An AI-based optimization analysis method for arc plate welding processes

Abstract

This invention belongs to the field of welding process optimization technology, specifically disclosing an artificial intelligence-based method for optimizing and analyzing the welding process of curved plates. By identifying the position and geometric contour of the areas to be welded on the surface of the curved plate workpiece, and determining the first welding area based on the position information, the stress distribution on the surface of the curved plate workpiece is detected after the first welding area is completed. Based on this, the welding sequence of subsequent areas to be welded is determined until all areas are welded. This method can minimize the deformation and stress concentration of the workpiece during welding, thereby significantly reducing the incidence of additional workpiece correction. Simultaneously, during the welding of each area, the welding temperature is collected in real time and temperature gradient analysis is performed. The welding parameters are then dynamically adjusted based on the temperature gradient to maintain a stable temperature gradient, which can reduce the thermal stress and shrinkage effect of the workpiece to a certain extent, thereby reducing the risk of welding deformation.

Description

Technical Field

[0001] This invention belongs to the field of welding process optimization technology, and specifically discloses an artificial intelligence-based method for optimizing and analyzing the welding process of curved plates. Background Art

[0002] Welding, as a key manufacturing process, has a wide range of applications in modern society. Because the welding process involves highly complex physical phenomena, significant uncertainties, variability, and multivariate coupling characteristics, it is difficult to guarantee consistent and high-quality welding results every time without targeted optimization and adjustments. Therefore, in practice, it is usually necessary to optimize and adjust the welding procedures to achieve high-quality welding.

[0003] There are already various optimization schemes for welding processes in the existing technology. For example, Chinese invention patent with publication number CN111461398A proposes a welding process parameter optimization method based on a neural network model. By training the neural network with training samples, a nonlinear mapping relationship between actual welding process parameters and penetration depth data is established. By utilizing the predictive ability of the trained neural network model, the actual process parameter combination is continuously adjusted to make it approach the optimal process parameter combination corresponding to the target penetration depth data, thereby simplifying the welding parameter adjustment process and improving welding quality.

[0004] For example, Chinese invention patent CN118863159A proposes a method and system for dynamic optimization of weld processes combined with tracking and monitoring. This method involves acquiring historical welding record sets, analyzing these records based on the target welding scenario to determine a calibrated welding process set, configuring a look-ahead acquisition step size, initializing and activating the weld acquisition component for continuous acquisition, and obtaining weld contour data. A displacement weld model containing multiple weld cross-sections is generated through 3D reconstruction. A set of weld feature parameters is extracted and used as an index constraint to traverse the calibrated welding process set for matching, obtaining a welding process sequence. Based on the welding process sequence, continuous welding control of the target weld is performed, and the tracking and monitoring component is activated to continuously monitor the welding results, generate welding feedback information, and respond to the welding process accordingly, thereby improving the dynamic adjustment capability of the welding process.

[0005] While the aforementioned technical solutions have made significant progress in optimizing welding process parameters, they primarily focus on optimizing parameters such as welding speed and current, neglecting the importance of the welding sequence. Specifically, in actual welding operations, workpieces typically contain multiple welding areas. If the welding sequence of these areas is not rationally planned and is arbitrarily selected, it may lead to inconsistent heat input and cooling rates in different welding areas, resulting in localized stress concentration and increasing the risk of crack formation. Furthermore, the thermal stress and shrinkage effects generated during welding can cause workpiece deformation, requiring additional workpiece straightening after welding, increasing production costs and time. This characteristic is particularly evident in the welding of curved plates. Curved plates have complex geometries, and the stress distribution varies significantly at different locations during welding, easily leading to stress concentration. Curved plates are widely used not only in traditional manufacturing but also in emerging technology fields such as aerospace, shipbuilding, and energy infrastructure. Therefore, optimizing the welding sequence is especially necessary in the optimization of curved plate welding processes. Summary of the Invention

[0006] Therefore, one objective of this application is to provide an artificial intelligence-based method for optimizing the welding process of curved plates, thereby solving the problems mentioned in the background art by optimizing the welding sequence for multiple welding areas of curved plate workpieces.

[0007] The purpose of this invention can be achieved through the following technical solution: an artificial intelligence-based method for optimizing the welding process of arc plate, comprising the following steps: (1) marking the areas to be welded on the surface of the arc plate workpiece, and performing high-resolution image acquisition on the marked workpiece surface, and then locating the position of each area to be welded from the acquired image, while capturing the geometric contour of each area to be welded.

