Welding method for floating ship plate of large oil storage tank

Abstract

The invention provides a welding method for a floating ship plate of a large oil storage tank, which belongs to the technical field of electric digital data processing and comprises the following steps: firstly, acquiring three-dimensional point cloud data through a sensor group on a crawler-type welding robot, and acquiring a feature image of a to-be-welded area by using a camera; a welding coordinate system is established based on the data, a groove contour is calculated, and an initial welding track is generated. And in combination with welding process parameters and environmental conditions, an Euler angle sequential sequence calculation equation set is established, and the posture of a welding head is adjusted in real time. Groove forming data in the welding process are monitored in real time through a sensor, when the fusion depth or the excess weld metal of a connector does not meet the requirement, a system can automatically recalculate the Euler angle sequence and adjust welding parameters till the technological standard is met, and therefore high-quality automatic welding is achieved, and the welding efficiency is improved. The technical problem that in the prior art, welding parameters and the motion trail of the welding robot are difficult to automatically adjust according to the welding state sensed in real time in the welding process is solved.

Description

Technical Field

[0001] The invention belongs to the technical field of electric digital data processing, and in particular relates to a welding method for a large-scale oil storage tank pontoon plate. Background Art

[0002] As an important equipment in the energy industry, the manufacturing and maintenance process of large oil storage tanks has always been a hot topic in the industry. Among them, welding process is one of the core processes in the manufacturing process. Since the tank shell is made of thick steel plates and has a complex and changeable structure, the welding quality is required to meet strict safety standards, which brings great challenges to the welding process.

[0003] To address this problem, the prior art mainly adopts the following welding methods: 1. Manual welding: It relies on the welder's experience and proficiency. This method is low-cost, but has poor reliability, difficult to guarantee weld quality, low efficiency, and is difficult to adapt to the welding needs of large structural parts.

[0004] 2. Automatic welding: Using welding robots to automatically complete the entire welding process can improve efficiency and quality consistency. However, for complex shapes and changing welding environments, it is difficult for robots to adapt autonomously, and a lot of offline programming and debugging work is required, which limits efficiency.

[0005] 3. Semi-automatic welding: Using robots to assist in manual operation, using machine vision, force sensing and other technologies to enhance the intelligence level of manual welding, it can adapt to complex environments to a certain extent, but it still requires a lot of manual participation, and it is difficult to fully realize adaptive welding.

[0006] The above-mentioned prior art generally has the following problems when facing the welding requirements of large and complex structural parts: 1. It is difficult to perceive and adapt to the complex welding environment in real time, which makes it difficult to control the quality of the weld and ensure the consistency and stability of the welding quality.

[0007] 2. Lack of intelligent welding parameter optimization and trajectory planning capabilities, unable to autonomously adjust the welding process according to real-time changing welding conditions, limiting the adaptive welding capabilities.

[0008] 3. Due to the limitations of the robot's own kinematic and dynamic performance, it is difficult to effectively compensate for various dynamic errors in the welding process, which affects the reliability of the weld quality.

[0009] Therefore, the prior art has the technical problem of being difficult to realize the technical problem of automatically adjusting the welding parameters and the motion trajectory of the welding robot according to the real-time sensed welding status during the welding process. Summary of the invention

[0010] In view of this, the present invention provides a large oil tank floating plate welding method, which can solve the technical problem that the existing technology is difficult to achieve in the welding process and automatically adjust the welding parameters and the motion trajectory of the welding robot according to the real-time sensed welding status.

[0011] The present invention is achieved in that: The present invention provides a large-scale petroleum storage tank pontoon plate welding method, comprising the following steps: S10, collecting three-dimensional point cloud data of the area to be welded of the floating plate through a sensor group provided on the crawler welding robot; the sensor group includes a laser line scanning sensor, a structured light sensor, an inertial measurement unit and a torque sensor; S20, using a camera on the welding robot to obtain an image of the area to be welded, and preprocessing the image of the area to be welded to obtain a characteristic image of the area to be welded; S30, establishing a welding coordinate system based on the three-dimensional point cloud data and the characteristic image of the area to be welded, and calculating the three-dimensional contour of the groove; S40, calculating the initial Euler angle of the welding head according to the three-dimensional contour of the groove, and generating a motion trajectory of the welding head; S50, using the welding current, voltage, wire feeding speed, shielding gas flow rate and welding speed in the welding process parameter database, combined with the initial Euler angle, groove geometry, plate thickness and ambient temperature, to establish an Euler angle timing sequence calculation equation group; S60, obtaining a posture adjustment sequence of the welding head during the welding process through the Euler angle timing sequence calculation equation group, and generating a welding trajectory compensation amount according to the posture adjustment sequence; S70, adjusting the motion trajectory of the welding head in real time based on the welding trajectory compensation amount, and collecting groove formation data during the welding process through the sensor group; S80, using the groove forming data to calculate the joint penetration and the residual height, when the joint penetration is less than 90% of the plate thickness or the residual height is greater than a preset threshold, return to step S50 to recalculate the Euler angle timing sequence until the joint penetration and the residual height meet the process requirements.

