Joint coating quality evaluation method and device and electronic equipment

Abstract

The invention discloses a joint coating quality evaluation method and device and electronic equipment, relates to the technical field of nondestructive testing, and aims to visually reflect the quality condition of a pipeline joint coating. The method comprises the steps that a time domain echo signal in a to-be-detected area is obtained after the to-be-detected area is detected through an ultrasonic pulse echo method, a first characteristic parameter is extracted from the time domain echo signal, and the first characteristic parameter is used for representing the quality of a pipeline joint coating; identifying abnormal data in the time domain echo signal, and preliminarily judging whether the quality of the pipeline joint coating is qualified or not; the time domain echo signal is converted into a frequency domain echo signal, a second characteristic parameter is extracted from the frequency domain echo signal, and the second characteristic parameter is used for representing the quality of the pipeline joint coating; and fusing the first feature parameter and the second feature parameter, constructing a joint coating quality evaluation model, and outputting a joint coating quality score through the joint coating quality evaluation model.

Description

Technical Field

[0001] This application relates to the field of nondestructive testing technology, and in particular to a method, apparatus and electronic equipment for evaluating the quality of joint repairs. Background Technology

[0002] Pipeline joint repair is a crucial step in ensuring the integrity of pipeline corrosion protection. The quality of pipeline joint repair directly affects the overall performance, safety, and service life of the pipeline. Non-destructive testing (NDT) technology can detect the presence of pipeline joints without damaging the pipe, offering high efficiency and ease of operation.

[0003] Currently, there is a method for detecting pipe joints using the water immersion ultrasonic pulse echo method. This method obtains the average energy and low-frequency energy parameter curves of a standard sample and compares them with the parameter values ​​obtained from on-site testing to evaluate the joint quality. However, this method is not intuitive enough in evaluating joint quality. Summary of the Invention

[0004] The purpose of this application is to provide a method, apparatus, and electronic device for evaluating the quality of pipeline repair joints, which aims to intuitively reflect the quality status of pipeline repair joints.

[0005] To achieve the above objectives, this application adopts the following technical solution:

[0006] Firstly, this application provides a method for evaluating the quality of patch joints, including:

[0007] After the area to be tested is detected by ultrasonic pulse echo method, the time domain echo signal in the area to be tested is obtained, and the first characteristic parameter is extracted from the time domain echo signal. The first characteristic parameter is used to characterize the quality of the pipe joint.

[0008] Identify abnormal data in the time-domain echo signal to make a preliminary judgment on whether the quality of the pipeline patch is up to standard.

[0009] The time-domain echo signal is converted into a frequency-domain echo signal, and a second characteristic parameter is extracted from the frequency-domain echo signal. The second characteristic parameter is used to characterize the quality of the pipe joint.

[0010] By integrating the first and second feature parameters, a joint quality evaluation model is constructed, and the joint quality score is output through the joint quality evaluation model.

[0011] The patch joint quality evaluation method provided in this application extracts feature parameters from the time-domain signal, converts the time-domain signal to the frequency-domain signal, extracts feature parameters again, and fuses the feature parameters extracted from the time-domain and frequency-domain analyses to construct a patch joint quality evaluation model. This model quantitatively analyzes the patch joint quality and outputs a specific patch joint quality score. By combining time-domain and frequency-domain analysis, richer and more comprehensive information can be captured, thereby improving detection accuracy and comprehensiveness. By outputting the patch joint quality score, the actual quality status of the pipeline patch joint can be reflected more intuitively in numerical form, quantifying the patch joint quality and providing support for accurate patch joint quality assessment. This also provides users with intuitive and accurate patch joint quality evaluation results.

[0012] In some embodiments, identifying abnormal data in the time-domain echo signal and making a preliminary judgment on whether the quality of the pipeline patch is qualified includes: analyzing the time-domain echo signal in the area to be detected using a patch judgment strategy to determine whether a patch exists in the area to be detected, and extracting the pipeline patch echo signal from the time-domain echo signal; analyzing the pipeline patch echo signal using a time-domain analysis strategy to identify abnormal data in the pipeline patch echo signal and make a preliminary judgment on whether the quality of the pipeline patch is qualified.

[0013] In some embodiments, a patching determination strategy is used to analyze the time-domain echo signal in the area to be detected, determine whether a patch exists in the area to be detected, and extract the pipe patch echo signal from the time-domain echo signal. This includes: acquiring the time-domain echo signal of the area to be detected and preprocessing the time-domain echo signal; setting an echo threshold for the time-domain echo signal, defining a baseline, and marking the baseline in the time-domain echo signal; if there is no amplitude exceeding the baseline in the time-domain echo signal, it is determined that there is no patch in the area to be detected; if there is an amplitude exceeding the baseline in the time-domain echo signal, it is determined that there is a patch in the area to be detected, and a first patch echo signal and a second patch echo signal of the pipe patch are extracted from the time-domain echo signal. The first patch echo signal is the echo signal passing through the outer bonding surface of the pipe patch, and the second patch echo signal is the echo signal passing through the inner bonding surface of the pipe patch.

[0014] In some embodiments, extracting the first and second patch echo signals of the pipeline patch from the time-domain echo signal includes: recording the first amplitude value that first exceeds the baseline in the time-domain echo signal and the corresponding first time point; obtaining the first time window width corresponding to the first time point, and extracting the first patch echo signal from the time-domain echo signal with the first time point as the starting point and the sum of the first time point and the first time window width as the ending point; removing the first patch echo signal from the time-domain echo signal; if there is no amplitude exceeding the baseline in the time-domain echo signal after removing the first patch echo signal, determining that the second patch echo signal has not been identified, and determining that the quality of the pipeline patch is unqualified; if there is an amplitude exceeding the baseline in the time-domain echo signal after removing the first patch echo signal, recording the second amplitude value that first exceeds the baseline in the time-domain echo signal and the corresponding second time point; obtaining the second time window width corresponding to the second time point, and extracting the second patch echo signal from the time-domain echo signal with the second time point as the starting point and the sum of the second time point and the second time window width as the ending point.

[0015] In some embodiments, a time-domain analysis strategy is used to analyze the pipeline patch echo signal to identify abnormal data and preliminarily determine whether the pipeline patch is of acceptable quality. This includes: extracting the first echo peak value from the first patch echo signal and the second echo peak value from the second patch echo signal; determining the echo peak value difference based on the first and second echo peak values; determining the quality of the pipeline patch is acceptable if the echo peak value difference is less than or equal to a peak value difference threshold; and determining the quality of the pipeline patch is unacceptable if the echo peak value difference is greater than the peak value difference threshold.

[0016] In some embodiments, converting a time-domain echo signal into a frequency-domain echo signal and extracting a second feature parameter from the frequency-domain echo signal includes: converting the time-domain echo signal into a frequency-domain echo signal using a feature extraction strategy and extracting a second feature parameter from the frequency-domain echo signal; converting the time-domain echo signal into a frequency-domain echo signal using a feature extraction strategy and extracting a second feature parameter from the frequency-domain echo signal includes: converting a first-parsed echo signal into a first-parsed frequency-domain signal using Fourier transform, and converting a second-parsed echo signal into a second-parsed frequency-domain signal; reading a first angular frequency and a first frequency window width from the first-parsed frequency-domain signal, and the second-parsed frequency-domain signal. The second angular frequency and the second frequency window width in the signal are calculated; the first spectral average value of the first supplemented frequency domain signal and the second spectral average value of the second supplemented frequency domain signal are calculated; based on the first angular frequency, the first frequency window width, and the first spectral average value of the first supplemented frequency domain signal, the ratio of the fourth-order central moment to the square of the second-order central moment of the first supplemented frequency domain signal is calculated to obtain the first spectral kurtosis of the first supplemented frequency domain signal; based on the second angular frequency, the second frequency window width, and the second spectral average value of the second supplemented frequency domain signal, the ratio of the fourth-order central moment to the square of the second-order central moment of the second supplemented frequency domain signal is calculated to obtain the second spectral kurtosis of the second supplemented frequency domain signal.