[0008] (2) Determine the first welding area based on the location of each area to be welded.

[0009] (3) During the welding process in the first welding area, the welding temperature of the arc plate workpiece is collected, and the temperature gradient analysis is performed based on the collected welding temperature, thereby dynamically adjusting the welding parameters.

[0010] (4) After the first welding area is completed, stress distribution detection is performed on the arc plate workpiece, and the subsequent welding areas are determined in sequence according to the stress distribution detection results. Temperature gradient analysis and dynamic adjustment of welding parameters are performed on each subsequent welding area until the welding of all welding areas is completed.

[0011] (5) After completing the welding of all areas to be welded on the arc plate, the surface of the arc plate is image acquired, and stress defect detection and quality evaluation of the arc plate welding sequence optimization are performed from the acquired surface images of the arc plate.

[0012] Combining all the above technical solutions, the positive effects of this invention are as follows: 1. This invention accurately identifies the position and geometric contour of the area to be welded on the surface of the arc-shaped plate workpiece, and determines the first welding area based on this information. Subsequently, after completing the welding of the first welding area, stress distribution detection is performed on the surface of the arc-shaped plate workpiece. Based on the stress distribution detection results, the welding sequence of subsequent areas to be welded is further optimized and determined until all areas to be welded are completed. This method can minimize the deformation and stress concentration of the workpiece during the welding process, thereby significantly reducing the incidence of additional workpiece correction, and ultimately achieving the goal of reducing welding costs and time.

[0013] 2. During the welding of each area to be welded, this invention collects the welding temperature in real time and performs temperature gradient analysis. Then, it dynamically adjusts the welding parameters according to the temperature gradient to maintain a stable temperature gradient. This can reduce the thermal stress and shrinkage effect of the workpiece to a certain extent, thereby reducing the risk of welding deformation. In addition, the analysis of the temperature gradient is fed back to the adjustment of welding parameters to achieve closed-loop control, ensuring that the parameters are always in the optimal state during the welding process, which is conducive to maintaining the stability of welding quality.

[0014] 3. After completing the welding of all areas to be welded on the arc plate, the present invention acquires images of the arc plate surface and performs stress defect detection from the acquired images of the arc plate surface. This enables the quality evaluation of the arc plate welding sequence optimization and realizes the feasibility evaluation of the arc plate welding sequence optimization. It can intuitively provide welding managers with specific optimization basis, enabling welding managers to make more scientific process optimization and management decisions. Attached Figure Description

[0015] The present invention will be further described with reference to the accompanying drawings, but the embodiments in the drawings do not constitute any limitation on the present invention. For those skilled in the art, other drawings can be obtained based on the following drawings without creative effort.

[0016] Figure 1 This is a diagram illustrating the implementation steps of the method of the present invention.

[0017] Figure 2 This is a planar schematic diagram of the center distance and boundary distance of the area to be welded on the surface of the arc-shaped plate in this invention.

[0018] Figure 3 This is a flowchart illustrating the dynamic adjustment of welding parameters for the area to be welded in this invention. Detailed Implementation

[0019] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. 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 skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] See Figure 1 As shown, the present invention proposes an artificial intelligence-based method for optimizing the welding process of arc plate, including the following steps: (1) Marking the areas to be welded on the surface of the arc plate workpiece, and performing high-resolution image acquisition on the marked workpiece surface, and then locating the position of each area to be welded from the acquired image, while capturing the geometric contour of each area to be welded.

[0021] It is important to know that marking the areas to be welded on the surface of the curved plate workpiece according to the welding design drawings before welding can ensure that the welder can accurately find and perform the welding operation, avoiding welding deviations caused by inaccurate positioning.

[0022] When marking the area to be welded, a laser line marker can be used to project the outline of the weld seam onto the workpiece surface. Compared with the traditional manual marking method, the laser line marker reduces human error and can precisely control the size and spacing of the weld seam, ensuring that the position of each welding area meets the design requirements. In addition, the laser line marker can complete the marking of the weld seam outline in a short time, which significantly improves marking efficiency and shortens preparation time.

[0023] To apply the above scheme, the geometric contours of each area to be welded are captured as follows: the surface image of the curved plate workpiece is focused on each area to be welded, and the contour lines of each area to be welded are extracted by contour detection.