[0012] On the basis of the above technical solution, a large oil storage tank pontoon plate welding method of the present invention can also be improved as follows: The Euler angle timing sequence calculation equation group includes a posture prediction equation, a trajectory planning equation, a dynamic compensation equation and a welding process mapping equation.

[0013] Furthermore, the posture prediction equation is used to predict the posture change trend of the welding head during the movement process, the input includes the initial Euler angle, the three-dimensional contour data of the groove and the movement speed of the welding head, and the output is the predicted posture sequence of the welding head; The trajectory planning equation is used to generate a smooth and continuous welding trajectory. The input includes the predicted posture sequence, groove geometry and welding process parameters, and the output is the reference motion trajectory of the welding head. The dynamic compensation equation is used to compensate for the inertial effect of the welding robot during movement. The input includes the reference motion trajectory, the welding robot mass parameters and the motion speed, and the output is the compensated motion trajectory. The welding process mapping equation is used to establish a mapping relationship between welding process parameters and molten pool behavior. The input includes welding current, voltage, wire feeding speed, shielding gas flow rate and plate thickness, and the output is the expected penetration depth and residual height.

[0014] Furthermore, the preset threshold is specifically that when the thickness of the plate is not greater than 25 mm, the excess height is 3 mm, and when the thickness of the plate is greater than 25 mm, the excess height is 4 mm.

[0015] Furthermore, the step of preprocessing the image of the area to be welded to obtain a characteristic image of the area to be welded includes an image preprocessing step and an image feature extraction step.

[0016] Furthermore, the image preprocessing step specifically includes: S21, using a Gaussian filter to perform noise reduction processing on the image of the welding area; S22, graying the image after noise reduction; S23, improving the image contrast by using a histogram equalization method; S24, using morphological operation to perform edge enhancement on the image; S25, obtaining a binary image of the area to be welded through adaptive binarization processing.

[0017] Furthermore, the feature extraction step is specifically performed using a preset welding image feature extraction model, wherein the welding image feature extraction model includes an initial feature extraction module, a mathematical model module, and an accurate feature extraction module.

[0018] Furthermore, the initial feature extraction module is used to extract the initial contour features of the groove area from the binary image, the input is the preprocessed binary image and the preset groove type parameters, and the output is the initial contour feature vector of the area to be welded and the grayscale distribution matrix of the groove area; a deep convolutional neural network structure based on regional growth is adopted; The mathematical model module is a matrix equation group, including a contour optimization matrix equation, a groove characteristic matrix equation and a geometric constraint matrix equation; The precise feature extraction module is used to generate the final feature data of the area to be welded. The input is the optimized contour feature vector, the geometric parameters of the groove and the rationality judgment result. The output is the precise feature description data of the area to be welded. The residual attention network structure is adopted.

[0019] Furthermore, the profile optimization matrix equation is used to correct and optimize the initial profile features, the input is the initial profile feature vector and the preset groove standard parameters, and the output is the optimized profile feature vector; The groove characteristic matrix equation is used to calculate the key geometric parameters of the groove. The input is the optimized contour feature vector and the gray distribution matrix of the groove area. The output is the root gap, groove angle and groove depth data of the groove. The geometric constraint matrix equation is used to verify the validity of the groove feature, the input is the root gap, groove angle and groove depth data of the groove, and the output is the rationality judgment result of the groove feature.

[0020] Furthermore, the step of establishing a training data set for the welding image feature extraction model specifically includes: Step 1, collecting 5000 sets of floating plate welding images under different working conditions, wherein the different working conditions include different plate thicknesses, different welding currents, different welding voltages, different ambient temperatures and different welding speeds; Step 2: annotate the pontoon plate welding image, wherein the annotated content includes the groove contour line, the groove root position, the weld edge position and the molten pool boundary position; Step 3: Expand the training samples using data enhancement methods, wherein the data enhancement methods include image rotation, image scaling, brightness adjustment, contrast adjustment, and noise addition; Step 4: Divide the training samples into a training set, a validation set, and a test set in a ratio of 8:1:1; Step 5: Normalize the images in the training set, the validation set, and the test set, and adjust the image sizes to 1024 by 1024 pixels.

[0021] The step of training the welding image feature extraction model specifically includes: Step 11: Initialize the network parameters of the deep convolutional neural network and the residual attention network; Step 12: The deep convolutional neural network is trained using batch stochastic gradient descent method, with the learning rate set to 0.001, the number of training rounds set to 200 rounds, and the batch size set to 32; Step 13: Use a cross-validation method to evaluate the performance of the deep convolutional neural network, and perform early stopping when the accuracy of the validation set does not improve for five consecutive rounds; Step 14: using the output result of the trained deep convolutional neural network as the input of the residual attention network; Step 15: Adopt an adaptive learning rate optimization algorithm to train the residual attention network, set the initial learning rate to 0.0005, and set the number of training rounds to 100 rounds; Step 16: Evaluate the performance of the trained model on the test set. When the groove feature recognition accuracy reaches more than 95% and the average recognition time is less than 100 milliseconds, the model training is completed. Step 17: Save the parameters of the trained deep convolutional neural network and the residual attention network as the welding image feature extraction model.

