Welding data processing method and device, welding equipment, storage medium and processor
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- ZHONGKE YUNGU TECH
- Filing Date
- 2023-06-30
- Publication Date
- 2026-06-19
AI Technical Summary
During the welding of large booms, the uneven gap distribution caused by the boom length makes it difficult to select welding parameters. Prolonged welding can lead to changes in the position and shape of the weld, affecting the welding quality. Manual intervention is costly and poses safety risks.
By acquiring welding data, processing welding parameters, predicting welding quality scores, filtering and expanding welding parameters, and using machine learning models for real-time data analysis and adjustment, dynamic optimization and long-distance adaptive welding can be achieved.
It improves welding quality and structural strength, reduces manual intervention, increases work efficiency and safety, and reduces operator errors and fatigue.
Smart Images
Figure CN116618904B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of intelligent welding technology, specifically to a welding data processing method, apparatus, welding equipment, storage medium, and processor. Background Technology
[0002] In the welding of large crane booms, the boom length typically exceeds 10 meters, resulting in highly uneven gap distribution. The gap between the workpieces affects the selection of welding parameters. Furthermore, prolonged welding can cause changes in the position and shape of the weld seam due to thermal stress, thermal deformation, and assembly errors. Without real-time adjustments, this can lead to decreased weld quality and defects. Additionally, manual intervention and monitoring are costly and risky, reducing welding efficiency and potentially causing safety accidents. Summary of the Invention
[0003] The purpose of this application is to provide a welding data processing method, apparatus, welding equipment, storage medium, and processor.
[0004] To achieve the above objectives, the first aspect of this application provides a welding data processing method, comprising:
[0005] Acquire welding data of the welding equipment during the welding process. The welding data includes the first welding parameters when welding the current area and the gap data of the area to be welded.
[0006] The first welding parameters are processed, and the first welding quality score is predicted after the welding equipment performs welding on the area to be welded based on the processed first welding parameters.
[0007] If the first welding quality fraction is less than the preset quality fraction, multiple sets of second welding parameters corresponding to the gap data are selected from the database based on the gap data.
[0008] Each set of second welding parameters is expanded to obtain multiple sets of third welding parameters corresponding to each set of second welding parameters;
[0009] The predicted welding equipment performs welding on the area to be welded based on each set of third welding parameters, resulting in a second welding quality score.
[0010] The target welding parameter is selected from multiple sets of third welding parameters based on all the second welding quality scores, so that the welding equipment can weld the area to be welded according to the target welding parameter.
[0011] In the embodiments of this application, the selection of target welding parameters from multiple sets of third welding parameters based on all the second welding quality scores includes: for each set of third welding parameters, if the second welding quality score is greater than or equal to a preset quality score, the third welding parameter is determined as the fourth welding parameter; if multiple sets of fourth welding parameters exist among the multiple sets of third welding parameters, the fourth welding parameter closest to the first welding parameter is determined as the target welding parameter; if only one set of fourth welding parameters exists among the multiple sets of third welding parameters, the fourth welding parameter is determined as the target welding parameter.
[0012] In embodiments of this application, when multiple sets of fourth welding parameters exist among multiple sets of third welding parameters, determining the target welding parameter by the fourth welding parameter that is closest to the first welding parameter includes: when multiple sets of fourth welding parameters exist among multiple sets of third welding parameters, determining the weighted average value of each set of fourth welding parameters and the first welding parameter; and determining the fourth welding parameter corresponding to the minimum value among the multiple weighted average values as the target welding parameter.
[0013] In embodiments of this application, when multiple sets of fourth welding parameters exist among multiple sets of third welding parameters, determining the weighted average of each set of fourth welding parameters and the first welding parameter includes calculating the weighted average of the parameters according to the following formula (1):
[0014] (1)
[0015] in, This refers to the weighted average of the fourth welding parameter and the first welding parameter in each group, while V refers to the difference between the voltage in the fourth welding parameter and the voltage in the first welding parameter in each group. This refers to the weight corresponding to the voltage, and I refers to the difference between the current in the fourth welding parameter and the current in the first welding parameter in each group. This refers to the weight corresponding to the current. This refers to the temperature difference between the fourth welding parameter and the first welding parameter in each group. This refers to the weight corresponding to temperature, and S refers to the difference between the speed in the fourth welding parameter and the welding speed in the first welding parameter of each group. This refers to the weight corresponding to the welding speed.
