Weld penetration detection method and device, electronic equipment, storage medium and program product

Abstract

The invention provides a weld penetration detection method and device, electronic equipment, a storage medium and a program product, and relates to the technical field of computers. According to the method, the ultrasonic signal of the welding area is obtained, and the weld signal section is identified from the ultrasonic signal, so that the starting point and the ending point of the fusion depth can be more accurately determined, and then the fusion depth can be accurately measured according to the duration of the weld signal section and the signal propagation speed. Due to the fact that the ultrasonic detection method is nondestructive detection, the penetration depth of the weld joint can be rapidly and accurately detected, and the detection method can be suitable for rapid evaluation of the welding quality in industrial production.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method, device, electronic equipment, storage medium and program product for detecting the penetration depth of a weld. Background Art

[0002] Weld penetration is an important indicator of weld quality and a decisive factor in the load-bearing capacity of welded components. It is defined as the distance that the weld metal extends from the weld surface to the welded joint, excluding the weld excess height. If the weld penetration does not meet the requirements, the weld strength will be reduced. Long-term use under harsh conditions of high temperature or high pressure will easily cause weld corrosion and cracking, leading to joint failure.

[0003] At present, the penetration depth of welds is generally detected by slicing, that is, slicing is made at the weld, so that the penetration depth of the weld can be clearly observed. However, this is obviously a destructive detection method and can only be used as a verification during testing, but not as a rapid assessment during industrial production. Therefore, this penetration depth detection method is not suitable for rapid assessment of welding quality during industrial production. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide a weld penetration detection method, device, electronic device, storage medium and program product to improve the existing penetration detection method which is not suitable for rapid evaluation of welding quality during industrial production.

[0005] In a first aspect, an embodiment of the present application provides a method for detecting penetration of a weld, the method comprising: Acquire ultrasonic signals in the welding area; Identifying a weld signal segment from the ultrasonic signal; The penetration depth of the weld is determined according to the duration of the weld signal segment and the propagation speed of the ultrasonic signal.

[0006] In the above implementation process, by acquiring the ultrasonic signal of the welding area, the weld signal segment is identified from the ultrasonic signal, so that the starting point and the end point of the penetration depth can be determined more accurately, and then the penetration depth can be accurately measured according to the duration of the weld signal segment and the signal propagation speed. Since the ultrasonic detection method is a non-destructive test, the penetration depth of the weld can be detected quickly and accurately, and the detection method can be applied to the rapid evaluation of welding quality in industrial production.

[0007] Optionally, identifying a weld signal segment from the ultrasonic signal comprises: Based on the amplitude change of the ultrasonic signal in the time domain, identifying the signal position corresponding to the welding interface position; A weld signal segment is determined according to the signal position.

[0008] In the above implementation process, since the ultrasonic signals of the base material and the weld are different in signal amplitude, the signals of the weld and the base material can be clearly distinguished through the amplitude change, so the welding boundary position between the weld and the base material can be accurately determined, and then the weld signal segment can be accurately identified.

[0009] Optionally, the identifying the signal position corresponding to the welding interface position based on the amplitude change of the ultrasonic signal in the time domain includes: The switching time point when the amplitude in the ultrasonic signal switches between high and low is determined as the signal position corresponding to the welding junction position, wherein a high amplitude means that the amplitude is higher than the signal detection threshold, and a low amplitude means that the amplitude is lower than the signal detection threshold.

[0010] In the above implementation process, since there will be an obvious jump in the signal amplitude when the ultrasonic wave enters the weld from the base material or from the weld into the base material, the signal position corresponding to the welding interface position can be quickly determined by finding the time point of the amplitude jump.

[0011] Optionally, the signal detection threshold is determined by: Calculate the amplitude mean and standard deviation of the ultrasonic signal within the sliding window; The signal detection threshold is determined according to the amplitude mean and the standard deviation.

[0012] In the above implementation process, the signal detection threshold is dynamically calculated through a sliding window, which can adapt to different welding conditions and changes in material properties and improve the flexibility and accuracy of detection.

[0013] Optionally, the signal detection threshold is determined by: Extracting signal features of the ultrasonic signal; The signal feature is input into a pre-trained neural network model, and the signal detection threshold is predicted by the neural network model.

[0014] In the above implementation process, the neural network model can combine the correlation between multi-dimensional signal characteristics and thresholds. Therefore, threshold prediction through the neural network model can adapt to the situation where ultrasonic signals collected under various welding conditions may be different, thereby improving the accuracy of detection.

