A defect type identification method, device, equipment and product suitable for small-caliber branch pipe fillet weld

Abstract

This application discloses a method, apparatus, equipment, and product for defect type identification of fillet welds in small-diameter branch pipes, relating to the field of ultrasonic nondestructive testing technology. The method includes: establishing a three-dimensional structural simulation model of the fillet weld in a small-diameter branch pipe using CIVA software; processing standard test blocks for different types of defects; conducting numerical simulation and phased array detection experiments to obtain echo signals and typical response characteristics for different defect types, establishing a defect standard response feature library; detecting and extracting features from the small-diameter branch pipe fillet weld to be identified to obtain detection signal features; comparing the detection signal features with each typical response feature in the defect standard response feature library; obtaining the defect type identification result based on the comparison result; and analyzing and verifying the defect type identification result using quantitative defect parameters and weld manufacturing process characteristics. This application can solve the problems of low identification accuracy, weak anti-interference ability, and high dependence on personnel experience in existing technologies.

Description

Technical Field

[0001] This application relates to the field of ultrasonic nondestructive testing technology, and in particular to a method, apparatus, equipment and product for identifying defect types in small-diameter branch pipe fillet welds. Background Technology

[0002] Small-diameter branch pipe fillet welds (DN20-DN50) are widely used in critical equipment such as pressure vessels and industrial pipelines, and their welding quality directly determines the operational safety of the equipment. These welds have a unique structure, exhibiting a complex pipe-seat corner joint shape. The weld size continuously varies around the branch pipe, resulting in significant fluctuations in internal structural signals. Furthermore, they exhibit a variety of common defect types (porosity, strip defects, lack of fusion, incomplete penetration, cracks, etc.), with irregular defect morphology and distribution, posing a significant challenge to accurate defect identification.

[0003] Existing phased array ultrasonic testing technology for small-diameter branch pipe fillet weld inspection mainly focuses on beam coverage and defect localization, lacking a specific defect identification scheme tailored to the structural characteristics of this type of weld. Firstly, it fails to fully utilize simulation technology to predict defect response characteristics, relying on the experience of inspectors to judge waveforms, easily confusing defect signals with structural interference signals. Secondly, insufficient research on the differences in echo characteristics of different types and locations of defects makes it impossible to establish a unified identification standard, resulting in low accuracy in defect identification. Thirdly, there is a lack of methods for identifying low-amplitude diffraction signals such as sidewall incomplete fusion and upper-end cracks, easily leading to missed or incorrect identifications. Therefore, there is an urgent need for a simulation-supported, feature-clear, accurate, and efficient defect type identification method for small-diameter branch pipe fillet welds to address the problems of low identification accuracy, weak anti-interference ability, and high dependence on personnel experience in existing technologies. Summary of the Invention

[0004] The purpose of this application is to provide a method, device, equipment and product for identifying defect types in small-diameter branch pipe fillet welds, which can solve the problems of low identification accuracy, weak anti-interference ability and high dependence on personnel experience in the prior art.

[0005] To achieve the above objectives, this application provides the following solution: Firstly, this application provides a defect type identification method applicable to fillet welds of small-diameter branch pipes, including: A three-dimensional structural simulation model of the fillet weld of a small-diameter branch pipe was established using CIVA software, and standard test blocks with different types of defects were fabricated based on the three-dimensional structural simulation model. Based on the aforementioned three-dimensional structural simulation model, numerical simulation and phased array detection experiments were conducted to obtain echo signals from standard test blocks with different types of defects at different locations. Feature extraction is performed on the echo signal to obtain typical response features of different defect types, and a standard defect response feature library is established. The small-diameter branch pipe fillet weld to be identified was inspected according to the phased array ultrasonic testing standard to obtain the detection signal; Feature extraction is performed on the detection signal to obtain the detection signal features; The detection signal features are compared with each typical response feature in the defect standard response feature library to obtain the comparison result; Based on the comparison results, the defect type identification result is obtained; The defect type identification results are analyzed and verified using quantitative defect parameters and weld manufacturing process characteristics to obtain defect type and size information.

