A method and system for detecting and collecting TBM jacking section construction data

Abstract

This application relates to the field of data detection technology, and specifically relates to a method and system for detecting and collecting TBM empty-pushing section construction data. The method includes: collecting vibration signals during the construction of the TBM empty-pushing section; using a signal decomposition algorithm to obtain each IMF component and the residual term of the vibration signal; obtaining the periodic weight of each IMF component based on the low-frequency data and extreme value distribution of the IMF component; and then calculating the frequency domain characteristic factor of each IMF component; calculating the spike pulse coefficient of each IMF component; calculating the rock vibration deviation coefficient of each IMF component; and then obtaining the time domain characteristic factor of each IMF component; taking the sum of the frequency domain characteristic factor and the time domain characteristic factor as the rock vibration discrimination value of each IMF component, obtaining the denoised rock vibration signal, and detecting and collecting the TBM empty-pushing section construction data. This application improves the detection accuracy of TBM empty-pushing section construction data.

Description

Technical Field

[0001] The present application relates to the technical field of data detection, and particularly to a method and system for detecting and collecting TBM empty-push section construction data. Background Art

[0002] A tunnel boring machine (TBM) is a complete set of tunnel construction equipment integrating machinery, electricity, hydraulics, sensing, and information technologies. The TBM realizes continuous tunneling through the coordinated work of its rock-breaking mechanism, propulsion mechanism, and rock debris loading and transporting mechanism. During the TBM tunneling process, when encountering special geological changes, equipment maintenance, or construction adjustments, etc., empty-push operations are required. During the empty-push process, the propulsion mechanism of the TBM will work, but the rock-breaking mechanism is not in a working state.

[0003] During the TBM empty-push construction process, poor geological conditions will affect construction safety and propulsion efficiency. By detecting and collecting construction data in real time, the geological structure and equipment status can be understood in a timely manner to ensure the safety and stability of construction. During the process of detecting data, the seismic wave method is to arrange exciters on the heading face to emit vibration signals and use geophones to receive vibration signals, and the seismic wave method can be used for detection during the empty-push process. However, during the data detection process, the collected vibration signals will be interfered by various factors, such as construction vibration interference, strong electromagnetic fields, TBM equipment operation noise, etc., resulting in low-quality data obtained, which cannot meet the detection requirements and affects the accurate assessment of construction conditions. Summary of the Invention

[0004] In order to solve the above technical problems, the purpose of the present application is to provide a method and system for detecting and collecting TBM empty-push section construction data, and the specific technical solutions adopted are as follows:

[0005] In a first aspect, an embodiment of the present application provides a method for detecting and collecting TBM empty-push section construction data, and the method includes the following steps:

[0006] Collect vibration signals during the TBM empty-push section construction process;

[0007] Use a signal decomposition algorithm to obtain each IMF component and residual term of the vibration signal;

[0008] Obtain the periodic weight of each IMF component based on the low-frequency data and extreme value distribution of the IMF component;

[0009] Obtain the frequency domain characteristic factor of each IMF component based on the periodic weight, the discrete degree of the energy intensity of the frequency response of the IMF component, and the average situation of the frequency;

[0010] Obtain the spike pulse coefficient of each IMF component based on the distribution of elements near the extreme values in the IMF component;

[0011] Obtain the rock vibration deviation coefficient of each IMF component based on the correlation between the elements before and after in chronological order in the IMF component;

[0012] Obtain the time-domain characteristic factor of each IMF component based on the rock vibration deviation coefficient, spike pulse coefficient, and the degree of dispersion of extreme values in the IMF component;

[0013] Take the sum value of the frequency-domain characteristic factor and the time-domain characteristic factor as the rock vibration discrimination value of each IMF component, and combine it with the residual term to obtain the denoised rock vibration signal, and detect and collect the TBM jacking section construction data.

[0014] Furthermore, the method for obtaining the periodic weight is as follows:

[0015] Take each IMF component of the vibration signal as the input of the low-pass filter to obtain the low-frequency data of each IMF component;

[0016] Use the discrete Fourier transform to obtain the frequency response of the low-frequency data of each IMF component;

[0017] Use the peak detection algorithm to obtain the average period of each IMF component;

[0018] For each IMF component of the vibration signal, calculate the product of the maximum value of the energy intensity of the frequency response of the low-frequency data of the IMF component and the average period as the periodic weight of each IMF component.

