CN115901954A

CN115901954A - Nondestructive detection method for ultrasonic guided wave pipeline defects

Info

Publication number: CN115901954A
Application number: CN202211615969.0A
Authority: CN
Inventors: 徐伟; 宋俭; 李�杰; 贺龙飞
Original assignee: Southeast Sepp Testing Technology Co ltd
Current assignee: Southeast Sepp Testing Technology Co ltd
Priority date: 2022-12-15
Filing date: 2022-12-15
Publication date: 2023-04-04

Abstract

The method adopts an artificial intelligence detection technology based on deep learning to detect whether the pipeline to be detected has defects or not by comparing the multi-scale characteristic difference of a detection ultrasonic guided wave signal of the pipeline to be detected and a reference ultrasonic guided wave signal of a non-defective pipeline in a high-dimensional space. Thus, the nondestructive inspection of the pipe defect can be accurately performed.

Description

Nondestructive detection method for ultrasonic guided wave pipeline defects

Technical Field

The application relates to the technical field of nondestructive testing, in particular to an ultrasonic guided wave pipeline defect nondestructive testing method.

Background

Pipeline laying relates to various industries and bears important production missions. Most pipes are exposed to various complicated environments such as bad weather, impact, corrosion of chemicals inside the pipe, etc., and thus the pipes are susceptible to various defects. In engineering, because the event that the pipeline defect brings great damage to the survival and property safety of people frequently occurs, the detection of the health condition of the pipeline is very important.

At present, pipeline maintenance personnel generally detect the damage of a pipeline by methods such as visual detection, electromagnetic flaw detection and the like, and the methods not only take a long time, but also have low detection precision.

Therefore, an optimized non-destructive inspection scheme for pipe defects is desired.

Disclosure of Invention

The present application is proposed to solve the above-mentioned technical problems. The embodiment of the application provides an ultrasonic guided wave pipeline defect nondestructive testing method, which adopts an artificial intelligence detection technology based on deep learning to carry out multi-scale feature difference comparison on a detection ultrasonic guided wave signal of a pipeline to be tested and a reference ultrasonic guided wave signal of a defect-free pipeline in a high-dimensional space so as to detect and judge whether the pipeline to be tested has defects. Thus, nondestructive inspection of pipe defects can be accurately performed.

According to one aspect of the application, a nondestructive testing method for the defects of the ultrasonic guided wave pipeline is provided, and comprises the following steps: acquiring a detection ultrasonic guided wave signal and a reference ultrasonic guided wave signal of a to-be-detected pipeline, wherein the reference ultrasonic guided wave signal is an ultrasonic guided wave signal of a defect-free pipeline; respectively carrying out Fourier transform on the detection ultrasonic guided wave signal and the reference ultrasonic guided wave signal to obtain a plurality of detection frequency domain statistics values and a plurality of reference frequency domain statistics values; enabling the plurality of detection frequency domain statistics values and the oscillogram of the detection ultrasonic guided wave signal to pass through a first Clip model to obtain a detection ultrasonic characteristic matrix; enabling the plurality of reference frequency domain statistics and the reference ultrasonic guided wave signals to pass through a second Clip model to obtain a reference ultrasonic characteristic matrix; calculating a difference feature matrix between the detection ultrasonic feature matrix and the reference ultrasonic feature matrix; correcting the characteristic value of each position of the differential characteristic matrix to obtain a corrected differential characteristic matrix; and enabling the corrected differential feature matrix to pass through a classifier to obtain a classification result, wherein the classification result indicates whether the pipeline to be detected has defects or not.

In the nondestructive testing method for the defect of the ultrasonic guided wave pipeline, the step of passing the plurality of detection frequency domain statistics and the oscillogram of the detection ultrasonic guided wave signal through a first Clip model to obtain a detection ultrasonic characteristic matrix includes: inputting the plurality of detection frequency domain statistical values into a sequence encoder of the first Clip model to obtain detection frequency domain statistical feature vectors; inputting the oscillogram of the detected ultrasonic guided wave signal into an image encoder of the first Clip model to obtain a characteristic vector of the detected ultrasonic guided wave image; and inputting the detected ultrasonic guided wave image feature vector and the detected frequency domain statistical feature vector into a coding optimizer of the first Clip model to obtain the detected ultrasonic feature matrix.

In the above nondestructive testing method for defects of an ultrasonic guided wave pipeline, the inputting the plurality of detection frequency domain statistics values into the sequence encoder of the first Clip model to obtain detection frequency domain statistics feature vectors includes: inputting the plurality of detection frequency domain statistics into a first convolution layer of the multi-scale neighborhood feature extraction module to obtain a first scale detection frequency domain statistics feature vector, wherein the first convolution layer has a first one-dimensional convolution kernel with a first length; inputting the plurality of detection frequency domain statistics into a second convolution layer of the multi-scale neighborhood feature extraction module to obtain a second scale detection frequency domain statistics feature vector, wherein the second convolution layer has a second one-dimensional convolution kernel with a second length, and the first length is different from the second length; and cascading the first scale detection frequency domain statistical characteristic vector and the second scale detection frequency domain statistical characteristic vector to obtain the detection frequency domain statistical characteristic vector.

In the above nondestructive inspection method for ultrasonic guided wave pipeline defects, the inputting the oscillogram of the ultrasonic guided wave signals to be detected into the image encoder of the first Clip model to obtain the characteristic vector of the ultrasonic guided wave image to be detected includes: the layers of the image encoder using the first Clip model are respectively performed in the forward pass of the layers: performing convolution processing on input data to obtain a convolution characteristic diagram; performing mean pooling based on a local feature matrix on the convolution feature map to obtain a pooled feature map; and performing nonlinear activation on the pooled feature map to obtain an activated feature map; the output of the last layer of the image encoder of the first Clip model is the detected ultrasonic guided wave image characteristic vector, and the input of the first layer of the image encoder of the first Clip model is the oscillogram of the detected ultrasonic guided wave signal.

In the above nondestructive testing method for defects of an ultrasonic guided wave pipeline, the inputting the characteristic vector of the ultrasonic guided wave image to be tested and the statistical characteristic vector of the test frequency domain into the coding optimizer of the first Clip model to obtain the ultrasonic characteristic matrix to be tested includes: inputting the detected ultrasonic guided wave image feature vector and the detected frequency domain statistical feature vector into a coding optimizer of the first Clip model according to the following formula to obtain a detected ultrasonic feature matrix; wherein the formula is:

wherein

A transposed vector, V, representing the characteristic vector of the detected ultrasound guided wave image ₂ Represents the detected frequency domain statistical feature vector, M represents the detected ultrasound feature matrix, and->

Representing a matrix multiplication.

In the nondestructive testing method for the defect of the ultrasonic guided wave pipeline, the calculating a difference feature matrix between the detection ultrasonic feature matrix and the reference ultrasonic feature matrix includes: calculating a difference between the detection ultrasound feature matrix and the reference ultrasound feature matrix in the following formulaA difference feature matrix; wherein the formula is:

wherein M is ₁ Representing the detected ultrasound signature matrix, M ₂ Representing the reference ultrasound feature matrix, M _c Representing the difference feature matrix.

In the nondestructive testing method for the defect of the ultrasonic guided wave pipeline, the correcting the eigenvalue of each position of the differential characteristic matrix to obtain a corrected differential characteristic matrix includes: calculating a weight matrix between the detection ultrasonic characteristic matrix and the reference ultrasonic characteristic matrix in a full orthographic projection nonlinear weight weighting mode; and multiplying the difference feature matrix by the weight matrix according to position points to obtain the corrected difference feature matrix.