[0006] Secondly, this application provides a defect type identification device suitable for fillet welds of small-diameter branch pipes, comprising: The CIVA simulation platform is used to establish a three-dimensional structural simulation model of the fillet weld of a small-diameter branch pipe using CIVA software. Based on the three-dimensional structural simulation model, it is used to perform numerical simulation and phased array detection experiments to obtain echo signals of standard test blocks with different types of defects at different locations. The three-dimensional structural simulation model includes standard test blocks with different types of defects. The phased array ultrasonic testing instrument is used to acquire A / S / B / C / D type scanning images and raw echo signals of the detection area of ​​small-diameter branch pipe fillet welds by mechanical scanning with position sensors according to the set scanning step value and angle step value, so as to obtain the detection signal; The feature recognition and analysis processor is connected to the CIVA simulation platform and the phased array ultrasonic testing instrument, respectively. It is used to extract features from the echo signal to obtain typical response features of different defect types and establish a defect standard response feature library; to extract features from the detection signal to obtain detection signal features; to compare the detection signal features with each typical response feature in the defect standard response feature library to obtain comparison results; to obtain defect type identification results based on the comparison results; and to analyze and verify the defect type identification results using defect quantitative parameters and weld manufacturing process characteristics to obtain defect type and size information.

[0007] Thirdly, this application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described method for identifying defect types of fillet welds in small-diameter branch pipes.

[0008] Fourthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the above-described defect type identification method for small-diameter branch pipe fillet welds.

[0009] According to the specific embodiments provided in this application, this application has the following technical effects: This application provides a method, device, equipment, and product for defect type identification of fillet welds in small-diameter branch pipes. By leveraging CIVA simulation to establish a precise defect standard response feature library, and through feature comparison, quantitative determination of defect types is achieved, eliminating reliance on the experience of inspection personnel and effectively avoiding missed or false identifications, thereby improving identification accuracy. Simulation experiments clearly demonstrate the amplitude and morphological differences between defect signals and structural interference signals such as corner echoes. Interference signals can be accurately eliminated during signal preprocessing and feature comparison stages, improving anti-interference capabilities. By establishing a standardized "simulation modeling - feature library construction - signal acquisition - comparison and judgment" process, the parameter standards and operational requirements of each step are clearly defined, lowering the technical threshold and facilitating widespread application within the industry, thus solving the problem of high reliance on personnel experience. Attached Figure Description

[0010] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in 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.

[0011] Figure 1 A flowchart illustrating a defect type identification method for small-diameter branch pipe fillet welds provided in an embodiment of this application; Figure 2 This is a CIVA simulation modeling diagram of a small-diameter branch pipe corner joint provided in an embodiment of this application; Figure 3 A simulation diagram of the acoustic rays of a ball hole at different positions in the weld, provided in an embodiment of this application; Figure 4 A sector scan of a ball hole at different locations in the weld, provided as an embodiment of this application; Figure 5 A-scan images of a ball hole at different locations in the weld, provided in an embodiment of this application; Figure 6 A simulation diagram of the acoustic signature of a transverse through-hole at different locations in the weld, provided in an embodiment of this application; Figure 7 A sector scan of a transverse through-hole at different locations on a weld seam, provided in an embodiment of this application; Figure 8 A-scan images of a transverse through-hole at different locations on a weld, provided in an embodiment of this application; Figure 9 A simulated acoustic image of non-fusion at different locations in the weld, provided as an embodiment of this application; Figure 10A sector scan of the weld seam at different locations where fusion has not occurred, as provided in an embodiment of this application; Figure 11 A-scan images of non-fusion at different locations in the weld, provided in an embodiment of this application; Figure 12 A simulated acoustic image of incomplete penetration at different locations in the weld, provided as an embodiment of this application; Figure 13 Fan scan images of incomplete penetration at different locations of the weld provided in an embodiment of this application; Figure 14 A-scan images of incomplete penetration at different locations in the weld, provided in an embodiment of this application; Figure 15 A simulated acoustic image of a crack at different locations in a weld, provided as an embodiment of this application; Figure 16 A sector scan of a crack at different locations in a weld, provided as an embodiment of this application; Figure 17 A-scan images of cracks at different locations in the weld provided in an embodiment of this application; Figure 18 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0012] 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.

[0013] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0014] In one exemplary embodiment, this application provides a defect type identification method applicable to fillet welds of small-diameter branch pipes. This method is executed by a computer device, specifically a terminal or server, or both. In this embodiment, the method is described using a server as an example. Figure 1 As shown, the method includes: Step 100: Use CIVA software to establish a three-dimensional structural simulation model of the fillet weld of the small-diameter branch pipe, and process standard test blocks with different types of defects on the three-dimensional structural simulation model.

[0015] Step 101: Based on the three-dimensional structural simulation model, numerical simulation and phased array detection experiments are conducted to obtain echo signals of standard test blocks with different types of defects at different locations; Step 102: Extract features from the echo signal to obtain typical response features of different defect types, and establish a standard defect response feature library; Step 103: Perform real-time detection of the fillet weld of the small-diameter branch pipe to be identified according to the phased array ultrasonic testing specification to obtain the detection signal; Step 104: Extract features from the detection signal to obtain the detection signal features; Step 105: Compare the detection signal features with each typical response feature in the defect standard response feature library to obtain the comparison results; Step 106: Obtain the defect type identification result based on the comparison results; Step 107: Cross-validate the defect type identification results using defect quantitative parameters and weld manufacturing process characteristics to obtain defect type and size information.

