A drainage pipe corrosion detection method and device based on ultrasonic guided waves

Abstract

The present invention relates to the technical field of pipeline corrosion distribution detection, and discloses a drainage pipeline corrosion detection method and device based on ultrasonic guided waves. The method comprises: obtaining ultrasonic guided wave signals from the interior of a target drainage pipeline, transmitted by multiple ultrasonic guided wave transducers; the multiple ultrasonic guided wave transducers are evenly arranged circumferentially along the inner wall of the target drainage pipeline; performing signal conversion on the ultrasonic guided wave signals to obtain effective guided wave signals of the corrosion area; performing signal feature analysis on the effective guided wave signals of the corrosion area to obtain corrosion area distribution data; based on the effective guided wave signals of the corrosion area, using a convolutional neural network model to predict the corrosion state of the drainage pipeline to obtain corrosion development trend data; and obtaining drainage pipeline corrosion detection results based on the corrosion area distribution data and the corrosion development trend data. The present invention realizes full process automation for drainage pipeline corrosion detection, improving detection efficiency and accuracy.

Description

Technical Field

[0001] The present invention relates to the technical field of pipeline corrosion distribution detection, and in particular to a drainage pipeline corrosion detection method and device based on ultrasonic guided waves. Background Art

[0002] Drainage pipes, a vital component of urban infrastructure, collect and transport rainwater and sewage. Over time, internal corrosion can easily occur, leading to thinning of pipe walls and even perforations, which can cause leakage, structural damage, and other problems. These issues not only impact the proper functioning of drainage systems but can also pose a threat to the surrounding environment and infrastructure. Therefore, detecting and assessing internal corrosion in drainage pipes is crucial for ensuring their safe operation.

[0003] However, since the detection of internal corrosion conditions of drainage pipes requires a lot of manual intervention, it not only increases labor costs but also easily causes human errors, affecting the accuracy of the detection results. Summary of the Invention

[0004] In view of this, the present invention provides a drainage pipe corrosion detection method and device based on ultrasonic guided waves to solve the problem of low detection accuracy of the internal corrosion condition of the drainage pipe.

[0005] In a first aspect, the present invention provides a drainage pipe corrosion detection method based on ultrasonic guided waves, the method comprising:

[0006] Acquiring ultrasonic guided wave signals inside a target drainage pipe sent by a plurality of ultrasonic guided wave transducers; the plurality of ultrasonic guided wave transducers are evenly arranged along the circumference of the inner wall of the target drainage pipe to form an ultrasonic guided wave transducer array;

[0007] Perform signal conversion on the ultrasonic guided wave signal to obtain the effective guided wave signal of the corrosion area;

[0008] Perform signal feature analysis on the effective guided wave signal in the corrosion area to obtain the distribution data of the corrosion area;

[0009] Based on the effective guided wave signals in the corrosion area, the convolutional neural network model is used to predict the corrosion status of the drainage pipe and obtain the corrosion development trend data.

[0010] The drainage pipe corrosion detection results are obtained based on the corrosion area distribution data and corrosion development trend data.

[0011] This embodiment provides a drainage pipe corrosion detection method based on ultrasonic guided waves. By setting an ultrasonic guided wave transducer inside the target drainage pipe, it can achieve effective detection of slight corrosion and multiple corrosion in long-distance drainage pipes, and perform signal conversion on the ultrasonic guided wave signal, perform signal feature analysis on the effective guided wave signal in the corrosion area, and use a convolutional neural network model to predict the trend of the drainage pipe corrosion state. It can quickly complete tasks such as ultrasonic guided wave signal acquisition, signal conversion, position positioning, depth estimation, and corrosion analysis, and realize the full process automation of drainage pipe corrosion detection, greatly improving detection efficiency and detection accuracy, avoiding the influence of manual intervention and detection results, and improving the stability and reliability of the detection process. It is suitable for rapid detection of large-scale drainage pipe networks.

[0012] In an optional embodiment, performing signal conversion on the ultrasonic guided wave signal to obtain an effective guided wave signal of the corrosion area includes:

[0013] The ultrasonic guided wave signal is denoised using the adaptive wavelet threshold denoising method.

[0014] Filtering the denoised ultrasonic guided wave signal, and extracting the effective frequency characteristics of the corrosion area based on the filtered ultrasonic guided wave signal;

[0015] The effective frequency characteristics of the corrosion area are subjected to spectrum analysis to obtain the effective guided wave signal of the corrosion area.

[0016] This embodiment provides a drainage pipe corrosion detection method based on ultrasonic guided waves. By denoising and filtering the ultrasonic guided wave signal, the noise in the ultrasonic guided wave signal is effectively removed, thereby ensuring the quality of the ultrasonic guided wave signal. Spectral analysis is performed on the effective frequency characteristics of the corrosion area to extract the spectral characteristics of the ultrasonic guided wave signal. The effective guided wave signal in the corrosion area retains the signal amplitude and time information, providing reliable data for subsequent signal characteristic analysis of the effective guided wave signal in the corrosion area, thereby enhancing the accuracy and reliability of the drainage pipe corrosion detection results.

[0017] In an optional embodiment, the ultrasonic guided wave signal is denoised using an adaptive wavelet threshold denoising method, including:

[0018] Perform wavelet decomposition on the ultrasonic guided wave signal to obtain low-frequency coefficients and high-frequency coefficients;

[0019] Perform noise estimation based on the high-frequency coefficient to obtain a noise estimation value;

[0020] obtaining a signal-to-noise ratio corresponding to the ultrasonic guided wave signal, and determining an adaptive threshold based on the noise estimation value and the signal-to-noise ratio;

[0021] Using the adaptive threshold to filter the high-frequency coefficients, the filtered high-frequency coefficients are obtained;

[0022] Perform multi-scale interactive correction on the filtered high-frequency coefficients to obtain the corrected high-frequency coefficients;

[0023] Signal reconstruction is performed based on the low-frequency coefficients and the corrected high-frequency coefficients to obtain the denoised ultrasonic guided wave signal.

[0024] This embodiment provides a drainage pipe corrosion detection method based on ultrasonic guided waves. The adaptive wavelet threshold denoising method can dynamically adjust the denoising parameters, effectively remove noise interference in complex environments, retain key corrosion signals, and significantly improve signal quality. Compared with the fixed threshold denoising method, it can provide more stable and accurate signals under various working conditions, ensuring the reliability of subsequent corrosion detection.

[0025] In an optional embodiment, signal feature analysis is performed on the effective guided wave signal of the corrosion area to obtain the corrosion area distribution data, including:

[0026] Based on the effective guided wave signal of the corrosion area, the reflection time difference method and the amplitude attenuation method are used to determine the position and depth of the corrosion area respectively.

[0027] A multi-point corrosion distribution analysis is performed based on the location and depth of the corrosion area to obtain the corrosion area distribution data.

