Intelligent welding seam detection method and system based on ultrasonic waves

Abstract

The invention relates to an ultrasonic-based intelligent welding seam detection method and system, and relates to the field of welding seam monitoring, the method comprises the steps that current data of welding equipment during welding, a vibration change diagram of a workpiece and video information during welding are obtained, the video information comprises first video information and second video information, and after a welding seam is formed, the welding seam is detected; controlling the detection equipment to move along the welding seam and collect ultrasonic data of the welding seam in real time, so that the electronic equipment obtains the ultrasonic data, determines the fitting degree of the welding seam based on the first video information, the second video information and the ultrasonic data, judges whether the welding seam is qualified or not based on the current data, the vibration change diagram and the fitting degree, and if not, judges whether the welding seam is qualified. And if so, controlling the detection equipment to mark the workpiece. The method has the effects of monitoring the defects in the welding seam in time and improving the production efficiency of the mobile phone shell.

Description

Technical Field

[0001] This application relates to the field of weld monitoring, and in particular to an ultrasonic-based intelligent weld detection method and system. Background Technology

[0002] As people's living standards continue to improve, mobile phones have become an integral part of people's lives. The mobile phone industry is upgrading at a faster pace, and the production of mobile phone casings will also increase accordingly.

[0003] During the manufacturing process of mobile phone casings, the top and bottom sides of the workpiece are seamlessly welded simultaneously using friction stir welding. The existing inspection method is to sample and inspect the finished mobile phone casings, and most of the inspection focuses on the appearance of the weld. If multiple inspections fail, it may lead to the loss of a large number of workpieces and make it impossible to detect defects inside the weld in time, thus reducing the production efficiency of mobile phone casings. Summary of the Invention

[0004] In order to detect defects inside the weld in a timely manner and improve the production efficiency of mobile phone casings, this application provides an ultrasonic-based intelligent weld inspection method and system.

[0005] Firstly, this application provides an ultrasonic-based intelligent weld inspection method, employing the following technical solution: An ultrasonic-based intelligent weld inspection method includes: The welding equipment's current data, the workpiece's vibration variation diagram, and the welding video information are acquired during welding. The video information includes first video information and second video information. Once the weld is formed, the control detection equipment moves along the weld and collects the ultrasonic data of the weld in real time, so that the electronic equipment can acquire the ultrasonic data. The fit of the weld is determined based on the first video information, the second video information, and the ultrasonic data. The weld seam is judged to be qualified based on the current data, vibration change diagram and fit. If the workpiece fails to meet the requirements, the testing equipment is controlled to mark it.

[0006] By adopting the above technical solution, current data of the welding equipment, vibration change diagram of the workpiece, and video information during welding are obtained. During welding, the welding equipment is powered on and operates, and there is current inside. When the welding equipment rotates and contacts the workpiece, it also causes the workpiece to vibrate accordingly, causing the contact surfaces of the two workpieces to melt and fuse together, thus completing friction welding. After the weld is formed, the detection equipment is controlled to move along the weld and collect ultrasonic data of the weld in real time, so that the electronic device can acquire ultrasonic data. Based on the first video information, the second video information, and the ultrasonic data, the fit of the weld is determined. The fit reflects whether the outside and inside of the workpiece are in contact. The magnitude of the current affects whether the welding equipment can operate normally. If the vibration of the workpiece is too severe, it will cause the weld to deviate when the welding equipment rotates and contacts the workpiece, or even cause the workpiece to fly away and fail to complete the welding. Therefore, the weld is judged to be qualified based on the current data, vibration change diagram, and fit. If it is unqualified, the detection equipment is controlled to mark the workpiece, so as to promptly monitor the defects inside the weld and distinguish unqualified workpieces, thereby improving the production efficiency of mobile phone shells.

[0007] In another possible implementation, the first video information corresponds to the upper side of the workpiece being welded, and the second video information corresponds to the lower side of the workpiece being welded. The step of determining the weld fit based on the first video information, the second video information, and ultrasonic data includes: Weld seam identification is performed on the first video information and the second video information respectively to obtain a first identification result and a second identification result; Edge detection is performed based on the first and second identification results to determine the first range on the upper side of the weld and the second range on the lower side of the weld. Determine the similarity between the first range and the second range, and determine the first area of ​​the first range and the second area of ​​the second range; Determine the first difference between the first area and the second area; The weld fit is determined based on the similarity, the first difference, and the ultrasonic data.

[0008] In another possible implementation, determining the weld fit based on the similarity, the first difference, and the ultrasonic data includes: Acquire the echo signal of the ultrasonic data, and determine the amplitude variation graph and sound velocity variation graph of the echo signal; Based on the amplitude change graph, a first percentage of amplitudes exceeding a preset amplitude range is determined, and based on the sound speed change graph, a second percentage of sound speeds exceeding a preset sound speed range is determined. A first score is determined based on the similarity, difference, first proportion, second proportion, and their respective first coefficients. The first score characterizes the fit of the weld.

