A weld tracking and deviation correction system and method for narrow gap automatic welding

Abstract

The present application relates to the technical field of welding, in particular to a kind of weld seam tracking deviation rectification system and method of narrow gap automatic welding, solve the traditional welding quality monitoring and deviation rectification method mainly rely on manual operation, there is the problem of low monitoring efficiency, prone to miss detection and inaccurate alarm, not representative;The weld seam tracking deviation rectification system includes the following modules: image acquisition module, image analysis module, data analysis module, tracking deviation rectification platform and deviation rectification alarm module;The weld seam tracking deviation rectification system realizes automation and efficient monitoring, realizes accurate tracking and timely deviation rectification to weld, optimizes welding effect, improves welding quality, effectively solves the problem of traditional manual monitoring method, improves the accuracy and efficiency of monitoring, in addition, the system also has real-time alarm function, and the alarm function is accurate, can discover and handle problems in time, ensure the safety of pipeline.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of welding, in particular to a weld tracking and deviation correction system and method for narrow-gap automatic welding. BACKGROUND

[0002] P92 is a high-alloy steel with high high-temperature creep strength and fatigue resistance, commonly used in high-temperature and high-pressure pipeline and component manufacturing, P92 steel pipe can be used in high-temperature and high-pressure pipeline system, such as high-temperature steam pipeline, high-temperature and high-pressure vessels and other fields in petroleum chemical industry, energy, power and other fields. The quality of the weld of the steel pipe directly affects the safe operation of the pipeline. With the development of industrial technology, the requirements for welding process are getting higher and higher, especially in narrow-gap automatic welding, because the welding gap is small, the precision and stability of the welding equipment are extremely high. In the welding process, weld deviation may occur, which will seriously affect the welding quality if not corrected in time. Therefore, the quality monitoring and deviation correction of the steel pipe weld are particularly important, however, the traditional welding quality monitoring and deviation correction method mainly relies on manual operation, which has the problems of low monitoring efficiency, easy to miss detection and inaccurate alarm, and is not representative. Therefore, it is of great practical significance to develop a weld tracking and deviation correction system and method for narrow-gap automatic welding which can realize automatic correction of weld deviation with high efficiency and accurate alarm. SUMMARY

[0003] In order to overcome the above technical problems, the purpose of the present application is to provide a weld tracking and deviation correction system and method for narrow-gap automatic welding: the image acquisition module is used to take pictures of the welding object to obtain the images of the pre-weld gap and the monitoring weld, the image analysis module is used to obtain the welding deviation parameters according to the images of the pre-weld gap and the monitoring weld, the welding deviation parameters include the lack of welding surface value, the hole gap value and the width difference value, the data analysis module is used to obtain the welding deviation coefficient according to the welding deviation parameters, the tracking and deviation correction platform is used to generate the deviation correction alarm instruction according to the welding deviation coefficient, and the deviation correction alarm instruction is sent to the deviation correction alarm module, the deviation correction alarm module rings the deviation correction alarm bell after receiving the deviation correction alarm instruction, which solves the problems of the traditional welding quality monitoring and deviation correction method mainly relying on manual operation, low monitoring efficiency, easy to miss detection and inaccurate alarm, and not representative.

[0004] The purpose of the present application can be achieved by the following technical solutions:

[0005] A weld tracking and deviation correction system for narrow-gap automatic welding, comprising:

[0006] An image acquisition module is used to take pictures of the pre-weld gap and the monitoring weld, and send the images of the pre-weld gap and the monitoring weld to the image analysis module;

[0007] The image analysis module is used to obtain welding deviation parameters based on images of the pre-weld gap and the monitored weld, and send the welding deviation parameters to the data analysis module; among them, the welding deviation parameters include the missing weld area value HM, the cavity value DF, and the width difference value KC;

[0008] The data analysis module is used to obtain the welding deviation coefficient HP based on the welding deviation parameters and send the welding deviation coefficient HP to the tracking and correction platform.