[0016] By implementing steps 100-107 above, this application can overcome the shortcomings of existing phased array ultrasonic testing of small-diameter branch pipe fillet welds, such as low accuracy of defect type identification, weak anti-interference ability, and reliance on personnel experience. It can achieve efficient and accurate identification of common defects such as porosity, strip defects, lack of fusion, incomplete penetration, and cracks, thereby improving the reliability of testing.

[0017] In one exemplary embodiment of this application, in order to further improve the recognition accuracy, the implementation process of step 100 described above can be described as follows: Step 100-1: Using the pipe seat fillet weld simulation module in CIVA software, follow the set modeling parameters (e.g., material selected is carbon steel, density 7.8 g / cm³). 3 The longitudinal wave velocity is 5900 m / s, and the transverse wave velocity is 3230 m / s. (For inserted branch pipes, the detection surface is set to the container side.) A three-dimensional structural simulation model of the small-diameter branch pipe fillet weld is constructed. Among them, the pipe seat fillet weld simulation module is a functional module specifically designed for pipe seat fillet weld structures in the existing technology. It can accurately simulate various types of pipe seat fillet welds, such as placement and insertion types, greatly simplifying CAD modeling work. The CIVA simulation modeling results are as follows: Figure 2 As shown. Figure 2 Part (a) is a model of the fillet weld of the branch pipe with a main pipe size of 114×6mm and a branch pipe size of 25×4mm (i.e., the CIVA simulation modeling result). Figure 2 Part (b) is a model diagram of the fillet weld of the main pipe (219×8mm) and the branch pipe (48×5mm). Figure 2 Part (c) is a model diagram of the fillet weld of the main pipe (323.9×12.5mm) and the branch pipe (76×5mm). Figure 2 Part (d) is a model diagram of the fillet weld of the main pipe (559×20mm) and the branch pipe (114×6mm). Figure 2 Part (e) is a model diagram of the fillet weld of the main pipe (1016×26.2mm) and the branch pipe (114×6mm).

[0018] Step 100-2: In the 3D structural simulation model, set up standard test blocks corresponding to different defect types of small-diameter branch pipe fillet welds to cover the defect types of small-diameter branch pipe fillet welds. The standard test blocks include incomplete fusion standard reflectors, incomplete penetration standard reflectors, spherical hole standard reflectors, transverse through-hole standard reflectors, and crack standard reflectors. The arrangement scheme can be as follows: incomplete fusion standard reflectors are arranged on both sides of the weld bevel fusion line; incomplete penetration standard reflectors are arranged in the middle of the root; spherical hole standard reflectors (simulating porosity), transverse through-hole standard reflectors (simulating strip defects), and crack standard reflectors are arranged in the middle of the weld.

[0019] Furthermore, the three-dimensional structural simulation model constructed in this application is a 1:1 scale model of the fillet weld of a small-diameter branch pipe.

[0020] In an exemplary embodiment of this application, in order to construct a more accurate defect standard response feature library, the implementation process of step 102 above can be described as follows: Step 102-1: Set simulation parameters that match the actual detection (e.g., transverse wave oblique beam fan scanning angle 35°~75°), and perform simulation based on the simulation parameters to obtain the echo signals of standard test blocks with different types of defects at different positions. The transverse wave oblique beam fan scanning angle is set to be larger than the conventional angle, which can better cover the fillet weld range.

[0021] Step 102-2: Set matching detection parameters for the standard test block, conduct phased array detection experiments, and obtain echo signals of standard test blocks with different types of defects in the actual test block; based on the echo signals, obtain typical response characteristics of different defect types; typical response characteristics include core characteristic parameters such as echo amplitude, signal shape, and corner echo signals of standard test blocks with different types of defects at different positions.

[0022] Step 102-3: Establish a defect standard response feature library based on typical response characteristics.

