Multi-welding robot collaborative working system based on digital twinning

Abstract

The application discloses a multi-welding robot collaborative working system based on digital twinning, and belongs to the technical field of intelligent manufacturing and robot control, and the system comprises a physical space module, a virtual space module, a twinning data layer and a control module, communication connections are established between the physical space module, the virtual space module, the twinning data layer and the control module; the physical space module comprises a plurality of welding robots, a sensor group and a data transmission network; the virtual space module comprises a plurality of welding robot twins and a workpiece twinning model; the twinning data layer is used for connecting the physical space module and the virtual space module; and the control module generates a welding path optimization scheme, a multi-welding robot collision avoidance strategy and a welding quality feedback control instruction based on the twinning data layer. Through the construction of a closed-loop control framework of 'physical-virtual' bidirectional mapping, dynamic collaborative optimization of multi-robot motion trajectories, weld forming and thermal deformation is realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent manufacturing and robot control, in particular to a multi-welding robot collaborative operation system based on digital twinning. BACKGROUND

[0002] With the rapid growth of demand for large and complex components in the fields of aerospace, shipbuilding, rail transportation, etc., multi-robot collaborative welding technology has become a key means to improve production efficiency and quality. Multi-robot processing system has the characteristics of complex structure and operation mechanism, multi-source heterogeneous process data, and difficulty in collaborative optimization. It is extremely important to realize interference avoidance, trajectory planning, heterogeneous data fusion, process optimization and intelligent collaboration of multi-robot processing system to ensure efficient, high-quality and safe and reliable operation of the processing system.

[0003] After searching, it is found that Chinese patent publication No. CN108544495A discloses a welding path planning method, system and equipment for a multi-welding robot, which includes obtaining all welding trajectory points of a workpiece to be welded and the number of welding tasks of each welding robot, labeling all welding trajectory points, and each welding trajectory point has a unique label. According to all labels and the number of welding tasks of each welding robot, a plurality of welding paths are generated. It is judged whether the welding path meets the constraint condition. If yes, the welding path is used as the execution welding path of the multi-welding robot. Also, Chinese patent publication No. CN112453648B discloses an offline programming laser weld seam tracking system based on 3D vision. The specific operation process is that a 3D camera is installed above the welding workpiece. After the workpiece is installed, the photographing is triggered remotely to obtain the point cloud data of the welding site including the workpiece and the fixture. The above scheme integrates the 3D vision model reconstruction, offline programming and laser weld seam tracking technologies to realize unmanned welding site.

[0004] The above-mentioned patents have the advantages of improving the efficiency and flexibility of the multi-welding robot during welding work, and reducing the complexity of welding program demonstration and improving the efficiency of welding in the welding site. However, they lack fusion analysis of dynamic data during welding, and it is difficult to solve the path deviation problem caused by thermal deformation. Although local path correction can be achieved, a virtual-real collaborative closed-loop control framework is not constructed. Therefore, it is urgent to provide a multi-welding robot collaborative operation system based on digital twinning to solve the above problems. SUMMARY

[0005] The technical problem to be solved by the present application is to overcome the shortcomings of the prior art and provide a multi-welding robot collaborative operation system based on digital twinning.

[0006] To solve the above technical problems, the application adopts one technical solution: providing a multi-welding robot collaborative operation system based on digital twinning, comprising: a physical space module, a virtual space module, a twinning data layer, and a control module;

[0007] The physical space module comprises a plurality of welding robots, a sensor group, and a data transmission network.

[0008] The virtual space module comprises a plurality of welding robot twins and a workpiece twin model.

[0009] The twinning data layer is used to connect the physical space module and the virtual space module, fuse and synchronize the dynamic data and the motion trajectory, weld forming quality, and thermal deformation state data of the plurality of welding robot twins and the workpiece twin model, and predict the motion trajectory, weld forming quality, and thermal deformation state of the plurality of welding robots through a preset prediction unit.

[0010] The control module generates control instructions based on the twinning data layer and issues the control instructions to the plurality of welding robots for execution.

[0011] The application further provides that communication connections are established between the physical space module, the virtual space module, the twinning data layer, and the control module.

[0012] The sensor group in the physical space module comprises a vision sensor, a force sensor, a temperature sensor, a current and voltage sensor.

[0013] The dynamic data in the physical space module comprises welding parameter data, robot pose data, weld appearance data, and environmental temperature data.

[0014] The application further provides that the dynamic data acquisition method comprises:

[0015] S1, scanning the welding area of the workpiece through the vision sensor to obtain a first visual image of the weld position, shape, and size, and scanning the welding posture of the plurality of welding robots through the vision sensor to generate a second visual image, and using an image processing algorithm to denoise and enhance the features of the first visual image and the second visual image to generate weld appearance data and robot pose data.

