An ultrasonic-based weld seam defect detection method and system

Abstract

The application relates to the technical field of ultrasonic detection, and discloses a welding seam defect detection method and system based on ultrasonic waves, which comprises the following steps: establishing a historical database, and traversing ultrasonic echo signals in the historical database; determining a multiplexing defect strategy or an ultrasonic checking strategy according to a traversal result; when the ultrasonic checking strategy is determined, determining a first ultrasonic result based on echo delay and echo intensity, determining a second ultrasonic result based on ultrasonic echo signals and an ultrasonic characteristic model, determining whether a welding seam to be detected has defects according to the first ultrasonic result and the second ultrasonic result; performing Fourier transform on the ultrasonic echo signals, determining a defect type of the welding seam to be detected based on an ultrasonic characteristic spectrum, determining an attenuation result based on a three-dimensional model and a metal sample, and writing the attenuation result into a simulation database of a simulation environment; and verifying the defect type based on the relationship between an ultrasonic characteristic spectrum and a simulation spectrum curve. The application ensures the reliability and stability of ultrasonic detection.

Description

Technical Field

[0001] This invention relates to the field of ultrasonic testing technology, and more specifically, to an ultrasonic-based method and system for detecting weld defects. Background Technology

[0002] In industries such as petrochemicals, aerospace, and rail transportation, welding is often used to connect components. The quality of the weld directly determines the safety and reliability of the connected component structure. The weld formation process is affected by multiple factors such as welding process parameters, material properties, and operating environment, and certain defects may exist. If these defects are not detected and dealt with in time, they may lead to serious accidents such as leakage and breakage.

[0003] Currently, weld defect detection usually relies on the experience and subjective judgment of the inspectors. Different inspectors have different technical levels and practical experience. When inspecting welds of metal materials, the ultrasonic signals obtained may deviate in the determination of defect types, leading to misjudgment or omission of defect types, which affects the reliability and stability of the test results. Furthermore, with the increasing complexity of industrial products and the higher requirements for testing accuracy, relying on human experience is difficult to meet the requirements of high-precision and intelligent quality control.

[0004] Therefore, it is necessary to design an ultrasonic-based weld defect detection method and system to solve the problems existing in the current technology. Summary of the Invention

[0005] In view of this, the present invention proposes an ultrasonic-based weld defect detection method and system, which aims to solve the problem that the differences in technical level and practical experience of different inspectors can lead to deviations in the determination of defect type by the acquired ultrasonic signals when detecting weld defects in metal materials, resulting in misjudgment or omission of defect type, thereby affecting the reliability and stability of the detection results. Relying on human experience is difficult to meet the requirements of high precision and intelligent quality control.

[0006] In one aspect, the present invention proposes an ultrasonic-based method for detecting weld defects, comprising:

[0007] A historical database is established, which includes a historical normal database and a historical defect database. The ultrasonic echo signal of the weld to be inspected is obtained, and the ultrasonic echo signal is traversed in the historical database. Based on the traversal results, a defect reuse strategy or an ultrasonic verification strategy is determined.

[0008] When the ultrasonic verification strategy is determined, the echo delay and echo intensity of the ultrasonic echo signal are determined, and a first ultrasonic result is determined based on the echo delay and echo intensity. A second ultrasonic result is determined based on the ultrasonic echo signal and the ultrasonic feature model. The presence of a defect in the weld to be inspected is determined based on the first ultrasonic result and the second ultrasonic result.

[0009] When it is determined that there is a defect in the weld to be inspected, the ultrasonic echo signal is subjected to Fourier transform to determine the ultrasonic characteristic spectrum. Based on the ultrasonic characteristic spectrum, the defect type of the weld to be inspected is determined, a three-dimensional model of the weld to be inspected is established, a simulation environment is built and the three-dimensional model is imported into the simulation environment, and the attenuation result is determined based on the three-dimensional model and the metal sample and written into the simulation database of the simulation environment.

[0010] Based on the simulation database, a simulated ultrasonic probe array is determined. Wave field propagation simulation is performed based on the simulated ultrasonic probe array. The simulated spectrum curve is determined based on the wave field propagation simulation results. The defect type is verified based on the relationship between the ultrasonic characteristic spectrum diagram and the simulated spectrum curve.

[0011] Furthermore, when acquiring the ultrasonic echo signal of the weld to be inspected, traversing the ultrasonic echo signal in the historical database, and determining the defect reuse strategy or ultrasonic verification strategy based on the traversal results, the process includes:

[0012] If the weld to be inspected and the detection surface are parallel, a straight probe is used to obtain the ultrasonic echo signal. If the weld to be inspected and the detection surface are not parallel, an angled probe is used to obtain the ultrasonic echo signal. When using a straight probe or an angled probe to obtain the ultrasonic echo signal, a coupling agent is first applied between the straight probe or angled probe and the detection surface.

[0013] The historical database includes historical ultrasonic echo signals, historical ultrasonic sensor operating data, historical simulation spectrum curves, and historical defect types, and the historical ultrasonic echo signals, historical ultrasonic sensor operating data, historical simulation spectrum curves, and historical defect types correspond one-to-one.

[0014] The ultrasonic echo signal is traversed in the historical defect database to determine the defect reuse strategy or ultrasonic verification strategy.

[0015] Furthermore, when traversing the historical defect database using the ultrasonic echo signal to determine the multiplexing defect strategy or ultrasonic verification strategy, the process includes:

[0016] When the historical defect database contains data identical to the ultrasonic echo signal, it is determined to be the reuse defect strategy, and the historical defect type corresponding to the identical data is reused.

[0017] If no data matching the ultrasonic echo signal exists in the historical defect database, then the ultrasonic verification strategy is determined.

[0018] Furthermore, when determining the echo delay and echo intensity of the ultrasound echo signal, and determining a first ultrasound result based on the echo delay and echo intensity, and determining a second ultrasound result based on the ultrasound echo signal and ultrasound feature model, the process includes:

[0019] Obtain the standard echo delay range and the standard echo intensity range, and compare the echo delay and echo intensity with the standard echo delay range and the standard echo intensity range, respectively;

[0020] When the echo delay is within the standard echo delay range and the echo intensity is within the standard echo intensity range, the first ultrasound result is determined as the first output type.

[0021] If the echo delay is not within the standard echo delay range, or the echo intensity is not within the standard echo intensity range, then the first ultrasound result is determined as the second output type.