[0015] Optionally, the identifying the signal position corresponding to the welding interface position based on the amplitude change of the ultrasonic signal in the time domain includes: The time point at which the amplitude change rate of the signal amplitude in the ultrasonic signal exceeds a set threshold is determined as the signal position corresponding to the welding interface position; Alternatively, the signal amplitude inflection point in the ultrasonic signal is detected, and the time point corresponding to the signal amplitude inflection point is determined as the signal position corresponding to the welding boundary position.

[0016] In the above implementation process, the amplitude change rate reflects the severity of the signal change at each time point. A large change rate means that the signal has changed significantly. The inflection point is the position where the signal change trend changes. Therefore, the amplitude change rate and the inflection point can find some signal positions where the signal amplitude changes greatly. These signal positions can be used as the signal positions corresponding to the welding junction position.

[0017] Optionally, before acquiring the ultrasonic signal of the welding area, the method further includes: Acquire an image of the weld area; identifying a length and a width of a weld area in the image; The ultrasonic probe is controlled to scan according to the length and the width, so as to obtain ultrasonic signals.

[0018] In the above implementation process, by identifying the length and width of the welding area, the ultrasonic probe can be scanned according to the length and width to reduce the collection of excessive interference signals and improve the detection efficiency.

[0019] In a second aspect, an embodiment of the present application provides a device for detecting penetration of a weld, the device comprising: A signal acquisition module, used to acquire ultrasonic signals in the welding area; A signal segment determination module, used to identify a weld signal segment from the ultrasonic signal; The penetration depth detection module is used to determine the penetration depth of the weld according to the duration of the weld signal segment and the propagation speed of the ultrasonic signal.

[0020] In a third aspect, an embodiment of the present application provides an electronic device, comprising a processor and a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the steps in the method provided in the first aspect are performed.

[0021] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps in the method provided in the first aspect are performed.

[0022] In a fifth aspect, an embodiment of the present application provides a computer program product, comprising computer program instructions, which, when read and executed by a processor, execute the steps in the method provided in the first aspect above.

[0023] Other features and advantages of the present application will be described in the following description, and partly become apparent from the description, or be understood by practicing the embodiments of the present application. The purpose and other advantages of the present application can be realized and obtained by the structures specifically pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0025] Figure 1 A flow chart of a method for detecting the penetration depth of a weld provided in an embodiment of the present application; Figure 2 A schematic diagram of the structure of an ultrasonic detection provided in an embodiment of the present application; Figure 3 A schematic diagram of the grain structure of a parent material provided in an embodiment of the present application; Figure 4 A structural block diagram of a weld penetration detection device provided in an embodiment of the present application; Figure 5 A schematic diagram of the structure of an electronic device for performing a method for detecting weld penetration provided in an embodiment of the present application.

[0026] Icons: 200 - weld penetration detection device; 210 - signal acquisition module; 220 - signal segment determination module; 230 - penetration detection module; 310 - processor; 320 - communication interface; 330 - memory; 340 - communication bus. DETAILED DESCRIPTION

[0027] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present application.

[0028] It should be noted that the terms "system" and "network" in the embodiments of the present invention can be used interchangeably. "Multiple" means two or more. In view of this, in the embodiments of the present invention, "multiple" can also be understood as "at least two". "And / or" describes the association relationship of associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / ", unless otherwise specified, generally indicates that the previously associated objects are in an "or" relationship.

[0029] It should also be noted that all actions of acquiring signals, information or data in this application are carried out in compliance with the relevant data protection laws and policies of the country where they are located, and with the authorization given by the owner of the corresponding device.

[0030] At present, the penetration depth of welds is generally detected by slicing, that is, slicing is made at the weld, so that the penetration depth of the weld can be clearly observed. However, this is obviously a destructive detection method and can only be used as a verification during testing, but not as a rapid assessment during industrial production. Therefore, this penetration depth detection method is not suitable for rapid assessment of welding quality during industrial production.

[0031] Based on the above problems, an embodiment of the present application provides a method for detecting the penetration depth of a weld. The method obtains an ultrasonic signal in the welding area and identifies a weld signal segment from the ultrasonic signal, so that the starting point and the end point of the penetration depth can be determined more accurately, and then the penetration depth can be accurately measured according to the duration of the weld signal segment and the signal propagation speed. Since the ultrasonic detection method is a non-destructive test, the penetration depth of the weld can be detected quickly and accurately, and the detection method can be applied to the rapid evaluation of welding quality in industrial production.

[0032] Please refer to Figure 1 , Figure 1 A flow chart of a method for detecting the penetration depth of a weld provided in an embodiment of the present application, the method comprising the following steps: Step S110: Acquire the ultrasonic signal of the welding area.