[0019] Furthermore, the method for obtaining the average period is as follows:

[0020] Use the peak detection algorithm to obtain all the maximum points in each IMF component, and take the ratio of the duration of the IMF component to the total number of all maximum points in the IMF component as the average period of each IMF component.

[0021] Furthermore, the method for obtaining the frequency-domain characteristic factor is as follows:

[0022] Use the discrete Fourier transform to obtain the frequency response of each IMF component of the vibration signal;

[0023] The calculation formula of the frequency-domain characteristic factor is: ; where is the frequency-domain characteristic factor of the i-th IMF component; represents the variance of the energy intensity of all frequencies in the frequency response of the i-th IMF component; is the periodic weight of the i-th IMF component; It represents the mean value of all frequencies in the frequency response of the i-th IMF component.

[0024] Furthermore, the method for obtaining the spike pulse coefficient is as follows:

[0025] Based on the distribution of the maximum points in the IMF component, each rising interval and each falling interval in the IMF component are obtained;

[0026] The calculation formula for the spike pulse coefficient is as follows: ; In the formula, is the spike pulse coefficient of the i-th IMF component; is the range of all elements in the p-th rising interval of the i-th IMF component, represents the total number of elements in the p-th rising interval of the i-th IMF component, represents the range of all elements in the x-th falling interval of the i-th IMF component, is the total number of elements in the x-th falling interval of the i-th IMF component, m is the total number of rising intervals in the i-th IMF component, and n is the total number of falling intervals in the i-th IMF component.

[0027] Furthermore, the method for obtaining each rising interval and each falling interval is as follows:

[0028] For each IMF component of the vibration signal, for each maximum point in the IMF component, the interval composed of the IMF component data of a preset length before the maximum point is used as the rising interval, and the interval composed of the IMF component data of a preset length after the maximum point is used as the falling interval.

[0029] Furthermore, the method for obtaining the rock vibration deviation coefficient is as follows:

[0030] For each IMF component of the vibration signal, the sequence formed by arranging the first preset number of elements in the IMF component in the positive time order is used as the front-term sequence of each IMF component, and the sequence formed by arranging the other elements in the IMF component except those in the front-term sequence in the positive time order is used as the back-term sequence of each IMF component;

[0031] Calculate the DTW distance between the front-term sequence and the back-term sequence in each IMF component as the rock vibration deviation coefficient of each IMF component of the vibration signal.

[0032] Furthermore, the calculation formula for the time-domain characteristic factor is as follows: ; In the formula, is the time-domain characteristic factor of the i-th IMF component; represents the average value of the absolute values of all elements in the i-th IMF component; represents the variance of all maximum values in the i-th IMF component, It represents the variance of all minima in the \(i\)-th IMF component, which is the rock vibration deviation coefficient of the \(i\)-th IMF component, and is the spike pulse coefficient of the \(i\)-th IMF component.

[0033] Furthermore, the acquisition of the denoised rock vibration signal and the detection and collection of the TBM jacking section construction data include:

[0034] Taking the rock vibration discrimination values of all IMF components of the vibration signal as the input of the Otsu threshold segmentation algorithm to obtain the optimal segmentation threshold, and taking the IMF components corresponding to the rock vibration discrimination values greater than the optimal segmentation threshold as the IMF components of the rock vibration signal;

[0035] Superposing the IMF components and the residual term of the rock vibration signal to obtain the denoised rock vibration signal.

[0036] In a second aspect, an embodiment of the present application further provides a TBM jacking section construction data detection and collection system, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of the method described in any one of the above are implemented.