[0022] The sensor dataset and the historical database are divided into a training set and a test set. The ultrasound feature model is determined based on the training set and the test set. The ultrasound echo signal is substituted into the ultrasound feature model to determine the second ultrasound result. The second ultrasound result includes the first output type or the second output type.

[0023] Furthermore, when determining whether the weld to be inspected has defects based on the first and second ultrasonic results, the process includes:

[0024] When the output types of the first ultrasonic result and the second ultrasonic result are both the first output type, it is determined that the weld to be inspected has no defects, and the ultrasonic echo signal is stored in the historical normal database.

[0025] When the output types of the first ultrasonic result and the second ultrasonic result are both the second output type, or the output types are inconsistent, it is determined that the weld to be inspected has a defect.

[0026] Furthermore, when determining the defect type of the weld to be inspected based on the ultrasonic characteristic spectrum, the process includes:

[0027] Determine the amplitude jumps in the ultrasonic characteristic spectrum, and determine the first amplitude jump and the second amplitude jump, wherein the first amplitude jump is greater than the second amplitude jump;

[0028] When the amplitude jump is greater than the first amplitude jump, the defect type of the weld to be inspected is determined to be a crack;

[0029] When the amplitude jump is less than or equal to the first amplitude jump and greater than or equal to the second amplitude jump, the defect type of the weld to be inspected is determined to be porosity.

[0030] When the amplitude jump is less than the second amplitude jump, the defect type of the weld to be inspected is determined to be slag inclusion.

[0031] Furthermore, the process of establishing a three-dimensional model of the weld to be inspected, building a simulation environment and importing the three-dimensional model into the simulation environment, determining the attenuation result based on the three-dimensional model and the metal sample, and writing it into the simulation database of the simulation environment includes:

[0032] The weld to be inspected is collected segment by segment to determine point cloud data, and isolated points and noise points in the point cloud data are removed based on neighborhood statistics and curvature filtering algorithms. A three-dimensional model of the weld to be inspected is established based on ICP registration and surface reconstruction algorithms using the least squares method.

[0033] The simulation environment is built using simulation software, and the three-dimensional model is imported. A tetrahedral mesh is generated on the three-dimensional model according to an adaptive mesh generation algorithm. The mesh size is adjusted according to the wavelength of the ultrasonic echo signal. A metal sample of the same material as the weld to be inspected and the detection surface is obtained. The metal sample is subjected to attenuation test using pulse echo, and the attenuation result is determined by frequency domain analysis fitting. The attenuation result includes sound velocity, density, and attenuation parameters. The sound velocity, density, and attenuation parameters are imported into the software database of the simulation software to construct the simulation database.

[0034] Furthermore, when determining the simulated ultrasonic probe array based on the simulation database, performing wave field propagation simulation based on the simulated ultrasonic probe array, and determining the simulated spectrum curve based on the wave field propagation simulation results, the process includes:

[0035] The arrangement of the phased array ultrasonic sensors is determined based on the curvature of the three-dimensional model, and the array surface is deployed in the three-dimensional model according to the arrangement to determine the simulated ultrasonic probe array. The optimal spacing of the finite element mesh and the operating frequency of the phased array ultrasonic sensors are determined based on the simulation database.

[0036] In the Gaussian pulse signal of the simulated ultrasonic probe array, the beam bandwidth and excitation function are selected, and the vertical displacement component of the simulated ultrasonic probe array is obtained. Based on the simulation environment, a three-dimensional time-domain wave field analysis is performed to output the original time-domain waveform. The signal envelope is determined by Hilbert transform. Based on short-time Fourier transform and multi-layer wavelet packet decomposition, the frequency drift, bandwidth expansion, and energy distribution characteristics of the signal envelope in each frequency band are extracted to determine the simulated spectrum curve.

[0037] Furthermore, when verifying the defect type based on the relationship between the ultrasonic characteristic spectrum and the simulated spectrum curve, the following steps are included:

[0038] When the simulated spectrum curve is consistent with the ultrasonic characteristic spectrum Figure 1 If the condition is met, the defect type is determined to be correct, and the defect type and ultrasonic echo signal are stored in the historical defect database.

[0039] When the simulated spectrum curve is inconsistent with the ultrasonic characteristic spectrum diagram, it is determined that the defect type is incorrect, and the ultrasonic echo signal of the weld to be inspected is reacquired.

[0040] Compared with existing technologies, the advantages of this invention are as follows: Traditional ultrasonic testing relies on human experience, which is prone to misjudgment and omission due to differences in personnel skills. By establishing a historical database, a reference basis is provided for the analysis of ultrasonic echo signals, reducing the interference of human subjective bias on the test results and improving the reliability and stability of ultrasonic testing. When identifying defects, the invention combines echo delay, echo intensity, and ultrasonic feature models to obtain dual results and determine the existing defects, realizing multi-dimensional analysis of ultrasonic echo signals. This enables accurate capture of signal features, improves the accuracy of weld defect type identification, and effectively avoids the limitations of a single judgment method. The invention obtains ultrasonic feature spectrum diagrams through Fourier transform and verifies them by combining them with simulated spectrum curves formed by wave field propagation simulation, constructing a closed-loop process of identification-simulation-verification. This enhances the accuracy of defect type determination in ultrasonic testing. At the same time, the introduction of three-dimensional models and simulation environments allows ultrasonic testing to go beyond the signal itself. Through simulation databases and simulated ultrasonic probe arrays, the characteristics of defects under different ultrasonic propagation conditions are comprehensively analyzed, realizing the transformation of ultrasonic testing from reliance on manual labor to data-driven and intelligent analysis, thus improving the reliability and stability of ultrasonic testing.

[0041] On the other hand, this application also provides an ultrasonic-based weld defect detection system for applying the above-mentioned ultrasonic-based weld defect detection method, comprising:

[0042] The storage and analysis unit is configured to establish a historical database, which includes a historical normal database and a historical defect database, acquire the ultrasonic echo signal of the weld to be inspected, traverse the ultrasonic echo signal in the historical database, and determine a defect reuse strategy or an ultrasonic verification strategy based on the traversal results.

[0043] An ultrasonic testing unit is configured to, when the ultrasonic verification strategy is determined, determine the echo delay and echo intensity of the ultrasonic echo signal, determine a first ultrasonic result based on the echo delay and echo intensity, determine a second ultrasonic result based on the ultrasonic echo signal and an ultrasonic feature model, and determine whether there is a defect in the weld to be inspected based on the first ultrasonic result and the second ultrasonic result.

