Pipeline leakage crack morphology identification method, device and equipment and readable storage medium

Abstract

The application discloses a pipeline leakage crack morphology identification method, device and equipment and a readable storage medium, utilizes an improved remapping function, carries out fast local Laplace filtering on a wavelet time-frequency graph, and obtains an enhanced wavelet time-frequency graph; the enhanced wavelet time-frequency graph is input into a pipeline leakage crack morphology identification model trained in advance, and the pipeline leakage crack morphology is obtained; wherein the pipeline leakage crack morphology identification model is obtained by using the enhanced wavelet time-frequency graph and the corresponding leakage crack morphology as training samples to train a convolutional neural network based on MSCA-DAA, and the convolutional neural network based on MSCA-DAA comprises a multi-scale convolution module, a dimension perception attention module and a global self-attention layer connected in sequence. The application can highlight the fault frequency band of the wavelet time-frequency graph, smooth the noise interference information, improve the resolution capability of the subsequent model, thereby reducing the misjudgment, and taking into account the accuracy and efficiency of the model.

Description

TECHNICAL FIELD

[0001] The present application belongs to the field of pipeline leakage detection, and particularly relates to a pipeline leakage crack morphology identification method, device, equipment and readable storage medium. BACKGROUND

[0002] Water supply pipeline is an important part of water supply system. As a common method of pipeline connection, welding has strict design, manufacturing and installation standards. However, due to the non-uniform chemical composition and unstable mechanical properties of the welding joint, leakage may occur due to external interference, corrosion, pipe material and construction quality during long-term service, leading to accidents such as fire and explosion, causing significant economic losses, casualties and environmental pollution. Therefore, the problem of online monitoring of pressure pipeline leakage needs to be solved urgently.

[0003] Under the conditions of strong background noise and weak leakage rate, it is necessary to improve the representation ability of the features under the working conditions of weak leakage and strong background noise, and to explore suitable methods for pipeline leakage detection under various working conditions. The patent with publication number CN105864643A discloses a gas pipeline leakage positioning experimental device and method based on RBF neural network, which constructs feature vectors under different leakage pressures by obtaining the maximum peak value of the leakage signal, the (3, 0) node wavelet packet energy and the power spectrum peak value corresponding to the leakage characteristic frequency, to realize the identification of pipeline leakage. The patent with publication number CN118293367A discloses a gas pipeline working condition discrimination method based on multi-scale deep convolution auto-encoding, which uses multi-scale deep convolution layers for feature extraction, and uses multiple convolution kernels in various sizes to perform convolution and operation on the features, making the feature extraction more flexible and comprehensive. The two patents have the following problems: 1. Simple time-frequency domain signals cannot reflect the essential characteristics of leakage signals under strong background noise, which may easily lead to misjudgment; 2. Existing network models only focus on the extraction of multi-scale information, but ignore the problems caused by the subsequent fusion of different scale information. SUMMARY

[0004] In view of the problems in the prior art, the present application provides a pipeline leakage crack morphology identification method, device, equipment and readable storage medium, and proposes a feature extraction method for enhancing wavelet time-frequency diagram, which can highlight the fault frequency band of the wavelet time-frequency diagram, smooth the noise interference information and improve the resolution capability of the subsequent model, thereby reducing misjudgment. Finally, in order to balance the accuracy and efficiency of the model, a multi-scale convolutional neural network with dimension-aware attention (MSCA-DAA) is designed.