[0024] It should be added that after acquiring the surface image of the curved plate workpiece, image preprocessing is required, such as noise reduction and contrast enhancement. Noise reduction removes noise from the image and improves image quality, while contrast enhancement uses methods such as histogram equalization to enhance image contrast and make the markings more obvious.

[0025] The geometric contour of the area to be welded is obtained based on the contour lines of each area to be welded.

[0026] (2) Determine the first welding area based on the location of each area to be welded, specifically as follows: extract the boundary contour of the arc plate from the surface image of the arc plate workpiece, and mark the center point and boundary turning point based on the boundary contour.

[0027] The center point mentioned above is the geometric center point (centroid) for calculating the workpiece boundary profile. Boundary inflection points are key inflection points on the boundary profile (such as corners, protrusions, etc.), and these points are usually locations with significant structural changes.

[0028] For each area to be welded, calculate the distance between its geometric center and the center point of the workpiece, and denot it as the center distance.

[0029] Calculate the distance between the geometric center of each region to be welded and all boundary inflection points, and select the minimum value as the boundary distance. See also... Figure 2 As shown.

[0030] Compare the center distance and boundary distance of each area to be welded. If the center distance of an area to be welded is less than the boundary distance, the position of the area to be welded is biased towards the center; otherwise, the position of the area to be welded is biased towards the boundary.

[0031] It is important to understand that the center-biased area to be welded is usually located near the center of gravity of the workpiece, and the welding has less impact on the overall structure, which helps to maintain the stability of the workpiece.

[0032] The weldable area with a biased boundary is usually located at the edge of the workpiece or in a location with significant structural changes, and may have a significant impact on the local stress distribution during welding.

[0033] Identify whether there are center-biased areas among the positional biases of each area to be soldered. If so, count the number of center-biased areas to be soldered.

[0034] If there is only one, then that area to be welded is taken as the first welding area. If there is more than one, then the area to be welded with the shortest distance from the center of each area to the center of the area to be welded is taken as the first welding area.

[0035] It is important to emphasize that by prioritizing the area near the center of gravity as the first welding area, the workpiece can maintain high stability throughout the welding process, thereby improving welding accuracy. In addition, starting welding near the center of gravity allows the stress generated during the welding process to be transferred more evenly to the entire workpiece, avoiding structural problems caused by excessive local stress.

[0036] If there are no center-biased areas to be welded, then the maximum and minimum values ​​of the distances between the geometric center of each area to be welded and all boundary inflection points are extracted, and these values ​​are combined with the boundary distances to calculate the center proximity. The specific calculation formula is as follows: In the formula Indicates the proximity to the center. , These represent the maximum distance between the geometric center of the area to be welded and all boundary inflection points, and the boundary distance, respectively. This represents the sum of the boundary distances of all areas to be welded, and the area with the greatest center proximity is then selected as the first area to be welded.

[0037] It should be noted that when there are no center-biased areas to be welded, it means that all areas to be welded are boundary-biased areas. In this case, simply selecting the area with the largest boundary distance as the first welding area is a feasible method, because the larger the boundary distance, the closer the area is to the geometric center of the curved plate workpiece surface. However, to more accurately determine the first welding area, the above method comprehensively analyzes the boundary distance of the area to be welded and the distance difference between the geometric center and all boundary inflection points to evaluate the center proximity of the area to be welded. The boundary distance is defined as the shortest distance between the geometric center of the area to be welded and all boundary inflection points, reflecting the position of the area relative to the edge of the workpiece. The distance difference is defined as the difference in distance between the geometric center of the area to be welded and all boundary inflection points, reflecting the uniformity of the distance between the area and each boundary inflection point. The larger the distance difference, the more uneven the distance between the area to be welded and each boundary inflection point, indicating that the area is more biased towards a certain boundary inflection point, and its geometric center has poor symmetry with the overall structure of the workpiece. By comprehensively analyzing the boundary distance and distance difference of each area to be welded, the center proximity of each area to be welded can be calculated. The area to be welded with a higher center proximity indicates that its geometric center is closer to the overall geometric center of the workpiece, and the distance between it and each boundary turning point is more uniform. Selecting the area to be welded with a high center proximity as the first welding area helps to reduce stress concentration during the welding process and ensure the overall stability of the workpiece.

[0038] (3) During the welding process in the first welding area, the welding temperature of the arc plate workpiece is collected, and the temperature gradient analysis is performed based on the collected welding temperature, thereby dynamically adjusting the welding parameters.