[0016] S2, collecting temperature distribution data of a welding area of the multi-welding robot through the temperature sensor, recording a heat input change trend, and generating environment temperature data;

[0017] S3, continuously collecting current values, voltage values and wire feeding speed data of a preset welding power source through the current and voltage sensor, simultaneously, monitoring force changes of the multi-welding robot when a welding torch contacts a workpiece in real time through the force sensor, judging collision risks in a welding process, recording in real time, generating welding parameter data, and packing the welding parameter data, robot pose data, weld appearance data and environment temperature data to generate dynamic data, uploading the dynamic data to the twin data layer and the virtual space module through the data transmission network.

[0018] The application further provides that the specific steps for the virtual space module to be completely mapped by the physical space module are as follows:

[0019] M1, the virtual space module receives the dynamic data, and extracts mechanical structure parameters, motion joint parameters and welding process parameters of the multi-welding robot based on the dynamic data, and generates model data of a multi-welding robot twin corresponding to the multi-welding robot;

[0020] M2, according to the model data of the multi-welding robot twin, a three-dimensional geometric model and a motion model of the multi-welding robot twin are established, a workpiece twin model consistent with the workpiece is constructed in combination with the weld appearance data, the motion trajectory and the welding process parameters of the multi-welding robot twin are continuously corrected according to the real-time dynamic data in the physical space module, a virtual simulation unit is preset to verify the motion trajectory and the welding process parameters of the multi-welding robot twin after correction, consistency with the real-time dynamic data in the physical space module, and when verification is successful, a complete virtual space module is generated.

[0021] The application further provides that the specific steps for the virtual simulation unit to verify the consistency of the motion trajectory and the welding process parameters of the multi-welding robot twin after correction with the real-time dynamic data in the physical space module (1) in step M2 are as follows:

[0022] M21, based on the motion trajectory and the welding process parameters of the multi-welding robot twin after correction, the virtual simulation unit drives the multi-welding robot twin and the workpiece twin model to perform welding process simulation, and generates virtual welding parameters, virtual weld forming quality data and virtual thermal deformation state data;

[0023] M22, real-time comparison of the virtual welding parameters with the actual motion trajectory data of the multi-welding robot in the physical space module, and difference analysis of the virtual weld forming quality and the virtual thermal deformation state data with the weld appearance data and the environmental temperature data collected by the physical space module;

[0024] M23, if the difference analysis result exceeds the preset threshold value, it is determined that the virtual space module and the physical space module are inconsistent, triggering the virtual space module to re-correct the motion trajectory and welding parameters of the multi-welding robot twin; if the difference is within the threshold value, it is confirmed that the consistency verification is passed, and the current corrected virtual space module is locked as the effective mapping.

[0025] The application further provides that: the twin data layer fuses and synchronizes the dynamic data and the motion trajectory, weld forming quality and thermal deformation state data of the multi-welding robot twin and the workpiece twin model, and the specific method comprises:

[0026] Q1, the twin data layer receives the dynamic data transmitted by the physical space module, and analyzes the robot pose data, welding parameter data, weld appearance data and environmental temperature data in the dynamic data through a preset analysis unit;

[0027] Q2, the analyzed robot pose data is matched one by one with the motion joint parameters of the multi-welding robot twin, the welding parameter data is associated with the virtual welding process parameter of the welding torch of the multi-welding robot twin, and the weld appearance data and environmental temperature data are mapped to the corresponding area of the workpiece twin model;

[0028] Q3, the twin data layer drives the multi-welding robot twin to execute the same motion trajectory as the multi-welding robot in the virtual space based on the real-time analyzed dynamic data, and updates the thermal deformation state and weld forming quality of the workpiece twin model, to complete the fusion and synchronization of data.

[0029] The application further provides that: the specific steps of predicting the motion trajectory, weld forming quality and thermal deformation state of the multi-welding robot in the twin data layer through a preset prediction unit include:

[0030] Q4, based on the motion trajectory data of the multi-welding robot twin and the current thermal deformation state of the workpiece twin model, simulate the welding process in the future time period in the prediction unit to generate predicted motion trajectory data, predicted weld forming size data and predicted thermal deformation distribution data;

[0031] Q5, real-time comparative analysis of the predicted motion trajectory data and real-time motion trajectory of the multi-welding robot in the physical space module, and difference calculation of the predicted weld forming size data and the predicted thermal deformation distribution data and the weld appearance data and the environmental temperature data collected by the physical space module;

[0032] Q6, if the difference calculation result exceeds a preset threshold value, adjusting the weight coefficient of the welding process parameter in the prediction unit and the preset thermal deformation simulation algorithm according to the difference direction, re-executing steps Q4 to Q5 until the difference between the predicted motion trajectory data, the predicted weld forming size data and the predicted thermal deformation distribution data and the actual data collected by the physical space module is within the threshold value range; if the difference calculation result is less than the preset threshold value, outputting the predicted motion trajectory data, the predicted weld forming size data and the predicted thermal deformation distribution data to the control module.