[0044] The ultrasonic simulation unit is configured to, when it is determined that there is a defect in the weld to be inspected, perform Fourier transform on the ultrasonic echo signal to determine the ultrasonic characteristic spectrum, determine the defect type of the weld to be inspected based on the ultrasonic characteristic spectrum, establish a three-dimensional model of the weld to be inspected, build a simulation environment and import the three-dimensional model into the simulation environment, determine the attenuation result based on the three-dimensional model and the metal sample and write it into the simulation database of the simulation environment;

[0045] The ultrasonic verification unit is configured to determine a simulated ultrasonic probe array based on the simulation database, perform wave field propagation simulation based on the simulated ultrasonic probe array, determine a simulated spectrum curve based on the wave field propagation simulation results, and verify the defect type based on the relationship between the ultrasonic characteristic spectrum diagram and the simulated spectrum curve.

[0046] It is understandable that the above-mentioned ultrasonic-based weld defect detection method and system have the same beneficial effects, and will not be elaborated further here. Attached Figure Description

[0047] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0048] Figure 1 A flowchart of an ultrasonic-based weld defect detection method provided in an embodiment of the present invention;

[0049] Figure 2 This is a functional block diagram of an ultrasonic-based weld defect detection system provided in an embodiment of the present invention. Detailed Implementation

[0050] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the disclosure to those skilled in the art. It should be noted that, unless otherwise specified, embodiments and features in the embodiments of the present invention can be combined with each other. The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0051] See Figure 1 As shown in some embodiments of this application, an ultrasonic-based weld defect detection method includes:

[0052] S100: Establish a historical database, which includes a historical normal database and a historical defect database. Obtain the ultrasonic echo signal of the weld to be inspected and traverse the ultrasonic echo signal in the historical database. Determine the defect reuse strategy or ultrasonic verification strategy based on the traversal results.

[0053] S200: When the ultrasonic verification strategy is determined, the echo delay and echo intensity of the ultrasonic echo signal are determined, and a first ultrasonic result is determined based on the echo delay and echo intensity. A second ultrasonic result is determined based on the ultrasonic echo signal and the ultrasonic feature model. The presence of defects in the weld to be inspected is determined based on the first ultrasonic result and the second ultrasonic result.

[0054] S300: When it is determined that there is a defect in the weld to be inspected, the ultrasonic echo signal is subjected to Fourier transform to determine the ultrasonic characteristic spectrum. Based on the ultrasonic characteristic spectrum, the defect type of the weld to be inspected is determined, a three-dimensional model of the weld to be inspected is established, a simulation environment is built and the three-dimensional model is imported into the simulation environment, and the attenuation result is determined based on the three-dimensional model and the metal sample and written into the simulation database of the simulation environment.

[0055] S400: Based on the simulation database, determine the simulated ultrasonic probe array, perform wave field propagation simulation based on the simulated ultrasonic probe array, determine the simulated spectrum curve based on the wave field propagation simulation results, and verify the defect type based on the relationship between the ultrasonic characteristic spectrum diagram and the simulated spectrum curve.

[0056] Currently, weld defect detection technologies mainly include radiographic testing, ultrasonic testing, magnetic particle testing, and penetrant testing. Among them, ultrasonic testing, with its advantages of strong penetration, high sensitivity, and real-time detection, has become one of the mainstream technologies for detecting weld defects in metallic materials. Its basic principle is to emit ultrasonic waves into the weld area through the probe of an ultrasonic sensor. During propagation, the ultrasonic waves are reflected, refracted, or scattered when they encounter the defect interface. The receiving probe acquires the reflected signal (i.e., the ultrasonic echo signal), and the presence or absence of defects and related information are analyzed based on the signal characteristics.

[0057] Specifically, a historical database is established, comprising both historical normal and historical defect databases. By accumulating massive amounts of past weld inspection data, a benchmark database covering various normal states and defect characteristics is constructed. This data includes ultrasonic echo signals from different welding processes, materials, and environments, along with corresponding defect data. Given that differences in the experience of different inspectors can lead to subjective judgment biases, the historical database provides an objective and unified comparison standard. Ultrasonic sensors are used to form a probe array around the weld to be inspected, or inspection is performed directly. Once the ultrasonic echo signal of the weld to be inspected is acquired, it is traversed through the historical database to quickly determine whether the signal matches signals of known defects. This determines whether a defect reuse strategy or an ultrasonic verification strategy is employed. Under the defect reuse strategy, the defect situation is directly determined based on the historical database. Under the ultrasonic verification strategy, the signal characteristics are not very clear and require further verification, thus reducing reliance on human experience. Preliminary screening of inspection directions through data comparison improves the efficiency of ultrasonic inspection and lays the foundation for subsequent inspections. When an ultrasonic verification strategy is adopted, the existence of defects needs to be determined through dual verification. The echo delay and echo intensity of the ultrasonic echo signal are used to obtain the first ultrasonic result. The principle is that the echo delay is related to the location of the defect (sound wave propagation time reflects distance), and the echo intensity is related to the size and nature of the defect (different defects have different abilities to reflect sound waves). The second ultrasonic result is determined based on the ultrasonic echo signal and the ultrasonic feature model. The ultrasonic feature model is trained with a large amount of data and can extract subtle features in the signal and identify possible complex defect patterns. The echo delay and echo intensity may be affected by interference during propagation. However, by combining the artificial intelligence model with the echo delay and echo intensity, verification can be performed from different dimensions, reducing the risk of misjudgment, improving the accuracy of defect identification, and avoiding missed or misjudgments due to the deviation of a single indicator.

[0058] Understandably, once a defect is identified, a Fourier transform is performed on the ultrasonic echo signal to obtain an ultrasonic characteristic spectrum. The Fourier transform converts the time-domain signal into the frequency domain. Different defect types (such as cracks and pores) have certain differences in their spectral characteristics, which can be used to initially determine the defect type. A three-dimensional model is then established, and a simulation environment is built. The simulation environment supports multi-physics coupling and single-physics simulation, fully covering the entire physical process of ultrasonic propagation. Since the influence of weld seams and material properties on ultrasonic propagation varies among different metal materials, after importing the three-dimensional model, the attenuation results are determined based on the three-dimensional model and metal samples and written into the simulation database. This provides material property parameters for subsequent wave field propagation simulation. Based on the simulation database, a simulated ultrasonic probe array is determined to perform wave field propagation simulation, generating corresponding simulated spectrum curves. These curves are compared with the ultrasonic characteristic spectrum to verify the defect type. Based on ultrasonic sensing of defects in weld seams in metal materials, the entire process is simulated and verified to ensure the reliability of defect type determination. Through the synergistic effect of historical data comparison, dual verification, spectrum analysis, and simulation verification, the reliability of ultrasonic detection is improved, avoiding the subjectivity and uncertainty of human detection, and realizing intelligent and precise weld defect detection.