[0009] In another possible implementation, determining whether the weld is qualified based on the current data, vibration variation diagram, and fit includes: The number of maximum amplitudes and vibration periods are determined based on the vibration variation diagram. Based on the current data, the maximum current and the minimum current are determined, and a second difference between the maximum current and the minimum current is determined. The second score is determined based on the maximum amplitude, quantity, second difference, fit, and their respective second coefficients. The weld is judged to be qualified based on the second score.

[0010] In another possible implementation, the method further includes: Obtain the point cloud data of the marked workpiece; Crack identification is performed on the point cloud data to obtain crack identification results; Based on the crack identification results, determine the maximum length of the crack and the total length of all cracks; The degree of abnormality of the weld is determined based on the maximum length and the total length; The marked workpieces are marked differently based on the degree of abnormality.

[0011] In another possible implementation, the method further includes: Based on the first video information and the second video information, the upper width and lower width of the weld at each cross section along the welding direction of the workpiece are determined respectively. The maximum height of each cross-section is determined based on the ultrasonic data; The weld section mass score for each section is determined based on the upper width of the weld, the lower width of the weld, and the maximum height. The second score is adjusted based on the weld section quality score.

[0012] In another possible implementation, the number of marks and the total number of welds within a preset time period are determined; Determine the average score of the second score for all marked workpieces; A welding quality report is output to the management office, which includes the number of markings, the total number of welds, and the average score.

[0013] Secondly, this application provides an ultrasonic-based intelligent weld inspection system, which adopts the following technical solution: An ultrasonic-based intelligent weld inspection system includes: The first acquisition module is used to acquire current data of the welding equipment, vibration change diagram of the workpiece, and video information during welding. The video information includes first video information and second video information. The control module is used to control the detection equipment to move along the weld and collect the ultrasonic data of the weld in real time after the weld is formed, so that the electronic equipment can acquire the ultrasonic data. The first determining module is used to determine the fit of the weld seam based on the first video information, the second video information, and the ultrasonic data. The first judgment module is used to determine whether the weld is qualified based on the current data, vibration change diagram and fit. The first marking module is used to control the detection device to mark the workpiece if it fails to meet the requirements.

[0014] By adopting the above technical solution, the first acquisition module acquires the current data of the welding equipment, the vibration change diagram of the workpiece, and the video information during welding. During welding, the welding equipment is powered on and operates, and there is current inside. When the welding equipment rotates and contacts the workpiece, it also causes the workpiece to vibrate accordingly, causing the contact surfaces of the two workpieces to melt and fuse together, thereby completing friction welding. After the weld is formed, the control module controls the detection device to move along the weld and collect the ultrasonic data of the weld in real time, so that the electronic device can acquire the ultrasonic data. The first determination module determines the fit of the weld based on the first video information, the second video information, and the ultrasonic data. The fit reflects whether the outside and inside of the workpiece are in contact. The magnitude of the current affects whether the welding equipment can operate normally. If the vibration of the workpiece is too severe, it will cause the weld to deviate when the welding equipment rotates and contacts the workpiece, or even cause the workpiece to fly away and make welding impossible. Therefore, the first judgment module judges whether the weld is qualified based on the current data, the vibration change diagram, and the fit. If it is unqualified, the first marking module controls the detection device to mark the workpiece, thereby enabling timely monitoring of defects inside the weld and distinguishing unqualified workpieces, improving the production efficiency of mobile phone shells.

[0015] In another possible implementation, the first video information corresponds to the upper side of the workpiece being welded, and the second video information corresponds to the lower side of the workpiece being welded. When determining the weld fit based on the first video information, the second video information, and the ultrasonic data, the first determining module is specifically used for: Weld seam identification is performed on the first video information and the second video information respectively to obtain a first identification result and a second identification result; Edge detection is performed based on the first and second identification results to determine the first range on the upper side of the weld and the second range on the lower side of the weld. Determine the similarity between the first range and the second range, and determine the first area of ​​the first range and the second area of ​​the second range; Determine the first difference between the first area and the second area; The weld fit is determined based on the similarity, the first difference, and the ultrasonic data.

[0016] In another possible implementation, when the first determining module determines the weld fit based on the similarity, the first difference, and the ultrasonic data, it is specifically used for: Acquire the echo signal of the ultrasonic data, and determine the amplitude variation graph and sound velocity variation graph of the echo signal; Based on the amplitude change graph, a first percentage of amplitudes exceeding a preset amplitude range is determined, and based on the sound speed change graph, a second percentage of sound speeds exceeding a preset sound speed range is determined. A first score is determined based on the similarity, difference, first proportion, second proportion, and their respective first coefficients. The first score characterizes the fit of the weld.

[0017] In another possible implementation, when the first judgment module determines whether the weld is qualified based on the current data, vibration change diagram, and fit, it is specifically used for: The number of maximum amplitudes and vibration periods are determined based on the vibration variation diagram. Based on the current data, the maximum current and the minimum current are determined, and a second difference between the maximum current and the minimum current is determined. The second score is determined based on the maximum amplitude, quantity, second difference, fit, and their respective second coefficients. The weld is judged to be qualified based on the second score.

