Duct piece wall back grouting disease detection method, device and system, shield tunneling machine and medium

Abstract

The invention relates to a segment wall back grouting disease detection method, device and system, a shield tunneling machine and a medium. The segment wall post-grouting disease detection method comprises the following steps: acquiring a ground penetrating radar signal of segment wall post-grouting; performing signal processing on the ground penetrating radar signal; and carrying out target detection on the ground penetrating radar signal after signal processing, and identifying and positioning the grouting damage behind the duct piece wall. According to the invention, ground penetrating radar signals can be automatically processed, and segment wall back grouting diseases can be automatically identified and positioned.

Description

Technical Field

[0001] The present invention relates to the technical field of tunnel construction, and in particular to a method, device and system for detecting defects of post-grouting of a segment wall, a shield machine and a medium. Background Art

[0002] During the tunnel construction process of the shield machine, since the diameter of the cutter head is larger than the outer diameter of the segment, an annular gap will be formed between the segment and the soil. If this gap is not filled in time, or if there are defects such as voids, looseness, and insufficient interlayer bonding after filling, it may cause ground deformation, resulting in subsidence of the surface or sinking of the building. Summary of the invention

[0003] Through research, the inventors found that some related technologies have already appeared to detect grouting defects behind the segment wall using sound waves or ground penetrating radar, but the sound wave method of the related technology cannot accurately locate the grouting defects behind the segment wall, and the ground penetrating radar segment wall grouting defect detection technology of the related technology also requires a large number of professional and technical personnel to perform manual identification.

[0004] In view of at least one of the above technical problems, the present disclosure provides a method, device and system for detecting post-grouting defects in the segment wall, a shield machine and a medium, which can automatically process ground penetrating radar signals and automatically identify and locate post-grouting defects in the segment wall.

[0005] According to one aspect of the present disclosure, a method for detecting segment wall post-grouting defects is provided, comprising:

[0006] Acquire a ground penetrating radar signal, wherein the ground penetrating radar signal is a ground penetrating radar signal of a segment wall post-grouting position collected by the ground penetrating radar after the segment wall post-grouting;

[0007] performing signal processing on the ground penetrating radar signal;

[0008] The ground penetrating radar signal after signal processing is used for target detection, and the grouting defects behind the segment wall are identified and located.

[0009] In some embodiments of the present disclosure, the performing of target detection on the ground penetrating radar signal after signal processing and identifying and locating the grouting defect behind the segment wall includes:

[0010] The ground penetrating radar signal after signal processing is subjected to target detection to determine the type, confidence level and location of the grouting defect behind the segment wall.

[0011] In some embodiments of the present disclosure, the ground penetrating radar signal is a ground penetrating radar image, and the target detection is performed on the ground penetrating radar signal after signal processing to identify and locate the segment wall back grouting disease.

[0012] Adjusting the ground penetrating radar image after signal processing to an image of a first predetermined size;

[0013] Target detection is performed on the image of the first predetermined size to determine the type, confidence level and location of the post-grouting defect on the segment wall.

[0014] In some embodiments of the present disclosure, performing target detection on the image of the first predetermined size to determine the type, confidence level and location of the segment wall post-grouting defect includes:

[0015] Determine the type and confidence level of segment wall post-grouting defects;

[0016] Filter out the segment wall post-grouting defects with confidence values ​​lower than a predetermined confidence value threshold;

[0017] splicing a plurality of output images of the first predetermined size to restore the images to their original size;

[0018] Calculating the pixel position of the segment wall post-grouting defect in the original image;

[0019] According to the pixel position of the segment wall post-grouting defect in the original image, the actual position of the segment wall post-grouting defect is determined.

[0020] In some embodiments of the present disclosure, determining the actual position of the segment wall post-grouting defect according to the pixel position of the segment wall post-grouting defect in the original image includes:

[0021] The actual position of the segment wall post-grouting defect is determined based on the lateral pixel coordinates of the segment wall post-grouting defect in the original image, the lateral pixel length of the original image, the original image position and the conversion coefficient of the actual position.

[0022] In some embodiments of the present disclosure, the conversion factor is determined according to the radar scanning angle and the horizontal pixel length of the original image.

[0023] In some embodiments of the present disclosure, the segment wall post-grouting defects include at least one of voids, water-richness, and looseness.

[0024] In some embodiments of the present disclosure, the signal processing of the ground penetrating radar signal includes:

[0025] The ground penetrating radar signal is subjected to at least one of zero-time correction, DC drift removal, bandpass filtering, background elimination and gain processing.

[0026] In some embodiments of the present disclosure, performing zero-time correction on the ground penetrating radar signal includes:

[0027] Select a single-channel scanning signal in the original ground penetrating radar signal;

[0028] Cut off the data at the position with the maximum absolute value in the single-channel scanning signal data;

[0029] Each single-channel scanning signal data in the original ground penetrating radar signal is truncated at the data truncation position of the single-channel scanning signal, and the data after the truncation position is retained.

[0030] In some embodiments of the present disclosure, removing DC drift from the ground penetrating radar signal includes:

[0031] Calculate the average value of each single-channel scanning signal in the original ground penetrating radar signal;

[0032] For each single-channel scanning signal, the average value of the single-channel scanning signal is subtracted from each data of the single-channel scanning signal.