In the nondestructive testing method for the ultrasonic guided wave pipeline defect, the calculating a weight matrix between the detection ultrasonic characteristic matrix and the reference ultrasonic characteristic matrix in a full orthographic projection nonlinear weight weighting mode includes: calculating the weight matrix between the detection ultrasonic feature matrix and the reference ultrasonic feature matrix by adopting a full orthographic nonlinear weight weighting mode according to the following formula; wherein the formula is:

/>

wherein M is ₁ And M ₂ Respectively being the detection ultrasonic feature matrix and the reference ultrasonic feature matrix, M _w Is the weight matrix, reLU (-) represents the ReLU activation function,

which represents multiplication of matrices and division between a numerator matrix and a denominator matrix as division by location of eigenvalues of the matrices, exp (-) represents an exponential operation of a matrix, which represents calculation of a natural exponent function value raised to the eigenvalue of each location in the matrix.

In the nondestructive testing method for the defects of the ultrasonic guided wave pipeline, the step of passing the corrected differential feature matrix through a classifier to obtain a classification result, wherein the classification result indicates whether the pipeline to be tested has defects includes: expanding the corrected differential feature matrix into a classification feature vector according to a row vector or a column vector; performing full-joint coding on the classification feature vectors by using a full-joint layer of the classifier to obtain coded classification feature vectors; and inputting the encoding classification feature vector into a Softmax classification function of the classifier to obtain the classification result.

According to another aspect of the application, there is provided an ultrasonic guided wave pipe defect nondestructive testing system, comprising: the ultrasonic guided wave acquisition module is used for acquiring a detection ultrasonic guided wave signal and a reference ultrasonic guided wave signal of the pipeline to be detected, wherein the reference ultrasonic guided wave signal is an ultrasonic guided wave signal of the defect-free pipeline; the domain change module is used for respectively carrying out Fourier transform on the detection ultrasonic guided wave signal and the reference ultrasonic guided wave signal so as to obtain a plurality of detection frequency domain statistics values and a plurality of reference frequency domain statistics values; the detection ultrasonic coding module is used for enabling the plurality of detection frequency domain statistics values and the oscillogram of the detection ultrasonic guided wave signal to pass through a first Clip model so as to obtain a detection ultrasonic characteristic matrix; the reference ultrasonic encoding module is used for enabling the plurality of reference frequency domain statistics and the reference ultrasonic guided wave signals to pass through a second Clip model so as to obtain a reference ultrasonic characteristic matrix; a difference module for calculating a difference feature matrix between the detection ultrasonic feature matrix and the reference ultrasonic feature matrix; the eigenvalue correction module is used for correcting the eigenvalue of each position of the differential characteristic matrix to obtain a corrected differential characteristic matrix; and the detection result generation module is used for enabling the corrected differential characteristic matrix to pass through a classifier to obtain a classification result, and the classification result indicates whether the pipeline to be detected has defects or not.

In the above-mentioned ultrasonic guided wave pipeline defect nondestructive test system, the detection ultrasonic coding module includes: a sequence encoding unit, configured to input the multiple detection frequency domain statistics values into a sequence encoder of the first Clip model to obtain a detection frequency domain statistics feature vector; the image coding unit is used for inputting the oscillogram of the detected ultrasonic guided wave signal into the image coder of the first Clip model to obtain a characteristic vector of the detected ultrasonic guided wave image; and the coding optimization unit is used for inputting the detection ultrasonic guided wave image characteristic vector and the detection frequency domain statistical characteristic vector into the coding optimizer of the first Clip model to obtain the detection ultrasonic characteristic matrix.

In the above nondestructive detection system for defects of ultrasonic guided wave pipeline, the sequence encoding unit is further configured to: inputting the plurality of detection frequency domain statistics into a first convolution layer of the multi-scale neighborhood feature extraction module to obtain a first scale detection frequency domain statistics feature vector, wherein the first convolution layer has a first one-dimensional convolution kernel with a first length; inputting the plurality of detection frequency domain statistics into a second convolution layer of the multi-scale neighborhood feature extraction module to obtain a second scale detection frequency domain statistics feature vector, wherein the second convolution layer has a second one-dimensional convolution kernel with a second length, and the first length is different from the second length; and cascading the first scale detection frequency domain statistical characteristic vector and the second scale detection frequency domain statistical characteristic vector to obtain the detection frequency domain statistical characteristic vector.

In the above nondestructive inspection system for defects of ultrasonic guided wave pipeline, the image encoding unit is further configured to: the layers of the image encoder using the first Clip model are respectively performed in the forward pass of the layers: performing convolution processing on input data to obtain a convolution characteristic diagram; performing mean pooling on the convolution feature map based on a local feature matrix to obtain a pooled feature map; and performing nonlinear activation on the pooled feature map to obtain an activated feature map; the output of the last layer of the image encoder of the first Clip model is the detected ultrasonic guided wave image characteristic vector, and the input of the first layer of the image encoder of the first Clip model is the oscillogram of the detected ultrasonic guided wave signal.

In the above nondestructive testing system for defects of ultrasonic guided wave pipes, the encoding optimization unit is further configured to: inputting the detected ultrasonic guided wave image feature vector and the detected frequency domain statistical feature vector into a coding optimizer of the first Clip model according to the following formula to obtain a detected ultrasonic feature matrix; wherein the formula is:

wherein

A transposed vector, V, representing the characteristic vector of the detected ultrasonic guided wave image ₂ Represents the detected frequency domain statistical feature vector, M represents the detected ultrasound feature matrix, and->

Representing a matrix multiplication.

In the above nondestructive testing system for defects of ultrasonic guided wave pipes, the difference module is further configured to: calculating a difference feature matrix between the detection ultrasound feature matrix and the reference ultrasound feature matrix in the following formula; wherein the formula is:

wherein M is ₁ Representing the detected ultrasound signature matrix, M ₂ Representing the reference ultrasound signature matrix, M _c Representing the difference feature matrix.

In the above-mentioned ultrasonic guided wave pipeline defect nondestructive test system, the eigenvalue correction module includes: the weighting unit is used for calculating a weighting matrix between the detection ultrasonic characteristic matrix and the reference ultrasonic characteristic matrix in a full orthographic non-linear weighting mode; and the applying unit is used for multiplying the difference characteristic matrix by the weight matrix according to position points to obtain the corrected difference characteristic matrix.

In the above nondestructive testing system for defects of ultrasonic guided wave pipes, the weighting unit is further configured to: calculating the weight matrix between the detection ultrasonic feature matrix and the reference ultrasonic feature matrix by adopting a full orthographic nonlinear weight weighting mode according to the following formula; wherein the formula is:

wherein, M ₁ And M ₂ Respectively being the detection ultrasonic feature matrix and the reference ultrasonic feature matrix, M _w Is the weight matrix, reLU (-) represents the ReLU activation function,

representing the multiplication of matrices and the division between the numerator matrix and denominator matrix as a division by location of the eigenvalues of the matrices, exp (-) represents the exponential operation of the matrices, which represents the calculation of a natural exponential function value raised to the power of the eigenvalues of each location in the matrix.

In the above system for nondestructive testing of ultrasonic guided wave pipeline defects, the detection result generation module is further configured to: expanding the corrected differential feature matrix into a classification feature vector according to a row vector or a column vector; performing full-joint coding on the classification feature vectors by using a full-joint layer of the classifier to obtain coded classification feature vectors; and inputting the encoding classification feature vector into a Softmax classification function of the classifier to obtain the classification result.

According to still another aspect of the present application, there is provided an electronic apparatus including: a processor; and a memory having stored therein computer program instructions that, when executed by the processor, cause the processor to perform the method of nondestructive inspection of ultrasonic guided wave pipe defects as described above.

According to yet another aspect of the application, there is provided a computer readable medium having stored thereon computer program instructions which, when executed by a processor, cause the processor to perform a method of nondestructive inspection of an ultrasonic guided wave pipe defect as described above.