[0018] In another possible implementation, the system further includes: The second acquisition module is used to acquire the point cloud data of the marked workpiece; The identification module is used to identify cracks in the point cloud data and obtain crack identification results. The second determining module is used to determine the maximum length of the crack and the total length of all cracks based on the crack identification results. The third determining module is used to determine the degree of abnormality of the weld based on the maximum length and the total length; The second marking module is used to mark the marked workpiece differently based on the degree of abnormality.

[0019] In another possible implementation, the system further includes: The fourth determining module is used to determine the upper width and lower width of the weld at each cross section of the workpiece along the welding direction based on the first video information and the second video information, respectively. The fifth determining module is used to determine the maximum height of each cross-section based on the ultrasonic data; The sixth determining module is used to determine the weld section mass score of each section based on the upper side width, lower side width and maximum height of the weld. An adjustment module is used to adjust the second score based on the weld section quality score.

[0020] In another possible implementation, the system further includes: The seventh module is used to determine the number of marks and the total number of welds within a preset time period; The eighth determining module is used to determine the average score of the second score for all marked workpieces; The output module is used to output a welding quality report to the management office. The welding quality report includes the number of marks, the total number of welds, and the average score.

[0021] Thirdly, this application provides an electronic device that adopts the following technical solution: An electronic device comprising: At least one processor; Memory; At least one application, wherein the application is stored in memory and configured to be executed by at least one processor, the at least one configuration being for: executing an ultrasonic-based intelligent weld detection method as shown in any possible implementation of the first aspect.

[0022] Fourthly, this application provides a computer-readable storage medium, which adopts the following technical solution: A computer-readable storage medium, when the computer program is executed in a computer, causes the computer to perform the ultrasonic-based intelligent weld inspection method described in any one of the first aspects.

[0023] In summary, this application includes at least one of the following beneficial technical effects: The system acquires current data from the welding equipment, vibration patterns of the workpiece, and video information during welding. During welding, the equipment is powered on and operates, generating internal current. As the equipment rotates and contacts the workpiece, it causes the workpiece to vibrate, melting and fusing the contact surfaces of the two workpieces together, thus completing friction welding. Once the weld is formed, the detection equipment moves along the weld and collects ultrasonic data in real time, allowing the electronic device to acquire this data. Based on the first and second video information and the ultrasonic data, the weld fit is determined. The fit reflects whether the external and internal surfaces of the workpiece are properly aligned at the weld joint. The magnitude of the current affects the normal operation of the welding equipment. If the workpiece vibration is too severe, it can cause weld deviation or even cause the workpiece to bounce away, preventing welding from being completed. Therefore, the system judges the weld's quality based on current data, vibration patterns, and fit. If the weld is unqualified, the detection equipment marks the workpiece, enabling timely monitoring of internal weld defects and differentiation of unqualified workpieces, thus improving the production efficiency of mobile phone casings. Attached Figure Description

[0024] Figure 1 This is a schematic flowchart of an ultrasonic-based intelligent weld inspection method according to an embodiment of this application.

[0025] Figure 2 This is a schematic diagram of the structure of an ultrasonic-based intelligent weld inspection system according to an embodiment of this application.

[0026] Figure 3 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0027] The present application will be further described in detail below with reference to the accompanying drawings.

[0028] After reading this specification, those skilled in the art may make modifications to this embodiment without contributing any inventive step, but such modifications are protected by patent law as long as they fall within the scope of the claims of this application.

[0029] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0030] Furthermore, the term "and / or" in this article is merely a description of 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, or B existing alone. Additionally, the character " / " in this article, unless otherwise specified, generally indicates that the preceding and following related objects have an "or" relationship.

[0031] The embodiments of this application will now be described in further detail with reference to the accompanying drawings.

[0032] This application provides an ultrasonic-based intelligent weld inspection method, executed by an electronic device. This electronic device can be a server or a terminal device. The server can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smartphone, tablet, laptop, desktop computer, etc., but is not limited to these. The terminal device and the server can be directly or indirectly connected via wired or wireless communication. This application does not impose any limitations on this. Figure 1 As shown, the method includes steps S101, S102, S103, S104, and S105, wherein, S101, acquires current data of the welding equipment, vibration change diagram of the workpiece, and video information during welding.

[0033] The video information includes first video information and second video information.

[0034] In the embodiments of this application, the welding equipment is powered on and operates during welding, and there will be current inside. The magnitude of the current affects whether the welding equipment can operate normally. Therefore, a Hall current sensor can be installed on the outer wall of the welding equipment. The Hall current sensor is connected to an electronic device via wired or wireless connection. The electronic device acquires the current data of the welding equipment during welding, and the current data reflects the operating status of the welding equipment.

[0035] The welding equipment rotates and passes over the workpiece, simultaneously performing friction stir welding on the upper and lower sides of the workpiece to melt and fuse the contact surfaces of the two workpieces together, thus completing the friction welding. For welding to be successful, the workpiece must be fixed in place to maintain high precision. If the workpiece is too loose, deviations in the weld may occur when the welding equipment rotates and contacts it, or the workpiece may even bounce off, preventing the welding from being completed. Therefore, vibration sensors can be installed on the side wall of the workpiece placement table, allowing the sensors to contact the workpiece. The vibration sensors are wirelessly or wired connected to electronic equipment, which can then acquire vibration change maps of the workpiece during welding. These maps reflect whether the workpiece has become loose during the welding process.