[0016] In embodiments of this application, the processing method further includes: if the first welding quality fraction is greater than or equal to a preset quality fraction, determining the first welding parameter as the target welding parameter.
[0017] In the embodiments of this application, the processing method further includes a training step of a preset model. The preset model is used to predict the welding quality score of the area to be welded after welding by welding parameters. The training step includes: acquiring multiple sets of historical welding data, including historical gap data, historical welding parameters corresponding to the historical gap data, and historical temperature data; processing each set of historical welding data and extracting historical feature data of each set of historical welding data after processing; and training the preset model based on all historical feature data to obtain the trained preset model.
[0018] In embodiments of this application, historical feature data includes at least one of the energy output characteristics during the welding process, the temperature characteristics of the welding area, and the bevel characteristics.
[0019] A second aspect of this application provides a processor configured to perform the welding data processing method described above.
[0020] A third aspect of this application provides a welding data processing apparatus, including a processor configured to perform the welding data processing method described above.
[0021] A fourth aspect of this application provides a welding apparatus, including the aforementioned welding data processing device.
[0022] In embodiments of this application, the welding equipment further includes a current sensor for detecting the welding current of the welding equipment; a voltage sensor for detecting the welding voltage of the welding equipment; a laser rangefinder for detecting gap data of the area to be welded; and a temperature detection device for detecting the temperature of the current area, the temperature of the area to be welded, the temperature of the preheating area, and the global temperature.
[0023] A fifth aspect of this application provides a machine-readable storage medium storing instructions that, when executed by a processor, configure the processor to perform the welding data processing method described above.
[0024] The above technical solution acquires welding data during the welding process, including first welding parameters for the current area and gap data for the area to be welded. The first welding parameters are processed, and a first welding quality score is predicted after the welding equipment welds the area based on these parameters. If the first welding quality score is less than a preset score, multiple sets of second welding parameters corresponding to the gap data are selected from the database based on the gap data. Each set of second welding parameters is expanded to obtain multiple sets of third welding parameters corresponding to each set. A second welding quality score is predicted after the welding equipment welds the area based on each set of third welding parameters. A target welding parameter is selected from the multiple sets of third welding parameters based on all the second welding quality scores, allowing the welding equipment to weld the area according to the target welding parameter. Compared to traditional methods, this approach allows for prediction and control based on real-time welding data, enabling dynamic optimization and long-distance adaptive welding of the welding process. Furthermore, by combining real-time data with traversed welding parameters for parameter prediction, the obtained welding parameters are the most suitable, resulting in more stable welding quality and higher structural strength. Based on welding data processing, welding parameters can be automatically monitored, analyzed, and adjusted, reducing manual intervention and debugging work. This not only improves work efficiency and reduces operator errors and fatigue, but also enhances work safety.
[0025] Other features and advantages of the embodiments of this application will be described in detail in the following detailed description section. Attached Figure Description
[0026] The accompanying drawings are provided to further illustrate the embodiments of this application and form part of the specification. They are used together with the following detailed description to explain the embodiments of this application, but do not constitute a limitation on the embodiments of this application. In the drawings:
[0027] Figure 1 A schematic flowchart of a welding data processing method according to an embodiment of this application is shown.
[0028] Figure 2 This illustration schematically shows a step-by-step diagram of selecting target welding parameters according to an embodiment of this application;
[0029] Figure 3 This illustration schematically shows a step diagram of the training steps of a preset model according to an embodiment of this application;
[0030] Figure 4 A schematic diagram illustrating the structure of a welding data processing apparatus according to an embodiment of this application is shown.
[0031] Figure 5 A schematic diagram of a welding apparatus according to an embodiment of this application is shown.
[0032] Figure 6 The diagram illustrates the internal structure of a computer device according to an embodiment of this application. Detailed Implementation
[0033] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only for illustration and explanation of the embodiments of this application and are not intended to limit the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.
[0034] Figure 1 A schematic flowchart of a welding data processing method according to an embodiment of this application is shown. Figure 1 As shown, in one embodiment of this application, a welding data processing method is provided. This embodiment mainly uses the application of this method to the above-mentioned processing as an example for illustration, including the following steps:
[0035] S102, acquire welding data of the welding equipment during the welding process, including the first welding parameters when welding the current area and the gap data of the area to be welded.