[0037] The present application has at least the following beneficial effects:

[0038] By decomposing the vibration signal containing noise through the EMD algorithm, the present application obtains several IMF components and a residual term. Then, by analyzing the frequency, energy concentration, and periodicity of the rock vibration signal, operating noise, mechanical vibration, and electromagnetic wave signal in the frequency domain, as well as the forward and backward correlation, amplitude size, smoothness, and waveform characteristics in the time domain, the rock vibration signal is screened out from several IMF components, removing the interference of noise, enabling the finally collected rock vibration signal to more accurately reflect the rock characteristics, enhancing the data quality, and improving the detection accuracy of the TBM jacking section construction data. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0040] Figure 1 It is a step flowchart of a method for detecting and collecting TBM jacking section construction data provided by an embodiment of the present application;

[0041] Figure 2 Flow chart for obtaining the rock vibration discrimination value provided by an embodiment of the present application. Specific implementation manners

[0042] In order to further elaborate on the technical means and effects adopted by the present application to achieve the intended invention purpose, the following will, in conjunction with the accompanying drawings and preferred embodiments, elaborate in detail on a method and system for detecting and collecting TBM empty-push section construction data proposed according to the present application, including its specific implementation manners, structures, features, and effects. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0043] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which this application belongs.

[0044] The following will specifically describe the specific solutions of a method and system for detecting and collecting TBM empty-push section construction data provided by the present application in conjunction with the accompanying drawings.

[0045] Please refer to Figure 1 , which shows a flow chart of the steps of a method for detecting and collecting TBM empty-push section construction data provided by an embodiment of the present application. The method includes the following steps:

[0046] Step S1, collect vibration signals during the construction of the TBM empty-push section.

[0047] When there is a fracture zone in the rock in front of the tunnel face, the rock in the fracture zone usually has more cracks, and these cracks will change the wave velocity propagation characteristics of the rock; when there is water flow in front of the tunnel face, there are also obvious differences in the wave velocity propagation characteristics between the water flow and the rock. Therefore, the wave velocity propagation characteristics of the vibration signal in the rock in front of the tunnel face can be used to detect whether there is a fracture zone or water flow in the rock.

[0048] Arrange a shaker in the borehole on the side wall of the tunnel face to emit vibration signals into the surrounding rock in front; arrange a geophone at a certain distance from the shaker in the borehole on the side wall of the tunnel to receive the vibration signals. Among them, the distance between the shaker and the geophone should be determined according to the propagation speed and attenuation characteristics of the vibration signal in the rock. Generally, the distance range between the geophone and the shaker is set between 40m and 80m. In this embodiment, the distance between the geophone and the shaker is set to 50m, and the implementer can select other values within the range according to the actual situation.

[0049] Step S2, use the signal decomposition algorithm to obtain each IMF component and the residual term of the vibration signal; obtain the periodic weight of each IMF component based on the low-frequency data and extreme value distribution of the IMF component; obtain the frequency domain characteristic factor of each IMF component based on the periodic weight, the discrete degree of the energy intensity of the frequency response of the IMF component, and the average situation of the frequency; obtain the spike pulse coefficient of each IMF component based on the distribution of the elements near the extreme value in the IMF component.

[0050] Since the geophone can not only receive vibration signals, but also receive sound waves and electromagnetic waves. In the construction tunnel, the operation of the TBM equipment will generate noise and vibration, and the electrical equipment inside the TBM will also generate electromagnetic waves. These factors will interfere with the acquisition of vibration signals by the geophone, making the collected vibration signals unable to accurately reflect the rock characteristics. Therefore, it is necessary to clean the collected data.

[0051] During the operation of the TBM equipment, operation noise, mechanical vibration and electromagnetic waves will be generated, and these signals exist all the time. Take the vibration signal collected by the geophone as the input of the empirical mode decomposition (EMD) algorithm, set the number of intrinsic mode functions (IMF) to s, and the value range of the termination threshold is 0.2 - 0.3, and output each IMF component of the vibration signal and a residual term. In this embodiment, the value of s is 20, and the implementer can select other values according to the actual situation.

[0052] Decompose the vibration signal into each IMF component through the EMD algorithm. Among them, each IMF component contains the local characteristic information of the vibration signal at different time scales. Among them, the empirical mode decomposition (EMD) algorithm is a well-known technology and will not be elaborated in this embodiment.