[0005] To solve the above technical problems, the present application realizes the following technical solutions:

[0006] According to a first aspect of the present application, a pipeline leakage crack morphology identification method is provided, comprising:

[0007] An acoustic emission signal generated when a pipeline crack leaks is acquired;

[0008] The acoustic emission signal is down-sampled to obtain a down-sampled acoustic emission signal;

[0009] A wavelet time-frequency diagram of the down-sampled acoustic emission signal is extracted to obtain a wavelet time-frequency diagram of the acoustic emission signal;

[0010] The wavelet time-frequency diagram is subjected to fast local Laplacian filtering using an improved remapping function to obtain an enhanced wavelet time-frequency diagram;

[0011] The enhanced wavelet time-frequency diagram is input into a pre-trained pipeline leakage crack morphology identification model to obtain a pipeline leakage crack morphology; wherein the pipeline leakage crack morphology identification model is obtained by training a MSCA-DAA-based convolutional neural network using the enhanced wavelet time-frequency diagram and its corresponding leakage crack morphology as training samples, the MSCA-DAA-based convolutional neural network comprising a multi-scale convolution module, a dimension perception attention module and a global self-attention layer connected in sequence, the dimension perception attention module being configured to implement average pooling operations along a vertical dimension and a horizontal dimension, average pooling operations along a channel dimension and a horizontal dimension, and average pooling operations along a channel dimension and a vertical dimension, and finally fuse information along the channel dimension, the vertical dimension and the horizontal dimension through weighted fusion.

[0012] In a possible implementation form of the first aspect, the improved remapping function is:

[0013] r(i)=i-(i-g)(-m factor G σ (i-g) α )

[0014] wherein r(i) is the improved remapping function; G σ (i-g) is a Gaussian function with an intensity threshold value of σ, wherein g is a coefficient of a Gaussian pyramid, i is a coefficient of an input image at a pixel (x, y), G σ (i-g)=exp(-(i-g) 2 / 2σ 2 ); m factor is a magnification coefficient, and α is a control coefficient.

[0015] In a possible implementation form of the first aspect, the wavelet time-frequency diagram is subjected to fast local Laplacian filtering using the improved remapping function, specifically as follows:

[0016] a. using a point-by-point nonlinear function to obtain improved Gaussian pyramid coefficients g = G l [I](x,y), wherein I is an input image, l is the number of layers of a Gaussian pyramid, G l is a Gaussian function corresponding to the Gaussian pyramid layer l;

[0017] b. obtaining an intermediate image r(I g ), wherein different intermediate images are obtained for different g;

[0018] c. obtaining a result image L l [O](x,y), wherein L is a Laplace operation, and O is an output result image.

[0019] In a possible implementation of the first aspect, the multi-scale convolution module includes convolution kernels of three scales of 3x3, 5x5 and 7x7, and performs a Concatenation operation after completing three convolutions of different scales on the same input.

[0020] In a possible implementation of the first aspect, the multi-scale convolution module is configured to perform feature extraction on the enhanced wavelet time-frequency graph, the dimension-aware attention module is configured to perform weighted fusion on the extracted features to obtain fused features, and the global self-attention layer is configured to perform global self-attention calculation on the fused features.

[0021] In a possible implementation of the first aspect, the wavelet time-frequency graph extraction on the down-sampled acoustic emission signal is specifically:

[0022] The wavelet time-frequency graph of the down-sampled acoustic emission signal is obtained by using a wavelet basis function to perform continuous wavelet transform on the down-sampled acoustic emission signal.

[0023] According to a second aspect of the present application, a pipeline leakage crack morphology recognition device is provided, comprising:

[0024] An acquisition module is configured to acquire an acoustic emission signal generated when a pipeline crack leaks;

[0025] A down-sampling module is configured to perform down-sampling processing on the acoustic emission signal to obtain a down-sampled acoustic emission signal;

[0026] An extraction module is configured to perform wavelet time-frequency graph extraction on the down-sampled acoustic emission signal to obtain a wavelet time-frequency graph of the acoustic emission signal;

[0027] A filtering module is configured to use an improved remapping function to perform fast local Laplace filtering on the wavelet time-frequency graph to obtain an enhanced wavelet time-frequency graph;

[0028] The recognition module is configured to input the enhanced wavelet time-frequency diagram into a pre-trained pipeline leakage crack morphology recognition model to obtain a pipeline leakage crack morphology.

[0029] According to a third aspect of the present application, there is provided an apparatus comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the pipeline leakage crack morphology recognition method when executing the computer program.