[0033] The application further provides that the specific steps of the difference calculation in step Q5 include:

[0034] Q51, time stamp alignment of the predicted motion trajectory data, the predicted weld forming size data and the predicted thermal deformation distribution data generated by the prediction unit and the actual motion trajectory data, the actual weld appearance data and the actual environmental temperature data collected by the physical space module in the same time period;

[0035] Q52, coordinate deviation comparison of the predicted motion trajectory data and the actual motion trajectory data point by point, calculation of the average offset and the maximum offset of each robot joint position to obtain the trajectory offset, comparison of the weld width and height in the predicted weld forming size data and the measured values of the weld appearance data to calculate the width error percentage and the height absolute error value to obtain the weld error, comparison of the predicted deformation state data and the actual environmental temperature data to calculate the difference value of the predicted temperature and the actual temperature of the key area of the workpiece and the deviation amplitude of the deformation amount to obtain the thermal deformation deviation, and the trajectory offset, the weld error and the thermal deformation deviation are the difference calculation results.

[0036] The application further provides that the specific steps of the control module are as follows:

[0037] H1, generating a multi-robot cooperative collision avoidance path planning scheme based on the trajectory offset, the weld error and the thermal deformation deviation, adjusting the compensation value of the welding current and voltage parameter of the multi-welding robot according to the weld error, and optimizing the welding sequence based on the thermal deformation deviation;

[0038] H2, the generated multi-robot cooperative collision avoidance path planning scheme, compensation value and welding sequence are issued to the multi-welding robot in the physical space module (1) in real time through the logic controller, and the multi-welding robot is driven to execute the corrected welding action;

[0039] H3, in the welding process, the multi-welding robot continuously receives the predicted data updated by the twin data layer (3) and the dynamic data of the physical space module (1), and if it is detected that the error of the robot pose data or the weld appearance data exceeds the preset threshold, steps H2 to H3 are re-executed until the welding task is completed.

[0040] The beneficial effects of the present application are as follows:

[0041] 1. The present application collects multi-source heterogeneous data such as welding parameters, pose, temperature, etc. in real time through the physical space module, combines the fusion of the twin data layer with the high-fidelity twin model of the virtual space, constructs a closed-loop control framework of "physical-virtual" bidirectional mapping, realizes dynamic collaborative optimization of multi-robot motion trajectory, weld forming and thermal deformation, and improves welding precision and efficiency;

[0042] 2. Based on the real-time prediction of the workpiece thermal deformation state by the virtual simulation unit, combined with dynamic adjustment of the welding parameters, the robot motion path and welding process parameters are actively corrected, effectively inhibiting the weld offset and workpiece deformation caused by heat accumulation, and improving the welding quality of complex components. BRIEF DESCRIPTION OF DRAWINGS

[0043] Figure 1 is the system flowchart of the present application;

[0044] Figure 2 is the flowchart of the dynamic data acquisition method of the present application;

[0045] Figure 3 is the flowchart of the virtual space module completely mapped by the physical space module of the present application;

[0046] Figure 4 is the flowchart of the virtual simulation unit verification of the present application;

[0047] In the figure: 1, physical space module; 2, virtual space module; 3, twin data layer; 4, control module. DETAILED DESCRIPTION

[0048] The preferred embodiments of the present application will be described in detail below with reference to the accompanying drawings, so that the advantages and features of the present application can be more easily understood by those skilled in the art, and the protection scope of the present application can be more clearly and explicitly defined.

[0049] Please refer to Figures 1-4The application discloses a multi-welding robot collaborative operation system based on digital twinning, which comprises a physical space module 1, a virtual space module 2, a twinning data layer 3 and a control module 4.

[0050] The physical space module 1 comprises a plurality of welding robots, a sensor group and a data transmission network.

[0051] The sensor group in the physical space module 1 comprises a visual sensor, a force sensor, a temperature sensor, a current and voltage sensor.

[0052] The dynamic data in the physical space module 1 comprises welding parameter data, robot pose data, weld appearance data and environmental temperature data.

[0053] The welding parameter data comprises welding current, voltage, wire feeding speed, welding speed and welding gun force value.

[0054] S1, scanning the welding area of the workpiece by the visual sensor to obtain a first visual image of the weld position, shape and size, and scanning the welding posture of the multi-welding robot by the visual sensor to generate a second visual image.

[0055] S2, collecting the temperature distribution data of the welding area of the multi-welding robot by the temperature sensor to record the heat input trend and generate the environmental temperature data.