[0053] Furthermore, it is necessary to distinguish each IMF component to judge which IMF components may belong to the rock vibration signal. The operation noise mainly comes from the mechanical operation of the TBM equipment, such as the operation of the hydraulic system, ventilation equipment, etc. This kind of noise usually shows random fluctuations, there is no obvious correlation between the waveforms before and after, and the frequency is usually concentrated in the high frequency band (above 100 Hz), and the energy distribution is relatively dispersed; the mechanical vibration mainly comes from the impact of the cutter head, the load transfer of the propulsion system, and the vibration of the engine, etc. This kind of signal mainly propagates near the TBM equipment, so the amplitude of the mechanical vibration is relatively smaller than that of the rock vibration signal, the frequency is mainly concentrated in the low frequency band (below 20 Hz), and the energy distribution in the frequency domain is relatively concentrated; the electromagnetic wave signal mainly comes from the electrical system and cables of the TBM, and usually shows spike pulses or high-frequency oscillations, and the frequency is usually concentrated in the high frequency band (above 100 Hz).

[0054] The rock vibration signal is the signal emitted by the shaker to the rock, with a relatively large amplitude. It usually shows low-frequency (below 20 Hz), stable fluctuations, and the waveforms before and after are usually relatively consistent, with strong periodicity, and the energy distribution in the frequency domain is relatively concentrated and has a large intensity.

[0055] Taking each IMF component as the input of the low-pass filter respectively, the low-frequency data of each IMF component is obtained. In this embodiment, the cut-off frequency of the low-pass filter is set to 20 Hz. The principle of the low-pass filter is a well-known technology, and the specific process will not be elaborated here. Taking the low-frequency data of each IMF component as the input of the discrete Fourier transform (DFT) respectively, the frequency response of the low-frequency data of each IMF component is obtained. DFT is a well-known technology, and the specific process will not be elaborated here. Among them, the frequency response includes the energy intensity and frequency of the low-frequency data, which are well-known, and will not be elaborated in this embodiment.

[0056] Furthermore, the peak detection algorithm is used to obtain all the maximum points in each IMF component. The ratio of the duration of the IMF component to the total number of all the maximum points in the IMF component is used as the average period of each IMF component. Among them, the peak detection algorithm is a well-known technology, and will not be elaborated in this embodiment.

[0057] Based on the above analysis, in order to reflect the periodic strength of the low-frequency data of each IMF component, based on the distribution of the maximum values of each IMF component and the energy intensity of the low-frequency data of the IMF component, the periodic weight of each IMF component is obtained. The calculation formula is: ; In the formula, is the periodic weight of the i-th IMF component; is the average period of the i-th IMF component, represents the maximum value of the energy intensity in the frequency response of the low-frequency data of the i-th IMF component.

[0058] It should be noted that for each IMF component of the vibration signal, when the average period of the IMF component is longer and the maximum value of the energy intensity of the frequency response of the low-frequency data of the IMF is larger, it is more in line with the characteristics of the rock vibration signal. At this time, the obtained periodic weight has a larger value, indicating that the low-frequency data of the i-th IMF component has strong periodicity; on the contrary, when the characteristics of the IMF component are less in line with the characteristics of the rock vibration signal, the obtained periodic weight has a smaller value.

[0059] Furthermore, taking each IMF component of the vibration signal as the input of the discrete Fourier transform algorithm respectively, the frequency response of each IMF component of the vibration signal is obtained.

[0060] Further, in order to reflect the similarity between the frequency domain characteristics of each IMF component and those of the rock vibration signal, based on the degree of dispersion of the frequency response of the low-frequency data of the IMF component, the periodic weight, and the average of the frequencies of the frequency response of the IMF component, the frequency domain characteristic factor of each IMF component is obtained, and the calculation formula is: ; In the formula, is the frequency domain characteristic factor of the i-th IMF component; represents the variance of the energy intensity of all frequencies in the frequency response of the i-th IMF component; is the periodic weight of the i-th IMF component; represents the mean of all frequencies in the frequency response of the i-th IMF component.