[0059] In some embodiments of this application, when acquiring the ultrasonic echo signal of the weld to be inspected and traversing the ultrasonic echo signal in a historical database to determine a defect reuse strategy or ultrasonic verification strategy based on the traversal results, the process includes: if the weld to be inspected and the detection surface are parallel, a straight probe is used to acquire the ultrasonic echo signal; if the weld to be inspected and the detection surface are not parallel, an angled probe is used to acquire the ultrasonic echo signal. When acquiring the ultrasonic echo signal using a straight probe or an angled probe, a coupling agent is first applied between the straight probe or angled probe and the detection surface. The historical database includes historical ultrasonic echo signals, historical ultrasonic sensor operating data, historical simulation spectrum curves, and historical defect types, and these historical ultrasonic echo signals, historical ultrasonic sensor operating data, historical simulation spectrum curves, and historical defect types correspond one-to-one. The ultrasonic echo signal is traversed in the historical defect database to determine a defect reuse strategy or ultrasonic verification strategy.

[0060] Specifically, the detection surface is the workpiece surface that the ultrasonic probe directly contacts and emits and receives ultrasonic waves. It is typically the surface of the component being inspected (such as pipes, plates, containers, etc.) that contacts the probe. It is the entry point for the ultrasonic waves to enter the workpiece from the probe. For example, when inspecting pipe welds, the outer or inner wall of the pipe may serve as the detection surface; when inspecting butt welds on flat plates, the outer surface of the plate may serve as the detection surface. The parallelism or non-parallelism between the detection surface and the weld directly affects the incident angle and propagation path of the ultrasonic waves. If they are parallel, the vertical sound waves from a straight probe can efficiently reach the weld. If they are not parallel, the angled sound waves from an angled probe can adjust their angle to suit the position of the weld, ensuring that the ultrasonic waves are incident at a suitable angle to the weld, thus effectively covering the inspection area. When ultrasonic waves propagate in different media, the greater the difference in acoustic impedance, the more severe the reflection loss. The acoustic impedance of air differs significantly from that of metal and other workpiece materials. If an air gap exists between the ultrasonic probe and the detection surface, ultrasonic waves will be strongly reflected back to the probe, resulting in a significant amount of energy being reflected back and preventing the acquisition of ultrasonic echo signals. The acoustic impedance of a coupling agent (such as machine oil or glycerin) lies between the probe (a piezoelectric material) and the detection surface. This allows the agent to fill the tiny gaps between the probe and the detection surface, eliminating air and enabling smooth ultrasonic wave transmission. This reduces reflection loss and ensures the strength and integrity of the ultrasonic echo signal, preventing missed defect detection due to signal attenuation or loss. Furthermore, when acquiring ultrasonic echo signals, noise reduction and other processing are performed to ensure the stability and reliability of the signal. Multi-dimensional data in the historical database comprehensively reflects the characteristics of ultrasonic echo signals from different periods; historical sensor operating data reflects detection conditions; historical simulation spectrum curves provide theoretical references; and historical defect types represent the final conclusions determined in historical periods. By traversing the historical defect database, it is possible to accurately determine whether the signal matches a known defect, thus improving the stability and reliability of ultrasonic testing.

[0061] In some embodiments of this application, when traversing the ultrasonic echo signal in the historical defect database to determine a defect reuse strategy or an ultrasonic verification strategy, the following steps are taken: when there is data in the historical defect database that is the same as the ultrasonic echo signal, it is determined to be a defect reuse strategy, and the historical defect type corresponding to the same data is reused; when there is no data in the historical defect database that is the same as the ultrasonic echo signal, it is determined to be an ultrasonic verification strategy.

[0062] Specifically, ultrasonic weld inspection presents a complex testing scenario. The historical defect database has been validated. When identical historical ultrasonic echo signals exist, the corresponding historical defect type indicates that the defect has been fully identified. In this case, the defect reuse strategy can directly call upon known results, avoiding repeated analysis of similar defects and thus improving inspection efficiency. When identical historical ultrasonic echo signals do not exist, it indicates that the ultrasonic echo signals may be unknown data and correspond to new defect types. Direct judgment in such cases is prone to misjudgment due to a lack of reference. The ultrasonic verification strategy, through echo parameter analysis and feature model dual verification, deeply analyzes the potential information in the signal, compensating for the judgment blind spots caused by missing data. This avoids redundant operations and reduces the risk of missed or misjudged cases, improving the reliability of the results while ensuring ultrasonic inspection accuracy.

[0063] In some embodiments of this application, when determining the echo delay and echo intensity of an ultrasonic echo signal, and determining a first ultrasonic result based on the echo delay and echo intensity, and determining a second ultrasonic result based on the ultrasonic echo signal and an ultrasonic feature model, the process includes: obtaining a standard echo delay interval and a standard echo intensity interval; comparing the echo delay and echo intensity with the standard echo delay interval and the standard echo intensity interval respectively; when the echo delay is within the standard echo delay interval and the echo intensity is within the standard echo intensity interval, then determining the first ultrasonic result as a first output type; when the echo delay is not within the standard echo delay interval or the echo intensity is not within the standard echo intensity interval, then determining the first ultrasonic result as a second output type; dividing the sensor dataset and the historical database into a training set and a test set; determining an ultrasonic feature model based on the training set and the test set; and substituting the ultrasonic echo signal into the ultrasonic feature model to determine the second ultrasonic result, wherein the second ultrasonic result includes either the first output type or the second output type.

[0064] Specifically, since different metal materials have different densities, elastic moduli, and acoustic impedances, the propagation speed of ultrasound waves is directly affected. For example, the longitudinal wave velocity in steel is about 5900 m / s, and in aluminum it is about 6300 m / s. Therefore, the standard echo delay range and standard echo intensity range are dynamically determined based on the material properties of the detection surface and the weld to be inspected (such as aluminum, iron, etc.). When the echo delay is within the standard echo delay range and the echo intensity is within the standard echo intensity range, the first ultrasound result is determined as the first output type. The first output type reflects that there is no defect in the weld to be inspected, while the second output type reflects that there is a defect in the weld to be inspected. Regardless of whether the first ultrasound result is the first output type or the second output type, it needs to be further verified. The dual judgment mechanism can improve the accuracy and reliability of defect identification. The second ultrasound result relies on an ultrasound feature model. The sensor dataset contains parameters such as the operating frequency, reflection time, and accuracy of different types of ultrasound sensors. The sensor dataset and historical database are divided into training and testing sets, typically in a 4:1 ratio, to ensure the model's generalization ability and its ability to capture and identify relationships between different data. The training set is used to train the model to learn the characteristic patterns of ultrasound, while the testing set is used to verify the model's generalization ability, ensuring that the model can stably identify potential defects and uncover some deep features that cannot be reflected, thus compensating for the limitations of standard interval comparison. This dual-result cross-validation achieves rapid judgment through standard intervals while improving accuracy through model analysis, reducing the risk of missed or false judgments from a single judgment. Simultaneously, the model is continuously optimized based on historical data to adapt to diverse defect scenarios.

