A method, device and equipment for quality inspection of automobile exhaust pipe welds

Abstract

A method, device and equipment for quality inspection of welds in automobile exhaust pipes, relating to the field of weld inspection. The method is applied to a weld quality analysis system, and the method includes: heating the welds of automobile exhaust pipes, stopping the heating when the welds reach a specified temperature, and then monitoring the weld temperature change distribution diagram during the cooling process, because the cooling process of the defective area is somewhat different from that of the normal welds. The present application divides the weld area into multiple weld units, and then calculates the similarity value between the temperature change curve of each weld unit and the temperature change curve of the normal weld one by one. For weld units with lower similarity values, the weld defect type is identified to determine the defect type of the defective weld. The present application can not only discover deep defects in the weld defect area and improve the accuracy of weld quality inspection, but can also be used for quality inspection of the weld penetration, and has a wider range of applicable scenarios.

Description

Technical Field

[0001] The present application relates to the technical field of weld detection, and in particular to a method, device and equipment for quality detection of welds in automobile exhaust pipes. Background Art

[0002] To accommodate vehicle dimensions, automotive exhaust ducts often have irregular shapes, making them difficult to form in one piece. Currently, processing these irregular ducts typically involves manufacturing multiple components and then welding them together to create a complete duct. In this context, weld quality inspection is crucial. Currently, visual inspection technology is commonly used to inspect welds on exhaust ducts. This technology captures weld images and then uses weld inspection models to identify and classify them, identifying defects.

[0003] However, visual inspection technology not only has high requirements for image clarity, but also has difficulty detecting deep defects in welds, resulting in inaccurate quality inspection of automobile exhaust pipe welds. Summary of the Invention

[0004] To address the problem of inaccurate quality inspection of automobile exhaust pipe welds due to the difficulty of visual inspection technology in detecting deep weld defects, the present application provides a quality inspection method, device and equipment for automobile exhaust pipe welds.

[0005] In a first aspect, the present application provides a method for detecting the quality of a weld seam in an automobile exhaust pipe, which is applied to a weld quality analysis system. The method comprises:

[0006] Controlling the heating module to heat the weld to be detected, stopping heating when the weld to be detected reaches a target temperature, monitoring the temperature of the weld to be detected, and obtaining a weld temperature change distribution diagram of the weld to be detected;

[0007] Extracting temperature variation curves of a plurality of weld seam units from the weld seam temperature variation distribution diagram;

[0008] Calculating similarity between the temperature change curves of the plurality of weld seam units and the temperature change curve of a preset weld seam unit;

[0009] Calculating the similarity between the temperature variation curve of a first weld unit and the temperature variation curve of the preset weld unit, and determining whether the first weld unit is an abnormal weld unit, the first weld unit being any one of the plurality of weld units;

[0010] If the first weld unit is the abnormal weld unit, a characteristic analysis is performed on the temperature change curve of the abnormal weld unit to obtain the weld type of the abnormal weld unit, where the weld types include weld bead, weld penetration, porosity, undercut, poor forming and slag inclusion.

[0011] Optionally, before the controlling heating module heats the weld to be inspected and stops heating after the weld to be inspected reaches a target temperature, the method further includes:

[0012] Obtaining the welding material type of the weld to be inspected;

[0013] Matching the welding material type with a preset phase change temperature database to obtain the phase change temperature of the welding material;

[0014] The phase transition temperature is set as the target temperature.

[0015] Optionally, an initial thermal value distribution diagram of the weld temperature change distribution diagram is extracted, wherein the initial thermal value distribution diagram is composed of a plurality of thermal points, wherein one thermal point corresponds to one thermal value;

[0016] Cluster analysis is performed on the thermal values ​​of the plurality of thermal points to determine the plurality of weld units.

[0017] Optionally, performing cluster analysis on the thermal values ​​of the plurality of thermal points to determine the plurality of weld units specifically further includes:

[0018] Based on the preset area radius and the minimum number of points, traverse the heat values ​​of multiple heat points to obtain multiple core points;

[0019] Calculating the correlation distance between the plurality of core points, wherein the correlation distance includes a numerical distance and a size distance;

[0020] If the association distance between the first core point and the second core point meets the preset association distance threshold, it is determined that the first core point and the second core point belong to the same weld unit, and the first core point and the second core point are any two different core points among the multiple core points.