[0023] In practical applications, the defect standard response feature library is established as follows: based on simulation results (i.e., echo signals), typical response features of various defects are extracted and organized to establish the defect standard response feature library, as detailed below: (1) Pores (corresponding to simulated spherical holes): The defect echo energy is lower than the end-corner echo signal; the echo amplitude of the lower spherical hole (first wave detection) is lower than that of the upper spherical hole (second wave detection); the echo signal is singular, without complex diffraction peaks. For example, such as Figures 3-5 As shown, the defect echo energy of the spherical hole is lower than that of the end corner echo signal. This is mainly because the edge of the circular hole cannot effectively reflect ultrasonic waves. The echo amplitude of the lower spherical hole is lower than that of the upper spherical hole. Although the lower spherical hole is detected by primary wave and the upper spherical hole by secondary wave, the actual aperture becomes smaller due to the large excitation angle, and the energy also decreases accordingly. Ultimately, this results in the upper spherical hole echo being higher than that of the lower spherical hole.

[0024] (2) Strip-shaped defects (corresponding to simulated transverse through-holes): The defect echo energy is higher than the end corner echo signal; the echo amplitude of the lower transverse through-hole is lower than that of the upper transverse through-hole; the echo signal intensity is higher than that of pores, and the signal peak is clear. For example, Figures 6-8 As shown, the defect echo energy of the transverse through-hole is higher than that of the end-corner echo signal. This is mainly because the reflecting surface of the transverse through-hole is larger than that of the spherical hole, reflecting sufficient ultrasonic waves. Similar to the spherical hole, the echo amplitude of the lower transverse through-hole is lower than that of the upper one, which is also due to the excessively large excitation angle of the lower transverse through-hole. (3) Lack of fusion: This is an area-type defect, and the reflected wave amplitude is strongly correlated with the perpendicularity of the sound beam. At the branch pipe, the lack of fusion on the reflecting surface is close to 90° to the sound beam, resulting in an echo amplitude higher than the end-corner echo signal, making it easily identifiable. At the container, the lack of fusion on the reflecting surface is approximately 60° to the sound beam, so only diffraction signals can be received, with amplitudes lower than the reflected signals, resulting in weak signal amplitudes. For example, as... Figures 9-11 As shown, compared to the echo signal at the end corner, the echo amplitude of the non-fused defect at the branch pipe is higher, but the echo amplitude of the non-fused defect at the main pipe is lower. Since non-fusion is an area-type defect, its reflected wave amplitude is mainly related to whether the sound beam is perpendicular. When detecting non-fusion on the branch pipe side, the reflected surface is close to 90° with the sound beam, resulting in a higher reflected wave amplitude. However, for non-fusion defects on the container side, the angle between the reflected surface and the sound beam is approximately 60°, resulting in lower reflected echo energy, so only diffraction signals can be received. The amplitude of the diffraction signal is lower than that of the reflected signal.

[0025] (4) Incomplete penetration: The echo amplitude is lower than the corner echo signal but higher than the transverse through hole; incomplete penetration at the root easily forms corner reflections with a larger amplitude; the signal location is concentrated in the root area of ​​the weld. For example, Figures 12-14 As shown, the echo amplitude of incomplete penetration is lower than that of the corner echo signal, but higher than that of a through-hole. Incomplete penetration defects at the root are more likely to cause corner reflections in phased array detection, and their amplitude is larger. They can be easily distinguished and identified based on their location.

[0026] (5) Cracks: The echo amplitude varies significantly with position; cracks at the lower end of the weld resemble incomplete penetration, exhibiting corner reflection with higher amplitude; cracks at the upper end can only be detected by diffraction signals, and because the crack has multiple sharp corners, the signal contains multiple diffraction peaks, which can be distinguished from the single diffraction signal of incomplete fusion. For example, as Figures 15-17 As shown, the echo amplitude of the upper crack is lower than that of the lower crack compared to the corner echo signal. This difference in amplitude is due to the different beam angles at which the cracks are detected. The crack at the lower end of the weld resembles an incomplete penetration defect, exhibiting corner reflection with a higher amplitude. The crack at the upper end of the weld, however, only its diffraction signal can be detected. Unlike the incomplete fusion signal, the crack has multiple sharp corners, resulting in multiple diffraction signals in the crack's display signal. Figure 5 , Figure 8 , Figure 11 , Figure 14 and Figure 17 The waveforms in the examples are all measured on a uniform scale and are used only as examples. The specific choice of scale is not limited.

[0027] In an exemplary embodiment of this application, the implementation process of step 103 described above can be described as follows: The fillet weld of a small-diameter branch pipe is inspected according to the phased array ultrasonic testing standard. A / S / B / C / D type scanning images and original echo signals of the fillet weld inspection area of ​​the small-diameter branch pipe are acquired using a mechanical scanning method with a position sensor, according to a set scanning step value (e.g., no greater than 1 mm) and an angle step value (e.g., a maximum of 1°), to obtain the detection signal. During the scanning process, the signal covers the entire weld circumference, and the continuous loss length of the A-scan signal does not exceed 2 mm. The setting of the scanning step value is to make the scanning frequency more dense than usual, thereby improving the image resolution.