[0065] In some embodiments of this application, when determining whether there is a defect in the weld to be inspected based on the first ultrasonic result and the second ultrasonic result, the method includes: when the output types of the first ultrasonic result and the second ultrasonic result are both the first output type, it is determined that there is no defect in the weld to be inspected, and the ultrasonic echo signal is stored in the historical normal database; when the output types of the first ultrasonic result and the second ultrasonic result are both the second output type, or the output types are inconsistent, it is determined that there is a defect in the weld to be inspected.

[0066] Specifically, the first ultrasound result performs rapid screening based on a standard range, while the second ultrasound result relies on the model to achieve in-depth feature analysis. Both reflect the defect status from two dimensions: intuitive parameters and complex patterns, respectively. When both are the first output type, it indicates that the ultrasound echo signal conforms to the normal parameter range and has not been identified as having abnormal features by the model. This double confirmation reduces the risk of misjudgment. In this case, the signal is stored in a historical normal database for data-driven enrichment of the benchmark data. However, the generalization ability of the ultrasound feature model is limited by the training data. If the training set lacks samples of a certain type of defect, such as rare defects on small layers, or if the defect features are highly similar to normal signals (e.g., the reflection pattern of surface defects is close to the echo of the base material), the model may not be able to learn to distinguish the features. Moreover, the standard range may not be able to cover all defect scenarios. For example, extremely small point defects have weak reflection signals, and their echo intensity may fall exactly within the normal range. Alternatively, the echo delay of a tilted crack may coincide with the reflection time of a normal weld due to the special propagation path of the sound wave. Furthermore, material inhomogeneity, such as porous areas in castings, may cause normal signal fluctuations. Therefore, when the outputs of the two are inconsistent, a defect is still determined to exist. This is essentially due to the complementarity of dual verification. Even if one mechanism may miss a defect due to limitations, the result of the other mechanism can still trigger the defect, thereby improving the reliability of ultrasonic testing.

[0067] In some embodiments of this application, when determining the defect type of the weld to be inspected based on the ultrasonic characteristic spectrum, the method includes: determining the amplitude jump of the ultrasonic characteristic spectrum, and determining a first amplitude jump and a second amplitude jump, wherein the first amplitude jump is greater than the second amplitude jump; when the amplitude jump is greater than the first amplitude jump, the defect type of the weld to be inspected is determined to be a crack; when the amplitude jump is less than or equal to the first amplitude jump and greater than or equal to the second amplitude jump, the defect type of the weld to be inspected is determined to be a porosity; and when the amplitude jump is less than the second amplitude jump, the defect type of the weld to be inspected is determined to be a slag inclusion.

[0068] Specifically, the physical structures of different defects exhibit significantly different ultrasonic wave reflection characteristics. Cracks, often sharp and continuous linear defects, have a large reflecting area and a smooth interface, leading to drastic energy abrupt changes in the reflected signal, resulting in the largest amplitude jump. Pores, being closed cavities, are relatively regular in shape but have a moderate reflecting area, exhibiting a weaker amplitude jump than cracks. Inclusions, mostly loose impurities, have irregular reflecting interfaces and severe energy scattering, resulting in the smallest amplitude jump. Crack echo peak values ​​are often more than half higher than the reference peak value, meaning ΔA / A0 is greater than approximately 0.5. Pores both reflect and scatter ultrasonic waves, with amplitude variations falling between those of cracks and inclusions. Typically, ΔA / A0 falls between 0.1 and 0.5, indicating that the echo peak value can be 10% to 50% higher than the reference. Inclusions, with their irregular internal interfaces, exhibit weak absorption and scattering of ultrasonic waves, resulting in the smallest amplitude jump. In most cases, ΔA / A0 is less than 0.1, meaning the echo peak value differs from the reference by no more than 10%. By setting the first amplitude jump to 0.5 and the second amplitude jump to 0.1, subjective biases that rely on human experience are avoided, ensuring the reliability and stability of ultrasonic testing.

[0069] In some embodiments of this application, the process of establishing a three-dimensional model of the weld to be inspected, building a simulation environment and importing the three-dimensional model into the simulation environment, determining the attenuation result based on the three-dimensional model and metal samples, and writing it into the simulation database of the simulation environment includes: collecting point cloud data of the weld to be inspected segment by segment, removing isolated points and noise points of the point cloud data based on neighborhood statistics and curvature filtering algorithms, establishing a three-dimensional model of the weld to be inspected based on the least squares ICP registration and surface reconstruction algorithm, building a simulation environment using simulation software and importing the three-dimensional model, generating a tetrahedral mesh in the three-dimensional model according to an adaptive mesh generation algorithm, adjusting the mesh size according to the wavelength of the ultrasonic echo signal, obtaining a metal sample of the same material as the weld to be inspected and the detection surface, performing an attenuation test on the metal sample using pulse echo, and determining the attenuation result through frequency domain analysis fitting, the attenuation result including sound velocity, density, and attenuation parameters, importing the sound velocity, density, and attenuation parameters into the software database of the simulation software and constructing a simulation database.