[0033] In some embodiments of the present disclosure, bandpass filtering the ground penetrating radar signal includes:

[0034] The original ground penetrating radar signal is bandpass filtered, wherein the first threshold of the bandpass filter is set to 0.4 times the center frequency of the radar antenna, and the second threshold of the bandpass filter is set to 1.2 times the center frequency of the radar antenna.

[0035] In some embodiments of the present disclosure, performing background elimination on the ground penetrating radar signal includes:

[0036] Calculate the average value of each row of data in the two-dimensional profile image of the original ground penetrating radar signal to form a column of pixels;

[0037] Subtract the pixels in each column from the data in the 2D cross-section image.

[0038] In some embodiments of the present disclosure, the step of amplifying the ground penetrating radar signal comprises:

[0039] Perform segmented gain or automatic gain on the raw GPR signal.

[0040] In some embodiments of the present disclosure, automatically gaining the ground penetrating radar signal includes:

[0041] An automatic gain control is performed on the ground penetrating radar signal.

[0042] In some embodiments of the present disclosure, automatically gaining the ground penetrating radar signal includes:

[0043] Energy gain is performed on the ground penetrating radar signal.

[0044] In some embodiments of the present disclosure, performing segmented gain on the ground penetrating radar signal includes:

[0045] The number of segments of the segment gain is set to 6 to 8.

[0046] According to another aspect of the present disclosure, a segment wall post-grouting defect detection device is provided, comprising:

[0047] A signal acquisition module is configured to acquire a ground penetrating radar signal, wherein the ground penetrating radar signal is a ground penetrating radar signal of a segment wall post-grouting position collected by the ground penetrating radar after the segment wall post-grouting;

[0048] A signal processing module, configured to perform signal processing on the ground penetrating radar signal;

[0049] The detection and positioning module is configured to perform target detection on the ground penetrating radar signal after signal processing, and to identify and locate the grouting defects behind the pipe segment wall.

[0050] According to another aspect of the present disclosure, a segment wall post-grouting defect detection device is provided, comprising:

[0051] a memory configured to store instructions;

[0052] The processor is configured to execute the instructions so that the segment wall post-grouting defect detection device implements the segment wall post-grouting defect detection method as described in any of the above embodiments.

[0053] According to another aspect of the present disclosure, a segment wall post-grouting defect detection system is provided, comprising a ground penetrating radar and a segment wall post-grouting defect detection device as described in any of the above embodiments.

[0054] According to another aspect of the present disclosure, a shield machine is provided, comprising a segment wall post-grouting defect detection system as described in any of the above embodiments.

[0055] According to another aspect of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and when the instructions are executed by a processor, the method for detecting segment wall post-grouting defects as described in any of the above embodiments is implemented.

[0056] According to another aspect of the present disclosure, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the method for detecting segment wall post-grouting defects as described in any of the above embodiments is implemented.

[0057] The present invention can automatically process ground penetrating radar signals and automatically identify and locate segment wall back-grouting defects. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0059] Figure 1 Schematic diagrams of some embodiments of the segment wall post-grouting defect detection method disclosed in the present invention.

[0060] Figure 2 Schematic diagrams of some embodiments of the segment wall post-grouting defect detection device disclosed in the present invention.

[0061] Figure 3 Schematic diagram of the structure of other embodiments of the segment wall post-grouting defect detection device disclosed in the present invention.

[0062] Figure 4 Schematic diagrams of some embodiments of the segment wall post-grouting defect detection system disclosed in the present invention. DETAILED DESCRIPTION

[0063] The technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all of the embodiments. The following description of at least one exemplary embodiment is actually only illustrative and is by no means intended to limit the present disclosure and its application or use. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0064] Unless specifically stated otherwise, the relative arrangement of components and steps, the numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present disclosure.

[0065] At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.

[0066] Technologies, methods, and apparatus known to ordinary technicians in the relevant field may not be discussed in detail, but where appropriate, such technologies, methods, and apparatus should be considered part of the authorization specification.

[0067] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limiting. Therefore, other examples of the exemplary embodiments may have different values.

[0068] It should be noted that like reference numerals and letters refer to similar items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0069] Through research, the inventors found that the methods of detecting grouting defects behind the segment wall using sound waves or ground penetrating radar in related technologies have certain technical problems. For example, the sound wave method cannot accurately locate the grouting defects behind the segment wall, and the ground penetrating radar grouting defect detection technology behind the segment wall in related technologies also requires a large number of professional and technical personnel to perform manual processing and identification.

[0070] In view of at least one of the above technical problems, the present disclosure provides a method, device and system for detecting segment wall back grouting defects, a shield machine and a medium, and uses a ground penetrating radar to design a method that can automatically process ground penetrating radar signals and automatically identify and locate segment wall back grouting defects. The present disclosure is described below through specific embodiments.

