selected component signal.

[0107] When there is a signal segment in the second stage signal The result of multiplying the integral of the first stage signal segment is the largest, which means and has the maximum cross-correlation.

[0108] In this embodiment, the mth IMF component signal within the short-time window can be used as the selected component signal. A cross-correlation eigenvalue can be calculated between the selected component signal and the first-stage signal of each IMF component signal within the current short-time window. The maximum value among these values ​​is the maximum eigenvalue of the selected component signal, indicating the degree of characteristic expression with the maximum cross-correlation relationship with the selected component signal.

[0109] Step S403 , obtaining a second stage correction coefficient of the selected component signal in the short time window based on the first stage signal corresponding to the maximum eigenvalue of the selected component signal and the second stage signal corresponding to the selected component signal in combination with the maximum eigenvalue.

[0110] Specifically, the time length between the first stage signal corresponding to the maximum eigenvalue of the selected component signal and the second stage signal corresponding to the selected component signal is obtained, and the ratio of the time length to the maximum eigenvalue is normalized to obtain the second stage correction coefficient of the selected component signal in the short time window.

[0111] As a specific example, the calculation formula for the second stage correction coefficient of the selected component signal can be expressed as: ,in, represents the second-stage correction coefficient of the selected component signal, that is, the second-stage correction coefficient of the m-th IMF component signal in the short-time window, m represents the m-th IMF component signal, represents the time length between the first stage signal corresponding to the maximum eigenvalue of the selected component signal and the second stage signal corresponding to the selected component signal; represents the maximum eigenvalue of the selected component signal, t represents the time series, is the normalization function.

[0112] The time length refers to the time length between the first moment in the first stage signal corresponding to the maximum eigenvalue of the selected component signal and the first moment in the second stage signal corresponding to the selected component signal. It reflects the time difference between the first stage signal that has the maximum cross-correlation relationship with the selected component signal, and also represents the delay time between the original vibration signal and the possible echo signal.

[0113] In the ratio The larger the numerator, the smaller the denominator, which is the length of time The larger the value of , the smaller the maximum eigenvalue, which means the longer the echo delay time, the lower the credibility of the selected component signal with the echo characteristics, and the less the corresponding component components conform to the signal propagation characteristics of the second stage. Therefore, the more correction is needed, and the larger the value of the corresponding second-stage correction coefficient is, the greater the degree of correction required.

[0114] Step S500: Use the first-stage correction coefficient and the second-stage correction coefficient to correct the signal in the vibration propagation sequence, and obtain the vibration source signal segment corresponding to each monitoring point based on the correction result and the similarity between the IMF component signals of each vibration signal in each short-time window.

[0115] The first-stage correction coefficient reflects the degree to which each IMF component signal needs correction based on its propagation characteristics during the first stage. The second-stage correction coefficient reflects the degree to which each IMF component signal needs correction based on its propagation characteristics during the second stage. Based on this, the initially obtained vibration propagation chain is first corrected, combining the analysis results of the component signals' characteristics requiring correction in both aspects, to obtain a more accurate representation of the vibration source's propagation signal. Then, based on this corrected vibration propagation, the vibration source characteristics are analyzed to accurately determine the signal information of each individual vibration source.

[0116] In the first step, the signal in the vibration propagation sequence is corrected using the first-stage correction coefficient and the second-stage correction coefficient.

[0117] Specifically, the larger the first-stage correction coefficient value of each IMF component signal within the short-time window, the more chaotic the characteristic information of the corresponding IMF component signal is, and the greater the possibility of aliasing. The larger the second-stage correction coefficient value of each IMF component signal within the short-time window, the less likely the corresponding IMF component signal will subsequently experience an echo. In other words, the corresponding IMF component signal does not have the characteristics of a vibration wave signal propagating within the corridor foundation pit, and may not even be a vibration component.

[0118] It should be noted that the direction of signal correction in this embodiment is to further reduce the delay between adjacent signals. For example, within a short-time window, the first initial mutation point in the vibration propagation chain is moved closer to the second initial mutation point to reduce the time interval between the two initial mutation points.

[0119] More specifically, take any short-time window in any vibration signal as an example to illustrate, in the vibration propagation chain of the short-time window, such as Figure 4 As shown, the time interval between the initial mutation point of each IMF component signal and the initial mutation point of the next adjacent IMF component signal is obtained to obtain the characteristic time length of each IMF component signal. The moving time length of each IMF component signal is obtained by multiplying the mean of the first-stage correction coefficient and the second-stage correction coefficient of each IMF component signal by the characteristic time length.