[0061] It should be noted that for each IMF component, when the energy distribution of the frequency response of the low-frequency data of the IMF component is relatively concentrated, the energy will be concentrated in some frequency components, resulting in a situation where the energy of some frequency components is very large and the energy of some frequency components is very small. At this time, the variance of the energy intensity of all frequencies in the frequency response of the low-frequency data of the obtained IMF component is larger; when the periodicity of the IMF component is stronger, it indicates that the frequency domain characteristics of the IMF component are more in line with the characteristics of the rock vibration signal, and at this time, the value of the obtained periodic weight is larger; when there are more low-frequency components in the frequency domain of the IMF energy, it is more in line with the frequency domain characteristics of the rock vibration signal, the smaller the value of

[0062] the larger the value of the frequency domain characteristic factor of the obtained IMF component; on the contrary, the value of the frequency domain characteristic factor of the obtained IMF component is smaller.

[0063] Further, for each IMF component of the vibration signal, the extreme point detection algorithm is used to obtain each maximum value and each minimum value in the IMF component. For each maximum value point in the IMF component, the interval composed of the IMF component data with a preset length before the maximum value point is used as the rising interval, and the interval composed of the IMF component data with a preset length after the maximum value point is used as the falling interval; among them, the extreme point detection algorithm is a well-known technology, and this embodiment will not be elaborated. In this embodiment, the value of the preset length is 3, and the implementer can select other values according to the actual situation. ; In the formula, is the spike pulse coefficient of the i-th IMF component; is the range of all elements in the p-th rising interval of the i-th IMF component, represents the total number of elements in the p-th rising interval of the i-th IMF component, To represent the range of all elements in the x-th descending interval of the i-th IMF component, is the total number of elements in the x-th descending interval of the i-th IMF component, m is the total number of ascending intervals in the i-th IMF component, and n is the total number of descending intervals in the i-th IMF component.

[0064] It should be noted that The larger the value of, the steeper the p-th ascending interval of the i-th IMF component, and the more likely this ascending interval is the rising edge of a spike pulse; The larger the value of, the steeper the x-th descending interval of the i-th IMF component, and then the more likely this descending interval is the falling edge of a spike pulse.

[0065] Step S3: Obtain the rock vibration deviation coefficient of each IMF component based on the correlation between the elements before and after in the IMF component in chronological order; based on the rock vibration deviation coefficient, spike pulse coefficient, and the degree of dispersion of the extreme values in the IMF component, obtain the time-domain characteristic factor of each IMF component; take the sum value of the frequency-domain characteristic factor and the time-domain characteristic factor as the rock vibration discrimination value of each IMF component.

[0066] Furthermore, for each IMF component of the vibration signal, the sequence composed of the first preset number of elements in the IMF component in positive time order is used as the front-term sequence of each IMF component, and the sequence composed of the other elements in the IMF component except those in the front-term sequence in positive time order is used as the back-term sequence of each IMF component. In this embodiment, the value of the preset number is , where j is the total number of elements in the IMF component, is the rounding function, and the implementer can select other values according to the actual situation; calculate the DTW distance between the front-term sequence and the back-term sequence in each IMF component as the rock vibration deviation coefficient of each IMF component of the vibration signal.

[0067] Specifically, when the value of the rock vibration deviation coefficient is larger, the correlation between the waveform of the first half and the waveform of the second half of the IMF component of the vibration signal is smaller, and it is less in line with the characteristics of the rock vibration signal; on the contrary, when the value of the rock vibration deviation coefficient is smaller, the characteristics of the IMF component of the vibration signal are more in line with the characteristics of the rock vibration signal.

[0068] Furthermore, in order to reflect the similarity degree between the time-domain characteristics of the IMF component of the vibration signal and the time-domain characteristics of the rock vibration signal, based on the spike pulse coefficient, rock vibration deviation coefficient, and the average and dispersion of the elements in the IMF component, obtain the time-domain characteristic factor of each IMF component of the vibration signal, and the calculation formula is: ; in the formula, is the time-domain characteristic factor of the i-th IMF component; represents the average value of the absolute values of all elements in the \(i\)-th IMF component; represents the variance of all maxima in the \(i\)-th IMF component, represents the variance of all minima in the \(i\)-th IMF component, is the rock vibration deviation coefficient of the \(i\)-th IMF component, is the spike pulse coefficient of the \(i\)-th IMF component.