[0021] Optionally, obtaining the thermal point density of the initial thermal value distribution map;

[0022] According to the density of the heat points, the area radius and the minimum number of points of the plurality of heat points are preset;

[0023] Traversing multiple adjacent thermal points of a thermal point to be analyzed, wherein the thermal point to be analyzed is any one of the multiple thermal points;

[0024] If the thermal values ​​of a plurality of adjacent thermal points exist within the range of the thermal point to be analyzed, and the number of adjacent thermal points is greater than or equal to the minimum number of points, the thermal point to be analyzed is determined to be a core point.

[0025] Optionally, performing cluster analysis on the thermal values ​​of the plurality of thermal points to determine the plurality of weld units specifically further includes:

[0026] Dividing the plurality of thermal points into a plurality of weld regions of equal area;

[0027] Calculating variances within a plurality of the equal-area weld regions;

[0028] If the variance in the first weld region is greater than or equal to a preset variance threshold, performing variance debugging on the first weld region to obtain a plurality of abnormal thermal points, wherein the first weld region is any one of the plurality of weld regions of equal area;

[0029] removing the plurality of abnormal thermal points from the first weld region to obtain a second weld region;

[0030] The second weld area is used as the weld unit.

[0031] Optionally, obtaining thermal properties of the welding material of the weld to be inspected;

[0032] Constructing a cross-sectional model of the abnormal weld unit based on the thermal properties of the welding material and the temperature variation curve of the abnormal weld unit;

[0033] Feature recognition is performed on the section model to obtain the weld type of the abnormal weld unit.

[0034] In a second aspect, the present application provides a quality detection device for automobile exhaust pipe welds, wherein the device is a weld quality analysis system, and the weld quality analysis system includes an input module, a processing module, and an output module, wherein:

[0035] The input module is used to control the heating module to heat the weld to be detected, stop heating when the weld to be detected reaches the target temperature, monitor the temperature of the weld to be detected, and obtain a weld temperature change distribution diagram of the weld to be detected;

[0036] The processing module is configured to extract temperature change curves of a plurality of weld units from the weld temperature change distribution diagram; perform similarity calculation between the temperature change curves of the plurality of weld units and the temperature change curve of a preset weld unit; calculate the similarity between the temperature change curves of a first weld unit and the preset weld unit, and determine whether the first weld unit is an abnormal weld unit, the first weld unit being any one of the plurality of weld units;

[0037] The output module is used to perform characteristic analysis on the temperature change curve of the abnormal weld unit if the first weld unit is the abnormal weld unit, so as to obtain the weld type of the abnormal weld unit, where the weld types include weld bead, weld penetration, porosity, undercut, poor forming and slag inclusion.

[0038] In a third aspect, the present application provides an electronic device comprising a processor, a memory, a user interface, and a network interface, wherein the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes a method as described in any one of the first aspects.

[0039] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores instructions, and when the instructions are executed, the method as described in any one of the first aspects is executed.

[0040] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0041] 1. By heating the weld of the automobile exhaust pipe, stopping the heating when the weld reaches the specified temperature, and then monitoring the weld temperature change distribution diagram during the cooling process, it can be understood that for the defective area in the weld, since its shape is different from that of the normal weld, the cooling process of these defective areas is somewhat different from that of the normal weld. Based on this, the present application divides the weld area into multiple weld units, and then calculates the similarity value between the temperature change curve of each weld unit and the temperature change curve of the normal weld one by one. For weld units with lower similarity values, the weld defect type is identified to determine the defect type of the defective weld. This process can not only detect deep defects in the weld defect area based on the temperature change of the defect area, improve the accuracy of weld quality detection, but also be used for quality detection of the weld penetration depth, and has a wider range of applicable scenarios.

[0042] 2. When dividing the weld units, in order to increase the proportion of the same welding structure in each weld unit, this application performs cluster analysis on the weld area, clustering the defective area in one weld unit and the non-defective area in one weld unit, thereby improving the subsequent recognition accuracy of weld defects. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 It is a flow chart of a quality inspection method for automobile exhaust pipe welds provided in an embodiment of the present application.

[0044] Figure 2This is a partial diagram of an initial thermal value distribution diagram provided in an embodiment of the present application.