[0009] The tracking and correction platform is used to generate correction alarm commands based on the welding deviation coefficient HP, and send the correction alarm commands to the correction alarm module.

[0010] The correction alarm module is used to sound a correction alarm bell after receiving a correction alarm command.

[0011] As a further aspect of the present invention, the specific process by which the image acquisition module captures images of the pre-weld gap and the monitored weld is as follows:

[0012] The objects to be welded are brought together and the gap formed by the contact is marked as a pre-weld gap. The weld formed by welding using welding equipment is marked as a monitoring weld. Images of the pre-weld gap and the monitoring weld are captured using a high-definition camera and sent to an image analysis module. The object to be welded is a steel pipe, specifically a P92 steel pipe with a specification of φ550×94mm.

[0013] As a further aspect of the present invention, the specific process by which the image analysis module obtains the welding deviation parameters is as follows:

[0014] Obtain the edge contour of the pre-weld gap image, obtain the position of the pre-weld gap image based on the coordinates of each point on the edge contour, and mark it as the gap region. Obtain the edge contour of the monitored weld image, obtain the position of the monitored weld image based on the coordinates of each point on the edge contour, and mark it as the weld region. Obtain the overlapping area of ​​the gap region and the weld region and the total area of ​​the gap region, obtain the area difference between the two, and mark it as the missing weld surface value HM.

[0015] The number of holes and cracks on the monitored weld images is obtained and labeled as hole value DS and crack value FS, respectively. The hole value DS and crack value FS are quantized, their values ​​are extracted, and then substituted into a formula for calculation. The hole and seam value DF is obtained, where s1 and s2 are the preset proportional coefficients corresponding to the set hole value DS and seam value FS, respectively. s1 and s2 satisfy s1+s2=1, 0<s1<s2<1, and take s1=0.38 and s2=0.62.

[0016] Obtain the maximum and minimum widths on the image of the monitored weld, find the width difference between the two, and label it as the width difference KC;

[0017] The missing weld value HM, the cavity value DF, and the width difference value KC are sent to the data analysis module.

[0018] As a further aspect of the present invention, the specific process by which the data analysis module obtains the welding deviation coefficient HP is as follows:

[0019] The missing weld area value HM, the cavity value DF, and the width difference KC are quantified, and their values ​​are extracted. These values ​​are then substituted into the formula for calculation. The welding deviation coefficient HP is obtained, where e and π are mathematical constants, and p1, p2 and p3 are preset weighting factors corresponding to the set missing weld surface value HM, the hole gap value DF and the width difference value KC, respectively. p1, p2 and p3 satisfy p1>p2>p3>1.213, and we take p1=1.82, p2=1.65 and p3=1.44.

[0020] The welding deviation coefficient HP is sent to the tracking and correction platform.

[0021] As a further aspect of the present invention, the specific process by which the tracking and correction platform generates correction alarm commands is as follows:

[0022] The welding deviation coefficient HP is compared with the preset welding deviation threshold HPy:

[0023] If the welding deviation coefficient HP ≥ welding deviation threshold HPy, then the type of the welding object corresponding to the welding deviation coefficient HP is marked as a welding defective object.

[0024] If the welding deviation coefficient HP < welding deviation threshold HPy, then the type of the welding object corresponding to the welding deviation coefficient HP is marked as a qualified welding object.

[0025] The first defective weld is marked as a correction object, and a preset number of weld objects are recorded starting from the correction object.

[0026] Obtain the total number of non-conforming welds and mark them with the non-conformance value BS;

[0027] The number of times that two adjacent welded objects are both defective is obtained and marked as the consecutive defect value LC;

[0028] The non-conforming values ​​BS and LC are quantified to extract the hole value DS and seam value FS, which are then substituted into the formula for calculation. The anomaly coefficient YC is obtained, where π is a mathematical constant, and c1 and c2 are the preset proportional coefficients corresponding to the set non-conforming values ​​BS and consecutive non-conforming values ​​LC, respectively. c1 and c2 satisfy c1+c2=1, 0<c1<c2<1, and we take c1=0.41 and c2=0.59.