[0028] This embodiment provides a drainage pipe corrosion detection method based on ultrasonic guided waves, which combines the reflection time difference method and the amplitude attenuation method. On the basis of ensuring signal denoising, it can simultaneously achieve accurate positioning of the corrosion position and accurate estimation of the depth, solving the problem of large errors in corrosion depth estimation. In addition, multi-point corrosion distribution analysis realizes accurate analysis of the distribution of corrosion areas, providing structured information for drainage pipe corrosion analysis.

[0029] In an optional embodiment, based on the effective guided wave signal of the corrosion area, the position of the corrosion area and the depth of the corrosion area are determined using the reflection time difference method and the amplitude attenuation method respectively, including:

[0030] Determine the arrival time, propagation velocity and start offset time of the reflected signal based on the effective guided wave signal in the corrosion area, and calculate the axial position of the corrosion reflection point based on the arrival time, propagation velocity and start offset time of the reflected signal;

[0031] Obtain the signal phase difference, drainage pipe diameter, and guided wave wavelength corresponding to the effective guided wave signal in the corrosion area, and calculate the circumferential angle of the corrosion area based on the signal phase difference, drainage pipe diameter, and guided wave wavelength;

[0032] Determine the location of the corrosion area based on the axial position of the corrosion reflection point and the circumferential angle of the corrosion area;

[0033] The effective guided wave signal in the corrosion area is curve fitted to obtain the depth of the corrosion area.

[0034] This embodiment provides a drainage pipe corrosion detection method based on ultrasonic guided waves. The axial position of the corrosion reflection point is calculated based on the arrival time of the reflected signal, the guided wave propagation velocity, and the signal start offset time. The positions of multiple corrosion reflection points can be accurately extracted to solve the problem of overlapping interference of reflected signals. By calculating the circumferential angle of the corrosion area, the spatial distribution of the corrosion area is further refined. By calculating the depth of the corrosion area, the degree of corrosion weakening of the drainage pipe wall thickness can be reflected, providing support for the construction of a three-dimensional corrosion distribution pattern.

[0035] In an optional embodiment, the method further includes:

[0036] Visualize the corrosion area distribution data and corrosion development trend data.

[0037] In a second aspect, the present invention provides a drainage pipe corrosion detection device based on ultrasonic guided waves, the device comprising:

[0038] A guided wave transceiver module is used to obtain ultrasonic guided wave signals inside the target drainage pipe sent by multiple ultrasonic guided wave transducers; multiple ultrasonic guided wave transducers are evenly arranged along the circumference of the inner wall of the target drainage pipe to form an ultrasonic guided wave transducer array;

[0039] A signal conversion module is used to convert the ultrasonic guided wave signal to obtain an effective guided wave signal in the corrosion area;

[0040] An analysis module is used to analyze the signal characteristics of the effective guided wave signal in the corrosion area to obtain the distribution data of the corrosion area;

[0041] The prediction module is used to predict the corrosion status of drainage pipes based on the effective guided wave signals in the corrosion area using a convolutional neural network model to obtain corrosion development trend data;

[0042] The generation module is used to generate drainage pipe corrosion detection results based on corrosion area distribution data and corrosion development trend data.

[0043] In a third aspect, the present invention provides a computer device comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to thereby execute a drainage pipe corrosion detection method based on ultrasonic guided waves according to the first aspect or any corresponding embodiment thereof.

[0044] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute a drainage pipe corrosion detection method based on ultrasonic guided waves according to the first aspect or any corresponding embodiment thereof.

[0045] In a fifth aspect, the present invention provides a computer program product comprising computer instructions for enabling a computer to execute a drainage pipe corrosion detection method based on ultrasonic guided waves according to the first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0047] Figure 1 1 is a flow chart of a drainage pipe corrosion detection method based on ultrasonic guided waves according to an embodiment of the present invention;

[0048] Figure 2 is a schematic diagram of the placement of an ultrasonic guided wave transducer in a target drainage pipe according to an embodiment of the present invention;

[0049] Figure 3 1 is a flow chart of another drainage pipe corrosion detection method based on ultrasonic guided waves according to an embodiment of the present invention;

[0050] Figure 4 is a schematic flow chart of an adaptive wavelet threshold denoising method according to an embodiment of the present invention;

[0051] Figure 5 is a schematic diagram of group velocity dispersion according to an embodiment of the present invention;

[0052] Figure 6 1 is a flow chart of another drainage pipe corrosion detection method based on ultrasonic guided waves according to an embodiment of the present invention;

[0053] Figure 7 is a schematic diagram of the axial positioning of a corrosion defect structure according to an embodiment of the present invention;

[0054] Figure 8 is a schematic structural diagram of a convolutional neural network model according to an embodiment of the present invention;

[0055] Figure 91 is a schematic diagram of a process for predicting the corrosion status of a drainage pipe according to a convolutional neural network model according to an embodiment of the present invention;

[0056] Figure 10 2. It is a schematic diagram of the working principle framework of the drainage pipe corrosion distribution condition detection system based on ultrasonic guided waves according to an embodiment of the present invention;

[0057] Figure 11 is a schematic diagram of a simulation signal of ultrasonic guided wave corrosion defects in a drainage pipe according to an embodiment of the present invention;

[0058] Figure 12 is a schematic diagram of an ultrasonic guided wave simulation signal after adding Gaussian white noise according to an embodiment of the present invention;

[0059] Figure 13 1 is a schematic diagram of a first-layer denoised signal using an adaptive wavelet threshold denoising method based on the db8 wavelet according to an embodiment of the present invention;

[0060] Figure 14 2 is a schematic diagram of a second-layer denoised signal using an adaptive wavelet threshold denoising method based on the db8 wavelet according to an embodiment of the present invention;

[0061] Figure 15 2 is a schematic diagram of a third-layer denoised signal using an adaptive wavelet threshold denoising method based on the db8 wavelet according to an embodiment of the present invention;

[0062] Figure 16 1 is a structural block diagram of a drainage pipe corrosion detection device based on ultrasonic guided waves according to an embodiment of the present invention;

[0063] Figure 17 Schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0064] To make the purpose, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative efforts shall fall within the scope of protection of the present invention.

[0065] In recent years, ultrasonic guided wave detection technology has been widely used in the field of non-destructive testing. Ultrasonic guided waves have a long propagation distance and high sensitivity. They can detect corrosion defects in a large range of pipelines without blocking the pipelines. The detection can be completed when the pipelines are operating normally. Using ultrasonic guided wave technology to detect pipeline corrosion can not only improve detection efficiency, but also achieve high-precision positioning of the corrosion area inside the pipeline and accurate assessment of the corrosion depth.