[0033] A weld is a fusion zone formed at the joint of two or more parts due to the melting and penetration of welding materials during the welding process. The penetration of a weld can be understood as the depth to which the parent material is melted under the action of the heat source during the welding process. More directly, it refers to the vertical distance from the surface of the parent material to the deepest point of the melting zone.

[0034] In order to detect the quality of the weld, the penetration depth of the weld is a key indicator. In order to achieve non-destructive detection of the penetration depth of the weld, this solution performs detection by acquiring ultrasonic signals in the welding area.

[0035] Exemplarily, the welding area may refer to the welding position between the parent materials, such as the weld area formed after welding two plates, and then the welding position is ultrasonically detected by an ultrasonic probe to collect the ultrasonic signal of the welding area.

[0036] Step S120: Identify the weld signal segment from the ultrasonic signal.

[0037] Since the ultrasonic probe scans from the surface of the plate, the ultrasonic signal obtained by scanning will contain the signal of the base material, so it is also necessary to identify the base material signal and the weld signal. Figure 2 As shown, Figure 2 What is shown in the figure is a schematic diagram of the welding between the end plate base material and the side plate base material. The ultrasonic probe scans from the upper surface and first detects the signal of the side plate base material, then the weld, and then the signal of the end plate base material. Therefore, the ultrasonic signal obtained in this way contains the signals of the side plate base material and the end plate base material. Therefore, it is also necessary to identify the weld signal segment therefrom. The weld signal segment refers to the signal where the weld is located.

[0038] Step S130: Determine the penetration depth of the weld according to the duration of the weld signal segment and the propagation speed of the ultrasonic signal.

[0039] After the weld signal segment is determined, the starting point and the ending point of the penetration depth can be identified, and then the penetration depth of the weld can be determined based on this segment of the signal.

[0040] Specifically, the duration of the weld signal segment can be considered as the time for the ultrasonic wave to propagate in the weld area. Therefore, the calculation formula for the penetration depth can be as follows: h=(v*t') / 2, h represents the penetration depth, v represents the propagation speed of the ultrasonic signal, and t' represents the duration of the weld signal segment.

[0041] In the above implementation process, by acquiring the ultrasonic signal of the welding area, the weld signal segment is identified from the ultrasonic signal, so that the starting point and the end point of the penetration depth can be determined more accurately, and then the penetration depth can be accurately measured according to the duration of the weld signal segment and the signal propagation speed. Since the ultrasonic detection method is a non-destructive test, the penetration depth of the weld can be detected quickly and accurately, and the detection method can be applied to the rapid evaluation of welding quality in industrial production.

[0042] Based on the above embodiment, in the method of identifying the weld signal segment from the ultrasonic signal, the signal position corresponding to the welding junction position can be first identified based on the amplitude change of the ultrasonic signal in the time domain, and then the weld signal segment can be determined according to the signal position.

[0043] Among them, the welding interface position refers to the interface position between the base material and the weld, which can refer to the interface position between the side plate base material and the weld, and the interface position between the end plate base material and the weld.

[0044] The signal position corresponding to the welding junction position can refer to the starting position and ending position of the weld penetration. Identifying the signal position corresponding to the junction position from the ultrasonic signal is equivalent to identifying the base material signal and the weld signal from the ultrasonic signal. The weld signal can then be processed for penetration detection.

[0045] Because there are great differences in the grain structure between the parent material and the weld, such as the relatively uniform grain size of the parent material, the shape and distribution are also relatively stable and uniform, such as Figure 3 As shown, the grains in the weld area are small and unevenly distributed. Therefore, in the ultrasonic signal, for the base material area, its structure is uniform, the acoustic impedance is continuous, the ultrasonic propagation is stable, and there is less scattering, so the signal amplitude is high. However, in the weld area, due to the high temperature of the welding process, the grains are refined or coarsened, forming an uneven structure, which will cause the ultrasonic scattering to be enhanced and the signal amplitude is low.

[0046] Based on this discovery, it is possible to identify the amplitude changes of ultrasonic signals in the time domain. For example, when the signal amplitude in an ultrasonic signal changes from a larger amplitude to a smaller amplitude, or from a smaller amplitude to a larger amplitude, this indicates that the signal enters the weld from the base material, or enters the base material from the weld. Therefore, the positions with larger amplitude changes can be identified from the ultrasonic signal, and these positions can be used as the signal positions corresponding to the welding junction positions. Then, the signal segment between two adjacent signal positions with signal amplitudes below a certain threshold can be used as the weld signal segment.