[0017] In some embodiments, the method further includes: constructing a first feature parameter matrix of a first time-domain echo signal, the first feature parameter matrix consisting of a first padded echo signal, a first echo peak value, a first echo root mean square value, a first spectral average value, and a first spectral kurtosis; constructing a second feature parameter matrix of a second time-domain echo signal, the second feature parameter matrix consisting of a second padded echo signal, a second echo peak value, a second echo root mean square value, a second spectral average value, and a second spectral kurtosis; determining the maximum value of the echo peak value, the maximum value of the echo root mean square value, the optimal value of the spectral average value, and the optimal value of the spectral kurtosis; and determining a lower limit threshold and an upper limit threshold for the spectral average value. The system defines the allowable range of threshold values ​​and spectral average values, as well as the lower threshold, upper threshold, and allowable range of spectral kurtosis. Based on the maximum echo peak value, the maximum echo root mean square value, the optimal spectral average value, the optimal spectral kurtosis value, the lower threshold, upper threshold, and allowable range of spectral average values, the lower and upper thresholds of spectral kurtosis, and the allowable range of spectral kurtosis, the system calculates the quality scores of the outer and inner bonding surfaces of the pipe joint. Finally, it generates and outputs a joint inspection file containing the quality scores of both the outer and inner bonding surfaces of the pipe joint.

[0018] In some embodiments, the method further includes: collecting a dataset containing echo peak value, spectral mean value, echo root mean square (RMS), and spectral kurtosis to construct a first feature parameter set; standardizing the value of each feature parameter in the first feature parameter set to obtain a second feature parameter set; dividing the value of each feature parameter in the second feature parameter set into a preset number of equally wide intervals; counting the number of samples in each interval and calculating the probability of the feature parameter value in each interval; calculating the difference coefficients of echo peak value, echo RMS, spectral mean, and spectral kurtosis respectively; and normalizing the difference coefficients of echo peak value, echo RMS, spectral mean, and spectral kurtosis respectively to obtain the weighting coefficients of echo peak value, echo RMS, spectral mean, and spectral kurtosis.

[0019] Secondly, this application provides a joint quality evaluation device, including an analysis module, which is used for:

[0020] After the area to be tested is detected by ultrasonic pulse echo method, the time domain echo signal in the area to be tested is obtained, and the first characteristic parameter is extracted from the time domain echo signal. The first characteristic parameter is used to characterize the quality of the pipe joint.

[0021] Identify abnormal data in the time-domain echo signal to make a preliminary judgment on whether the quality of the pipeline patch is up to standard.

[0022] The time-domain echo signal is converted into a frequency-domain echo signal, and a second characteristic parameter is extracted from the frequency-domain echo signal. The second characteristic parameter is used to characterize the quality of the pipe joint.

[0023] By integrating the first and second feature parameters, a joint quality evaluation model is constructed, and the joint quality score is output through the joint quality evaluation model.

[0024] In some embodiments, the analysis module is specifically used to: analyze the time-domain echo signal in the area to be detected using a patching judgment strategy, determine whether a patch exists in the area to be detected, and extract the pipe patch echo signal from the time-domain echo signal; analyze the pipe patch echo signal using a time-domain analysis strategy, identify abnormal data in the pipe patch echo signal, and preliminarily determine whether the quality of the pipe patch is qualified.

[0025] In some embodiments, the analysis module is specifically used to: acquire the time-domain echo signal of the area to be detected and preprocess the time-domain echo signal; set the echo threshold of the time-domain echo signal, define a baseline, and mark the baseline in the time-domain echo signal; if there is no amplitude exceeding the baseline in the time-domain echo signal, it is determined that there is no patch in the area to be detected; if there is an amplitude exceeding the baseline in the time-domain echo signal, it is determined that there is a patch in the area to be detected, and extract the first patch echo signal and the second patch echo signal of the pipe patch from the time-domain echo signal, wherein the first patch echo signal is the echo signal passing through the outer bonding surface of the pipe patch, and the second patch echo signal is the echo signal passing through the inner bonding surface of the pipe patch.

[0026] In some embodiments, the analysis module is specifically used to: record the first amplitude value that first exceeds the baseline in the time-domain echo signal and the corresponding first time point; obtain the first time window width corresponding to the first time point, and extract the first patch echo signal from the time-domain echo signal with the first time point as the starting point and the sum of the first time point and the first time window width as the ending point; remove the first patch echo signal from the time-domain echo signal; if there is no amplitude exceeding the baseline in the time-domain echo signal after removing the first patch echo signal, determine that the second patch echo signal has not been identified, and determine that the quality of the pipe patch is unqualified; if there is an amplitude exceeding the baseline in the time-domain echo signal after removing the first patch echo signal, record the second amplitude value that first exceeds the baseline in the time-domain echo signal and the corresponding second time point; obtain the second time window width corresponding to the second time point, and extract the second patch echo signal from the time-domain echo signal with the second time point as the starting point and the sum of the second time point and the second time window width as the ending point.

[0027] In some embodiments, the analysis module is specifically used to: extract the first echo peak value in the first patch echo signal and the second echo peak value in the second patch echo signal; determine the echo peak value difference based on the first echo peak value and the second echo peak value; if the echo peak value difference is less than or equal to the peak value difference threshold, determine that the quality of the pipe patch is qualified; if the echo peak value difference is greater than the peak value difference threshold, determine that the quality of the pipe patch is unqualified.

[0028] In some embodiments, the analysis module is specifically used to: convert the time-domain echo signal into a frequency-domain echo signal using a feature extraction strategy, and extract a second feature parameter from the frequency-domain echo signal; the analysis module is specifically used to: convert the first padded echo signal into a first padded frequency-domain signal using Fourier transform, and convert the second padded echo signal into a second padded frequency-domain signal; read the first angular frequency and the first frequency window width in the first padded frequency-domain signal, and the second angular frequency and the second frequency window width in the second padded frequency-domain signal; calculate the first spectral average value of the first padded frequency-domain signal and the second spectral average value of the second padded frequency-domain signal; based on the first angular frequency, the first frequency window width, and the first spectral average value of the first padded frequency-domain signal, calculate the ratio of the fourth-order central moment to the square of the second-order central moment of the first padded frequency-domain signal to obtain the first spectral kurtosis of the first padded frequency-domain signal; based on the second angular frequency, the second frequency window width, and the second spectral average value of the second padded frequency-domain signal, calculate the ratio of the fourth-order central moment to the square of the second-order central moment of the second padded frequency-domain signal to obtain the second spectral kurtosis of the second padded frequency-domain signal.

[0029] In some embodiments, the analysis module is further configured to: construct a first feature parameter matrix of a first time-domain echo signal, the first feature parameter matrix consisting of a first padded echo signal, a first echo peak value, a first echo root mean square, a first spectral average value, and a first spectral kurtosis; construct a second feature parameter matrix of a second time-domain echo signal, the second feature parameter matrix consisting of a second padded echo signal, a second echo peak value, a second echo root mean square, a second spectral average value, and a second spectral kurtosis; determine the maximum value of the echo peak value, the maximum value of the echo root mean square, the optimal value of the spectral average value, and the optimal value of the spectral kurtosis; and determine the lower limit threshold and the upper limit threshold of the spectral average value. The system defines the allowable range of threshold values ​​and spectral average values, as well as the lower threshold, upper threshold, and allowable range of spectral kurtosis. Based on the maximum echo peak value, the maximum echo root mean square value, the optimal spectral average value, the optimal spectral kurtosis value, the lower threshold, upper threshold, and allowable range of spectral average values, the lower and upper thresholds of spectral kurtosis, and the allowable range of spectral kurtosis, the system calculates the quality scores of the outer and inner bonding surfaces of the pipe joint. Finally, it generates and outputs a joint inspection file containing the quality scores of both the outer and inner bonding surfaces of the pipe joint.

[0030] In some embodiments, the analysis module is further configured to: collect a dataset containing echo peak value, spectral mean value, echo root mean square (RMS), and spectral kurtosis to construct a first feature parameter set; standardize the value of each feature parameter in the first feature parameter set to obtain a second feature parameter set; divide the value of each feature parameter in the second feature parameter set into a preset number of equally wide intervals; count the number of samples in each interval and calculate the probability of the feature parameter value in each interval; calculate the difference coefficients of echo peak value, echo root mean square (RMS), spectral mean value, and spectral kurtosis respectively; and normalize the difference coefficients of echo peak value, echo root mean square (RMS), spectral mean value, and spectral kurtosis respectively to obtain the weighting coefficients of echo peak value, echo root mean square (RMS), spectral mean value, and spectral kurtosis.