[0066] However, ultrasonic guided wave detection systems are mostly used for industrial pipelines, and there are relatively few dedicated systems for drainage pipeline corrosion conditions. In addition, there are still problems such as large noise interference, complex signal processing, and less intuitive data analysis results during the detection process. Although wavelet threshold denoising methods are widely used in the field of signal processing, most methods rely on fixed wavelet bases and threshold settings and cannot adapt to changes in different types of signals and complex noise. In particular, in pipeline corrosion detection, ultrasonic guided wave signals are greatly affected by noise interference. Wavelet denoising methods usually use a fixed threshold processing method and fail to dynamically adjust the threshold according to the specific characteristics of the signal, resulting in unstable denoising effects under different working conditions and difficult to guarantee the denoising effect.

[0067] The process of detecting pipeline corrosion using ultrasonic guided wave technology is mostly semi-automated, and data analysis, result generation and other links in the detection process still require a lot of manual intervention, which not only increases labor costs but also easily causes human errors, affecting the accuracy of detection results. In large-scale pipeline networks, the task of corrosion detection is huge and frequent, and the efficiency of manual intervention and data processing is low, which cannot meet the needs of modern industry for fast and accurate detection. Therefore, it is necessary to develop a drainage pipeline corrosion distribution condition detection system based on ultrasonic guided waves, which can efficiently detect pipeline corrosion without affecting the original structure and operation of the drainage pipeline, and provide a scientific basis for pipeline detection and operation and maintenance.

[0068] An embodiment of the present invention provides a drainage pipe corrosion detection method based on ultrasonic guided waves. The method generates and receives ultrasonic guided waves to obtain reflected signals from inside the pipe. An adaptive wavelet threshold denoising method is used to effectively remove noise from the signal and retain valid information about the corrosion area. The reflection time difference method and amplitude attenuation method are used to comprehensively analyze the multi-point corrosion distribution, accurately estimate the location and depth of the corrosion area, and use a convolutional neural network model (CNN) to intelligently predict the distribution trend of the corrosion area, providing decision support for pipeline maintenance. Ultimately, a corrosion distribution status report for the entire pipeline is generated and the data is sent to the cloud. The embodiment of the present invention overcomes the problems of signal noise interference, inaccurate depth estimation, and lack of intelligent prediction in traditional technologies. It has the characteristics of high precision, automation, and intelligence, is applicable to different types of pipelines, and can operate stably in complex environments, achieving efficient risk management and improving the quality and efficiency of drainage pipe networks.

[0069] An embodiment of the present invention provides a drainage pipe corrosion detection method based on ultrasonic guided waves. It should be noted that the drainage pipe corrosion detection method based on ultrasonic guided waves provided in the embodiment of the present invention can be executed by a drainage pipe corrosion detection device based on ultrasonic guided waves. The drainage pipe corrosion detection device based on ultrasonic guided waves can be implemented as part or all of an electronic device through software, hardware, or a combination of software and hardware. The electronic device can be a server or a terminal. The server in the embodiment of the present application can be a single server or a server cluster composed of multiple servers. The terminal in the embodiment of the present application can be a smart phone, a personal computer, a tablet computer, a wearable device, an intelligent robot, or other intelligent hardware devices. In the following method embodiments, the execution subject is an electronic device as an example for explanation.

[0070] According to an embodiment of the present invention, an embodiment of a drainage pipe corrosion detection method based on ultrasonic guided waves is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0071] In this embodiment, a drainage pipe corrosion detection method based on ultrasonic guided waves is provided, which can be used for the above-mentioned electronic equipment. Figure 1 FIG. 1 is a flow chart of a drainage pipe corrosion detection method based on ultrasonic guided waves according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0072] Step S101: Acquire ultrasonic guided wave signals inside a target drainage pipe sent by a plurality of ultrasonic guided wave transducers; the plurality of ultrasonic guided wave transducers are evenly arranged along the circumference of the inner wall of the target drainage pipe to form an ultrasonic guided wave transducer array.

[0073] Specifically, if Figure 2 As shown in the figure, the ultrasonic guided wave transducer array consists of multiple ultrasonic guided wave transducers a arranged uniformly along the inner wall of the target drainage pipe A to form an array structure, thereby realizing 360° omnidirectional guided wave transmission and reception; the ultrasonic guided wave transducer has a real-time parameter adaptive optimization function, which can dynamically adjust the emission intensity, frequency, and waveform of the guided wave based on the pipe material, shape, and internal fluid state, ensuring that high-quality guided wave signals can be stably generated under various working conditions; the ultrasonic guided wave transducer adopts multi-band excitation and sensing, taking advantage of the strong propagation capability of low-frequency guided waves (20-50kHz) and the high-resolution characteristics of high-frequency guided waves (50-100kHz), to achieve effective detection of slight corrosion and multiple corrosion in long-distance pipelines.

[0074] Step S102: performing signal conversion on the ultrasonic guided wave signal to obtain an effective guided wave signal of the corrosion area.

[0075] Step S103 , performing signal feature analysis on the effective guided wave signal of the corrosion area to obtain corrosion area distribution data.

[0076] In step S104, based on the effective guided wave signal in the corrosion area, a convolutional neural network model is used to predict the corrosion state of the drainage pipe to obtain corrosion development trend data.

[0077] Step S105 : obtaining drainage pipe corrosion detection results based on the corrosion area distribution data and the corrosion development trend data.

[0078] Specifically, based on the corrosion area information obtained from data analysis (i.e., corrosion area distribution data and corrosion development trend data), the system will integrate information on all corroded parts of the pipeline, generate a pipeline corrosion distribution status report, and transmit the data wirelessly to the cloud; the pipeline corrosion distribution status report includes a corrosion distribution map, which uses color cards to indicate the severity of the corrosion area, so that operation and maintenance personnel can quickly judge the health status of the pipeline.

[0079] Furthermore, the corrosion area distribution data and the corrosion development trend data are visualized; wherein, the corrosion area distribution data and the corrosion development trend data are visualized in two and three dimensions, including a heat map display of the corrosion location and an isoline map of the corrosion depth.

[0080] This embodiment provides a drainage pipe corrosion detection method based on ultrasonic guided waves. By setting an ultrasonic guided wave transducer inside the target drainage pipe, it can achieve effective detection of slight corrosion and multiple corrosion in long-distance drainage pipes, and perform signal conversion on the ultrasonic guided wave signal, perform signal feature analysis on the effective guided wave signal in the corrosion area, and use a convolutional neural network model to predict the trend of the drainage pipe corrosion state. It can quickly complete tasks such as ultrasonic guided wave signal acquisition, signal conversion, position positioning, depth estimation, and corrosion analysis, and realize the full process automation of drainage pipe corrosion detection, greatly improving detection efficiency and detection accuracy, avoiding the influence of manual intervention and detection results, and improving the stability and reliability of the detection process. It is suitable for rapid detection of large-scale drainage pipe networks.

