CN113064166A - Method and device for detecting thickness of thin layer defect of multilayer concrete structure and terminal - Google Patents

Abstract

The invention is applicable to the technical field of concrete structure detection, and provides a method for detecting the thickness of thin layer defects of a multi-layer concrete structure, comprising: acquiring an echo signal, wherein the echo signal is a signal returned from the detection of the concrete structure by a ground penetrating radar; Fractional S-transformation is used to preprocess the echo signal to strengthen the signal features corresponding to thin layer defects in the echo signal; a grayscale image is generated based on the preprocessed echo signal; the grayscale image is input into the trained thickness Identify the model to obtain thickness information of thin layer defects in concrete structures. In the present invention, the feature enhancement processing is performed on the echo signal, which can improve the detection accuracy of the thickness information of the thin layer defect. The thickness information of the thin layer defect can be obtained through the thickness identification model, and the thickness information of the thin layer defect caused by multiple factors can be determined. .

Description

A method, device and terminal for detecting thickness of thin layer defect of multi-layer concrete structure

technical field

The invention belongs to the technical field of concrete structure detection, and in particular relates to a method, a device and a terminal for detecting the thickness of a thin layer defect of a multi-layer concrete structure.

Background technique

Multi-layer concrete structure is an important structural type for ballastless track and tunnel lining of high-speed railway. In a multi-layer concrete structure, the deformation of different concrete slabs due to the effect of temperature will cause warping and form seams. The thickness of the separation seam directly affects the stability and smoothness of the structure. Measuring the thickness information of the separation seam defect has always been the focus of the quality inspection of multi-layer concrete structures.

The current ground penetrating radar method can realize large-scale void defect detection by analyzing different interface echoes. However, for thin-layer separation defects, the scale is small, and the echo signals of the upper and lower interfaces are seriously overlapped and mixed, so it is difficult to determine the defect thickness. .

SUMMARY OF THE INVENTION

In view of this, the present invention provides a method, a device and a terminal for detecting the thickness of a thin layer defect of a multi-layer concrete structure, so as to solve the problem that it is difficult to determine the thickness of a thin layer separation gap defect in the prior art.

A first aspect of the embodiments of the present invention provides a method for detecting the thickness of a thin layer defect of a multi-layer concrete structure, including:

Obtaining an echo signal, wherein the echo signal is a signal returned from the detection of the concrete structure by the ground penetrating radar;

The echo signal is preprocessed by fractional S-transform to strengthen the signal features corresponding to thin layer defects in the echo signal;

Generate a grayscale image based on the preprocessed echo signal;

The grayscale image is input into the trained thickness recognition model to obtain the thickness information of thin layer defects in the concrete structure.

A second aspect of the embodiments of the present invention provides a thin layer defect thickness detection device for a multi-layer concrete structure, including:

a signal acquisition module for acquiring echo signals, wherein the echo signals are the signals returned by the ground penetrating radar from the detection of the concrete structure;

The feature enhancement module is used to preprocess the echo signal by using fractional S-transform, so as to strengthen the signal feature corresponding to the thin layer defect in the echo signal;

The image conversion module is used to generate a grayscale image based on the preprocessed echo signal;

The thickness analysis module is used to input the gray image into the trained thickness recognition model to obtain the thickness information of the thin layer defects in the concrete structure.

A third aspect of the embodiments of the present invention provides a terminal, 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 multi-layer concrete structure such as any one can be realized. Steps of a thin layer defect thickness detection method.

A fourth aspect of the embodiments of the present invention provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, any method for detecting the thickness of a thin layer defect in a multi-layer concrete structure is implemented. A step of.

Compared with the prior art, the present invention has the following beneficial effects:

The invention provides a method for detecting the thickness of thin layer defects of a multi-layer concrete structure. The method includes: acquiring an echo signal, wherein the echo signal is a signal returned from the detection of a concrete structure by a ground penetrating radar; The echo signal is preprocessed to strengthen the signal characteristics corresponding to the thin layer defects in the echo signal; a grayscale image is generated based on the preprocessed echo signal; the grayscale image is input into the trained thickness recognition model to obtain the concrete structure Thickness information for medium and thin layer defects. In the present invention, the feature enhancement processing is performed on the echo signal, which can improve the detection accuracy of the thickness information of the thin layer defect, and the thickness information of the thin layer defect can be obtained through the thickness identification model, and the thickness information of the thin layer defect caused by multiple factors can be determined. .