[0036] The first and second cameras can be installed in advance by the staff on the side wall of the workpiece table. Both cameras are connected to the electronic equipment by wire or wireless means. The first camera collects the first video information above the workpiece, and the second camera collects the second video information below the workpiece. The electronic equipment then obtains the video information during welding.

[0037] S102, After the weld is formed, the control detection equipment moves along the weld and collects the ultrasonic data of the weld in real time, so that the electronic equipment can acquire the ultrasonic data.

[0038] In the embodiments of this application, after welding is completed, a weld seam is formed at the welded joint of the workpiece. After the weld seam is formed, the detection equipment is controlled to move along the weld seam and collect the ultrasonic data of the weld seam in real time. The detection equipment can be an ultrasonic flaw detector, which is controlled by a robot arm and moves according to a preset weld seam route. The robot arm is wired to the electronic equipment. When the welding is detected to be completed, the robot arm controls the ultrasonic flaw detector to move. The ultrasonic flaw detector is wirelessly connected to the electronic equipment so that the electronic equipment can obtain the ultrasonic data at the weld seam.

[0039] S103, determine the fit of the weld seam based on the first video information, the second video information and the ultrasonic data.

[0040] In the embodiments of this application, the electronic device determines the fit of the weld seam based on the first video information, the second video information, and the ultrasonic data. The fit reflects whether the weld joint of the workpiece fits.

[0041] S104 determines whether the weld is qualified based on current data, vibration change diagram, and fit.

[0042] In the embodiments of this application, current data characterizes whether the current is stable when the welding equipment is running, vibration change graph reflects whether the workpiece is loose, and fit degree characterizes the fit of the weld. The electronic device judges whether the weld is qualified based on current data, vibration change graph and fit degree.

[0043] S105 If the workpiece fails to meet the requirements, the testing equipment will mark it.

[0044] In this embodiment, if the weld is defective, the control and inspection equipment marks the workpiece. The inspection equipment may be equipped with an inkjet printer, the ink color of which is different from the workpiece color. The inkjet printer is wirelessly connected to an electronic device. When the electronic device detects a defective weld, it sends a signal to the inkjet printer, which receives the signal and marks the workpiece. Based on video information from the upper and lower sides of the workpiece during welding, as well as ultrasonic data from inside the weld, the fit within the weld is determined. Then, based on current data, vibration variation diagrams, and fit, the weld's quality is judged. When a defect is found, the workpiece is marked. This allows for timely monitoring of defects inside the weld and differentiation of defective workpieces, improving the production efficiency of mobile phone casings.

[0045] In one possible implementation of this application embodiment, the first video information corresponds to the upper welding side of the workpiece, and the second video information corresponds to the lower welding side of the workpiece. Step S103 determines the weld fit based on the first video information, the second video information, and ultrasonic data, specifically including steps S1031 (not shown in the figure), S1032 (not shown in the figure), S1033 (not shown in the figure), S1034 (not shown in the figure), and S1035 (not shown in the figure). Step S1031: Weld seam identification is performed on the first video information and the second video information respectively to obtain the first identification result and the second identification result.

[0046] In this embodiment of the application, the electronic device inputs the first video information and the second video information into a trained network model for weld seam recognition, respectively, to obtain a first recognition result and a second recognition result. The network model can be a convolutional neural network model, a recurrent neural network model, or other types of network models.

[0047] Step S1032: Based on the first identification result and the second identification result, perform edge detection to determine the first range on the upper side of the weld and the second range on the lower side of the weld.

[0048] In the embodiments of this application, the electronic device performs edge detection based on the first recognition result and the second recognition result to determine the first range on the upper side of the weld and the second range on the lower side of the weld. The first range characterizes the range of the weld left by the welding equipment in contact with the workpiece surface, and the second range characterizes the size of the welding mark left by the welding equipment when welding to the bottom of the workpiece.

[0049] Step S1033: Determine the similarity between the first range and the second range, and determine the first area of ​​the first range and the second area of ​​the second range.

[0050] In the embodiments of this application, in order to fully weld the workpiece, it is necessary to perform friction stir welding on the upper and lower sides of the workpiece simultaneously, penetrating the upper and lower sides of the workpiece. The electronic device determines the similarity between the first range and the second range. If the similarity is too low, there may be a situation where welding is abnormal on one side or welding is abnormal on both sides at the same time, and determines the first area of ​​the first range and the second area of ​​the second range.

[0051] Step S1034: Determine the first difference between the first area and the second area.

[0052] In the embodiments of this application, the electronic device determines a first difference between the first area and the second area. The larger the first difference, the larger the area where the weld has not penetrated to the bottom of the workpiece.

[0053] Step S1035: Determine the fit of the weld seam based on similarity, first difference and ultrasonic data.

[0054] In the embodiments of this application, similarity and first difference reflect the surface condition of the weld exterior, while ultrasonic data reflects the interior condition of the weld. Therefore, the electronic device determines the weld fit based on similarity, first difference, and ultrasonic data.