[0022] The relevant equations are described in detail below: 1. Contour optimization matrix equation: The contour optimization matrix equation is specifically expressed as follows: ; In the formula, is the optimized contour feature vector ; is the initial contour feature vector ; To optimize the weight matrix ; is the contour correction matrix ; is the contour error vector ; is the standard contour vector ; is the adjustment coefficient, ; is the feature vector dimension; is the error vector dimension.

[0023] Parameter acquisition method: 1. Obtained through the output of the initial feature extraction module; 2. Calculate by following the steps below: ; In the formula, For feature points and The Euclidean distance between is the Gaussian kernel parameter, the default value is 0.1; 3. and Calculated by comparing with the standard contour template: ; In the formula, is the coordinate of the current contour point; is the coordinate of the corresponding standard template point.

[0024] The equation adopts the form of weighted combination, which is mainly based on the following principles: (1) Weight matrix In exponential form ( ) is because it is necessary to reflect the rapid decay characteristics of spatial correlation. The farther the distance, the smaller the impact, which is consistent with the characteristics of the Gaussian kernel; (2) Error correction term The linear combination form is adopted to maintain the controllability and stability of the correction; (3) Standard items As a benchmark constraint, it ensures that the optimization result does not deviate too much from the standard contour; Compared with the existing technology, this equation introduces adaptive weights and multi-level constraints to improve the robustness of contour recognition.

[0025] 2. Groove characteristic matrix equation: The groove characteristic matrix equation is specifically expressed as follows: ; In the formula, is the root gap; is the groove angle; is the groove depth; is the feature mapping matrix ; is the optimized contour feature vector ; is the grayscale influence matrix ; is the grayscale distribution matrix ; is the grayscale weight vector ; is the error vector .

[0026] Parameter acquisition method: 1. The least squares fitting method is used to obtain: ; In the formula, is the measured groove parameter matrix.

[0027] 2. and Obtained through grayscale gradient analysis: ; In the formula, For the characteristic parameters; For the Grayscale features.

[0028] The equation takes the form of a linear mapping plus a nonlinear correction: (1) Linear term It reflects the basic correspondence between contour features and geometric parameters; (2) Grayscale influence item The matrix multiplication form is adopted to reflect the modulation effect of gray distribution on feature extraction; (3) Through partial derivatives Construct the grayscale influence matrix to reflect the sensitivity relationship between parameters; This equation innovatively introduces image grayscale information into the feature extraction process, improving the accuracy of parameter recognition.

[0029] 3. Geometric constraint matrix equation: The geometric constraint matrix equation is specifically expressed as follows: ; In the formula, is the rationality judgment result vector ; is the constraint coefficient matrix ; is the groove parameter vector ; is the dynamic constraint matrix ; is the correction vector .

[0030] Parameter acquisition method: and It is obtained through test calibration, the steps are as follows: 1. Use standard specimens for welding tests; 2. Record the welding quality under different parameter combinations; 3. Establish constraint relationships through multiple regression analysis.

[0031] The equation is constructed based on the theory of dynamic systems: (1) Static constraints Reflects the steady-state relationship between parameters; (2) Dynamic Constraints Introduce time derivative to consider the influence of parameter change rate; (3) Correction vector Used to compensate for system errors and nonlinear effects; This equation breaks through the limitations of traditional static constraints and can better adapt to the dynamic welding process.

[0032] 4.Euler angle timing sequence calculation equation group: The posture prediction equation is specifically expressed as follows: ; In the formula, is the current Euler angle vector; is the welding head velocity vector; is the speed influence matrix; is the acceleration influence matrix; is a random disturbance term.

[0033] The posture prediction equation adopts the idea of ​​Taylor expansion: (1) Speed ​​​​term Reflects the first-order change trend; (2) Acceleration term Consider the second-order dynamic characteristics; (3) Random disturbance term Used to model system noise and uncertainty.

[0034] The trajectory planning equation is specifically expressed as follows: ; In the formula, To plan the trajectory; is the control point; for Sub-B-spline basis functions; is the smoothing term; is the smoothing coefficient.

[0035] The trajectory planning equation is based on B-spline theory: (1) Basis functions Ensure the continuity and smoothness of the trajectory; (2) Smoothness term Used to suppress trajectory oscillation.

[0036] The dynamic compensation equation is specifically expressed as follows: ; In the formula, is the compensation amount; is the inertia matrix; is the joint angle vector; is the Coriolis moment matrix; is the gravity matrix.