[0028] In an exemplary embodiment of this application, to avoid the influence of noise, after the small-diameter branch pipe fillet weld is detected in real time according to the phased array ultrasonic testing specification in step 103, the detected signal needs to be preprocessed, such as: noise reduction processing of the detected signal, elimination of invalid signals such as environmental interference and poor coupling, and extraction of effective defect candidate signals (i.e., detection signals). Based on this, the implementation process of step 105 mainly involves: comparing the amplitude characteristics, morphological characteristics, and positional characteristics of the effective defect candidate signals with various defect characteristics (i.e., typical response characteristics) in the defect standard response feature library one by one.

[0029] In an exemplary embodiment of this application, in order to further improve the accuracy of defect type identification, the implementation process of step 106 provided above in this application can be described as follows: ① If the signal echo energy in the detection signal characteristics is low, has a single peak, is located inside the weld, and has a similar length and width, then the defect type identification result is porosity.

[0030] ②If the signal echo energy in the detection signal characteristics is high, the peak value is clear, it is located inside the weld, and the length is significantly greater than the width, then the defect type identification result is determined to be a strip-shaped defect.

[0031] ③ If the signal amplitude in the detection signal characteristics is high and concentrated on the branch pipe side, the defect type and size information is determined to be non-fusion at the branch pipe; if the signal amplitude is high and concentrated on the container / main pipe side, the defect type identification result is determined to be non-fusion at the container / main pipe.

[0032] ④ If the signal in the detection signal characteristics is located at the root and has a high amplitude, then the defect type and size information are determined to be incomplete penetration.

[0033] ⑤ If the signal in the detection signal features contains multiple diffraction peaks, or the lower end is a high-amplitude end-angle reflection signal and the upper end is a weak diffraction signal, then the defect type identification result is determined to be a crack.

[0034] In one exemplary embodiment of this application, in order to ensure the accuracy of the identification results, the implementation process of step 107 provided above in this application can be described as follows: Step 107-1: Use the defect quantitative parameters (depth, indication length, height) and the characteristics of the weld manufacturing process to determine whether there are defects with ambiguous features in the defect type identification results.

[0035] Step 107-2: When there are defects with ambiguous features in the defect type identification results, increase the scanning position and adjust the sensitivity parameters, then re-perform real-time detection of the small diameter branch pipe fillet weld according to the phased array ultrasonic testing specification, and return to step 104 (i.e., re-acquire the signal and make a judgment again).

[0036] Step 107-3: When there are no defects with ambiguous features in the defect type identification results, obtain the defect type and size information.

[0037] In an exemplary embodiment of this application, the implementation process and effects of the above-mentioned method provided in this application are described using the defect identification of fillet welds in an insert-type carbon steel small-diameter branch pipe with a pipe thickness of 20mm and a pipe diameter of DN100 as an example.

[0038] 1. Preliminary Preparations: The inspection target is clearly defined as the fillet weld of an insert-type small-diameter carbon steel branch pipe, made of carbon steel (density 7.8 g / cm³). 3The longitudinal wave velocity is 5900 m / s, and the transverse wave velocity is 3230 m / s. The pipe thickness is 20 mm, and the pipe diameter is DN100. A phased array ultrasonic detector, a 7.5 MHz conventional linear array probe (32 crystals, 19.2 mm excitation aperture) and a matching wedge (42 mm length, 15.6 mm leading edge, 55° angle, and 27.5 mm height) are used for identification.

[0039] 2. Simulation Modeling: Using the fillet weld simulation module of the pipe seat in CIVA software, a 1:1 three-dimensional structural simulation model of the fillet weld of the insert-type carbon steel small-diameter branch pipe was established, with the inspection surface set to the container side; standard test blocks such as ball holes, transverse through holes, lack of fusion (both sides of the bevel), incomplete penetration (root), and cracks (middle of the weld) were arranged in the three-dimensional structural simulation model; the fan scanning angle was set to 40°~70°, and echo signals of various defects were collected to establish a local defect standard response feature library.

[0040] 3. Actual detection signal acquisition: Mechanical scanning method was adopted, with a scanning step value of 1mm, an angle step value of 1°, an average signal count of 6, and a pulse repetition frequency (PRF) of 600Hz. The entire weld seam was scanned in a counterclockwise direction, and A / S / B / C / D type scanning images and original echo signals were acquired. The continuous signal loss length was 0.5mm, which meets the requirements.