Compared with the prior art, the ultrasonic guided wave pipeline defect nondestructive testing method provided by the application adopts an artificial intelligence detection technology based on deep learning, so that the detection judgment of whether the pipeline to be detected has defects or not is carried out by carrying out multi-scale characteristic difference comparison on the detection ultrasonic guided wave signal of the pipeline to be detected and the reference ultrasonic guided wave signal of the defect-free pipeline in a high-dimensional space. Thus, the nondestructive inspection of the pipe defect can be accurately performed.

Drawings

The above and other objects, features and advantages of the present application will become more apparent by describing in more detail embodiments of the present application with reference to the attached drawings. The accompanying drawings are included to provide a further understanding of the embodiments of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the principles of the application. In the drawings, like reference numbers generally represent like parts or steps.

Fig. 1 is a scene diagram of an application of the nondestructive testing method for the defect of the ultrasonic guided wave pipeline according to the embodiment of the application.

FIG. 2 is a flow chart of a nondestructive testing method for defects of an ultrasonic guided wave pipeline according to an embodiment of the application.

FIG. 3 is an architecture diagram of a nondestructive testing method for defects of an ultrasonic guided wave pipeline according to an embodiment of the application.

FIG. 4 is a block diagram of an ultrasonic guided wave pipe flaw nondestructive inspection system according to an embodiment of the present application.

Fig. 5 is a block diagram of an electronic device according to an embodiment of the application.

Detailed Description

Hereinafter, example embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be understood that the described embodiments are only some embodiments of the present application and not all embodiments of the present application, and that the present application is not limited by the example embodiments described herein.

Summary of the application

As mentioned in the background, pipelaying is a major production mission that involves all industries. Most pipes are exposed to various complicated environments such as severe weather, impact, corrosion of chemicals inside the pipe, etc., and thus the pipes are susceptible to various defects. In engineering, because the event that the pipeline defect brings great damage to the survival and property safety of people frequently occurs, the detection of the health condition of the pipeline is very important.

At present, pipeline maintenance personnel generally detect the damage of the pipeline by methods such as visual detection, electromagnetic flaw detection and the like, and the methods not only take long time, but also have low detection precision. Therefore, an optimized non-destructive inspection scheme for pipe defects is desired.

At present, deep learning and neural networks have been widely applied in the fields of computer vision, natural language processing, speech signal processing, and the like. In addition, deep learning and neural networks also exhibit a level close to or even exceeding that of humans in the fields of image classification, object detection, semantic segmentation, text translation, and the like.

In recent years, deep learning and development of neural networks provide new solutions for nondestructive detection of pipeline defects.

Accordingly, the nondestructive test is to detect the defects of the tested piece on the premise of not damaging the test piece. The nondestructive detection has the advantages of non-destructiveness, low detection cost, wide detection range and high detection precision. The ultrasonic wave is a mechanical wave with the frequency higher than 20KHz, and is widely applied to the fields of thickness measurement, nondestructive inspection and the like. In practice, the elastic medium of the pipe is limited by edges, so that the ultrasonic wave in the process of propagating the ultrasonic wave is guided wave. Therefore, the defect detection can be performed by comparing the ultrasonic guided wave signal actually detected in the pipe with the reference ultrasonic guided wave signal of the defect-free pipe. However, it is considered that it is difficult to perform comparative observation and detection of the ultrasonic guided wave signal and the pipe defect in practical application because the amount of information contained in the ultrasonic guided wave signal is large, and it is difficult to perform nondestructive detection of the pipe defect because the defect in the pipe is characteristic information of a small scale.

Based on this, in the technical scheme of the application, it is desirable to adopt an artificial intelligence detection technology based on deep learning to perform detection and judgment on whether the pipeline to be detected has defects by performing multi-scale feature difference comparison on the detection ultrasonic guided wave signal of the pipeline to be detected and the reference ultrasonic guided wave signal of the defect-free pipeline in a high-dimensional space. Therefore, nondestructive detection of the pipeline defects can be accurately carried out, and further the health condition of the pipeline can be concerned constantly, so that the loss of the pipeline defects to the survival and property safety of people can be avoided.

Specifically, in the technical scheme of the application, firstly, a detection ultrasonic guided wave signal and a reference ultrasonic guided wave signal of a to-be-detected pipeline are acquired, wherein the reference ultrasonic guided wave signal is an ultrasonic guided wave signal of a defect-free pipeline. Next, considering that the detection ultrasonic guided wave signal and the reference ultrasonic guided wave signal are represented in a waveform diagram in a time domain, an image encoder can be used to perform time domain feature extraction of the detection ultrasonic guided wave signal and the reference ultrasonic guided wave signal, and thus feature differential distribution information can be used to perform defect detection of a pipe. However, when the pipeline defect detection is performed by using the time domain characteristic difference distribution information of the detection ultrasonic guided wave signal and the reference ultrasonic guided wave signal, the time domain characteristic includes more environmental noise interference characteristic information, which may cause a serious influence on the detection result, and therefore, the detection accuracy is improved by further combining the correlation characteristic distribution between the frequency domain statistical characteristic values of the ultrasonic guided wave signal. That is, the detection ultrasonic guided wave signal and the reference ultrasonic guided wave signal are further subjected to fourier transform to obtain a plurality of detection frequency domain statistics and a plurality of reference frequency domain statistics, respectively.

Then, for feature extraction of the detected ultrasonic guided wave signals, a first Clip model comprising a sequence encoder and an image encoder is used for processing the plurality of detected frequency domain statistics and the oscillogram of the detected ultrasonic guided wave signals respectively to obtain a detected ultrasonic feature matrix. Specifically, firstly, considering that the defect feature in the pipeline is small-scale feature information, feature mining is performed on a plurality of detection frequency domain statistical values of the detected ultrasonic guided wave signal by using the sequence encoder of the first Clip model, so as to extract multi-scale implicit association feature distribution information among the plurality of detection frequency domain statistical values, thereby obtaining a detection frequency domain statistical feature vector. In particular, here, the sequence encoder uses a multi-scale neighborhood feature extraction module to perform relevance feature extraction of the plurality of detected frequency domain statistics. And then, performing feature mining on the oscillogram of the detected ultrasonic guided wave signal by using the image encoder of the first Clip model to extract time domain implicit feature distribution information of the detected ultrasonic guided wave signal so as to obtain a detected ultrasonic guided wave image feature vector. And finally, inputting the detected ultrasonic guided wave image characteristic vector and the detected frequency domain statistical characteristic vector into a coding optimizer of the first Clip model to obtain the detected ultrasonic characteristic matrix. Namely, image attribute coding optimization is carried out on the time domain implicit characteristics of the waveform diagram of the detected ultrasonic guided wave signal based on the multi-scale implicit correlation characteristic information of the frequency domain statistical characteristic value of the detected ultrasonic guided wave signal so as to obtain the detected ultrasonic characteristic matrix. Therefore, the obtained detection ultrasonic characteristic matrix not only contains the frequency domain characteristic content of the detection ultrasonic guided wave signal, but also reflects the change rule characteristic of the frequency domain content along with time, and the accuracy of detecting the pipeline defects is improved.

Similarly, for the acoustic feature extraction of the reference ultrasonic guided wave signal, in consideration of the fact that the periodicity feature information of the reference ultrasonic guided wave signal and the periodicity feature of the detection ultrasonic guided wave signal have similar regularity, in the technical solution of the present application, a Clip model is also used for encoding the reference ultrasonic guided wave signal. Specifically, the reference ultrasonic guided wave signals and the plurality of reference frequency domain statistics are processed through a second Clip model comprising a column encoder and an image encoder to obtain a reference ultrasonic characteristic matrix, and then image attribute coding optimization is performed on time domain implicit characteristics of a waveform diagram of the reference ultrasonic guided wave signals based on multi-scale implicit correlation characteristics of the frequency domain statistics of the reference ultrasonic guided wave signals to obtain the reference ultrasonic characteristic matrix.