[0029] The anomaly coefficient YC is compared with the preset anomaly threshold YCy:

[0030] If the abnormal coefficient YC ≥ the abnormal threshold YCy, a correction alarm command is generated and sent to the correction alarm module.

[0031] As a further aspect of the present invention: a weld seam tracking and correction method for narrow-gap automatic welding, comprising the following steps:

[0032] Step 1: The image acquisition module takes pictures of the welding object to obtain images of the pre-weld gap and the monitored weld, and sends the images of the pre-weld gap and the monitored weld to the image analysis module;

[0033] The specific process is as follows: the objects to be welded are brought together and the gap formed by the contact of the objects is marked as the pre-weld gap, and the weld formed by welding with welding equipment is marked as the monitoring weld. The image acquisition module uses a high-definition camera to capture images of the pre-weld gap and the monitoring weld, and sends the images of the pre-weld gap and the monitoring weld to the image analysis module.

[0034] Step 2: The image analysis module obtains welding deviation parameters based on the images of the pre-weld gap and the monitored weld. The welding deviation parameters include the missing weld area value HM, the cavity value DF, and the width difference value KC, and sends the welding deviation parameters to the data analysis module.

[0035] The specific process is as follows: The image analysis module obtains the edge contour of the image of the pre-weld gap, obtains the position of the image of the pre-weld gap according to the coordinates of each point on the edge contour, and marks it as the gap area; the image of the monitored weld is obtained, the position of the image of the monitored weld is obtained according to the coordinates of each point on the edge contour, and marked as the weld area; the overlapping area of ​​the gap area and the weld area and the total area of ​​the gap area are obtained, the area difference between the two is obtained, and it is marked as the missing weld surface value HM;

[0036] The image analysis module acquires the number of holes and cracks in the monitored weld images and labels them as hole value DS and crack value FS, respectively. The hole value DS and crack value FS are quantized, their values ​​are extracted, and then substituted into a formula for calculation. The hole and seam value DF is obtained, where s1 and s2 are the preset proportional coefficients corresponding to the set hole value DS and seam value FS, respectively. s1 and s2 satisfy s1+s2=1, 0<s1<s2<1, and take s1=0.38 and s2=0.62.

[0037] The image analysis module obtains the maximum and minimum widths of the monitored weld seam in the image, acquires the width difference between the two, and marks it as the width difference KC.

[0038] The image analysis module sends the missing weld surface value HM, the cavity gap value DF, and the width difference value KC to the data analysis module;

[0039] Step 3: The data analysis module obtains the welding deviation coefficient HP based on the welding deviation parameters and sends the welding deviation coefficient HP to the tracking and correction platform;

[0040] The specific process is as follows:

[0041] The data analysis module quantifies the missing weld area value HM, the cavity value DF, and the width difference KC, extracts the values ​​of these three values, and substitutes them into the formula for calculation. The welding deviation coefficient HP is obtained, where e and π are mathematical constants, and p1, p2 and p3 are preset weighting factors corresponding to the set missing weld surface value HM, the hole gap value DF and the width difference value KC, respectively. p1, p2 and p3 satisfy p1>p2>p3>1.213, and we take p1=1.82, p2=1.65 and p3=1.44.

[0042] The data analysis module sends the welding deviation coefficient HP to the tracking and correction platform;

[0043] Step 4: The tracking and correction platform generates a correction alarm command based on the welding deviation coefficient HP, and sends the correction alarm command to the correction alarm module;

[0044] The specific process is as follows:

[0045] The tracking and correction platform compares the welding deviation coefficient HP with the preset welding deviation threshold HPy:

[0046] If the welding deviation coefficient HP ≥ welding deviation threshold HPy, then the type of the welding object corresponding to the welding deviation coefficient HP is marked as a welding defective object.