[0081] In this embodiment, a drainage pipe corrosion detection method based on ultrasonic guided waves is provided, which can be used for the above-mentioned electronic equipment. Figure 3 FIG. 1 is a flow chart of a drainage pipe corrosion detection method based on ultrasonic guided waves according to an embodiment of the present invention. Figure 3 As shown, the process includes the following steps:

[0082] Step S301: Acquire ultrasonic guided wave signals from the target drainage pipe, which are sent by multiple ultrasonic guided wave transducers. Multiple ultrasonic guided wave transducers are evenly arranged along the circumference of the inner wall of the target drainage pipe to form an ultrasonic guided wave transducer array. Figure 1 Step S101 of the illustrated embodiment will not be described in detail here.

[0083] Step S302: performing signal conversion on the ultrasonic guided wave signal to obtain an effective guided wave signal of the corrosion area.

[0084] Specifically, the above step S302 includes:

[0085] Step S3021: De-noising the ultrasonic guided wave signal using an adaptive wavelet threshold denoising method.

[0086] Specifically, in the adaptive wavelet threshold denoising method, adaptation refers to dynamically adjusting the threshold according to the signal characteristics of the ultrasonic guided wave signal.

[0087] In some optional embodiments, such as Figure 4 As shown, the above step S3022 includes:

[0088] Step a1: performing wavelet decomposition on the ultrasonic guided wave signal to obtain low-frequency coefficients and high-frequency coefficients.

[0089] Specifically, the ultrasonic guided wave signal is first transformed using discrete wavelet transform (DWT) Decompose into The low-frequency and high-frequency coefficients of the layer:

[0090] (1)

[0091] in, and Indicates the The low-frequency coefficients and high-frequency coefficients of the layer, and represents the low-frequency wavelet basis function and the high-frequency wavelet basis function.

[0092] Furthermore, the energy distribution characteristics of the signal are calculated, and the wavelet basis is dynamically selected to obtain the optimally selected wavelet basis. The calculation formula is as follows:

[0093] (2)

[0094] in, represents the optimally selected wavelet basis, Represents the wavelet basis The signal energy distribution obtained after decomposition is Represents the energy distribution of a specific frequency band of the corrosion signal.

[0095] Furthermore, since the noise intensity estimation in the high-frequency coefficients directly depends on the decomposition results, and the decomposition effect is closely related to the selection of the wavelet basis, the wavelet basis is optimized and selected. The optimized wavelet basis concentrates the noise in the high-frequency coefficients, making the noise estimation more accurate and facilitating the setting of a suitable denoising threshold. The optimized wavelet basis makes the noise more concentrated, the effective signal more prominent, and the adaptive threshold design more reliable. In addition, the smooth correction between multiple scales requires the use of the decomposition characteristics of the wavelet basis at different scales, so that the correction of the high-frequency coefficients is smoother. The dynamic wavelet basis ensures that during multi-scale correction, the signal energy distribution between different scales is more consistent, thereby reducing signal distortion. In addition, the dynamic wavelet basis makes the reconstructed signal closer to the original signal, and the noise is effectively filtered out.

[0096] Step a2: performing noise estimation based on the high frequency coefficients to obtain a noise estimation value.

[0097] Specifically, the standard deviation of the high-frequency coefficients is used to estimate the noise level, and the noise estimation value is The calculation formula is as follows:

[0098] (3)

[0099] in, Represents the median absolute deviation of the high-frequency coefficients.

[0100] Step a3: Obtain a signal-to-noise ratio corresponding to the ultrasonic guided wave signal, and determine an adaptive threshold based on the noise estimation value and the signal-to-noise ratio.

[0101] Specifically, the adaptive threshold is dynamically adjusted according to the signal-to-noise ratio and noise estimation value of each scale , adaptive threshold The calculation formula is as follows:

[0102] (4)

[0103] in, Indicates the The length of the high-frequency coefficients of the layer, Represents the adjustment coefficient, which is used to control the change of the threshold with the signal-to-noise ratio. Indicates the The signal-to-noise ratio of the layer.

[0104] Step a4: Filter the high-frequency coefficients using the adaptive threshold to obtain filtered high-frequency coefficients.

[0105] Specifically, the high-frequency coefficients are compared with the adaptive threshold. The high-frequency coefficients smaller than the adaptive threshold are regarded as noise and cleared, and the high-frequency coefficients larger than the adaptive threshold are retained. In the high-frequency coefficients after adaptive threshold processing, the noise part has been cleared, and the remaining useful signal components and low-frequency coefficients are reconstructed through inverse wavelet transform to reconstruct the original signal.

[0106] Step a5: Perform multi-scale interactive correction on the filtered high-frequency coefficients to obtain corrected high-frequency coefficients.

[0107] Specifically, for each layer of high-frequency coefficients after screening , smooth correction is performed based on the coefficient information of the adjacent scales. The formula for multi-scale interactive correction is as follows:

[0108] (5)

[0109] in, Indicates the The high-frequency coefficients after layer correction, Represents the weight coefficient, which is used to adjust the contribution of the current scale and the adjacent scale. Indicates the The high-frequency coefficients of the layer, Indicates the The high-frequency coefficients of the layer.

[0110] Step a6: reconstruct the signal based on the low-frequency coefficient and the corrected high-frequency coefficient to obtain a denoised ultrasonic guided wave signal.

[0111] Specifically, the processed low-frequency and high-frequency coefficients are recombined using the Inverse Discrete Wavelet Transform (IDWT) to obtain the denoised ultrasonic guided wave signal. It can be expressed as:

[0112] (6)

[0113] This embodiment provides a drainage pipe corrosion detection method based on ultrasonic guided waves. The adaptive wavelet threshold denoising method can dynamically adjust the denoising parameters, effectively remove noise interference in complex environments, retain key corrosion signals, and significantly improve signal quality. Compared with the fixed threshold denoising method, it can provide more stable and accurate signals under various working conditions, ensuring the reliability of subsequent corrosion detection.

[0114] Step S3022: Filter the ultrasonic guided wave signal after the denoising process, and extract the effective frequency characteristics of the corrosion area based on the ultrasonic guided wave signal after the filtering process.

[0115] Specifically, the frequency band of the denoised signal is selected through a bandpass filter to filter out irrelevant frequency components and extract the effective frequency characteristics of the corrosion area.

[0116] Furthermore, according to the derivation of the elastic wave dynamics motion equation, in the dispersion equation in the pipeline, the elastic coefficient of the solid medium is related to the pipe diameter, the Lame constant of the material, and the density of the material. , angular velocity , wave number The solutions of the dispersion equations correspond to the three modes of guided waves in the pipe: longitudinal mode L(0, m), torsional mode T(0, m) and bending mode F(n, m), where n is the order in the circumferential direction and m is the radial vibration mode.

