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

Abstract

This application provides a method, apparatus, electronic device, storage medium, and program product for detecting weld penetration depth, relating to the field of computer technology. The method acquires ultrasonic signals from the welding area, identifies weld signal segments from the ultrasonic signals, thus more accurately determining the start and end points of the penetration depth. Then, based on the duration of the weld signal segment and the signal propagation speed, the penetration depth can be precisely measured. Since ultrasonic testing is a non-destructive testing method, it can quickly and accurately detect weld penetration depth, making it suitable for rapid evaluation of welding quality in industrial production.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer, in particular to a weld penetration detection method and device, electronic equipment, storage medium and program product. BACKGROUND

[0002] Weld penetration is an important indicator to measure the quality of the weld, and is a decisive factor of the load bearing capacity of the welded structure. The definition of the weld penetration is the distance of the weld metal extending from the surface of the weld to the joint, excluding the weld reinforcement. If the weld penetration does not meet the requirements, the strength of the weld will be reduced, and the weld will be easily corroded and cracked under the harsh conditions of high temperature or high pressure for a long time, resulting in joint failure.

[0003] At present, the weld penetration is generally detected by the slicing method, that is, a slice is made at the weld, so that the weld penetration can be observed obviously. However, this method is obviously a destructive detection method, which can only be used as verification in testing, and cannot be used for rapid evaluation in industrial production. Therefore, this weld penetration detection method is not suitable for rapid evaluation of the welding quality in industrial production. SUMMARY

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

[0005] In a first aspect, the embodiments of the present application provide a weld penetration detection method, which comprises:

[0006] obtaining an ultrasonic signal of a welding area;

[0007] identifying a weld signal segment from the ultrasonic signal;

[0008] determining the weld penetration according to the time length of the weld signal segment and the propagation speed of the ultrasonic signal.

[0009] In the above implementation process, the ultrasonic signal of the welding area is obtained, and the weld signal segment is identified from the ultrasonic signal, so that the starting point and the ending point of the weld penetration can be determined more accurately. Then, the weld penetration can be accurately measured according to the time length of the weld signal segment and the signal propagation speed. Since the ultrasonic detection method is a non-destructive detection method, the weld penetration can be quickly and accurately detected, and the detection method can be applied to rapid evaluation of the welding quality in industrial production.

[0010] Optionally, the weld signal segment is identified from the ultrasonic signal, comprising:

[0011] identify a signal position corresponding to the welding interface position based on a change in amplitude of the ultrasonic signal in a time domain;

[0012] determine a weld signal segment according to the signal position.

[0013] In the above implementation process, since the ultrasonic signals of the base material and the weld have a difference in signal amplitude, the signals of the weld and the base material can be clearly distinguished by the change in amplitude, and the welding interface position of the weld and the base material can be accurately determined, and the weld signal segment can be accurately identified.

[0014] Optionally, the identifying a signal position corresponding to the welding interface position based on a change in amplitude of the ultrasonic signal in a time domain comprises:

[0015] determining, as the signal position corresponding to the welding interface position, a switching time point at which the amplitude of the ultrasonic signal switches between high and low, wherein the high amplitude refers to an amplitude higher than a signal detection threshold, and the low amplitude refers to an amplitude lower than the signal detection threshold.

[0016] In the above implementation process, since the ultrasonic wave has a relatively obvious jump in signal amplitude when it enters the weld from the base material or enters the base material from the weld, the signal position corresponding to the welding interface position can be quickly determined by finding the time point of the amplitude jump.

[0017] Optionally, the signal detection threshold is determined in the following manner:

[0018] calculating a mean value and a standard deviation of the amplitude of the ultrasonic signal in a sliding window;

[0019] determining the signal detection threshold according to the mean value and the standard deviation.

[0020] In the above implementation process, the signal detection threshold is dynamically calculated by using a sliding window, which can adapt to changes in different welding conditions and material characteristics, and improve the flexibility and accuracy of detection.

[0021] Optionally, the signal detection threshold is determined in the following manner:

[0022] extracting a signal feature of the ultrasonic signal;

[0023] inputting the signal feature into a pre-trained neural network model, and predicting the signal detection threshold by using the neural network model.

[0024] In the above implementation process, the neural network model can combine the correlation between the multi-dimensional signal feature and the threshold value, so that the threshold value is predicted by using the neural network model, which can adapt to different situations of the ultrasonic signal collected under various welding conditions, and improve the accuracy of detection.