[0036] Welding data refers to physical quantities that reflect the welding state during the welding process. Welding data includes the initial welding parameters for the current area and the gap data of the area to be welded. The initial welding parameters reflect the welding state of the welding equipment. Examples include the welding current, arc voltage, welding speed, wire (electrode) diameter, current polarity, wire extension length, and shielding gas flow rate during the welding process. Welding data can also include external parameters reflecting the welding state, such as gap data and temperature data of the welded workpiece. Gap data can be at least one of the following: the gap size of the lower surface, the gap size of the upper surface, the cross-sectional area, and misalignment of the welded workpiece. The processor can acquire the initial welding parameters for the current area and the gap data of the area to be welded. The area to be welded refers to the area to be welded next after the current area has been welded.
[0037] S104, process the first welding parameters and predict the first welding quality score after the welding equipment welds the area to be welded according to the processed first welding parameters.
[0038] The processor can process the first welding parameters. Specifically, it can perform data cleaning and data transformation on the first welding parameters. Data cleaning refers to cleaning, denoising, and handling outliers in the collected data to determine data quality. Data transformation refers to standardizing, normalizing, or performing other transformation operations on the data to make it suitable for subsequent parameter prediction and generation. Then, the processor can predict the first welding quality score corresponding to the welded area after the welding equipment welds the area to be welded according to the processed first welding parameters. The prediction method can be a deep learning model using machine learning. The welding quality score is used to characterize the post-weld quality; the higher the welding quality score, the better the welding quality and effect. The first welding quality score is used to characterize the welding quality after the welding equipment welds the area to be welded using the processed first welding parameters. That is, it predicts the post-weld quality when the welding equipment continues to maintain the current welding state of the area to be welded.
[0039] S106, if the first welding quality fraction is less than the preset quality fraction, select multiple sets of second welding parameters that are close to the gap data from the database based on the gap data.
[0040] The preset quality score is an empirical value set by technicians based on various factors such as the material of the workpiece, the welding equipment, and the intended use of the workpiece. Only when the preset quality score is achieved can the welding quality be considered to have met the expected standard. If the welding equipment welds the area to be welded according to the first welding parameters, and the processor predicts a first welding quality score lower than the preset quality score, then the processor can, based on the gap data of the area to be welded, summarize and filter multiple sets of second welding parameters from the database for this gap data. The database stores multiple sets of standard welding parameters that have yielded the best welding quality through multiple welds by technicians. Each set of standard welding parameters corresponds one-to-one with historical gap data; the standard welding parameters are the operating parameters of the welding equipment. For each type of historical gap data, the welding equipment can execute the corresponding set of standard welding parameters to achieve the best welding quality. In other words, the second welding parameters refer to the standard welding parameters corresponding to historical gap data in the database that are close to the gap data of the area to be welded. Examples include the welding current, arc voltage, welding speed of the welding torch, as well as the diameter of the welding wire (electrode), current polarity, wire extension length, and shielding gas flow rate.
[0041] S108, each group of second welding parameters is expanded to obtain multiple groups of third welding parameters corresponding to each group of second welding parameters.
[0042] For these second welding parameter sets, if they are used as input values for welding equipment to weld the area to be welded, although the historical gap data corresponding to these second welding parameter sets in the database are close to the gap data of the area to be welded, these second welding parameter sets are not precise. Therefore, the processor can expand each set of second welding parameters to obtain multiple sets of third welding parameters corresponding to each set of second welding parameters. Specifically, there are certain ranges between identical second welding parameters in different sets of second welding parameters. Then, the processor can expand the parameters within these ranges to generate multiple sets of third welding parameters. For example, if the second welding parameters include voltage, current, temperature, and speed, and the processor selects 3 sets of second welding parameters from the database, then the processor fine-tunes the voltage, current, temperature, and speed of each set, expanding them within their respective ranges. If each set of second welding parameters is expanded to obtain 1000 sets of third welding parameters, then a total of 3000 sets of third welding parameters can be obtained.
[0043] S110, predicts the second welding quality score after the welding equipment welds the area to be welded according to the third welding parameters of each group.