[0120] As a specific example, the calculation formula for the moving time length of the i-th IMF component signal in the vibration propagation sequence within the short-time window can be expressed as: ,in represents the moving time length of the i-th IMF component signal in the vibration propagation sequence within the short-time window, represents the characteristic time length of the i-th IMF component signal in the vibration propagation sequence within the short-time window, represents the first-stage correction coefficient of the i-th IMF component signal in the vibration propagation sequence within the short-time window, It represents the second-stage correction coefficient of the i-th IMF component signal in the vibration propagation sequence within the short-time window.

[0121] Then, the initial mutation point of each IMF component signal corresponding to the vibration propagation sequence is shifted to the right by the moving time length to obtain a moving signal recorded as a corrected propagation signal of each IMF component signal, and the sequence composed of the corrected propagation signals of all IMF component signals in the short-time window is taken as a corrected propagation sequence, and the corrected propagation sequence is the correction result.

[0122] It's understandable that the revised propagation sequence is arranged in the same chronological order as the initial vibration propagation sequence. This correction process involves shifting each initial mutation point in the vibration propagation chain in the direction of increasing time by the corresponding shift time length, completing the correction process. This revised vibration propagation chain more accurately represents the propagation characteristics of the first vibration signal component (the first vibration source).

[0123] It should be noted that, for the same reason as in step 302, the next adjacent IMF component signal cannot be obtained for the last IMF component signal in the vibration propagation chain, and the above calculation is not performed in this embodiment. In other embodiments, the implementer may make settings according to the specific implementation scenario.

[0124] In the second step, the vibration source signal segment corresponding to each monitoring point is obtained based on the correction results and the similarity between the IMF component signals of each vibration signal in each short-time window.

[0125] The modified vibration sequence characterizes the relative relationship between the vibration propagation of each component signal of the vibration signal, and then extracts the information of the propagation characteristics by analyzing the signal characteristics in each short-time window, and analyzes the similarity between the propagation characteristics of each short-time window and the modified vibration sequence, and then selects the short-time window where the vibration signal that best meets the vibration propagation characteristics in the current vibration signal is located, and then determines the complete vibration source signal by analyzing the signal segment range of the continuous propagation of the vibration source. Based on this, Figure 7 As shown, the method for acquiring the vibration source signal segment corresponding to the monitoring point can be implemented by steps S501 to S503.

[0126] Step S501 : Arrange the average phases corresponding to all IMF component signals within a short-time window in ascending order of the average phases to form a propagation phase sequence.

[0127] First, the signal characteristics in each short-term window of the vibration signal are analyzed to extract the propagation characteristic information corresponding to the vibration signal. The absolute value of the difference between each average phase and the next adjacent average phase in each propagation phase sequence can be used to calculate a phase delay. .

[0128] Step S502, based on the time length between the vibration propagation signals of two adjacent IMF component signals in each short-time window, combined with the difference between two adjacent average phases in the propagation phase sequence and the time series length of the vibration propagation sequence, obtain the similarity index between each short-time window and the modified propagation sequence.

[0129] Since the initial mutation point represents the initial location of the vibration mutation, the vibration propagation chain formed by the initial mutation point represents the relative relationship between the vibration propagation of the vibration signal's various component signals. Therefore, if the vibration signal in subsequent short-term windows is generated by a continuous independent vibration source, the relative propagation relationship between the various component signals in these short-term windows will remain basically unchanged. Unless the vibration source is interrupted and a new vibration source is generated, the propagation relationship will change. Therefore, the short-term window with greater similarity is more likely to be within the signal range of the continuous propagation of the vibration source. Based on this, it is necessary to quantify the similarity index between the vibration signal and the modified propagation sequence in each short-term window.

[0130] As a specific example, the signal propagation information within the short-time window is compared with the modified vibration propagation chain to obtain all short-time windows from the propagation of the vibration source to the dissipation. In this embodiment, taking the u-th short-time window of any vibration signal as an example, the calculation formula for the similarity index between the u-th short-time window and the modified propagation sequence can be expressed as:

[0131]

[0132] in, It represents the similarity index between the u-th short-time window of any vibration signal and the modified propagation sequence, It represents the time interval between the initial mutation point of the i-th IMF component signal and the initial mutation point of the next adjacent IMF component signal in the modified propagation sequence within the u-th short-time window. Indicates the total number of IMF component signals contained in the short-time window, represents the time length of the modified propagation sequence, The absolute value of the average phase difference between the i-th IMF component signal and the adjacent next IMF component signal in the propagation phase sequence of the u-th short-time window of the vibration signal, that is, the phase delay, Represents the maximum value of all phase delays in the u-th short-time window of the vibration signal, represents the exponential function with the natural constant e as the base, is the normalization function.