[0025] Optionally, identifying the signal position corresponding to the weld junction based on the amplitude change of the ultrasonic signal in the time domain includes:

[0026] The time point when the rate of change of the amplitude of the ultrasonic signal exceeds a set threshold is determined as the signal position corresponding to the welding junction.

[0027] Alternatively, the inflection point of the ultrasonic signal amplitude can be detected, and the time point corresponding to the inflection point can be determined as the signal position corresponding to the welding junction.

[0028] In the above implementation process, the amplitude change rate reflects the degree of change of the signal at each time point. A large change rate means that the signal has changed significantly. The inflection point is the position where the trend of signal change changes. Therefore, both the amplitude change rate and the inflection point can identify some signal positions with large changes in signal amplitude. These signal positions can be used as the signal positions corresponding to the welding junction.

[0029] Optionally, before acquiring the ultrasonic signal of the welding area, the method further includes:

[0030] Acquire an image of the welding area;

[0031] Identify the length and width of the welding area in the image;

[0032] The ultrasonic probe is controlled to scan according to the length and width to obtain ultrasonic signals.

[0033] In the above implementation process, by identifying the length and width of the welding area, the ultrasonic probe can scan according to the length and width, thereby reducing the acquisition of too many interference signals and improving detection efficiency.

[0034] Secondly, embodiments of this application provide a weld penetration depth detection device, the device comprising:

[0035] The signal acquisition module is used to acquire ultrasonic signals from the welding area.

[0036] A signal segment determination module is used to identify weld signal segments from the ultrasonic signals;

[0037] The weld penetration detection module is used to determine the weld penetration based on the duration of the weld signal segment and the propagation speed of the ultrasonic signal.

[0038] Thirdly, embodiments of this application provide an electronic device, including 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 of the method provided in the first aspect above are performed.

[0039] Fourthly, embodiments of this application provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the steps of the method provided in the first aspect above.

[0040] Fifthly, embodiments of this application provide a computer program product, including computer program instructions, which, when read and executed by a processor, perform the steps of the method provided in the first aspect above.

[0041] Other features and advantages of this application will be set forth in the following description and will be apparent in part from the description or may be learned by practicing embodiments of this application. The objectives and other advantages of this application may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings. Attached Figure Description

[0042] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0043] Figure 1 A flowchart illustrating a weld penetration detection method provided in this application embodiment;

[0044] Figure 2 This is a schematic diagram of an ultrasonic testing structure provided in an embodiment of this application;

[0045] Figure 3 A schematic diagram of the grain structure of a base material provided in an embodiment of this application;

[0046] Figure 4 A structural block diagram of a weld penetration detection device provided in this application embodiment;

[0047] Figure 5 This is a schematic diagram of the structure of an electronic device for performing a weld penetration detection method, as provided in an embodiment of this application.

[0048] 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 Implementation

[0049] The technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings.

[0050] It should be noted that the terms "system" and "network" in the embodiments of this invention can be used interchangeably. "Multiple" refers to two or more; therefore, in the embodiments of this invention, "multiple" can also be understood as "at least two". "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / ", unless otherwise specified, generally indicates that the preceding and following related objects have an "or" relationship.

[0051] It should also be noted that all actions involving the acquisition of signals, information, or data in this application are carried out in compliance with the relevant data protection laws and policies of the country where the application is located, and with the authorization granted by the owner of the relevant device.

[0052] Currently, the common method for detecting weld penetration depth is the slice method, which involves creating a slice at the weld joint. This allows for clear observation of the weld penetration depth. However, this is clearly a destructive testing method and can only be used for verification during experiments, not for rapid evaluation in industrial production. Therefore, this penetration depth detection method is not suitable for rapid assessment of welding quality in industrial production.

[0053] To address the aforementioned issues, this application provides a method for detecting weld penetration depth. This method acquires ultrasonic signals from the welding area and identifies weld signal segments from these signals. This allows for more accurate determination of the start and end points of the penetration depth. Then, based on the duration of the weld signal segment and the signal propagation speed, the penetration depth can be precisely measured. Since ultrasonic testing is a non-destructive testing method, it can quickly and accurately detect weld penetration depth. This method is suitable for rapid evaluation of welding quality in industrial production.

[0054] Please refer to Figure 1 , Figure 1 A flowchart of a weld penetration detection method provided in this application embodiment, the method including the following steps:

[0055] Step S110: Acquire the ultrasonic signal of the welding area.