[0117] Furthermore, if Figure 5 As shown in the figure, the velocity of the longitudinal guided wave L(0,2) mode does not change with frequency near 30~100kHz, so the signal shape and amplitude can be preserved during the propagation process; and its propagation speed is the fastest, so it can reach the guided wave receiving device faster than other modes of guided waves, making it easier to distinguish in the time domain; in addition, the radial displacement component of the guided wave L(0,2) mode is relatively small, and the axial displacement component is relatively large, and the amplitude difference is not much; therefore, it has the same sensitivity to the inner and outer surfaces of the pipe, and Figure 7The figure shows that the velocity of the torsional guided wave T(0,1) mode does not change with frequency, and the overall curve is non-dispersive. 20-50 kHz is a frequency range commonly used in engineering, which can ensure signal integrity while taking into account propagation distance and detection sensitivity. For corrosion or circumferential defect detection, this frequency range provides the best balance. Therefore, the frequency range of ultrasonic guided waves is usually 20-100 kHz. The L(0,2) mode exhibits non-dispersive characteristics in the frequency range of 30-100 kHz, which is suitable for signal shape preservation and long-distance propagation. The T(0,1) mode is stable in the low-frequency range of 20-50 kHz, which is suitable for detecting large-area corrosion on the outer wall of the pipeline.

[0118] Step S3023: Perform spectrum analysis on the effective frequency characteristics of the corrosion area to obtain the effective guided wave signal of the corrosion area.

[0119] Specifically, the filtered signal is converted into the frequency domain based on the fast Fourier transform algorithm, and the frequency distribution characteristics of the corrosion area are extracted through power spectrum density analysis, and then the effective waveguide signal reflecting the frequency distribution characteristics of the corrosion area is extracted.

[0120] Furthermore, the signal processed by the filtering unit (i.e., the effective frequency characteristics of the corrosion area) is subjected to a fast Fourier transform to convert the time domain signal into a frequency domain signal. The output of the frequency domain signal is a complex array representing the amplitude and phase of each frequency component. The amplitude part of the frequency component is extracted for the calculation of the power spectrum.

[0121] Furthermore, the power spectral density is calculated using the amplitude of the frequency domain signal. The calculation formula is as follows:

[0122] (7)

[0123] in, represents the power spectral density, represents the power of the frequency component, Indicates the number of signal samples.

[0124] Furthermore, the power spectrum density curve is analyzed to find the frequency peak and energy concentration area of ​​the corrosion area signal, and the characteristic information is extracted. Then, the power density characteristics of different frequency bands are compared and matched with the known corrosion signal pattern to determine the distribution characteristics of the corrosion.

[0125] Step S303: Perform signal feature analysis on the effective guided wave signal in the corrosion area to obtain the distribution data of the corrosion area. Figure 1 Step S103 of the illustrated embodiment will not be described in detail here.

[0126] Step S304: Based on the effective guided wave signal in the corrosion area, a convolutional neural network model is used to predict the corrosion status of the drainage pipe and obtain corrosion development trend data. Figure 1 Step S104 of the illustrated embodiment will not be described in detail here.

[0127] Step S305: Obtain drainage pipe corrosion detection results based on the corrosion area distribution data and corrosion development trend data. Figure 1 Step S105 of the illustrated embodiment will not be described in detail here.

[0128] This embodiment provides a drainage pipe corrosion detection method based on ultrasonic guided waves. By denoising and filtering the ultrasonic guided wave signal, the noise in the ultrasonic guided wave signal is effectively removed, thereby ensuring the quality of the ultrasonic guided wave signal. Spectral analysis is performed on the effective frequency characteristics of the corrosion area to extract the spectral characteristics of the ultrasonic guided wave signal. The effective guided wave signal in the corrosion area retains the signal amplitude and time information, providing reliable data for subsequent signal characteristic analysis of the effective guided wave signal in the corrosion area, thereby enhancing the accuracy and reliability of the drainage pipe corrosion detection results.

[0129] In this embodiment, a drainage pipe corrosion detection method based on ultrasonic guided waves is provided, which can be used for the above-mentioned electronic equipment. Figure 6 FIG. 1 is a flow chart of a drainage pipe corrosion detection method based on ultrasonic guided waves according to an embodiment of the present invention. Figure 6 As shown, the process includes the following steps:

[0130] Step S601: Acquire ultrasonic guided wave signals from the target drainage pipe, which are sent by multiple ultrasonic guided wave transducers. Multiple ultrasonic guided wave transducers are evenly arranged along the circumference of the inner wall of the target drainage pipe to form an ultrasonic guided wave transducer array. Figure 3 Step S301 of the illustrated embodiment will not be described in detail here.

[0131] Step S602: Convert the ultrasonic guided wave signal to obtain an effective guided wave signal of the corrosion area. Figure 3 Step S302 of the illustrated embodiment will not be described in detail here.

[0132] Step S603: performing signal feature analysis on the effective guided wave signal of the corrosion area to obtain corrosion area distribution data.

[0133] Specifically, the above step S603 includes:

[0134] Step S6031 : Based on the effective guided wave signal of the corrosion area, the position of the corrosion area and the depth of the corrosion area are determined using the reflection time difference method and the amplitude attenuation method respectively.

[0135] In some optional implementations, step S6031 includes:

[0136] Step b1, determine the arrival time, waveguide propagation velocity and signal start offset time of the reflected signal based on the effective waveguide signal in the corrosion area, and calculate the axial position of the corrosion reflection point based on the arrival time, waveguide propagation velocity and signal start offset time of the reflected signal.

[0137] Specifically, based on the reflection time difference characteristics of the effective guided wave signal in the corrosion area, the arrival time of multiple reflection signals is extracted to locate the axial position of the defect, such as Figure 7 As shown in Figure 2, the calculation formula for the axial position of the corrosion reflection point (i.e., the corrosion area) is:

[0138] (8)

[0139] in, Indicates the The distance between the corrosion reflection points, that is, the axial position of the corrosion reflection point, represents the propagation velocity of the guided wave, represents the arrival time of the reflected signal, Indicates the signal start offset time, which is used to correct system delay.

[0140] Step b2: Obtain the signal phase difference, the drainage pipe diameter, and the waveguide wavelength corresponding to the effective waveguide signal in the corrosion area, and calculate the circumferential angle of the corrosion area based on the signal phase difference, the drainage pipe diameter, and the waveguide wavelength.

[0141] Specifically, in pipeline corrosion detection, there will be a signal phase difference at the receivers at different circumferential positions of the guided wave signal. The signal phase difference is related to the circumferential angle of the corrosion area on the pipe cross section. Based on the propagation characteristics of guided waves, the circumferential angle of the corrosion area can be calculated by the following formula :

[0142] (9)

[0143] in, represents the guided wave wavelength, Indicates the diameter of the drainage pipe.

[0144] Step b3: determining the position of the corrosion area based on the axial position of the corrosion reflection point and the circumferential angle of the corrosion area.

[0145] Step b4: performing curve fitting on the effective guided wave signal of the corrosion area to obtain the depth of the corrosion area.