Further, a difference characteristic matrix between the detection ultrasonic characteristic matrix and the reference ultrasonic characteristic matrix is calculated to represent the difference characteristics of the actual detection ultrasonic guided wave signal of the pipeline to be detected and the reference ultrasonic guided wave signal of the non-defective pipeline in a high-dimensional space, and the difference characteristics are used as a classification characteristic matrix to be classified in a classifier, so that a classification result for representing whether the pipeline to be detected has defects is obtained. Therefore, nondestructive detection of the pipeline defects can be accurately carried out, and further the health condition of the pipeline is concerned constantly, so that the loss of the pipeline defects to the survival and property safety of people is avoided.

Particularly, in the technical solution of the present application, when the difference feature matrix is obtained by calculating the feature matrix between the detection ultrasonic feature matrix and the reference ultrasonic feature matrix, since the calculation of the difference feature matrix is a difference calculation according to the position feature value between the detection ultrasonic feature matrix and the reference ultrasonic feature matrix, it is desirable that the feature distribution between the detection ultrasonic feature matrix and the reference ultrasonic feature matrix keeps the same-phase distribution as much as possible, that is, it is desirable that the negative correlation relationship between the corresponding positions of the detection ultrasonic feature matrix and the reference ultrasonic feature matrix is avoided as much as possible, thereby improving the calculation accuracy of the difference feature matrix.

Therefore, the applicant of the present application adopts a full orthographic nonlinear weighting method to calculate a weighting matrix between the detection ultrasound feature matrix and the reference ultrasound feature matrix, which is expressed as:

M ₁ and M ₂ Respectively being the detection ultrasonic feature matrix and the reference ultrasonic feature matrix, M _c Is the weight matrix and the division between the numerator matrix and the denominator matrix is a division by position of the matrix eigenvalues.

Here, the full forward projection nonlinear weighting guarantees full positive of the projection by the ReLU function to avoid aggregating negatively correlated information, and at the same time introduces a nonlinear weighting mechanism to aggregate eigenvalue distributions of the detected ultrasound signature matrix and the reference ultrasound signature matrix with respect to each other, so that the inherent structure of the weighting matrix can penalize distant connections to strengthen local coupling. In this way, the point multiplication is performed on the difference feature matrix by the weight matrix to perform the position-based weighting, so that the synergistic effect of spatial feature transformation (feature transform) corresponding to the full orthographic projection weighting in the high-dimensional feature space of the detection ultrasonic feature matrix and the reference ultrasonic feature matrix is realized, the calculation accuracy of the difference feature matrix is improved, and the classification accuracy is improved. Therefore, nondestructive detection of the pipeline defects can be accurately carried out, and further the health condition of the pipeline is concerned constantly, so that the loss of the pipeline defects to the survival and property safety of people is avoided.

Based on this, this application has proposed a supersound guided wave pipeline defect nondestructive test method, it includes: acquiring a detection ultrasonic guided wave signal and a reference ultrasonic guided wave signal of a to-be-detected pipeline, wherein the reference ultrasonic guided wave signal is an ultrasonic guided wave signal of a defect-free pipeline; respectively carrying out Fourier transform on the detection ultrasonic guided wave signal and the reference ultrasonic guided wave signal to obtain a plurality of detection frequency domain statistics values and a plurality of reference frequency domain statistics values; enabling the plurality of detection frequency domain statistics values and the oscillogram of the detection ultrasonic guided wave signal to pass through a first Clip model to obtain a detection ultrasonic characteristic matrix; enabling the plurality of reference frequency domain statistics and the reference ultrasonic guided wave signals to pass through a second Clip model to obtain a reference ultrasonic characteristic matrix; calculating a difference feature matrix between the detection ultrasonic feature matrix and the reference ultrasonic feature matrix; correcting the characteristic value of each position of the differential characteristic matrix to obtain a corrected differential characteristic matrix; and passing the corrected differential feature matrix through a classifier to obtain a classification result, wherein the classification result indicates whether the pipeline to be detected has defects or not.

FIG. 1 is an application scene diagram of an ultrasonic guided wave pipeline defect nondestructive testing method according to an embodiment of the application. As shown in fig. 1, in this application scenario, an ultrasonic guided wave detector (e.g., se as illustrated in fig. 1) is first used to acquire a detection ultrasonic guided wave signal of a pipe to be detected (e.g., P as illustrated in fig. 1). Further, the ultrasonic guided wave signals for detecting the pipe to be detected are input into a server (for example, S shown in fig. 1) deployed with an ultrasonic guided wave pipe defect nondestructive detection algorithm, where the server can process the ultrasonic guided wave signals for detecting the pipe to be detected based on the ultrasonic guided wave pipe defect nondestructive detection algorithm to obtain a classification result for indicating whether the pipe to be detected has a defect.

Having described the general principles of the present application, various non-limiting embodiments of the present application will now be described with reference to the accompanying drawings.

Exemplary method

FIG. 2 is a flow chart of a nondestructive testing method for defects of an ultrasonic guided wave pipeline according to an embodiment of the application. As shown in fig. 2, the nondestructive testing method for the defect of the ultrasonic guided wave pipeline according to the embodiment of the application includes: s110, acquiring a detection ultrasonic guided wave signal and a reference ultrasonic guided wave signal of a to-be-detected pipeline, wherein the reference ultrasonic guided wave signal is an ultrasonic guided wave signal of a defect-free pipeline; s120, performing Fourier transform on the detection ultrasonic guided wave signal and the reference ultrasonic guided wave signal respectively to obtain a plurality of detection frequency domain statistics values and a plurality of reference frequency domain statistics values; s130, enabling the plurality of detection frequency domain statistics values and the oscillogram of the detection ultrasonic guided wave signal to pass through a first Clip model to obtain a detection ultrasonic characteristic matrix; s140, enabling the plurality of reference frequency domain statistics values and the reference ultrasonic guided wave signals to pass through a second Clip model to obtain a reference ultrasonic characteristic matrix; s150, calculating a difference feature matrix between the detection ultrasonic feature matrix and the reference ultrasonic feature matrix; s160, correcting the characteristic value of each position of the differential characteristic matrix to obtain a corrected differential characteristic matrix; and S170, enabling the corrected differential characteristic matrix to pass through a classifier to obtain a classification result, wherein the classification result indicates whether the pipeline to be detected has defects or not.

FIG. 3 is an architecture diagram of a nondestructive testing method for defects of an ultrasonic guided wave pipeline according to an embodiment of the application. As shown in fig. 3, in the framework, first, a detection ultrasonic guided wave signal and a reference ultrasonic guided wave signal of a to-be-detected pipe are obtained, where the reference ultrasonic guided wave signal is an ultrasonic guided wave signal of a defect-free pipe. And then, respectively carrying out Fourier transform on the detection ultrasonic guided wave signal and the reference ultrasonic guided wave signal to obtain a plurality of detection frequency domain statistics values and a plurality of reference frequency domain statistics values. Then, the plurality of detection frequency domain statistics and the oscillogram of the detection ultrasonic guided wave signal pass through a first Clip model to obtain a detection ultrasonic characteristic matrix, and meanwhile, the plurality of reference frequency domain statistics and the reference ultrasonic guided wave signal pass through a second Clip model to obtain a reference ultrasonic characteristic matrix. Then, a difference feature matrix between the detection ultrasound feature matrix and the reference ultrasound feature matrix is calculated. And then, correcting the characteristic value of each position of the differential characteristic matrix to obtain a corrected differential characteristic matrix. And then, the corrected differential feature matrix is passed through a classifier to obtain a classification result, and the classification result indicates whether the pipeline to be detected has defects or not.