Description of drawings

In order to illustrate the technical solutions in the embodiments of the present invention more clearly, the following briefly introduces the accompanying drawings that need to be used in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only for the present invention. In some embodiments, for those of ordinary skill in the art, other drawings can also be obtained according to these drawings without any creative effort.

Fig. 1 is a realization flow chart of the method for detecting the thickness of thin layer defects of multilayer concrete structures provided by the embodiment of the present invention;

2 is a schematic structural diagram of a device for detecting the thickness of a thin layer defect of a multi-layer concrete structure provided by an embodiment of the present invention;

3 is a schematic diagram of a terminal provided by an embodiment of the present invention;

4 is a comparison diagram of S-transformation and cross-entropy values corresponding to different fractional factor values in the embodiment of the present invention;

FIG. 5 is a schematic structural diagram of a neural network provided by an embodiment of the present invention.

Detailed ways

In the following description, for the purpose of illustration rather than limitation, specific details such as specific system structures and technologies are set forth in order to provide a thorough understanding of the embodiments of the present invention. However, it will be apparent to those skilled in the art that the present invention may be practiced in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.

In order to make the objectives, technical solutions and advantages of the present invention clearer, the following descriptions will be given through specific embodiments in conjunction with the accompanying drawings.

Referring to FIG. 1 , it shows the implementation flow chart of the method for detecting the thickness of thin layer defects in a multilayer concrete structure provided by an embodiment of the present invention, which is described in detail as follows:

The embodiment of the present invention provides a method for detecting the thickness of a thin layer of a multi-layer concrete structure, including:

Step 101, acquiring an echo signal, wherein the echo signal is a signal returned by the ground penetrating radar detecting the concrete structure;

Step 102, using fractional S-transform to preprocess the echo signal to strengthen the signal feature corresponding to the thin layer defect in the echo signal;

In this embodiment, the echo signal is preprocessed by fractional S-transform, so as to strengthen the signal features of the echo signal corresponding to the thin layer defects, including:

Determine the fractional factor in the fractional S-transform;

Optionally, determining the fractional factor in the fractional S-transform includes:

According to the preset cross-entropy formula, calculate the cross-entropy when the echo signal contains only one signal and when both the upper surface reflection signal and the lower surface reflection signal are included. The cross-entropy formula is:

表示

与

之间的交叉熵，

表示只包含一个信号的回波信号，

表示同时包含上表面反射信号与下表面反射信号的回波信号；in,

express

and

The cross entropy between,

represents the echo signal containing only one signal,

Indicates the echo signal containing both the upper surface reflection signal and the lower surface reflection signal;

Take the score factor that makes the cross-entropy appear the most minimum value as the determined score factor.

In this embodiment, the determination of the optimal fractional order is to ensure that the rotated S transform contains as much information as possible, and the optimal fractional order can be determined by the method of minimum cross entropy. Assuming that the thickness of the thin layer defect tends to 0, at this time, the echo signal has only one echo signal, namely

y ⁰ (t)=αy ₁ (t)

When the echo signal contains both the upper and lower surface echoes of the thin layer defect, the echo signal is expressed as

y ⁱ (t)=αy ₁ (t)+βy ₁ (t-Δt _i )

和

则定义薄层缺陷回波信号a阶分数S变换

和

之间的交叉熵为：The a-order fractional S transforms of y ⁰ (t) and y ⁱ (t) are expressed as

and

Then define the a-order fractional S transform of the echo signal of the thin layer defect

and

The cross entropy between is:

Then the loss function is:

Figure 4 shows the Ricker wavelet time-domain waveform, S-transform waveform, different fractional-order S-transform waveform and cross-entropy waveform when the signal-to-noise ratio SNR=20dB after normalization.

From the cross-entropy display results in Figure 4, when a=0.44, both n=5 and 10 have the smallest cross-entropy with n=0. Therefore, this paper believes that when a=0.44, the fractional S-transform has the most abundant features.

Select the Ricker wavelet time domain interval value range of [0.1, 1], the frequency domain interval [0.3fM, 1.8fM] as the characteristic interval (fM is the central frequency of the Ricker wavelet), the corresponding a=0.44 order fractional S transform is the characteristic value.

At the same time, in order to further eliminate the influence of different input wavelets, the eigenvalue when a=0.44 is defined in the actual processing process is:

The echo signal is subjected to fractional S-transformation according to the preset fractional-order S-transformation formula, and the fractional-order S-transformation formula is:

Among them, FrST _y (t, f, a) represents the echo signal after fractional S-transformation, Y _a (τ) represents the Fourier transform signal of the echo signal, and a represents the fractional factor.