[0030] According to a fourth aspect of the present application, there is provided a computer readable storage medium storing a computer program, wherein the computer program implements the steps of the pipeline leakage crack morphology recognition method when executed by a processor.

[0031] Compared with the prior art, the present application has at least the following beneficial effects:

[0032] The application provides a pipeline leakage crack morphology identification method, wavelet time-frequency diagram extraction is performed on the acoustic emission signal after downsampling, and a modified remapping function is used to perform fast local Laplace filtering on the wavelet time-frequency diagram, the edge retention and contour information detail enhancement of the fast local Laplace filtering are obtained, and the enhanced wavelet time-frequency diagram is obtained, which provides more reliable input for a pipeline leakage crack morphology identification model; meanwhile, the fast local Laplace filtering effectively enhances the contrast of the wavelet time-frequency diagram, so that the information of the fault frequency band is more prominent, thereby reducing the misjudgment of the pipeline leakage crack morphology identification model.

[0033] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the following preferred embodiments are described in detail below, and the accompanying drawings are described as follows. BRIEF DESCRIPTION OF DRAWINGS

[0034] In order to more clearly illustrate the technical solutions in the specific embodiments of the present application, the following will briefly introduce the drawings needed to be used in the description of the specific embodiments. Obviously, the drawings in the following description are some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.

[0035] Figure 1 The flow chart of the pipeline leakage crack morphology identification method of the present application.

[0036] Figure 2 The schematic diagram of the acoustic emission signal acquisition system in the embodiment.

[0037] Figure 3 The pipeline diagram of different morphology cracks in the embodiment.

[0038] Figure 4a The wavelet time-frequency diagram of the curved crack pipeline leakage in the embodiment, Figure 4b The enhanced wavelet time-frequency diagram of the curved crack pipeline leakage in the embodiment.

[0039] Figure 5The diagram shows the structure of the convolutional neural network based on MSCA-DAA in this embodiment.

[0040] In the figure: 1-Acoustic emission sensor; 2-Preamplifier; 3-Data acquisition card; 4-Host computer; 5-Weld cracked pipe with different crack morphologies. Detailed Implementation

[0041] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0042] like Figure 1 As shown, this embodiment of the invention provides a method for identifying the morphology of pipeline leakage cracks, specifically including the following steps:

[0043] S1. Obtain the acoustic emission signal generated when there is a leak at the crack in the pipeline.

[0044] Specifically, a specialized acoustic emission detection system is configured to capture acoustic emission signals when a pipeline crack leaks. This system includes a high-sensitivity acoustic emission sensor, a data acquisition unit (DAQ), and a signal preprocessing module. The acoustic emission sensor needs to be installed at the pipeline to be inspected to accurately capture the weak acoustic emission signals generated during a leak.

[0045] The acoustic emission detection system is activated to continuously monitor areas of the pipeline suspected of having cracks. When the system detects an abnormal acoustic emission signal (i.e., a signal generated when the pipeline is leaking due to a crack), the data acquisition mechanism is immediately triggered to record and save complete acoustic emission signal data.

[0046] S2. The acoustic emission signal is downsampled to obtain the downsampled acoustic emission signal.

[0047] Specifically, the original acoustic emission signal is downsampled to reduce the amount of data and improve the efficiency of subsequent processing. The specific downsampling method can be selected according to the signal characteristics and system requirements. For example, downsampling based on Shannon's theorem can yield an undistorted acoustic emission signal, i.e., the downsampled acoustic emission signal.

[0048] S3. Extract the wavelet time-frequency diagram of the downsampled acoustic emission signal to obtain the wavelet time-frequency diagram of the acoustic emission signal.

[0049] Specifically, the continuous wavelet transform (CWT) is performed on the down-sampled acoustic emission signal to obtain the energy distribution of the signal at different time and frequency scales. A suitable wavelet basis function is selected to ensure that the key features in the signal can be fully captured. The results of the wavelet transform are converted into a time-frequency diagram, i.e. a three-dimensional image of time-frequency-energy density. The time-frequency diagram can intuitively show the frequency components and their energy intensity of the signal over time, providing a basis for subsequent feature extraction and recognition.