[0069] It should be noted that, the larger the value of \(\cdots\), the larger the amplitude of the \(i\)-th IMF component, and the more likely the \(i\)-th IMF component is a rock vibration signal; the smaller the value of \(\cdots\), the smoother the waveform of the \(i\)-th IMF component, and the more likely the \(i\)-th IMF component is a rock vibration signal; the smaller the value of the rock vibration deviation coefficient, the stronger the correlation between the waveform before and after the \(i\)-th IMF component, indicating that the \(i\)-th IMF component is more likely to be a rock vibration signal; the smaller the value of \(\cdots\), the less the waveform of the \(i\)-th IMF component is a spike pulse, and the more likely the \(i\)-th IMF component is a rock vibration signal.

[0070] Furthermore, according to the frequency-domain characteristic factor and time-domain characteristic factor of the \(i\)-th IMF component, a rock vibration discrimination value is constructed to characterize the possibility that the \(i\)-th IMF component belongs to a rock vibration signal. The calculation formula is: ; where, is the rock vibration discrimination value of the \(i\)-th IMF component; is the frequency-domain characteristic factor of the \(i\)-th IMF component; is the time-domain characteristic factor of the \(i\)-th IMF component. Among them, the flowchart for obtaining the rock vibration discrimination value is as shown in Figure 2 shown.

[0071] It should be noted that when the IMF component of the vibration signal is more likely to be a rock vibration signal, the IMF component of the vibration signal conforms to the characteristics of the rock vibration signal both in the time domain and the frequency domain. At this time, the values of the frequency-domain characteristic factor and the time-domain characteristic factor obtained are larger, that is, the rock vibration discrimination value is larger; on the contrary, the obtained rock vibration discrimination value is smaller.

[0072] Calculate the rock vibration discrimination value of each IMF component, use all the rock vibration discrimination values as the input of the Otsu threshold segmentation algorithm to obtain the optimal segmentation threshold, and use the IMF components corresponding to the rock vibration discrimination values greater than the optimal segmentation threshold as the IMF components of the rock vibration signal.

[0073] So far, the IMF components belonging to the rock vibration signal have been obtained.

[0074] Step S4: Obtain the denoised rock vibration signal by combining the residual term, and detect and collect the construction data of the TBM jacking section.

[0075] Further, superimpose the IMF components belonging to the rock vibration signal and the residual term to obtain the denoised rock vibration signal, obtain a more accurate rock vibration signal, and complete the detection and collection of the construction data of the TBM jacking section.

[0076] Based on the same inventive concept as the above method, an embodiment of the present application further provides a detection and collection system for TBM jacking section construction data, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of any one of the above methods for detecting and collecting TBM jacking section construction data are implemented.

[0077] It should be noted that the above sequence of embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above describes specific embodiments of this specification. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0078] Each embodiment in the present application is described in a progressive manner. The same or similar parts between the embodiments can be referred to each other, and the key points of each embodiment are the differences from other embodiments.