In this embodiment, in order to improve the identification accuracy of the thin layer defect of the multi-layer concrete structure, the A-Scan signal of the ground penetrating radar needs to be preprocessed.

Define the A-Scan signal as y(t), then its fractional Fourier transform is:

K_a(u,t)表示分数阶傅立叶变换的核函数，表达式为：Among them, a represents the order of the fractional Fourier transform, and the corresponding rotation angle is

Ka ( _u ,t) represents the kernel function of fractional Fourier transform, and the expression is:

The a-order fractional S-transform FrST of y(t) is defined as:

这种操作将增加薄层缺陷信号在探地雷达子波在主频区域的特征。At this time, the fractional S transformation can be understood as the rotation angle of the S transformation in the t and f planes

This operation will increase the characteristic of the thin layer defect signal in the dominant frequency region of the GPR wavelet.

Step 103, generating a grayscale image based on the preprocessed echo signal;

In this embodiment, generating a grayscale image based on the preprocessed echo signal includes:

The grayscale image corresponding to the preprocessed echo signal is calculated by the preset grayscale image conversion formula. The grayscale image conversion formula is:

表示预处理后的回波信号的绝对值，t、f表示S变换所处平面。where I represents a grayscale image,

represents the absolute value of the preprocessed echo signal, and t and f represent the plane where the S transform is located.

Step 104: Input the grayscale image into the trained thickness identification model to obtain the thickness information of the thin layer defect in the concrete structure.

In the present embodiment, before inputting the grayscale image into the trained thickness recognition model, it also includes:

Establish an echo signal model library, the echo signal model library contains the echo signals corresponding to multi-layer concrete with different thin layer defect thicknesses;

In this embodiment, establishing an echo signal model library includes:

acquiring the echo signal used for establishing the echo signal model library, wherein the echo signal used for establishing the echo signal model library is the signal returned by the ground penetrating radar detecting the concrete structure for which the thickness information of the thin layer defect is known;

Using fractional S-transform to preprocess the echo signal used for establishing the echo signal model library, so as to strengthen the signal features corresponding to thin layer defects in the echo signal used for establishing the echo signal model library;

The processed echo signals used for establishing the echo signal model library and the thickness information of the corresponding thin layer defects are used as data in the echo signal model library.

In this embodiment, the echo signal model library adopts the method of combining numerical simulation and model test. The numerical model adopts the finite time-domain difference method to construct different thin sandwich thickness models. Assuming that the cavity defects in the concrete are located in the shallow surface layer and the filling medium is air, the grid is divided into (1mm, 1mm) and the sampling time is 6ns. At this time, the calculated value of the number of sampling points is about 1600 sampling points, so the calculation interval of cavity defects is 7ns. *3*1011/1024≈2mm, considering two-way travel, the minimum cavity thickness is 1mm. The model is shown in Figure 5. The model is divided into three layers, and the upper and lower layers are made of concrete. In order to prevent the echo from the upper layer and the echo from the lower layer of the model from aliasing with the cavity echo, l ₀ and l ₁ are taken as 30cm and 20cm, respectively.

The thickness identification model is trained through the echo signal model library, and the trained thickness identification model is obtained.

In this embodiment, in order to identify the thickness information of the thin layer defects in the above concrete structure, a convolutional neural network is constructed as a thickness identification model, and FIG. 5 shows the structure of the neural network. The input content of the input layer is the grayscale image transformed by the absolute value of the fractional S-transformed data, namely

The middle layer is 3 convolution layers, of which the activation function is the Relu function; the output layer includes a fully connected layer and a Softmax logistic regression layer, whose output value is Oi.

In the actual measurement process, the defect thickness is represented by the number of samples in the echo data, so the sample interval is used as the true value ti in the model, and it is marked as one-hot form, then its cross entropy is:

The neural network is trained through the echo signal model library, and the parameters of each layer in the neural network are optimized.

As can be seen from the above, the present invention first obtains the echo signal, wherein the echo signal is the signal returned by the ground penetrating radar detecting the concrete structure; and then uses the fractional-order S transform to preprocess the echo signal to strengthen the echo signal. Corresponding to the signal characteristics of thin layer defects; then generate a grayscale image based on the preprocessed echo signal; finally, input the grayscale image into the trained thickness identification model to obtain the thickness information of thin layer defects in concrete structures. In the present invention, the feature enhancement processing is performed on the echo signal, which can improve the detection accuracy of the thickness information of the thin layer defect, and the thickness information of the thin layer defect can be obtained through the thickness identification model, and the thickness information of the thin layer defect caused by multiple factors can be determined. .