In step S110, a detection ultrasonic guided wave signal and a reference ultrasonic guided wave signal of the pipe to be detected are obtained, where the reference ultrasonic guided wave signal is an ultrasonic guided wave signal of the pipe without defects. As mentioned in the background, pipelaying is a major production mission that involves all industries. Most pipes are exposed to various complicated environments such as severe weather, impact, corrosion of chemicals inside the pipe, etc., and thus the pipes are susceptible to various defects. In engineering, because the event that the pipeline defect brings great damage to the survival and property safety of people frequently occurs, the detection of the health condition of the pipeline is very important. At present, pipeline maintenance personnel generally detect the damage of a pipeline by methods such as visual detection, electromagnetic flaw detection and the like, and the methods not only take a long time, but also have low detection precision. Therefore, an optimized non-destructive inspection scheme for pipe defects is desired.

Correspondingly, the nondestructive test is to detect the defects of the tested piece on the premise of not damaging the test piece. The nondestructive detection has the advantages of non-destructiveness, low detection cost, wide detection range and high detection precision. The ultrasonic wave is a mechanical wave with the frequency higher than 20KHz, and is widely applied to the fields of thickness measurement, nondestructive inspection and the like. In practice, the elastic medium of the pipe is limited by edges, so that the ultrasonic wave in the process of propagating the ultrasonic wave is guided wave. Therefore, the defect detection can be performed by comparing the ultrasonic guided wave signal actually detected in the pipe with the reference ultrasonic guided wave signal of the defect-free pipe. However, it is considered that it is difficult to perform comparative observation and detection of the ultrasonic guided wave signal in practical use because the amount of information included in the ultrasonic guided wave signal is large, and it is difficult to perform nondestructive detection of a pipe defect because the defect in the pipe is characteristic information of a small scale.

Based on this, in the technical scheme of the application, it is desirable to adopt an artificial intelligence detection technology based on deep learning to perform detection and judgment on whether the to-be-detected pipeline has defects or not by performing multi-scale feature difference comparison on the detection ultrasonic guided wave signal of the to-be-detected pipeline and the reference ultrasonic guided wave signal of the non-defective pipeline in a high-dimensional space. Therefore, nondestructive detection of the pipeline defects can be accurately carried out, and further the health condition of the pipeline is concerned constantly, so that the loss of the pipeline defects to the survival and property safety of people is avoided. Specifically, in the technical scheme of the application, firstly, a detection ultrasonic guided wave signal and a reference ultrasonic guided wave signal of a to-be-detected pipeline are acquired, wherein the reference ultrasonic guided wave signal is an ultrasonic guided wave signal of a defect-free pipeline. Here, the ultrasonic guided wave signal for detection of the pipe to be detected can be obtained by an ultrasonic guided wave instrument, and the reference ultrasonic guided wave signal is existing data.

In step S120, fourier transform is performed on the detected ultrasonic guided wave signal and the reference ultrasonic guided wave signal respectively to obtain a plurality of detected frequency domain statistics and a plurality of reference frequency domain statistics. Considering that the detection ultrasonic guided wave signal and the reference ultrasonic guided wave signal are represented in a waveform diagram in the time domain, an image encoder can be used for extracting the time domain features of the detection ultrasonic guided wave signal and the reference ultrasonic guided wave signal, and the defect detection of the pipeline can be carried out according to the feature difference distribution information. However, when the pipeline defect detection is performed by using the time domain characteristic difference distribution information of the detection ultrasonic guided wave signal and the reference ultrasonic guided wave signal, the time domain characteristics include more environmental noise interference characteristic information, which may cause a serious influence on a detection result, and therefore, the detection accuracy is further improved by combining the correlation characteristic distribution between the frequency domain statistical characteristic values of the ultrasonic guided wave signal. That is, the detection ultrasonic guided wave signal and the reference ultrasonic guided wave signal are further subjected to fourier transform to obtain a plurality of detection frequency domain statistics and a plurality of reference frequency domain statistics, respectively.

In step S130, the plurality of detection frequency domain statistics and the oscillogram of the detected ultrasonic guided wave signal are passed through a first Clip model to obtain a detection ultrasonic feature matrix. And for the feature extraction of the detected ultrasonic guided wave signals, respectively processing the plurality of detected frequency domain statistics values and the oscillogram of the detected ultrasonic guided wave signals by using a first Clip model comprising a sequence encoder and an image encoder to obtain a detected ultrasonic feature matrix.

Specifically, firstly, considering that the defect feature in the pipeline is small-scale feature information, feature mining is performed on a plurality of detection frequency domain statistical values of the detected ultrasonic guided wave signal by using the sequence encoder of the first Clip model, so as to extract multi-scale implicit association feature distribution information among the plurality of detection frequency domain statistical values, thereby obtaining a detection frequency domain statistical feature vector. In particular, here, the sequence encoder uses a multi-scale neighborhood feature extraction module to perform relevance feature extraction of the plurality of detected frequency domain statistics. In an embodiment of the present application, the inputting the plurality of detection frequency domain statistics values into the sequence encoder of the first Clip model to obtain a detection frequency domain statistical feature vector includes: inputting the plurality of detection frequency domain statistics into a first convolution layer of the multi-scale neighborhood feature extraction module to obtain a first scale detection frequency domain statistics feature vector, wherein the first convolution layer has a first one-dimensional convolution kernel with a first length; inputting the plurality of detection frequency domain statistics into a second convolution layer of the multi-scale neighborhood feature extraction module to obtain a second scale detection frequency domain statistics feature vector, wherein the second convolution layer has a second one-dimensional convolution kernel with a second length, and the first length is different from the second length; and cascading the first scale detection frequency domain statistical characteristic vector and the second scale detection frequency domain statistical characteristic vector to obtain the detection frequency domain statistical characteristic vector. Here, the multi-scale neighborhood feature extraction module may extract multi-scale neighborhood correlation features of the multiple detection frequency domain statistics at different time spans to represent multi-scale neighborhood dynamic change feature information of the detection frequency domain statistics in a time dimension, and simultaneously, output features include smoothed features, and original input features are stored to avoid information loss, thereby improving accuracy of subsequent classification.

And then, performing feature mining on the oscillogram of the detected ultrasonic guided wave signal by using the image encoder of the first Clip model to extract time domain implicit feature distribution information of the detected ultrasonic guided wave signal so as to obtain a detected ultrasonic guided wave image feature vector. Specifically, in this embodiment of the application, the inputting the oscillogram of the detected ultrasonic guided wave signal into the image encoder of the first Clip model to obtain the feature vector of the detected ultrasonic guided wave image includes: the layers of the image encoder using the first Clip model are respectively performed in the forward pass of the layers: carrying out convolution processing on input data to obtain a convolution characteristic diagram; performing mean pooling based on a local feature matrix on the convolution feature map to obtain a pooled feature map; and performing nonlinear activation on the pooled feature map to obtain an activated feature map; the output of the last layer of the image encoder of the first Clip model is the detected ultrasonic guided wave image characteristic vector, and the input of the first layer of the image encoder of the first Clip model is the oscillogram of the detected ultrasonic guided wave signal.

And finally, inputting the detected ultrasonic guided wave image characteristic vector and the detected frequency domain statistical characteristic vector into a coding optimizer of the first Clip model to obtain the detected ultrasonic characteristic matrix. Namely, image attribute coding optimization is carried out on the time domain implicit characteristics of the waveform diagram of the ultrasonic guided wave signals to obtain the ultrasonic characteristic matrix. Specifically, in the technical solution of the present application, the inputting the detected ultrasonic guided wave image feature vector and the detected frequency domain statistical feature vector into the coding optimizer of the first Clip model to obtain the detected ultrasonic feature matrix includes: inputting the detected ultrasonic guided wave image feature vector and the detected frequency domain statistical feature vector into a coding optimizer of the first Clip model according to the following formula to obtain a detected ultrasonic feature matrix; wherein the formula is:

wherein

A transposed vector, V, representing the characteristic vector of the detected ultrasound guided wave image ₂ Representing the detected frequency domain statistical feature vector, M denotes the detection ultrasound feature matrix, < > or >>

Representing a matrix multiplication. Therefore, the obtained detection ultrasonic characteristic matrix not only contains the frequency domain characteristic content of the detection ultrasonic guided wave signal, but also reflects the change rule characteristic of the frequency domain content along with time, and the accuracy of detecting the pipeline defects is improved.