[0031] Thirdly, this application provides an electronic device, including: one or more processors; one or more memories; wherein the one or more memories are used to store computer program code, the computer program code including computer instructions, and when the one or more processors execute the computer instructions, the electronic device executes any of the plating quality evaluation methods provided in the first aspect above.

[0032] Fourthly, this application provides a computer-readable storage medium storing computer-executable instructions that, when executed on a computer, cause the computer to perform any of the plating quality evaluation methods provided in the first aspect above.

[0033] Fifthly, this application provides a computer program product including computer instructions that, when executed on an electronic device, cause the electronic device to perform any of the plating quality evaluation methods provided in the first aspect.

[0034] For a detailed description of the second to fifth aspects and their various implementations in this application, please refer to the detailed description in the first aspect and its various implementations; and for a detailed analysis of the beneficial effects of the second to fifth aspects and their various implementations in the first aspect and its various implementations, please refer to the beneficial effect analysis in the first aspect and its various implementations, which will not be repeated here.

[0035] These or other aspects of this application will become more readily apparent in the following description. Attached Figure Description

[0036] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0037] Figure 1 This is a schematic diagram of the structure of a joint quality evaluation system provided in an embodiment of this application;

[0038] Figure 2 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application;

[0039] Figure 3 This is a schematic diagram of the structure of a computing device provided in an embodiment of this application;

[0040] Figure 4 A flowchart of a joint quality evaluation method provided in this application embodiment;

[0041] Figure 5 A schematic diagram illustrating the echo signal extraction process provided in an embodiment of this application;

[0042] Figure 6 A logical diagram illustrating a time-domain analysis strategy provided in an embodiment of this application;

[0043] Figure 7 A logical schematic diagram of a feature extraction strategy provided in an embodiment of this application;

[0044] Figure 8 A logical diagram illustrating an analysis strategy provided in an embodiment of this application;

[0045] Figure 9 This is a schematic diagram of a joint quality evaluation device provided in an embodiment of this application. Detailed Implementation

[0046] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0047] In the description of this application, it should be understood that the terms "upper," "lower," "left," "right," "front," "rear," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or relative positional relationship shown in the accompanying drawings. They are used only for the convenience of describing this application and for simplification, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this application. Unless otherwise specified, the above-mentioned orientational descriptions can be flexibly set in practical applications, provided that the relative positional relationships shown in the accompanying drawings are satisfied.

[0048] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, unless otherwise stated, "a plurality of" means two or more.

[0049] In the description of this application, it should be noted that, unless otherwise expressly specified and limited, the terms "installation," "connection," "linking," and "communication" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection. They can refer to a direct connection or an indirect connection through an intermediate medium, or a connection within two components. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances.

[0050] In embodiments of this application, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, article, or apparatus that includes that element.

[0051] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design that is described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design. Specifically, the use of the terms "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0052] In the description of this specification, specific features, structures, materials, or characteristics may be combined in any suitable manner in one or more embodiments or examples.

[0053] Pipeline joint repair is a crucial step in ensuring the integrity of pipeline corrosion protection. The quality of pipeline joint repair directly affects the overall performance, safety, and service life of the pipeline. Non-destructive testing (NDT) technology can detect the presence of pipeline joints without damaging the pipe, offering high efficiency and ease of operation.

[0054] Currently, there is a method for detecting pipe joints using the water immersion ultrasonic pulse echo method. This method obtains the average energy and low-frequency energy parameter curves of a standard sample and compares them with the parameter values ​​obtained from on-site testing to evaluate the joint quality. However, this method is not intuitive enough in evaluating joint quality.

[0055] Based on this, this application provides a method for evaluating the quality of pipe repair joints. The method involves acquiring the time-domain echo signal in the area to be inspected after ultrasonic pulse echo testing, extracting a first feature parameter from the time-domain echo signal (the first feature parameter characterizes the quality of the pipe repair joint), identifying abnormal data in the time-domain echo signal to preliminarily determine whether the quality of the pipe repair joint is acceptable, converting the time-domain echo signal into a frequency-domain echo signal, and extracting a second feature parameter from the frequency-domain echo signal (the second feature parameter characterizes the quality of the pipe repair joint), fusing the first and second feature parameters to construct a repair joint quality evaluation model, and outputting a repair joint quality score through the model. This application's solution first extracts feature parameters from the time-domain signal, then converts the time-domain signal into a frequency-domain signal, and then extracts feature parameters again. By fusing the feature parameters extracted from the time-domain and frequency-domain analyses, a repair joint quality evaluation model is constructed to quantitatively analyze the repair joint quality and output a specific repair joint quality score. Combining time-domain and frequency-domain analysis allows for the capture of richer and more comprehensive information, thereby improving detection accuracy and comprehensiveness. By outputting the quality score of the pipe joint, the actual quality status of the pipe joint can be reflected more intuitively in numerical form, the quality of the joint is quantified, support is provided for the accurate assessment of the joint quality, and users are provided with intuitive and accurate evaluation results of the joint quality.

[0056] Please refer to Figure 1 This illustrates the joint quality evaluation system provided in this application. The joint quality evaluation system includes: joint inspection equipment 10 and electronic equipment 20.

[0057] The patch detection device 10 establishes a communication connection with the electronic device 20. It should be understood that the connection method can be wireless or wired.

[0058] In some embodiments, the patch quality evaluation system may further include a switch ( Figure 1 (Not shown), the switch is used to connect the patch detection device 10 and the electronic device 20 to build a local area network and realize communication between the patch detection device and the electronic device 20.

[0059] The joint inspection equipment 10 employs non-destructive testing (NDT) technology to inspect pipe joints. NDT refers to a testing method that examines the surface and internal quality of components without damaging the workpiece or raw materials. Common NDT techniques include ultrasonic testing, radiographic testing, magnetic particle testing, penetrant testing, and infrared thermography. This application primarily relates to ultrasonic testing. Ultrasonic testing utilizes the reflection and refraction of ultrasonic waves at the interface between two media with different acoustic impedances, as well as the attenuation during propagation. An ultrasonic wave is emitted from a transmitting probe towards the object being inspected, and the probe receives the reflected ultrasonic waves from the interface or the transmitted waves after passing through the object, thereby detecting the presence of defects in the component.

[0060] The patch inspection device 10 is used to transmit ultrasonic signals to the area to be inspected, and to receive ultrasonic signals reflected back from the area to be inspected, and to send the received signals to the electronic device 20.

[0061] Electronic device 20 is used to receive the echo signal of ultrasonic waves, perform time-domain analysis and frequency-domain analysis on the echo signal, detect whether there is a patch in the pipeline in the area to be detected, and determine the quality score of the patch if a patch exists, and find quality problems or abnormalities in the pipeline patch.

[0062] like Figure 2 As shown, the electronic device may include an analysis module, which is specifically divided into a time-domain analysis unit, a frequency-domain analysis unit, and a joint analysis unit.

[0063] The time-domain analysis unit is used to process and analyze the time-domain echo signal, extracting the first characteristic parameters related to the quality of the patch, such as the abrupt change point, peak value, and duration of the time-domain echo signal; it is also used to analyze the changes of the time-domain echo signal over time, identify abnormal patterns or trends in the time-domain echo signal, and thus make a preliminary judgment on the quality of the patch to determine whether the quality of the pipeline patch is qualified.

[0064] The frequency domain analysis unit is used to convert the time domain echo signal into a frequency domain echo signal, analyze the frequency domain echo signal, and extract a second characteristic parameter related to the quality of the pipe patch, such as the presence of frequency components and the frequency range of energy concentration. The second characteristic parameter helps to further determine whether there are potential quality problems in the pipe patch.

[0065] The joint analysis unit is used to fuse the features extracted by the time domain analysis unit and the frequency domain analysis unit to achieve quantitative analysis of the patching quality. At the same time, it constructs a patching evaluation model, and by comparing the correlation and complementarity between different features, it forms a comprehensive evaluation of the patching quality and outputs a quantitative patching quality score, providing operators with intuitive and accurate quality evaluation results.

[0066] In some specific embodiments, the patch inspection device 10 is an ultrasonic testing device. The ultrasonic testing device includes a scanning frame, a probe, a field-programmable gate array (FPGA) control unit, a power management unit, a signal transmitter, a signal receiver, and a data processing unit.