[0045] Figure 3 It is a structural schematic diagram of a quality inspection device for automobile exhaust pipe welds provided in an embodiment of the present application.

[0046] Figure 4 This is a structural diagram of an electronic device provided in an embodiment of the present application.

[0047] Explanation of the accompanying drawings: 1. Input module; 2. Processing module; 3. Output module; 400. Electronic device; 401. Processor; 402. Communication bus; 403. User interface; 404. Network interface; 405. Memory. DETAILED DESCRIPTION

[0048] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0049] In the description of the embodiments of this application, words such as "for example" or "for instance" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "for example" or "for instance" in the embodiments of this application should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "for example" or "for instance" is intended to present the relevant concepts in a concrete manner.

[0050] In the description of the embodiments of the present application, the term "multiple" means two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0051] The production of automotive exhaust ducts typically involves both mold forming and welding. However, for irregularly shaped ducts, mold design is difficult and prone to damage, significantly increasing costs. Therefore, most manufacturers use welding, where weld quality inspection is particularly important.

[0052] Currently, the most common method for weld inspection is visual inspection. This involves capturing weld images and identifying their edge features. These features are then fed into a weld inspection model for identification and classification, ultimately determining the weld defect type. However, visual inspection technology not only requires high image clarity but also struggles to detect deep-seated weld defects, leading to inaccurate weld quality inspections for automotive exhaust pipes.

[0053] In order to solve the above problems, the present application provides a method for detecting the quality of automobile exhaust pipe welds, which is applied to a weld quality analysis system, such as Figure 1 As shown, the method includes steps S101 to S105, which are as follows:

[0054] S101, controlling the heating module to heat the weld to be inspected, stopping the heating when the weld to be inspected reaches the target temperature, monitoring the weld temperature, and obtaining a weld temperature change distribution diagram of the weld to be inspected.

[0055] In the above steps, the weld quality analysis system controls the heating module to heat the weld under test until the weld temperature reaches the target temperature, then stops heating. The temperature detection module then monitors the weld area until the weld temperature drops to room temperature, generating a weld temperature distribution map.

[0056] To avoid damaging the weld during heating, the phase transition temperature of the weld to be tested should be queried from a preset phase transition temperature database based on the type of welding material to be tested. The phase transition temperature can be understood as the temperature at which the internal structure of the material undergoes transformation during heating or cooling. This phase transition temperature is then used as the target temperature to avoid structural damage to the weld. Furthermore, since the phase transition temperature of some welding materials is higher than that of the welded component (such as the automobile exhaust pipe), the target temperature should be lower than the phase transition temperature of the welding material to avoid damage to the welded component caused by the target temperature.

[0057] S102. Extracting temperature variation curves of multiple weld units from the weld temperature variation distribution diagram.

[0058] In the above steps, the weld temperature change distribution diagram is a dynamic temperature change model, which characterizes the overall dynamic change of the temperature distribution of the weld to be tested over time. The defective area of ​​the weld is more obvious in the weld temperature change distribution diagram because its size structure is different from that of a normal weld. For example, a common welding defect: a weld nodule, its size structure is compared with that of a normal weld, and it appears as a nodule on the weld surface. When heated, the weld nodule will accumulate more heat, which will make the subsequent heat dissipation time longer than that of a normal weld. Based on this feature, the present application divides the weld temperature change distribution diagram into multiple weld units, and then extracts the temperature change curve of each weld unit to facilitate the subsequent analysis of the defect type of the weld.

[0059] In one possible embodiment, the weld unit represents a weld area, which includes both normal weld areas and defective weld areas. However, when extracting the temperature change curve of the weld unit, the present application considers the average distribution of the entire weld unit. Therefore, if the normal weld area in the weld unit is much larger than the defective weld area, the defective weld area will be masked, thereby reducing the accuracy of weld detection. In order to solve this problem, the present application uses cluster analysis when dividing the welding unit to extract the initial thermal value distribution map of the weld temperature change distribution map. The initial thermal value distribution map includes the distribution of thermal points of the entire weld area, and each thermal point corresponds to a thermal value; then cluster analysis is performed on the multiple thermal points in the initial thermal value distribution map to increase the proportion of the main component in each weld unit, thereby reducing the influence of the secondary component data on the main component data. Specifically:

[0060] In one embodiment, first, based on the preset domain radius and the minimum number of points, the thermal values ​​of multiple thermal points are traversed to obtain multiple core points; specifically: first, the thermal point density of the initial thermal value distribution map is obtained; then, based on the thermal point density, the domain radius and the minimum number of points of multiple thermal points are preset. It should be noted that the thermal density is determined by the system analysis capability, and the specific setting standard is determined according to the actual situation, which is not limited in this application; finally, the multiple adjacent thermal points corresponding to the multiple thermal points are traversed. If the thermal values ​​of multiple adjacent thermal points of a certain thermal point exist within the domain range of the thermal point, and the number of adjacent thermal points is greater than or equal to the minimum number of points, then the thermal point is determined to be a core point. For example, if Figure 2 As shown, Figure 2A local diagram of an initial thermal value distribution diagram provided in an embodiment of the present application, with a preset domain radius of 1 and a minimum number of points of 6. Area A represents a thermal point, and area B represents another thermal point. The thermal value of point A is 60, and the thermal value of point B is 62. At this time, the domain of point A is [59, 61], and the domain of point B is [61, 63]. It can be seen from the figure that among the 8 thermal points adjacent to point A, the domain radius that satisfies point A includes [60.5, 60.4, 60.5, 60.7, 61, 59.9, 60], and the domain radius that satisfies point B includes [61.4, 61.6, 61.5, 61]. Through statistics, the number of points at point A is 7, and the number of points at point B is 4. At this time, the number of points at point A is greater than the minimum number of points 6, then point A is a core point, and the number of points at point B is less than the minimum number of points 6, then point B is a non-core point.

[0061] After obtaining multiple core points, since the core points are relatively scattered, this application integrates the multiple core points by calculating the correlation distance between the multiple core points, so as to obtain a complete weld unit, wherein the correlation distance includes numerical distance and size distance. The numerical distance is the distance between the thermal values ​​of the two core points, and the size distance is the distance between the two core points on the weld to be detected. At this time, by setting a preset correlation distance threshold, it is determined whether different core points are suitable for being divided into the same weld unit. Specifically, the correlation distance is calculated using the following formula:

[0062]

[0063] Among them, α is the association distance, S1 is the numerical distance, S2 is the size distance, σ1 is the variance of the numerical distance, and σ2 is the variance of the size distance.

[0064] In the above formula, It can be regarded as a Gaussian distribution representation of the numerical distance. It can be viewed as a Gaussian distribution representation of dimensional distance. As can be seen from the above formula, when the numerical distance remains constant and the dimensional distance decreases, the overall degree of correlation increases. Similarly, when the numerical distance remains constant and the dimensional distance increases, the overall degree of correlation decreases. However, when both are in a state of change, the degree of change is amplified by an exponential function, making it very suitable for calculating the correlation distance of multiple thermal points with subtle changes in thermal values.

[0065] When the correlation distance between two thermal points is less than the correlation distance threshold, it is determined that the two thermal points are suitable for being divided into the same weld unit.

[0066] In another embodiment, if the number of core points in the initial thermal value distribution map is too scattered and small, the weld units constructed based on the correlation distances between the core points will be discretely distributed, resulting in an inability to effectively distinguish between normal weld areas and defective weld areas. To address this situation, this application proposes another clustering analysis method, specifically:

[0067] First, the initial thermal value distribution map is divided into multiple equal-area weld areas, and the thermal points in each equal-area weld area are connected to each other; then the variance in multiple equal-area weld areas is calculated, that is, the discrete degree of the thermal values ​​of multiple thermal points in each equal-area weld area is calculated, and then a preset variance threshold is set, and the variance of each weld area is debugged to obtain multiple abnormal thermal points; it needs to be further explained that in the variance debugging process, when the variance of the equal-area weld area is greater than the preset variance threshold, the influence of the variance of each thermal point in the equal-area weld area is tested one by one, and when a thermal point After elimination, if the variance of the equal-area weld region is less than or equal to the preset variance threshold, the eliminated thermal point is considered an anomalous thermal point. In reality, there may be more than one anomalous thermal point within an equal-area weld region. Therefore, during variance adjustment, the variance adjustment is gradually increased from a single thermal point to multiple thermal points. That is, if the variance of all thermal points within the equal-area weld region is still greater than the preset variance threshold after variance adjustment, the number of thermal points used for adjustment is increased to two, three, four, and so on, until the variance of the equal-area weld region is less than or equal to the preset variance threshold. Finally, the weld region without multiple anomalous thermal points is considered a weld unit. This process considers the uniformity of thermal values ​​within each weld region as a whole, without considering the differences between individual thermal points. It only needs to understand the impact of each thermal point on the overall weld region, thus allowing the divided weld units to be better viewed as a whole.