[0055] One possible implementation of this application embodiment is that step S1035, which determines the weld fit based on similarity, a first difference, and ultrasonic data, specifically includes steps S1 (not shown in the figure), S2 (not shown in the figure), and S3 (not shown in the figure), wherein... Step S1: Obtain the echo signal of the ultrasonic data and determine the amplitude variation diagram and sound velocity variation diagram of the echo signal.

[0056] In the embodiments of this application, the electronic device acquires the echo signal of the ultrasonic data and determines the amplitude change graph and sound velocity change graph of the echo signal. The amplitude and sound velocity of the echo signal can reflect the defect status and size inside the weld of the workpiece.

[0057] Step S2: Determine the first proportion of amplitudes exceeding the preset amplitude range based on the amplitude change graph, and determine the second proportion of sound speeds exceeding the preset sound speed range based on the sound speed change graph.

[0058] In the embodiments of this application, different types of workpieces correspond to different amplitude ranges and sound speed ranges. The electronic device determines a first proportion of amplitudes exceeding a preset amplitude range based on the amplitude change graph, and determines a second proportion of sound speeds exceeding a preset sound speed range based on the sound speed change graph.

[0059] Step S3: Determine the first score based on similarity, first difference, first proportion, second proportion, and their respective first coefficients.

[0060] The first score represents the fit of the weld.

[0061] In the embodiments of this application, similarity, first difference, first proportion, and second proportion are all important factors affecting the weld fit. Similarity and first difference reflect the surface condition of the weld. The lower the similarity or the larger the first difference, the less well the weld fits. The larger the first proportion and second proportion, the more defects may exist inside the weld. Therefore, the electronic device determines the first score based on similarity, first difference, first proportion, second proportion, and their respective first coefficients. The higher the first score, the better the weld fit.

[0062] One possible implementation of this application embodiment is that step S104, which determines whether the weld is qualified based on current data, vibration change diagram, and fit, specifically includes steps S1041 (not shown in the figure), S1042 (not shown in the figure), S1043 (not shown in the figure), and S1044 (not shown in the figure), wherein... Step S1041: Determine the number of maximum amplitudes and vibration periods based on the vibration variation diagram.

[0063] In the embodiments of this application, when the workpiece is welded, the contact of the welding equipment will generate resonance. Therefore, the electronic equipment determines the maximum amplitude and the number of vibration cycles. The larger the maximum amplitude, the larger the vibration range of the workpiece. The more cycles there are, the higher the vibration frequency and the looser the workpiece.

[0064] Step S1042: Determine the maximum current and minimum current based on the current data, and determine the second difference between the maximum current and the minimum current.

[0065] In the embodiments of this application, a stable current is required for the welding equipment to perform friction welding smoothly. The electronic device determines the maximum and minimum currents based on the current data and determines a second difference between the maximum and minimum currents. The larger the second difference, the more unstable the current is when the welding equipment is running, which leads to unstable rotation speed and may result in gaps or uneven density inside the weld.

[0066] Step S1043: Determine the second score based on the maximum amplitude, quantity, second difference, fit, and their respective second coefficients.

[0067] In the embodiments of this application, the electronic device determines a second score based on the maximum amplitude, quantity, second difference, fit, and their respective second coefficients. The lower the second score, the worse the welding quality.

[0068] Step S1044: Determine whether the weld is qualified based on the second score.

[0069] In this embodiment of the application, if the second score reaches the preset score threshold, it indicates that the weld is qualified; if the second score is lower than the preset score threshold, it indicates that the weld is unqualified. The electronic device judges the second score and then judges whether the weld is qualified.

[0070] One possible implementation of this application embodiment includes steps one, two, three, four, and five, wherein step one can be executed after step S105. Step 1: Obtain the point cloud data of the marked workpiece.

[0071] In this embodiment of the application, a lidar can be installed on the side of a robotic arm. When ultrasonic data is collected on the weld, the lidar simultaneously collects point cloud data of the workpiece. The lidar is also wirelessly connected to an electronic device, so that the electronic device can obtain the point cloud data of the marked workpiece.

[0072] Step 2: Perform crack identification on the point cloud data to obtain crack identification results.

[0073] In this embodiment of the application, the electronic device inputs point cloud data into a trained network model to identify cracks and obtains crack identification results, which reflect the internal defects of the marked workpiece.

[0074] Step 3: Determine the maximum length of the crack and the total length of all cracks based on the crack identification results.

[0075] In the embodiments of this application, the electronic device determines the length of each crack based on the crack identification results, identifies the crack with the longest length, and the total length of all cracks. The longer the crack, the less sufficient the internal fusion of the weld is, and the worse the quality of the weld.

[0076] Step 4: Determine the degree of abnormality of the weld based on the maximum length and the total length.

[0077] In the embodiments of this application, the electronic device determines the degree of abnormality of the weld corresponding to the maximum length and the total length based on the preset degree of abnormality corresponding to the type of workpiece.

[0078] Step 5: Mark the marked workpiece differently based on the degree of abnormality.