[0044] If the welding equipment welds the area to be welded according to the third welding parameters, then for each set of third welding parameters, the processor can predict the second welding quality score of the area to be welded. It is understood that the second welding quality score is relative to the first welding quality score. The second welding quality score is used to characterize the welding quality of the area to be welded after the welding equipment uses the third welding parameters. That is, each set of third welding parameters has a corresponding predicted second welding quality score.
[0045] S112, select the target welding parameter from multiple sets of third welding parameters based on all the second welding quality scores, so that the welding equipment can weld the area to be welded according to the target welding parameter.
[0046] After predicting all the second welding quality scores corresponding to all the third welding parameter groups according to the above scheme, the processor can filter out the target welding parameters from multiple groups of third welding parameters based on the magnitude of the second welding quality scores. The target welding parameter refers to the input value used by the welding equipment to weld the area to be welded. For example, the processor can select the third welding parameter corresponding to the highest second welding quality score as the target welding parameter, thereby controlling the welding equipment to weld the area to be welded according to the target welding parameter. Compared with traditional methods, prediction and control can be performed based on real-time welding data, thereby achieving dynamic optimization of the welding process and long-distance adaptive welding. Furthermore, by combining real-time data with traversed welding parameters for parameter prediction, the obtained welding parameters are the most suitable parameters, resulting in more stable welding quality and higher structural strength.
[0047] In one embodiment, the processing method further includes: if the first welding quality fraction is greater than or equal to a preset quality fraction, determining the first welding parameter as the target welding parameter.
[0048] If the welding equipment welds the area to be welded according to the first welding parameters, and the processor predicts a first welding quality score that is greater than or equal to a preset quality score, then the processor can directly use the first welding parameters as the target welding parameters. The processor can control the welding equipment to continue welding the current area to be welded without adjusting the welding parameters of the welding equipment.
[0049] refer to Figure 2 In one embodiment, selecting target welding parameters from multiple sets of third welding parameters based on all second welding quality scores includes the following steps:
[0050] S202, for each group of third welding parameters, if the second welding quality fraction is greater than or equal to the preset quality fraction, the third welding parameter is determined as the fourth welding parameter.
[0051] S204. Determine whether there are multiple sets of fourth welding parameters among the multiple sets of third welding parameters. If yes, execute S206; otherwise, execute S208.
[0052] S206, determine the target welding parameter by the fourth welding parameter that is closest to the first welding parameter.
[0053] S208, the fourth welding parameter is determined as the target welding parameter.
[0054] The processor expands each set of second welding parameters to obtain multiple sets of third welding parameters corresponding to each set. If the welding equipment welds the area to be welded according to the third welding parameters, the processor can predict the second welding quality score of the area to be welded after welding for each set of third welding parameters. If the second welding quality score is greater than or equal to the preset quality score, it means that the welding equipment can weld the area to be welded by executing this set of third welding parameters, and the weld quality is likely to meet the expected requirements. Then, the processor can determine the third welding parameters as the fourth welding parameters. The fourth welding parameter refers to the input value of the welding equipment corresponding to the predicted welding quality that meets the expected requirements after welding the area to be welded. If multiple sets of third welding parameters meet the requirements for the fourth welding parameters, the target welding parameters can be further selected based on these multiple sets of fourth welding parameters. If only one set of third welding parameters meets the requirements for the fourth welding parameters, the processor can directly use this set of fourth welding parameters as the target welding parameters. In this way, the welding equipment can weld the area to be welded according to the target welding parameters.
[0055] In one embodiment, when multiple sets of fourth welding parameters exist among multiple sets of third welding parameters, determining the target welding parameter based on the multiple sets of fourth welding parameters includes: determining the weighted average value of each set of fourth welding parameters and the first welding parameter; and determining the fourth welding parameter corresponding to the minimum value among the multiple weighted average values as the target welding parameter.
[0056] If multiple sets of third welding parameters are obtained, and several sets of fourth welding parameters meet the requirements, then the target welding parameter can be further selected based on these multiple sets of fourth welding parameters. Specifically, for each set of fourth welding parameters, the processor can calculate the weighted average of the fourth welding parameters and the first welding parameters. The smaller the weighted average, the closer the fourth welding parameter is to the first welding parameter. Therefore, the processor can filter out the minimum value among the multiple weighted averages and use the fourth welding parameter corresponding to this minimum value as the target welding parameter.