[0047] In the above implementation process, since the ultrasonic signals of the base material and the weld are different in signal amplitude, the signals of the weld and the base material can be clearly distinguished through the amplitude change, so the welding boundary position between the weld and the base material can be accurately determined, and then the weld signal segment can be accurately identified.

[0048] On the basis of the above embodiments, the implementation methods of identifying the signal position corresponding to the welding interface position based on the amplitude change may include the following: Method 1, the switching time point when the amplitude of the ultrasonic signal switches between high and low is determined as the signal position corresponding to the welding junction position, where a high amplitude means that the amplitude is higher than the signal detection threshold, and a low amplitude means that the amplitude is lower than the signal detection threshold.

[0049] For example, a signal detection threshold is preset, and a signal whose amplitude is greater than or equal to the signal detection threshold is considered to be a signal of the base material, and if the signal amplitude is less than the signal detection threshold, it is considered to be a signal of the weld.

[0050] Theoretically, for the weld area, its signal amplitude is lower than the signal detection threshold (or the average signal amplitude is lower than the signal detection threshold), and the signal corresponding to this area is a continuous signal. For the base material area, its signal amplitude should be higher than the signal detection threshold (or the average signal amplitude is higher than the signal detection threshold). Therefore, the switching time point when the signal amplitude changes from a high signal (the signal amplitude is higher than or equal to the signal detection threshold) to a low signal (the signal amplitude is lower than the signal detection threshold) and the switching time point when the signal amplitude changes from a low signal to a high signal can be found from the ultrasonic signal. These switching time points are considered to be the signal positions corresponding to the welding interface.

[0051] For example, when analyzing the ultrasonic signal from the weld surface (t=0), if the ultrasonic probe scans the weld area at the beginning, the signal amplitude will be lower than the signal detection threshold and will continue to be lower than the signal detection threshold, indicating that the ultrasonic wave is still propagating in the weld area and the penetration depth increases with time. When the signal amplitude exceeds the signal detection threshold (time point t1), it is determined that the ultrasonic wave has reached the base material interface. At this time, time point t1 is the switching time point for high and low switching.

[0052] Moreover, considering the existence of heat-affected zones, including the side plate heat-affected zone and the end plate heat-affected zone, the heat-affected zone is the area where the base material is heated but not melted during the welding process. The grain structure of this area will change, which is reflected in the ultrasonic signal. Its amplitude may be between the signal amplitudes of the base material and the weld, usually lower than the base material signal amplitude but higher than the weld signal amplitude. Therefore, when setting the signal detection threshold, the signal amplitude of the heat-affected zone should also be considered. For example, the signal detection threshold should be less than the signal amplitude of the heat-affected zone, so that the signal of the heat-affected zone can be screened out to improve the accuracy of the identification of the welding interface position.

[0053] In the above implementation process, since there will be an obvious jump in the signal amplitude when the ultrasonic wave enters the weld from the base material or from the weld into the base material, the signal position corresponding to the welding interface position can be quickly determined by finding the time point of the amplitude jump.

[0054] Method 2: The time point when the amplitude change rate of the signal amplitude of the ultrasonic signal exceeds the set threshold is determined as the signal position corresponding to the welding interface position.

[0055] Among them, the first-order derivative of the ultrasonic signal with respect to time can be calculated to obtain the signal amplitude change rate. The amplitude change rate reflects the severity of the signal change at each time point. A large change rate means that the signal has changed significantly, such as the position where the high and low signals switch. Therefore, when the amplitude change rate exceeds the set threshold, it is considered that the position is the junction between the weld and the base material.

[0056] Method 3, detecting the signal amplitude inflection point in the ultrasonic signal, and determining the time point corresponding to the signal amplitude inflection point as the signal position corresponding to the welding interface position.

[0057] The signal amplitude inflection point can be obtained by calculating the second-order derivative of the ultrasonic signal with respect to time. The inflection point is the position where the signal change trend changes, so the signal amplitude inflection point can be determined as the signal position corresponding to the welding interface position.

[0058] In some implementations, the above three methods can be combined. For example, the above three methods can be used respectively to determine the signal position. At this time, for the position of a certain starting point of penetration, three signal positions may be determined by three methods. In principle, these three signal positions are relatively close. Then, the three signal positions can be averaged, and the average value can be used as the signal position corresponding to the welding junction position. The end point of penetration can also be obtained in this way.

[0059] Alternatively, for the starting point or ending point of the penetration depth, multiple positions may be determined according to Method 2 and Method 3. Usually, the starting point of the penetration depth corresponds to the significant change point when the signal enters the weld from the base material, that is, the position where the rate of change suddenly increases and an inflection point appears. At this time, the overlapping point determined by these two methods can be found and determined as the signal position, such as position a. Alternatively, it can be combined with the signal position determined by Method 1 to find the signal position b determined by Method 1 that is closest to position a, and then average position a and position b, and the average value obtained is used as the final signal position.