[0079] In the embodiments of this application, the electronic device distinguishes the degree of abnormality of each marked workpiece, and can then mark the marked workpiece differently based on the degree of abnormality. Different colors can be used to distinguish the different degrees of abnormality of the marked workpiece.

[0080] One possible implementation of this application embodiment includes steps S1, S2, S3, and S4, wherein step S1 can be executed after step S1043, wherein... Step S1: Based on the first video information and the second video information, determine the upper width and lower width of the weld seam of each cross section of the workpiece along the welding direction.

[0081] In the embodiments of this application, the electronic device determines the upper width of the weld on each cross section of the workpiece along the welding direction based on the first video information, and determines the lower width of the weld based on the second video information. The upper and lower sides of the workpiece are simultaneously subjected to friction stir welding. The width should be the same; if it is too large or too small, it is an abnormal welding situation.

[0082] Step S2: Determine the maximum height of each cross-section based on the ultrasonic data.

[0083] In the embodiments of this application, during welding, there may be weld beads, grooves or impurities, which may cause changes in the height of the weld. Therefore, the electronic device determines the maximum height of each cross section based on ultrasonic data.

[0084] Step S3: Determine the weld section mass score for each section based on the upper width of the weld, the lower width of the weld, and the maximum height.

[0085] In the embodiments of this application, the electronic device determines a third difference between the maximum height and the workpiece height, and a fourth difference between the upper width of the weld and the lower width of the weld. Based on the third difference, the fourth difference, and their respective third coefficients, a third score for each section is determined, and the average of the third scores of all sections is calculated to determine the weld section quality score.

[0086] Step S4: Adjust the second score based on the weld section quality score.

[0087] In the embodiments of this application, the lower the weld section quality score, the more serious the external defects of the weld. Therefore, the electronic device adjusts the second score based on the weld section quality score, and the final score can be determined by subtracting the weld quality score from the second score.

[0088] One possible implementation of this application embodiment includes steps six, seven, and eight, wherein step six can be executed after step S4, wherein... Step 6: Determine the number of marks and the total number of welds within the preset time period.

[0089] In this embodiment of the application, the electronic device determines the number of marks and the total number of welds within a preset time period.

[0090] Step 7: Determine the average score of the second score for all marked workpieces.

[0091] In this embodiment of the application, the electronic device determines the average score of the second score of all marked workpieces. The lower the average score, the worse the quality of the marked workpiece.

[0092] Step 8: Submit a welding quality report to the management office.

[0093] The welding quality report includes the number of markings, the total number of welds, and the average score.

[0094] In this embodiment of the application, the electronic device outputs a welding quality report to the management office. The number of markings and the total number of welds reflect the welding efficiency and non-conforming rate of the welding equipment within a preset time period, and the average score reflects the degree of non-conformity of the marked workpieces.

[0095] The above embodiments describe an ultrasonic-based intelligent weld inspection method from the perspective of process flow. The following embodiments describe an ultrasonic-based intelligent weld inspection system from the perspective of virtual modules or virtual units. For details, please refer to the following embodiments.

[0096] This application provides an ultrasonic-based intelligent weld inspection system 20, such as... Figure 2 As shown, the ultrasonic-based intelligent weld inspection system 20 may specifically include: The first acquisition module 201 is used to acquire the current data of the welding equipment, the vibration change diagram of the workpiece, and the video information during welding. The video information includes first video information and second video information. The control module 202 is used to control the detection equipment to move along the weld and collect ultrasonic data of the weld in real time after the weld is formed, so that the electronic equipment can acquire ultrasonic data. The first determining module 203 is used to determine the fit of the weld seam based on the first video information, the second video information and the ultrasonic data; The first judgment module 204 is used to judge whether the weld is qualified based on current data, vibration change diagram and fit. The first marking module 205 is used to control the testing equipment to mark the workpiece if it fails to meet the requirements.

[0097] This application discloses an ultrasonic-based intelligent weld detection system 20. The system includes a first acquisition module 201 that acquires current data from the welding equipment, vibration patterns of the workpiece, and video information during welding. During welding, the welding equipment is powered on and operates, generating internal current. As the welding equipment rotates and contacts the workpiece, it causes corresponding vibrations in the workpiece, melting and fusing the contact surfaces of the two workpieces together, thus completing friction welding. After the weld is formed, a control module 202 controls the detection equipment to move along the weld and collect ultrasonic data of the weld in real time, enabling the electronic device to acquire the ultrasonic data. A first determination module 203, based on the first video... Information, second video information, and ultrasonic data determine the weld fit. Fit reflects whether the outside and inside of the workpiece weld are in contact. The magnitude of the current affects whether the welding equipment can operate normally. If the workpiece vibrates too much, when the welding equipment rotates and contacts the workpiece, it will cause the weld to deviate or even cause the workpiece to fly away, making welding impossible. Therefore, the first judgment module 204 judges whether the weld is qualified based on the current data, vibration change diagram, and fit. If it is unqualified, the first marking module 205 controls the detection equipment to mark the workpiece, thereby enabling timely monitoring of defects inside the weld and distinguishing unqualified workpieces, improving the production efficiency of mobile phone shells.