[0057] In one embodiment, when multiple sets of fourth welding parameters exist among multiple sets of third welding parameters, a weighted average of the parameters between each set of fourth welding parameters and the first welding parameters is determined. For example, when the parameters included in the fourth welding parameters and the first welding parameters are current, voltage, temperature, and speed, the processor can calculate the weighted average of the parameters according to the following formula (1):
[0058] (1)
[0059] in, This refers to the weighted average of the fourth welding parameter and the first welding parameter in each group, while V refers to the difference between the voltage in the fourth welding parameter and the voltage in the first welding parameter in each group. This refers to the weight corresponding to the voltage, and I refers to the difference between the current in the fourth welding parameter and the current in the first welding parameter in each group. This refers to the weight corresponding to the current. This refers to the temperature difference between the fourth welding parameter and the first welding parameter in each group. This refers to the weight corresponding to temperature, and S refers to the difference between the speed in the fourth welding parameter and the welding speed in the first welding parameter of each group. This refers to the weight corresponding to the welding speed. The processor can then filter out the minimum value among the weighted averages of multiple parameters and use the fourth welding parameter corresponding to this minimum value as the target welding parameter. The processor can then input the values of current, voltage, temperature, and speed from the target welding parameter into the welding equipment, causing the equipment to execute the target welding parameters to weld the area to be welded. In this way, the welding parameters that achieve the best welding quality can be accurately selected, significantly reducing the number of parameter changes and improving the surface quality and stability of the welded parts. While ensuring stable welding quality and higher structural strength, it also makes the welding process more stable, achieving dynamic optimization of the welding process and long-distance adaptive welding.
[0060] like Figure 3 Show, Figure 3 The illustration schematically depicts the training steps of a preset model according to an embodiment of this application. (Reference) Figure 3 In one embodiment, the processing method further includes a training step for a preset model, which is used to predict the welding quality score of the area to be welded after welding, and the training step includes:
[0061] S302, acquire multiple sets of historical welding data, including historical gap data, historical welding parameters corresponding to the historical gap data, and historical temperature data.
[0062] S304, process each set of historical welding data and extract the historical feature data of each set of historical welding data after processing.
[0063] S306, Train the preset model based on all historical feature data to obtain the trained preset model.
[0064] In one embodiment, historical feature data includes at least one of the energy output characteristics during the welding process, the temperature characteristics of the welding area, and the bevel characteristics.
[0065] Specifically, when the processor predicts the weld quality score of the area to be welded after welding by the welding equipment based on a first welding parameter or a third welding parameter, the processor can input the first welding parameter or the third welding parameter into a preset model to output a first weld quality score corresponding to the first welding parameter, or a second weld quality score corresponding to the third welding parameter. The preset model can be a deep learning model obtained through machine learning. To obtain a preset model that can be used for prediction, the processor can acquire historical welding data, including historical gap data, historical welding parameters corresponding to the historical gap data, and historical temperature data.
[0066] Historical welding data refers to the physical quantities of welding states that can be observed during historical welding processes. Historical gap data, historical welding parameters, and historical temperature data are all sets of historical welding data collected at the same welding time. For each set of historical welding data, the processor can process the data and extract historical feature data. Historical feature data refers to data that shows the influence and relationship between historical welding data and welding quality. The processor can then train a preset model based on all historical feature data to obtain a trained preset model.
[0067] Specifically, the processor can perform rule-based denoising on historical welding data, removing spot weld data, out-of-range data, starting point data, and abnormal fluctuation data. Furthermore, the processor can utilize the DBScan clustering algorithm (Density-Based Spatial Clustering of Applications with Noise) to remove outliers from the historical welding data. Further, for the processed historical welding data, the processor can extract historical feature data from each data set. Specifically, the processor can perform standardization or normalization transformation on the processed historical welding data to extract features useful for machine learning algorithms. Historical feature data includes at least one of the following: energy output features during the welding process, temperature features of the welding area, and bevel features. Among these, energy output features include voltage data from the historical welding data. Current Frequency, Current / (Gap) At least one of the following: welding speed. Temperature characteristics include global maximum temperature. Temperature of the area to be welded At least one of the preheating temperatures. Bevel characteristics include at least one of the following: bevel cross-sectional area, upper surface clearance, and lower surface clearance.
