Automatic evaluation method and device for steel pipe end groove defects based on ultrasonic phased array technology

Abstract

The invention discloses a steel pipe end groove defect automatic evaluation method based on an ultrasonic phased array technology, and relates to the technical field of ultrasonic non-destructive testing, and the method comprises the following steps: collecting phased array map data of a steel pipe end groove by adopting the ultrasonic phased array detection technology; performing target detection area extraction on the phased array map data, and outputting target image data; reconstructing the target image data into a three-dimensional dense point cloud, setting a target threshold and a Gaussian blur factor, performing Gaussian blur processing on the three-dimensional dense point cloud, traversing all point cloud data, and marking points greater than the target threshold; performing merging and feature extraction on the adjacent marked areas to obtain defect data; performing noise suppression and defect screening on the defect data, and outputting groove defect data; and judging the groove defect data by calling a groove detection standard, and generating defect judgment data. According to the method, by optimizing the Gaussian blur factor and a dynamic threshold selection mechanism, the distinction degree of the structure echo and the real defect echo is remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of ultrasonic non-destructive testing, and in particular to a method and device for automatically evaluating defects in steel pipe end grooves based on ultrasonic phased array technology. Background Art

[0002] During the production and welding of oil and gas pipelines, the quality of the pipe end bevel directly impacts the mechanical properties and service reliability of the welded joint. According to the National Pipeline Network Group's design and engineering construction standard, "Technical Specifications for Welded Pipe for Gas Pipeline Projects," and related ordering technical agreements, pipe ends must be machined into a V-shaped groove. Geometric parameters (such as groove angle and blunt edge dimensions) are tailored to the welding process (e.g., manual welding, semi-automatic welding, combined automatic welding, and fully automatic welding). However, during the bevel processing process, defects such as excessive delamination and mechanical damage are common. If these defects are not effectively detected and controlled, they can significantly reduce the structural integrity of the welded joint, leading to welding defects such as lack of fusion, porosity, or cracks, ultimately impacting the pipeline's pressure-bearing capacity and fatigue life. Therefore, to ensure pipeline welding quality meets international standards, high-precision nondestructive testing of the pipe end bevel is essential before welding to identify and eliminate groove defects that do not meet technical specifications. This ensures the stability of the subsequent welding process and the long-term safe operation of the pipeline system.

[0003] However, in pipeline welding inspection, the pipe end groove is prone to generate fixed structure echoes (such as groove contour reflection and diffraction signals) due to its complex geometric structure. Using traditional ultrasonic testing methods to detect it is prone to the following problems: 1. Manual interpretation is highly subjective: it relies on the experience of the inspectors and is prone to missed detection or misjudgment; 2. The damage data collected during the inspection has a lot of structural noise interference, which makes it difficult to distinguish between the groove geometry echo and the actual defect signal (such as lack of fusion and cracks); 3. Low detection efficiency: Manual analysis is time-consuming and difficult to meet the needs of large-scale industrial inspection. When using traditional edge detection algorithms, factors such as the ovality of the steel pipe itself or the slight vibration of the probe during the scanning process will cause the groove structure echo signal, which should be continuous, to become intermittent. The corresponding structure echo signal will fluctuate back and forth and left and right. These variations make it very difficult to use software algorithms to identify the groove structure echo. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to overcome the shortcomings of the prior art and provide a method and device for automatically evaluating steel pipe end groove defects based on ultrasonic phased array technology.

[0005] In order to solve the above technical problems, the technical solutions of the present invention are as follows: An automatic evaluation method for steel pipe end groove defects based on ultrasonic phased array technology includes: Ultrasonic phased array testing technology is used to collect phased array atlas data of the steel pipe end groove; Extract target detection area from phased array map data and output target image data; Reconstruct the target image data into a 3D dense point cloud, set the target threshold and Gaussian blur factor, perform Gaussian blur processing on the 3D dense point cloud, and traverse all point cloud data to mark points larger than the target threshold; Merge and extract features of adjacent marked areas to obtain defect data; Perform noise suppression and defect screening on defect data and output groove defect data; The groove inspection standard is called to judge the groove defect data and generate defect judgment data.