In step S140, the plurality of reference frequency domain statistics and the reference ultrasonic guided wave signals are passed through a second Clip model to obtain a reference ultrasonic feature matrix. Similarly, for the acoustic feature extraction of the reference ultrasonic guided wave signal, in consideration of the fact that the periodicity feature information of the reference ultrasonic guided wave signal and the periodicity feature of the detection ultrasonic guided wave signal have similar regularity, in the technical solution of the present application, a Clip model is also used for encoding the reference ultrasonic guided wave signal. Specifically, the reference ultrasonic guided wave signals and the plurality of reference frequency domain statistics values are passed through a second Clip model comprising a column encoder and an image encoder to obtain a reference ultrasonic feature matrix, and then image attribute coding optimization is performed on the time domain implicit features of the waveform diagram of the reference ultrasonic guided wave signals based on the multi-scale implicit correlation features of the frequency domain statistics values of the reference ultrasonic guided wave signals to obtain the reference ultrasonic feature matrix.

In step S150, a difference feature matrix between the detection ultrasound feature matrix and the reference ultrasound feature matrix is calculated. Namely, a difference feature matrix between the detection ultrasonic feature matrix and the reference ultrasonic feature matrix is calculated to represent the difference features of the actual detection ultrasonic guided wave signals of the pipeline to be detected and the reference ultrasonic guided wave signals of the defect-free pipeline in a high-dimensional space.

Specifically, in this embodiment of the present application, the calculating a difference feature matrix between the detection ultrasound feature matrix and the reference ultrasound feature matrix includes: calculating a difference feature matrix between the detection ultrasound feature matrix and the reference ultrasound feature matrix in the following formula; wherein the formula is:

In step S160, the eigenvalues of each position of the differential characteristic matrix are corrected to obtain a corrected differential characteristic matrix. Particularly, in the technical solution of the present application, when the difference feature matrix is obtained by calculating the feature matrix between the detection ultrasonic feature matrix and the reference ultrasonic feature matrix, since the calculation of the difference feature matrix is a difference calculation according to the position feature value between the detection ultrasonic feature matrix and the reference ultrasonic feature matrix, it is desirable that the feature distribution between the detection ultrasonic feature matrix and the reference ultrasonic feature matrix keeps the same-phase distribution as much as possible, that is, it is desirable that the negative correlation relationship between the corresponding positions of the detection ultrasonic feature matrix and the reference ultrasonic feature matrix is avoided as much as possible, thereby improving the calculation accuracy of the difference feature matrix. Therefore, the applicant of the present application calculates the weight matrix between the detection ultrasound feature matrix and the reference ultrasound feature matrix by using a full orthographic non-linear weight weighting method.

Specifically, in this embodiment of the present application, the correcting the eigenvalue of each position of the difference eigenvalue matrix to obtain a corrected difference eigenvalue matrix includes: calculating a weight matrix between the detection ultrasonic characteristic matrix and the reference ultrasonic characteristic matrix in a full orthographic projection nonlinear weight weighting mode; and multiplying the difference feature matrix by the weight matrix according to position points to obtain the corrected difference feature matrix.

More specifically, in this embodiment of the present application, the calculating a weight matrix between the detection ultrasound feature matrix and the reference ultrasound feature matrix by using a full forward projection nonlinear weight weighting method includes: calculating the weight matrix between the detection ultrasonic characteristic matrix and the reference ultrasonic characteristic matrix by adopting a full orthographic nonlinear weight weighting mode according to the following formula; wherein the formula is:

representing multiplication of matrices and the numerator matrix and denominator matrixThe division between them is a division by position of the eigenvalues of the matrix, exp (-) denotes an exponential operation of the matrix, which denotes the calculation of a natural exponential function value raised to the power of the eigenvalues of the individual positions in the matrix.

Here, the full forward projection nonlinear re-weighting guarantees full positive of the projection by the ReLU function to avoid aggregating negatively correlated information, and at the same time introduces a nonlinear re-weighting mechanism to cluster the eigenvalue distributions of the detected ultrasound signature matrix and the reference ultrasound signature matrix with respect to each other, so that the inherent structure of the weight matrix can penalize distant connections to strengthen local coupling. In this way, the point multiplication is performed on the difference feature matrix by the weight matrix to perform the position-based weighting, so that the synergistic effect of spatial feature transformation (feature transform) corresponding to the full orthographic projection weighting in the high-dimensional feature space of the detection ultrasonic feature matrix and the reference ultrasonic feature matrix is realized, the calculation accuracy of the difference feature matrix is improved, and the classification accuracy is improved. Therefore, nondestructive detection of the pipeline defects can be accurately carried out, and further the health condition of the pipeline is concerned constantly, so that the loss of the pipeline defects to the survival and property safety of people is avoided.

In step S170, the corrected differential feature matrix is passed through a classifier to obtain a classification result, where the classification result indicates whether the pipe to be detected has a defect. Therefore, nondestructive detection of the pipeline defects can be accurately carried out, and further the health condition of the pipeline is concerned constantly, so that the loss of the pipeline defects to the survival and property safety of people is avoided.

Specifically, in this embodiment of the present application, the passing the corrected differential feature matrix through a classifier to obtain a classification result, where the classification result indicates whether the pipe to be detected has a defect, includes: expanding the corrected differential feature matrix into classified feature vectors according to row vectors or column vectors; performing full-joint coding on the classification feature vectors by using a full-joint layer of the classifier to obtain coded classification feature vectors; and inputting the encoding classification feature vector into a Softmax classification function of the classifier to obtain the classification result.

In summary, the nondestructive testing method for the defects of the ultrasonic guided wave pipeline based on the embodiment of the present application is illustrated, and an artificial intelligence detection technology based on deep learning is adopted to perform multi-scale feature difference comparison on the detection ultrasonic guided wave signal of the pipeline to be detected and the reference ultrasonic guided wave signal of the defect-free pipeline in a high-dimensional space so as to detect and judge whether the defect exists in the pipeline to be detected. Thus, nondestructive inspection of pipe defects can be accurately performed.

Exemplary System

FIG. 4 is a block diagram of an ultrasonic guided wave pipe flaw nondestructive inspection system according to an embodiment of the present application. As shown in fig. 4, the system 100 for nondestructive testing of defects of ultrasonic guided wave pipes according to the embodiment of the present application includes: the ultrasonic guided wave acquisition module 110 is configured to acquire a detection ultrasonic guided wave signal and a reference ultrasonic guided wave signal of a to-be-detected pipeline, where the reference ultrasonic guided wave signal is an ultrasonic guided wave signal of a defect-free pipeline; a domain change module 120, configured to perform fourier transform on the detected ultrasonic guided wave signal and the reference ultrasonic guided wave signal respectively to obtain a plurality of detected frequency domain statistics and a plurality of reference frequency domain statistics; the detection ultrasonic encoding module 130 is configured to pass the multiple detection frequency domain statistics and the oscillogram of the detection ultrasonic guided wave signal through a first Clip model to obtain a detection ultrasonic feature matrix; a reference ultrasonic encoding module 140, configured to pass the multiple reference frequency domain statistics and the reference ultrasonic guided wave signal through a second Clip model to obtain a reference ultrasonic feature matrix; a difference module 150, configured to calculate a difference feature matrix between the detection ultrasound feature matrix and the reference ultrasound feature matrix; the eigenvalue correction module 160 is configured to correct the eigenvalues of each position of the differential eigenvalue matrix to obtain a corrected differential eigenvalue matrix; and a detection result generating module 170, configured to pass the corrected differential feature matrix through a classifier to obtain a classification result, where the classification result indicates whether the pipeline to be detected has a defect.