[0068] The processor trains a pre-defined model based on the aforementioned historical feature data to obtain a trained model. Specifically, the pre-defined model can be the LightGBM model. Furthermore, the parameters of the LGBM model, such as the learning rate, tree depth, and number of leaf nodes, are adjusted according to actual conditions to optimize the model's performance and generalization ability. Further, all historical feature data is divided into training, testing, and validation sets. The training set is input into the LightGBM model for training. Through iterative optimization algorithms, the LightGBM model learns and adjusts based on the input features and corresponding labels, gradually improving its predictive ability. The trained LightGBM model is evaluated using the testing set. The performance and generalization ability of the model are assessed by calculating the difference between the predicted results and the actual labels (accuracy, recall, F1 score, etc.). Based on the evaluation results, the model can be fine-tuned and improved. Finally, after optimization, the validation set is used for the final evaluation of the LightGBM model's performance. If it passes the evaluation, the LightGBM model is imported into the adaptive system for subsequent application and inference to derive target welding parameters. Compared to traditional methods, machine learning-based adaptive welding data processing can automatically monitor, analyze, and adjust welding parameters, reducing manual intervention and debugging work. This not only improves work efficiency but also reduces operator errors and fatigue, thus enhancing work safety.
[0069] Through the above technical solution, a machine learning-based adaptive welding data processing system was established. This system can predict and control the welding process based on real-time welding data, thereby achieving dynamic optimization of the welding process and enabling long-distance adaptive welding. This allows for stable and efficient long-distance variable-gap robotic welding operations on large cranes. The real-time quality prediction method based on the machine learning model can determine whether the welding state is sustainable and whether the welding quality meets standards. When the model determines that welding is unsustainable in the current state, it searches for optimal welding parameters by combining real-time data with traversed welding parameters. This results in more stable welding quality and higher structural strength. Compared to traditional methods, this significantly reduces the number of parameter changes and improves the surface quality and stability of welded components. The machine learning-based adaptive welding data processing system can automatically monitor, analyze, and adjust welding parameters, reducing manual intervention and debugging work. This not only improves work efficiency but also reduces operator errors and fatigue, and enhances work safety.
[0070] Figure 1 This is a flowchart illustrating a welding data processing method in one embodiment. It should be understood that, although... Figure 1The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order in which these steps are executed, and they can be performed in other orders. Figure 1 At least some of the steps in the process may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.
[0071] In one embodiment, such as Figure 4 As shown, a welding data processing device 400 is provided, including a data acquisition module, a first prediction module, a data filtering module, a data expansion module, a second prediction module, and a first data determination module, wherein:
[0072] The data acquisition module 402 is used to acquire welding data of the welding equipment during the welding process. The welding data includes the first welding parameters when welding the current area and the gap data of the area to be welded.
[0073] The first prediction module 404 is used to process the first welding parameters and predict the first welding quality score after the welding equipment welds the area to be welded according to the processed first welding parameters.
[0074] The data filtering module 406 is used to filter out multiple sets of second welding parameters that are close to the gap data from the database when the first welding quality fraction is less than the preset quality fraction.
[0075] The data expansion module 408 is used to expand each group of second welding parameters to obtain multiple groups of third welding parameters corresponding to each group of second welding parameters.
[0076] The second prediction module 410 is used to predict the second welding quality score after the welding equipment welds the area to be welded according to each set of third welding parameters.
[0077] The first data determination module 412 is used to filter the target welding parameters from multiple sets of third welding parameters based on all the second welding quality scores, so that the welding equipment can weld the area to be welded according to the target welding parameters.
[0078] In one embodiment, the first data determination module 412 is further configured to, for each group of third welding parameters, determine the third welding parameter as the fourth welding parameter if the second welding quality score is greater than or equal to a preset quality score; if multiple groups of fourth welding parameters exist among multiple groups of third welding parameters, determine the fourth welding parameter closest to the first welding parameter as the target welding parameter; and if only one group of fourth welding parameters exists among multiple groups of third welding parameters, determine the fourth welding parameter as the target welding parameter.