[0071] Figure 1 Schematic diagram of some embodiments of the segment wall post-grouting defect detection method disclosed in the present invention. Preferably, this embodiment can be performed by the segment wall post-grouting defect detection device disclosed in the present invention or the segment wall post-grouting defect detection system disclosed in the present invention. Figure 1 As shown, Figure 1 The method of the embodiment may include at least one of steps 1 to 3.

[0072] Step 1, obtaining a ground penetrating radar signal, wherein the ground penetrating radar signal is a ground penetrating radar signal of a segment wall post-grouting position collected by the ground penetrating radar after the segment wall post-grouting.

[0073] In some embodiments of the present disclosure, the ground penetrating radar signal is a ground penetrating radar signal obtained by detecting the back grouting position of the segment wall using a ground penetrating radar after the segment wall is back grouted.

[0074] In some embodiments of the present disclosure, step 1 may include: receiving a ground penetrating radar signal after grouting of the segment wall collected by the ground penetrating radar.

[0075] In some embodiments of the present disclosure, the ground penetrating radar signal is a ground penetrating radar image.

[0076] Step 2: performing signal processing on the ground penetrating radar signal.

[0077] In some embodiments of the present disclosure, step 2 may include: performing at least one of signal processing such as zero-time correction, DC drift removal, bandpass filtering, background elimination and gain on the ground penetrating radar signal.

[0078] In some embodiments of the present disclosure, step 2 may include at least one step from step 21 to step 25, and the order of step 21 to step 25 may be adjusted.

[0079] Step 21, performing zero-time correction on the original ground penetrating radar signal.

[0080] In some embodiments of the present disclosure, step 21 may include: selecting a single-channel scanning signal in the original ground-penetrating radar signal; truncating the data of the single-channel scanning signal at the position where the absolute value is the largest; truncating each single-channel scanning signal data in the original ground-penetrating radar signal at the position where the data of the single-channel scanning signal is truncated, and retaining the data after the truncation position.

[0081] In some embodiments of the present disclosure, the single-channel scanning signal is an A-Scan signal.

[0082] In some embodiments of the present disclosure, A-SCAN (Amplitude Scan) mainly acquires the reflection signal of a single measuring point.

[0083] In some embodiments of the present disclosure, A-SCAN processes the transmitted electromagnetic wave signal and the received reflected signal to form a one-dimensional waveform image. This scanning method is mainly used to obtain the reflection information of a single measuring point to help determine whether there are anomalies or defects underground, as well as their location and size. The signal processing of A-SCAN includes filtering and denoising the received signal, and finally obtaining a waveform graph in the time domain.

[0084] In some embodiments of the present disclosure, step 21 may include: selecting an A-Scan signal in the ground penetrating radar signal, obtaining the position with the largest absolute value in the A-Scan data and truncating it, and each A-Scan data in the ground penetrating radar signal is truncated at the position where the data of this A-Scan is truncated, and retaining the data after this position.

[0085] The zero-time correction of the above-mentioned embodiment of the present disclosure can make the starting position of the data consistent with the starting position of the actual detection.

[0086] Step 22, removing DC drift from the original ground penetrating radar signal.

[0087] In some embodiments of the present disclosure, step 22 may include: calculating the average value of each single-channel scanning signal in the original ground penetrating radar signal; for each single-channel scanning signal, subtracting the average value of the single-channel scanning signal from each data of the single-channel scanning signal.

[0088] In some embodiments of the present disclosure, step 22 may include: calculating an average value of each A-Scan signal, and then subtracting the average value of the A-Scan from each data of the A-Scan.

[0089] The inventors have discovered through research that due to the coupling effect and different signal saturation levels, the initial signal components and low-frequency signals of the radar wave will cause the average value of the single-channel data amplitude to deviate from the zero line. The above-mentioned embodiment of the present disclosure uses a DC drift removal method to solve this technical problem.

[0090] Step 23, bandpass filtering the original ground penetrating radar signal.

[0091] In some embodiments of the present disclosure, step 23 may include: selecting a bandpass filter such as a Butterworth filter to perform bandpass filtering on the original ground penetrating radar signal.

[0092] In some embodiments of the present disclosure, the first threshold of the bandpass filter is set to 0.4 times the center frequency of the radar antenna, and the second threshold of the bandpass filter is set to 1.2 times the center frequency of the radar antenna, wherein the second threshold is higher than the first threshold.

[0093] In some embodiments of the present disclosure, the first threshold may be a low frequency threshold, and the second threshold may be a high frequency threshold.

[0094] In some embodiments of the present disclosure, the first threshold and the second threshold may be determined according to the on-site filtering quality.

[0095] The bandpass filtering of the above-mentioned embodiment of the present disclosure can improve the signal-to-noise ratio by filtering out signal components in the data whose frequencies exceed the main working frequency bandwidth of the adopted ground penetrating radar system.

[0096] Step 24, performing background elimination on the original ground penetrating radar signal.

[0097] In some embodiments of the present disclosure, step 24 may include: calculating the average value of each row of data in the two-dimensional profile image of the original ground penetrating radar signal to form a column of pixels; and subtracting the column of pixels from each column of data in the two-dimensional profile image.

[0098] In some embodiments of the present disclosure, the two-dimensional cross-sectional image is a B-SCAN signal.