[0146] Specifically, the specific steps of curve fitting for the effective waveguide signal in the corrosion area include: determining the signal amplitude change of each corrosion reflection point based on the effective waveguide signal in the corrosion area; constructing an amplitude attenuation model; fitting the material attenuation coefficient, that is, preliminarily setting the material attenuation coefficient value (known or experimentally calibrated), using multiple reflection point data for optimization, and selecting the material attenuation coefficient value that best suits the data distribution; fitting the corrosion depth curve, that is, substituting the amplitude of each reflection signal into the amplitude attenuation model to solve the depth of the corrosion area; summarizing the depths of all corrosion areas to form a multi-point corrosion depth distribution curve; comparing the signal amplitude of the actually measured corrosion reflection point with the signal amplitude of the corrosion reflection point calculated by the amplitude attenuation model to see if they are consistent. If the error is large, adjust the material attenuation coefficient value and re-fit; and generate a corrosion depth distribution map using the final fitting result to reflect the corrosion conditions of each reflection point in the pipeline.

[0147] Furthermore, the expression of the amplitude attenuation model is as follows:

[0148] (10)

[0149] in, represents the amplitude of the reflected signal, Indicates the emission amplitude of the initial signal, that is, the amplitude of the signal when it is just emitted. Indicates the depth of the corroded area.

[0150] Furthermore, the amplitude attenuation model is used to curve fit multiple reflected signals in the effective guided wave signal of the corrosion area. For different corrosion areas, combined with the material attenuation coefficient A depth estimation formula is established, and the calculation formula for the depth of the corrosion area is:

[0151] (11)

[0152] in, Indicates the The depth of the corrosion area corresponding to each corrosion reflection point is Indicates the The signal amplitude change of each corrosion reflection point, Indicates the emission amplitude of the initial signal.

[0153] This embodiment provides a drainage pipe corrosion detection method based on ultrasonic guided waves. The axial position of the corrosion reflection point is calculated based on the arrival time of the reflected signal, the guided wave propagation velocity, and the signal start offset time. The positions of multiple corrosion reflection points can be accurately extracted to solve the problem of overlapping interference of reflected signals. By calculating the circumferential angle of the corrosion area, the spatial distribution of the corrosion area is further refined. By calculating the depth of the corrosion area, the degree of corrosion weakening of the drainage pipe wall thickness can be reflected, providing support for the construction of a three-dimensional corrosion distribution pattern.

[0154] Step S6032: Perform multi-point corrosion distribution analysis based on the position and depth of the corrosion area to obtain corrosion area distribution data.

[0155] Specifically, the distance between the corrosion areas is analyzed based on the location and depth of the corrosion areas. The calculation formula is as follows:

[0156] (12)

[0157] in, and Respectively represent The corrosion area and The location of the corrosion area.

[0158] Furthermore, the spacing distribution between adjacent corrosion areas is first counted to analyze the density of corrosion areas and identify possible corrosion clusters or individual corrosion areas. The depth distribution of the corrosion areas is then analyzed to identify the severity of corrosion and decide which corrosion areas need priority repair or reinforcement. Finally, the analysis results of the position distribution and depth distribution are combined to form a comprehensive corrosion distribution pattern, such as point distribution, strip distribution, uniform distribution, etc., and the priority of repair and treatment is provided according to the distribution pattern and severity area.

[0159] In step S604, based on the effective guided wave signal in the corrosion area, a convolutional neural network model is used to predict the corrosion state of the drainage pipe to obtain corrosion development trend data.

[0160] Specifically, if Figure 8 As shown in the figure, the convolutional neural network model includes an input layer, a preprocessing layer, a feature extraction layer, a convolution layer, a pooling layer, a batch normalization layer, a classification layer, a prediction layer and an output layer. The convolutional neural network model is used to extract and classify the features of the signals in the corrosion area. The subtle change characteristics of the signals in the corrosion area are identified through multi-layer convolution operations and pooling operations, and the corrosion development trend data is analyzed in combination with historical data.

[0161] Furthermore, if Figure 9As shown in the figure, the steps of using the convolutional neural network model to predict the trend of the corrosion status of the drainage pipe include: the input layer receives the effective waveguide signal in the corrosion area and passes it to the preprocessing layer; the preprocessing layer normalizes and amplifies the effective waveguide signal in the corrosion area to construct a standardized data set; the feature extraction layer uses a multi-layer convolutional neural network model structure to perform multi-scale analysis on the corrosion signal, and extracts corrosion feature information by setting convolution layer, pooling layer and batch normalization layer; the classification layer uses a fully connected layer, a dropout layer (Dropout layer) and a Softmax (normalization index) classifier to realize corrosion type identification and degree assessment, among which the dropout layer is used to suppress overfitting and enhance the generalization ability of the model; the prediction layer uses the trained deep learning model to predict the trend of the pipeline corrosion status based on the real-time collected corrosion signal features and historical database; the output layer outputs the results such as corrosion type, corrosion degree and corrosion state trend, and uses the corrosion type, corrosion degree and corrosion state trend as corrosion development trend data.

[0162] Step S605: Obtain drainage pipe corrosion detection results based on the corrosion area distribution data and corrosion development trend data. Figure 3 Step S305 of the illustrated embodiment will not be described in detail here.

[0163] This embodiment provides a drainage pipe corrosion detection method based on ultrasonic guided waves, which combines the reflection time difference method and the amplitude attenuation method. On the basis of ensuring signal denoising, it can simultaneously achieve accurate positioning of the corrosion position and accurate estimation of the depth, solving the problem of large errors in corrosion depth estimation. In addition, multi-point corrosion distribution analysis realizes accurate analysis of the distribution of corrosion areas, providing structured information for drainage pipe corrosion analysis.

[0164] The following is a specific example to illustrate the specific steps of the drainage pipe corrosion detection method based on ultrasonic guided waves.

[0165] Example 1:

[0166] like Figure 10 As shown, the specific steps of the drainage pipe corrosion detection method based on ultrasonic guided waves include:

[0167] The guided wave transducer generates and receives ultrasonic guided wave signals. The ultrasonic guided wave transducer has a real-time parameter adaptive optimization function, which can dynamically adjust the emission intensity, frequency, and waveform of the guided wave based on the pipeline material, shape, and internal fluid state, ensuring the stable generation of high-quality guided wave signals under various working conditions. The ultrasonic guided wave transducer adopts multi-band excitation and perception, and takes advantage of the strong propagation capability of low-frequency guided waves (20~50kHz) and the high-resolution characteristics of high-frequency guided waves (50~100kHz) to achieve effective detection of slight corrosion and multiple corrosion in long-distance pipelines.

[0168] The received ultrasonic guided wave signal is denoised and features extracted; in the process of denoising the ultrasonic guided wave signal, the db8 wavelet basis is selected, and the adaptive threshold design method is applied, and then multi-scale interactive correction and signal reconstruction are performed, and finally the signal is output.