[0060] In some implementations, in order to improve the accuracy of recognition, the signal positions determined in the above manner may also be verified to exclude some misjudged points. For example, for any of the methods, multiple adjacent signal points may be selected near each signal position for verification, such as a certain number of points may be selected before and after each signal position to form two verification intervals.

[0061] For example, for signal position a, some signal points can be taken forward to form verification interval 1, and some signal points can be taken backward to form verification interval 2. Then, signal feature analysis can be performed on the signal points in verification interval 1 and verification interval 2 respectively, such as calculating the average value and standard deviation of the signal strength. If the average value of the signal points in verification interval 1 is greater than or equal to the signal detection threshold, and the average value of the signal points in verification interval 2 is less than the signal detection threshold, or vice versa, the average value of the signal points in verification interval 1 is less than the signal detection threshold, and the average value of the signal points in verification interval 2 is greater than or equal to the signal detection threshold, then signal position a is considered to be a reliable signal position.

[0062] Alternatively, the standard deviation of the signal points in verification interval 1 is less than a threshold 1, and the standard deviation of the signal points in verification interval 2 is less than a threshold 2. These two thresholds may be different. If they are met, signal position a is considered to be a reliable signal position. If the above conditions are not met, signal position a is considered to be an unreliable signal position. At this time, signal position a can be eliminated and other position points can be searched again, such as re-finding a reliable signal position according to method 2 or method 3.

[0063] On the basis of the above embodiment, when the signal position is determined by the above method 1, the signal detection threshold value may be a value preset according to actual experience. In other implementations, the signal detection threshold value may also be determined dynamically, such as calculating the amplitude mean and standard deviation of the ultrasonic signal in the sliding window, and then determining the signal detection threshold value according to the amplitude mean and standard deviation.

[0064] The size of the sliding window can be flexibly set according to the actual situation, such as the latest N sampling points, so that the amplitude mean and standard deviation of these N sampling points can be calculated. Of course, these N sampling points contain parts with obvious signal high and low changes. For example, slide the sliding window on the ultrasonic signal, and slide to the signal containing a large signal amplitude change in the window, such as the base material signal and the weld area signal, and then calculate the mean and standard deviation of the signal amplitude in the sliding window.

[0065] When determining the signal detection threshold, it can be calculated in the following way: ; Where X represents the signal detection threshold, represents the mean amplitude, It represents the empirical coefficient, which is used to control the sensitivity and can be set according to actual needs. Represents standard deviation.

[0066] In the above implementation process, the signal detection threshold is dynamically calculated through a sliding window, which can adapt to different welding conditions and changes in material properties and improve the flexibility and accuracy of detection.

[0067] On the basis of the above-mentioned embodiment, in the method of dynamically determining the signal detection threshold, the signal characteristics of the ultrasonic signal can also be extracted, and then the signal characteristics are input into a pre-trained neural network model, and the signal detection threshold is predicted by the neural network model.

[0068] The neural network model may be a convolutional neural network model or a long short-term memory network model, etc. By training the neural network model, the neural network model can learn the mapping relationship between the signal feature and the optimal threshold.

[0069] During the model training process, the signal characteristics of ultrasonic signals under different welding conditions, such as signal amplitude, energy, spectral entropy, zero-crossing rate, etc., can be extracted, the penetration value can be marked, and the input can be input into the model for training. In this way, the model can learn to distinguish between base material signals and weld signals through thresholds during the training process. After the training is completed, a trained neural network model can be obtained.

[0070] When the signal detection threshold is dynamically determined, the signal characteristics of the ultrasonic signal can be extracted, such as the signal amplitude, energy, spectral entropy, zero-crossing rate and other characteristics mentioned above. The base material signal and the weld signal may have different signal characteristics, so the model can predict the signal detection threshold based on these signal characteristics, so as to distinguish the base material signal and the weld signal in the ultrasonic signal through the signal detection threshold, and then find the accurate welding interface position.

[0071] In the above implementation process, the neural network model can combine the correlation between multi-dimensional signal characteristics and thresholds. Therefore, threshold prediction through the neural network model can adapt to the situation where ultrasonic signals collected under various welding conditions may be different, thereby improving the accuracy of detection.