[0056] A weld is a fused area formed at the joint between two or more components during the welding process due to the melting and penetration of the welding material. The weld penetration depth can be understood as the depth to which the base material is melted under the influence of heat during welding; more directly, it refers to the vertical distance from the surface of the base material to the deepest point of the molten zone.

[0057] For weld quality inspection, weld penetration depth is a key indicator. To achieve non-destructive testing of weld penetration depth, this solution utilizes ultrasonic signals from the weld area for detection.

[0058] For example, the welding area can refer to the welding position between the base materials, such as the weld seam area formed after welding two plates. Then, the ultrasonic signal of the welding area can be collected by ultrasonic detection of the welding position using an ultrasonic probe.

[0059] Step S120: Identify the weld signal segment from the ultrasonic signal.

[0060] Since the ultrasonic probe scans the surface of the plate, the ultrasonic signal obtained will contain the signal of the base material. Therefore, it is necessary to identify the base material signal and the weld signal from it. Figure 2 As shown, Figure 2 The diagram shows the welding of the end plate base material and the side plate base material. The ultrasonic probe scans from the top surface, first detecting 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 includes the signals of the side plate base material and the end plate base material. Thus, it is also necessary to identify the weld signal segment, which refers to the signal where the weld is located.

[0061] Step S130: Determine the weld penetration depth based on the duration of the weld signal segment and the propagation speed of the ultrasonic signal.

[0062] Once the weld signal segment is determined, the start and end points of the weld penetration can be identified, and the weld penetration can then be determined based on this signal segment.

[0063] Specifically, the duration of the weld signal segment can be considered as the time it takes for the ultrasonic wave to propagate within the weld area. Therefore, the formula for calculating the weld penetration depth is as follows:

[0064] h=(v*t') / 2, where h represents the penetration depth, v represents the propagation speed of the ultrasonic signal, and t' represents the duration of the weld signal segment.

[0065] In the above process, by acquiring ultrasonic signals from the welding area and identifying weld signal segments from these signals, the starting and ending points of the weld penetration can be determined more accurately. Then, based on the duration of the weld signal segment and the signal propagation speed, the weld penetration can be precisely measured. Since ultrasonic testing is a non-destructive testing method, it can quickly and accurately detect the weld penetration, making it suitable for rapid evaluation of welding quality in industrial production.

[0066] Based on the above embodiments, in the method of identifying weld signal segments from ultrasonic signals, the signal position corresponding to the weld junction can be identified first 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.

[0067] The welding interface refers to the interface between the base material and the weld, which can be the interface between the base material of the side plate and the weld, or between the base material of the end plate and the weld.

[0068] The signal position corresponding to the weld interface can refer to the start and end positions of the weld penetration. Identifying the signal position corresponding to the interface from the ultrasonic signal is equivalent to identifying the base material signal and the weld signal from the ultrasonic signal. Then, the weld signal can be processed to perform penetration detection.

[0069] Because there are significant differences in grain structure between the base metal and the weld, such as the base metal having relatively uniform grain size, morphology, and distribution, and thus... Figure 3 As shown, the weld area has fine and unevenly distributed grains. Therefore, in the ultrasonic signal, the base material area has a uniform structure, continuous acoustic impedance, stable ultrasonic wave propagation, and less scattering, resulting in a higher signal amplitude. However, the weld area, due to the high temperature during the welding process, causes grain refinement or coarsening, forming an uneven structure, which leads to enhanced ultrasonic wave scattering and a lower signal amplitude.

[0070] Based on this discovery, by identifying the amplitude changes of ultrasonic signals in the time domain, such as when the amplitude of an ultrasonic signal changes from a large amplitude to a small amplitude, or from a small amplitude to a large amplitude, it indicates that the signal is entering the weld from the base material or from the weld to the base material. Therefore, the locations with large amplitude changes can be identified from the ultrasonic signal, and these locations can be used as the signal locations corresponding to the weld junction. Then, the signal segment between two adjacent signal locations with a signal amplitude below a certain threshold is used as the weld signal segment.

[0071] In the above implementation process, since the ultrasonic signals of the base material and the weld are different in amplitude, the signals of the weld and the base material can be clearly distinguished by the amplitude change, so that the welding interface position of the weld and the base material can be accurately determined, and the weld signal segment can be accurately identified.

[0072] Based on the above embodiments, the methods for identifying the signal position corresponding to the weld junction based on amplitude changes can include the following:

[0073] Method 1: The switching time point where the amplitude of the ultrasonic signal is switched between high and low is determined as the signal position corresponding to the welding junction. Here, high amplitude means the amplitude is higher than the signal detection threshold, and low amplitude means the amplitude is lower than the signal detection threshold.