[0133] Reflects the phase delay change rate of the i-th IMF component signal in the vibration propagation information within the u-th short-time window, It reflects the slope value of the initial mutation point corresponding to the i-th IMF component signal in the modified vibration propagation chain. It represents the error between the slope of each initial mutation point in the corrected vibration propagation chain and the phase delay change rate of all component signals in the current short-time window. The smaller the difference between the two, the greater the corresponding similarity, that is, the larger the value of the similarity index.

[0134] If the time distance between the initial mutation points in the corrected vibration propagation chain is large, it is possible that they are not different vibration signal components generated by the same vibration source. Therefore, it is necessary to give a calculation question factor to the large time delay, that is, the time delay The larger it is, the smaller the corresponding questioning factor value is, and it is used as the weight to weight the above differences.

[0135] Step S503 , obtaining the vibration source signal segment of the monitoring point corresponding to each vibration signal according to the change of the similarity index between each short-time window of each vibration signal and the modified propagation sequence.

[0136] For any vibration signal, the larger the value of the similarity index between each short-time window and the corrected propagation sequence, the more the propagation characteristics of the vibration signal within the short-time window conform to the propagation characteristics of the corrected vibration propagation chain, that is, the greater the possibility that the short-time window is within the signal segment range of continuous propagation of the vibration source.

[0137] Based on this, the vibration source in each vibration signal is determined by analyzing the changing trends of the similarity index within each short-time window. Specifically, for any vibration signal, the first-order difference of the similarity index corresponding to each short-time window in the vibration signal is calculated. The short-time window immediately preceding the short-time window corresponding to the minimum of all first-order differences is used as the first vibration source signal segment.

[0138] It should be noted that since the signal propagation characteristics may be about to change in this time window with the minimum first-order difference of similarity, the previous time window is considered to be the last window before the signal propagation characteristics change significantly. Therefore, it is used as the cutoff position of the first vibration signal source. This fully captures the complete signal segment of the signal source during the relatively stable propagation phase, thereby better analyzing and extracting the characteristics of the signal source itself.

[0139] It can be understood that the first vibration source signal is the result of feature analysis of the first group of mutation points extracted from the original group of vibration signals, that is, a group of mutation points corresponds to a possible vibration source. Therefore, after obtaining the first vibration source signal segment, the first vibration source signal segment is removed from the original vibration signal, that is, starting from the next moment adjacent to the last signal of the vibration source signal segment, the feature analysis process of the new vibration source signal segment is performed according to the same method as the first vibration source signal segment, that is, the aforementioned steps of this embodiment, and so on, until all independent vibration sources are extracted, and all vibration source signal segments of the monitoring points corresponding to the vibration signal can be finally obtained.

[0140] The vibration signal data collected by the vibration sensor at each monitoring point may be separated into different independent vibration source signal segments.

[0141] Step S600: Obtain deformation monitoring results of the deep foundation pit of the pipeline corridor based on the vibration signal segment corresponding to each monitoring point and the point cloud data inside the deep foundation pit of the pipeline corridor.

[0142] Specifically, for each vibration source signal segment at each of four adjacent monitoring points, the time difference between the vibration signal reaching different vibration sensors can be calculated using the cross-correlation method, and then the beamforming method is used to deduce the incident direction of the vibration source relative to the array. Based on the direction estimation result and the known layout of the sensor array, the position of the vibration source is calculated using the triangulation method. Combined with the geometric positioning method, the estimated values ​​in different directions are intersected to determine the three-dimensional coordinate position of each independent vibration source. Among them, the cross-correlation algorithm, beamforming method, and geometric positioning method are commonly used in the fields of signal processing and vibration detection. They are all well-known technologies and will not be elaborated on.

[0143] It should be noted that the method for locating the signal source for each monitoring point corresponding to the vibration source signal extracted by the vibration sensor is a technique well known to those skilled in the art. This is only briefly introduced here and will not be elaborated on in detail. Furthermore, after determining the location of the signal source, the location of the vibration signal source can be detected by relevant staff to determine whether deformation has occurred. In other embodiments, the implementer can select an appropriate method for processing according to the specific implementation scenario.