[0039] In the above-mentioned scheme, the welding temperature acquisition is implemented as follows: During the welding process in the first welding area, an infrared thermal imager is used to acquire thermal images of the arc-shaped plate workpiece, and the area is marked from the thermal image according to the geometric contour of the first welding area.

[0040] The welding temperature of the first welding area is determined by comparing the chromaticity values ​​of the marked area with the correspondence between chromaticity and temperature in the thermal image.

[0041] The correspondence between chromaticity and temperature in the above-mentioned thermal images can be established by creating a calibration curve or lookup table between chromaticity values ​​and temperature, which is usually provided by the infrared thermal imager manufacturer or obtained through laboratory calibration.

[0042] It is important to understand that infrared thermal imagers can measure temperature without contacting the workpiece, avoiding interference with the welding process and ensuring that the welding quality is not affected. In addition, infrared thermal imagers can provide high-resolution temperature distribution maps, ensuring the accuracy of welding temperature.

[0043] In a further implementation of the above scheme, the temperature gradient analysis is performed as follows: the temperature gradient of the first welded area at different acquisition times is obtained by subtracting the welding temperature of the first welded area at the current acquisition time from the welding temperature at the previous acquisition time.

[0044] In a further possible implementation of the above scheme, see [link to relevant documentation]. Figure 3 As shown, the dynamic adjustment of welding parameters is described in the following process: When welding the first welding area using welding equipment according to the preset welding parameters, the temperature gradient at each acquisition time is divided by the interval between adjacent acquisition times to obtain the temperature increase rate at each acquisition time.

[0045] The welding parameters mentioned above refer to welding speed and welding current. The preset welding parameters depend on the material type, material thickness, and weld type of the curved plate workpiece, and can be determined based on historical welding experience before welding.

[0046] The temperature increase rate of the first welding area at each acquisition time is compared with the set increase rate threshold. For example, the increase rate threshold is 40°C / min. If the temperature increase rate at a certain acquisition time is higher than the increase rate threshold, the first welding area is focused from the thermal image of the arc plate workpiece at the current acquisition time to identify whether there is oxidation in the weld of the first welding area. If there is oxidation, the welding current is reduced at the current acquisition time, and vice versa. If there is no temperature increase rate at a certain acquisition time that is higher than the increase rate threshold, the preset welding parameters are used to continue welding until the welding is completed.

[0047] It should be noted that during the welding process, the welding temperature often rises too quickly. This can be caused by improper settings of the welding current, voltage, or welding speed, which may lead to a rapid increase in temperature in localized areas. Additionally, when welding thick plates, the large heat capacity of the workpiece results in slow heat dissipation, making it difficult for the temperature in the welding area to dissipate, thus causing a rapid temperature increase. Furthermore, some materials have high thermal conductivity, allowing heat to easily dissipate during welding, but if not properly controlled, localized overheating may still occur. In such cases, it is necessary to adjust the welding parameters to mitigate the excessively rapid temperature increase.

[0048] It's important to explain that when the temperature increase reaches a threshold, the focus is on the first weld area to identify whether oxidation exists in the weld. This is because metals at high temperatures readily react with oxygen in the air to form an oxide layer. Oxidation not only affects the quality and appearance of the weld but also reduces the mechanical properties of the material. When oxidation is detected, it indicates that the welding area temperature is too high and oxidation has already occurred. Continuing to use the current welding parameters at this point will cause the oxide layer to expand further, affecting weld quality and material properties. Reducing the welding current is one of the most direct and effective methods to quickly reduce heat input to the welding area and prevent further oxidation. In addition, a lower current can also reduce the risk of welding stress and deformation.

[0049] If no oxidation is detected, it means the temperature of the current welding area is still within a controllable range and has not yet reached the critical oxidation temperature. In this case, heat input can be optimized by increasing the welding speed. Increasing the welding speed means reducing the time the welding head spends at each position, and consequently reducing the amount of heat input per unit area. This shortens the time the welding area is exposed to high temperatures, avoiding localized overheating. Furthermore, rapidly moving the welding head allows for a more even distribution of heat over a larger area, preventing prolonged exposure of localized areas to high temperatures and reducing the risk of oxidation. Increasing the welding speed also increases production efficiency and shortens welding time.