[0074] For example, a signal detection threshold is preset. If the signal amplitude is greater than or equal to the signal detection threshold, it is considered to be a signal from the base material. If the signal amplitude is less than the signal detection threshold, it is considered to be a signal from the weld.

[0075] In theory, for the weld area, the signal amplitude is always below the signal detection threshold (or the average signal amplitude is below the signal detection threshold), and the signal corresponding to this area is a continuous signal. For the base material area, the signal amplitude should always be above the signal detection threshold (or the average signal amplitude is above the signal detection threshold). Therefore, the switching time points from high signal (signal amplitude is higher than or equal to the signal detection threshold) to low signal (signal amplitude is lower than the signal detection threshold) and from low signal to high signal can be found from the ultrasonic signal. These switching time points are considered to be the signal positions corresponding to the weld interface.

[0076] For example, if the ultrasonic signal is analyzed starting from the weld surface (t=0), and the ultrasonic probe initially scans the weld area, the signal amplitude will be lower than the signal detection threshold and remain below the signal detection threshold. This indicates that the ultrasonic wave is still propagating within the weld area and the penetration depth increases over 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. This time point t1 is the switching time point for high and low voltage switching.

[0077] Furthermore, considering the existence of heat-affected zones (HAZs), including the side plate HAZ and end plate HAZ, these zones are areas of the base material that are heated but not melted during welding. The grain structure of these areas changes, which is reflected in the ultrasonic signal. The amplitude of this change may fall between the signal amplitudes of the base material and the weld, typically 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 HAZ should also be considered. For example, the signal detection threshold should be lower than the signal amplitude of the HAZ, thus filtering out the signals from the HAZ and improving the accuracy of weld interface identification.

[0078] In the above implementation process, since there is a relatively obvious jump in the signal amplitude when the ultrasonic wave enters the weld from the base material or from the weld to the base material, the signal position corresponding to the weld junction can be quickly determined by finding the time point of the amplitude jump.

[0079] Method 2: The time point when the amplitude change rate of the ultrasonic signal exceeds a set threshold is determined as the signal position corresponding to the welding interface.

[0080] The first 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 degree of change of the signal 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, the position can be considered as the interface between the weld and the base material.

[0081] Method 3: Detect the inflection point of the ultrasonic signal amplitude and determine the time point corresponding to the inflection point as the signal position corresponding to the welding interface.

[0082] The inflection point of the signal amplitude can be obtained by calculating the second derivative of the ultrasonic signal with respect to time. The inflection point is the position where the trend of signal change changes, so the inflection point of the signal amplitude can be determined as the signal position corresponding to the welding interface.

[0083] In some implementations, the three methods described above can be combined. For example, the signal position can be determined using the three methods respectively. In this case, for the position of the starting point of a certain penetration depth, three signal positions may be determined by the three methods. These three signal positions are in principle relatively close to each other. Then, the three signal positions can be averaged, and the average value can be used as the signal position corresponding to the welding interface. The termination point of the penetration depth can also be obtained in the same way.

[0084] Alternatively, for the starting or ending point of the weld penetration, multiple location points may be determined according to methods 2 and 3. Typically, the starting point of the weld penetration corresponds to a significant change point where the signal enters the weld from the base material, i.e., the location where the rate of change suddenly increases and an inflection point appears. In this case, the overlapping point determined by these two methods can be identified as the signal location, such as location a. Alternatively, it can be combined with the signal location determined by method 1 to find the signal location b closest to location a, and then the average of location a and location b can be taken as the final signal location.

[0085] In some implementations, to improve the accuracy of identification, the signal positions determined in the above methods can be verified to eliminate some false positives. For example, for any method, multiple adjacent signal points can be selected near each signal position for verification. For instance, a certain number of points can be selected before and after each signal position to form two verification intervals.

[0086] 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, while 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, while 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 a reliable signal position.

[0087] 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 can be different. If the conditions are met, the signal position a is considered a reliable signal position. If the above conditions are not met, the signal position a is considered an unreliable signal position. In this case, the signal position a can be eliminated, and other position points can be searched again, such as finding a reliable signal position by following the scheme of method 2 or method 3.

[0088] Based on the above embodiments, when determining the signal location using method 1, the signal detection threshold can be a value preset based on practical experience. In other embodiments, the signal detection threshold can also be dynamically determined, such as by calculating the mean amplitude and standard deviation of the ultrasonic signal within the sliding window, and then determining the signal detection threshold based on the mean amplitude and standard deviation.