[0056] The heat input change trend includes the temperature change curve (such as the peak temperature, the temperature rise rate, and the cooling rate) of each monitoring point in the welding area with time, and the cumulative distribution trend of heat on the workpiece in the continuous welding process, which specifically represents the expansion range of the heat-affected zone with the welding path, the temperature superposition effect of adjacent welding points, and the dynamic evolution process of the overall thermal deformation. Real-time data collected by the temperature sensor is used to generate a temperature gradient graph and a heat input history curve, which are used to analyze the influence of the welding thermal cycle on the deformation of the workpiece.

[0057] S3, continuously collecting the current value, voltage value and wire feeding speed data of the preset welding power source through the current and voltage sensor, and simultaneously, monitoring the force change of the welding gun when contacting the workpiece through the force sensor to judge the collision risk in the welding process, and recording in real time to generate welding parameter data, and packaging the welding parameter data, robot pose data, weld appearance data and environmental temperature data to generate dynamic data, and uploading the dynamic data to the twin data layer 3 and the virtual space module 2 through the data transmission network;

[0058] The specific steps of judging the collision risk in the welding process are as follows:

[0059] S31, collecting the force value and torque change data in multiple directions when the welding gun contacts the workpiece in real time through the force sensor;

[0060] S32, setting the dynamic safety threshold range of the force in each direction according to the current welding parameters and the welding gun attitude;

[0061] S33, if the force value and torque change data of the welding gun exceed the dynamic safety threshold within a preset time period or there is an abnormal force peak, it is determined that there is a collision risk;

[0062] S34, generating a welding gun avoidance path adjustment instruction according to the collision risk judgment result, and issuing it to the multi-welding robot in real time through the data transmission network for execution.

[0063] The virtual space module 2 includes a multi-welding robot twin and a workpiece twin model, and the virtual space module 2 is completely mapped from the physical space module 1; wherein the specific steps of completely mapping the virtual space module 2 from the physical space module 1 are:

[0064] M1, the virtual space module 2 receives dynamic data, and extracts mechanical structure parameters, motion joint parameters and welding process parameters of the multi-welding robot based on the dynamic data, and generates model data of the multi-welding robot twin corresponding to the multi-welding robot, wherein the generation method of the model data of the multi-welding robot twin is as follows: first, the virtual space module 2 receives the dynamic data packet from the physical space module 1, and analyzes the robot mechanical structure parameters (including mechanical arm length, joint connection mode and welding gun installation position), motion joint parameters (including the degree of freedom, motion range and dynamic response characteristics of each joint) and welding process parameters (including preset current, voltage, wire feeding speed and welding path planning data) therein; secondly, the analyzed mechanical structure parameters are converted into a three-dimensional geometric model through a parameterized modeling tool, and a kinematics model of the multi-welding robot twin is constructed in combination with the motion joint parameters, simulating the joint motion range and linkage relationship thereof; at the same time, the welding process parameters are bound with the virtual welding gun model, and the current, voltage data are associated with the virtual welding effect (such as molten pool shape, heat input); finally, the joint motion accuracy and welding process parameters of the twin are continuously calibrated through real-time dynamic data, so as to ensure that the virtual model is completely consistent with the mechanical structure, motion characteristics and process setting of the physical robot, and form a high-fidelity multi-welding robot twin model data;

[0065] M2, according to the model data of the multi-welding robot twin, a three-dimensional geometric model and a motion model of the multi-welding robot twin are established, and a workpiece twin model consistent with the workpiece is constructed in combination with the weld appearance data, and the motion trajectory and welding process parameters of the multi-welding robot twin are continuously corrected according to the real-time dynamic data in the physical space module 1, and a virtual simulation unit is preset to verify the consistency of the motion trajectory and welding process parameters of the corrected multi-welding robot twin with the real-time dynamic data in the physical space module 1, and when the verification is successful, a complete virtual space module 2 is generated.

[0066] Wherein, according to the real-time dynamic data in the physical space module 1, the motion trajectory and welding process parameters of the multi-welding robot twin are continuously corrected, and the steps are as follows:

[0067] M201, the virtual space module 2 receives the robot pose data and welding parameter data uploaded by the physical space module 1 in real time, and dynamically compares the current motion trajectory and process parameters of the multi-welding robot twin, calculates the coordinate offset of the actual pose and the virtual model and the welding parameter deviation;

[0068] The method for calculating the coordinate offset of the actual pose and the virtual model and the welding parameter deviation is: real-time acquisition of the actual welding gun position coordinates (such as X / Y / Z axis coordinates) and joint angle data of the plurality of welding robots in the physical space module (1) is performed, and the welding gun virtual coordinates and joint angles of the plurality of welding robot twins in the virtual space module (2) are compared point by point, and the position difference (such as the Euclidean distance) and the joint angle deviation in the three-dimensional space are calculated; at the same time, the actual welding current and voltage values collected in the physical space are compared with the process parameters bound in the virtual model, and the current deviation and voltage deviation are calculated, and finally the pose offset, current deviation and voltage deviation are comprehensively generated to generate the coordinate offset and the welding parameter deviation;