[0050] The oxidation phenomenon mentioned above can be identified by real-time monitoring of the temperature distribution in the welding area using an infrared thermal imager, which can identify high-temperature areas (usually areas with a high risk of oxidation).

[0051] In the example above, let's assume the initial settings for welding an arc-shaped plate: welding current set to 150A, welding speed to 5mm / s, and preset temperature increase threshold to 40°C / min.

[0052] If the temperature increase at the current acquisition moment exceeds 40°C / min, the initial welding area is extracted from the thermal image to analyze for oxidation. If oxidation is present (assuming the temperature exceeds 450°C), the welding current is reduced to 135A (a 10% decrease) to reduce heat input and prevent further oxidation. If no oxidation is present, the welding speed is increased to 6mm / s (a 20% increase) to shorten the heat input time per unit area and avoid localized overheating. Temperature changes during the welding process are continuously monitored, the effects of the adjustments are evaluated, and welding parameters are further fine-tuned based on feedback to ensure welding quality.

[0053] (4) After the first welding area is completed, stress distribution detection is performed on the arc plate workpiece, and the subsequent welding areas are determined in sequence according to the stress distribution detection results. Temperature gradient analysis and dynamic adjustment of welding parameters are performed on each subsequent welding area until the operation of all welding areas is completed.

[0054] Preferably, the stress distribution detection process is as follows: after welding is completed in the first welding area, multiple ultrasonic probes are used to emit ultrasonic pulses to the arc-shaped plate workpiece to ensure that the entire surface of the arc-shaped plate workpiece is covered, and the reflected ultrasonic signals are received. At the same time, the ultrasonic signal data is recorded and stress calculation is performed to obtain the stress value of the arc-shaped plate workpiece at different ultrasonic probe emission positions.

[0055] It should be noted that the use of ultrasound for distribution detection in curved plate workpieces is due to the influence of the propagation speed and attenuation of ultrasound waves within the material on the internal stress state. Specifically: in the absence of stress, the propagation speed and path of ultrasound waves are fixed; however, when stress is present, the propagation speed of ultrasound waves changes (usually slows down), and may result in displacement or deformation. Therefore, by analyzing the changes in the ultrasound signal, the internal stress state of the material can be inferred.

[0056] Ultrasonic stress distribution testing is a non-destructive testing method that does not cause any physical damage to the workpiece, ensuring the integrity of the workpiece and the safety of its subsequent use.

[0057] More preferably, the subsequent welding area is determined based on the stress distribution detection results as follows: a stress distribution diagram is drawn based on the stress values ​​of the arc-shaped plate workpiece at different ultrasonic probe emission positions.

[0058] Extract the boundary lines of each stress region from the stress distribution map and mark the stress values ​​of each stress region.

[0059] The stress region where the remaining area to be welded is located is determined by comparing the geometric contour of the remaining area to be welded with the boundary line of the stress region, and the stress value of the stress region where the remaining area to be welded is located is obtained.

[0060] In the specific implementation of the above scheme, the stress value of the stress region where the remaining area to be welded is located is obtained as follows: The number of stress regions involved in the remaining area to be welded is counted. If a remaining area to be welded is located within only one specific stress region, the stress value of that stress region is directly used as the stress value of the area to be welded. If a remaining area to be welded spans multiple stress regions, the stress values ​​of all stress regions involved in the area to be welded are compared, and the maximum value among these stress values ​​is selected as the stress value of the stress region where the area to be welded is located. This is because during the welding process, higher stress values ​​often correspond to higher risks (such as crack formation, deformation, etc.), and selecting the maximum stress value can obtain the stress situation of the area to be welded under the most unfavorable conditions.

[0061] The symmetrical region of the first welding area on the surface of the curved plate workpiece is determined based on the location of the first welding area on the surface of the curved plate workpiece.

[0062] The exemplary method for determining the symmetrical region of the first welding area on the surface of the curved plate workpiece is as follows: If the workpiece is symmetrical, a corresponding axis of symmetry can be defined. For example, assuming the workpiece is a circular plate, the axis of symmetry can be defined by the center of the circle, and the symmetrical region of the first welding area can be determined through geometric transformations (such as reflection transformation). For example, if the axis of symmetry is a straight line perpendicular to a certain direction, the coordinates of the symmetrical region can be obtained through reflection transformation.

[0063] The symmetrical distance between the remaining area to be welded and the first area is obtained by comparing the geometric center of the remaining area to be welded with the geometric center of the corresponding symmetrical area of ​​the first area to be welded.