[0079] In one embodiment, the first data determination module 412 is further configured to determine the weighted average value of each group of fourth welding parameters and the first welding parameters when there are multiple groups of fourth welding parameters among multiple groups of third welding parameters; and to determine the fourth welding parameter corresponding to the minimum value among the multiple weighted average values as the target welding parameter.
[0080] In one embodiment, the first data determination module 412 is further configured to calculate the weighted average of the parameters according to the following formula (1):
[0081] (1)
[0082] in, This refers to the weighted average of the fourth welding parameter and the first welding parameter in each group, while V refers to the difference between the voltage in the fourth welding parameter and the voltage in the first welding parameter in each group. This refers to the weight corresponding to the voltage, and I refers to the difference between the current in the fourth welding parameter and the current in the first welding parameter in each group. This refers to the weight corresponding to the current. This refers to the temperature difference between the fourth welding parameter and the first welding parameter in each group. This refers to the weight corresponding to temperature, and S refers to the difference between the speed in the fourth welding parameter and the welding speed in the first welding parameter of each group. This refers to the weight corresponding to the welding speed.
[0083] In one embodiment, the welding data processing device 400 further includes a second data determination module (not shown in the figure), used to determine the first welding parameter as the target welding parameter when the first welding quality fraction is greater than or equal to a preset quality fraction.
[0084] In one embodiment, the welding data processing device 400 further includes a training module (not shown in the figure) for training a preset model, which is used to acquire multiple sets of historical welding data, including historical gap data, historical welding parameters corresponding to the historical gap data, and historical temperature data; process each set of historical welding data, extract historical feature data of each set of historical welding data after processing; and train the preset model based on all historical feature data to obtain the trained preset model.
[0085] In one embodiment, historical feature data includes at least one of the energy output characteristics during the welding process, the temperature characteristics of the welding area, and the bevel characteristics.
[0086] Figure 5 A schematic diagram of a welding apparatus according to an embodiment of this application is shown. (Reference) Figure 5 In one embodiment, a welding apparatus 500 is provided, including the aforementioned welding data processing device 400. The welding data processing device 400 includes a processor configured to execute the aforementioned welding data processing method. The processor can predict and control based on real-time welding data, thereby achieving dynamic optimization of the welding process and enabling long-distance adaptive welding of the welding equipment.
[0087] refer to Figure 5 In one embodiment, the welding equipment 500 further includes a current sensor 510 for detecting the welding current of the welding equipment; a voltage sensor 520 for detecting the welding voltage of the welding equipment; a laser rangefinder 530 for detecting gap data of the area to be welded; and a temperature detection device 540 for detecting the temperature of the current area, the temperature of the area to be welded, the temperature of the preheating area, and the global temperature. When the welding equipment is welding the current area, the welding data of the current area and the welding data of the area to be welded can be collected to predict the welding quality based on the welding data. The welding data can also be saved to a database or used to train a machine learning model.
[0088] The welding data processing device includes a processor and a memory. The data acquisition module, the first prediction module, the data filtering module, the data expansion module, the second prediction module, and the first data determination module are all stored in the memory as program units. The processor executes the program modules stored in the memory to implement the corresponding functions.
[0089] The processor contains a kernel, which retrieves the corresponding program unit from memory. One or more kernels can be configured, and the welding data processing method can be implemented by adjusting the kernel parameters.
[0090] The memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.
[0091] This application provides a storage medium storing a program that, when executed by a processor, implements the above-described welding data processing method.
[0092] This application provides a processor for running a program, wherein the program executes the above-described welding data processing method during runtime.
[0093] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 6 As shown. The computer device includes a processor A01, a network interface A02, memory (not shown), and a database (not shown) connected via a system bus. The processor A01 provides computing and control capabilities. The memory includes internal memory A03 and a non-volatile storage medium A04. The non-volatile storage medium A04 stores an operating system B01, a computer program B02, and a database (not shown). The internal memory A03 provides an environment for the operation of the operating system B01 and the computer program B02 stored in the non-volatile storage medium A04. The database stores data for welding data processing methods. The network interface A02 communicates with external terminals via a network connection. When the computer program B02 is executed by the processor A01, it implements a welding data processing method.
[0094] Those skilled in the art will understand that Figure 6 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.
[0095] This application provides an apparatus including a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it implements the steps of a welding data processing method.
[0096] This application also provides a computer program product that, when executed on a data processing device, is suitable for executing a program that initializes a welding data processing method step.