[0169] The constructed drainage pipe ultrasonic guided wave corrosion defect simulation signal is as follows Figure 11 As shown, the ultrasonic guided wave signal with Gaussian white noise added is as follows Figure 12 As shown in Table 1, under the conditions of db8 wavelet basis and 2 decomposition levels, with signal-to-noise ratio (SNR) and root mean square error (RMSE) as evaluation indicators, the comparison results of the processing effects of the adaptive threshold design method and other threshold methods are shown in Table 1 below.

[0170] Table 1:

[0171]

[0172] As shown in Table 1 above, the adaptive threshold design method has better processing effect than other methods, with higher signal-to-noise ratio and smaller root mean square error.

[0173] The adaptive wavelet threshold denoising method is used under the db8 wavelet base. The number of decomposition layers of the denoised signal is 1 to 3 layers. The denoising effect of the first layer is as follows: Figure 13 As shown, the denoising effect of the second layer is as follows Figure 14 As shown, the denoising effect of the third layer is as follows Figure 15 As shown in the figure, the adaptive wavelet threshold denoising method is used under the db8 wavelet basis. The denoising effects under different decomposition layers are shown in Table 2 below.

[0174] Table 2:

[0175]

[0176] The denoised signal is subjected to frequency band selection through a bandpass filter to filter out irrelevant frequency components and extract the effective frequency characteristics of the corrosion area. The filtered signal is converted into the frequency domain based on the fast Fourier transform algorithm, and the frequency distribution characteristics of the corrosion area are extracted through power spectral density analysis.

[0177] Analyze signal characteristics, accurately assess the location and depth of corrosion areas, and predict corrosion development trends.

[0178] Based on the corrosion area information obtained from data analysis, the information of all corroded parts of the pipeline will be integrated to generate a pipeline corrosion distribution status report.

[0179] This embodiment also provides a drainage pipe corrosion detection device based on ultrasonic guided waves. The device is used to implement the above-mentioned embodiments and preferred embodiments, and the details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation using hardware, or a combination of software and hardware, is also possible and contemplated.

[0180] This embodiment provides a drainage pipe corrosion detection device based on ultrasonic guided waves, such as Figure 16 As shown, including:

[0181] The guided wave transceiver module 1601 is used to obtain ultrasonic guided wave signals inside the target drainage pipe sent by multiple ultrasonic guided wave transducers; the multiple ultrasonic guided wave transducers are evenly arranged along the circumference of the inner wall of the target drainage pipe to form an ultrasonic guided wave transducer array;

[0182] The signal conversion module 1602 is used to convert the ultrasonic guided wave signal to obtain an effective guided wave signal of the corrosion area;

[0183] Analysis module 1603, used to perform signal feature analysis on the effective guided wave signal of the corrosion area to obtain the distribution data of the corrosion area;

[0184] Prediction module 1604 is used to predict the corrosion status of the drainage pipe based on the effective guided wave signal of the corrosion area using a convolutional neural network model to obtain corrosion development trend data;

[0185] The generating module 1605 is used to generate drainage pipe corrosion detection results based on the corrosion area distribution data and the corrosion development trend data.

[0186] In some optional implementations, the signal conversion module 1602 includes:

[0187] A denoising unit, configured to perform denoising processing on the ultrasonic guided wave signal using an adaptive wavelet threshold denoising method;

[0188] a filtering unit, configured to filter the ultrasonic guided wave signal after the denoising process, and extract effective frequency characteristics of the corrosion area based on the ultrasonic guided wave signal after the filtering process;

[0189] The spectrum analysis unit is used to perform spectrum analysis on the effective frequency characteristics of the corrosion area to obtain the effective guided wave signal of the corrosion area.

[0190] In some optional implementations, the denoising unit includes:

[0191] A decomposition subunit, used for performing wavelet decomposition on the ultrasonic guided wave signal to obtain low-frequency coefficients and high-frequency coefficients;

[0192] A noise estimation subunit, configured to perform noise estimation based on the high frequency coefficients to obtain a noise estimation value;

[0193] an acquisition subunit, configured to acquire a signal-to-noise ratio corresponding to the ultrasonic guided wave signal, and determine an adaptive threshold based on the noise estimation value and the signal-to-noise ratio;

[0194] A screening subunit, configured to screen high-frequency coefficients using an adaptive threshold to obtain screened high-frequency coefficients;

[0195] The correction subunit is used to perform multi-scale interactive correction on the filtered high-frequency coefficients to obtain the corrected high-frequency coefficients;

[0196] The signal reconstruction subunit is used to reconstruct the signal based on the low-frequency coefficients and the corrected high-frequency coefficients to obtain the ultrasonic guided wave signal after denoising.

[0197] In some optional implementations, the analysis module 1603 includes:

[0198] a determination unit for determining the position of the corrosion area and the depth of the corrosion area by using a reflection time difference method and an amplitude attenuation method based on an effective guided wave signal of the corrosion area;

[0199] The multi-point corrosion distribution analysis unit is used to perform multi-point corrosion distribution analysis based on the position of the corrosion area and the depth of the corrosion area to obtain corrosion area distribution data.

[0200] In some optional implementations, the determining unit includes:

[0201] a first calculation subunit, configured to determine an arrival time, a guided wave propagation velocity, and a signal start offset time of a reflected signal based on an effective guided wave signal in the corrosion area, and calculate an axial position of a corrosion reflection point based on the arrival time, the guided wave propagation velocity, and the signal start offset time of the reflected signal;

[0202] The second calculation subunit is used to obtain the signal phase difference, the drainage pipe diameter and the guided wave wavelength corresponding to the effective guided wave signal of the corrosion area, and calculate the circumferential angle of the corrosion area based on the signal phase difference, the drainage pipe diameter and the guided wave wavelength;

[0203] a determination subunit, configured to determine a position of the corrosion region based on an axial position of the corrosion reflection point and a circumferential angle of the corrosion region;

[0204] The fitting subunit is used to perform curve fitting on the effective guided wave signal of the corrosion area to obtain the depth of the corrosion area.

[0205] In some optional embodiments, the method further includes:

[0206] The visualization display module is used to visualize the corrosion area distribution data and corrosion development trend data.

[0207] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0208] In this embodiment, a drainage pipe corrosion detection device based on ultrasonic guided waves is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0209] The embodiment of the present invention also provides a computer device having the above Figure 16 A drainage pipe corrosion detection device based on ultrasonic guided waves is shown.

[0210] See also Figure 17 , Figure 17 is a structural diagram of a computer device provided by an optional embodiment of the present invention, such as Figure 17 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components utilize different buses to communicate with each other and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of a GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories. Equally, multiple computer devices can be connected, and each device provides part of the necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 17 A processor 10 is taken as an example.

[0211] The processor 10 may be a central processing unit, a network processor, or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit, a programmable logic device, or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic, or any combination thereof.