[0006] As a preferred embodiment of the method for automatically evaluating steel pipe end groove defects based on ultrasonic phased array technology of the present invention, the target detection area is extracted from the phased array image data and the target image data is outputted, including: Selecting a target area in the phased array atlas data; The coordinate mapping relationship is established as: ,in, is the image coordinate, t is the time axis, is the actual space coordinate; Perform data normalization on the target area: .

[0007] As a preferred embodiment of the method for automatically evaluating defects in steel pipe end grooves based on ultrasonic phased array technology of the present invention, the defect data obtained by merging and extracting features from adjacent marked areas includes: The neighborhood merging algorithm based on graph search constructs the marked point cloud into an undirected graph, and uses breadth-first search or depth-first search to traverse the undirected graph, merge all connected vertices, and generate candidate defect areas; The QuickHull algorithm is used to calculate the three-dimensional convex hull of each candidate defect area, and the maximum amplitude and coordinates in each convex hull are recorded.

[0008] As a preferred embodiment of the method for automatically evaluating steel pipe end groove defects based on ultrasonic phased array technology of the present invention, the method of performing noise suppression and defect screening on defect data and outputting groove defect data includes: Calculate the principal axis length of each candidate defect area and eliminate the candidate defect areas whose principal axis length is greater than the length threshold; Setting a gain value based on a target threshold value, and removing all candidate defect regions whose maximum amplitude is smaller than the target threshold value and whose difference between the maximum amplitude and the maximum amplitude is larger than the gain value; The remaining data is output as groove defect data.

[0009] As a preferred solution of the method for automatically evaluating steel pipe end groove defects based on ultrasonic phased array technology according to the present invention, the method of evaluating groove defect data by calling groove detection standards and generating defect evaluation data includes: Invoke the groove inspection standard and establish a defect assessment model based on machine learning; The groove defect data is evaluated by the defect evaluation model and the defect evaluation data is output.

[0010] The present invention also provides a device for automatically evaluating steel pipe end groove defects based on ultrasonic phased array technology, comprising: A data acquisition module is used to collect phased array atlas data of the steel pipe end groove using ultrasonic phased array detection technology; The target selection module is used to extract the target detection area from the phased array image data and output the target image data; The 3D point cloud reconstruction module is used to reconstruct the target image data into a 3D dense point cloud, set the target threshold and Gaussian blur factor, perform Gaussian blur processing on the 3D dense point cloud, and traverse all point cloud data to mark points larger than the target threshold; Feature extraction module, used to merge and extract features from adjacent marked areas to obtain defect data; Defect screening module, used to suppress noise and screen defects in defect data, and output groove defect data; The defect judgment module is used to call the groove detection standard to judge the groove defect data and generate defect judgment data.

[0011] The present invention also provides a computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the method described in any of the above-mentioned methods for automatically evaluating steel pipe end groove defects using ultrasonic phased array technology.

[0012] The present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in any of the above-mentioned methods for automatically evaluating steel pipe end groove defects using ultrasonic phased array technology.

[0013] The beneficial effects of the present invention are: (1) The present invention adopts an adaptive three-dimensional point cloud processing algorithm, which effectively solves the problem of irregularity of fixed structure echo caused by the geometric characteristics of the groove in traditional detection. By optimizing the Gaussian fuzzy factor and the dynamic threshold selection mechanism, the distinction between structure echo and real defect echo is significantly improved; secondly, the neighborhood clustering method based on the graph search algorithm (BFS / DFS) is used to achieve accurate extraction of defect areas. Through convex hull calculation and extreme value analysis, a mathematical representation model of defect characteristics is established; thus, the detection accuracy is greatly improved compared with traditional methods, the need for manual intervention is greatly reduced, the detection efficiency is significantly improved, and the detection results have better repeatability and stability.