[0089] The size of the sliding window can be flexibly set according to the actual situation, such as the most recent N sampling points. This allows for the calculation of the mean and standard deviation of the amplitude of these N sampling points. Of course, these N sampling points include parts where the signal amplitude varies significantly. For example, the sliding window can be moved across the ultrasonic signal. When it slides into a window that contains signals with large amplitude variations, such as signals from the base material and the weld area, the mean and standard deviation of the signal amplitude within that sliding window can then be calculated.

[0090] The signal detection threshold can be calculated in the following way:

[0091] ;

[0092] Where X represents the signal detection threshold, Indicates the mean amplitude. This represents an empirical coefficient used to control sensitivity; its value can be selected based on actual needs. It represents the standard deviation.

[0093] In the above implementation process, the signal detection threshold is dynamically calculated by using a sliding window, which can adapt to different welding conditions and material properties, thereby improving the flexibility and accuracy of detection.

[0094] Based on the above embodiments, in the method of dynamically determining the signal detection threshold, the signal features of the ultrasonic signal can also be extracted, and then the signal features are input into a pre-trained neural network model, through which the signal detection threshold is predicted.

[0095] The neural network model can 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 signal features and the optimal threshold.

[0096] During model training, signal features such as signal amplitude, energy, spectral entropy, and zero-crossing rate can be extracted from ultrasonic signals under different welding conditions. The penetration depth can be labeled and input into the model for training. This allows the model to learn to distinguish between base material signals and weld signals through thresholds during training. After training, a well-trained neural network model can be obtained.

[0097] When dynamically determining the signal detection threshold, the signal characteristics of the ultrasonic signal can be extracted, such as the signal amplitude, energy, spectral entropy, and zero-crossing rate 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. The base material signal and the weld signal in the ultrasonic signal can be distinguished by the signal detection threshold, and then the accurate welding interface position can be found.

[0098] In the above implementation process, the neural network model can combine the correlation between multi-dimensional signal features and thresholds. Therefore, using the neural network model for threshold prediction can adapt to the different ultrasonic signals collected under various welding conditions, thereby improving the accuracy of detection.

[0099] In some implementations, the signal detection threshold can be obtained in multiple ways. In practical applications, a final signal detection threshold can be determined by combining the signal detection thresholds obtained in multiple ways. For example, the signal detection threshold 1 can be determined by a sliding window, and the signal detection threshold 2 can be determined by a neural network model. Then, the signal detection threshold 1 and the signal detection threshold 2 can be averaged or weighted to obtain the final signal detection threshold. The final signal detection threshold is then used for subsequent signal location identification.

[0100] Building upon the above embodiments, the method for identifying the signal location corresponding to the weld interface can also incorporate analysis using time-frequency signals. Specifically, wavelet transforms can be applied to the ultrasonic signal in the frequency domain, and mother wavelets of different scales can be used to match signal abrupt changes to identify instantaneous frequency or energy abrupt changes at the interface between the weld and the base material. Furthermore, the distribution of signal energy in the time-frequency plane can be analyzed using the Wigner-Ville distribution to capture the non-stationary characteristics at the interface between the base material and the weld.

[0101] In the method of identifying signal location using wavelet transform, the mother wavelet (such as Daubechies (dbN), suitable for abrupt signals, and Morlet wavelet, suitable for time-frequency localization analysis) can be selected first based on the characteristics of the weld material. Then, the preprocessed ultrasonic signal can be decomposed into wavelet coefficients of different frequency bands (e.g., decomposed to 5-8 layers, covering the main ultrasonic frequency bands). The modulus maxima of the wavelet coefficients at each scale can be calculated. The material discontinuity at the weld interface will lead to a significant increase in the modulus maxima. In this way, the time point corresponding to the interface can be determined by the energy concentration region on the scale-time plane. After determining the time point, the weld depth can be calculated by combining it with the sound velocity.

[0102] In identifying signal location using the Wigner-Ville distribution, the Wigner-Ville distribution (WVD) can be calculated first on the pre-processed ultrasonic signal. Then, a smoothed pseudo-Wigner-Ville distribution (SPWVD) or Choi-Williams distribution is used, and a windowing function is applied to reduce cross-term interference of multi-component signals. In the time-frequency plane, the non-stationary characteristics at the weld interface manifest as instantaneous frequency jumps or abrupt energy changes in specific frequency bands (such as sudden attenuation of high-frequency components). Therefore, the time coordinates of the abrupt change region can be located using thresholding methods or edge detection algorithms (such as the Canny operator), and these time coordinates can be used as the signal location corresponding to the weld interface.