[0098] In one possible implementation of this application embodiment, the first video information corresponds to the upper welding side of the workpiece, and the second video information corresponds to the lower welding side of the workpiece. When determining the weld fit based on the first video information, the second video information, and ultrasonic data, the first determining module 203 is specifically used for: Weld seam identification is performed on the first video information and the second video information respectively to obtain the first identification result and the second identification result; Edge detection is performed based on the first and second identification results to determine the first range on the upper side of the weld and the second range on the lower side of the weld. Determine the similarity between the first range and the second range, and determine the first area of ​​the first range and the second area of ​​the second range; Determine the first difference between the first area and the second area; The fit of the weld is determined based on similarity, first difference, and ultrasonic data.

[0099] In one possible implementation of this application embodiment, when the first determining module 203 determines the weld fit based on similarity, a first difference, and ultrasonic data, it is specifically used for: Acquire echo signals from ultrasonic data and determine the amplitude and velocity variations of the echo signals. Based on the amplitude change graph, a first proportion of amplitudes exceeding a preset amplitude range is determined, and based on the sound speed change graph, a second proportion of sound speeds exceeding a preset sound speed range is determined. The first score is determined based on similarity, difference, first proportion, second proportion, and their respective first coefficients. The first score characterizes the fit of the weld.

[0100] In one possible implementation of this application embodiment, when the first judgment module 204 judges whether the weld is qualified based on current data, vibration change diagram, and fit, it is specifically used for: The number of maximum amplitudes and vibration periods were determined based on the vibration variation diagram; The maximum and minimum currents are determined based on the current data, and a second difference between the maximum and minimum currents is determined. The second score is determined based on the maximum amplitude, quantity, second difference, fit, and their respective second coefficients. The weld is judged to be qualified based on the second score.

[0101] In one possible implementation of this application embodiment, system 20 further includes: The second acquisition module is used to acquire the point cloud data of the marked workpiece; The identification module is used to identify cracks in the point cloud data and obtain crack identification results. The second determining module is used to determine the maximum length of the crack and the total length of all cracks based on the crack identification results. The third determining module is used to determine the degree of abnormality of the weld based on the maximum length and the total length; The second marking module is used to mark the marked workpiece differently based on the degree of abnormality.

[0102] In one possible implementation of this application embodiment, system 20 further includes: The fourth determining module is used to determine the upper width and lower width of the weld at each cross section of the workpiece along the welding direction based on the first video information and the second video information, respectively. The fifth determining module is used to determine the maximum height of each cross-section based on the ultrasonic data; The sixth determining module is used to determine the weld section mass score of each section based on the upper side width, lower side width and maximum height of the weld. An adjustment module is used to adjust the second score based on the weld section quality score.

[0103] In one possible implementation of this application embodiment, system 20 further includes: The seventh module is used to determine the number of marks and the total number of welds within a preset time period; The eighth determining module is used to determine the average score of the second score for all marked workpieces; The output module is used to output a welding quality report to the management office. The welding quality report includes the number of markings, the total number of welds, and the average score.

[0104] This application provides an electronic device, such as... Figure 3 As shown, Figure 3 The illustrated electronic device 30 includes a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, for example, via a bus 302. Optionally, the electronic device 30 may also include a transceiver 304. It should be noted that in practical applications, the transceiver 304 is not limited to one type, and the structure of this electronic device 30 does not constitute a limitation on the embodiments of this application.

[0105] Processor 301 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 301 may also be a combination that implements computational functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0106] Bus 302 may include a pathway for transmitting information between the aforementioned components. Bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Bus 302 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 3 The symbol is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0107] The memory 303 may be a ROM (Read Only Memory) or other type of static storage device capable of storing static information and instructions, RAM (Random Access Memory) or other type of dynamic storage device capable of storing information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), CD-ROM (Compact Disc Read Only Memory) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto.

[0108] The memory 303 is used to store application code that executes the solution of this application, and its execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the content shown in the foregoing method embodiments.

[0109] Electronic devices include, but are not limited to: mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), and in-vehicle terminals (such as in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Servers can also be included. Figure 3 The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0110] This application provides a computer-readable storage medium storing a computer program that, when run on a computer, enables the computer to execute the corresponding content in the aforementioned method embodiments. Compared with related technologies, this application embodiment acquires current data of the welding equipment, vibration change diagram of the workpiece, and video information during welding. During welding, the welding equipment is powered on and operates, and there is current inside. When the welding equipment rotates and contacts the workpiece, it also causes the workpiece to vibrate accordingly, causing the contact surfaces of the two workpieces to melt and fuse together, thereby completing friction welding. After the weld is formed, the detection equipment is controlled to move along the weld and collect ultrasonic data of the weld in real time, so that the electronic device can acquire ultrasonic data. Based on the first video information, the second video information, and the ultrasonic data, the weld fit is determined. The fit reflects whether the outside and inside of the workpiece are in contact. The magnitude of the current affects whether the welding equipment can operate normally. If the workpiece vibration is too severe, it will cause the weld to deviate when the welding equipment rotates and contacts the workpiece, or even cause the workpiece to bounce away and fail to complete the welding. Therefore, the weld is judged to be qualified based on the current data, vibration change diagram, and fit. If it is unqualified, the detection equipment is controlled to mark the workpiece, so as to promptly monitor the defects inside the weld and distinguish unqualified workpieces, thereby improving the production efficiency of mobile phone shells.