[0099] In some embodiments of the present disclosure, B-SCAN (Brightness Scan) combines multiple A-SCAN signals into a two-dimensional image to provide more comprehensive underground structure information.

[0100] In some embodiments of the present disclosure, the B-SCAN signal is a combination of multiple A-SCAN signals arranged at a certain distance into a two-dimensional image. This scanning method can reflect the cross-sectional conditions of underground structures and is suitable for observing underground static structures. The signal processing of B-SCAN includes arranging multiple A-SCAN signals according to horizontal distance and depth to form a two-dimensional image, thereby providing more comprehensive underground structure information.

[0101] In some embodiments of the present disclosure, step 24 may include: calculating the average value of RGB pixels in each row of the B-SCAN image, and then subtracting the column from each column of data in the B-SCAN image, as shown in formula (1).

[0102] (1)

[0103] In formula (1), , is the signal before and after processing, is the column number of the sample, is the number of columns of the B-SCAN image.

[0104] The background elimination of the above-mentioned embodiment of the present disclosure can effectively eliminate the consistent noise in the entire profile, highlight the target signal, and suppress the energy with consistent level.

[0105] Step 25, amplify the original ground penetrating radar signal.

[0106] In some embodiments of the present disclosure, step 25 may include: selecting to perform segmented gain or automatic gain on the original ground penetrating radar signal.

[0107] In some embodiments of the present disclosure, in step 25, the step of automatically gaining the ground penetrating radar signal may include: performing automatic gain control (AGC) on the ground penetrating radar signal.

[0108] In some other embodiments of the present disclosure, in step 25, automatically gaining the ground penetrating radar signal includes: performing energy gain on the ground penetrating radar signal.

[0109] In some embodiments of the present disclosure, in step 25, the step of performing segmented gain on the ground penetrating radar signal may include: setting the number of segments of the segmented gain to 6 to 8.

[0110] In some embodiments of the present disclosure, the specific type of automatic gain or the number of segments of segmented gain may be determined according to the quality of field data collection.

[0111] The inventors have found through research that due to the dispersion characteristics and propagation loss of electromagnetic waves, the GPR signal will generally attenuate during the propagation of radar waves on the road surface, making it difficult to detect defect targets deep in the structure, affecting the defect identification results. Therefore, the above embodiments of the present disclosure enhance the signal strength at the target by performing gain processing on the signal.

[0112] In some embodiments of the present disclosure, step 2 may include at least one of steps 201 to 203 .

[0113] Step 201, performing at least one of zero-time correction, DC offset removal and bandpass filtering on a single-channel scanning signal (A-SCAN signal) in an original ground penetrating radar signal.

[0114] In some embodiments of the present disclosure, step 201 may include at least one of steps 21 to 23.

[0115] Step 202 , stitching the processed single-channel scanning signals into a two-dimensional cross-sectional image (B-SCAN signal).

[0116] Step 203: performing at least one of background elimination and gain signal processing on the two-dimensional cross-sectional image (B-SCAN signal).

[0117] In some embodiments of the present disclosure, step 203 may include at least one of steps 24 to 25.

[0118] Step 3: Target detection is performed on the ground penetrating radar signal after signal processing, and the grouting defects behind the segment wall are identified and located.

[0119] In some embodiments of the present disclosure, the ground penetrating radar signal after signal processing is a picture after signal processing.

[0120] In some embodiments of the present disclosure, step 3 may include: training a target detection model; inputting the processed ground penetrating radar signal into the trained target detection model to perform target detection, and identify and locate the post-grouting defects on the segment wall.

[0121] In some embodiments of the present disclosure, step 3 may include: inputting the ground penetrating radar image with marked defects into the YOLOV8 model for training to obtain a trained model; during the process of model deployment and use, inputting the ground penetrating radar image into the model, and the model will automatically output the disease type, confidence level and location of the disease in the image; and then calibrating the image coordinates using the image lateral coordinate length and the actual radar detection range.

[0122] In some embodiments of the present disclosure, the target detection model is a YOLOv8 model.

[0123] In some embodiments of the present disclosure, the step of training the target detection model may include: when training the YOLOv8 model, adjusting the image pixel size to 448×448; setting the Batch-size to 16, where Batch-size refers to the number of samples used in each iteration during the model training process; setting Epochs to 500, where Epoch means that all training data sets are trained once, and is defined as a single training iteration of all batches in forward and backward propagation, and epochs refers to the number of times all training data are trained during the training process; using a cosine learning rate scheduler to dynamically adjust the learning rate, and to prevent the model from overfitting, setting the number of early stopping waiting rounds to 100, and training the YOLOv8 model.

[0124] In some embodiments of the present disclosure, the segment wall post-grouting defects include at least one of grouting defects such as voids, water abundance, insufficient interlayer bonding, and looseness.

[0125] In some embodiments of the present disclosure, voids are a type of grouting hazard, which refers to the formation of voids in the lining (concrete) due to soil leakage, insufficient grouting, etc. during grouting.

[0126] In some embodiments of the present disclosure, water-rich refers to a post-grouting defect of the segment wall in which water accumulates in the cavity due to groundwater leakage.