[0047] If the welding deviation coefficient HP < welding deviation threshold HPy, then the type of the welding object corresponding to the welding deviation coefficient HP is marked as a qualified welding object.

[0048] The tracking and correction platform marks the first non-conforming weld as the correction object, and records the type of a preset number of weld objects starting from the correction object;

[0049] The tracking and correction platform obtains the total number of non-conforming welds and marks them with a non-conforming value BS.

[0050] The tracking and correction platform obtains the number of times that two adjacent welded objects are both unqualified, and marks them as the consecutive difference value LC.

[0051] The tracking and correction platform quantifies the non-conforming values ​​BS and LC, extracts the hole values ​​DS and seam values ​​FS, and substitutes them into the formula for calculation. The anomaly coefficient YC is obtained, where π is a mathematical constant, and c1 and c2 are the preset proportional coefficients corresponding to the set non-conforming values ​​BS and consecutive non-conforming values ​​LC, respectively. c1 and c2 satisfy c1+c2=1, 0<c1<c2<1, and we take c1=0.41 and c2=0.59.

[0052] The tracking and correction platform compares the anomaly coefficient YC with the preset anomaly threshold YCy:

[0053] If the abnormality coefficient YC ≥ the abnormality threshold YCy, a correction alarm command is generated and sent to the correction alarm module.

[0054] Step 5: After receiving the correction alarm command, the correction alarm module will sound the correction alarm bell.

[0055] The beneficial effects of this invention are:

[0056] This invention discloses a weld seam tracking and correction system and method for narrow-gap automatic welding. An image acquisition module captures images of the welding object, obtaining images of the pre-weld gap and the monitored weld seam. An image analysis module obtains welding deviation parameters based on these images, including the value of missing weld area, the value of punctures, and the width difference. A data analysis module obtains a welding deviation coefficient based on these parameters. A tracking and correction platform generates a correction alarm command based on the welding deviation coefficient and sends it to a correction alarm module. Upon receiving the correction alarm command, the correction alarm module sounds a correction alarm. This weld seam tracking and correction system obtains welding deviation parameters through analysis of the pre-weld gap and the monitored weld seam. The welding deviation coefficient obtained from these parameters comprehensively measures the degree of deviation in welding the pre-weld gap; a larger welding deviation coefficient indicates a greater degree of deviation. The higher the degree of deviation, the more unreasonable the monitored weld is, requiring follow-up and correction of deviations in subsequent welding work. If a non-conforming weld is found, tracking begins to obtain an anomaly coefficient. The anomaly coefficient measures whether the weld deviation is accidental or widespread. A small anomaly coefficient indicates that the weld deviation is accidental, and subsequent automatic correction restores the welding process to normal. A large anomaly coefficient indicates that the weld deviation is widespread, and weld deviations continue to occur, requiring alarm and maintenance. This weld tracking and correction system achieves automated and highly efficient monitoring, enabling precise tracking and timely correction of welds, optimizing welding effects, improving welding quality, effectively solving the problems of traditional manual monitoring methods, and improving the accuracy and efficiency of monitoring. In addition, the system also has a real-time alarm function with high accuracy, enabling timely detection and handling of problems, ensuring pipeline safety. Attached Figure Description

[0057] The invention will now be further described with reference to the accompanying drawings.

[0058] Figure 1 This is a schematic diagram of a weld seam tracking and correction system for narrow-gap automatic welding according to the present invention. Detailed Implementation

[0059] The technical solutions of the present invention will be clearly and completely described below with reference to the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0060] Example 1:

[0061] Please see Figure 1As shown, this embodiment is a weld seam tracking and correction system for narrow gap automatic welding, including the following modules: image acquisition module, image analysis module, data analysis module, tracking and correction platform, and correction alarm module;

[0062] The image acquisition module is used to capture images of the pre-weld gap and the monitored weld, and send the images of the pre-weld gap and the monitored weld to the image analysis module;

[0063] The image analysis module is used to obtain welding deviation parameters based on images of the pre-weld gap and the monitored weld, and send the welding deviation parameters to the data analysis module; the welding deviation parameters include the missing weld area value HM, the cavity value DF, and the width difference value KC;

[0064] The data analysis module is used to obtain the welding deviation coefficient HP based on the welding deviation parameters and send the welding deviation coefficient HP to the tracking and correction platform.