[0037] The dynamic compensation equation is based on the robot dynamics model: (1) Inertia term Reflects the inertial force generated by accelerated motion; (2) Coriolis force term Consider the joint coupling effect; (3) Gravity term Compensate for gravity effects.

[0038] The welding process mapping equation is specifically expressed as follows: ; In the formula, is the melting depth; For Yu Gao; is the welding current; is the voltage; is the wire feeding speed; is the gas flow rate; is the plate thickness; is the process coefficient; is the error term.

[0039] This equation uses matrix form to express the multi-parameter coupling relationship: (1) Process coefficient matrix Reflects the influence weight of different parameters on the penetration depth and residual height; (2) Error term Account for model errors and random disturbances.

[0040] 5. Real-time adjustment of trajectory compensation: The real-time trajectory adjustment equation is specifically expressed as follows: ; In the formula, is the trajectory after compensation; is the original trajectory; is the compensation amount; is the compensation coefficient.

[0041] This equation is built based on the PID control principle: (1) Proportional term Ensure fast response; (2) Integral item Eliminate steady-state errors; (3) Differential term Provides predictive capabilities.

[0042] 6. Joint quality calculation: The calculation equation for the penetration depth is specifically expressed as follows: ; In the formula, is the distribution of melting depth; is the metal density distribution; is the depth weight function; is the plate thickness.

[0043] The penetration depth is calculated in integral form: (1) Density distribution Reflects the melting state of the material; (2) Weight function Consider the energy attenuation in the depth direction.

[0044] The coheight calculation equation is specifically expressed as follows: ; In the formula, is the residual height distribution; is the weld surface height; is the parent material surface height; is the weld width.

[0045] The residual height is calculated using the maximum value operation: (1) By Calculate and extract the weld bulge height; (2) Subtract the reference height Get the actual residual height.

[0046] Compared with the prior art, the present invention provides a large-scale oil tank pontoon plate welding method, which first collects the three-dimensional point cloud data and image features of the welding area in real time by installing multiple sensors on the welding robot, including laser scanners, structured light sensors, inertial measurement units, etc. Then, based on these high-precision three-dimensional and two-dimensional information, a welding coordinate system is established, and key geometric features such as groove profile and shape are obtained.

[0047] Next, an adaptive trajectory planning and welding parameter optimization algorithm is used to predict the posture changes of the welding head during movement and generate a smooth and continuous welding trajectory, combining the groove geometry characteristics and welding process parameters. At the same time, according to the dynamic characteristics of the welding robot itself, a dynamic compensation algorithm is used to eliminate the trajectory deviation caused by inertia and other factors.

[0048] During the welding process, the sensor system monitors the weld formation in real time, including characteristic parameters such as penetration depth and excess height. Once a welding quality deviation is found, the method automatically adjusts process parameters such as welding current, voltage, wire feeding speed, and corrects the welding trajectory in real time to ensure that the weld quality meets the requirements.

[0049] Compared with the prior art, the adaptive welding method of the present invention has the following advantages: 1. It integrates a number of advanced technologies such as 3D modeling, image recognition, and adaptive trajectory planning, and can sense and adapt to complex welding environments in real time, greatly improving the consistency and stability of welding quality.

[0050] 2. The adaptive welding parameter optimization algorithm based on the Euler angle timing sequence can dynamically adjust the welding process according to the real-time changing welding status, significantly enhancing the adaptive welding capability.

[0051] 3. The robot dynamic compensation model is integrated to effectively eliminate various dynamic errors in the welding process and ensure the reliability of weld quality.

[0052] In summary, the adaptive welding method proposed in the present invention solves the technical problem that the existing technology is difficult to achieve in automatically adjusting the welding parameters and the motion trajectory of the welding robot according to the real-time perceived welding status during the welding process through the integrated application of technologies such as multi-sensor fusion, adaptive parameter optimization and dynamic trajectory compensation. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 A flow chart of the method provided by the present invention; Figure 2 Flowchart of image preprocessing steps. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical solution and advantages of the embodiments of the present invention more clear, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0055] like Figure 1 FIG. 1 is a flow chart of a large-scale oil storage tank pontoon plate welding method provided by the present invention, and the method comprises the following steps: S10, collecting three-dimensional point cloud data of the area to be welded of the floating plate through a sensor group arranged on the crawler welding robot; the sensor group includes a laser line scanning sensor, a structured light sensor, an inertial measurement unit and a torque sensor; S20, using a camera on the welding robot to obtain an image of the area to be welded, and preprocessing the image of the area to be welded to obtain a characteristic image of the area to be welded; S30, establishing a welding coordinate system based on the three-dimensional point cloud data and the characteristic image of the area to be welded, and calculating the three-dimensional contour of the groove; S40, calculating the initial Euler angle of the welding head according to the three-dimensional contour of the groove, and generating a motion trajectory of the welding head; S50, using the welding current, voltage, wire feeding speed, shielding gas flow rate and welding speed in the welding process parameter database, combined with the initial Euler angle, groove geometry, plate thickness and ambient temperature, to establish the Euler angle timing sequence calculation equation group; S60, obtaining a posture adjustment sequence of the welding head during the welding process by calculating the equation group through the Euler angle timing sequence, and generating a welding trajectory compensation amount according to the posture adjustment sequence; S70, adjusting the motion trajectory of the welding head in real time based on the welding trajectory compensation amount, and collecting groove forming data during the welding process through the sensor group; S80, using the groove forming data to calculate the joint penetration and the residual height. When the joint penetration is less than 90% of the plate thickness or the residual height is greater than a preset threshold, return to step S50 to recalculate the Euler angle timing sequence until the joint penetration and the residual height meet the process requirements.