[0069] M202, based on the coordinate offset and the welding parameter deviation, the joint motion trajectory of the plurality of welding robot twins is adjusted through an interpolation algorithm, so that the virtual welding gun position is synchronized with the actual plurality of welding robot poses, and the virtual values of the welding current and voltage parameters are dynamically compensated to match the real-time process state of the physical device;

[0070] M203, the corrected motion trajectory of the plurality of welding robot twins and the welding parameters are input into the virtual simulation unit to simulate the welding process in the future time period, generate predicted weld forming and thermal deformation data, and verify the consistency with the real-time collected data of the physical space module 1;

[0071] M204, if the verification result shows that the error between the predicted data and the actual data exceeds the preset threshold, the smoothing coefficient of the motion model of the plurality of welding robot twins and the weight of the welding process parameters are adjusted again, and steps M21 to M23 are executed in a loop until the error converges to within the threshold range.

[0072] In step M2, the virtual simulation unit verifies the consistency of the corrected motion trajectory of the plurality of welding robot twins and the welding process parameters with the real-time dynamic data in the physical space module 1, and the specific steps are:

[0073] M21, based on the corrected motion trajectory of the plurality of welding robot twins and the welding process parameters, the virtual simulation unit drives the plurality of welding robot twins and the workpiece twin model to perform welding process simulation, and generates virtual welding parameters, virtual weld forming quality data and virtual thermal deformation state data;

[0074] M22, the virtual welding parameters are compared with the actual motion trajectory data of the plurality of welding robots in the physical space module 1 in real time, and the virtual weld forming quality and virtual thermal deformation state data are analyzed for differences with the weld appearance data and environmental temperature data collected by the physical space module 1;

[0075] The difference analysis in step M22 specifically includes: comparing the weld width, height and geometric shape parameters in the virtual weld forming quality data with the measured values of the actual weld appearance data collected by the physical space module 1, and calculating the size error percentage of the two; at the same time, the temperature distribution and workpiece deformation in the virtual thermal deformation state data are regionally matched with the environmental temperature data of the physical space, and the temperature difference and deformation deviation amplitude of each monitoring point are analyzed; the virtual and physical data are aligned based on the time stamp, and if there is a time delay, the comparison is compensated by interpolation, and finally it is determined whether the weld forming error exceeds ± 5%, the temperature deviation exceeds ± 10℃ or the deformation error exceeds ± 0.2mm, and any index exceeding the limit triggers correction;

[0076] M23, if the difference analysis result exceeds the preset threshold, it is determined that the virtual space module 2 and the physical space module 1 are inconsistent, and the motion trajectory and welding parameter of the multi-welding robot twin are triggered to be corrected by the virtual space module 2; if the difference is within the threshold, it is confirmed that the consistency verification is passed, and the current corrected virtual space module 2 is locked as the effective mapping.

[0077] The virtual space module 2 simulates the welding process in real time through the multi-welding robot twin and the workpiece twin model;

[0078] The twin data layer 3 is used to connect the physical space module 1 and the virtual space module 2, fuse and synchronize the data of the dynamic data and the motion trajectory, weld forming quality and thermal deformation state of the multi-welding robot twin and the workpiece twin model, and predict the motion trajectory, weld forming quality and thermal deformation state of the multi-welding robot through a preset prediction unit;

[0079] In the twin data layer 3, the data of the dynamic data and the motion trajectory, weld forming quality and thermal deformation state of the multi-welding robot twin and the workpiece twin model are fused and synchronized, and the specific method includes:

[0080] Q1, the twin data layer 3 receives the dynamic data transmitted by the physical space module 1, and analyzes the robot pose data, welding parameter data, weld appearance data and environmental temperature data in the dynamic data through a preset analysis unit;

[0081] Q2, the analyzed robot pose data is one-to-one matched with the motion joint parameters of the multi-welding robot twin, the welding parameter data is associated with the virtual welding process parameters of the welding gun of the multi-welding robot twin, and the weld appearance data and the environmental temperature data are mapped to the corresponding regions of the workpiece twin model;

[0082] Q3, the twin data layer 3 is based on the dynamic data of real-time analysis, drives the multi-welding robot twin to execute the same motion trajectory in the virtual space as the multi-welding robot, and updates the thermal deformation state and weld forming quality of the workpiece twin model, and completes the fusion and synchronization of data.