In one example, in the above system 100 for nondestructive testing of a defect in an ultrasonic guided wave pipe, the ultrasonic encoding module 130 for testing includes: a sequence encoding unit, configured to input the multiple detection frequency domain statistics values into a sequence encoder of the first Clip model to obtain a detection frequency domain statistics feature vector; the image coding unit is used for inputting the oscillogram of the detected ultrasonic guided wave signal into the image coder of the first Clip model to obtain a characteristic vector of the detected ultrasonic guided wave image; and the coding optimization unit is used for inputting the detection ultrasonic guided wave image characteristic vector and the detection frequency domain statistical characteristic vector into the coding optimizer of the first Clip model to obtain the detection ultrasonic characteristic matrix.

In an example, in the above system 100, the sequence encoding unit is further configured to: inputting the plurality of detection frequency domain statistics into a first convolution layer of the multi-scale neighborhood feature extraction module to obtain a first scale detection frequency domain statistics feature vector, wherein the first convolution layer has a first one-dimensional convolution kernel with a first length; inputting the plurality of detection frequency domain statistics into a second convolution layer of the multi-scale neighborhood feature extraction module to obtain a second scale detection frequency domain statistics feature vector, wherein the second convolution layer has a second one-dimensional convolution kernel with a second length, and the first length is different from the second length; and cascading the first scale detection frequency domain statistical characteristic vector and the second scale detection frequency domain statistical characteristic vector to obtain the detection frequency domain statistical characteristic vector.

In one example, in the above nondestructive inspection system 100 for defects of ultrasonic guided wave pipe, the image encoding unit is further configured to: the layers of the image encoder using the first Clip model are respectively performed in the forward pass of the layers: performing convolution processing on input data to obtain a convolution characteristic diagram; performing mean pooling on the convolution feature map based on a local feature matrix to obtain a pooled feature map; and performing nonlinear activation on the pooled feature map to obtain an activated feature map; the output of the last layer of the image encoder of the first Clip model is the detected ultrasonic guided wave image characteristic vector, and the input of the first layer of the image encoder of the first Clip model is the oscillogram of the detected ultrasonic guided wave signal.

In an example, in the above system 100, the encoding optimization unit is further configured to: inputting the detected ultrasonic guided wave image feature vector and the detected frequency domain statistical feature vector into a coding optimizer of the first Clip model according to the following formula to obtain a detected ultrasonic feature matrix; wherein the formula is:

/>

wherein

Representing a matrix multiplication.

In one example, in the above nondestructive inspection system 100 for defects of ultrasonic guided wave pipes, the difference module 150 is further configured to: calculating a difference feature matrix between the detection ultrasound feature matrix and the reference ultrasound feature matrix in the following formula; wherein the formula is:

In one example, in the above nondestructive inspection system 100 for ultrasonic guided wave pipe defects, the eigenvalue correction module 160 comprises: the weighting unit is used for calculating a weighting matrix between the detection ultrasonic characteristic matrix and the reference ultrasonic characteristic matrix in a full orthographic non-linear weighting mode; and the applying unit is used for multiplying the difference characteristic matrix by the weight matrix according to position points to obtain the corrected difference characteristic matrix.

In one example, in the above nondestructive inspection system 100 for defects of ultrasonic guided wave pipe, the weighting unit is further configured to: calculating the weight matrix between the detection ultrasonic characteristic matrix and the reference ultrasonic characteristic matrix by adopting a full orthographic nonlinear weight weighting mode according to the following formula; wherein the formula is:

wherein M is ₁ And M ₂ Respectively the detection ultrasonic feature matrix and the reference ultrasonic feature matrix, M _w Is the weight matrix, reLU (-) represents the ReLU activation function,

In an example, in the above nondestructive inspection system 100 for defects of ultrasonic guided wave pipes, the inspection result generating module 170 is further configured to: expanding the corrected differential feature matrix into a classification feature vector according to a row vector or a column vector; performing full-concatenation coding on the classification feature vectors by using a full-concatenation layer of the classifier to obtain coded classification feature vectors; and inputting the encoding classification feature vector into a Softmax classification function of the classifier to obtain the classification result.

Here, it can be understood by those skilled in the art that the detailed functions and operations of the respective units and modules in the above-described system 100 for nondestructive inspection of defects of an ultrasonic guided wave pipe have been described in detail in the above description of the method for nondestructive inspection of defects of an ultrasonic guided wave pipe with reference to fig. 1 to 3, and thus, a repetitive description thereof will be omitted.

As described above, the ultrasonic guided wave pipe defect nondestructive inspection system 100 according to the embodiment of the present application can be implemented in various terminal devices, such as a server for ultrasonic guided wave pipe defect nondestructive inspection, and the like. In one example, the ultrasonic guided wave pipe flaw nondestructive inspection system 100 according to the embodiment of the present application can be integrated into a terminal device as one software module and/or hardware module. For example, the ultrasonic guided wave pipe flaw nondestructive detection system 100 can be a software module in the operating system of the terminal device or can be an application developed for the terminal device; of course, the system 100 for nondestructive testing of defects in ultrasonic guided wave pipes can also be one of many hardware modules of the terminal device.

Alternatively, in another example, the guided ultrasonic wave pipe flaw nondestructive inspection system 100 and the terminal device can also be separate devices, and the guided ultrasonic wave pipe flaw nondestructive inspection system 100 can be connected to the terminal device through a wired and/or wireless network and transmit interactive information according to an agreed data format.

Exemplary electronic device

Next, an electronic apparatus according to an embodiment of the present application is described with reference to fig. 5. Fig. 5 is a block diagram of an electronic device according to an embodiment of the application. As shown in fig. 5, the electronic device 10 includes one or more processors 11 and memory 12.

The processor 11 may be a Central Processing Unit (CPU) or other form of processing unit having data processing capabilities and/or instruction execution capabilities, and may control other components in the electronic device 10 to perform desired functions.

Memory 12 may include one or more computer program products that may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory. The volatile memory may include, for example, random Access Memory (RAM), cache memory (cache), and/or the like. The non-volatile memory may include, for example, read Only Memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer readable storage medium and executed by the processor 11 to implement the functions in the ultrasonic guided wave pipe flaw nondestructive testing methods of the various embodiments of the present application described above and/or other desired functions. Various contents such as a detection ultrasonic guided wave signal and a reference ultrasonic guided wave signal of the pipe to be detected can be stored in the computer readable storage medium.

In one example, the electronic device 10 may further include: an input device 13 and an output device 14, which are interconnected by a bus system and/or other form of connection mechanism (not shown).

The input device 13 may include, for example, a keyboard, a mouse, and the like.

The output device 14 can output various information including the classification result to the outside. The output devices 14 may include, for example, a display, speakers, a printer, and a communication network and its connected remote output devices, among others.

Of course, for simplicity, only some of the components of the electronic device 10 relevant to the present application are shown in fig. 5, and components such as buses, input/output interfaces, and the like are omitted. In addition, the electronic device 10 may include any other suitable components depending on the particular application.

Exemplary computer program product and computer-readable storage Medium

In addition to the methods and apparatus described above, embodiments of the present application can also be a computer program product comprising computer program instructions that, when executed by a processor, cause the processor to perform the steps in the functions of the method for nondestructive inspection of defects in an ultrasonic guided wave pipeline according to various embodiments of the present application described in the "exemplary methods" section above of this specification.

The computer program product may be written with program code for performing the operations of embodiments of the present application in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server.

Furthermore, embodiments of the present application may also be a computer readable storage medium having stored thereon computer program instructions that, when executed by a processor, cause the processor to perform the steps in the functions in the method for nondestructive inspection of an ultrasonic guided wave pipe defect according to various embodiments of the present application described in the above section "exemplary method" of this specification.