[0056] The preset threshold is specifically that when the thickness of the plate is not greater than 25 mm, the excess height is 3 mm, and when the thickness of the plate is greater than 25 mm, the excess height is 4 mm.

[0057] Furthermore, the step of preprocessing the image of the area to be welded to obtain the characteristic image of the area to be welded includes the steps of image preprocessing and image feature extraction. Figure 2 As shown, the image preprocessing steps specifically include: S21, using a Gaussian filter to perform noise reduction processing on the image of the welding area; S22, graying the image after noise reduction; S23, improving the image contrast by using a histogram equalization method; S24, using morphological operation to perform edge enhancement on the image; S25, obtaining a binary image of the area to be welded through adaptive binarization processing.

[0058] The specific implementation methods of the steps of the present invention are described in detail below: The specific implementation method of step S10 is to first collect the three-dimensional point cloud data of the area to be welded by a group of sensors set on the welding robot. These sensors include laser line scanning sensors, structured light sensors, and inertial measurement units. The laser line scanning sensors and structured light sensors can obtain high-precision three-dimensional data of the area to be welded, while the inertial measurement unit can provide the motion state information of the welding equipment itself. By processing and analyzing these three-dimensional point cloud data, the shape and contour features of the area to be welded can be accurately obtained, laying the foundation for subsequent welding path planning and welding parameter optimization.

[0059] The specific implementation method of step S20 is to first obtain a two-dimensional image of the area to be welded through a camera installed on the welding robot. Then, these images are preprocessed, including: Gaussian filtering for noise reduction, grayscale processing, histogram equalization for contrast enhancement, and morphological edge enhancement, and finally a binary image of the area to be welded is obtained. The purpose of these preprocessing steps is to enhance the feature information of the area to be welded and prepare for subsequent feature extraction.

[0060] The specific implementation method of step S30 is to first establish a welding coordinate system based on the three-dimensional point cloud data obtained in step S10 and the characteristic image of the area to be welded obtained in step S20. This coordinate system takes the geometric center of the area to be welded as the origin, the X-axis is along the direction of the edge to be welded, the Y-axis is perpendicular to the X-axis, and the Z-axis is perpendicular to the surface of the workpiece. Then, based on the three-dimensional point cloud data, the three-dimensional contour information of the groove is calculated, including the shape and size of the groove. This information will provide an important basis for the subsequent welding head motion trajectory planning and welding parameter optimization.

[0061] The specific implementation method of step S40 is to first calculate the initial Euler angle of the welding head according to the three-dimensional contour information of the groove obtained in step S30. The Euler angle is three rotation angles that describe the posture of the welding head, including the pitch angle, the yaw angle and the roll angle. These initial Euler angles provide a starting point for the subsequent generation of the welding head motion trajectory. Then, combined with the geometric characteristics of the groove, a trajectory planning algorithm is used to generate a smooth and continuous welding head motion trajectory. The trajectory planning equation based on B-spline is used here ,in To plan the trajectory, is the control point, is the B-spline basis function, is the smoothing term, is the smoothness coefficient. This equation can generate a smooth welding trajectory and meet the requirements of continuity and controllability.

[0062] The specific implementation method of step S50 is to first obtain the welding current from the welding process parameter database ,Voltage Wire feeding speed , Shielding gas flow And welding speed Then, the initial Euler angle calculated in step S40 is obtained. , groove geometry, plate thickness As well as the ambient temperature, a Euler angle timing sequence calculation equation group is established. This equation group includes the following 4 equations: 1. Posture prediction equation: , used to predict the posture change trend of the welding head during movement. and is the influence matrix of velocity and acceleration, is a random disturbance term.

[0063] 2. Trajectory planning equation: , used to generate a smooth and continuous welding trajectory. Among them, is the control point, is the B-spline basis function, is the smoothing term, is the smoothing coefficient.

[0064] 3. Dynamic compensation equation: , used to compensate for the inertia effect of the welding robot during movement. is the inertia matrix, is the Coriolis force matrix, is the gravity matrix, is the joint angle vector.

[0065] 4. Welding process mapping equation: , used to establish the mapping relationship between welding process parameters and molten pool behavior. Among them, is the melting depth, For Yu Gao, is the process coefficient, and is the error term.