It should be understood that the size of the sequence numbers of the steps in the above embodiments does not mean the sequence of execution, and the execution sequence of each process should be determined by its functions and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

The following are apparatus embodiments of the present invention, and for details that are not described in detail, reference may be made to the above-mentioned corresponding method embodiments.

FIG. 2 shows a schematic structural diagram of the device for detecting the thickness of thin layer defects in a multi-layer concrete structure provided by an embodiment of the present invention. For the convenience of description, only the parts related to the embodiment of the present invention are shown, and the details are as follows:

As shown in Figure 2, the device 2 for detecting the thickness of the thin layer defect of the multi-layer concrete structure includes:

The signal acquisition module 21 is used for acquiring an echo signal, wherein the echo signal is a signal returned from the detection of the concrete structure by the ground penetrating radar;

The feature enhancement module 22 is used to preprocess the echo signal by using fractional S-transform, so as to strengthen the signal feature corresponding to the thin layer defect in the echo signal;

The image conversion module 23 is used for generating a grayscale image based on the preprocessed echo signal;

The thickness analysis module 24 is used for inputting the grayscale image into the trained thickness identification model to obtain the thickness information of the thin layer defects in the concrete structure.

In this embodiment, the device for detecting the thickness of the thin layer defect of the multi-layer concrete structure further includes:

The model library establishment module is used to establish the echo signal model library before inputting the gray image into the trained thickness identification model, and the echo signal model library contains the echo signals corresponding to the multilayer concrete with different thickness of the thin layer defect;

The model training module is used to train the thickness recognition model through the echo signal model library before inputting the grayscale image into the trained thickness recognition model to obtain the trained thickness recognition model.

In this embodiment, the model library establishment module includes:

The signal acquisition unit is used for acquiring the echo signal used for establishing the echo signal model library, wherein the echo signal used for establishing the echo signal model library is a concrete structure for which the thickness information of the thin layer defect is known by the ground penetrating radar The signal returned by the detection;

The preprocessing unit is used for preprocessing the echo signal used for establishing the echo signal model library by using fractional S transform, so as to strengthen the signal corresponding to the thin layer defect in the echo signal used for establishing the echo signal model library feature;

The data modification unit is configured to use the processed echo signals for establishing the echo signal model library and the thickness information of the corresponding thin layer defects as data in the echo signal model library.

In this embodiment, the image conversion module is also used for:

The grayscale image corresponding to the preprocessed echo signal is calculated by the preset grayscale image conversion formula. The grayscale image conversion formula is:

表示预处理后的回波信号的绝对值，t、f表示S变换所处平面。where I represents a grayscale image,

represents the absolute value of the preprocessed echo signal, and t and f represent the plane where the S transform is located.

In this embodiment, the feature enhancement module further includes:

The fractional factor determination unit is used to determine the fractional factor in the fractional S-transform;

The fractional-order S-transformation unit is used to perform fractional-order S-transformation on the echo signal according to a preset fractional-order S-transformation formula, and the fractional-order S-transformation formula is:

Among them, FrST _y (t, f, a) represents the echo signal after fractional S-transformation, Y _a (τ) represents the Fourier transform signal of the echo signal, and a represents the fractional factor.

In this embodiment, determining the fractional factor in the fractional S-transform includes:

According to the preset cross-entropy formula, calculate the cross-entropy when the echo signal contains only one signal and when both the upper surface reflection signal and the lower surface reflection signal are included. The cross-entropy formula is:

表示

与

之间的交叉熵，

表示只包含一个信号的回波信号，

表示同时包含上表面反射信号与下表面反射信号的回波信号；in,

express

and

the cross-entropy between

represents the echo signal containing only one signal,

Indicates the echo signal containing both the upper surface reflection signal and the lower surface reflection signal;

Take the score factor that makes the cross-entropy appear the most minimum value as the determined score factor.