[0072] In some embodiments, the signal detection threshold can be obtained in a variety of ways. In actual applications, the signal detection thresholds obtained in a variety of ways can be combined to determine a final signal detection threshold. For example, the signal detection threshold 1 is determined by a sliding window, and the signal detection threshold 2 is determined by a neural network model. Then, the signal detection threshold 1 and the signal detection threshold 2 can be averaged, or weighted averaged to obtain the final signal detection threshold. When the signal position is subsequently identified, the final signal detection threshold is used for identification.

[0073] On the basis of the above embodiment, in the above method of identifying the signal position corresponding to the welding interface position, the time-frequency signal can also be combined for analysis. Specifically, the instantaneous frequency or energy mutation at the interface between the weld and the base material can be identified by performing wavelet transformation on the ultrasonic signal in the frequency domain and matching the signal mutation point using mother wavelets of different scales. The distribution of signal energy on the time-frequency plane can also be analyzed by Wigner-Ville distribution to capture the non-stationary characteristics of the interface between the base material and the weld.

[0074] Among them, in the method of identifying the signal position through wavelet transform, the mother wavelet can be selected according to the characteristics of the weld material (such as Daubechies (dbN), which is suitable for mutation signals, and Morlet wavelet is suitable for time-frequency localization analysis); then the pre-processed ultrasonic signal can be decomposed by multi-scale wavelets to generate wavelet coefficients of different frequency bands (such as decomposition to 5~8 layers, covering the main frequency band of ultrasonic waves), and the modulus maximum of each scale wavelet coefficient is calculated. The material discontinuity at the junction of the weld will cause the modulus maximum to increase significantly. In this way, the time point corresponding to the junction position can be determined through the energy accumulation area on the scale-time plane. After determining the time point, the penetration depth can be calculated in combination with the sound velocity.

[0075] In the method of identifying the signal position through Wigner-Ville distribution, the Wigner-Ville distribution (WVD) can be calculated for the preprocessed ultrasonic signal, and then the smooth pseudo Wigner-Ville distribution (SPWVD) or Choi-Williams distribution can be used to reduce the cross-term interference of multi-component signals through the windowing function. On the time-frequency plane, the non-stationary characteristics of the weld junction will appear as instantaneous frequency jumps or energy mutations in a specific frequency band (such as sudden attenuation of high-frequency components), so the time coordinates of the mutation area can be located by the threshold method or edge detection algorithm (such as the Canny operator), and the time coordinates can be used as the signal position corresponding to the welding junction.

[0076] On the basis of the above embodiments, in order to improve the accuracy of penetration detection and reduce the influence of interference signals on the detection results, the original ultrasonic signal can be preprocessed after receiving the ultrasonic signal. The preprocessing may include filtering (such as wavelet threshold denoising, bandpass filtering, etc.) to eliminate environmental noise and circuit interference. The signal amplitude may also be dynamically adjusted according to the sound wave attenuation characteristics (such as exponential attenuation model). This can improve the signal-to-noise ratio and the accuracy of subsequent analysis.

[0077] On the basis of the above embodiment, in order to facilitate the rapid identification of weld signals from ultrasonic signals and reduce the interference of excessive base material signals, it is also possible to obtain an image of the welding area before obtaining the ultrasonic signal, and then identify the length and width of the welding area in the image, and then control the ultrasonic probe to scan according to the length and width to scan and obtain the ultrasonic signal.

[0078] Among them, the image of the welding area can be collected by an industrial camera or a CCD camera, and then the collected image can be transmitted to an electronic device for subsequent processing. The electronic device can use a neural network model or a related image processing algorithm (such as an edge detection algorithm) to segment the welding area in the image to segment the welding area from the image.

[0079] After segmenting the welding area, it is equivalent to removing the background area. Then the rectangular frame where the welding area is located can be detected. The length and width of the rectangular frame can be used as the length and width of the welding area. Of course, if the welding area is in the form of a curve, the rectangular frame can be segmented, and the length and width of each rectangular frame are the length and width of the welding area in the rectangular frame.

[0080] Alternatively, the length and width of the welding area may be detected by using relevant image processing algorithms or machine learning models, etc. Alternatively, the length and width of the welding area may be calculated by analyzing the contour of the welding area, which may be achieved using functions in image processing software.

[0081] After determining the length and width of the welding area, it is equivalent to determining the scanning range of the ultrasonic probe. At this time, the electronic device can control the ultrasonic probe to scan according to the length and width. For example, first control the ultrasonic probe to scan according to the width, and then move a little in the length direction, and continue to scan according to the width until the entire length is scanned, or scan the entire width of the welding area in the length direction, so that an ultrasonic signal can be obtained.

[0082] That is, the scanning path of the ultrasonic probe can be planned according to the length and width of the welding area. Usually, the probe will scan along the center line of the welding area and cover the entire welding area at the same time to improve the scanning efficiency.