[0066] This Euler angle timing sequence calculation equation group can comprehensively consider the welding head posture prediction, trajectory planning, dynamic compensation, and the relationship between welding process parameters and molten pool behavior, providing a basis for subsequent real-time adjustment of the welding trajectory.

[0067] The specific implementation of step S60 is to first use the Euler angle timing sequence calculation equation group established in step S50 to obtain the posture adjustment sequence of the welding head during the welding process through a numerical solution method. This posture adjustment sequence describes the Euler angle changes that the welding head needs to make during the movement process. Then, based on this posture adjustment sequence, the compensation amount of the welding trajectory is calculated. , the specific expression is: ; in, is the trajectory after compensation, is the original trajectory, The compensation value can adjust the motion trajectory of the welding head in real time, so that it can better adapt to the actual welding process.

[0068] The specific implementation method of step S70 is that during the welding process, the sensor group in step S10 collects the groove forming data in real time, including the weld surface height. And metal density distribution Then use this data to calculate the depth of penetration and Yu Gao , the specific calculation formula is: Depth of penetration calculation: ; Co-height calculation: ; in, is the depth weight function, is the parent material surface height, By real-time monitoring of the penetration depth and excess height data of the joint, the deviation of welding quality can be discovered in time, providing a basis for the next step of process optimization.

[0069] The specific implementation of step S80 is to first determine whether the penetration and residual height of the current welding joint meet the requirements. If the penetration is less than 90% of the plate thickness or the residual height is greater than the preset threshold (for plates below 25 mm, the threshold is 3 mm; for plates above 25 mm, the threshold is 4 mm), it is necessary to return to step S50 and recalculate the Euler angle timing sequence to optimize the welding parameters. This cyclic iterative process will continue until the penetration and residual height meet the process requirements.

[0070] The following is an example of a specific application scenario of the present invention: A large petrochemical enterprise is building a new 2 million cubic meter floating roof storage tank, which is currently the largest storage tank of the enterprise. The storage tank is made of Q390D high-strength steel plate with a thickness of 30 mm, and the outer shell adopts a floating ship plate structure. The technical team of the enterprise decided to adopt the adaptive welding method proposed in the present invention. First, they integrated a variety of sensor devices such as laser scanning sensors, structured light sensors, inertial measurement units and high-definition cameras on the welding robot. This sensor system can fully perceive the three-dimensional geometric features and two-dimensional image information of the area to be welded.

[0071] In the welding preparation stage, the operator moves the welding robot to the edge of the floating plate to be welded. The sensor system is then started to collect 3D point cloud data and 2D images. By processing and analyzing these data, a welding coordinate system with the geometric center of the floating plate as the origin is established, and the key parameters of the area to be welded are extracted, as shown in Table 1: Table 1 Geometric parameters of the area to be welded parameter Numeric Groove root clearance 4.2mm Bevel angle 30° Groove Depth 8.5mm Plate thickness 30mm From the process parameter database, the operator retrieved the welding parameters suitable for 30 mm thick Q390D steel plate, as shown in Table 2: Table 2 Welding process parameters parameter Numeric Welding current 320A Welding voltage 28V Wire feeding speed 8m / min Shielding gas flow 18L / min Welding speed 30cm / min With these key information, the welding control system begins to establish the Euler angle timing sequence calculation equation group. First, through the posture prediction equation , predict the posture change trend of the welding head during the movement. Among them, and They are the influence matrices of velocity and acceleration, which are calibrated by experiments and taken as and ; is Gaussian white noise with a mean of 0 and a variance of 0.01.

[0072] Then, based on the B-spline curve theory, the trajectory planning equation was established By optimizing the control points and smoothing coefficient , a smooth and continuous welding trajectory was generated.

[0073] In order to compensate for the dynamic characteristics of the welding robot itself, a dynamic compensation equation was constructed. .in, for Inertia matrix, for Coriolis force matrix, for Gravity matrix, obtained through calibration test: kg m ; N m s / rad N ; Finally, in order to establish the mapping relationship between welding process parameters and molten pool behavior, the welding process mapping equation was designed. .here, is the melting depth, For Yu Gao, is the welding current, is the welding voltage, is the wire feeding speed, For the protective gas flow, is the plate thickness, is the process coefficient, is a random error.

[0074] With the above series of algorithm models, the welding control system starts to execute the adaptive welding process. First, according to the trajectory planning algorithm of step S40, the system generates the initial motion trajectory of the welding head. Then, during the welding process, the sensor system collects weld formation data in real time, including parameters such as penetration depth and residual height.

[0075] Through the calculation formula of penetration depth and residual height in step S70, the control system monitors the weld quality in real time: Depth of penetration calculation: ; Co-height calculation: ; in, is the metal density distribution, is the depth weight function, is the weld surface height distribution, mm is the height of the parent material surface.

[0076] By real-time analysis of weld quality data, once it is found that the penetration depth is less than 27 mm (90% of the plate thickness) or the excess height is greater than 4 mm, the control system will automatically trigger the process optimization process of step S80.