[0083] Wherein, the specific steps of predicting the motion trajectory, weld forming quality and thermal deformation state of the multi-welding robot in the twin data layer 3 through the preset prediction unit include:

[0084] Q4, based on the motion trajectory data of the multi-welding robot twin and the current thermal deformation state of the workpiece twin model, simulate the welding process in the prediction unit in the future time period, generate predicted motion trajectory data, predicted weld forming size data and predicted thermal deformation distribution data;

[0085] Q5, real-time comparison and analysis of the predicted motion trajectory data and the real-time motion trajectory of the multi-welding robot in the physical space module 1, and difference calculation of the predicted weld forming size data and the predicted thermal deformation distribution data and the weld appearance data and the environmental temperature data collected by the physical space module 1;

[0086] Q6, if the difference calculation result exceeds the preset threshold value, adjust the weight coefficient of the welding process parameter in the prediction unit and the preset thermal deformation simulation algorithm according to the difference direction, and re-execute steps Q4 to Q5 until the difference between the predicted motion trajectory data, the predicted weld forming size data and the predicted thermal deformation distribution data and the actual data collected by the physical space module 1 is within the threshold value; if the difference calculation result is less than the preset threshold value, output the predicted motion trajectory data, the predicted weld forming size data and the predicted thermal deformation distribution data to the control module 4, wherein the specific content of adjusting according to the difference direction includes: if the weld forming size predicted value is greater than the actual value, reduce the weight coefficient of the welding current parameter and increase the weight of the wire feeding speed to reduce the simulation size of the virtual molten pool; if the thermal deformation predicted value exceeds the actual temperature distribution, reduce the thermal conductivity coefficient of the heat input simulation model or increase the cooling rate parameter; if the motion trajectory prediction deviation direction is consistent with the actual deviation, increase the smoothing coefficient of the path planning or limit the joint motion acceleration threshold; at the same time, dynamically optimize the iteration step length of the thermal deformation simulation algorithm and the correlation weight of the welding parameters based on the historical error data until the prediction data and the physical data are consistent.

[0087] Wherein, the specific steps of difference calculation in step Q5 include:

[0088] Q51, align the predicted motion trajectory data, the predicted weld forming size data and the predicted thermal deformation distribution data generated by the prediction unit with the actual motion trajectory data, the actual weld appearance data and the actual environmental temperature data collected by the physical space module 1 in the same time period;

[0089] Timestamp alignment method: unify the predicted data and the acquisition time of the data in the physical space module to the same clock source. For the data segment with missing or delayed timestamp, insert a virtual data point in the predicted time sequence by linear interpolation method, or truncate the unaligned time segment in the physical data; At the same time, set a sliding time window (such as 0.1 seconds) to ensure that the prediction and the physical data match within the same time window;

[0090] Q52, compare the coordinate deviation of the predicted motion trajectory data and the actual motion trajectory data point by point in time, calculate the average offset and the maximum offset of each robot joint position, obtain the trajectory offset, compare the weld width and height in the predicted weld forming size data with the measured values of the weld appearance data, calculate the width error percentage and the height absolute error value, obtain the weld error, compare the predicted deformation state data with the actual environment temperature data, calculate the difference between the predicted temperature and the actual temperature of the key area of the workpiece, and the deviation amplitude of the deformation amount, obtain the thermal deformation deviation, the trajectory offset, the weld error and the thermal deformation deviation are the difference calculation results.

[0091] The calculation method of the trajectory offset is to calculate the Euclidean distance of the predicted and actual coordinates point by point, and to calculate the average offset and the maximum offset value of all robot joints.

[0092] The calculation method of the weld error is to compare the width and height of the predicted and actual welds, and to calculate the width error (predicted value-actual value / actual value x 100%) and the height absolute error (predicted value-actual value).

[0093] The calculation method of the thermal deformation deviation is to select the key area of the workpiece (such as the weld periphery), calculate the average difference between the predicted temperature and the actual temperature, and the geometric deviation of the deformation amount (the vector module length average of the predicted deformation coordinates-actual deformation coordinates).

[0094] The control module 4 generates the welding path optimization scheme, the multi-welding robot collision avoidance strategy and the welding quality feedback control instruction based on the twin data layer 3, and sends the control instruction to the multi-welding robot in the physical space module 1 through the preset logic controller.

[0095] The specific steps of the control module 4 are as follows:

[0096] H1, based on the trajectory offset, the weld error and the thermal deformation deviation, generate a multi-robot collision avoidance path planning scheme, adjust the compensation value of the welding current and voltage parameters of the multi-welding robot according to the weld error, and optimize the welding sequence based on the thermal deformation deviation;

[0097] H2, the generated multi-robot cooperative collision avoidance path planning scheme, compensation value and welding sequence are transmitted to the multi-welding robot in the physical space module 1 through a logic controller in real time, and the multi-welding robot is driven to execute the corrected welding action;

[0098] H3, in the welding process, the multi-welding robot continuously receives the predicted data updated by the twin data layer 3 and the dynamic data of the physical space module 1, and if it is detected that the error of the robot pose data or the weld appearance data exceeds the preset threshold, steps H2 to H3 are re-executed until the welding task is completed.