[0068] In one possible implementation, for each weld unit that eliminates multiple abnormal thermal points, if one of the abnormal thermal points is adjacent to another weld unit, the abnormal thermal point can be divided into the adjacent weld unit for variance debugging, thereby improving the data integrity of each weld unit.

[0069] S103 , performing similarity calculation between the temperature change curves of the plurality of weld seam units and the temperature change curve of a preset weld seam unit.

[0070] S104, calculating the similarity between the temperature change curves of the first weld unit and the preset weld unit, and determining whether the first weld unit is an abnormal weld unit, where the first weld unit is any one of the plurality of weld units.

[0071] S105. If the first weld unit is an abnormal weld unit, characteristic analysis is performed on the temperature variation curve of the abnormal weld unit to obtain the weld type of the abnormal weld unit. The weld types include weld bead, weld penetration, porosity, undercut, poor forming, and slag inclusion.

[0072] In the above steps S103 to S105, the preset weld unit is a weld unit of a normal weld, and its temperature change curve is obtained based on actual testing. By calculating the similarity between the temperature change curves of multiple weld units of the weld to be detected and the temperature change curve of the preset weld unit, the abnormal weld unit with weld defects among the multiple weld units of the weld to be detected is determined.

[0073] When performing similarity calculation, it is taken into account that the temperature change curve of a normal weld unit is only an idealized characteristic curve, and the actual weld unit is affected by the process, material, welding method, etc. Even if the actual weld unit is a normal weld, its temperature change curve is quite different from the idealized characteristic curve. Therefore, when performing similarity calculation, the present application first sets the curve deviation interval of the preset weld unit according to the actual welding process, material, welding method, etc., and then extracts multiple characteristic curves of the actual weld unit according to the actual welding process, material, welding method, etc., and finally combines the multiple characteristic curves of the weld unit into a single curve. The degree of overlap between the characteristic curves and the preset weld unit is calculated. If the proportion of the multiple characteristic curves in the curve deviation interval of the preset weld unit is less than the preset proportion, the weld unit is determined to be an abnormal weld unit. It should be further explained that when setting the curve deviation interval of the preset weld unit, a large amount of historical welding data is analyzed and the control variable method is used to calculate the influence coefficient of each weld influencing factor on the weld. Then, according to the multiple influence coefficients, the ideal curve of the preset weld unit is adjusted to generate multiple influence curves. At this time, the closed area between the multiple influence curves is used as the curve deviation interval of the preset weld unit.

[0074] In order to further determine the defect type of the weld defect, the present application analyzes the temperature change curve of the abnormal weld unit and converts the temperature change curve of the abnormal weld unit into a structural model of the abnormal weld unit according to the thermal properties of the welding material of the weld to be detected. The principle is that before the temperature of the welding material reaches the phase transition temperature, its temperature change shows a linear change law. As its structure changes, the temperature change will also change. Therefore, its structural change can be inferred from its temperature change. Finally, the structural model of the abnormal weld unit is cut into a cross-sectional model, and then the cross-sectional model is feature-recognized to obtain the defect type of the abnormal weld unit. The solution of the present application is not only suitable for detecting deep defects in welds, but also for testing the penetration quality of welds. For example, due to the structural differences between the welding material and the base material, that is, the different phase transition temperatures, the temperature change curve of the weld will show a more obvious change when the weld is heated to different stages. By analyzing this change trend, the quality of the weld penetration can be detected. Therefore, the solution of the present application can have good adaptability in the quality inspection of most welding processes.