[0127] In some embodiments of the present disclosure, the non-compactness is caused by soil leakage or unsaturated grouting, resulting in the formation of a honeycomb structure on the lining and a non-compacted segment wall post-grouting disease.

[0128] In some embodiments of the present disclosure, step 3 may include: performing target detection on the ground penetrating radar signal after signal processing to determine the type, confidence level and location of the segment wall post-grouting defect.

[0129] In some embodiments of the present disclosure, step 3 may include at least one of steps 31 to 32.

[0130] Step 31: adjust the ground penetrating radar image after signal processing to an image of a first predetermined size.

[0131] In some embodiments of the present disclosure, the first predetermined size is 448×448.

[0132] Step 32, performing target detection on the image of the first predetermined size to determine the type, confidence level and location of the post-grouting defect on the segment wall.

[0133] In some embodiments of the present disclosure, step 31 and step 32 may include: after the data is signal processed, the data pixel size is adjusted to 448×448, and sent to the trained YOLOv8 model for target detection. The model outputs output data such as grouting defects, confidence of grouting defects, and the position of grouting defects in image pixels.

[0134] In some embodiments of the present disclosure, the position of the grouting defect in the image pixel may be the lateral pixel coordinate of the grouting defect in the B-Scan radar image.

[0135] In some embodiments of the present disclosure, step 32 may include at least one of steps 321 to 325, and the order of steps 321 to 325 may be adjusted.

[0136] Step 321, determine the type and confidence level of the segment wall post-grouting defect.

[0137] Step 322, filtering out the segment wall post-grouting defects with confidence levels lower than a predetermined confidence level threshold.

[0138] In some embodiments of the present disclosure, the predetermined confidence threshold may be 50%.

[0139] In some embodiments of the present disclosure, the specific value of the predetermined confidence threshold may depend on the quality of field data collection.

[0140] In some embodiments of the present disclosure, step 322 may include: filtering out segment wall post-grouting defects with a confidence level lower than 50%.

[0141] Step 323: splice the multiple output images of the first predetermined size to restore the images to their original size.

[0142] In some embodiments of the present disclosure, step 323 may include: the YOLOv8 model outputs a 448×448 image, and then stitches several 448×448 images to restore the image to its original size.

[0143] Step 324, calculating the pixel position of the post-grouting defect on the segment wall in the original image.

[0144] Step 325, determining the actual position of the segment wall post-grouting defect according to the pixel position of the segment wall post-grouting defect in the original image.

[0145] In some embodiments of the present disclosure, step 325 may include: determining the actual position of the segment wall post-grouting defect based on the lateral pixel coordinates of the segment wall post-grouting defect in the original image, the lateral pixel length of the original image, the original image position and the conversion coefficient of the actual position.

[0146] In some embodiments of the present disclosure, the conversion factor is determined according to the radar scanning angle and the horizontal pixel length of the original image.

[0147] In some embodiments of the present disclosure, step 325 may include: calculating the actual location of the disease according to formula (2): .

[0148] (2)

[0149] In formula (2), is the empty position, is the horizontal pixel coordinate of the center of the hole in the B-Scan radar image, is the horizontal pixel length of the B-Scan radar image, It is the conversion factor between the B-Scan radar chart position and the actual position.

[0150] In some embodiments of the present disclosure, the conversion factor It is the angle swept by the radar divided by the pixel length of the B-Scan radar image.

[0151] When the above-mentioned embodiments of the present disclosure perform model training, the input is annotated ground penetrating radar B-SCAN images, which can be acquired in large quantities.

[0152] The model of the above embodiment of the present disclosure directly outputs a ground penetrating radar image with defects and confidence marks and their positions in the image pixels based on the input ground penetrating radar image.

[0153] The above-mentioned embodiment of the present disclosure uses a ground penetrating radar, which can automatically process the ground penetrating radar signal and automatically identify and locate the grouting defects behind the pipe wall without the need for manual processing and identification by professional technicians.

[0154] The above-mentioned embodiments of the present disclosure can realize accurate positioning of post-grouting defects on the wall of the pipe segment.

[0155] Figure 2 Schematic diagrams of some embodiments of the segment wall post-grouting defect detection device disclosed in the present invention. Figure 2 As shown, the segment wall post-grouting defect detection device disclosed in the present invention may include a signal acquisition module 41 , a signal processing module 42 and a detection and positioning module 43 .

[0156] The signal acquisition module 41 is configured to acquire a ground penetrating radar signal, wherein the ground penetrating radar signal is a ground penetrating radar signal of a segment wall post-grouting position collected by the ground penetrating radar after the segment wall post-grouting.

[0157] The signal processing module 42 is configured to perform signal processing on the ground penetrating radar signal.

[0158] In some embodiments of the present disclosure, the signal processing module 42 is configured to perform at least one of zero-time correction, DC drift removal, bandpass filtering, background elimination, and gain processing on the ground penetrating radar signal.

[0159] In some embodiments of the present disclosure, when performing zero-time correction on the ground penetrating radar signal, the signal processing module 42 can be configured to select a single-channel scanning signal in the original ground penetrating radar signal; truncate the data of the single-channel scanning signal at the position where the absolute value is the largest; truncate each single-channel scanning signal data in the original ground penetrating radar signal at the position where the data of the single-channel scanning signal is truncated, and retain the data after the truncation position.