[0099] The above is only an embodiment of the present application, and does not limit the patent scope of the present application, and any equivalent structure or equivalent process transformation using the content of the present application specification and drawings, or direct or indirect application in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A multi-welding robot collaborative working system based on digital twinning, characterized in that: The application relates to a welding system, which comprises a physical space module (1), a virtual space module (2), a twin data layer (3) and a control module (4). The physical space module (1) comprises a plurality of welding robots, a sensor group and a data transmission network, the physical space module (1) performs a welding task through the plurality of welding robots, collects dynamic data in a welding process in real time through the sensor group, and transmits the dynamic data through the data transmission network. The virtual space module (2) comprises a plurality of welding robot twins and a workpiece twin model, and is completely mapped by the physical space module (1); the virtual space module (2) simulates a welding process in real time through the plurality of welding robot twins and the workpiece twin model. The twin data layer (3) is used for connecting the physical space module (1) and the virtual space module (2), fusing and synchronizing data of the dynamic data, motion trajectories of the plurality of welding robot twins and the workpiece twin model, welding forming quality and thermal deformation states, and predicting the motion trajectories of the plurality of welding robots, the welding forming quality and the thermal deformation states through a preset prediction unit. The control module (4) generates a control instruction based on the twin data layer (3) and sends the control instruction to the plurality of welding robots for execution. Communication connections are established among the physical space module (1), the virtual space module (2), the twin data layer (3) and the control module (4). The sensor group in the physical space module (1) comprises a visual sensor, a force sensor, a temperature sensor, a current and voltage sensor. The dynamic data in the physical space module (1) comprises welding parameter data, robot pose data, weld appearance data and environmental temperature data. The dynamic data collection method comprises the following steps: S1, scanning a to-be-welded area of a workpiece through the visual sensor to obtain a first visual image of a weld position, shape and size, scanning a welding posture of the plurality of welding robots through the visual sensor to generate a second visual image, and using an image processing algorithm to denoise and enhance features of the first visual image and the second visual image to generate weld appearance data and robot pose data. S2, collecting temperature distribution data of a welding area of the plurality of welding robots through the temperature sensor, recording a heat input change trend, and generating environmental temperature data. ​ S3, continuously collect the current value, voltage value and wire feeding speed data of the preset welding power source through the current and voltage sensor, at the same time, monitor the force change of the welding gun of the multi-welding robot when it contacts with the workpiece through the force sensor, judge the collision risk in the welding process, record in real time, generate welding parameter data, package the welding parameter data, the robot pose data, the weld appearance data and the environment temperature data to generate dynamic data, and upload the dynamic data to the twin data layer (3) and the virtual space module (2) through the data transmission network; The twin data layer (3) fuses and synchronizes the dynamic data and the motion trajectory, welding forming quality and thermal deformation state of the multi-welding robot twin and the workpiece twin model, and the specific method comprises: Q1, the twin data layer (3) receives the dynamic data transmitted by the physical space module (1), and analyzes the robot pose data, welding parameter data, weld appearance data and environment temperature data in the dynamic data through a preset analysis unit; Q2, match the analyzed robot pose data with the motion joint parameters of the multi-welding robot twin one by one, associate the welding parameter data with the virtual welding process parameters of the welding gun of the multi-welding robot twin, and map the weld appearance data and environment temperature data to the corresponding area of the workpiece twin model; Q3, based on the real-time analyzed dynamic data, the twin data layer (3) drives the multi-welding robot twin to execute the same motion trajectory as the multi-welding robot in the virtual space, and updates the thermal deformation state and weld forming quality of the workpiece twin model, completing data fusion and synchronization.

2. The digital-twin-based multi-welding robot collaborative working system according to claim 1, characterized in that: The specific steps of the virtual space module (2) completely mapped by the physical space module (1) are: M1, the virtual space module (2) receives the dynamic data, and extracts the mechanical structure parameters, motion joint parameters and welding process parameters of the multi-welding robot based on the dynamic data, to generate model data of the multi-welding robot twin corresponding to the multi-welding robot; M2, according to the model data of the multi-welding robot twin, establish a three-dimensional geometric model and a motion model of the multi-welding robot twin, and construct a workpiece twin model consistent with the workpiece in combination with the weld appearance data, and continuously correct the motion trajectory and welding process parameters of the multi-welding robot twin according to the real-time dynamic data in the physical space module (1), and preset a virtual simulation unit to verify the consistency of the corrected motion trajectory and welding process parameters of the multi-welding robot twin with the real-time dynamic data in the physical space module (1), and generate a complete virtual space module (2) after verification success.