[0014] (2) The present invention provides a reliable automated detection method for pipeline welding quality control, which significantly reduces labor costs while ensuring detection accuracy. It has important engineering application value, and its algorithm framework can be extended to other non-destructive testing fields of complex geometric structures. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0016] Figure 1 A schematic flow chart of the method for automatically evaluating steel pipe end groove defects based on ultrasonic phased array technology provided by the present invention; Figure 2 This is a schematic diagram of the automatic evaluation device for steel pipe end groove defects based on ultrasonic phased array technology provided by the present invention; Figure 3 A schematic diagram of a computer device provided by the present invention. DETAILED DESCRIPTION

[0017] In order to make the contents of the present invention more clearly understood, the present invention is further described below in detail based on specific implementation methods in conjunction with the accompanying drawings.

[0018] Figure 1 This is a flow chart of a method for automatically evaluating steel pipe end groove defects based on ultrasonic phased array technology provided in this embodiment. The method specifically includes the following steps: Step S101: using ultrasonic phased array detection technology to collect phased array atlas data of the steel pipe end groove.

[0019] Step S102: extracting the target detection area from the phased array image data and outputting target image data.

[0020] Specifically, when performing automatic identification, the global analysis mode can be used to completely process the phased array map data, or the regional selection mode can be used to specifically select a certain area in the phased array map for identification and analysis.

[0021] After selecting the target area, the coordinate mapping relationship is established as follows: ,in, is the image coordinate, t is the time axis, is the actual space coordinate, and then the target area is normalized: .

[0022] Step S103: reconstruct the target image data into a three-dimensional dense point cloud, set the target threshold and Gaussian blur factor, perform Gaussian blur processing on the three-dimensional dense point cloud, traverse all point cloud data, and mark points greater than the target threshold.

[0023] Specifically, the optimal segmentation threshold is automatically determined using the Otsu algorithm or the maximum inter-class variance method. Scale space theory is then used to adaptively select the Gaussian kernel standard deviation based on the point cloud density. Next, a three-dimensional Gaussian convolution kernel is used to smooth and reduce noise on the point cloud data. Finally, the Statistical Outlier Removal (SOR) algorithm is used to remove isolated noise points and improve the signal-to-noise ratio (SNR) of defect detection.

[0024] Step S104: Merge and extract features of adjacent marked areas to obtain defect data.

[0025] Specifically, the labeled point cloud is first constructed into an undirected graph using a graph search neighborhood merging algorithm. A breadth-first search (BFS) or depth-first search (DFS) is then used to traverse the undirected graph, merging all connected vertices to generate candidate defect regions. The QuickHull algorithm is then applied to each candidate region to calculate its three-dimensional convex hull. Finally, the maximum amplitude and coordinates within each convex hull are recorded.

[0026] Step S105: noise suppression and defect screening are performed on the defect data, and the groove defect data is output.

[0027] Specifically, the main axis length of each candidate region is calculated, and regions with a main axis length greater than a threshold are removed, retaining compact defects. Then, a gain value is set based on the target threshold to perform defect screening, removing all regions with a maximum amplitude less than the threshold, retaining high-confidence defects.

[0028] In this embodiment, the gain value is set to 12 dB, and all echo signals below the threshold of 12 dB will be eliminated.

[0029] Step S106: calling the groove detection standard to judge the groove defect data and generate defect judgment data.

[0030] Specifically, the corresponding groove inspection standards are selected, and an automatic defect assessment model based on machine learning is established to achieve accurate quantification of defect parameters and compliance judgment, and finally provide defect evaluation information.

[0031] The above technical solution adopts an adaptive three-dimensional point cloud processing algorithm, which effectively solves the problem of irregularity of fixed structure echoes caused by the geometric characteristics of the groove in traditional detection. By optimizing the Gaussian fuzzy factor and the dynamic threshold selection mechanism, the distinction between structure echoes and real defect echoes is significantly improved; secondly, the neighborhood clustering method based on the graph theory search algorithm (BFS / DFS) realizes the precise extraction of defect areas. Through convex hull calculation and extreme value analysis, a mathematical representation model of defect characteristics is established, which greatly improves the detection accuracy compared with traditional methods, greatly reduces the need for manual intervention, significantly improves the detection efficiency, and makes the detection results more repeatable and stable.