[0075] Reference Figure 3 The present application also provides a quality detection device for automobile exhaust pipe welds, which is a weld quality analysis system. The weld quality analysis system includes an input module 1, a processing module 2, and an output module 3, wherein:

[0076] Input module 1 is used to control the heating module to heat the weld to be inspected, stop heating when the weld to be inspected reaches the target temperature, monitor the temperature of the weld to be inspected, and obtain a weld temperature change distribution diagram of the weld to be inspected;

[0077] Processing module 2 is used to extract temperature change curves of multiple weld units from the weld temperature change distribution diagram; perform similarity calculation on the temperature change curves of the multiple weld units and the temperature change curve of a preset weld unit; calculate the similarity between the temperature change curves of a first weld unit and the preset weld unit, and determine whether the first weld unit is an abnormal weld unit, the first weld unit being any one of the multiple weld units;

[0078] Output module 3 is used to perform characteristic analysis on the temperature change curve of the abnormal weld unit if the first weld unit is an abnormal weld unit, and obtain the weld type of the abnormal weld unit. The weld types include weld bead, weld penetration, porosity, undercut, poor forming and slag inclusion.

[0079] In a possible implementation, before controlling the heating module to heat the weld to be inspected and stopping heating after the weld to be inspected reaches a target temperature, the method further includes:

[0080] Obtain the welding material type of the weld to be inspected;

[0081] Matching the welding material type with a preset phase change temperature database to obtain the phase change temperature of the welding material;

[0082] Set the phase transition temperature to the target temperature.

[0083] In a possible implementation, an initial thermal value distribution diagram of the weld temperature change distribution diagram is extracted, where the initial thermal value distribution diagram is composed of a plurality of thermal points, wherein one thermal point corresponds to one thermal value;

[0084] Cluster analysis is performed on the thermal values ​​of multiple thermal points to determine multiple weld units.

[0085] In a possible implementation, cluster analysis is performed on the thermal values ​​of multiple thermal points to determine multiple weld units, which specifically includes:

[0086] Based on the preset area radius and minimum number of points, traverse the heat values ​​of multiple heat points to obtain multiple core points;

[0087] Calculate the correlation distance between multiple core points, which includes numerical distance and size distance;

[0088] If the association distance between the first core point and the second core point meets the preset association distance threshold, it is determined that the first core point and the second core point belong to the same weld unit, and the first core point and the second core point are any two different core points among the multiple core points.

[0089] In a possible implementation, obtaining the thermal point density of the initial thermal value distribution map;

[0090] Based on the density of heat points, preset the area radius and minimum number of heat points;

[0091] Traversing multiple adjacent thermal points of the thermal point to be analyzed, where the thermal point to be analyzed is any one of the multiple thermal points;

[0092] If the thermal values ​​of multiple adjacent thermal points exist within the range of the thermal point to be analyzed, and the number of adjacent thermal points is greater than or equal to the minimum number of points, the thermal point to be analyzed is determined to be a core point.

[0093] In a possible implementation, cluster analysis is performed on the thermal values ​​of multiple thermal points to determine multiple weld units, which specifically includes:

[0094] Divide multiple thermal points into multiple equal-area weld areas;

[0095] Calculate the variance within multiple equal-area weld regions;

[0096] If the variance in the first weld region is greater than or equal to a preset variance threshold, performing variance debugging on the first weld region to obtain multiple abnormal thermal points, the first weld region being any one of multiple equal-area weld regions;

[0097] Eliminating multiple abnormal thermal points from the first weld region to obtain a second weld region;

[0098] The second weld area is treated as a weld element.

[0099] In one possible implementation, thermal properties of the welding material of the weld to be inspected are obtained;

[0100] Based on the thermal properties of the welding material and the temperature change curve of the abnormal weld unit, a cross-sectional model of the abnormal weld unit is constructed;

[0101] The features of the section model are recognized to obtain the weld type of the abnormal weld unit.

[0102] It should be noted that the above embodiments provide devices that implement their functions using only the division of the above functional modules as examples. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiments are based on the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0103] This application also discloses an electronic device. Figure 4 , Figure 4 The electronic device 400 may include: at least one processor 401 , at least one network interface 404 , a user interface 403 , a memory 405 , and at least one communication bus 402 .

[0104] The communication bus 402 is used to implement the connection and communication between these components.

[0105] The user interface 403 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 403 may also include a standard wired interface and a wireless interface.