[0065] The tracking and correction platform is used to generate a correction alarm command based on the welding deviation coefficient HP, and send the correction alarm command to the correction alarm module.

[0066] The correction alarm module is used to sound a correction alarm bell after receiving a correction alarm command.

[0067] Example 2:

[0068] This embodiment describes a weld seam tracking and correction method for narrow-gap automatic welding, including the following steps:

[0069] Step 1: The image acquisition module takes pictures of the welding object to obtain images of the pre-weld gap and the monitored weld, and sends the images of the pre-weld gap and the monitored weld to the image analysis module;

[0070] The specific process is as follows: the objects to be welded are brought together and the gap formed by the contact of the objects is marked as the pre-weld gap, and the weld formed by welding with welding equipment is marked as the monitoring weld. The image acquisition module uses a high-definition camera to capture images of the pre-weld gap and the monitoring weld, and sends the images of the pre-weld gap and the monitoring weld to the image analysis module.

[0071] Step 2: The image analysis module obtains welding deviation parameters based on the images of the pre-weld gap and the monitored weld. The welding deviation parameters include the missing weld area value HM, the cavity value DF, and the width difference value KC, and sends the welding deviation parameters to the data analysis module.

[0072] The specific process is as follows: The image analysis module obtains the edge contour of the image of the pre-weld gap, obtains the position of the image of the pre-weld gap according to the coordinates of each point on the edge contour, and marks it as the gap area; the image of the monitored weld is obtained, the position of the image of the monitored weld is obtained according to the coordinates of each point on the edge contour, and marked as the weld area; the overlapping area of ​​the gap area and the weld area and the total area of ​​the gap area are obtained, the area difference between the two is obtained, and it is marked as the missing weld surface value HM;

[0073] The image analysis module acquires the number of holes and cracks in the monitored weld images and labels them as hole value DS and crack value FS, respectively. The hole value DS and crack value FS are quantized, their values ​​are extracted, and then substituted into a formula for calculation. The hole and seam value DF is obtained, where s1 and s2 are the preset proportional coefficients corresponding to the set hole value DS and seam value FS, respectively. s1 and s2 satisfy s1+s2=1, 0<s1<s2<1, and take s1=0.38 and s2=0.62.

[0074] The image analysis module obtains the maximum and minimum widths of the monitored weld seam in the image, acquires the width difference between the two, and marks it as the width difference KC.

[0075] The image analysis module sends the missing weld surface value HM, the cavity gap value DF, and the width difference value KC to the data analysis module;

[0076] Step 3: The data analysis module obtains the welding deviation coefficient HP based on the welding deviation parameters and sends the welding deviation coefficient HP to the tracking and correction platform;

[0077] The specific process is as follows:

[0078] The data analysis module quantifies the missing weld area value HM, the cavity value DF, and the width difference KC, extracts the values ​​of these three values, and substitutes them into the formula for calculation. The welding deviation coefficient HP is obtained, where e and π are mathematical constants, and p1, p2 and p3 are preset weighting factors corresponding to the set missing weld surface value HM, the hole gap value DF and the width difference value KC, respectively. p1, p2 and p3 satisfy p1>p2>p3>1.213, and we take p1=1.82, p2=1.65 and p3=1.44.