The computer readable storage medium may take any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may include, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

The foregoing describes the general principles of the present application in conjunction with specific embodiments, however, it is noted that the advantages, effects, etc. mentioned in the present application are merely examples and are not limiting, and they should not be considered essential to the various embodiments of the present application. Furthermore, the foregoing disclosure of specific details is for the purpose of illustration and description and is not intended to be limiting, since the foregoing disclosure is not intended to be exhaustive or to limit the disclosure to the precise details disclosed.

The block diagrams of devices, apparatuses, devices, systems referred to in this application are only used as illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. These devices, apparatuses, devices, systems may be connected, arranged, configured in any manner, as will be appreciated by one skilled in the art. Words such as "including," "comprising," "having," and the like are open-ended words that mean "including, but not limited to," and are used interchangeably therewith. The words "or" and "as used herein mean, and are used interchangeably with, the word" and/or, "unless the context clearly dictates otherwise. The word "such as" is used herein to mean, and is used interchangeably with, the phrase "such as but not limited to".

It should also be noted that in the devices, apparatuses, and methods of the present application, the components or steps may be decomposed and/or recombined. These decompositions and/or recombinations should be considered as equivalents of the present application.

The previous description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects without departing from the scope of the application. Thus, the present application is not intended to be limited to the aspects shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

The foregoing description has been presented for purposes of illustration and description. Furthermore, the description is not intended to limit embodiments of the application to the form disclosed herein. While a number of example aspects and embodiments have been discussed above, those of skill in the art will recognize certain variations, modifications, alterations, additions and sub-combinations thereof.

Claims

1. A nondestructive detection method for defects of ultrasonic guided wave pipelines is characterized by comprising the following steps: acquiring a detection ultrasonic guided wave signal and a reference ultrasonic guided wave signal of a to-be-detected pipeline, wherein the reference ultrasonic guided wave signal is an ultrasonic guided wave signal of a defect-free pipeline; respectively carrying out Fourier transform on the detection ultrasonic guided wave signal and the reference ultrasonic guided wave signal to obtain a plurality of detection frequency domain statistics values and a plurality of reference frequency domain statistics values; enabling the plurality of detection frequency domain statistics values and the oscillogram of the detection ultrasonic guided wave signal to pass through a first Clip model to obtain a detection ultrasonic characteristic matrix; enabling the plurality of reference frequency domain statistics and the reference ultrasonic guided wave signals to pass through a second Clip model to obtain a reference ultrasonic characteristic matrix; calculating a difference feature matrix between the detection ultrasonic feature matrix and the reference ultrasonic feature matrix; correcting the characteristic value of each position of the differential characteristic matrix to obtain a corrected differential characteristic matrix; and passing the corrected differential feature matrix through a classifier to obtain a classification result, wherein the classification result indicates whether the pipeline to be detected has defects or not.

2. The method for nondestructive testing of the defect of the ultrasonic guided wave pipeline according to claim 1, wherein the step of passing the plurality of detection frequency domain statistics and the oscillogram of the detected ultrasonic guided wave signal through a first Clip model to obtain a detection ultrasonic feature matrix comprises the steps of: inputting the plurality of detection frequency domain statistical values into a sequence encoder of the first Clip model to obtain detection frequency domain statistical feature vectors; inputting the oscillogram of the detected ultrasonic guided wave signal into an image encoder of the first Clip model to obtain a characteristic vector of the detected ultrasonic guided wave image; and inputting the detection ultrasonic guided wave image feature vectors and the detection frequency domain statistical feature vectors into a coding optimizer of the first Clip model to obtain the detection ultrasonic feature matrix.

3. The method according to claim 2, wherein the inputting the plurality of detection frequency domain statistics into the sequence encoder of the first Clip model to obtain the detection frequency domain statistical feature vector comprises: inputting the plurality of detection frequency domain statistics into a first convolution layer of the multi-scale neighborhood feature extraction module to obtain a first scale detection frequency domain statistics feature vector, wherein the first convolution layer has a first one-dimensional convolution kernel with a first length; inputting the plurality of detection frequency domain statistics into a second convolution layer of the multi-scale neighborhood feature extraction module to obtain a second scale detection frequency domain statistics feature vector, wherein the second convolution layer has a second one-dimensional convolution kernel with a second length, and the first length is different from the second length; and cascading the first scale detection frequency domain statistical characteristic vector and the second scale detection frequency domain statistical characteristic vector to obtain the detection frequency domain statistical characteristic vector.

4. The method for nondestructive detection of the defect of the ultrasonic guided wave pipeline according to claim 3, wherein the step of inputting the oscillogram of the ultrasonic guided wave signal to be detected into the image encoder of the first Clip model to obtain the characteristic vector of the ultrasonic guided wave image comprises the following steps: the layers of the image encoder using the first Clip model are respectively performed in the forward pass of the layers: performing convolution processing on input data to obtain a convolution characteristic diagram; performing mean pooling based on a local feature matrix on the convolution feature map to obtain a pooled feature map; and carrying out nonlinear activation on the pooling feature map to obtain an activation feature map; the output of the last layer of the image encoder of the first Clip model is the detected ultrasonic guided wave image characteristic vector, and the input of the first layer of the image encoder of the first Clip model is the oscillogram of the detected ultrasonic guided wave signal.

5. The method for nondestructive testing of the defect of the ultrasonic guided wave pipeline according to claim 4, wherein the inputting the feature vector of the ultrasonic guided wave image to be tested and the statistical feature vector of the frequency domain to be tested into a coding optimizer of the first Clip model to obtain the ultrasonic feature matrix to be tested comprises: inputting the detected ultrasonic guided wave image feature vector and the detected frequency domain statistical feature vector into a coding optimizer of the first Clip model according to the following formula to obtain a detected ultrasonic feature matrix; wherein the formula is:

wherein->

Representing a matrix multiplication. />

6. The method for nondestructive testing of defects of ultrasonic guided wave pipelines according to claim 5, wherein the calculating of the differential feature matrix between the test ultrasonic feature matrix and the reference ultrasonic feature matrix comprises: calculating a difference feature matrix between the detection ultrasound feature matrix and the reference ultrasound feature matrix in the following formula; wherein the formula is:

7. The method for nondestructive testing of defects of ultrasonic guided wave pipelines according to claim 6, wherein the step of correcting the eigenvalue of each position of the differential characteristic matrix to obtain a corrected differential characteristic matrix comprises the following steps: calculating a weight matrix between the detection ultrasonic characteristic matrix and the reference ultrasonic characteristic matrix in a full orthographic projection nonlinear weight weighting mode; and multiplying the difference characteristic matrix by the weight matrix according to position points to obtain the corrected difference characteristic matrix.

8. The method for nondestructive testing of the defect of the ultrasonic guided wave pipeline according to claim 7, wherein the calculating the weight matrix between the detection ultrasonic feature matrix and the reference ultrasonic feature matrix by adopting a full orthographic nonlinear re-weighting method comprises: calculating the weight matrix between the detection ultrasonic feature matrix and the reference ultrasonic feature matrix by adopting a full orthographic nonlinear weight weighting mode according to the following formula; wherein the formula is:

wherein M is ₁ And M ₂ Respectively being the detection ultrasonic feature matrix and the reference ultrasonic feature matrix, M _w Is the weight matrix, reLU (·) denotes a ReLU activation function,

9. The method for nondestructive testing of the defect of the ultrasonic guided wave pipeline according to claim 8, wherein the step of passing the corrected differential feature matrix through a classifier to obtain a classification result, wherein the classification result indicates whether the pipeline to be tested has the defect comprises the steps of: expanding the corrected differential feature matrix into classified feature vectors according to row vectors or column vectors; performing full-concatenation coding on the classification feature vectors by using a full-concatenation layer of the classifier to obtain coded classification feature vectors; and inputting the encoding classification feature vector into a Softmax classification function of the classifier to obtain the classification result.