[0064] Substitute the stress value of the stress region where the remaining area to be welded is located, along with the symmetrical distance between the remaining area to be welded and the first welded area, into the evaluation formula. The selection value of the remaining areas to be welded is obtained. In the formula This indicates the stress value of the stress region where the remaining area to be welded is located. This indicates the symmetrical distance between the remaining area to be welded and the area of ​​the first weld. This represents the sum of stress values ​​in the stress regions encompassing all remaining areas to be welded. This represents the sum of the symmetrical distances between all remaining areas to be welded and the first area to be welded.

[0065] Select the remaining welding area with the highest selection value from the remaining areas to be welded as the subsequent welding area.

[0066] This invention determines subsequent welding areas based on stress distribution detection of the curved plate workpiece after the initial welding area is completed. This determination is made by combining the stress value of the remaining welding area and the distance between the remaining welding area and the symmetrical area of ​​the initial welding area. The remaining welding area with the lowest stress value and the shortest distance to the symmetrical area of ​​the initial welding area is preferentially selected as the subsequent welding area. This is because prioritizing welding the area with the lowest stress value reduces local stress concentration, avoiding cracks and deformation caused by high stress, and providing a more stable starting point for subsequent welding. It also reduces quality problems caused by improper initial welding. Prioritizing welding the area symmetrical to the initial welding area maintains symmetry during the welding process, helps to evenly distribute the heat and stress generated during welding, and reduces the risk of overall structural deformation. Therefore, combining stress value and distance factors allows for more accurate selection of subsequent welding areas, ensuring that each welding operation is performed under optimal conditions and improving welding precision.

[0067] (5) After completing the welding of all areas to be welded on the arc plate, the surface of the arc plate is image acquired, and stress defects are detected from the acquired images of the arc plate surface to evaluate the quality of the arc plate welding sequence optimization.

[0068] In the above-mentioned scheme, the stress defect detection process is as follows: the surface image of the arc-shaped plate workpiece after welding and the surface image of the arc-shaped plate workpiece before welding are respectively used to extract the shape contour of the arc-shaped plate.

[0069] The shape profile of the arc plate after welding is aligned with that of the arc plate before welding, and the shape deformation is calculated accordingly.

[0070] Specifically, when aligning the arc plate shape contours before and after welding, geometric transformations (such as translation, rotation, and scaling) can be used to make the two contours coincide as much as possible. After alignment, the area difference between the regions enclosed by the contours before and after welding can be calculated by dividing the area enclosed by the arc plate shape contours before welding to obtain the shape deformation degree.

[0071] Crack identification was performed on the surface images of the arc-shaped plate workpiece after welding and before welding, and the crack initiation rate was calculated accordingly.

[0072] Specifically, crack identification can use methods such as gray-level co-occurrence matrix and wavelet transform to extract image features and identify potential crack areas. After crack identification, the number of cracks can be counted and the crack generation area can be marked. Then, the cracks identified on the surface of the arc plate workpiece after welding are compared with the cracks identified on the surface of the arc plate workpiece before welding. The number of newly generated cracks is divided by the number of cracks identified on the surface of the arc plate workpiece after welding to obtain the crack generation rate.

[0073] In a further feasible manner of the above scheme, the evaluation of the quality of the optimized arc plate welding sequence is carried out as follows: The shape deformation and crack initiation rate of the arc plate before welding sequence optimization are compared with those after welding sequence optimization, and an evaluation method is used. Optimize the welding sequence of the arc plate to obtain quality In the formula , These represent the degree of deformation of the arc-shaped plate before and after welding sequence optimization, respectively. , These represent the degree of new crack formation in the arc-shaped plate before and after welding sequence optimization, respectively.

[0074] It should be noted that by determining the welding method of subsequent welding areas based on the stress distribution on the workpiece surface after each welding, compared with arbitrary welding sequence settings, this stress analysis-based optimized welding sequence method can effectively reduce stress concentration during welding, further reducing the occurrence rate of workpiece deformation and cracks. Therefore, when performing welding sequence optimization quality analysis, the deformation degree and crack initiation degree of the arc plate after welding sequence optimization of the same specification and model workpiece are compared with the deformation degree and crack initiation degree of the arc plate before welding sequence optimization, so as to realize the quantification of welding sequence optimization quality.