[0041] 4. Defect type identification: The collected signal was denoised, and one valid defect candidate signal was extracted. This signal is a weak diffraction signal with an amplitude 13dB lower than the reflection signal and no obvious peak value. It was compared with the defect standard response feature library and it was found to be consistent with the characteristics of incomplete fusion at the container. Combined with quantitative parameters (depth 15mm, indication length 4mm) and welding process (incomplete fusion is prone to occur at the fusion line on the container side) for cross-verification, it was determined to be incomplete fusion at the container.

[0042] 5. Result verification: Two additional scanning positions were added to reacquire signals, and weak diffraction signals with the same characteristics were obtained, further confirming that the defect type was non-fusion at the container, and the identification result was accurate.

[0043] When using traditional experience-based identification methods to inspect the fillet weld of the insert-type carbon steel small-diameter branch pipe in this embodiment, the inspector could only identify the presence of defects, but could not distinguish whether it was a lack of fusion at the container or other weak signal defects, and was ultimately misjudged as a crack. After review by the method provided in this application, it was corrected to a lack of fusion at the container, proving that the identification accuracy of this application is significantly better than that of traditional experience-based identification methods.

[0044] In an exemplary embodiment of this application, the implementation process and effects of the above-mentioned method provided in this application are described using the defect identification of fillet welds in a small-diameter carbon steel branch pipe with a pipe thickness of 8mm and a pipe diameter of DN50 as an example.

[0045] 1. Preliminary preparation: The object to be inspected is the fillet weld of a small-diameter carbon steel branch pipe with a thickness of 8mm and a diameter of DN50; the same inspection equipment and probe wedge combination as in the previous exemplary embodiment are selected.

[0046] 2. Simulation Modeling: A 1:1 three-dimensional structural simulation model of the placement corner joint was established using CIVA software. Various defect reflectors were arranged, the fan scanning angle was set to 35° to 75°, and defect response signals were collected and added to the feature library.

[0047] 3. Actual detection signal acquisition: Set the scanning step value to 0.8mm, the angle step value to 0.8°, the signal averaging frequency to 4, PRF=500Hz, scan the entire weld seam clockwise, and acquire valid detection signals.

[0048] 4. Defect type identification: One defect candidate signal was extracted. The signal has high echo energy and clear peak value. The lower end of the signal amplitude is 3.2dB lower than the upper end, which is a perfect match with the characteristics of transverse through hole (strip defect) in the feature library. Combined with quantitative parameters (depth 6mm, indication length 5mm) for verification, it is determined to be a strip defect.

[0049] Based on the above description, in practical applications, the simulation parameters of the CIVA software in this application can be adaptively adjusted according to the actual specifications and materials of the branch pipe being inspected, ensuring that the simulation features match the actual defect signals. The coupling agent used during the inspection process can be a material with good sound transmission properties, such as chemical paste or water, that does not damage the workpiece surface. The coupling agent must be applied evenly to avoid affecting signal quality due to poor coupling. This method can also be used for defect identification of fillet welds in small-diameter austenitic stainless steel branch pipes with diameters of 4mm to 10mm (excluding 10mm). When using this method, the material acoustic parameters (sound velocity, density, etc.) in the simulation model need to be adjusted.

[0050] In addition, in practical applications, testing personnel must possess phased array ultrasonic testing qualifications, master the operation methods of CIVA simulation software, and understand the structural and manufacturing process characteristics of small-diameter branch pipe fillet welds to ensure the accuracy of simulation modeling and signal acquisition.

[0051] In summary, compared with the prior art, this application has at least the following advantages: 1) High recognition accuracy: By using CIVA simulation to establish an accurate defect standard response feature library, the defect type can be quantitatively determined through feature comparison, eliminating the dependence on the experience of the inspection personnel and effectively avoiding missed or false judgments. Through experiments, the recognition accuracy of common defects can be improved to over 95%.

[0052] 2) Strong anti-interference capability: Through simulation, the amplitude difference and shape difference between defect signals and structural interference signals such as end corner echoes are clearly identified. Interference signals can be accurately eliminated in the signal preprocessing and feature comparison stages, which is suitable for the detection scenarios of complex structures of small-diameter branch pipe corner welds.

[0053] 3) Highly targeted and widely adaptable: The simulation modeling and identification scheme is specifically designed for the structural characteristics of small-diameter branch pipe fillet welds (placement type, insertion type, etc.), covering carbon steel branch pipes with a thickness range of 4mm to 30mm. It can accurately identify various common defects and has clear applicable scenarios.

[0054] 4) Standardized operation and easy to promote: A standardized process of "simulation modeling - feature library construction - signal acquisition - comparison and judgment" has been established, clarifying the parameter standards and operational requirements of each link, reducing the technical threshold and facilitating its promotion and application in the industry.