[0083] The ultrasonic probe can scan the entire welding area. When the ultrasonic signal is subsequently analyzed, the penetration depth of the weld at different scanning positions may be obtained. The penetration depth of the entire weld may include the penetration depths at different positions, or the penetration depths at different positions may be averaged, and the obtained mean value is used as the final penetration depth of the weld.

[0084] After determining the penetration depth of the weld, the welding quality can be tested based on the penetration depth. For example, if the penetration depth is within the set range, it means that the welding quality is qualified. Otherwise, it means that the welding quality is unqualified. For unqualified products, the staff can be prompted to return them for repair or scrap them.

[0085] The detected penetration depth of the weld can be output for display, and the welding quality test results can also be output and displayed, so that the staff can quickly obtain the corresponding results for subsequent processing.

[0086] In some embodiments, in order to facilitate viewing by staff, the signal strength of the ultrasonic signal can also be imaged according to color. For example, the signal for the base material area can be red, indicating no penetration, the signal for the heat-affected zone can be yellow, and the signal for the weld area can be blue, indicating penetration. In this way, the penetration of the weld at different positions can be intuitively seen through the signal color.

[0087] In the above implementation process, by identifying the length and width of the welding area, the ultrasonic probe can be scanned according to the length and width to reduce the collection of excessive interference signals and improve the detection efficiency.

[0088] Please refer to Figure 4 , Figure 4 1 is a structural block diagram of a weld penetration detection device 200 provided in an embodiment of the present application. The weld penetration detection device 200 may be a module, program segment or code on an electronic device. It should be understood that the weld penetration detection device 200 is similar to the above-mentioned Figure 1 The method embodiment corresponds to and can be executed Figure 1 The various steps involved in the method embodiment and the specific functions of the weld penetration detection device 200 can be found in the above description. To avoid repetition, the detailed description is appropriately omitted here.

[0089] Optionally, the weld penetration detection device 200 comprises: A signal acquisition module 210 is used to acquire ultrasonic signals in a welding area; A signal segment determination module 220, configured to identify a weld signal segment from the ultrasonic signal; The penetration detection module 230 is used to determine the penetration of the weld according to the duration of the weld signal segment and the propagation speed of the ultrasonic signal.

[0090] Optionally, the signal segment determination module 220 is used to identify the signal position corresponding to the welding interface position based on the amplitude change of the ultrasonic signal in the time domain; and determine the weld signal segment according to the signal position.

[0091] Optionally, the signal segment determination module 220 is used to determine the switching time point when the amplitude in the ultrasonic signal switches between high and low as the signal position corresponding to the welding junction position, wherein a high amplitude means that the amplitude is higher than a signal detection threshold, and a low amplitude means that the amplitude is lower than the signal detection threshold.

[0092] Optionally, the signal segment determination module 220 is used to calculate the amplitude mean and standard deviation of the ultrasonic signal within the sliding window; and determine the signal detection threshold according to the amplitude mean and the standard deviation.

[0093] Optionally, the signal segment determination module 220 is used to extract signal features of the ultrasonic signal; input the signal features into a pre-trained neural network model, and predict the signal detection threshold through the neural network model.

[0094] Optionally, the signal segment determination module 220 is used to determine the time point when the amplitude change rate of the signal amplitude in the ultrasonic signal exceeds a set threshold as the signal position corresponding to the welding junction position; or, to detect the signal amplitude inflection point in the ultrasonic signal, and determine the time point corresponding to the signal amplitude inflection point as the signal position corresponding to the welding junction position.

[0095] Optionally, the weld penetration detection device 200 further includes: The welding area recognition module is used to obtain an image of the welding area; identify the length and width of the welding area in the image; and control the ultrasonic probe to scan according to the length and the width to scan and obtain ultrasonic signals.

[0096] It should be noted that those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0097] Please refer to Figure 5 , Figure 5 A schematic diagram of the structure of an electronic device for performing a method for detecting the penetration depth of a weld provided in an embodiment of the present application, the electronic device may include: at least one processor 310, such as a CPU, at least one communication interface 320, at least one memory 330 and at least one communication bus 340. Among them, the communication bus 340 is used to realize the connection and communication between these components. Among them, the communication interface 320 of the device in the embodiment of the present application is used to communicate signals or data with other node devices. The memory 330 can be a high-speed RAM memory, or it can be a non-volatile memory (non-volatile memory), such as at least one disk storage. The memory 330 can optionally also be at least one storage device located away from the aforementioned processor. Computer-readable instructions are stored in the memory 330. When the computer-readable instructions are executed by the processor 310, the electronic device executes the above-mentioned Figure 1 The method process is shown.