[0079] The data analysis module sends the welding deviation coefficient HP to the tracking and correction platform;

[0080] Step 4: The tracking and correction platform generates a correction alarm command based on the welding deviation coefficient HP, and sends the correction alarm command to the correction alarm module;

[0081] The specific process is as follows:

[0082] The tracking and correction platform compares the welding deviation coefficient HP with the preset welding deviation threshold HPy:

[0083] If the welding deviation coefficient HP ≥ welding deviation threshold HPy, then the type of the welding object corresponding to the welding deviation coefficient HP is marked as a welding defective object.

[0084] If the welding deviation coefficient HP < welding deviation threshold HPy, then the type of the welding object corresponding to the welding deviation coefficient HP is marked as a qualified welding object.

[0085] The tracking and correction platform marks the first non-conforming weld as the correction object, and records the type of a preset number of weld objects starting from the correction object;

[0086] The tracking and correction platform obtains the total number of non-conforming welds and marks them with a non-conforming value BS.

[0087] The tracking and correction platform obtains the number of times that two adjacent welded objects are both unqualified, and marks them as the consecutive difference value LC.

[0088] The tracking and correction platform quantifies the non-conforming values ​​BS and LC, extracts the hole values ​​DS and seam values ​​FS, and substitutes them into the formula for calculation. The anomaly coefficient YC is obtained, where π is a mathematical constant, and c1 and c2 are the preset proportional coefficients corresponding to the set non-conforming values ​​BS and consecutive non-conforming values ​​LC, respectively. c1 and c2 satisfy c1+c2=1, 0<c1<c2<1, and we take c1=0.41 and c2=0.59.

[0089] The tracking and correction platform compares the anomaly coefficient YC with the preset anomaly threshold YCy:

[0090] If the abnormality coefficient YC ≥ the abnormality threshold YCy, a correction alarm command is generated and sent to the correction alarm module.

[0091] Step 5: After receiving the correction alarm command, the correction alarm module will sound the correction alarm bell.

[0092] In the description of this specification, references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0093] The above description is merely an example and illustration of the present invention. Those skilled in the art can make various modifications or additions to the specific embodiments described, or use similar methods to replace them, as long as they do not deviate from the invention or exceed the scope defined in the claims, all of which should fall within the protection scope of the present invention.

Claims

1. A weld seam tracking and correction system for narrow-gap automatic welding, characterized in that, include: The image acquisition module is used to capture images of the pre-weld gap and the monitored weld, and send the images of the pre-weld gap and the monitored weld to the image analysis module; The image analysis module is used to obtain welding deviation parameters based on images of the pre-weld gap and the monitored weld, and then send these parameters to the data analysis module. The welding deviation parameters include the missing weld area value (HM), the cavity value (DF), and the width difference value (KC). The specific process by which the image analysis module obtains the welding deviation parameters is as follows: Obtain the edge contour of the pre-weld gap image, obtain the position of the pre-weld gap image based on the coordinates of each point on the edge contour, and mark it as the gap region. Obtain the edge contour of the monitored weld image, obtain the position of the monitored weld image based on the coordinates of each point on the edge contour, and mark it as the weld region. Obtain the overlapping area of ​​the gap region and the weld region and the total area of ​​the gap region, obtain the area difference between the two, and mark it as the missing weld surface value HM. The number of pores and cracks on the monitored weld images are obtained and labeled as pore value DS and crack value FS, respectively. The pore value DS and crack value FS are then quantified according to the formula... The hole and seam value DF is obtained, where s1 and s2 are the preset proportional coefficients corresponding to the set hole value DS and seam value FS, respectively. Obtain the maximum and minimum widths on the image of the monitored weld, find the width difference between the two, and label it as the width difference KC; Send the missing weld value HM, the cavity value DF, and the width difference value KC to the data analysis module; The data analysis module is used to quantify the missing weld area value (HM), the cavity gap value (DF), and the width difference value (KC) according to the formula. The welding deviation coefficient HP is obtained, where e and π are mathematical constants, and p1, p2 and p3 are preset weighting factors corresponding to the set missing weld surface value HM, the hole gap value DF and the width difference value KC, respectively. The welding deviation coefficient HP is then sent to the tracking and correction platform. The tracking and correction platform is used to generate correction alarm commands based on the welding deviation coefficient HP, and send the correction alarm commands to the correction alarm module. The correction alarm module is used to sound a correction alarm bell after receiving a correction alarm command.