[0050] S4, using the improved remapping function, the wavelet time-frequency diagram is quickly locally Laplace filtered to obtain an enhanced wavelet time-frequency diagram.

[0051] Specifically, the generated wavelet time-frequency diagram is processed by fast local Laplace filtering using the improved remapping function, aiming to enhance the edge and texture information in the image, improve the contrast and clarity of the image, and facilitate subsequent crack morphology recognition. By adjusting the filtering parameters, the best image enhancement effect is achieved.

[0052] The improved remapping function is specifically:

[0053] r(i) = i - (i-g)(-m factor G σ (i-g) α )

[0054] In the formula, r(i) is the improved remapping function; G σ (i-g) is a Gaussian function with intensity threshold value σ, where g is the coefficient of the Gaussian pyramid, i is the coefficient of the input image at pixel (x, y), G σ (i-g) = exp(-(i-g) 2 / 2σ 2 ); m factor is the magnification coefficient, and a is the control coefficient.

[0055] S5, the enhanced wavelet time-frequency diagram is input into a pre-trained pipeline leakage crack morphology recognition model to obtain the pipeline leakage crack morphology. The pipeline leakage crack morphology recognition model is obtained by training the convolutional neural network based on MSCA-DAA using the enhanced wavelet time-frequency diagram and its corresponding leakage crack morphology as training samples.

[0056] In combination Figure 5As shown, the convolutional neural network based on MSCA-DAA includes a multi-scale convolutional module, a dimension-aware attention module, and a global self-attention layer connected in sequence. The dimension-aware attention module is used to implement average pooling operations along the vertical and horizontal dimensions (VH Avg pool), average pooling operations along the channel and horizontal dimensions (CH Avg pool), and average pooling operations along the channel and vertical dimensions (CV Avg pool). Finally, it solves the semantic inconsistency problem caused by convolutional operations at different scales by weighted fusion of information from the channel, vertical, and horizontal dimensions.

[0057] like Figure 5 As shown, the multi-scale convolution module includes convolutional kernels of three scales: 3×3, 5×5, and 7×7. After performing three convolutions at different scales on the same input, a concatenation operation is performed. The multi-scale convolution module is used to extract features from the enhanced wavelet time-frequency map. The dimension-aware attention module is used to perform weighted fusion of the extracted features to obtain fused features. The global self-attention layer is used to perform global self-attention calculation on the fused features, specifically: for a given pixel... First, extract a value starting with x. ij A local region ab∈X centered at X with a spatial extent of k k (i,j), referred to as the memory block, is used to calculate the single-head attention for pixel output as follows:

[0058]

[0059] Where, q ij =W Q x ij k ab =W K x ab v ab =W V x ab It is a linear transformation between the pixel at position ij and its neighboring pixels; softmax ab This represents the softmax applied to the computation of all logits within the ij neighborhood; Both involve learning transformations, and their essence is similar to variable weights in convolution kernels.

[0060] Specifically, the pre-training of the pipeline leakage crack morphology recognition model is as follows: a series of enhanced wavelet time-frequency maps and their corresponding pipeline leakage crack morphology data are prepared in advance as training samples. Then, a convolutional neural network model based on MSCA-DAA (Multi-Scale Channel Attention with Dense Aggregation and Adaptive Activation) is constructed. This model improves the feature representation capability and recognition accuracy through multi-scale feature extraction, channel attention mechanism, dense connection, and adaptive activation function strategy. The MSCA-DAA-based convolutional neural network is trained using the training samples until the predetermined performance indicators are reached.

[0061] After the model training is completed, the enhanced wavelet time-frequency map is input into the trained pipeline leakage crack morphology recognition model. The model automatically extracts the key features in the image and performs classification and recognition, and finally outputs the morphology description of the pipeline leakage crack. The morphology description can include specific parameters such as the length, width, depth, and direction of the crack, as well as information such as the geometric shape and distribution characteristics of the crack.