[0098] Understandably, Figure 5 The structure shown is for illustration only, and the electronic device may also include Figure 5 More or fewer components as shown, or with Figure 5 Different configurations are shown. Figure 5 Each component shown in the figure can be implemented by hardware, software or a combination thereof.

[0099] The present application embodiment provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the following is performed: Figure 1The method process in the method embodiment shown is executed by the electronic device.

[0100] This embodiment discloses a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions. When the program instructions are executed by a computer, the computer can perform the methods provided by the above method embodiments, for example, including: Acquire ultrasonic signals in the welding area; Identifying a weld signal segment from the ultrasonic signal; The penetration depth of the weld is determined according to the duration of the weld signal segment and the propagation speed of the ultrasonic signal.

[0101] In summary, the embodiments of the present application provide a method, device, electronic device, storage medium and program product for detecting the penetration depth of a weld. By acquiring an ultrasonic signal in a welding area and identifying a weld signal segment from the ultrasonic signal, the starting point and the end point of the penetration depth can be determined more accurately. Then, the penetration depth can be accurately measured according to the duration of the weld signal segment and the signal propagation speed. Since the ultrasonic detection method is a non-destructive test, the penetration depth of a weld can be detected quickly and accurately. The detection method can be applied to the rapid evaluation of welding quality in industrial production.

[0102] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0103] In addition, the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0104] Furthermore, the functional modules in the various embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

[0105] In this document, relational terms such as first and second, etc. are used merely to distinguish one entity or operation from another entity or operation, but do not necessarily require or imply any such actual relationship or order between these entities or operations.

[0106] The above description is only an embodiment of the present application and is not intended to limit the protection scope of the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for detecting the penetration depth of a weld, characterized in that: The method comprises: Acquire ultrasonic signals in the welding area; Identifying a weld signal segment from the ultrasonic signal; Determining the penetration depth of the weld according to the duration of the weld signal segment and the propagation speed of the ultrasonic signal; Wherein, identifying the weld signal segment from the ultrasonic signal includes: Based on the amplitude change of the ultrasonic signal in the time domain, identifying the signal position corresponding to the welding interface position; A weld signal segment is determined according to the signal position.

2. The method according to claim 1, characterized in that The step of identifying the signal position corresponding to the welding interface position based on the amplitude change of the ultrasonic signal in the time domain includes: The switching time point when the amplitude in the ultrasonic signal switches between high and low is determined as the signal position corresponding to the welding junction position, wherein a high amplitude means that the amplitude is higher than the signal detection threshold, and a low amplitude means that the amplitude is lower than the signal detection threshold.

3. The method according to claim 2, characterized in that The signal detection threshold is determined by: Calculate the amplitude mean and standard deviation of the ultrasonic signal within the sliding window; The signal detection threshold is determined according to the amplitude mean and the standard deviation.

4. The method according to claim 2, characterized in that: The signal detection threshold is determined by: Extracting signal features of the ultrasonic signal; The signal feature is input into a pre-trained neural network model, and the signal detection threshold is predicted by the neural network model.

5. The method according to claim 1, characterized in that The step of identifying the signal position corresponding to the welding interface position based on the amplitude change of the ultrasonic signal in the time domain includes: The time point at which the amplitude change rate of the signal amplitude in the ultrasonic signal exceeds a set threshold is determined as the signal position corresponding to the welding interface position; Alternatively, the signal amplitude inflection point in the ultrasonic signal is detected, and the time point corresponding to the signal amplitude inflection point is determined as the signal position corresponding to the welding boundary position.

6. The method according to any one of claims 1 to 5, characterized in that: Before obtaining the ultrasonic signal of the welding area, the method further includes: Acquire an image of the weld area; identifying a length and a width of a weld area in the image; The ultrasonic probe is controlled to scan according to the length and the width, so as to obtain ultrasonic signals.

7. A device for detecting the penetration depth of a weld, characterized in that: The device comprises: A signal acquisition module, used to acquire ultrasonic signals in the welding area; A signal segment determination module, used to identify the signal position corresponding to the welding interface position based on the amplitude change of the ultrasonic signal in the time domain, and determine the weld signal segment according to the signal position; The penetration depth detection module is used to determine the penetration depth of the weld according to the duration of the weld signal segment and the propagation speed of the ultrasonic signal.

8. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, the method according to any one of claims 1 to 6 is executed.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is executed.

10. A computer program product, characterized in that The method comprises computer program instructions, and when the computer program instructions are read and executed by a processor, the method according to any one of claims 1 to 6 is executed.

Images