[0032] Figure 2 This is a schematic diagram of the automatic steel pipe end groove defect assessment device based on ultrasonic phased array technology provided in this embodiment. The device includes: a data acquisition module 201, a target selection module 202, a 3D point cloud reconstruction module 203, a feature extraction module 204, a defect screening module 205, and a defect identification module 206.

[0033] Specifically, the data acquisition module 201 is used to acquire phased array atlas data of the steel pipe end groove using ultrasonic phased array detection technology.

[0034] The target selection module 202 is used to extract the target detection area from the phased array map data and output target image data. The target area includes the entire phased array map or a certain area in the phased array map.

[0035] The 3D point cloud reconstruction module 203 is used to reconstruct the target image data into a 3D dense point cloud, set the target threshold and Gaussian blur factor, perform Gaussian blur processing on the 3D dense point cloud, and traverse all point cloud data to mark points greater than the target threshold.

[0036] Specifically, the 3D point cloud reconstruction module 203 automatically determines the optimal segmentation threshold based on the Otsu algorithm or the maximum inter-class variance method, then uses the scale space theory to adaptively select the Gaussian kernel standard deviation according to the point cloud density. Next, a 3D Gaussian convolution kernel is used to smooth and reduce noise on the point cloud data. Finally, the Statistical Outlier Removal (SOR) algorithm is used to remove isolated noise points and improve the signal-to-noise ratio of defect detection.

[0037] The feature extraction module 204 is used to merge and extract features from adjacent marked areas to obtain defect data.

[0038] Specifically, the feature extraction module 204 constructs the marked point cloud into an undirected graph based on the neighborhood merging algorithm of graph search, and then uses breadth-first search (BFS) or depth-first search (DFS) to traverse the undirected graph, merge all connected vertices, and generate candidate defect areas. Then, the QuickHull algorithm is applied to each candidate area to calculate its three-dimensional convex hull, and finally the maximum amplitude and coordinates within each convex hull are recorded.

[0039] The defect screening module 205 is used to suppress noise and screen defects in the defect data and output groove defect data. Specifically, the defect screening module is used to suppress excessively long data (structure echoes) and remove echoes with a gain value less than a threshold.

[0040] The defect judgment module 206 is used to call the groove detection standard to judge the groove defect data and generate defect judgment data.

[0041] See also Figure 3 This embodiment also provides a computer device, the components of which may include but are not limited to: one or more processors or processing units, a system memory, and a bus connecting different system components (including the system memory and the processing unit).

[0042] The term "bus" refers to one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures. Examples of these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect (PCI) bus.

[0043] The computer system / server typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the computer system / server, including volatile and non-volatile media, removable and non-removable media.

[0044] The system memory may include computer system readable media in the form of volatile memory, such as random access memory (RAM) and / or cache memory. The computer device may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system may be used to read and write non-removable, non-volatile magnetic media. A disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk") may be provided, as well as an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media). In these cases, each drive may be connected to the bus via one or more data medium interfaces. The memory may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of various embodiments of the present invention.

[0045] A program / utility having a set (at least one) of program modules, which may be stored, for example, in a memory, includes, but is not limited to, an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may include an implementation of a network environment. The program modules generally perform the functions and / or methods of the embodiments described herein.

[0046] A computer device may also communicate with one or more external devices, such as a keyboard, pointing device, display, etc. Such communication may be performed via an input / output (I / O) interface. Furthermore, a computer device may also communicate with one or more networks, such as a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet, via a network adapter.

[0047] The processing unit executes the functions and / or methods described in the embodiments of the present invention by running the programs stored in the system memory.

[0048] The above-mentioned computer program can be set in a computer storage medium, that is, the computer storage medium is encoded with a computer program, and when the program is executed by one or more computers, it enables one or more computers to perform the method flow and / or device operation shown in the above-mentioned embodiments of the present invention.