[0212] The memory 20 stores instructions that can be executed by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0213] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created based on the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0214] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0215] The computer device further includes a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0216] The embodiment of the present invention also provides a computer-readable storage medium. The above-mentioned method according to the embodiment of the present invention can be implemented in hardware, firmware, or implemented as a computer code that can be recorded in a storage medium, or implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and downloaded through a network and will be stored in a local storage medium, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state drive, etc.; further, the storage medium can also include a combination of the above-mentioned types of memory. It can be understood that a computer, a processor, a microprocessor controller or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor or hardware, the method shown in the above embodiment is implemented.

[0217] A portion of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the form in which the computer program instruction exists in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc. Accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium that can be accessed by the computer.

[0218] Although the embodiments of the present invention have been described with reference to the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention. Such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A drainage pipe corrosion detection method based on ultrasonic guided waves, characterized in that: The method comprises: Acquiring ultrasonic guided wave signals inside a target drainage pipe sent by a plurality of ultrasonic guided wave transducers; the plurality of ultrasonic guided wave transducers are evenly arranged along the circumference of the inner wall of the target drainage pipe to form an ultrasonic guided wave transducer array; Performing signal conversion on the ultrasonic guided wave signal to obtain an effective guided wave signal of the corrosion area; Performing signal characteristic analysis on the effective guided wave signal of the corrosion area to obtain corrosion area distribution data; Based on the effective guided wave signal of the corrosion area, a convolutional neural network model is used to predict the corrosion state of the drainage pipe to obtain corrosion development trend data; Obtaining drainage pipe corrosion detection results based on the corrosion area distribution data and the corrosion development trend data; The converting the ultrasonic guided wave signal to obtain an effective guided wave signal of the corrosion area includes: De-noising the ultrasonic guided wave signal using an adaptive wavelet threshold denoising method; Filtering the denoised ultrasonic guided wave signal, and extracting the effective frequency characteristics of the corrosion area based on the filtered ultrasonic guided wave signal; Performing spectrum analysis on the effective frequency characteristics of the corrosion area to obtain an effective guided wave signal of the corrosion area; The denoising process of the ultrasonic guided wave signal using an adaptive wavelet threshold denoising method comprises: performing wavelet decomposition on the ultrasonic guided wave signal to obtain low-frequency coefficients and high-frequency coefficients; Performing noise estimation based on the high frequency coefficient to obtain a noise estimation value; Acquire a signal-to-noise ratio corresponding to the ultrasonic guided wave signal, and determine an adaptive threshold based on the noise estimation value and the signal-to-noise ratio; Filtering the high-frequency coefficients using the adaptive threshold to obtain filtered high-frequency coefficients; Performing multi-scale interactive correction on the filtered high-frequency coefficients to obtain corrected high-frequency coefficients; Signal reconstruction is performed based on the low-frequency coefficients and the corrected high-frequency coefficients to obtain the ultrasonic guided wave signal after the denoising process.

2. The method according to claim 1, characterized in that The performing signal characteristic analysis on the effective guided wave signal of the corrosion area to obtain the corrosion area distribution data includes: Based on the effective guided wave signal of the corrosion area, the position of the corrosion area and the depth of the corrosion area are determined by using the reflection time difference method and the amplitude attenuation method respectively; A multi-point corrosion distribution analysis is performed based on the position of the corrosion area and the depth of the corrosion area to obtain the corrosion area distribution data.

3. The method according to claim 2, characterized in that The method of determining the position and depth of the corrosion area based on the effective guided wave signal of the corrosion area by using a reflection time difference method and an amplitude attenuation method respectively includes: Determining the arrival time, waveguide propagation velocity, and signal start offset time of the reflected signal based on the effective waveguide signal of the corrosion area, and calculating the axial position of the corrosion reflection point based on the arrival time, waveguide propagation velocity, and signal start offset time of the reflected signal; Obtaining the signal phase difference, the drainage pipe diameter, and the guided wave wavelength corresponding to the effective guided wave signal of the corrosion area, and calculating the circumferential angle of the corrosion area based on the signal phase difference, the drainage pipe diameter, and the guided wave wavelength; Determining the position of the corrosion area based on the axial position of the corrosion reflection point and the circumferential angle of the corrosion area; The effective guided wave signal of the corrosion area is subjected to curve fitting to obtain the depth of the corrosion area.

4. The method according to claim 1, wherein Also includes: The corrosion area distribution data and the corrosion development trend data are visualized and displayed.

5. A drainage pipe corrosion detection device based on ultrasonic guided waves, characterized in that: The device comprises: A guided wave transceiver module is used to obtain ultrasonic guided wave signals inside the target drainage pipe sent by multiple ultrasonic guided wave transducers; the multiple ultrasonic guided wave transducers are evenly arranged along the circumference of the inner wall of the target drainage pipe to form an ultrasonic guided wave transducer array; A signal conversion module, used to convert the ultrasonic guided wave signal to obtain an effective guided wave signal of the corrosion area; An analysis module is used to perform signal characteristic analysis on the effective guided wave signal of the corrosion area to obtain corrosion area distribution data; A prediction module is used to predict the corrosion state of the drainage pipe based on the effective guided wave signal of the corrosion area using a convolutional neural network model to obtain corrosion development trend data; A generation module, configured to generate drainage pipe corrosion detection results based on the corrosion area distribution data and the corrosion development trend data; The signal conversion module includes: A denoising unit, configured to perform denoising processing on the ultrasonic guided wave signal using an adaptive wavelet threshold denoising method; a filtering unit, configured to filter the ultrasonic guided wave signal after the denoising process, and extract effective frequency characteristics of the corrosion area based on the ultrasonic guided wave signal after the filtering process; A spectrum analysis unit is used to perform spectrum analysis on the effective frequency characteristics of the corrosion area to obtain the effective guided wave signal of the corrosion area; The denoising unit includes: A decomposition subunit, used for performing wavelet decomposition on the ultrasonic guided wave signal to obtain low-frequency coefficients and high-frequency coefficients; A noise estimation subunit, configured to perform noise estimation based on the high frequency coefficients to obtain a noise estimation value; an acquisition subunit, configured to acquire a signal-to-noise ratio corresponding to the ultrasonic guided wave signal, and determine an adaptive threshold based on the noise estimation value and the signal-to-noise ratio; A screening subunit, configured to screen high-frequency coefficients using an adaptive threshold to obtain screened high-frequency coefficients; The correction subunit is used to perform multi-scale interactive correction on the filtered high-frequency coefficients to obtain the corrected high-frequency coefficients; The signal reconstruction subunit is used to reconstruct the signal based on the low-frequency coefficients and the corrected high-frequency coefficients to obtain the ultrasonic guided wave signal after denoising.

6. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the drainage pipe corrosion detection method based on ultrasonic guided waves according to any one of claims 1 to 4 by executing the computer instructions.

7. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the drainage pipe corrosion detection method based on ultrasonic guided waves according to any one of claims 1 to 4.

8. A computer program product, characterized in that The method comprises computer instructions for causing a computer to execute the drainage pipe corrosion detection method based on ultrasonic guided waves according to any one of claims 1 to 4.

Images