[0103] Based on the above embodiments, in order to improve the accuracy of melt depth detection and reduce the impact of interference signals on the detection results, the original ultrasonic signal can be preprocessed after receiving the ultrasonic signal. The preprocessing can include filtering (such as wavelet threshold denoising, bandpass filtering, etc.) to eliminate environmental noise and circuit interference. The signal amplitude can also be dynamically adjusted according to the acoustic attenuation characteristics (such as exponential attenuation model), which can improve the signal-to-noise ratio and improve the accuracy of subsequent analysis.

[0104] Based on the above embodiments, in order to facilitate the rapid identification of weld signals from ultrasonic signals and reduce interference from excessive base material signals, an image of the welding area can be acquired before acquiring the ultrasonic signal. Then, the length and width of the welding area in the image can be identified, and the ultrasonic probe can be controlled to scan based on the length and width to obtain the ultrasonic signal.

[0105] The welding area can be captured by an industrial camera or CCD camera, and then the captured image is transmitted to an electronic device for further processing. The electronic device can use a neural network model or related image processing algorithms (such as edge detection algorithms) to segment the welding area in the image, so as to extract the welding area from the image.

[0106] After segmenting the welding area, the background area has been removed. Then, the rectangle containing the welding area can be detected. The length and width of the rectangle can be used as the length and width of the welding area. Of course, if the welding area is curved, the rectangle can be segmented, and the length and width of each segment are the length and width of the welding area within that segment.

[0107] Alternatively, the length and width of the weld area can be detected using relevant image processing algorithms or machine learning models. Or, the length and width of the weld area can be calculated by analyzing its contours; this can be achieved using functions in image processing software.

[0108] Once the length and width of the welding area are determined, the scanning range of the ultrasonic probe is essentially determined. At this point, 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 it a little along the length direction and continue scanning according to the width until the entire length is scanned, or scan the entire width of the welding area along the length direction. In this way, an ultrasonic signal can be obtained.

[0109] In other words, the scanning path of the ultrasonic probe can be planned according to the length and width of the welding area. Typically, the probe will scan along the center line of the welding area, covering the entire welding area to improve scanning efficiency.

[0110] An ultrasonic probe can scan the entire welding area. When analyzing the ultrasonic signal later, the weld penetration depth at different scanning positions may be obtained. The penetration depth of the entire weld can include the penetration depth at different positions, or the penetration depth at different positions can be averaged and the average value obtained can be used as the final penetration depth of the weld.

[0111] Once the weld penetration depth is determined, the welding quality can be inspected based on the penetration depth. For example, if the penetration depth is within the set range, the welding quality is qualified; otherwise, the welding quality is unqualified. For unqualified products, staff can be prompted to rework or scrap them.

[0112] The system can output and display the weld penetration depth, as well as the welding quality inspection results, allowing staff to quickly obtain the relevant results for subsequent processing.

[0113] In some implementations, to facilitate viewing by staff, the signal intensity of the ultrasonic signal can be imaged according to color. For example, the signal in the base material area can be displayed in red, representing no penetration depth; the signal in the heat-affected zone can be displayed in yellow; and the signal in the weld area can be displayed in blue, representing penetration depth. In this way, the penetration depth of the weld at different locations can be seen intuitively through the signal color.

[0114] In the above implementation process, by identifying the length and width of the welding area, the ultrasonic probe can scan according to the length and width, thereby reducing the acquisition of too many interference signals and improving detection efficiency.

[0115] Please refer to Figure 4 , Figure 4 This is a structural block diagram of a weld penetration detection device 200 provided in an embodiment of this application. The weld penetration detection device 200 can be a module, program segment, or code on an electronic device. It should be understood that this weld penetration detection device 200 is similar to the one described above. Figure 1 The method implementation corresponds to this and can be executed. Figure 1 The specific functions of the weld penetration detection device 200, which involves various steps in the method embodiment, can be found in the description above. To avoid repetition, detailed descriptions are omitted here.

[0116] Optionally, the weld penetration detection device 200 includes:

[0117] Signal acquisition module 210 is used to acquire ultrasonic signals from the welding area;

[0118] Signal segment determination module 220 is used to identify weld signal segments from the ultrasonic signals;

[0119] The penetration depth detection module 230 is used to determine the penetration depth of the weld based on the duration of the weld signal segment and the propagation speed of the ultrasonic signal.