[0160] In some embodiments of the present disclosure, the signal processing module 42 can be configured to calculate the average value of each single-channel scanning signal in the original ground penetrating radar signal when removing DC drift from the ground penetrating radar signal; for each single-channel scanning signal, the average value of the single-channel scanning signal is subtracted from each data of the single-channel scanning signal.

[0161] In some embodiments of the present disclosure, the signal processing module 42 can be configured to perform bandpass filtering on the original ground penetrating radar signal when performing bandpass filtering on the ground penetrating radar signal, wherein the first threshold of the bandpass filter is set to 0.4 times the center frequency of the radar antenna, and the second threshold of the bandpass filter is set to 1.2 times the center frequency of the radar antenna.

[0162] In some embodiments of the present disclosure, when performing background elimination on the ground penetrating radar signal, the signal processing module 42 can be configured to calculate the average value of each row of data in the two-dimensional profile image of the original ground penetrating radar signal to form a column of pixels; and subtract the column of pixels from each column of data in the two-dimensional profile image.

[0163] In some embodiments of the present disclosure, when performing gain on the ground penetrating radar signal, the signal processing module 42 may be configured to perform segmented gain or automatic gain on the original ground penetrating radar signal.

[0164] In some embodiments of the present disclosure, when the signal processing module 42 performs automatic gain control on the ground penetrating radar signal, it can be configured to perform automatic gain control on the ground penetrating radar signal.

[0165] In some other embodiments of the present disclosure, the signal processing module 42 may be configured to perform energy gain on the ground penetrating radar signal when automatically performing gain on the ground penetrating radar signal.

[0166] In some embodiments of the present disclosure, when performing segmented gain on the ground penetrating radar signal, the signal processing module 42 may be configured to set the number of segments of the segmented gain to 6 to 8.

[0167] The detection and positioning module 43 is configured to perform target detection on the ground penetrating radar signal after signal processing, and to identify and locate the grouting defects behind the segment wall.

[0168] In some embodiments of the present disclosure, the segment wall post-grouting defects include at least one of voids, water-richness, and looseness.

[0169] In some embodiments of the present disclosure, the detection and positioning module 43 may be configured to perform target detection on the ground penetrating radar signal after signal processing, and determine the type, confidence level and location of the post-grouting defect of the segment wall.

[0170] In some embodiments of the present disclosure, the detection and positioning module 43 can be configured to adjust the ground penetrating radar image after signal processing to an image of a first predetermined size; perform target detection on the image of the first predetermined size to determine the type, confidence and location of the post-grouting defect of the segment wall.

[0171] In some embodiments of the present disclosure, the detection and positioning module 43, when performing target detection on the image of the first predetermined size and determining the type, confidence and position of the post-grouting disease of the segment wall, can be configured to determine the type and confidence of the post-grouting disease of the segment wall; filter out the post-grouting disease of the segment wall whose confidence is lower than the predetermined confidence threshold; splice multiple output images of the first predetermined size to restore the image to its original size; calculate the pixel position of the post-grouting disease of the segment wall in the original image; and determine the actual position of the post-grouting disease of the segment wall based on the pixel position of the post-grouting disease of the segment wall in the original image.

[0172] In some embodiments of the present disclosure, when the detection and positioning module 43 determines the actual position of the segment wall post-grouting disease based on the pixel position of the segment wall post-grouting disease in the original image, it can be configured to determine the actual position of the segment wall post-grouting disease based on the lateral pixel coordinates of the segment wall post-grouting disease in the original image, the lateral pixel length of the original image, the original image position and the conversion coefficient of the actual position.

[0173] In some embodiments of the present disclosure, the conversion factor may be determined according to the radar scanning angle and the horizontal pixel length of the original image.

[0174] In some embodiments of the present disclosure, the segment wall post-grouting defect detection device of the present disclosure may also be configured to execute the segment wall post-grouting defect detection method described in any of the above embodiments of the present disclosure.

[0175] Figure 3 Schematic diagram of the structure of some other embodiments of the segment wall post-grouting disease detection device disclosed in the present invention. Figure 3 As shown, the segment wall post-grouting defect detection device includes a memory 51 and a processor 52.

[0176] The memory 51 is used to store instructions, the processor 52 is coupled to the memory 51, and the processor 52 is configured to execute the segment wall post-grouting defect detection method described in any of the above embodiments of the present disclosure based on the instructions stored in the memory.

[0177] like Figure 3 As shown, the segment wall post-grouting defect detection device also includes a communication interface 53 for information exchange with other devices. At the same time, the segment wall post-grouting defect detection device also includes a bus 54, and the processor 52, the communication interface 53, and the memory 51 communicate with each other through the bus 54.

[0178] The memory 51 may include a high-speed RAM memory, and may also include a non-volatile memory, such as at least one disk memory. The memory 51 may also be a memory array. The memory 51 may also be divided into blocks, and the blocks may be combined into virtual volumes according to certain rules.

[0179] In addition, the processor 52 may be a central processing unit (CPU), or may be an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present disclosure.