[0111] It should be understood that although the steps in the flowcharts of the accompanying figures are shown sequentially as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the accompanying figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0112] The above description is only a partial embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. An intelligent weld inspection method based on ultrasonic waves, characterized in that, include: Acquire current data of the welding equipment, vibration change diagram of the workpiece, and video information during welding, wherein the video information includes first video information and second video information; Once the weld is formed, the control detection equipment moves along the weld and collects the ultrasonic data of the weld in real time, so that the electronic equipment can acquire the ultrasonic data. The fit of the weld is determined based on the first video information, the second video information, and the ultrasonic data. The weld seam is judged to be qualified based on the current data, vibration change diagram and fit. If the workpiece fails to meet the requirements, the testing equipment is controlled to mark it.

2. The ultrasonic-based intelligent weld inspection method according to claim 1, characterized in that, The first video information corresponds to the upper side of the workpiece during welding, and the second video information corresponds to the lower side of the workpiece during welding. Determining the weld fit based on the first video information, the second video information, and ultrasonic data includes: Weld seam identification is performed on the first video information and the second video information respectively to obtain a first identification result and a second identification result; Edge detection is performed based on the first and second identification results to determine the first range on the upper side of the weld and the second range on the lower side of the weld. Determine the similarity between the first range and the second range, and determine the first area of ​​the first range and the second area of ​​the second range; Determine the first difference between the first area and the second area; The weld fit is determined based on the similarity, the first difference, and the ultrasonic data.

3. The ultrasonic-based intelligent weld inspection method according to claim 2, characterized in that, Determining the weld fit based on the similarity, the first difference, and the ultrasonic data includes: Acquire the echo signal of the ultrasonic data, and determine the amplitude variation graph and sound velocity variation graph of the echo signal; Based on the amplitude change graph, a first percentage of amplitudes exceeding a preset amplitude range is determined, and based on the sound speed change graph, a second percentage of sound speeds exceeding a preset sound speed range is determined. A first score is determined based on the similarity, difference, first proportion, second proportion, and their respective first coefficients. The first score characterizes the fit of the weld.

4. The ultrasonic-based intelligent weld inspection method according to claim 1, characterized in that, The determination of whether the weld is qualified based on the current data, vibration change diagram, and fit includes: The number of maximum amplitudes and vibration periods are determined based on the vibration variation diagram. Based on the current data, the maximum current and the minimum current are determined, and a second difference between the maximum current and the minimum current is determined. The second score is determined based on the maximum amplitude, quantity, second difference, fit, and their respective second coefficients. The weld is judged to be qualified based on the second score.

5. The ultrasonic-based intelligent weld inspection method according to claim 1, characterized in that, The method further includes: Obtain the point cloud data of the marked workpiece; Crack identification is performed on the point cloud data to obtain crack identification results; Based on the crack identification results, determine the maximum length of the crack and the total length of all cracks; The degree of abnormality of the weld is determined based on the maximum length and the total length; The marked workpieces are marked differently based on the degree of abnormality.

6. The ultrasonic-based intelligent weld inspection method according to claim 2 or 4, characterized in that, The method further includes: Based on the first video information and the second video information, the upper width and lower width of the weld at each cross section of the workpiece along the welding direction are determined respectively. The maximum height of each cross-section is determined based on the ultrasonic data; The weld section mass score for each section is determined based on the upper width of the weld, the lower width of the weld, and the maximum height. The second score is adjusted based on the weld section quality score.

7. The ultrasonic-based intelligent weld inspection method according to claim 1, characterized in that, The method further includes: Determine the number of markings and the total number of welds within the preset time period; Determine the average score of the second score for all marked workpieces; A welding quality report is output to the management office, which includes the number of markings, the total number of welds, and the average score.

8. An intelligent weld inspection system based on ultrasonic waves, characterized in that, include: The first acquisition module is used to acquire current data of the welding equipment, vibration change diagram of the workpiece, and video information during welding. The video information includes first video information and second video information. The control module is used to control the detection equipment to move along the weld and collect the ultrasonic data of the weld in real time after the weld is formed, so that the electronic equipment can acquire the ultrasonic data. The first determining module is used to determine the fit of the weld seam based on the first video information, the second video information, and the ultrasonic data. The first judgment module is used to determine whether the weld is qualified based on the current data, vibration change diagram and fit. The first marking module is used to control the detection device to mark the workpiece if it fails to meet the requirements.

9. An electronic device, characterized in that, It includes: At least one processor; Memory; At least one application, wherein the at least one application is stored in the memory and configured to be executed by the at least one processor, the at least one application being used to execute an ultrasonic-based intelligent weld detection method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed in the computer, the computer is instructed to perform the ultrasonic-based intelligent weld detection method according to any one of claims 1 to 7.

Images