[0120] Optionally, the signal segment determination module 220 is used to identify the signal position corresponding to the welding junction position based on the amplitude change of the ultrasonic signal in the time domain; and to determine the weld signal segment according to the signal position.

[0121] Optionally, the signal segment determination module 220 is used to determine the switching time point of the amplitude switching in the ultrasonic signal as the signal position corresponding to the welding junction position, wherein high amplitude means the amplitude is higher than the signal detection threshold, and low amplitude means the amplitude is lower than the signal detection threshold.

[0122] Optionally, the signal segment determination module 220 is used to calculate the mean amplitude and standard deviation of the ultrasonic signal within the sliding window; and to determine the signal detection threshold based on the mean amplitude and the standard deviation.

[0123] Optionally, the signal segment determination module 220 is used to extract the 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.

[0124] Optionally, the signal segment determination module 220 is used to determine the time point when the amplitude change rate of the ultrasonic signal exceeds a set threshold as the signal position corresponding to the welding junction; or, to detect the inflection point of the ultrasonic signal amplitude and determine the time point corresponding to the inflection point as the signal position corresponding to the welding junction.

[0125] Optionally, the weld penetration detection device 200 further includes:

[0126] A welding area recognition module is used to acquire 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 width to obtain ultrasonic signals.

[0127] It should be noted that those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the device described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0128] Please refer to Figure 5 , Figure 5This is a schematic diagram of an electronic device for performing a weld penetration detection method according to an embodiment of this 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. The communication bus 340 is used to establish communication between these components. In this embodiment, the communication interface 320 is used for signaling or data communication with other node devices. The memory 330 may be a high-speed RAM or a non-volatile memory, such as at least one disk storage device. Optionally, the memory 330 may also be at least one storage device located remotely from the aforementioned processor. The memory 330 stores computer-readable instructions. When the computer-readable instructions are executed by the processor 310, the electronic device performs the aforementioned... Figure 1 The method and process are shown.

[0129] Understandable. Figure 5 The structure shown is for illustrative purposes only; the electronic device may also include components that are more advanced than those shown. Figure 5 The more or fewer components shown, or having the same Figure 5 The different configurations shown. Figure 5 The components shown can be implemented using hardware, software, or a combination thereof.

[0130] This application provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, performs the following... Figure 1 The method process executed by the electronic device in the illustrated method embodiment.

[0131] 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, and when the program instructions are executed by a computer, the computer can perform the methods provided in the above-described method embodiments, such as including:

[0132] Acquire ultrasonic signals from the welding area;

[0133] The weld signal segment is identified from the ultrasonic signal;

[0134] The weld penetration depth is determined based on the duration of the weld signal segment and the propagation speed of the ultrasonic signal.

[0135] In summary, this application provides a method, apparatus, electronic device, storage medium, and program product for detecting weld penetration depth. By acquiring ultrasonic signals from the welding area and identifying weld signal segments from the ultrasonic signals, the starting and ending points of the penetration depth can be determined more accurately. Then, the penetration depth can be precisely measured based on the duration of the weld signal segment and the signal propagation speed. Since ultrasonic testing is a non-destructive testing method, it can quickly and accurately detect the penetration depth of the weld. This testing method is suitable for rapid evaluation of welding quality in industrial production.

[0136] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some communication interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.

[0137] Furthermore, the units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0138] Furthermore, the functional modules in the various embodiments of this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0139] In this document, relational terms such as first and second are used only to distinguish one entity or operation from another entity or operation, without necessarily requiring or implying any such actual relationship or order between these entities or operations.