FIG. 3 is a schematic diagram of a terminal provided by an embodiment of the present invention. As shown in FIG. 3 , the terminal 3 of this embodiment includes: a processor 30 , a memory 31 , and a computer program 32 stored in the memory 31 and executable on the processor 30 . When the processor 30 executes the computer program 32, the steps in each of the above embodiments of the method for detecting the thickness of thin layer defects in a multi-layer concrete structure are implemented, for example, steps 101 to 103 shown in FIG. 1 . Alternatively, when the processor 30 executes the computer program 32, the functions of the modules/units in the foregoing device embodiments, for example, the functions of the units 31 to 33 shown in FIG. 3 are implemented.

Exemplarily, the computer program 32 can be divided into one or more modules/units, and the one or more modules/units are stored in the memory 31 and executed by the processor 30 to complete the this invention. The one or more modules/units may be a series of computer program instruction segments capable of performing specific functions, and the instruction segments are used to describe the execution process of the computer program 32 in the terminal 3 .

The terminal 3 may be a computing device such as a desktop computer, a notebook, a handheld computer, and a cloud server. The terminal may include, but is not limited to, the processor 30 and the memory 31 . Those skilled in the art can understand that FIG. 3 is only an example of the terminal 3, and does not constitute a limitation on the terminal 3. It may include more or less components than the one shown in the figure, or combine some components, or different components, such as The terminal may also include input and output devices, network access devices, buses, and the like.

The so-called processor 30 may be a central processing unit (Central Processing Unit, CPU), and may also be other general-purpose processors, digital signal processors (Digital Signal Processors, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), Field-Programmable Gate Array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

The memory 31 may be an internal storage unit of the terminal 3 , such as a hard disk or a memory of the terminal 3 . The memory 31 may also be an external storage device of the terminal 3, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card equipped on the terminal 3, Flash card (Flash Card) and so on. Further, the memory 31 may also include both an internal storage unit of the terminal 3 and an external storage device. The memory 31 is used to store the computer program and other programs and data required by the terminal. The memory 31 can also be used to temporarily store data that has been output or will be output.

Those skilled in the art can clearly understand that, for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. Module completion, that is, dividing the internal structure of the device into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment may be integrated in one processing unit, or each unit may exist physically alone, or two or more units may be integrated in one unit, and the above-mentioned integrated units may adopt hardware. It can also be realized in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing from each other, and are not used to limit the protection scope of the present application. For the specific working processes of the units and modules in the above-mentioned system, reference may be made to the corresponding processes in the foregoing method embodiments, which will not be repeated here.

In the foregoing embodiments, the description of each embodiment has its own emphasis. For parts that are not described or described in detail in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Skilled artisans may implement the described functionality using different methods for each particular application, but such implementations should not be considered beyond the scope of the present invention.

In the embodiments provided by the present invention, it should be understood that the disclosed apparatus/terminal and method may be implemented in other manners. For example, the device/terminal embodiments described above are only illustrative. For example, the division of the modules or units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or Components may be combined or may be integrated into another system, or some features may be omitted, or not implemented. On the other hand, the shown or discussed mutual coupling or direct coupling or communication connection may be through some interfaces, indirect coupling or communication connection of devices or units, and may be in electrical, mechanical or other forms.

The units described as separate components may or may not be physically separated, and components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution in this embodiment.

In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit. The above-mentioned integrated units may be implemented in the form of hardware, or may be implemented in the form of software functional units.

The integrated modules/units, if implemented in the form of software functional units and sold or used as independent products, may be stored in a computer-readable storage medium. Based on this understanding, the present invention can implement all or part of the processes in the methods of the above embodiments, and can also be completed by instructing relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the program is executed by the processor, the steps of the foregoing method embodiments can be implemented. Wherein, the computer program includes computer program code, and the computer program code may be in the form of source code, object code, executable file or some intermediate form, and the like. The computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM, Read-Only Memory) , Random Access Memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable media may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction, for example, in some jurisdictions, according to legislation and patent practice, the computer-readable media Excluded are electrical carrier signals and telecommunication signals.

The above-mentioned embodiments are only used to illustrate the technical solutions of the present invention, but not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: it is still possible to implement the foregoing implementations. The technical solutions described in the examples are modified, or some technical features thereof are equivalently replaced; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the within the protection scope of the present invention.

Claims (10)

1. A method for detecting the defect thickness of a thin layer of a multilayer concrete structure is characterized by comprising the following steps:

acquiring an echo signal, wherein the echo signal is a signal returned by a ground penetrating radar for detecting a concrete structure;

preprocessing the echo signal by utilizing fractional order S transformation to strengthen signal characteristics corresponding to thin layer defects in the echo signal;

generating a gray image based on the preprocessed echo signal;

and inputting the gray level image into a trained thickness recognition model to obtain thickness information of the thin layer defect in the concrete structure.