[0062] In one implementation, the wavelet time-frequency map is subjected to fast local Laplacian filtering using an improved remapping function, specifically:

[0063] a. An improved Gaussian pyramid coefficient g = G l [O] (x, y) is obtained using a point-by-point nonlinear function, where I is the input image, l is the number of layers of the Gaussian pyramid, G l is the corresponding Gaussian function when the number of layers of the Gaussian pyramid is l;

[0064] b. An intermediate image r(I g ) is obtained, where different intermediate images are obtained for different g;

[0065] c. A result image L l [O] (x, y) is obtained, where L is the Laplace operation and O is the output result image.

[0066] In an implementation manner, regarding wavelet time-frequency map extraction on the down-sampled acoustic emission signal, specifically, considering the non-stationary and multi-scale characteristics of the pipeline leakage acoustic emission signal, a Daubechies (dbN) series wavelet is used as a base function. Specifically, the db4 wavelet can be selected because it has a good balance between the time domain and the frequency domain, can capture the detailed information of the signal, and can maintain a certain smoothness, which is helpful for subsequent feature extraction and identification. The selected db4 wavelet base is used to perform continuous wavelet transform on the down-sampled acoustic emission signal. Through the continuous wavelet transform, a group of coefficients at different scales (frequencies) and shifts (times) is obtained. These coefficients reflect the energy distribution of the signal at different times and frequencies. Visualizing these coefficients can obtain the wavelet time-frequency map of the acoustic emission signal. The generated wavelet time-frequency map can clearly show the time-frequency characteristics of the pipeline leakage acoustic emission signal, including the time of the leakage event, the frequency distribution range, and the energy intensity, etc. These characteristic information provides an important basis for feature extraction and crack morphology identification.

[0067] For example, the wavelet base function formula is represented as:

[0068]

[0069] In the formula, a is a scale stretching factor, τ is a shift moving factor, ψ a,τ (t) is a base wavelet function attached to parameters a and τ, ψ a,τ (t) is a continuous base wavelet function.

[0070] The continuous wavelet transform on the down-sampled acoustic emission signal can be represented as:

[0071]

[0072] In the formula, f(t) is the down-sampled acoustic emission signal, WT f (a, τ) is the wavelet transform coefficient.

[0073] Embodiment case:

[0074] As Figure 2 shown is an acoustic emission signal collection schematic diagram of the pipeline weld crack leakage in the embodiment, mainly including an acoustic emission sensor 1, a preamplifier 2, a data acquisition card 3, an upper computer 4, and a weld crack pipeline 5 with different crack morphologies, wherein the acoustic emission sensor 1, the preamplifier 2, the data acquisition card 3, and the upper computer 4 are sequentially connected to form an acoustic emission signal collection system, and the acoustic emission signal collection system collects acoustic emission signals in real time during the pipeline leakage process.

[0075] In this embodiment, the acoustic emission sensor 1 is 100 mm away from the leakage center, the diameter of the weld crack pipeline 5 with different crack morphologies is 60 mm, the wall thickness is 4 mm, and the pipeline is connected by butt welding through two sections of 50 cm galvanized steel pipes. The pipeline is connected by flange connection at both ends, coupling agent is used to ensure the close fit between the acoustic emission sensor 1 and the weld crack pipeline 5 with different crack morphologies, and adhesive tape is used to ensure that the acoustic emission sensor 1 does not move during the leakage of the weld crack pipeline 5 with different crack morphologies, and the sampling rate is 1 MHz.

[0076] Three pipelines with different crack morphologies are used in this embodiment, which are axial cracks, curved cracks and circumferential cracks, as shown in Figure 3 .

[0077] Step one: use the pipeline weld crack leakage acoustic emission monitoring system provided in Figure 2 to collect pipeline leakage acoustic emission signals under different crack morphologies.