2. The weld seam tracking and correction system for narrow-gap automatic welding according to claim 1, characterized in that, The specific process by which the image acquisition module captures images of the pre-weld gap and the monitored weld is as follows: The objects to be welded are brought together and the gap formed by the contact is marked as a pre-weld gap. The weld formed by welding with welding equipment is marked as a monitoring weld. Images of the pre-weld gap and the monitoring weld are captured by a high-definition camera and sent to the image analysis module.

3. The weld seam tracking and correction system for narrow-gap automatic welding according to claim 2, characterized in that, The object to be welded is a steel pipe, which is a P92 steel pipe with a specification of φ550×94mm.

4. The weld seam tracking and correction system for narrow-gap automatic welding according to claim 1, characterized in that, The specific process by which the data analysis module obtains the welding deviation coefficient HP is as follows: The weld deviation coefficient HP is obtained by quantifying the missing weld area value HM, the cavity value DF, and the width difference value KC. The welding deviation coefficient HP is sent to the tracking and correction platform.

5. The weld seam tracking and correction system for narrow-gap automatic welding according to claim 1, characterized in that, The specific process by which the tracking and correction platform generates correction alarm commands is as follows: The welding deviation coefficient HP is compared with the preset welding deviation threshold HPy: If the welding deviation coefficient HP ≥ welding deviation threshold HPy, then the type of the welding object corresponding to the welding deviation coefficient HP is marked as a welding defective object. The first defective weld is marked as a correction object, and a preset number of weld objects are recorded starting from the correction object. Obtain the total number of non-conforming welds and mark them with the non-conformance value BS; The number of times that two adjacent welded objects are both defective is obtained and marked as the consecutive defect value LC; The non-consistent values ​​BS and consecutive values ​​LC are quantized according to the formula. The anomaly coefficient YC is obtained, where π is a mathematical constant, and c1 and c2 are preset proportional coefficients corresponding to the set non-conforming values ​​BS and consecutive non-conforming values ​​LC, respectively. The anomaly coefficient YC is compared with the preset anomaly threshold YCy: If the abnormal coefficient YC ≥ the abnormal threshold YCy, a correction alarm command is generated and sent to the correction alarm module.

6. The weld seam tracking and correction system for narrow-gap automatic welding according to claim 5, characterized in that, If the welding deviation coefficient HP < welding deviation threshold HPy, then the type of the welding object corresponding to the welding deviation coefficient HP is marked as a qualified welding object.

7. A method for weld seam tracking and correction in a narrow-gap automatic welding system according to any one of claims 1-6, characterized in that, Includes the following steps: Step 1: The image acquisition module takes pictures of the welding object to obtain images of the pre-weld gap and the monitored weld, and sends the images of the pre-weld gap and the monitored weld to the image analysis module; Step 2: The image analysis module obtains welding deviation parameters based on the images of the pre-weld gap and the monitored weld. The welding deviation parameters include the missing weld area value HM, the cavity value DF, and the width difference value KC, and sends the welding deviation parameters to the data analysis module. Step 3: The data analysis module obtains the welding deviation coefficient HP based on the welding deviation parameters and sends the welding deviation coefficient HP to the tracking and correction platform.

8. The weld seam tracking and correction method for narrow-gap automatic welding according to claim 7, characterized in that, It also includes the following steps: The tracking and correction platform generates a correction alarm command based on the welding deviation coefficient HP and sends the correction alarm command to the correction alarm module. Upon receiving a correction alarm command, the correction alarm module will sound a correction alarm bell.

Images