2. The method for detecting the thickness of the thin layer defect of the multi-layer concrete structure according to claim 1, wherein before inputting the gray-scale image into the trained thickness recognition model, the method further comprises:

establishing an echo signal model base, wherein the echo signal model base comprises echo signals corresponding to multiple layers of concrete with different thin-layer defect thicknesses;

and training the thickness recognition model through the echo signal model library to obtain the trained thickness recognition model.

3. The method for detecting the defect thickness of the thin layer of the multilayer concrete structure as claimed in claim 2, wherein the establishing of the echo signal model library comprises:

acquiring an echo signal for establishing an echo signal model library, wherein the echo signal for establishing the echo signal model library is a signal returned by a ground penetrating radar for detecting a concrete structure with known thickness information of a thin layer defect;

preprocessing the echo signals for establishing an echo signal model library by utilizing fractional order S transformation so as to strengthen signal characteristics corresponding to thin layer defects in the echo signals for establishing the echo signal model library;

and taking the processed echo signals for establishing an echo signal model library and the thickness information of the corresponding thin layer defects as data in the echo signal model library.

4. The method for detecting the defect thickness of the thin layer of the multilayer concrete structure according to claim 3, wherein the step of generating a gray scale image based on the preprocessed echo signals comprises the following steps:

calculating a gray level image corresponding to the preprocessed echo signal through a preset gray level image conversion formula, wherein the gray level image conversion formula is as follows:

wherein, I represents a gray-scale image,

the absolute value of the preprocessed echo signal is shown, and t and f represent the plane where the S transformation is located.

5. The method for detecting the thickness of the thin layer defect of the multilayer concrete structure according to any one of claims 1 to 4, wherein the step of preprocessing the echo signal by utilizing fractional order S transformation to strengthen the signal characteristic of the echo signal corresponding to the thin layer defect comprises the following steps:

determining fractional factors in fractional order S transformation;

performing fractional order S transformation on the echo signal according to a preset fractional order S transformation formula, wherein the fractional order S transformation formula is as follows:

wherein, FrST_y(t, f, a) represents an echo signal after fractional S conversion, Y_a(τ) represents a Fourier transform signal of the echo signal, and a represents a fractional factor.

6. The method of claim 5, wherein the determining fractional factors in fractional order S transformation comprises:

calculating the cross entropy of the echo signal when only one signal is contained and when the echo signal contains an upper surface reflection signal and a lower surface reflection signal at the same time according to a preset cross entropy formula, wherein the cross entropy formula is as follows:

wherein,

to represent

And

the cross-entropy between the two is,

representing an echo signal containing only one signal,

representing an echo signal containing both an upper surface reflection signal and a lower surface reflection signal;

and taking the fraction factor which enables the cross entropy to appear at most as a determined fraction factor.

7. A multilayer concrete structure thin layer defect thickness detection device, characterized by includes:

the signal acquisition module is used for acquiring echo signals, wherein the echo signals are returned by a ground penetrating radar for detecting the concrete structure;

the characteristic strengthening module is used for preprocessing the echo signal by utilizing fractional order S transformation so as to strengthen the signal characteristics corresponding to the thin layer defects in the echo signal;

the image conversion module is used for generating a gray image based on the preprocessed echo signal;

and the thickness analysis module is used for inputting the gray level image into a trained thickness recognition model to obtain the thickness information of the thin layer defect in the concrete structure.

8. The apparatus for detecting the defect thickness of a thin layer of a multi-layered concrete structure according to claim 7, further comprising:

the model base establishing module is used for establishing an echo signal model base before inputting the gray level image into a trained thickness recognition model, wherein the echo signal model base comprises echo signals corresponding to multiple layers of concrete with different thin layer defect thicknesses;

and the model training module is used for training the thickness recognition model through the echo signal model library before inputting the gray level image into the trained thickness recognition model to obtain the trained thickness recognition model.

9. A terminal comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor when executing the computer program implements the steps of the method for detecting the defect thickness of thin layers of a multi-layer concrete structure as claimed in any one of the preceding claims 1 to 6.

10. A computer-readable storage medium, in which a computer program is stored, which computer program, when being executed by a processor, carries out the steps of the method for detecting the thickness of a defect in a thin layer of a multi-layer concrete structure as claimed in any one of the preceding claims 1 to 6.

Images