[0144] In summary, this embodiment uses ITD decomposition and short-time Fourier transform to derive the initial mutation point based on the sudden change of the vibration source. This then generates a vibration propagation chain and corrects it based on the propagation characteristics of the vibration signal. The system then establishes a propagation phase sequence within each short-time window and, based on the similarity between the propagation phase sequence and the corrected propagation chain, determines the signal cutoff point for each independent vibration source. Ultimately, each independent vibration source signal is independently isolated, significantly improving accuracy. This approach solves the challenge of locating vibration sources in complex environments such as corridor foundation pits and enables the precise separation and location of independent vibration sources.

[0145] The present invention also provides an intelligent detection system for pipe gallery deep foundation pit deformation, comprising a memory, a processor, and a computer program stored in the memory and running on the processor. When executed by the processor, the computer program implements the steps of an intelligent detection method for pipe gallery deep foundation pit deformation. Since an embodiment of an intelligent detection method for pipe gallery deep foundation pit deformation has already been described in detail, further description is omitted here.

[0146] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application, and should all be included in the scope of protection of the present application.

Claims

1. An intelligent detection method for deformation of deep foundation pit of pipe gallery, characterized in that: The method comprises the following steps: Obtain the vibration signal at each monitoring point in the deep foundation pit of the pipeline corridor, perform signal feature decomposition on the vibration signal of each monitoring point to obtain the IMF component signal of each vibration signal in each short-time window; According to the changing trend of each IMF component signal of each vibration signal in each short-time window, the mutation signal point is analyzed to obtain the vibration propagation sequence of each vibration signal in each short-time window and the first-stage signal corresponding to each IMF; The first-stage correction coefficient is obtained based on the similarity between the IMF component signal and the corresponding vibration signal in each short-time window of each vibration signal, combined with the similarity between the first-stage signals corresponding to adjacent IMFs in the short-time window; Obtain a second-stage signal corresponding to each IMF according to the vibration propagation sequence and the IMF component signal of each vibration signal in each short-time window; and obtain a second-stage correction coefficient according to a signal correlation relationship between the first-stage signal and the second-stage signal; The signals in the vibration propagation sequence are corrected using the first-stage correction coefficients and the second-stage correction coefficients, and the vibration source signal segment corresponding to each monitoring point is obtained based on the correction results and the similarity between the IMF component signals of each vibration signal in each short-time window; Based on the vibration signal segment corresponding to each monitoring point and combined with the point cloud data inside the deep foundation pit of the pipeline corridor, the deformation monitoring results of the deep foundation pit of the pipeline corridor are obtained; The method of analyzing the mutation signal point according to the change trend of each IMF component signal of each vibration signal in each short-time window, and obtaining the vibration propagation sequence of each vibration signal in each short-time window and the first-stage signal corresponding to each IMF specifically includes: For any short-time window of any vibration signal; Obtain the second-order difference value of each IMF component signal respectively, record the moment when the second-order difference value is greater than the preset threshold as the mutation point, and record the signal corresponding to the first mutation point in each IMF component signal as the initial mutation signal; The initial mutation signals of all IMF component signals in the short-time window constitute the vibration propagation sequence of the vibration signal in the short-time window; the signal segment corresponding to the time period corresponding to the initial mutation signal in the vibration propagation sequence is obtained on each IMF component signal in the short-time window as the first-stage signal corresponding to each IMF in the short-time window.

2. The intelligent detection method for deformation of a deep foundation pit of a pipe gallery according to claim 1 is characterized in that: The first-stage correction coefficient is obtained based on the similarity between the IMF component signal and the corresponding vibration signal in each short-time window of each vibration signal, combined with the similarity between the first-stage signals corresponding to adjacent IMFs in the short-time window, specifically including: For any short-time window of any vibration signal, any IMF component signal is recorded as the target component signal; Determining a first characteristic factor based on a similarity between the first-stage signal corresponding to the target component signal and the original vibration signal; Obtaining the number of repetitions between all frequency components in the target component signal and all frequency components in the next adjacent IMF component signal as the second characteristic factor; A first-stage correction coefficient of the target component signal is determined based on a negative correlation coefficient of a ratio between the first characteristic factor and the second characteristic factor.

3. The intelligent detection method for deformation of a deep foundation pit of a pipe gallery according to claim 1 is characterized in that: The step of obtaining a second-stage signal corresponding to each IMF according to the vibration propagation sequence and the IMF component signal of each vibration signal in each short-time window specifically includes: The time period after obtaining the last initial mutation point of all IMF component signals in the short-time window is recorded as the second stage; The signal corresponding to each IMF component signal in the short-time window in the second stage is used as the second-stage signal corresponding to each IMF in the short-time window.