[0070] Specifically, by accurately reconstructing the geometric features and material physical properties of the weld to be inspected, a high-fidelity digital foundation is provided for subsequent wavefield simulation, ensuring a high degree of consistency between the simulation results and the actual inspection scenario. After segmented acquisition of point cloud data, neighborhood statistics and curvature filtering are used to remove isolated points and noise. The original point cloud data is susceptible to environmental interference and errors; filtering can prevent outliers from distorting the geometric shape of the weld to be inspected. ICP registration based on the least squares method can achieve accurate stitching of multiple point cloud segments, while surface reconstruction transforms discrete points into a continuous three-dimensional model, ensuring accurate reconstruction of the geometric structure of the weld to be inspected and providing an accurate spatial carrier for the simulation environment. COMSOL Multiphysics simulation software is typically used to build the simulation environment, and tetrahedral meshes are adaptively generated. The mesh size is adjusted according to the wavelength of the ultrasonic echo signal. The mesh accuracy directly affects the accuracy of subsequent wavefield propagation simulation; a mesh that is too coarse will miss acoustic details, while a mesh that is too fine will increase the computational load. A mesh that matches the wavelength can achieve high accuracy. A balance is struck between efficiency and simulation to ensure accurate simulation of the physical processes of ultrasonic reflection and refraction. The metal sample represents the material properties of the probe surface and the weld to be inspected (such as aluminum and iron). Because different metals have different sound velocities, densities, and attenuation characteristics, these factors determine the propagation laws of ultrasonic waves. Pulse echoes, combined with frequency domain analysis, can accurately extract these parameters, ensuring that the material properties of the simulation environment are consistent with the actual workpiece. This avoids simulation distortion caused by parameter deviations. The sound velocity, density, and attenuation parameters are imported into the simulation software's database to build a simulation database. Typically, the simulation software provides some basic software databases as simulation data. Integrating the attenuation test results of the pulse echoes on the metal sample into the software database provides a comprehensive and accurate physical parameter benchmark for subsequent wave field simulations, ensuring the reliability of the simulation results. This allows the wave field propagation simulation to realistically reproduce the ultrasonic wave's action process, providing a theoretical basis for defect type verification, improving the objectivity and accuracy of defect verification, and providing solid support for the reliability of ultrasonic testing.

[0071] In some embodiments of this application, when determining the simulated ultrasonic probe array based on a simulation database, performing wave field propagation simulation based on the simulated ultrasonic probe array, and determining the simulation spectrum curve based on the wave field propagation simulation results, the process includes: determining the arrangement of the phased array ultrasonic sensors based on the curvature of the three-dimensional model, deploying the array surface on the three-dimensional model according to the arrangement to determine the simulated ultrasonic probe array, determining the optimal spacing of the finite element mesh and the operating frequency of the phased array ultrasonic sensors based on the simulation database, selecting the beam bandwidth and excitation function in the Gaussian pulse signal of the simulated ultrasonic probe array, obtaining the vertical displacement component of the simulated ultrasonic probe array, performing three-dimensional time-domain wave field analysis based on the simulation environment to output the original time-domain waveform, using Hilbert transform to determine the signal envelope, and extracting the frequency drift, bandwidth expansion, and energy distribution characteristics of the signal envelope between frequency bands based on short-time Fourier transform and multi-layer wavelet packet decomposition to determine the simulation spectrum curve.

[0072] Specifically, by accurately determining the working state and wave field propagation law of the simulated ultrasonic probe array, a spectral curve that truly reflects the defect characteristics is extracted, providing a reliable reference for defect type verification. The phased array arrangement and array surface deployment are determined based on the curvature of the 3D model because the surface curvature of the weld to be inspected affects the coupling effect of the probe and the incident angle of the sound wave. An arrangement that matches the curvature ensures uniform sound wave coverage of the detection area, avoiding signal distortion caused by poor probe fit. Generally, planes or near-planes with large curvature (such as butt welds on flat plates or the outer surface of large containers) use a linear array arrangement. The crystals of the linear array probes are arranged in a straight line, and the sound wave is incident perpendicularly, suitable for welds parallel to the detection surface. For example, the curvature of a flat plate weld is close to zero, and a linear array can achieve full coverage, avoiding signal distortion caused by probe tilt. Cylindrical surfaces or annular structures (such as circumferential welds on pipes or pressure vessels) use an annular array arrangement. The crystals of the annular array are distributed circumferentially, and the sound wave is incident radially, suitable for the circumferential detection requirements of cylindrical surfaces. For example, the curvature of a pipe circumferential weld is a constant radius. A ring array can cover the entire weld through full circumferential scanning. For complex irregular curved surfaces (such as aero-engine blades and welds of irregular structures), or areas with drastic curvature changes, a matrix array arrangement is used. The crystals of the matrix array are arranged in two-dimensional rectangles, and three-dimensional spatial scanning can be achieved through dynamic focusing and beam deflection. For example, the curvature of a blade tenon weld is complex and varies in multiple directions. The matrix array can adjust the incident angle of the sound wave through electronic scanning to ensure that the reflected signal of the defect at any position is captured. Determining the optimal spacing of the finite element mesh and the operating frequency of the phased array ultrasonic sensor is because the mesh spacing needs to be matched with the wavelength of the sound wave to balance the simulation accuracy and efficiency. The operating frequency determines the sound wave resolution (high frequency is suitable for small defects). The combination of the two can accurately reproduce the detailed characteristics of wave field propagation. Selecting the beam bandwidth of the Gaussian pulse, the excitation function, and obtaining the vertical displacement component are to simulate the emission characteristics of real ultrasonic signals. The vertical displacement component can focus the energy changes in the main propagation direction of the sound wave to improve the signal-to-noise ratio. The processing using three-dimensional time-domain wave field analysis, Hilbert transform, and short-time Fourier transform is because the original time-domain waveform contains a large amount of redundant information. Hilbert transform can extract the signal envelope to simplify analysis, while short-time Fourier transform and wavelet packet decomposition can capture dynamic features such as frequency drift and bandwidth expansion. These features are directly related to defect types (such as the abundance of high-frequency components in cracks and the energy dispersion of inclusions), and can be transformed into simulated spectrum curves that distinguish defect types. The simulated spectrum curves can accurately map the interaction law between defect types and ultrasonic waves, improving the stability and reliability of ultrasonic testing.

[0073] In some embodiments of this application, when verifying the defect type based on the relationship between the ultrasonic characteristic spectrum and the simulated spectrum curve, the method includes: when the simulated spectrum curve and the ultrasonic characteristic spectrum... Figure 1If the simulation spectrum curve does not match the ultrasonic characteristic spectrum diagram, the defect type is determined to be incorrect, and the ultrasonic echo signal of the weld to be inspected is reacquired.

[0074] Specifically, the ultrasonic characteristic spectrum is the actual signal characteristic detected. If the simulated spectrum curve and the ultrasonic characteristic spectrum are consistent, it means that the actual defect characteristics match the simulation results, verifying the correctness of the previous defect type determination. If they are inconsistent, it indicates that there may be detection interference (such as poor coupling), model error or unknown defects. In this case, the signal needs to be re-acquired to eliminate interference. The comparison of the dual spectra reduces the risk of misjudging the defect type, ensures the accuracy of the determination results, and improves the reliability and stability of ultrasonic detection.