[0078] Step two: taking the curved crack as an example, the collected acoustic emission signals are down-sampled, and the down-sampled acoustic emission signals are wavelet transformed to obtain the wavelet time-frequency diagram as shown in Figure 4a .

[0079] Step three: using the improved remapping function, the obtained wavelet time-frequency diagram is quickly locally Laplacian filtered to obtain the enhanced wavelet time-frequency diagram as shown in Figure 4b .

[0080] Step four: repeat steps one to three to establish a pipeline leakage enhanced wavelet time-frequency diagram dataset under three different crack morphologies.

[0081] Step five: input the enhanced wavelet time-frequency diagram dataset obtained in step four into the pipeline leakage crack morphology recognition model, which is trained by the convolutional neural network based on MSCA-DAA as shown in Figure 5 , to complete the classification and recognition of input features, and the highest accuracy is 98.22%.

[0082] From the above experiment, the application can fully utilize the information of the acoustic emission signal, extract the essential characteristics of the pipeline leakage acoustic emission signal, and the information of the fault frequency band is obviously strengthened, and the information of the non-fault frequency band is obviously inhibited and smoothed. Combined with the convolutional neural network based on MSCA-DAA, an accurate recognition model is constructed, and the accurate recognition of the pipeline leakage acoustic emission signal under different working conditions is realized, thereby providing an accurate and reliable method for pipeline leakage crack morphology recognition. Specifically, the acoustic emission signal is fully utilized, the improved remapping function is used for fast local Laplacian filtering processing of the wavelet time-frequency graph, the enhanced wavelet time-frequency graph is used for feature extraction and recognition of pipeline leakage of different morphology cracks, and the accuracy can reach 98.22%. The method provided by the application is simple, the physical meaning of the feature is clear, and the method has high reliability and robustness, and provides an effective method for online positioning and recognition of pipeline leakage crack morphology.

[0083] In one embodiment, the application provides a pipeline leakage crack morphology recognition device, comprising:

[0084] The acquisition module is configured to acquire an acoustic emission signal generated when a pipeline crack leaks.

[0085] The downsampling module is configured to perform downsampling processing on the acoustic emission signal to obtain a downsampled acoustic emission signal.

[0086] The extraction module is configured to extract a wavelet time-frequency graph of the downsampled acoustic emission signal to obtain the wavelet time-frequency graph of the acoustic emission signal.

[0087] The filtering module is configured to use an improved remapping function to perform fast local Laplacian filtering on the wavelet time-frequency graph to obtain an enhanced wavelet time-frequency graph.

[0088] The recognition module is configured to input the enhanced wavelet time-frequency graph into a pre-trained pipeline leakage crack morphology recognition model to obtain a pipeline leakage crack morphology. The pipeline leakage crack morphology recognition model is obtained by training a convolutional neural network based on MSCA-DAA using the enhanced wavelet time-frequency graph and its corresponding leakage crack morphology as training samples. The convolutional neural network based on MSCA-DAA comprises a multi-scale convolution module, a dimension perception attention module and a global self-attention layer connected in sequence. The dimension perception attention module is configured to perform average pooling operations along the vertical dimension and the horizontal dimension, average pooling operations along the channel dimension and the horizontal dimension, and average pooling operations along the channel dimension and the vertical dimension, and finally fuse the information of the channel dimension, the vertical dimension and the horizontal dimension through weighted fusion.

[0089] The foregoing embodiments of the pipeline leakage crack morphology identification method all relate to the functions of the function modules of a pipeline leakage crack morphology identification device, and thus the detailed descriptions of the functions of the function modules are not repeated. The division of the modules in the embodiments of the present application is illustrative, and is merely a logical function division. In actual implementation, another division manner can be used. In addition, the function modules in the various embodiments of the present application can be integrated in one processor, or can be physically separated, or two or more modules can be integrated in one module. The integrated module can be implemented in the form of hardware or in the form of a software function module.