3. The digital-twin-based multi-welding robot collaborative working system according to claim 2, characterized in that: The specific steps of the virtual simulation unit preset in step M2 to verify the consistency of the corrected motion trajectory and welding process parameters of the multi-welding robot twin with the real-time dynamic data in the physical space module (1) are: M21, based on the corrected motion trajectory of the multi-welding robot twin and the welding process parameters, the virtual simulation unit drives the multi-welding robot twin to carry out welding process simulation with the workpiece twin model, and generates virtual welding parameters, virtual weld forming quality data and virtual thermal deformation state data; M22, the virtual welding parameters are compared with the actual motion trajectory data of the multi-welding robot in the physical space module (1) in real time, and the virtual weld forming quality and the virtual thermal deformation state data are analyzed by difference with the weld appearance data and the environmental temperature data collected by the physical space module (1); M23, if the difference analysis result exceeds the preset threshold value, it is judged that the virtual space module (2) and the physical space module (1) are inconsistent, and the virtual space module (2) is triggered to re-correct the motion trajectory and welding parameters of the multi-welding robot twin; if the difference is within the threshold value, it is confirmed that the consistency verification is passed, and the current corrected virtual space module (2) is locked as the effective mapping.

4. The digital-twin-based multi-welding robot collaborative working system according to claim 3, characterized in that: The specific steps of predicting the motion trajectory, weld forming quality and thermal deformation state of the multi-welding robot in the twin data layer (3) through the preset prediction unit include: Q4, based on the motion trajectory data of the multi-welding robot twin and the current thermal deformation state of the workpiece twin model, simulate the welding process in the future time period in the prediction unit, generate predicted motion trajectory data, predicted weld forming size data and predicted thermal deformation distribution data; Q5, the predicted motion trajectory data is compared with the real-time motion trajectory of the multi-welding robot in the physical space module (1) in real time, and the predicted weld forming size data and the predicted thermal deformation distribution data are calculated by difference with the weld appearance data and the environmental temperature data collected by the physical space module (1); Q6, if the difference calculation result exceeds the preset threshold value, adjust the weight coefficient of the welding process parameters in the prediction unit and the preset thermal deformation simulation algorithm according to the difference direction, and re-execute steps Q4 to Q5 until the predicted motion trajectory data, the predicted weld forming size data and the predicted thermal deformation distribution data are within the threshold range of the actual data collected by the physical space module (1); if the difference calculation result is less than the preset threshold value, output the predicted motion trajectory data, the predicted weld forming size data and the predicted thermal deformation distribution data to the control module (4).

5. The digital-twin-based multi-welding robot collaborative working system according to claim 4, characterized in that: The specific steps of difference calculation in step Q5 include: Q51, the predicted motion trajectory data, the predicted weld forming size data and the predicted thermal deformation distribution data generated by the prediction unit are time stamped and aligned with the actual motion trajectory data, actual weld appearance data and actual environmental temperature data collected by the physical space module (1) in the same time period; Q52. Compare the coordinate deviations of the predicted motion trajectory data and the actual motion trajectory data at each time point, calculate the average and maximum offsets of each robot joint position to obtain the trajectory offset, compare the weld width and height in the predicted weld forming size data with the measured values ​​of the weld morphology data, calculate the width error percentage and the height absolute error value to obtain the weld error, compare the predicted deformation state data with the actual ambient temperature data, calculate the difference between the predicted temperature and the actual temperature of the key area of ​​the workpiece, as well as the deviation amplitude of the deformation, to obtain the thermal deformation deviation. The trajectory offset, the weld error, and the thermal deformation deviation are the difference calculation results.

6. The digital-twin-based multi-welding robot collaborative working system according to claim 5, characterized in that: The specific steps of the control module (4) are as follows: H1. Based on the trajectory offset, the weld error, and the thermal deformation deviation, a multi-robot collaborative collision avoidance path planning scheme is generated. At the same time, the compensation values ​​of the welding current and voltage parameters of the multi-welding robots are adjusted according to the weld error, and the welding sequence is optimized based on the thermal deformation deviation. H2. The generated multi-robot collaborative collision avoidance path planning scheme, compensation value and welding sequence are sent to the multi-welding robot in the physical space module (1) in real time through the logic controller, and the multi-welding robot is driven to perform the corrected welding action. H3. During the welding process, the multi-welding robot continuously receives the prediction data updated by the twin data layer (3) and the dynamic data of the physical space module (1). If the error of the robot pose data or the weld morphology data exceeds the preset threshold, steps H2 to H3 are re-executed until the welding task is completed.

Images