[0106] The network interface 404 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0107] The processor 401 may include one or more processing cores. The processor 401 utilizes various interfaces and lines to connect various parts of the entire server, and executes various server functions and processes data by running or executing instructions, programs, code sets, or instruction sets stored in the memory 405, and calling data stored in the memory 405. Optionally, the processor 401 may be implemented in at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), or programmable logic array (PLA). The processor 401 may integrate one or a combination of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. The CPU primarily processes the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display; and the modem is used to handle wireless communications. It is understandable that the above-mentioned modem may not be integrated into the processor 401 and may be implemented separately through a single chip.

[0108] Among them, the memory 405 may include a random access memory (RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 405 includes a non-transitory computer-readable storage medium. The memory 405 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 405 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 405 may also be optionally at least one storage device located away from the aforementioned processor 401. Reference Figure 4 , as a computer storage medium, the memory 405 may include an operating system, a network communication module, a user interface module, and an application program for a quality detection method for a weld of an automobile exhaust pipe.

[0109] exist Figure 4In the electronic device 400 shown, the user interface 403 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 401 can be used to call an application program stored in the memory 405 for a quality inspection method for automobile exhaust pipe welds. When executed by one or more processors 501, the electronic device 400 executes one or more of the methods described in the above embodiments. It should be noted that for the aforementioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should know that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for this application.

[0110] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0111] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are merely schematic, such as the division of units, which is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interface, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0112] Units described as separate components may or may not be physically separate, and 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 these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0113] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0114] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a memory and includes several instructions for enabling a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned memory includes various media that can store program codes, such as USB flash drives, mobile hard drives, magnetic disks or optical disks.

[0115] The foregoing is merely an exemplary embodiment of the present disclosure and is not intended to limit the scope of the present disclosure. In other words, any equivalent variations and modifications made in accordance with the teachings of the present disclosure are still within the scope of the present disclosure. Those skilled in the art will readily conceive of other embodiments of the present disclosure after considering the disclosure and the practical implications thereof.

[0116] This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art not described herein. The description and examples are to be considered as exemplary only, and the scope and spirit of the present disclosure are to be defined by the claims.

Claims

1. A quality inspection method for automobile exhaust pipe welds, characterized in that: Applied to a weld quality analysis system, the method includes: Controlling the heating module to heat the weld to be detected, stopping heating when the weld to be detected reaches a target temperature, monitoring the temperature of the weld to be detected, and obtaining a weld temperature change distribution diagram of the weld to be detected; Extracting temperature variation curves of a plurality of weld seam units from the weld seam temperature variation distribution diagram; Calculating similarity between the temperature change curves of the plurality of weld seam units and the temperature change curve of a preset weld seam unit; Calculating the similarity between the temperature variation curve of a first weld unit and the temperature variation curve of the preset weld unit, and determining whether the first weld unit is an abnormal weld unit, the first weld unit being any one of the plurality of weld units; If the first weld unit is the abnormal weld unit, characteristic analysis is performed on the temperature change curve of the abnormal weld unit to obtain the weld type of the abnormal weld unit, where the weld types include weld bead, weld penetration, porosity, undercut, poor forming, and slag inclusion. The step of extracting the temperature change curves of a plurality of weld units from the weld temperature change distribution diagram specifically includes: Extracting an initial thermal value distribution diagram of the weld temperature change distribution diagram, wherein the initial thermal value distribution diagram is composed of a plurality of thermal points, wherein one thermal point corresponds to one thermal value; Performing cluster analysis on the thermal values ​​of the plurality of thermal points to determine a plurality of weld units; The cluster analysis of the thermal values ​​of the plurality of thermal points to determine the plurality of weld units specifically includes: Based on the preset area radius and the minimum number of points, traverse the heat values ​​of multiple heat points to obtain multiple core points; Calculate the correlation distance between the multiple core points. The correlation distance includes a numerical distance and a size distance. The numerical distance is the distance between the thermal values ​​of the two core points. The size distance is the distance between the two core points on the weld to be inspected. The correlation distance is calculated using the following formula: Among them, α is the association distance, S1 is the numerical distance, S2 is the size distance, σ1 is the variance of the numerical distance, and σ2 is the variance of the size distance; If the association distance between the first core point and the second core point meets the preset association distance threshold, it is determined that the first core point and the second core point belong to the same weld unit, and the first core point and the second core point are any two different core points among the multiple core points.