[0075] In summary, the beneficial effects of this invention are as follows: Traditional ultrasonic testing relies on human experience, which is prone to misjudgment and omission due to differences in personnel skills. By establishing a historical database, a reference basis is provided for the analysis of ultrasonic echo signals, reducing the interference of human subjective bias on the test results and improving the reliability and stability of ultrasonic testing. When identifying defects, the invention combines echo delay, echo intensity, and ultrasonic feature models to obtain dual results and determine the existing defects, realizing multi-dimensional analysis of ultrasonic echo signals. This enables accurate capture of signal features, improves the accuracy of weld defect type identification, and effectively avoids the limitations of a single judgment method. The ultrasonic feature spectrum is obtained through Fourier transform and verified by combining it with the simulated spectrum curve formed by wave field propagation simulation. This constructs a closed-loop process of identification-simulation-verification, enhancing the accuracy of defect type determination in ultrasonic testing. At the same time, the introduction of three-dimensional models and simulation environments allows ultrasonic testing to go beyond the signal itself. Through simulation databases and simulated ultrasonic probe arrays, the characteristics of defects under different ultrasonic propagation conditions are comprehensively analyzed, realizing the transformation of ultrasonic testing from reliance on manual labor to data-driven and intelligent analysis, thus improving the reliability and stability of ultrasonic testing.

[0076] In another preferred embodiment based on the above embodiments, see [reference] Figure 2 As shown, this embodiment provides an ultrasonic-based weld defect detection system for applying the above-described ultrasonic-based weld defect detection method, including:

[0077] The storage and analysis unit is configured to establish a historical database, which includes a historical normal database and a historical defect database, acquire the ultrasonic echo signal of the weld to be inspected, traverse the ultrasonic echo signal in the historical database, and determine the defect reuse strategy or ultrasonic verification strategy based on the traversal results.

[0078] The ultrasonic testing unit is configured to, when an ultrasonic verification strategy is determined, determine the echo delay and echo intensity of the ultrasonic echo signal, determine a first ultrasonic result based on the echo delay and echo intensity, determine a second ultrasonic result based on the ultrasonic echo signal and ultrasonic feature model, and determine whether there is a defect in the weld to be inspected based on the first ultrasonic result and the second ultrasonic result.

[0079] The ultrasonic simulation unit is configured to perform Fourier transform on the ultrasonic echo signal to determine the ultrasonic characteristic spectrum when it is determined that there is a defect in the weld to be inspected; determine the defect type of the weld to be inspected based on the ultrasonic characteristic spectrum; establish a three-dimensional model of the weld to be inspected; build a simulation environment and import the three-dimensional model into the simulation environment; determine the attenuation result based on the three-dimensional model and the metal sample and write it into the simulation database of the simulation environment.

[0080] The ultrasonic verification unit is configured to determine a simulated ultrasonic probe array based on a simulation database, perform wave field propagation simulation based on the simulated ultrasonic probe array, determine the simulated spectrum curve based on the wave field propagation simulation results, and verify the defect type based on the relationship between the ultrasonic characteristic spectrum diagram and the simulated spectrum curve.

[0081] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program goods. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program goods embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0082] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program goods according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0083] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0084] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0085] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the protection scope of the claims of the present invention.

Claims

1. A method for detecting weld defects based on ultrasound, characterized in that, include: A historical database is established, which includes a historical normal database and a historical defect database. The ultrasonic echo signal of the weld to be inspected is obtained, and the ultrasonic echo signal is traversed in the historical database. Based on the traversal results, a defect reuse strategy or an ultrasonic verification strategy is determined. When the ultrasonic verification strategy is determined, the echo delay and echo intensity of the ultrasonic echo signal are determined, and a first ultrasonic result is determined based on the echo delay and echo intensity. A second ultrasonic result is determined based on the ultrasonic echo signal and the ultrasonic feature model. The presence of a defect in the weld to be inspected is determined based on the first ultrasonic result and the second ultrasonic result. When it is determined that there is a defect in the weld to be inspected, the ultrasonic echo signal is subjected to Fourier transform to determine the ultrasonic characteristic spectrum. Based on the ultrasonic characteristic spectrum, the defect type of the weld to be inspected is determined, a three-dimensional model of the weld to be inspected is established, a simulation environment is built and the three-dimensional model is imported into the simulation environment, and the attenuation result is determined based on the three-dimensional model and the metal sample and written into the simulation database of the simulation environment. Based on the simulation database, a simulated ultrasonic probe array is determined. Wave field propagation simulation is performed based on the simulated ultrasonic probe array. The simulated spectrum curve is determined based on the wave field propagation simulation results. The defect type is verified based on the relationship between the ultrasonic characteristic spectrum diagram and the simulated spectrum curve. When determining the echo delay and echo intensity of the ultrasound echo signal, and determining a first ultrasound result based on the echo delay and echo intensity, and determining a second ultrasound result based on the ultrasound echo signal and ultrasound feature model, the process includes: Obtain the standard echo delay range and the standard echo intensity range, and compare the echo delay and echo intensity with the standard echo delay range and the standard echo intensity range, respectively; When the echo delay is within the standard echo delay range and the echo intensity is within the standard echo intensity range, the first ultrasound result is determined as the first output type. If the echo delay is not within the standard echo delay range, or the echo intensity is not within the standard echo intensity range, then the first ultrasound result is determined as the second output type. The sensor dataset and the historical database are divided into a training set and a test set. The ultrasound feature model is determined based on the training set and the test set. The ultrasound echo signal is substituted into the ultrasound feature model to determine the second ultrasound result. The second ultrasound result includes the first output type or the second output type.

2. The ultrasonic-based weld defect detection method according to claim 1, characterized in that, When acquiring the ultrasonic echo signal of the weld to be inspected, traversing the ultrasonic echo signal in the historical database, and determining the defect reuse strategy or ultrasonic verification strategy based on the traversal results, the process includes: If the weld to be inspected and the detection surface are parallel, a straight probe is used to obtain the ultrasonic echo signal. If the weld to be inspected and the detection surface are not parallel, an angled probe is used to obtain the ultrasonic echo signal. When using a straight probe or an angled probe to obtain the ultrasonic echo signal, a coupling agent is first applied between the straight probe or angled probe and the detection surface. The historical database includes historical ultrasonic echo signals, historical ultrasonic sensor operating data, historical simulation spectrum curves, and historical defect types, and the historical ultrasonic echo signals, historical ultrasonic sensor operating data, historical simulation spectrum curves, and historical defect types correspond one-to-one. The ultrasonic echo signal is traversed in the historical defect database to determine the defect reuse strategy or ultrasonic verification strategy.