[0140] The above description is merely an embodiment of this application and is not intended to limit the scope of protection of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for detecting the penetration depth of a weld, characterized in that, The method includes: Acquire ultrasonic signals from the welding area; The weld signal segment is identified from the ultrasonic signal; The weld penetration depth is determined based on the duration of the weld signal segment and the propagation speed of the ultrasonic signal. The step of identifying the weld signal segment from the ultrasonic signal includes: Based on the amplitude change of the ultrasonic signal in the time domain, the signal position corresponding to the welding junction is identified; Determine the weld signal segment based on the signal position; The method of identifying the signal position corresponding to the weld junction based on the amplitude change of the ultrasonic signal in the time domain includes the following three methods: Method 1: The switching time point of the amplitude of the ultrasonic signal is switched between high and low is determined as the signal position corresponding to the welding junction. Here, high amplitude means the amplitude is higher than the signal detection threshold, and low amplitude means the amplitude is lower than the signal detection threshold. Method 2: The time point when the amplitude change rate of the ultrasonic signal exceeds a set threshold is determined as the signal position corresponding to the welding interface. Method 3: Detect the inflection point of the ultrasonic signal amplitude and determine the time point corresponding to the inflection point of the signal amplitude as the signal position corresponding to the welding interface; After determining the signal position using any of the three methods mentioned above, and before determining the weld signal segment based on the signal position, the method further includes: For each identified signal location, reliability is verified to identify reliable and unreliable signal locations. For unreliable signal locations, select other methods to determine the signal location and repeat the reliability verification steps until a reliable signal location is determined. The steps for verifying the reliability of the signal location include: For each determined signal location, acquire the signal points in the ultrasonic signal that are adjacent to the signal location to form two verification intervals. One of the two verification intervals includes signal points whose time is earlier than the signal location, and the other verification interval includes signal points whose time is later than the signal location. Feature analysis is performed on the signal points within the two verification intervals to obtain the average or standard deviation of the signal intensity for each verification interval. If the average signal strength of the two verification intervals shows an opposite trend, or if the standard deviation of the signal strength in one verification interval is less than a first threshold and the standard deviation of the signal strength in the other verification interval is less than a second threshold, and the first threshold and the second threshold are different, then the signal location is determined to be reliable.

2. The method according to claim 1, characterized in that, The signal detection threshold is determined using the following method: Calculate the mean amplitude and standard deviation of the ultrasonic signal within the sliding window; The signal detection threshold is determined based on the mean amplitude and the standard deviation.

3. The method according to claim 1, characterized in that, The signal detection threshold is determined using the following method: Extract the signal features of the ultrasonic signal; The signal features are input into a pre-trained neural network model, and the signal detection threshold is predicted by the neural network model.

4. The method according to any one of claims 1-3, characterized in that, Before acquiring the ultrasonic signal of the welding area, the method further includes: Acquire an image of the welding area; Identify the length and width of the welding area in the image; The ultrasonic probe is controlled to scan according to the length and width to obtain ultrasonic signals.

5. A weld penetration depth detection device, characterized in that, The device includes: The signal acquisition module is used to acquire ultrasonic signals from the welding area. The signal segment determination module is used to identify the signal position corresponding to the weld junction position based on the amplitude change of the ultrasonic signal in the time domain, and to determine the weld signal segment according to the signal position. The weld penetration detection module is used to determine the weld penetration based on the duration of the weld signal segment and the propagation speed of the ultrasonic signal. The signal segment determination module is specifically used to determine the signal position in the following three ways: Method 1: Determine the signal position corresponding to the welding junction position by the switching time point where the amplitude of the ultrasonic signal switches between high and low, where high amplitude means the amplitude is higher than the signal detection threshold and low amplitude means the amplitude is lower than the signal detection threshold; Method 2: Determine the signal position corresponding to the welding junction position by the time point where the amplitude change rate of the ultrasonic signal exceeds a set threshold; Method 3: Detect the inflection point of the signal amplitude in the ultrasonic signal and determine the time point corresponding to the inflection point of the signal amplitude as the signal position corresponding to the welding junction position. The device further includes: The signal location verification module is used to verify the reliability of each signal location after selecting any one of the three methods mentioned above, and to filter out reliable and unreliable signal locations. For unreliable signal locations, other methods are selected to determine the signal location, and the reliability verification steps are repeated until a reliable signal location is determined. The steps for verifying the reliability of the signal location include: For each determined signal location, acquire signal points adjacent to that signal location in the ultrasonic signal to form two verification intervals. One verification interval includes signal points earlier than the signal location, and the other verification interval includes signal points later than the signal location. Perform feature analysis on the signal points in the two verification intervals to obtain the average or standard deviation of the signal intensity for each verification interval. If the average signal intensity of the two verification intervals shows opposite trends, or if the standard deviation of the signal intensity of one verification interval is less than a first threshold, and the standard deviation of the signal intensity of the other verification interval is less than a second threshold, and the first threshold and the second threshold are different, then the signal location is determined to be reliable.

6. An electronic device, characterized in that, It includes a processor and a memory, the memory storing computer-readable instructions that, when executed by the processor, perform the method as described in any one of claims 1-4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it performs the method as described in any one of claims 1-4.

8. A computer program product, characterized in that, It includes computer program instructions, which, when read and executed by a processor, perform the method as described in any one of claims 1-4.

Images