[0180] Figure 4 Schematic diagram of some embodiments of the segment wall post-grouting disease detection system disclosed in the present invention. Figure 4 As shown, the segment wall post-grouting defect detection system disclosed in the present invention may include a ground penetrating radar 100 and a segment wall post-grouting defect detection device 200 .

[0181] The ground penetrating radar 100 is configured to collect raw data of the back-wall grouting, and send the raw data of the back-wall grouting to the segment back-wall grouting defect detection device 200.

[0182] In some embodiments of the present disclosure, the raw data of the back-grouting is a ground penetrating radar signal of the back-grouting of the segment wall.

[0183] The segment wall post-grouting defect detection device 200 is configured to receive the segment wall post-grouting ground-penetrating radar signal collected by the ground-penetrating radar 100; perform signal processing on the segment wall post-grouting ground-penetrating radar signal; perform target detection on the processed segment wall post-grouting defect.

[0184] In some embodiments of the present disclosure, the segment wall post-grouting defect detection device 200 may be a segment wall post-grouting defect detection device as described in any of the above embodiments.

[0185] In some embodiments of the present disclosure, the segment wall post-grouting defect detection device 200 may be a ground penetrating radar wall post-grouting detection device.

[0186] In some embodiments of the present disclosure, the segment wall post-grouting defect detection device 200 can be implemented as a signal receiving and storing device.

[0187] The above-mentioned embodiment of the present invention discloses that the back grouting of the segment wall is detected by a ground penetrating radar, the signal collected by the ground penetrating radar is received and stored by a signal receiving and storage device, and then the data collected by the ground penetrating radar in the receiving and storage device are corrected at zero time, DC drift is removed, band-pass filtered, background is eliminated, and gain is performed, and then the back grouting defects of the segment wall are identified and located using a target detection algorithm.

[0188] According to another aspect of the present disclosure, a shield machine is provided, comprising a segment wall post-grouting defect detection system as described in any of the above embodiments.

[0189] In some embodiments of the present disclosure, the segment wall post-grouting defect detection device and the segment wall post-grouting defect detection system are installed on a shield machine.

[0190] According to another aspect of the present disclosure, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the method for detecting segment wall post-grouting defects as described in any of the above embodiments is implemented.

[0191] According to another aspect of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and when the instructions are executed by a processor, the method for detecting segment wall post-grouting defects as described in any of the above embodiments of the present disclosure is implemented.

[0192] In some embodiments of the present disclosure, the computer-readable storage medium may be a non-transitory computer-readable storage medium.

[0193] Those skilled in the art will appreciate that the embodiments of the present disclosure may be provided as methods, devices, or computer program products. Therefore, the present disclosure may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present disclosure may take the form of a computer program product implemented on one or more computer-usable non-transient storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0194] The present disclosure is described with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present disclosure. It should be understood that each process and / or block in the flowchart and / or block diagram and the combination of processes and / or blocks in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0195] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0196] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0197] The segment wall post-grouting defect detection device, signal acquisition module, signal processing module and detection positioning module described above can be implemented as a general-purpose processor, programmable logic controller (PLC), digital signal processor (DSP), application-specific integrated circuit (ASIC), field programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware component or any appropriate combination thereof for performing the functions described in this application.

[0198] So far, the present disclosure has been described in detail. In order to avoid obscuring the concept of the present disclosure, some details known in the art are not described. Based on the above description, those skilled in the art can fully understand how to implement the technical solution disclosed here.

[0199] A person skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware, or may be accomplished by instructing the relevant hardware through a program, and the program may be stored in a non-transitory computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc.

[0200] The description of the present disclosure is given for the purpose of illustration and description, and is not intended to be exhaustive or to limit the present disclosure to the disclosed form. Many modifications and variations will be apparent to those of ordinary skill in the art. The embodiments are selected and described in order to better illustrate the principles and practical applications of the present disclosure, and to enable those of ordinary skill in the art to understand the present disclosure and thereby design various embodiments with various modifications suitable for specific uses.

Claims

1. A method for detecting segment wall post-grouting defects, comprising: Acquire a ground penetrating radar signal, wherein the ground penetrating radar signal is a ground penetrating radar signal of a segment wall post-grouting position collected by the ground penetrating radar after the segment wall post-grouting; performing signal processing on the ground penetrating radar signal; The ground penetrating radar signal after signal processing is used for target detection, and the grouting defects behind the segment wall are identified and located.

2. The method for detecting segment wall post-grouting defects according to claim 1, wherein: The target detection of the ground penetrating radar signal after signal processing and the identification and positioning of the segment wall back grouting defects include: The ground penetrating radar signal after signal processing is subjected to target detection to determine the type, confidence level and location of the grouting defect behind the segment wall.

3. The method for detecting segment wall post-grouting defects according to claim 2, wherein: The ground penetrating radar signal is a ground penetrating radar image, and the target detection is performed on the ground penetrating radar signal after signal processing to identify and locate the grouting defect behind the pipe segment wall, including: Adjusting the ground penetrating radar image after signal processing to an image of a first predetermined size; Target detection is performed on the image of the first predetermined size to determine the type, confidence level and location of the post-grouting defect on the segment wall.