[0067] The probe is fixed by a scanning frame, allowing the frame to move so that the probe can move axially or circumferentially along the pipe for detection. Direct contact between the probe and the area to be inspected helps reduce attenuation and interference of sound waves during propagation, improving the accuracy and reliability of the detection. The probe sends ultrasonic signals to the area to be inspected and receives the returned ultrasonic signals. The initial center frequency of the probe is set to f. C The sampling rate is f s And f s ≥2f C This helps to avoid aliasing.

[0068] The FPGA control unit is used to generate signals to drive the transmitting circuit in the signal transmitter, save and output the received signal data, and realize the coordinated operation and control management between units.

[0069] The power management unit provides the power required by the ultrasonic testing equipment, including analog domain power and digital domain power.

[0070] The signal transmitter is used to receive drive signals from the FPGA control unit and generate multi-channel ultrasonic signals.

[0071] The signal receiver is mainly used to receive the returned ultrasonic signals. The received ultrasonic signals are transmitted to the data processing unit after passing through a variable gain amplifier and an anti-aliasing filter.

[0072] The data processing unit is used to perform A / D conversion on the output signal of the multi-channel signal receiver, generate time-domain signal data, and transmit the data to the FPGA control unit.

[0073] In some embodiments, the electronic device 20 may include a human-machine interface (HMI) device for displaying inspection results to a user. The inspection results include whether there are pipe repairs in the inspected area, and if so, a quality score for the pipe repair. For example, the HMI device may include a display providing an interactive interface to display the inspection results to the user in a graphical and textual format, and to receive user actions on the inspection results. The HMI device may also include operation buttons providing menu options to receive user actions such as saving, downloading, and viewing the inspection results.

[0074] Specifically, as follows Figure 2As shown, the analysis module of the electronic device 20 may also include a user interface unit. The user interface unit provides an intuitive user interface, allowing users to interact with the electronic device 20 and view the test results. The user interface unit may include a display screen and a control panel. The display screen shows relevant charts or data information of the test results, time-domain analysis, and frequency-domain analysis, facilitating a clear understanding of the patch's quality status. The control panel provides various operation buttons and menu options, allowing users to set and adjust various parameters or thresholds, such as adding analytical features or changing quality evaluation thresholds.

[0075] In some embodiments, the patching detection device 10 and the electronic device 20 can be two independent devices, or the electronic device 20 can be integrated into the patching detection device 10.

[0076] In some embodiments, the joint quality evaluation system may include one or more joint detection devices 10. When the joint quality evaluation system includes multiple joint detection devices 10, the electronic device 20 performs joint detection and joint quality evaluation on the echo signals of the ultrasonic waves sent by each joint detection device 10.

[0077] In some embodiments, the patching quality evaluation system may include one or more electronic devices 20. This allows for multiple patching detection results, avoiding errors that may occur in a single detection.

[0078] The hardware structure of electronic device 20 includes Figure 3 The components included in the computing device shown.

[0079] like Figure 3 As shown, the computing device may include a processor 201, a memory 202, a communication interface 203, and a bus 204. The processor 201, the memory 202, and the communication interface 203 can be connected via the bus 204.

[0080] Processor 201 is the control center of the computing device. It can be a single processor or a collective term for multiple processing elements. For example, processor 201 can be a general-purpose central processing unit (CPU) or other general-purpose processors. Among them, the general-purpose processor can be a microprocessor or any conventional processor.

[0081] As one embodiment, processor 201 may include one or more CPUs, for example Figure 3 CPU 0 and CPU 1 are shown in the diagram.

[0082] The memory 202 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but is not limited thereto.

[0083] In one possible implementation, the memory 202 can exist independently of the processor 201. The memory 202 can be connected to the processor 201 via a bus 204 and is used to store instructions or program code. When the processor 201 calls and executes the instructions or program code stored in the memory 202, it can implement the patching quality evaluation method provided in this application embodiment.

[0084] In another possible implementation, the memory 202 can also be integrated with the processor 201.

[0085] The communication interface 203 is used for connecting the computing device to other devices via a communication network, such as Ethernet, radio access network (RAN), wireless local area network (WLAN), etc. The communication interface 203 may include a receiving unit for receiving data and a transmitting unit for transmitting data.

[0086] Bus 204 can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. This bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 3 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0087] It should be pointed out that, Figure 3 The structure shown does not constitute a limitation on the computing device, except Figure 3In addition to the components shown, the computing device may include more or fewer components than illustrated, or combine certain components, or have different component arrangements.

[0088] The embodiments of this application will now be described in detail with reference to the accompanying drawings.

[0089] like Figure 4 As shown, this application embodiment provides a method for evaluating the quality of patching, which can be executed by the aforementioned electronic device 20. The method includes the following steps:

[0090] S101. Obtain the time-domain echo signal in the area to be detected after the area is detected by ultrasonic pulse echo method, and extract the first feature parameter from the time-domain echo signal.

[0091] The first characteristic parameter is used to characterize the quality of the pipe joint.

[0092] For example, the first characteristic parameter may include the abrupt change point, peak value, duration, etc. of the time-domain echo signal.

[0093] S102. Identify abnormal data in the time-domain echo signal to make a preliminary judgment on whether the quality of the pipeline patch is up to standard.

[0094] In some embodiments, step S102 can be specifically implemented as follows: analyzing the time-domain echo signal in the area to be detected using a patching judgment strategy to determine whether a patch exists in the area to be detected, and extracting the pipe patch echo signal from the time-domain echo signal; analyzing the pipe patch echo signal using a time-domain analysis strategy to identify abnormal data in the pipe patch echo signal, and preliminarily determining whether the quality of the pipe patch is qualified.

[0095] The gap-filling judgment strategy and the time-domain analysis strategy can be configured in the time-domain analysis unit.

[0096] The pipeline patch detection strategy analyzes the time-domain echo signal in the area to be inspected to determine whether a patch exists in the area, and also to determine whether there are special areas formed by material connections, repairs, or reinforcements. The pipeline patch echo signal refers to the return signal from the area where a patch exists. Abnormal data in the pipeline patch echo signal can include abnormal echo signals caused by defects, damage, or other anomalies at the patch.

[0097] In some embodiments, a patching determination strategy is used to analyze the time-domain echo signal in the area to be detected, determine whether a patch exists in the area to be detected, and extract the pipe patch echo signal from the time-domain echo signal. Specifically, this can be implemented as follows: acquire the time-domain echo signal of the area to be detected and preprocess the time-domain echo signal; set an echo threshold for the time-domain echo signal, define a baseline, and mark the baseline in the time-domain echo signal; if there is no amplitude exceeding the baseline in the time-domain echo signal, it is determined that there is no patch in the area to be detected; if there is an amplitude exceeding the baseline in the time-domain echo signal, it is determined that there is a patch in the area to be detected, and extract the first patch echo signal and the second patch echo signal from the time-domain echo signal. The first patch echo signal is the echo signal passing through the outer bonding surface of the pipe patch, and the second patch echo signal is the echo signal passing through the inner bonding surface of the pipe patch.

[0098] The preprocessing process involves using digital filtering techniques to remove noise components from the time-domain echo signal. Noise components may be caused by environmental factors, limitations of the equipment itself, or interference during signal transmission. The preprocessing process uses a signal amplifier to enhance the filtered echo signal, which helps to make subtle changes in the time-domain echo signal more apparent, thus making it easier to detect and identify anomalies.

[0099] The time-domain echo signal is represented by x(t), the echo threshold is represented by A, and the baseline is x=A. Marking the baseline in the time-domain echo signal can quickly identify whether there is a valid echo signal in the time-domain echo signal. If there is a valid echo signal, it means that there is a patch in the area to be detected. If there is no valid echo signal, it means that there is no patch in the area to be detected.

[0100] The first filler echo signal is characterized by R1(t), and the second filler echo signal is characterized by R2(t).

[0101] In some embodiments, extracting the first and second patch echo signals of the pipeline patch from the time-domain echo signal can be specifically implemented as follows: recording the first amplitude value that first exceeds the baseline in the time-domain echo signal and the corresponding first time point; obtaining the first time window width corresponding to the first time point, and extracting the first patch echo signal from the time-domain echo signal with the first time point as the starting point and the sum of the first time point and the first time window width as the ending point; removing the first patch echo signal from the time-domain echo signal; if there is no amplitude exceeding the baseline in the time-domain echo signal after removing the first patch echo signal, determining that the second patch echo signal has not been identified, and determining that the quality of the pipeline patch is unqualified; if there is an amplitude exceeding the baseline in the time-domain echo signal after removing the first patch echo signal, recording the second amplitude value that first exceeds the baseline in the time-domain echo signal and the corresponding second time point; obtaining the second time window width corresponding to the second time point, and extracting the second patch echo signal from the time-domain echo signal with the second time point as the starting point and the sum of the second time point and the second time window width as the ending point.