[0090] In another embodiment of the present application, a computer device is provided, which includes a processor and a memory. The memory is configured to store a computer program, and the computer program includes program instructions. The processor is configured to execute the program instructions stored in the computer storage medium. The processor can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, and the like. The processor is the computing core and control core of the terminal, and is suitable for implementing one or more instructions, and is specifically suitable for loading and executing one or more instructions in the computer storage medium to implement a corresponding method flow or a corresponding function. The processor in the embodiments of the present application can be used for the operation of the pipeline leakage crack morphology identification method.

[0091] In still another embodiment, the present application provides a storage medium, specifically a computer readable storage medium (Memory), which is a memory device in a computer device, for storing programs and data. It can be understood that the computer readable storage medium here can include the built-in storage medium of the computer device, and of course can also include the expansion storage medium supported by the computer device. The computer readable storage medium provides a storage space, which stores the operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by the processor are also stored in the storage space, and these instructions can be one or more computer programs (including program codes). It should be noted that the computer readable storage medium here can be a high-speed RAM memory, or a non-volatile memory such as at least one disk memory. One or more instructions stored in the computer readable storage medium can be loaded and executed by the processor to implement the corresponding steps of the pipeline leakage crack morphology identification method in the above embodiment.

[0092] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage, etc.) containing computer-usable program code.

[0093] The present application is described with reference to the flowcharts and / or block diagrams of the method, device (system), and computer program product according to the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of the flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a means for implementing the functions specified in the flowcharts and / or block diagrams. Figure 1 The functions specified in one or more flows and / or blocks Figure 1 The means for implementing the functions specified in one or more flows and / or blocks.

[0094] These computer program instructions can also be stored in a computer readable storage medium, which can guide the computer or other programmable data processing devices to work in a specific manner, so that the instructions stored in the computer readable storage medium produce a product including instruction means, which implements the functions specified in the flowcharts and / or block diagrams. Figure 1 The functions specified in one or more flows and / or blocksFigure 1 the function specified in the one or more blocks.

[0095] These computer program instructions can also be loaded into a computer or other programmable data processing devices, so that a series of operation steps are performed on the computer or other programmable devices to generate a computer-implemented process, thus the instructions executed on the computer or other programmable devices provide a process for implementing the flowchart Figure 1 the flowchart or flowcharts and / or a block Figure 1 the function specified in the one or more blocks.

[0096] In the present application, the terms "one embodiment", "some embodiments", "example", "specific example" or "some examples" etc. mean that the specific feature, structure, material or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present application. In the description of the present application, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Also, the specific features, structures, materials or characteristics described can be combined in any appropriate manner in one or more embodiments or examples. In addition, the skilled person in the art can combine and combine the different embodiments or examples described in the present specification and the features of the different embodiments or examples, without contradiction.

[0097] Finally, it should be noted that the above-described embodiments are merely specific embodiments of the present application, which are used to illustrate the technical solutions of the present application, but not to limit the same. The protection scope of the present application is not limited thereto, although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can modify or easily think of changes to the technical solutions recorded in the foregoing embodiments, or make equivalent replacements to some technical features thereof, without departing from the technical scope disclosed by the present application; and these modifications, changes or replacements do not make the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for identifying the morphology of pipeline leakage cracks, characterized in that, include: Acquire acoustic emission signals generated when a leak occurs at a pipe crack; The acoustic emission signal is downsampled to obtain a downsampled acoustic emission signal; Wavelet time-frequency plot extraction is performed on the downsampled acoustic emission signal to obtain the wavelet time-frequency plot of the acoustic emission signal; Using an improved remapping function, a fast local Laplace filter is applied to the wavelet time-frequency plot to obtain an enhanced wavelet time-frequency plot. The enhanced wavelet time-frequency image is input into a pre-trained pipeline leakage crack morphology recognition model to obtain the pipeline leakage crack morphology. The pipeline leakage crack morphology recognition model is obtained by training an MSCA-DAA-based convolutional neural network using the enhanced wavelet time-frequency image and its corresponding leakage crack morphology as training samples. The MSCA-DAA-based convolutional neural network includes a multi-scale convolutional module, a dimension-aware attention module, and a global self-attention layer connected sequentially. The dimension-aware attention module is used to implement average pooling operations along the vertical and horizontal dimensions, along the channel and horizontal dimensions, and along the channel and vertical dimensions, and finally fuses the information from the channel, vertical, and horizontal dimensions through weighted fusion.