4. The method for detecting segment wall post-grouting defects according to claim 3, wherein: The performing target detection on the image of the first predetermined size to determine the type, confidence level and location of the segment wall post-grouting defect comprises: Determine the type and confidence level of segment wall post-grouting defects; Filter out the segment wall post-grouting defects with confidence values ​​lower than a predetermined confidence value threshold; splicing a plurality of output images of the first predetermined size to restore the images to their original size; Calculating the pixel position of the segment wall post-grouting defect in the original image; According to the pixel position of the segment wall post-grouting defect in the original image, the actual position of the segment wall post-grouting defect is determined.

5. The method for detecting segment wall post-grouting defects according to claim 4, wherein: Determining the actual position of the segment wall post-grouting defect according to the pixel position of the segment wall post-grouting defect in the original image includes: The actual position of the segment wall post-grouting defect is determined based on the lateral pixel coordinates of the segment wall post-grouting defect in the original image, the lateral pixel length of the original image, the original image position and the conversion coefficient of the actual position.

6. The method for detecting segment wall post-grouting defects according to claim 5, wherein: The conversion factor is determined according to the radar scanning angle and the horizontal pixel length of the original image.

7. The method for detecting segment wall post-grouting defects according to any one of claims 1 to 6, wherein: The segment wall post-grouting defects include at least one of voids, water-richness and looseness.

8. The method for detecting segment wall post-grouting defects according to any one of claims 1 to 6, wherein: The signal processing of the ground penetrating radar signal comprises: The ground penetrating radar signal is subjected to at least one of zero-time correction, DC drift removal, bandpass filtering, background elimination and gain processing.

9. The method for detecting segment wall post-grouting defects according to claim 8, wherein: The zero-time correction of the ground penetrating radar signal comprises: Select a single-channel scanning signal in the original ground penetrating radar signal; Cut off the data at the position with the maximum absolute value in the single-channel scanning signal data; Each single-channel scanning signal data in the original ground penetrating radar signal is truncated at the data truncation position of the single-channel scanning signal, and the data after the truncation position is retained.

10. The method for detecting segment wall post-grouting defects according to claim 8, wherein: The removing DC drift from the ground penetrating radar signal comprises: Calculate the average value of each single-channel scanning signal in the original ground penetrating radar signal; For each single-channel scanning signal, the average value of the single-channel scanning signal is subtracted from each data of the single-channel scanning signal.

11. The method for detecting segment wall post-grouting defects according to claim 8, wherein: The bandpass filtering of the ground penetrating radar signal comprises: The original ground penetrating radar signal is bandpass filtered, wherein the first threshold of the bandpass filter is set to 0.4 times the center frequency of the radar antenna, and the second threshold of the bandpass filter is set to 1.2 times the center frequency of the radar antenna.

12. The method for detecting segment wall post-grouting defects according to claim 8, wherein: The background elimination of the ground penetrating radar signal comprises: Calculate the average value of each row of data in the two-dimensional profile image of the original ground penetrating radar signal to form a column of pixels; Subtract the pixels in each column from the data in the 2D cross-section image.

13. The method for detecting segment wall post-grouting defects according to claim 8, wherein: The step of gaining the ground penetrating radar signal comprises: Perform segmented gain or automatic gain on the raw GPR signal.

14. The method for detecting segment wall post-grouting defects according to claim 13, wherein: The automatic gaining of the ground penetrating radar signal comprises: Automatic gain for automatically controlling the gain of the ground penetrating radar signal; or, Energy gain is performed on the ground penetrating radar signal.

15. The method for detecting segment wall post-grouting defects according to claim 13, wherein: The performing segmented gain on the ground penetrating radar signal comprises: The number of segments of the segment gain is set to 6 to 8.

16. A segment wall post-grouting defect detection device, comprising: A signal acquisition module is configured to acquire a ground penetrating radar signal, wherein the ground penetrating radar signal is a ground penetrating radar signal of a segment wall post-grouting position collected by the ground penetrating radar after the segment wall post-grouting; A signal processing module, configured to perform signal processing on the ground penetrating radar signal; The detection and positioning module is configured to perform target detection on the ground penetrating radar signal after signal processing, and to identify and locate the grouting defects behind the pipe segment wall.

17. A segment wall post-grouting defect detection device, comprising: a memory configured to store instructions; The processor is configured to execute the instructions so that the segment wall post-grouting defect detection device implements the segment wall post-grouting defect detection method as described in any one of claims 1-15.

18. A segment wall post-grouting defect detection system, comprising a ground penetrating radar and a segment wall post-grouting defect detection device as claimed in claim 16 or 17.

19. A shield machine, comprising the segment wall post-grouting defect detection system as claimed in claim 18.

20. A computer-readable storage medium, wherein: The computer-readable storage medium stores computer instructions, and when the instructions are executed by a processor, the segment wall post-grouting defect detection method according to any one of claims 1 to 15 is implemented.

21. A computer program product comprising a computer program, wherein: When the computer program is executed by a processor, the method for detecting segment wall post-grouting defects according to any one of claims 1 to 15 is implemented.

Images