[0102] Here, the first amplitude is represented by ε1, and the first time point is represented by t1. The first amplitude ε1 is the signal intensity reflected back when the ultrasonic wave reaches the outer bonding surface of the joint, and the first time point t1 is the time when the reflected signal after passing through the outer bonding surface is first received.

[0103] Since the echo signal is a continuous signal and is continuously received over a period of time, the time window width Δt1 of the first time point t1 is obtained based on the first amplitude ε1 and its growth and decline phases. The first supplementary echo signal R1(t) is extracted from the time-domain echo signal x(t) with t1 as the starting point and t1+Δt1 as the ending point. Here, Δt1 is the time interval from the first amplitude ε1 as the starting point, the amplitude goes through a growth phase to reach the peak, and then goes through a decline phase or declines to the echo threshold.

[0104] The first supplementary echo signal R1(t) is removed from the time-domain echo signal to facilitate the determination of whether there are other valid echoes in the current time-domain echo signal.

[0105] If there is no amplitude exceeding the baseline in the current time-domain echo signal, it means that there are no other valid echoes in the current time-domain echo signal. Only the echo signal R1(t) of the outer bonding surface is identified, and the echo signal R2(t) of the inner bonding surface is not identified. This is because the outer bonding surface of the patch has fallen off, causing the ultrasonic wave to be unable to penetrate to the inner bonding surface and be reflected. Therefore, the patch quality can be judged to be unqualified.

[0106] The second amplitude is represented by ε2, and the second time point is represented by t2. The second amplitude ε2 is the signal intensity reflected back when the ultrasonic wave reaches the inner bonding surface of the joint. The second time point t2 is the time when the reflected signal after passing through the inner bonding surface is first received. Δt2 is the time interval from the second amplitude ε2, when the amplitude goes through a growth phase to reach its peak, and then goes through a decline phase or declines to the echo threshold.

[0107] If there is an amplitude exceeding the baseline in the current time-domain echo signal, it indicates that there are other valid echoes in the current time-domain echo signal. Record the second amplitude ε2 that first exceeds the baseline in the current time-domain echo signal and the corresponding second time point t2. Obtain the time window width Δt2 of the second time point, and extract the second supplementary echo signal R2(t) from the time-domain echo signal x(t) with t2 as the starting point and t2+Δt2 as the ending point.

[0108] In summary, the process from acquiring the time-domain echo signal to extracting the first and second patch echo signals can be described as follows: Figure 5 As shown.

[0109] In some embodiments, a time-domain analysis strategy is used to analyze the pipeline patch echo signal to identify abnormal data and preliminarily determine whether the pipeline patch is of acceptable quality. This includes: extracting the first echo peak value from the first patch echo signal and the second echo peak value from the second patch echo signal; determining the echo peak value difference based on the first and second echo peak values; determining the quality of the pipeline patch is acceptable if the echo peak value difference is less than or equal to a peak value difference threshold; and determining the quality of the pipeline patch is unacceptable if the echo peak value difference is greater than the peak value difference threshold.

[0110] That is, such as Figure 6 As shown, the specific steps of the time-domain analysis strategy include:

[0111] (1) Obtain the first port echo signal R1(t) and the second port echo signal R2(t).

[0112] (2) Extract the first echo peak value A1 = max{R1(t)} from the first supplementary echo signal R1(t) and obtain the first peak time corresponding to the first echo peak value.

[0113] (3) Extract the second echo peak value A2 = max{R2(t)} from the second echo signal R2(t) and obtain the second peak time corresponding to the second echo peak value.

[0114] (4) Calculate the thickness Δd of the joint.

[0115] Obtain the propagation velocity c1 of the ultrasonic wave in the pipe medium and c2 of the propagation velocity c2 in the joint medium, and calculate the joint thickness Δd, as shown in the following expression:

[0116]

[0117] Wherein, d1 is the distance from the outer bonding surface of the patch to the surface of the area to be tested, and d2 is the distance from the inner bonding surface of the patch to the surface of the area to be tested. d1 and d2 are used to determine the specific location of the patch.

[0118] (5) Calculate the root mean square of the first echo signal R1(t) of the first compensation port echo signal. The expression is as follows:

[0119]

[0120] Calculate the root mean square of the second echo signal R2(t) from the second port. The expression is as follows:

[0121]

[0122] (6) Calculate the echo peak difference.

[0123] Calculate the echo peak difference ΔA = |A1-A2| between the first and second port echo signals R1(t) and R2(t).

[0124] (7) Set the peak difference threshold as

[0125] (8) Determine the quality of the patching.

[0126] Determine if there is a quality problem with the patch: If The peak value difference between the first patch echo signal R1(t) and the second patch echo signal R2(t) is small, indicating that the patching quality is qualified; if The significant difference in peak values ​​between the first patch echo signal R1(t) and the second patch echo signal R2(t) indicates that there may be gaps, incomplete penetration, or incomplete fusion at the patch, thus the patch quality is deemed unqualified.

[0127] S103. Convert the time-domain echo signal into a frequency-domain echo signal, and extract the second characteristic parameter from the frequency-domain echo signal.

[0128] The second characteristic parameter is used to characterize the quality of the pipe joint.

[0129] For example, the second characteristic parameter may include the presence of a specific frequency component, the frequency range of energy concentration, etc.

[0130] In some embodiments, a feature extraction strategy is configured within the frequency domain analysis unit. The feature extraction strategy is used to convert the time domain echo signal into a frequency domain echo signal and extract feature parameters from the frequency domain echo signal.

[0131] Converting a time-domain echo signal to a frequency-domain echo signal and extracting a second feature parameter from the frequency-domain echo signal includes: converting the time-domain echo signal to a frequency-domain echo signal using a feature extraction strategy and extracting a second feature parameter from the frequency-domain echo signal; converting the time-domain echo signal to a frequency-domain echo signal using a feature extraction strategy and extracting a second feature parameter from the frequency-domain echo signal includes: converting a first-parsed echo signal to a first-parsed frequency-domain signal using Fourier transform, and converting a second-parsed echo signal to a second-parsed frequency-domain signal; reading the first angular frequency and the first frequency window width in the first-parsed frequency-domain signal, and the second-parsed frequency-domain signal... The second angular frequency and the second frequency window width are calculated; the first spectral average value of the first supplementary frequency domain signal and the second spectral average value of the second supplementary frequency domain signal are calculated; based on the first angular frequency, the first frequency window width, and the first spectral average value of the first supplementary frequency domain signal, the ratio of the fourth-order central moment to the square of the second-order central moment of the first supplementary frequency domain signal is calculated to obtain the first spectral kurtosis of the first supplementary frequency domain signal; based on the second angular frequency, the second frequency window width, and the second spectral average value of the second supplementary frequency domain signal, the ratio of the fourth-order central moment to the square of the second-order central moment of the second supplementary frequency domain signal is calculated to obtain the second spectral kurtosis of the second supplementary frequency domain signal.

[0132] That is, such as Figure 7 As shown, the specific steps of the feature extraction strategy include:

[0133] (1) Convert the echo signal into a frequency domain signal.

[0134] The first-patch echo signal R1(t) is converted into the first-patch frequency domain signal R1(ω) using Fourier transform, as shown in the following expression:

[0135]

[0136] The second-patch echo signal R2(t) is converted into the second-patch frequency domain signal R2(ω) using Fourier transform, as shown in the following expression:

[0137]

[0138] (2) Extract the first angular frequency ω1 and the first frequency window width Δω1 from the first supplementary frequency domain signal R1(ω).

[0139] (3) Extract the second angular frequency ω2 and the second frequency window width Δω2 from the second supplementary frequency domain signal R2(ω).

[0140] (4) Calculate the average value of the spectrum.

[0141] Calculate the spectral average value of the first compensation frequency domain signal R1(ω). The expression is as follows:

[0142]

[0143] Calculate the spectral average value of the second-complement frequency domain signal R1(ω). The expression is as follows:

[0144]

[0145] In the formula, Let R1(ω) be the first spectral average value of the first supplementary frequency domain signal. It is the second spectral average value of the second supplementary frequency domain signal R2(ω).