[0079] The above are only the preferred embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for detecting and collecting TBM air inference surface construction data, characterized in that: The method comprises the following steps: Collect vibration signals during TBM air-to-air surface construction; Use signal decomposition algorithm to obtain the IMF components and residual terms of the vibration signal; Based on the low-frequency data and extreme value distribution of IMF components, the periodic weights of each IMF component are obtained; Based on the periodic weight, the discrete degree of the energy intensity of the frequency response of the IMF component and the average frequency, the frequency domain characteristic factor of each IMF component is obtained; Obtain the peak pulse coefficient of each IMF component based on the distribution of elements near the extreme value in the IMF component; The IMF components are divided to obtain the front sequence and the back sequence of the IMF components; based on the correlation between the front sequence and the back sequence of the IMF components, the rock vibration deviation coefficient of the IMF components is obtained, wherein the larger the value of the rock vibration deviation coefficient is, the smaller the correlation between the front sequence and the back sequence is; Based on the rock vibration deviation coefficient, peak pulse coefficient and the degree of dispersion of the extreme values ​​in the IMF components, the time domain characteristic factors of each IMF component are obtained; The sum of the frequency domain characteristic factor and the time domain characteristic factor is used as the rock vibration discrimination value of each IMF component, and the denoised rock vibration signal is obtained by combining the residual term to detect and collect the TBM air-inferred surface construction data. The method for obtaining the periodic weight is: Each IMF component of the vibration signal is used as the input of a low-pass filter to obtain low-frequency data of each IMF component; Use discrete Fourier transform to obtain the frequency response of low-frequency data of each IMF component; Use the peak detection algorithm to obtain the average period of each IMF component; For each IMF component of the vibration signal, the product of the maximum value of the energy intensity of the frequency response of the low-frequency data of the IMF component and the average period is calculated as the periodicity weight of each IMF component; The method for obtaining the average period is: Use the peak detection algorithm to obtain all the maximum points in each IMF component, and take the ratio of the duration of the IMF component to the total number of all the maximum points in the IMF component as the average period of each IMF component; The method for obtaining the frequency domain characteristic factor is: Use discrete Fourier transform to obtain the frequency response of each IMF component of the vibration signal; The calculation formula of the frequency characteristic factor is: ; In the formula, is the frequency domain characteristic factor of the i-th IMF component; represents the variance of the energy intensity of all frequencies in the frequency response of the i-th IMF component; is the cyclical weight of the ith IMF component; represents the mean of all frequencies in the frequency response of the i-th IMF component; The method for obtaining the peak pulse coefficient is: Based on the distribution of the maximum value points in the IMF components, each rising interval and each falling interval in the IMF components are obtained; The calculation formula of the peak pulse coefficient is: ; In the formula, is the peak impulse coefficient of the i-th IMF component; is the range of all elements in the pth rising interval of the ith IMF component, represents the total number of elements in the pth rising interval of the i-th IMF component, represents the range of all elements in the xth descending interval of the ith IMF component, is the total number of elements in the xth descending interval in the ith IMF component, m is the total number of ascending intervals in the ith IMF component, and n is the total number of descending intervals in the ith IMF component; The calculation formula of the time domain characteristic factor is: ; In the formula, is the time domain characteristic factor of the i-th IMF component; represents the average of the absolute values ​​of all elements in the i-th IMF component; represents the variance of all maxima in the i-th IMF component, represents the variance of all minima in the ith IMF component, is the rock vibration deviation coefficient of the i-th IMF component, is the peak impulse coefficient of the i-th IMF component.

2. A TBM air inference surface construction data detection and collection method as claimed in claim 1, characterized in that: The method for obtaining each ascending interval and each descending interval is: For each IMF component of the vibration signal and each maximum point in the IMF component, the interval consisting of the IMF component data of a preset length before the maximum point is used as the rising interval, and the interval consisting of the IMF component data of a preset length after the maximum point is used as the falling interval.

3. A TBM air inference surface construction data detection and collection method as claimed in claim 1, characterized in that: The method for obtaining the rock vibration deviation coefficient is: For each IMF component of the vibration signal, a sequence consisting of the first preset number of elements in the IMF component in positive time order is used as the preceding sequence of each IMF component, and a sequence consisting of the other elements in the IMF component except the preceding sequence in positive time order is used as the succeeding sequence of each IMF component; The DTW distance between the preceding sequence and the succeeding sequence in each IMF component is calculated as the rock vibration deviation coefficient of each IMF component of the vibration signal.

4. A TBM air inference surface construction data detection and collection method as claimed in claim 1, characterized in that: The method of obtaining the denoised rock vibration signal and detecting and collecting TBM air-inferred surface construction data includes: The rock vibration discrimination values ​​of all IMF components of the vibration signal are used as the input of the Otsu threshold segmentation algorithm to obtain the optimal segmentation threshold, and the IMF components corresponding to the rock vibration discrimination values ​​greater than the optimal segmentation threshold are used as the IMF components of the rock vibration signal; The IMF component and residual term of the rock vibration signal are superimposed to obtain the denoised rock vibration signal.

5. A TBM empty inference surface construction data detection and collection system, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of a TBM empty inference surface construction data detection and collection method as described in any one of claims 1-4 are implemented.

Images