[0097] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0098] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0099] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.
[0100] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0101] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0102] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.
[0103] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.
[0104] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.
[0105] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.
Claims
1. A welding data processing method, characterized in that, The processing method includes: The welding data of the welding equipment during the welding process is acquired, including the first welding parameters when welding the current area and the gap data of the area to be welded; The first welding parameters are processed, and the first welding quality score is predicted after the welding equipment performs welding on the area to be welded based on the processed first welding parameters. If the first welding quality fraction is less than the preset quality fraction, multiple sets of second welding parameters that are close to the gap data are selected from the database based on the gap data. Each set of second welding parameters is expanded to obtain multiple sets of third welding parameters corresponding to each set of second welding parameters; Predict the second welding quality score after the welding equipment welds the area to be welded according to each set of third welding parameters; The target welding parameter is selected from the multiple sets of third welding parameters based on all the second welding quality scores, so that the welding equipment can weld the area to be welded according to the target welding parameter; The step of selecting the target welding parameter from the multiple sets of third welding parameters based on all the second welding quality scores includes: For each group of third welding parameters, if the second welding quality fraction is greater than or equal to the preset quality fraction, the third welding parameter is determined as the fourth welding parameter. When multiple sets of fourth welding parameters exist among the multiple sets of third welding parameters, determine the parameter weighted average value between each set of fourth welding parameters and the first welding parameter; The fourth welding parameter corresponding to the minimum value among the weighted averages of multiple parameters is determined as the target welding parameter; If only one set of fourth welding parameters exists among the multiple sets of third welding parameters, then the fourth welding parameter is determined as the target welding parameter.
2. The welding data processing method according to claim 1, characterized in that, In the case where multiple sets of fourth welding parameters exist among the multiple sets of third welding parameters, determining the weighted average of the parameters between each set of fourth welding parameters and the first welding parameters includes calculating the weighted average of the parameters according to the following formula (1): （1） in, This refers to the weighted average of the fourth welding parameter and the first welding parameter in each group, where V is the difference between the voltage in the fourth welding parameter and the voltage in the first welding parameter in each group. This refers to the weight corresponding to the voltage, and I refers to the difference between the current in the fourth welding parameter group and the current in the first welding parameter group. This refers to the weight corresponding to the current. This refers to the temperature difference between the fourth welding parameter and the first welding parameter in each group. This refers to the weight corresponding to temperature, and S refers to the difference between the speed in the fourth welding parameter group and the welding speed in the first welding parameter group. This refers to the weight corresponding to the welding speed.
3. The welding data processing method according to claim 1, characterized in that, The processing method further includes: If the first welding quality fraction is greater than or equal to the preset quality fraction, the first welding parameter is determined as the target welding parameter.
4. The welding data processing method according to claim 1, characterized in that, The processing method further includes a training step for a preset model, wherein the preset model is used to predict the welding quality score after welding the area to be welded by welding parameters, and the training step includes: Acquire multiple sets of historical welding data, including historical gap data, historical welding parameters corresponding to the historical gap data, and historical temperature data; Process each set of historical welding data and extract the historical feature data of each set of processed historical welding data. The preset model is trained based on all historical feature data to obtain the trained preset model.
5. The welding data processing method according to claim 4, characterized in that, The historical feature data includes at least one of the energy output characteristics during the welding process, the temperature characteristics of the welding area, and the bevel characteristics.
6. A processor, characterized in that, It is configured to perform the welding data processing method according to any one of claims 1 to 5.
7. A welding data processing device, characterized in that, Includes the processor as described in claim 6.
8. A welding device, characterized in that, Includes the welding data processing apparatus as described in claim 7.
9. The welding equipment according to claim 8, characterized in that, The welding equipment also includes: A current sensor is used to detect the welding current of the welding equipment; A voltage sensor is used to detect the welding voltage of the welding equipment; A laser rangefinder is used to detect gap data in the area to be welded. A temperature detection device is used to detect the temperature of the current area, the temperature of the area to be welded, the temperature of the preheating area, and the global temperature.
10. A machine-readable storage medium storing instructions thereon, characterized in that, When executed by a processor, this instruction causes the processor to be configured to perform the welding data processing method according to any one of claims 1 to 5.