3. The ultrasonic-based weld defect detection method according to claim 2, characterized in that, When traversing the historical defect database to determine the reuse defect strategy or ultrasonic verification strategy by the ultrasonic echo signal, the process includes: When the historical defect database contains data identical to the ultrasonic echo signal, it is determined to be the reuse defect strategy, and the historical defect type corresponding to the identical data is reused. If no data matching the ultrasonic echo signal exists in the historical defect database, then the ultrasonic verification strategy is determined.

4. The ultrasonic-based weld defect detection method according to claim 3, characterized in that, When determining whether the weld to be inspected has defects based on the first ultrasonic result and the second ultrasonic result, the following steps are included: When the output types of the first ultrasonic result and the second ultrasonic result are both the first output type, it is determined that the weld to be inspected has no defects, and the ultrasonic echo signal is stored in the historical normal database. When the output types of the first ultrasonic result and the second ultrasonic result are both the second output type, or the output types are inconsistent, it is determined that the weld to be inspected has a defect.

5. The ultrasonic-based weld defect detection method according to claim 4, characterized in that, When determining the defect type of the weld to be inspected based on the ultrasonic characteristic spectrum, the following steps are included: Determine the amplitude jumps in the ultrasonic characteristic spectrum, and determine the first amplitude jump and the second amplitude jump, wherein the first amplitude jump is greater than the second amplitude jump; When the amplitude jump is greater than the first amplitude jump, the defect type of the weld to be inspected is determined to be a crack. When the amplitude jump is less than or equal to the first amplitude jump and greater than or equal to the second amplitude jump, the defect type of the weld to be inspected is determined to be porosity. When the amplitude jump is less than the second amplitude jump, the defect type of the weld to be inspected is determined to be slag inclusion.

6. The ultrasonic-based weld defect detection method according to claim 5, characterized in that, The process of establishing a three-dimensional model of the weld to be inspected, building a simulation environment and importing the three-dimensional model into the simulation environment, determining the attenuation results based on the three-dimensional model and metal samples, and writing them into the simulation database of the simulation environment includes: The weld to be inspected is collected segment by segment to determine point cloud data, and isolated points and noise points in the point cloud data are removed based on neighborhood statistics and curvature filtering algorithms. A three-dimensional model of the weld to be inspected is established based on ICP registration and surface reconstruction algorithms using the least squares method. The simulation environment is built using simulation software, and the three-dimensional model is imported. A tetrahedral mesh is generated on the three-dimensional model according to an adaptive mesh generation algorithm. The mesh size is adjusted according to the wavelength of the ultrasonic echo signal. A metal sample of the same material as the weld to be inspected and the detection surface is obtained. The metal sample is subjected to attenuation test using pulse echo, and the attenuation result is determined by frequency domain analysis fitting. The attenuation result includes sound velocity, density, and attenuation parameters. The sound velocity, density, and attenuation parameters are imported into the software database of the simulation software to construct the simulation database.

7. The ultrasonic-based weld defect detection method according to claim 6, characterized in that, When determining a simulated ultrasonic probe array based on the simulation database, performing wave field propagation simulation based on the simulated ultrasonic probe array, and determining the simulated spectrum curve based on the wave field propagation simulation results, the process includes: The arrangement of the phased array ultrasonic sensors is determined based on the curvature of the three-dimensional model, and the array surface is deployed in the three-dimensional model according to the arrangement to determine the simulated ultrasonic probe array. The optimal spacing of the finite element mesh and the operating frequency of the phased array ultrasonic sensors are determined based on the simulation database. In the Gaussian pulse signal of the simulated ultrasonic probe array, the beam bandwidth and excitation function are selected, and the vertical displacement component of the simulated ultrasonic probe array is obtained. Based on the simulation environment, a three-dimensional time-domain wave field analysis is performed to output the original time-domain waveform. The signal envelope is determined by Hilbert transform. Based on short-time Fourier transform and multi-layer wavelet packet decomposition, the frequency drift, bandwidth expansion, and energy distribution characteristics of the signal envelope in each frequency band are extracted to determine the simulated spectrum curve.

8. The ultrasonic-based weld defect detection method according to claim 7, characterized in that, When verifying the defect type based on the relationship between the ultrasonic characteristic spectrum and the simulated spectrum curve, the following steps are included: When the simulated spectrum curve matches the ultrasonic characteristic spectrum, the defect type is determined to be correct, and the defect type and ultrasonic echo signal are stored in the historical defect database. When the simulated spectrum curve is inconsistent with the ultrasonic characteristic spectrum diagram, it is determined that the defect type is incorrect, and the ultrasonic echo signal of the weld to be inspected is reacquired.

9. An ultrasonic-based weld defect detection system, used for applying the ultrasonic-based weld defect detection method as described in any one of claims 1-8, characterized in that, include: The storage and analysis unit is configured to establish a historical database, which includes a historical normal database and a historical defect database, acquire the ultrasonic echo signal of the weld to be inspected, traverse the ultrasonic echo signal in the historical database, and determine a defect reuse strategy or an ultrasonic verification strategy based on the traversal results. An ultrasonic testing unit is configured to, when the ultrasonic verification strategy is determined, determine the echo delay and echo intensity of the ultrasonic echo signal, determine a first ultrasonic result based on the echo delay and echo intensity, determine a second ultrasonic result based on the ultrasonic echo signal and an ultrasonic feature model, and determine whether there is a defect in the weld to be inspected based on the first ultrasonic result and the second ultrasonic result. The ultrasonic simulation unit is configured to, when it is determined that there is a defect in the weld to be inspected, perform Fourier transform on the ultrasonic echo signal to determine the ultrasonic characteristic spectrum, determine the defect type of the weld to be inspected based on the ultrasonic characteristic spectrum, establish a three-dimensional model of the weld to be inspected, build a simulation environment and import the three-dimensional model into the simulation environment, determine the attenuation result based on the three-dimensional model and the metal sample and write it into the simulation database of the simulation environment; The ultrasonic verification unit is configured to determine a simulated ultrasonic probe array based on the simulation database, perform wave field propagation simulation based on the simulated ultrasonic probe array, determine a simulated spectrum curve based on the wave field propagation simulation results, and verify the defect type based on the relationship between the ultrasonic characteristic spectrum diagram and the simulated spectrum curve.

Images