[0077] First, the system will re-optimize the welding process parameters according to the current welding parameters through the Euler angle timing sequence calculation equation group in step S50. The adjusted parameters are shown in Table 3: Table 3 Optimized welding process parameters parameter Numeric Welding current 340A Welding voltage 30V Wire feeding speed 9m / min Shielding gas flow 20L / min Welding speed 25cm / min Then, according to the optimized parameters, the control system recalculates the motion trajectory of the welding head. Through the trajectory compensation algorithm in step S60, the posture and position of the welding head are adjusted in real time to adapt to the current welding state.

[0078] After this round of adaptive optimization, the sensor system monitored the weld quality again and found that the penetration depth reached 28.5mm and the residual height was controlled within 3.8mm. So far, the adaptive welding task of the floating ship section has been successfully completed.

[0079] The entire welding process took 12.5 hours and was carried out for 3 adaptive optimization cycles. Compared with traditional manual welding, not only the welding efficiency was greatly improved, but also the consistency and stability of the weld quality were greatly improved.

[0080] Specifically, the principle of the present invention is to use multi-source perception information to build a high-precision welding geometry model, and based on this, establish an adaptive welding parameter optimization and trajectory planning algorithm, and ultimately achieve intelligent control of welding quality.

[0081] First, by integrating laser scanning sensors, structured light sensors, and inertial measurement units on the welding robot, high-precision three-dimensional point cloud data of the area to be welded can be obtained. These three-dimensional information lays the foundation for the subsequent establishment of the welding coordinate system and extraction of the groove contour.

[0082] At the same time, the camera installed on the welding robot can also collect two-dimensional images of the area to be welded. By preprocessing these images, including filtering, grayscale, histogram equalization, edge enhancement and other steps, a binary image rich in the characteristics of the area to be welded is finally obtained. These two-dimensional feature information will be integrated with the three-dimensional point cloud data to provide support for the accurate description of the groove geometry.

[0083] Based on the acquired 3D point cloud data and 2D feature images, the present invention first establishes a welding coordinate system with the geometric center of the area to be welded as the origin. Then, by analyzing the 3D point cloud data, key geometric features such as the shape and size of the groove are extracted. This information lays the foundation for the subsequent welding head motion trajectory planning and welding parameter optimization.

[0084] Next, the present invention adopts an adaptive Euler angle timing sequence calculation equation group, combined with the welding current, voltage, wire feeding speed and other data obtained from the process parameter database, to predict the posture change trend of the welding head during the movement process and generate a smooth and continuous welding trajectory. This equation group includes modules such as posture prediction, trajectory planning, dynamic compensation and welding process mapping, which can fully consider multiple factors such as the movement characteristics of the welding head and the influence of welding process parameters on the behavior of the molten pool.

[0085] At the same time, in order to eliminate the trajectory deviation caused by the dynamic characteristics of the welding robot itself, the present invention also incorporates a compensation algorithm based on the robot dynamics model. By real-time compensation for the influence of factors such as inertia, Coriolis force and gravity, the high accuracy of the welding trajectory is ensured.

[0086] During the welding process, the sensor system monitors the weld formation in real time, including characteristic parameters such as penetration depth and excess height. Once the penetration depth is less than 90% of the plate thickness or the excess height is greater than the preset threshold, the method will automatically return to the process parameter optimization step and recalculate the Euler angle timing sequence until the weld quality meets the requirements. This closed-loop control ensures the reliability of welding quality.

[0087] It should be noted that the explanation of relevant variables is shown in Table 4 below: Table 4 Variable explanation table

[0088] The above description is only a specific implementation mode of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A large oil tank pontoon plate welding method, characterized in that: The following steps are involved: S10, collecting three-dimensional point cloud data of the area to be welded of the floating plate through a sensor group provided on the crawler welding robot; the sensor group includes a laser line scanning sensor, a structured light sensor, an inertial measurement unit and a torque sensor; S20, using a camera on the welding robot to obtain an image of the area to be welded, and preprocessing the image of the area to be welded to obtain a characteristic image of the area to be welded; S30, establishing a welding coordinate system based on the three-dimensional point cloud data and the characteristic image of the area to be welded, and calculating the three-dimensional contour of the groove; S40, calculating the initial Euler angle of the welding head according to the three-dimensional contour of the groove, and generating a motion trajectory of the welding head; S50, using the welding current, voltage, wire feeding speed, shielding gas flow rate and welding speed in the welding process parameter database, combined with the initial Euler angle, groove geometry, plate thickness and ambient temperature, to establish an Euler angle timing sequence calculation equation group; S60, obtaining a posture adjustment sequence of the welding head during the welding process through the Euler angle timing sequence calculation equation group, and generating a welding trajectory compensation amount according to the posture adjustment sequence; S70, adjusting the motion trajectory of the welding head in real time based on the welding trajectory compensation amount, and collecting groove formation data during the welding process through the sensor group; S80, using the groove forming data to calculate the joint penetration and the residual height, when the joint penetration is less than 90% of the plate thickness or the residual height is greater than a preset threshold, return to step S50 to recalculate the Euler angle timing sequence until the joint penetration and the residual height meet the process requirements.