[0146] (5) Calculate the spectral kurtosis.

[0147] The spectral kurtosis K of the frequency domain signal is obtained by calculating the ratio of the fourth central moment to the square of the second central moment, as shown in the following expression:

[0148]

[0149] In the formula, Let R1(ω) be the first spectral kurtosis of the first complement frequency domain signal. The second spectral kurtosis is the second frequency domain signal R2(ω).

[0150] S104. Integrate the first feature parameter and the second feature parameter to construct a joint quality evaluation model, and output the joint quality score through the joint quality evaluation model.

[0151] In some embodiments, the joint analysis unit is configured with an analysis strategy, which is used to receive the extracted parameters and construct a patching evaluation model based on the feature parameters to perform quantitative analysis on the patching quality.

[0152] The specific steps of the analysis strategy include:

[0153] A first characteristic parameter matrix is ​​constructed for the first time-domain echo signal, consisting of the first padded echo signal, the first echo peak value, the first echo root mean square (RMS), the first spectral average value, and the first spectral kurtosis. A second characteristic parameter matrix is ​​constructed for the second time-domain echo signal, consisting of the second padded echo signal, the second echo peak value, the second echo RMS, the second spectral average value, and the second spectral kurtosis. The maximum value of the echo peak value, the maximum value of the echo RMS, the optimal value of the spectral average value, and the optimal value of the spectral kurtosis are determined. The lower threshold, upper threshold, and other threshold values ​​for the spectral average value are also determined. The system determines the allowable range of values, as well as the lower threshold, upper threshold, and allowable range of spectral kurtosis. Based on the maximum value of echo peak value, the maximum value of echo root mean square value, the optimal value of spectral average value, the optimal value of spectral kurtosis, the lower threshold, upper threshold, and allowable range of spectral average value, the lower and upper thresholds of spectral kurtosis, and the allowable range of spectral kurtosis, it calculates the quality scores of the outer and inner bonding surfaces of the pipe joint. It then generates and outputs a joint inspection file containing the quality scores of both the outer and inner bonding surfaces of the pipe joint.

[0154] like Figure 8 As shown:

[0155] (1) Construct the characteristic parameter matrix of the port echo signal.

[0156] The first characteristic parameter matrix for constructing the first compensation echo signal R1(t) is as follows: And the second characteristic parameter matrix of the second compensation port echo signal R2(t) is

[0157] (2) Set the maximum or optimal value of each characteristic parameter.

[0158] Set the maximum value of the echo peak to A max The maximum value of the root mean square of the echo is E max The optimal value of the average value of the spectrum is The optimal value for spectral kurtosis is K. bes t.

[0159] (3) Set the allowable range for the average value and kurtosis of the spectrum.

[0160] Set the lower limit threshold for the average spectrum value as follows: Upper limit threshold is And define the allowable range of the average spectral value as follows:

[0161] Set the lower limit threshold for spectral kurtosis to K. min The upper limit threshold is K. maxAnd define the allowable range of spectral kurtosis as [K]. min K max ].

[0162] (4) Calculate the quality scores of the outer and inner bonding surfaces.

[0163] The quality scores S for the outer and inner bonding surfaces of the joint are calculated separately, as shown in the following expressions:

[0164]

[0165] In the formula, The quality score is determined by the quality of the outer bonding surface of the joint. To determine the quality score of the bonding surface inside the joint, w A w E , w K Let be the weight coefficients of each feature parameter, and

[0166] (5) Generate patch detection file.

[0167] Generate a patch joint inspection file, including a patch joint quality judgment (pass or fail) and abnormal behavior (whether there is adhesive detachment), patch joint thickness, characteristic parameter matrix of echo signal, and patch joint quality score. The patch test file is then transmitted to the user interface unit, allowing the user to not only know whether the patch quality is up to standard, but also to obtain the specific parameters of the patch test and the specific score of the patch quality, thus gaining a clearer understanding of the quality level.

[0168] In some embodiments, the construction of weight coefficients in the analysis strategy includes: collecting a dataset containing echo peak value, spectral mean value, echo root mean square (RMS), and spectral kurtosis to construct a first feature parameter set; standardizing the value of each feature parameter in the first feature parameter set to obtain a second feature parameter set; dividing the value of each feature parameter in the second feature parameter set into a preset number of equally wide intervals; counting the number of samples in each interval and calculating the probability of the feature parameter value in each interval; calculating the difference coefficients of echo peak value, echo root mean square (RMS), spectral mean, and spectral kurtosis respectively; and normalizing the difference coefficients of echo peak value, echo root mean square (RMS), spectral mean, and spectral kurtosis respectively to obtain the weight coefficients of echo peak value, echo root mean square (RMS), spectral mean, and spectral kurtosis.

[0169] Collection includes feature parameters The dataset, and construct the first feature parameter set X. ′ =(X′ 1, X ′ 2, ..., X ′ n ); where n is the number of samples collected, and each sample contains the values ​​of four feature parameters.

[0170] The Z-score standardization method is used to standardize the values ​​of each feature parameter in the first feature parameter set to eliminate the dimensional differences between different features, ensuring that the data have the same scale in computation, thus obtaining the second feature dataset X = (X1, X2, ..., X...). n ).

[0171] Based on the maximum and minimum values ​​of each feature parameter in the second feature dataset, the value of each feature parameter is divided into m equally wide intervals. For example, extract the maximum value 'a' of the echo peak value in the second feature dataset X. max and minimum value a min Calculate the width of each interval. Based on the m equal-width intervals [a] of the obtained echo peak value min ,a min +Δa), [a min +Δa,a min +2·Δa), ..., [a] min +(m-1)·Δa,a max ].

[0172] Count the number of samples within each interval and calculate the probability of the feature parameter value within each interval. For example, for the echo peak, the probability of the feature parameter value within the first interval is... The probability of the feature parameter value in the m-th interval is in, The number of samples in the first interval. The number of samples in the m-th interval, and

[0173] The dissimilarity coefficient G for each feature parameter is calculated as follows:

[0174]

[0175] In the formula, G A The difference coefficient of echo peak value, Let G be the probability of the echo peak value in the i-th interval. E The root mean square difference coefficient of the echo. Let be the root mean square probability of the echo in the i-th interval. The coefficient of variation of the average spectrum. G is the probability of the average spectral value within the i-th interval. KThe coefficient representing the difference in spectral kurtosis. Let be the probability of spectral kurtosis in the i-th interval.

[0176] The difference coefficient G of the characteristic parameters A G E , G K Normalization is performed so that the sum of the difference coefficients of the feature parameters equals 1. The expression is as follows:

[0177]

[0178] In the formula, w A w is the weighting factor for the echo peak value. E The weighting coefficients are the root mean square values ​​of the echo. w is the weighting coefficient for the average value of the spectrum. K This is the weighting coefficient for spectral kurtosis.

[0179] Figure 4 The technical solution presented offers at least the following benefits: It extracts feature parameters from the time-domain signal, analyzes the patch from a time-domain perspective to preliminarily determine its quality, converts the time-domain signal to a frequency-domain signal, extracts feature parameters again, and fuses the feature parameters extracted from the time-domain and frequency-domain analyses to construct a patch quality evaluation model. This model quantitatively analyzes the patch quality and outputs a specific patch quality score. Combining time-domain and frequency-domain analysis captures richer and more comprehensive information, thereby improving detection accuracy and comprehensiveness. By outputting a patch quality score, the actual quality status of the pipeline patch can be reflected more intuitively in numerical form, quantifying the patch quality and supporting accurate patch quality assessment. It also provides users with intuitive and accurate patch quality evaluation results.

[0180] The foregoing primarily describes the solutions provided by the embodiments of this application from a methodological perspective. To achieve the aforementioned functions, it includes corresponding hardware structures and / or software modules for executing each function. Those skilled in the art should readily recognize that, in conjunction with the units and algorithm steps of the various examples described in the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art may use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0181] like Figure 9As shown in the figure, this application embodiment also provides a joint quality evaluation device for executing the joint quality evaluation scheme shown in the above method embodiment. The joint quality evaluation device 300 includes: an analysis module 301.