4. The intelligent detection method for deformation of a deep foundation pit of a pipe gallery according to claim 1 is characterized in that: The obtaining of the second-stage correction coefficient according to the signal correlation between the first-stage signal and the second-stage signal specifically includes: For any short-time window of any vibration signal; Obtain the first-stage signal function and the second-stage signal function corresponding to each IMF; calculate the product between each first-stage signal function and the second-stage signal function within the short-time window, and the integral value at the corresponding time as the cross-correlation eigenvalue between each first-stage signal and each second-stage signal; Record any IMF component signal as a selected component signal, obtain the maximum value of the cross-correlation eigenvalue between the selected component signal and each first-stage signal and record it as the maximum eigenvalue of the selected component signal; The time length between the first stage signal corresponding to the maximum eigenvalue of the selected component signal and the second stage signal corresponding to the selected component signal is obtained, and the ratio of the time length to the maximum eigenvalue is normalized to obtain the second stage correction coefficient of the selected component signal in the short time window.

5. The intelligent detection method for deformation of a deep foundation pit of a pipe gallery according to claim 4 is characterized in that: The correcting the signal in the vibration propagation sequence by using the first-stage correction coefficient and the second-stage correction coefficient specifically includes: For any short-time window of any vibration signal; Obtain the time interval between the initial mutation point of each IMF component signal and the initial mutation point of the next adjacent IMF component signal in the vibration propagation sequence, and obtain the characteristic time length of each IMF component signal; Calculating the product of the mean value between the first-stage correction coefficient and the second-stage correction coefficient of each IMF component signal and the characteristic time length to obtain the moving time length of each IMF component signal; The initial mutation point of each IMF component signal corresponding to the vibration propagation sequence is shifted to the right by the shift time length to obtain a shift signal which is recorded as a modified propagation signal of each IMF component signal; A sequence composed of the corrected propagation signals of all IMF component signals within a short-time window is used as a corrected propagation sequence, and the corrected propagation sequence is a correction result.

6. The intelligent detection method for deformation of a deep foundation pit of a pipe gallery according to claim 5 is characterized in that: The method of obtaining the vibration source signal segment corresponding to each monitoring point based on the correction result and the similarity between the IMF component signals of each vibration signal in each short-time window specifically includes: The average phases corresponding to all IMF component signals in the short-time window are arranged in ascending order to form a propagation phase sequence; According to the time length between the vibration propagation signals of two adjacent IMF component signals in each short-time window, combined with the difference between the two adjacent average phases in the propagation phase sequence and the time series length of the vibration propagation sequence, the similarity index between each short-time window and the modified propagation sequence is obtained; According to the change of the similarity index between each short-time window of each vibration signal and the modified propagation sequence, the vibration source signal segment of the monitoring point corresponding to each vibration signal is obtained.

7. The intelligent detection method for deformation of a deep foundation pit of a pipe gallery according to claim 6 is characterized in that: The calculation formula of the similarity index between each short-term window and the modified propagation sequence is: in, It represents the similarity index between the u-th short-time window of any vibration signal and the modified propagation sequence, It represents the time interval between the initial mutation point of the i-th IMF component signal and the initial mutation point of the next adjacent IMF component signal in the modified propagation sequence within the u-th short-time window. Indicates the total number of IMF component signals contained in the short-time window, represents the time length of the modified propagation sequence, The absolute value of the average phase difference between the i-th IMF component signal and the adjacent next IMF component signal in the propagation phase sequence of the u-th short-time window of the vibration signal, that is, the phase delay, Represents the maximum value of all phase delays in the u-th short-time window of the vibration signal, represents the exponential function with the natural constant e as the base, is the normalization function.

8. The intelligent detection method for deformation of a deep foundation pit of a pipe gallery according to claim 6 is characterized in that: The step of obtaining the vibration source signal segment of the monitoring point corresponding to each vibration signal according to the change of the similarity index between each short-time window of each vibration signal and the modified propagation sequence specifically includes: For any vibration signal, calculate the first-order difference value of the similarity index corresponding to each short-time window in the vibration signal, and take the previous short-time window adjacent to the short-time window corresponding to the minimum value of all first-order difference values ​​as the first vibration source signal segment; According to the same method as the first vibration source signal segment, the mutation point is re-acquired within the short time window after the vibration source signal segment, and the second vibration source signal segment is determined. And so on, all vibration source signal segments corresponding to the monitoring points of the vibration signal are obtained.

9. An intelligent detection system for deformation of a deep foundation pit of a pipe gallery, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the computer program is executed by a processor, the steps of the intelligent detection method for deformation of a deep foundation pit of a pipe gallery as described in any one of claims 1 to 8 are implemented.

Images