2. The method for identifying pipeline leakage crack morphology according to claim 1, characterized in that, The improved remapping function is: r(i)=i-(i-g)(-m factor G σ (i-g) α ) In the formula, r(i) is the improved remapping function; G σ (ig) is the Gaussian function when the intensity threshold is σ, where g is the coefficient of the Gaussian pyramid, i is the coefficient of the input image at pixel (x,y), and G... σ (ig)=exp(-(ig) 2 / 2σ 2 );m factor α is the amplification factor, and α is the control factor.

3. The method for identifying pipeline leakage crack morphology according to claim 2, characterized in that, The step of using an improved remapping function to perform fast local Laplace filtering on the wavelet time-frequency graph is as follows: a. Obtaining the improved Gaussian pyramid coefficients g = G using pointwise nonlinear functions. l [I](x,y), where I is the input image, l is the number of layers in the Gaussian pyramid, and G... l It is the Gaussian function corresponding to the number of layers in the Gaussian pyramid being l; b. Obtain the intermediate image r(I) g ), where different intermediate images are obtained for different g; c. Obtain the resulting image L l [O](x,y), where L is the Laplacian operation and O is the output image.

4. The method for identifying pipeline leakage crack morphology according to claim 1, characterized in that, The multi-scale convolution module includes convolution kernels of three scales: 3×3, 5×5, and 7×7. After performing three convolutions of different scales on the same input, a concatenation operation is performed on it.

5. The method for identifying pipeline leakage crack morphology according to claim 1, characterized in that, The multi-scale convolution module is used to extract features from the enhanced wavelet time-frequency map, the dimension-aware attention module is used to perform weighted fusion of the extracted features to obtain fused features, and the global self-attention layer is used to perform global self-attention calculation on the fused features.

6. The method for identifying pipeline leakage crack morphology according to claim 1, characterized in that, The process of extracting the wavelet time-frequency graph from the downsampled acoustic emission signal specifically involves: The downsampled acoustic emission signal is subjected to continuous wavelet transform using wavelet basis functions to obtain the wavelet time-frequency diagram of the acoustic emission signal.

7. A device for identifying the morphology of pipe leak cracks, characterized in that, include: The acquisition module is used to acquire acoustic emission signals generated when a leak occurs at a crack in the pipeline. The downsampling module is used to downsample the acoustic emission signal to obtain a downsampled acoustic emission signal. The extraction module is used to extract the wavelet time-frequency diagram of the downsampled acoustic emission signal to obtain the wavelet time-frequency diagram of the acoustic emission signal; The filtering module is used to perform fast local Laplace filtering on the wavelet time-frequency graph using an improved remapping function to obtain an enhanced wavelet time-frequency graph. The identification module is used to input the enhanced wavelet time-frequency image into a pre-trained pipeline leakage crack morphology identification model to obtain the pipeline leakage crack morphology. The pipeline leakage crack morphology identification model is obtained by training an MSCA-DAA-based convolutional neural network using the enhanced wavelet time-frequency image and its corresponding leakage crack morphology as training samples. The MSCA-DAA-based convolutional neural network includes a multi-scale convolutional module, a dimension-aware attention module, and a global self-attention layer connected in sequence. The dimension-aware attention module is used to implement average pooling operations along the vertical and horizontal dimensions, along the channel and horizontal dimensions, and along the channel and vertical dimensions, and finally fuses the information from the channel, vertical, and horizontal dimensions through weighted fusion.

8. An apparatus comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the pipeline leakage crack morphology identification method as described in any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the pipeline leakage crack morphology identification method as described in any one of claims 1 to 6.

Images