[0049] As time goes by and technology develops, the meaning of medium becomes more and more extensive. The dissemination path of computer programs is no longer limited to tangible media, and can also be downloaded directly from the Internet. Any combination of one or more computer-readable media can be used. Computer-readable media can be computer-readable signal media or computer-readable storage media. Computer-readable storage media can be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or components, or any combination of the above. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, device or device.

[0050] A computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal may take a variety of forms, including, but not limited to, electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0051] Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0052] Computer program code for performing the operations of the present invention may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0053] In addition to the above embodiments, the present invention may also have other implementation methods; any technical solutions formed by equivalent replacement or equivalent transformation fall within the protection scope required by the present invention.

Claims

1. A method for automatically evaluating steel pipe end groove defects based on ultrasonic phased array technology, characterized by: include: Ultrasonic phased array testing technology is used to collect phased array atlas data of the steel pipe end groove; Extract target detection area from phased array map data and output target image data; Reconstruct the target image data into a 3D dense point cloud, set the target threshold and Gaussian blur factor, perform Gaussian blur processing on the 3D dense point cloud, and traverse all point cloud data to mark points larger than the target threshold; Merge and extract features of adjacent marked areas to obtain defect data; Perform noise suppression and defect screening on defect data and output groove defect data; The groove inspection standard is called to judge the groove defect data and generate defect judgment data.

2. The method for automatic assessment of steel pipe end groove defects based on ultrasonic phased array technology according to claim 1 is characterized in that: The target detection area extraction of the phased array atlas data and the output of the target image data include: Selecting a target area in the phased array atlas data; The coordinate mapping relationship is established as: ,in, is the image coordinate, t is the time axis, is the actual space coordinate; Perform data normalization on the target area: .

3. The method for automatic assessment of steel pipe end groove defects based on ultrasonic phased array technology according to claim 1 is characterized in that: The merging and feature extraction of adjacent marked areas to obtain defect data includes: The neighborhood merging algorithm based on graph search constructs the marked point cloud into an undirected graph, and uses breadth-first search or depth-first search to traverse the undirected graph, merge all connected vertices, and generate candidate defect areas; The QuickHull algorithm is used to calculate the three-dimensional convex hull of each candidate defect area, and the maximum amplitude and coordinates in each convex hull are recorded.

4. The method for automatically evaluating steel pipe end groove defects based on ultrasonic phased array technology according to claim 3 is characterized in that: The noise suppression and defect screening of the defect data and the output of the groove defect data include: Calculate the principal axis length of each candidate defect area and eliminate the candidate defect areas whose principal axis length is greater than the length threshold; Setting a gain value based on a target threshold value, and removing all candidate defect regions whose maximum amplitude is smaller than the target threshold value and whose difference between the maximum amplitude and the maximum amplitude is larger than the gain value; The remaining data is output as groove defect data.

5. The method for automatic evaluation of steel pipe end groove defects based on ultrasonic phased array technology according to claim 1 is characterized in that: The calling of the groove inspection standard to judge the groove defect data and generate defect judgment data includes: Invoke the groove inspection standard and establish a defect assessment model based on machine learning; The groove defect data is evaluated by the defect evaluation model and the defect evaluation data is output.

6. An automatic assessment device for steel pipe end groove defects based on ultrasonic phased array technology, characterized by: include: A data acquisition module is used to collect phased array atlas data of the steel pipe end groove using ultrasonic phased array detection technology; The target selection module is used to extract the target detection area from the phased array image data and output the target image data; The 3D point cloud reconstruction module is used to reconstruct the target image data into a 3D dense point cloud, set the target threshold and Gaussian blur factor, perform Gaussian blur processing on the 3D dense point cloud, and traverse all point cloud data to mark points larger than the target threshold; Feature extraction module, used to merge and extract features from adjacent marked areas to obtain defect data; Defect screening module, used to suppress noise and screen defects in defect data, and output groove defect data; The defect judgment module is used to call the groove detection standard to judge the groove defect data and generate defect judgment data.

7. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the method according to any one of claims 1 to 5 is implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

Images