[0075] This invention acquires images of the arc plate surface after welding all areas to be welded, and detects stress defects from the acquired images. This allows for quality evaluation of the arc plate welding sequence optimization, enabling a feasibility evaluation of the optimized arc plate welding sequence. It provides welding managers with specific optimization criteria, allowing them to make more scientific process optimization and management decisions.

[0076] The above description is merely an example and illustration of the structure 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 structure of the invention or exceed the scope defined by the present invention, they should all fall within the protection scope of the present invention.

Claims

1. A method for optimizing and analyzing the welding process of arc-shaped plates based on artificial intelligence, characterized in that, Includes the following steps: (1) Mark the areas to be welded on the surface of the arc plate workpiece, and perform high-resolution image acquisition on the marked workpiece surface. Then locate the position of each area to be welded from the acquired image, and capture the geometric contour of each area to be welded. (2) Determine the first welding area based on the location of each area to be welded; (3) During the welding process in the first welding area, the welding temperature of the arc plate workpiece is collected, and the temperature gradient analysis is performed based on the collected welding temperature, thereby dynamically adjusting the welding parameters. (4) After the first welding area is completed, stress distribution detection is performed on the arc plate workpiece, and the subsequent welding areas are determined in sequence according to the stress distribution detection results. Temperature gradient analysis and dynamic adjustment of welding parameters are performed on each subsequent welding area until the welding of all welding areas is completed. (5) After welding all areas of the arc plate, images of the arc plate surface are acquired, and stress defect detection and quality evaluation of the arc plate welding sequence optimization are performed from the acquired images of the arc plate surface; The process of determining the subsequent welding areas based on the stress distribution detection results is as follows: Stress distribution diagrams were drawn based on the stress values ​​of the arc-shaped plate workpiece at different ultrasonic probe emission positions. Extract the boundary lines of each stress region from the stress distribution map and mark the stress values ​​of each stress region; The stress region where the remaining area to be welded is located is determined by comparing the geometric contour of the remaining area to be welded with the boundary line of the stress region, and the stress value of the stress region where the remaining area to be welded is located is obtained. The symmetrical region of the first welding area on the surface of the curved plate workpiece is determined based on the location of the first welding area on the surface of the curved plate workpiece. The symmetrical distance between the remaining area to be welded and the first welded area is obtained by comparing the geometric center of the remaining area to be welded with the geometric center of the corresponding symmetrical area of ​​the first welded area. Substitute the stress value of the stress region where the remaining area to be welded is located, along with the symmetrical distance between the remaining area to be welded and the first welded area, into the evaluation formula. The selection value of the remaining areas to be welded is obtained. In the formula This indicates the stress value of the stress region where the remaining area to be welded is located. This indicates the symmetrical distance between the remaining area to be welded and the area of ​​the first weld. This represents the sum of stress values ​​in the stress regions encompassing all remaining areas to be welded. This represents the sum of the symmetrical distances between all remaining areas to be welded and the first welded area; Select the remaining welding area with the highest selection value from the remaining areas to be welded as the subsequent welding area.

2. The method for optimizing and analyzing the welding process of arc-shaped plates based on artificial intelligence as described in claim 1, characterized in that: The process for capturing the geometric contours of each area to be welded is described below: The surface image of the curved plate workpiece is focused on each area to be welded, and the contour lines of each area to be welded are extracted by contour detection. The geometric contour of the area to be welded is obtained based on the contour lines of each area.

3. The method for optimizing and analyzing the welding process of arc-shaped plates based on artificial intelligence as described in claim 1, characterized in that: The process for determining the first welding area is as follows: Extract the boundary contour of the curved plate from the surface image of the curved plate workpiece, and mark the center point and boundary turning point based on the boundary contour; For each area to be welded, calculate the distance between its geometric center and the center point of the workpiece, and record it as the center distance; Calculate the distance between the geometric center of each area to be welded and all boundary inflection points, and select the minimum value as the boundary distance; Compare the center distance and boundary distance of each area to be welded. If the center distance of an area to be welded is less than the boundary distance, the position of the area to be welded is biased towards the center; otherwise, the position of the area to be welded is biased towards the boundary. Identify whether there are center-biased areas to be welded from the positional bias of each area to be welded; if so, count the number of center-biased areas to be welded. If there is only one, then the area to be welded is taken as the first welding area; if there is more than one, then the area to be welded with the shortest distance from the center of each area to the center of the area to be welded is selected as the first welding area. If there are no center-biased areas to be welded, then the maximum and minimum values ​​of the distances between the geometric center of each area to be welded and all boundary inflection points are extracted, and these values ​​are combined with the boundary distances to calculate the center proximity. The specific calculation formula is as follows: In the formula Indicates the proximity to the center. , These represent the maximum distance between the geometric center of the area to be welded and all boundary inflection points, and the boundary distance, respectively. This represents the sum of the boundary distances of all areas to be welded, and the area with the greatest center proximity is then taken as the first area to be welded.