[0182] The analysis module 301 is used to: acquire the time-domain echo signal in the area to be tested after the ultrasonic pulse echo method is used to test the area to be tested, and extract a first feature parameter from the time-domain echo signal, which is used to characterize the quality of the pipe patch; identify abnormal data in the time-domain echo signal and preliminarily determine whether the quality of the pipe patch is qualified; convert the time-domain echo signal into a frequency-domain echo signal and extract a second feature parameter from the frequency-domain echo signal, which is used to characterize the quality of the pipe patch; fuse the first feature parameter and the second feature parameter to construct a patch quality evaluation model, and output a patch quality score through the patch quality evaluation model.

[0183] Specifically, the analysis module 301 includes a time-domain analysis unit 3011, a frequency-domain analysis unit 3012, and a joint analysis unit 3013. The time-domain analysis unit 3011 acquires the time-domain echo signal in the area to be tested after ultrasonic pulse echo testing, extracts a first feature parameter from the time-domain echo signal, and identifies abnormal data in the time-domain echo signal to preliminarily determine whether the quality of the pipe joint is qualified. The frequency-domain analysis unit 3012 converts the time-domain echo signal into a frequency-domain echo signal and extracts a second feature parameter from the frequency-domain echo signal. The joint analysis unit 3013 fuses the first and second feature parameters to construct a joint quality evaluation model, and outputs a joint quality score through the joint quality evaluation model.

[0184] In some embodiments, the analysis module 301 is specifically used to: analyze the time-domain echo signal in the area to be detected using a patching judgment strategy, determine whether a patch exists in the area to be detected, and extract the pipe patch echo signal from the time-domain echo signal; analyze the pipe patch echo signal using a time-domain analysis strategy, identify abnormal data in the pipe patch echo signal, and preliminarily determine whether the quality of the pipe patch is qualified.

[0185] In some embodiments, the analysis module 301 is specifically used to: acquire the time-domain echo signal of the area to be detected and preprocess the time-domain echo signal; set the echo threshold of the time-domain echo signal, define a baseline, and mark the baseline in the time-domain echo signal; if there is no amplitude exceeding the baseline in the time-domain echo signal, determine that there is no patch in the area to be detected; if there is an amplitude exceeding the baseline in the time-domain echo signal, determine that there is a patch in the area to be detected, and extract the first patch echo signal and the second patch echo signal of the pipe patch from the time-domain echo signal, wherein the first patch echo signal is the echo signal passing through the outer bonding surface of the pipe patch, and the second patch echo signal is the echo signal passing through the inner bonding surface of the pipe patch.

[0186] In some embodiments, the analysis module 301 is specifically used to: record the first amplitude value that first exceeds the baseline in the time-domain echo signal and the corresponding first time point; obtain the first time window width corresponding to the first time point, and extract the first patch echo signal from the time-domain echo signal with the first time point as the starting point and the sum of the first time point and the first time window width as the ending point; remove the first patch echo signal from the time-domain echo signal; if there is no amplitude exceeding the baseline in the time-domain echo signal after removing the first patch echo signal, determine that the second patch echo signal has not been identified, and determine that the quality of the pipe patch is unqualified; if there is an amplitude exceeding the baseline in the time-domain echo signal after removing the first patch echo signal, record the second amplitude value that first exceeds the baseline in the time-domain echo signal and the corresponding second time point; obtain the second time window width corresponding to the second time point, and extract the second patch echo signal from the time-domain echo signal with the second time point as the starting point and the sum of the second time point and the second time window width as the ending point.

[0187] In some embodiments, the analysis module 301 is specifically used to: extract the first echo peak value in the first patch echo signal and the second echo peak value in the second patch echo signal; determine the echo peak value difference based on the first echo peak value and the second echo peak value; if the echo peak value difference is less than or equal to the peak value difference threshold, determine that the quality of the pipe patch is qualified; if the echo peak value difference is greater than the peak value difference threshold, determine that the quality of the pipe patch is unqualified.

[0188] In some embodiments, the analysis module 301 is specifically used to: convert the time-domain echo signal into a frequency-domain echo signal using a feature extraction strategy, and extract a second feature parameter from the frequency-domain echo signal; the analysis module 301 is specifically used to: convert the first padded echo signal into a first padded frequency-domain signal using Fourier transform, and convert the second padded echo signal into a second padded frequency-domain signal; read the first angular frequency and the first frequency window width in the first padded frequency-domain signal, and the second angular frequency and the second frequency window width in the second padded frequency-domain signal; calculate the first padded frequency-domain signal... The first spectral average value and the second spectral average value of the second-supplemented frequency domain signal are calculated. Based on the first angular frequency, the first frequency window width, and the first spectral average value of the first-supplemented frequency domain signal, the ratio of the fourth-order central moment to the square of the second-order central moment of the first-supplemented frequency domain signal is calculated to obtain the first spectral kurtosis of the first-supplemented frequency domain signal. Based on the second angular frequency, the second frequency window width, and the second spectral average value of the second-supplemented frequency domain signal, the ratio of the fourth-order central moment to the square of the second-order central moment of the second-supplemented frequency domain signal is calculated to obtain the second spectral kurtosis of the second-supplemented frequency domain signal.

[0189] In some embodiments, the analysis module 301 is further configured to: construct a first feature parameter matrix of a first time-domain echo signal, the first feature parameter matrix consisting of a first padded echo signal, a first echo peak value, a first echo root mean square, a first spectral average value, and a first spectral kurtosis; construct a second feature parameter matrix of a second time-domain echo signal, the second feature parameter matrix consisting of a second padded echo signal, a second echo peak value, a second echo root mean square, a second spectral average value, and a second spectral kurtosis; determine the maximum value of the echo peak value, the maximum value of the echo root mean square, the optimal value of the spectral average value, and the optimal value of the spectral kurtosis; and determine the lower limit threshold of the spectral average value and the spectral average value. The upper limit threshold and allowable range of the spectral average value are determined, as well as the lower limit threshold, upper limit threshold and allowable range of the spectral kurtosis. Based on the maximum value of the echo peak value, the maximum value of the echo root mean square value, the optimal value of the spectral average value, the optimal value of the spectral kurtosis, the lower limit threshold of the spectral average value, the upper limit threshold of the spectral average value, the allowable range of the spectral average value, the lower limit threshold of the spectral kurtosis, the upper limit threshold of the spectral kurtosis and the allowable range of the spectral kurtosis, the quality scores of the outer bonding surface and the inner bonding surface of the pipe joint are calculated. A joint inspection file containing the quality scores of the outer bonding surface and the inner bonding surface of the pipe joint is generated and output.

[0190] Specifically, the joint analysis unit 3013 is configured with an analysis strategy for constructing a joint quality evaluation model and performing quantitative analysis on the joint quality. The specific content of the analysis strategy is as described above.

[0191] In some embodiments, the analysis module 301 is further configured to: collect a dataset containing echo peak value, spectral average value, echo root mean square (RMS), and spectral kurtosis to construct a first feature parameter set; standardize the value of each feature parameter in the first feature parameter set to obtain a second feature parameter set; divide the value of each feature parameter in the second feature parameter set into a preset number of equally wide intervals; count the number of samples in each interval and calculate the probability of the feature parameter value in each interval; calculate the difference coefficients of echo peak value, echo root mean square (RMS), spectral average value, and spectral kurtosis respectively; and normalize the difference coefficients of echo peak value, echo root mean square (RMS), spectral average value, and spectral kurtosis respectively to obtain the weighting coefficients of echo peak value, echo root mean square (RMS), spectral average value, and spectral kurtosis.

[0192] In some embodiments, the analysis module 301 further includes a user interface unit 3014. The user interface unit 3014 is used to provide an interactive page, which displays the detection results of the pipe patch to the user. The interactive page includes operation buttons and menu options to receive user input operations on the interactive page.

[0193] It should be noted that, Figure 9 The module division shown is illustrative and represents only one logical functional division; in actual implementation, other division methods are possible. For example, two or more functions can be integrated into one module. The integrated module described above can be implemented in hardware or as a software functional module.

[0194] Another embodiment of this application also provides an electronic device, including: one or more processors; one or more memories; wherein the one or more memories are used to store computer program code, the computer program code including computer instructions, and when the one or more processors execute the computer instructions, the electronic device performs any of the patching quality evaluation methods provided in the first aspect above.

[0195] Another embodiment of this application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed on a computer, cause the computer to perform any of the patching quality evaluation methods provided in the first aspect above.

[0196] Another embodiment of this application also provides a computer program product, which includes computer instructions that, when executed on an electronic device, cause the electronic device to perform any of the patch quality evaluation methods provided in the first aspect above.