[0055] 5) Improve detection efficiency: Through standardized identification processes and feature comparison mechanisms, the time for determining defect types is significantly shortened, and the detection efficiency is improved by more than 40% compared with traditional experience-based judgment methods.

[0056] Based on the same inventive concept, this application also provides a defect type identification device for small-diameter branch pipe fillet welds, which implements the defect type identification method for small-diameter branch pipe fillet welds described above. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations of one or more embodiments of the defect type identification device for small-diameter branch pipe fillet welds provided below can be found in the limitations of the defect type identification method for small-diameter branch pipe fillet welds described above, and will not be repeated here.

[0057] In one exemplary embodiment, a defect type identification device suitable for fillet welds of small-diameter branch pipes is provided, comprising: a CIVA simulation platform, a phased array ultrasonic testing instrument, and a feature recognition and analysis processor. Both the CIVA simulation platform and the phased array ultrasonic testing instrument are connected to the feature recognition and analysis processor.

[0058] The CIVA simulation platform is used to create a three-dimensional structural simulation model of the fillet weld of a small-diameter branch pipe using CIVA software. Based on the three-dimensional structural simulation model, it is used to perform numerical simulation and phased array detection experiments to obtain echo signals of standard test blocks with different types of defects at different locations. The three-dimensional structural simulation model includes standard test blocks with different types of defects. The phased array ultrasonic testing instrument is used to acquire A / S / B / C / D type scanning images and raw echo signals of the detection area of ​​small-diameter branch pipe fillet welds according to the set scanning step value and angle step value, and obtain the detection signal. The feature recognition and analysis processor is used to extract features from the echo signal to obtain typical response features of different defect types and establish a defect standard response feature library; to extract features from the detection signal to obtain detection signal features; to compare the detection signal features with each typical response feature in the defect standard response feature library to obtain comparison results; to obtain defect type identification results based on the comparison results; and to analyze and verify the defect type identification results using defect quantitative parameters and weld manufacturing process characteristics to obtain defect type and size information.

[0059] As an optional implementation, the phased array ultrasonic testing instrument is equipped with a shear wave phased array probe (such as a conventional linear array probe with a working frequency of 7.5MHz, 32 crystals, and an excitation aperture length of 19.2mm) and a matching wedge (such as a length of 42mm, a leading edge of 15.6mm, an angle of 55°, and a height of 27.5mm) to realize phased array ultrasonic testing of the detection signal.

[0060] As an optional implementation method, in order to further improve the accuracy of the detection, a phased array ultrasonic testing instrument that meets the requirements of NB / T47013.15 can be selected for testing.

[0061] In one exemplary embodiment, a computer device is provided, which may be a server or a terminal, and its internal structure diagram may be as follows. Figure 18 As shown, the computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs in the non-volatile storage media. The database stores defect type identification data applicable to small-diameter branch pipe fillet welds. The I / O interfaces are used for information exchange between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a defect type identification method applicable to small-diameter branch pipe fillet welds.

[0062] Those skilled in the art will understand that Figure 18 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer equipment to which the present application is applied. Specific computer equipment may include, for example, [the following is a list of possible additional structures]. Figure 18The diagram shows more or fewer components, or combinations of certain components, or different component arrangements.

[0063] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0064] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0065] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0066] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (RRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0067] The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0068] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0069] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for identifying defect types in fillet welds of small-diameter branch pipes, characterized in that, include: A three-dimensional structural simulation model of the fillet weld of a small-diameter branch pipe was established using CIVA software, and standard test blocks with different types of defects were fabricated on the three-dimensional structural simulation model. Based on the aforementioned three-dimensional structural simulation model, numerical simulation and phased array detection experiments were conducted to obtain echo signals from standard test blocks with different types of defects at different locations. Feature extraction is performed on the echo signal to obtain typical response features of different defect types, and a standard defect response feature library is established. The small-diameter branch pipe fillet weld to be identified was inspected according to the phased array ultrasonic testing standard to obtain the detection signal; Feature extraction is performed on the detection signal to obtain the detection signal features; The detection signal features are compared with each typical response feature in the defect standard response feature library to obtain the comparison result; Based on the comparison results, the defect type identification result is obtained; The defect type identification results are analyzed and verified using quantitative defect parameters and weld manufacturing process characteristics to obtain defect type and size information.