2. The method according to claim 1, characterized in that The control heating module heats the weld to be inspected, and before stopping heating when the weld to be inspected reaches a target temperature, the method further includes: Obtaining the welding material type of the weld to be inspected; Matching the welding material type with a preset phase change temperature database to obtain the phase change temperature of the welding material; The phase transition temperature is set as the target temperature.

3. The method according to claim 1, characterized in that Based on the preset area radius and the minimum number of points, the thermal values ​​of multiple thermal points are traversed to obtain multiple core points, specifically: Obtaining the thermal point density of the initial thermal value distribution map; According to the density of the thermal points, the area radius and the minimum number of points of the plurality of thermal points are preset; multiple adjacent thermal points of the thermal point to be analyzed are traversed, and the thermal point to be analyzed is any one of the plurality of thermal points; If the thermal values ​​of a plurality of adjacent thermal points exist within the range of the thermal point to be analyzed, and the number of adjacent thermal points is greater than or equal to the minimum number of points, the thermal point to be analyzed is determined to be a core point.

4. The method according to claim 1, wherein The characteristic analysis of the temperature change curve of the abnormal weld unit to obtain the weld type of the abnormal weld unit specifically includes: Obtaining thermal properties of the welding material of the weld to be inspected; Constructing a cross-sectional model of the abnormal weld unit based on the thermal properties of the welding material and the temperature variation curve of the abnormal weld unit; Feature recognition is performed on the section model to obtain the weld type of the abnormal weld unit.

5. A quality inspection device for automobile exhaust pipe welds, characterized in that: The device is a weld quality analysis system, comprising an input module (1), a processing module (2) and an output module (3), wherein: The input module (1) is used to control the heating module to heat the weld to be detected, stop heating when the weld to be detected reaches the target temperature, monitor the temperature of the weld to be detected, and obtain a weld temperature change distribution diagram of the weld to be detected; The processing module (2) is used to extract temperature change curves of multiple weld units from the weld temperature change distribution diagram; perform similarity calculation on the temperature change curves of the multiple weld units and the temperature change curve of a preset weld unit; calculate the similarity between the temperature change curves of a first weld unit and the preset weld unit, and determine whether the first weld unit is an abnormal weld unit, the first weld unit being any one of the multiple weld units; The step of extracting the temperature change curves of a plurality of weld units from the weld temperature change distribution diagram specifically includes: Extracting an initial thermal value distribution diagram of the weld temperature change distribution diagram, wherein the initial thermal value distribution diagram is composed of a plurality of thermal points, wherein one thermal point corresponds to one thermal value; Performing cluster analysis on the thermal values ​​of the plurality of thermal points to determine a plurality of weld units; The cluster analysis of the thermal values ​​of the plurality of thermal points to determine the plurality of weld units specifically includes: Based on the preset area radius and the minimum number of points, traverse the heat values ​​of multiple heat points to obtain multiple core points; Calculate the correlation distance between the multiple core points. The correlation distance includes a numerical distance and a size distance. The numerical distance is the distance between the thermal values ​​of the two core points. The size distance is the distance between the two core points on the weld to be inspected. The correlation distance is calculated using the following formula: Among them, α is the association distance, S1 is the numerical distance, S2 is the size distance, σ1 is the variance of the numerical distance, and σ2 is the variance of the size distance; If the association distance between the first core point and the second core point meets a preset association distance threshold, it is determined that the first core point and the second core point belong to the same weld unit, and the first core point and the second core point are any two different core points among the multiple core points; The output module (3) is used to perform characteristic analysis on the temperature change curve of the abnormal weld unit if the first weld unit is the abnormal weld unit, so as to obtain the weld type of the abnormal weld unit, wherein the weld type includes weld bead, weld penetration, air hole, undercut, poor forming and slag inclusion.

6. An electronic device, characterized in that: The electronic device (400) comprises a processor (401), a memory (405), a user interface (403) and a network interface (404), wherein the memory (405) is used to store instructions, the user interface (403) and the network interface (404) are used to communicate with other devices, and the processor (401) is used to execute the instructions stored in the memory (405) so that the electronic device (400) executes the method according to any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that The computer-readable storage medium stores instructions, and when the instructions are executed, the method according to any one of claims 1 to 4 is performed.

Images