4. The method for optimizing and analyzing the welding process of arc-shaped plates based on artificial intelligence as described in claim 2, characterized in that: The welding temperature acquisition is implemented as follows: During the welding process in the first welding area, an infrared thermal imager is used to acquire thermal images of the arc-shaped plate workpiece, and the area is marked from the thermal image according to the geometric contour of the first welding area. The welding temperature of the first welding area is determined by comparing the chromaticity values ​​of the marked area with the correspondence between chromaticity and temperature in the thermal image.

5. The method for optimizing and analyzing the welding process of arc-shaped plates based on artificial intelligence as described in claim 4, characterized in that: The temperature gradient analysis is described in the following procedure: The temperature gradient of the first welded area at different acquisition times is obtained by subtracting the welding temperature of the first welded area at the current acquisition time from the welding temperature at the previous acquisition time.

6. The method for optimizing and analyzing the welding process of arc-shaped plates based on artificial intelligence as described in claim 5, characterized in that: The dynamic adjustment of welding parameters is described in the following process: When welding the first welding area using welding equipment according to preset welding parameters, the temperature gradient at each acquisition time is divided by the interval between adjacent acquisition times to obtain the temperature increase rate at each acquisition time. The temperature increase of the first welding area at each acquisition time is compared with the set growth rate threshold. If the temperature increase at a certain acquisition time is higher than the growth rate threshold, the first welding area is focused from the thermal image of the arc plate workpiece at the current acquisition time to identify whether there is oxidation in the weld of the first welding area. If there is oxidation, the welding current is reduced at the current acquisition time, and vice versa. If there is no oxidation, the welding speed is increased at the current acquisition time. If there is no oxidation, the temperature increase at a certain acquisition time is higher than the growth rate threshold, the preset welding parameters are used to continue welding until the welding is completed.

7. The method for optimizing and analyzing the welding process of arc-shaped plates based on artificial intelligence as described in claim 1, characterized in that: The stress distribution detection process is as follows: After welding is completed in the first welding area, multiple ultrasonic probes are used to emit ultrasonic pulses to the arc-shaped plate workpiece and receive the reflected ultrasonic signals. At the same time, the ultrasonic signal data is recorded and stress calculation is performed to obtain the stress value of the arc-shaped plate workpiece at different ultrasonic probe emission positions.

8. The method for optimizing and analyzing the welding process of arc-shaped plates based on artificial intelligence as described in claim 1, characterized in that: The process of obtaining the stress value of the stress region where the remaining area to be welded is located is as follows: The number of stress regions involved in the remaining area to be welded is counted. If a remaining area to be welded is located in only one specific stress region, the stress value of that stress region is directly used as the stress value of the area to be welded. If a remaining area to be welded spans multiple stress regions, the stress values ​​of all stress regions involved in the area to be welded are compared, and the maximum value among these stress values ​​is selected as the stress value of the stress region where the area to be welded is located.

9. The method for optimizing and analyzing the welding process of arc-shaped plates based on artificial intelligence as described in claim 1, characterized in that: The stress defect detection and quality evaluation of the arc plate welding sequence optimization are described in the following process: The surface images of the arc-shaped plate after welding and before welding are used to extract the shape contour of the arc-shaped plate. The shape profile of the arc plate after welding is aligned with the shape profile of the arc plate before welding, and the shape deformation is calculated accordingly. Crack identification was performed on the surface images of the arc-shaped plate workpiece after welding and before welding, and the crack initiation rate was calculated accordingly. The shape deformation and crack initiation of the arc-shaped plate before and after welding sequence optimization were compared using an evaluation-based approach. Optimize the welding sequence of the arc plate to obtain quality In the formula , These represent the degree of deformation of the arc-shaped plate before and after welding sequence optimization, respectively. , These represent the degree of new crack formation in the arc-shaped plate before and after welding sequence optimization, respectively.

Images