2. The defect type identification method for fillet welds of small-diameter branch pipes according to claim 1, characterized in that, A three-dimensional structural simulation model of the fillet weld of a small-diameter branch pipe was established using CIVA software, including: A three-dimensional structural simulation model of the fillet weld of a small-diameter branch pipe was constructed using the pipe seat fillet weld simulation module in CIVA software according to the set modeling parameters. The set modeling parameters include: the material, density, longitudinal wave velocity, and transverse wave velocity of the small-diameter branch pipe fillet weld. In the three-dimensional structural simulation model, standard test blocks corresponding to different defect types of small-diameter branch pipe fillet welds are set to cover the defect types of small-diameter branch pipe fillet welds; the standard test blocks include incomplete fusion standard reflectors, incomplete penetration standard reflectors, spherical hole standard reflectors, transverse through-hole standard reflectors, and crack standard reflectors.

3. The defect type identification method for fillet welds of small-diameter branch pipes according to claim 2, characterized in that, The three-dimensional structural simulation model is a 1:1 scale model of the fillet weld of a small-diameter branch pipe.

4. The defect type identification method for fillet welds of small-diameter branch pipes according to claim 1, characterized in that, Feature extraction is performed on the echo signal to obtain typical response features for different defect types, and a standard defect response feature library is established, including: Set simulation parameters that match the actual detection, perform simulation based on the simulation parameters, and obtain the echo signals of standard test blocks with different types of defects at different locations; Matching detection parameters are set for standard test blocks, and phased array detection experiments are carried out to obtain echo signals of standard test blocks with different types of defects in actual test blocks; based on the echo signals, typical response characteristics of different defect types are obtained; the typical response characteristics include echo amplitude, signal shape, and corner echo signals of standard test blocks with different types of defects at different positions; Based on the typical response characteristics, a defect standard response feature library is established.

5. The defect type identification method for fillet welds of small-diameter branch pipes according to claim 1, characterized in that, The small-diameter branch pipe fillet weld to be identified was inspected according to the phased array ultrasonic testing standard, and the detection signals were obtained, including: The fillet welds of small-diameter branch pipes were inspected according to the phased array ultrasonic testing specifications. A / S / B / C / D type scanning images and original echo signals of the inspection area of ​​the fillet welds of small-diameter branch pipes were acquired using a mechanical scanning method with a position sensor, according to the set scanning step value and angle step value, to obtain the detection signal. During the scanning process, the signal covered the entire weld, and the continuous loss length of the A scan signal did not exceed 2mm.

6. The defect type identification method for fillet welds of small-diameter branch pipes according to claim 1, characterized in that, The defect type identification results are analyzed and verified using quantitative defect parameters and weld manufacturing process characteristics to obtain defect type and size information, including: The presence of defects with ambiguous features in the defect type identification results is determined by using quantitative defect parameters and weld manufacturing process characteristics. When there are defects with ambiguous features in the defect type identification results, after increasing the scanning position and adjusting the sensitivity parameters, the small diameter branch pipe fillet weld is re-detected in real time according to the phased array ultrasonic testing specification, and the process is returned to the step of extracting features from the detection signal to obtain the detection signal features. When there are no defects with ambiguous features in the defect type identification results, the defect type and size information are obtained.

7. A defect type identification device suitable for fillet welds of small-diameter branch pipes, characterized in that, include: The CIVA simulation platform is used to establish a three-dimensional structural simulation model of the fillet weld of a small-diameter branch pipe using CIVA software. Based on the three-dimensional structural simulation model, it is used to perform numerical simulation and phased array detection experiments to obtain echo signals of standard test blocks with different types of defects at different locations. The three-dimensional structural simulation model includes standard test blocks with different types of defects. The phased array ultrasonic testing instrument is used to acquire A / S / B / C / D type scanning images and raw echo signals of the detection area of ​​small-diameter branch pipe fillet welds by mechanical scanning with position sensors according to the set scanning step value and angle step value, so as to obtain the detection signal; The feature recognition and analysis processor is connected to the CIVA simulation platform and the phased array ultrasonic testing instrument, respectively, to extract features from the echo signal, obtain typical response features of different defect types, and establish a defect standard response feature library; and to extract features from the detection signal to obtain detection signal features. The detection signal features are compared with each typical response feature in the defect standard response feature library to obtain a comparison result; based on the comparison result, a defect type identification result is obtained. The defect type identification results are analyzed and verified using quantitative defect parameters and weld manufacturing process characteristics to obtain defect type and size information.

8. A computer device, comprising: A memory, a processor, and a computer program stored in the memory and capable of running on the processor, characterized in that the processor executes the computer program to implement the defect type identification method for small-diameter branch pipe fillet welds as described in any one of claims 1-6.

9. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program implements the defect type identification method for small-diameter branch pipe fillet welds as described in any one of claims 1-6.

Images