[0197] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for evaluating the quality of patching joints, characterized in that, include: After the area to be tested is detected using the ultrasonic pulse echo method, the time-domain echo signal in the area to be tested is obtained, and a first feature parameter is extracted from the time-domain echo signal. The first feature parameter is used to characterize the quality of the pipe joint. Identify abnormal data in the time-domain echo signal to preliminarily determine whether the quality of the pipe patch is up to standard. The time-domain echo signal is converted into a frequency-domain echo signal, and a second feature parameter is extracted from the frequency-domain echo signal. The second feature parameter is used to characterize the quality of the pipe patch. By integrating the first feature parameter and the second feature parameter, a patching quality evaluation model is constructed, and a patching quality score is output through the patching quality evaluation model.

2. The method according to claim 1, characterized in that, The step of identifying abnormal data in the time-domain echo signal and making a preliminary judgment on whether the quality of the pipe patch is up to standard includes: The pipeline patching detection strategy is used to analyze the time-domain echo signal in the detection area to determine whether there is a patch in the detection area, and to extract the pipeline patch echo signal from the time-domain echo signal. The pipeline patch echo signal is analyzed using a time-domain analysis strategy to identify abnormal data and preliminarily determine whether the quality of the pipeline patch is up to standard.

3. The method according to claim 2, characterized in that, The method of analyzing the time-domain echo signal in the detection area using the patching detection strategy to determine whether a patch exists in the detection area, and extracting the pipe patch echo signal from the time-domain echo signal, includes: Acquire the time-domain echo signal of the region to be detected, and preprocess the time-domain echo signal; Set the echo threshold of the time-domain echo signal, define a baseline, and mark the baseline in the time-domain echo signal; If the time-domain echo signal does not contain an amplitude exceeding the baseline, it is determined that there is no patching within the detection area. If the amplitude of the time-domain echo signal exceeds the baseline, it is determined that there is a patch in the area to be detected, and the first patch echo signal and the second patch echo signal of the pipe patch are extracted from the time-domain echo signal. The first patch echo signal is the echo signal passing through the outer bonding surface of the pipe patch, and the second patch echo signal is the echo signal passing through the inner bonding surface of the pipe patch.

4. The method according to claim 3, characterized in that, Extracting the first and second patch echo signals of the pipeline patch from the time-domain echo signal includes: Record the first amplitude value and the corresponding first time point in the time-domain echo signal that first exceeds the baseline. Obtain the width of the first time window corresponding to the first time point, and extract the first supplementary echo signal from the time domain echo signal with the first time point as the starting point and the sum of the first time point and the first time window width as the ending point. Remove the first supplementary echo signal from the time-domain echo signal; If the time-domain echo signal after removing the first patch echo signal does not contain an amplitude exceeding the baseline, it is determined that the second patch echo signal has not been identified, and the quality of the pipe patch is determined to be unqualified. If the time-domain echo signal after removing the first supplementary echo signal contains an amplitude exceeding the baseline, record the second amplitude that first exceeds the baseline in the time-domain echo signal and the corresponding second time point; Obtain the width of the second time window corresponding to the second time point, and extract the second supplementary echo signal from the time domain echo signal with the second time point as the starting point and the sum of the second time point and the second time window width as the ending point.

5. The method according to claim 4, characterized in that, The step of analyzing the pipeline patch echo signal using a time-domain analysis strategy to identify abnormal data in the pipeline patch echo signal and to preliminarily determine whether the quality of the pipeline patch is up to standard includes: Extract the first echo peak value from the first patch echo signal and the second echo peak value from the second patch echo signal; The echo peak difference is determined based on the first echo peak value and the second echo peak value; If the echo peak difference is less than or equal to the peak difference threshold, the quality of the pipe patch is determined to be qualified; If the echo peak difference is greater than the peak difference threshold, the quality of the pipe patch is determined to be unqualified.

6. The method according to claim 3, characterized in that, The step of converting the time-domain echo signal into a frequency-domain echo signal and extracting the second feature parameter from the frequency-domain echo signal includes: The time-domain echo signal is converted into a frequency-domain echo signal using a feature extraction strategy, and a second feature parameter is extracted from the frequency-domain echo signal. The step of converting the time-domain echo signal into a frequency-domain echo signal using a feature extraction strategy, and extracting a second feature parameter from the frequency-domain echo signal, includes: The first patch echo signal is converted into a first patch frequency domain signal using Fourier transform, and the second patch echo signal is converted into a second patch frequency domain signal. Read the first angular frequency and the first frequency window width in the first supplementary frequency domain signal, and the second angular frequency and the second frequency window width in the second supplementary frequency domain signal; Calculate the first spectral average value of the first compensated frequency domain signal and the second spectral average value of the second compensated frequency domain signal; Based on the first angular frequency, the first frequency window width, and the first spectral average value of the first supplementary frequency domain signal, the ratio of the fourth central moment to the square of the second central moment of the first supplementary frequency domain signal is calculated to obtain the first spectral kurtosis of the first supplementary frequency domain signal. Based on the second angular frequency, second frequency window width, and second spectral average value of the second supplementary frequency domain signal, the ratio of the fourth central moment to the square of the second central moment of the second supplementary frequency domain signal is calculated to obtain the second spectral kurtosis of the second supplementary frequency domain signal.

7. The method according to claim 6, characterized in that, The method further includes: Construct a first feature parameter matrix of the first time-domain echo signal. The first feature parameter matrix is ​​composed of the first port echo signal, the first echo peak value, the first echo root mean square, the first spectral average value, and the first spectral kurtosis. Construct a second characteristic parameter matrix of the second time-domain echo signal. The second characteristic parameter matrix consists of the second supplementary echo signal, the second echo peak value, the second echo root mean square, the second spectral average value, and the second spectral kurtosis. Determine the maximum value of echo peak value, the maximum value of echo root mean square value, the optimal value of spectral average value and the optimal value of spectral kurtosis; determine the lower threshold, the upper threshold and the allowable range of spectral average value; and determine the lower threshold, the upper threshold and the allowable range of spectral kurtosis. Based on the maximum value of the echo peak, the maximum value of the echo root mean square, the optimal value of the spectral average, the optimal value of the spectral kurtosis, the lower threshold of the spectral average, the upper threshold of the spectral average, the allowable range of the spectral average, the lower threshold of the spectral kurtosis, the upper threshold of the spectral kurtosis, and the allowable range of the spectral kurtosis, calculate the quality score of the outer bonding surface and the quality score of the inner bonding surface of the pipe joint. Generate and output a joint inspection file containing the quality scores of the outer bonding surface and the inner bonding surface of the pipe joint.

8. The method according to claim 7, characterized in that, The method further includes: Collect a dataset containing echo peak value, spectral average value, echo root mean square and spectral kurtosis, and construct the first feature parameter set; The values ​​of each feature parameter in the first feature parameter set are standardized to obtain the second feature parameter set. The value of each feature parameter in the second feature parameter set is divided into a preset number of equally wide intervals; Count the number of samples in each interval and calculate the probability of the feature parameter value in each interval; Calculate the difference coefficients for echo peak value, echo root mean square, spectral mean, and spectral kurtosis, respectively. The difference coefficients of echo peak value, echo root mean square, spectral mean, and spectral kurtosis are normalized to obtain the weighting coefficients of echo peak value, echo root mean square, spectral mean, and spectral kurtosis.

9. A joint quality evaluation device, characterized in that, Includes an analysis module, which is used for: After the area to be tested is detected using the ultrasonic pulse echo method, the time-domain echo signal in the area to be tested is obtained, and a first feature parameter is extracted from the time-domain echo signal. The first feature parameter is used to characterize the quality of the pipe joint. Identify abnormal data in the time-domain echo signal to preliminarily determine whether the quality of the pipe patch is up to standard. The time-domain echo signal is converted into a frequency-domain echo signal, and a second feature parameter is extracted from the frequency-domain echo signal. The second feature parameter is used to characterize the quality of the pipe patch. By integrating the first feature parameter and the second feature parameter, a patching quality evaluation model is constructed, and a patching quality score is output through the patching quality evaluation model.

10. An electronic device, characterized in that, include: One or more processors; one or more memories; wherein the one or more memories are used to store computer program code, the computer program code including computer instructions, and when the one or more processors execute the computer instructions, the electronic device performs the method of any one of claims 1-8.

Images