2. A large oil storage tank pontoon plate welding method according to claim 1, characterized in that: The Euler angle timing sequence calculation equation group includes a posture prediction equation, a trajectory planning equation, a dynamic compensation equation and a welding process mapping equation.

3. A large oil storage tank pontoon plate welding method according to claim 2, characterized in that: The posture prediction equation is used to predict the posture change trend of the welding head during the movement process. The input includes the initial Euler angle, the three-dimensional contour data of the groove and the movement speed of the welding head. The output is the predicted posture sequence of the welding head. The trajectory planning equation is used to generate a smooth and continuous welding trajectory. The input includes the predicted posture sequence, groove geometry and welding process parameters, and the output is the reference motion trajectory of the welding head. The dynamic compensation equation is used to compensate for the inertial effect of the welding robot during movement. The input includes the reference motion trajectory, the welding robot mass parameters and the motion speed, and the output is the compensated motion trajectory. The welding process mapping equation is used to establish a mapping relationship between welding process parameters and molten pool behavior. The input includes welding current, voltage, wire feeding speed, shielding gas flow rate and plate thickness, and the output is the expected penetration depth and residual height.

4. A large-scale oil storage tank pontoon plate welding method according to claim 3, characterized in that: The preset threshold is specifically that when the thickness of the plate is not greater than 25 mm, the excess height is 3 mm, and when the thickness of the plate is greater than 25 mm, the excess height is 4 mm.

5. A large oil storage tank pontoon plate welding method according to claim 4, characterized in that: The step of preprocessing the image of the area to be welded to obtain a characteristic image of the area to be welded includes an image preprocessing step and an image feature extraction step.

6. A large oil storage tank pontoon plate welding method according to claim 5, characterized in that: The image preprocessing step specifically includes: S21, using a Gaussian filter to perform noise reduction processing on the image of the welding area; S22, graying the image after noise reduction; S23, improving the image contrast by using a histogram equalization method; S24, using morphological operation to perform edge enhancement on the image; S25, obtaining a binary image of the area to be welded through adaptive binarization processing.

7. A large oil storage tank pontoon plate welding method according to claim 6, characterized in that: The feature extraction step specifically utilizes a preset welding image feature extraction model for extraction, wherein the welding image feature extraction model includes an initial feature extraction module, a mathematical model module, and an accurate feature extraction module.

8. A large-scale oil storage tank pontoon plate welding method according to claim 7, characterized in that: The initial feature extraction module is used to extract the initial contour features of the groove area from the binary image. The input is the preprocessed binary image and the preset groove type parameters. The output is the initial contour feature vector of the area to be welded and the grayscale distribution matrix of the groove area. A deep convolutional neural network structure based on regional growth is adopted. The mathematical model module is a matrix equation group, including a contour optimization matrix equation, a groove characteristic matrix equation and a geometric constraint matrix equation; The precise feature extraction module is used to generate the final feature data of the area to be welded. The input is the optimized contour feature vector, the geometric parameters of the groove and the rationality judgment result. The output is the precise feature description data of the area to be welded. The residual attention network structure is adopted.

9. A large-scale oil storage tank pontoon plate welding method according to claim 8, characterized in that: The profile optimization matrix equation is used to correct and optimize the initial profile features, the input is the initial profile feature vector and the preset groove standard parameters, and the output is the optimized profile feature vector; The groove characteristic matrix equation is used to calculate the key geometric parameters of the groove. The input is the optimized contour feature vector and the gray distribution matrix of the groove area. The output is the root gap, groove angle and groove depth data of the groove. The geometric constraint matrix equation is used to verify the validity of the groove feature, the input is the root gap, groove angle and groove depth data of the groove, and the output is the rationality judgment result of the groove feature.

10. A large oil storage tank pontoon plate welding method according to claim 9, characterized in that: The step of establishing a training data set for the welding image feature extraction model specifically includes: Step 1, collecting 5000 sets of floating plate welding images under different working conditions, wherein the different working conditions include different plate thicknesses, different welding currents, different welding voltages, different ambient temperatures and different welding speeds; Step 2: annotate the pontoon plate welding image, wherein the annotated content includes the groove contour line, the groove root position, the weld edge position and the molten pool boundary position; Step 3: Expand the training samples using data enhancement methods, wherein the data enhancement methods include image rotation, image scaling, brightness adjustment, contrast adjustment, and noise addition; Step 4: Divide the training samples into a training set, a validation set, and a test set in a ratio of 8:1:1; Step 5: Normalize the images in the training set, the validation set, and the test set, and adjust the image sizes to 1024 x 1024 pixels.

Images