Data processing method, device and processor for welding knowledge base

Abstract

Embodiments of the present application provide a data processing method and device for a welding knowledge base, a processor and a storage medium. The method comprises: obtaining a plurality of preset parameter groups; welding each parameter group to determine welding data corresponding to each parameter group; cutting the welding data to obtain a plurality of sub-welding data for each welding data; determining a welding index value of each sub-welding data; generating welding knowledge corresponding to each sub-welding data according to each sub-welding data and the welding index value corresponding to each sub-welding data to establish a welding knowledge base; in the case that the welding knowledge included in the welding knowledge base does not reach a preset condition, redetermining the plurality of parameter groups; updating the welding knowledge base according to the redetermined plurality of parameter groups until the welding knowledge included in the updated welding knowledge base reaches the preset condition to adjust the overall distribution of the welding knowledge and improve the quality and reliability of the welding knowledge base.

Description

Technical Field

[0001] The present application relates to the field of data processing, and in particular to a data processing method, device, storage medium and processor for a welding knowledge base. Background Art

[0002] With the continuous development of automated welding, the welding knowledge base has become the decision-making basis for intelligent welding operations. Currently, welding parts are generally welded using traditional welding processes, manually selecting welding experimental conditions, or following welding experiment design principles to obtain welding data and build a welding knowledge base.

[0003] Traditional welding processes only obtain overall information about the welding process and are unable to quickly acquire multiple pieces of welding knowledge. Consequently, building a welding knowledge base is inefficient and time-consuming. Manually selecting welding experimental conditions to obtain welding data for building a welding knowledge base is blind and uncertain, making it impossible to construct a more refined welding knowledge base. However, the experimental conditions set by welding experimental design principles for obtaining welding data to build a welding knowledge base do not change with the distribution of different types of data in the welding knowledge base, which can easily lead to an imbalance in the number of different types of data in the welding knowledge base, resulting in lower quality welding knowledge bases. Summary of the Invention

[0004] The purpose of the embodiments of the present application is to provide a data processing method, device, storage medium and processor for a welding knowledge base.

[0005] In order to achieve the above objectives, the present application provides, in a first aspect, a data processing method for a welding knowledge base, comprising:

[0006] Acquire multiple preset parameter groups, each parameter group including multiple welding factors and a factor value of each welding factor;

[0007] Welding the workpieces to be welded according to each parameter group to determine welding data corresponding to each parameter group;

[0008] For each welding data, cutting the welding data to obtain a plurality of sub-welding data;

[0009] Determine the welding index value of each sub-welding data;

[0010] Generating welding knowledge corresponding to each sub-welding data according to each sub-welding data and a welding index value corresponding to each sub-welding data to establish a welding knowledge base;

[0011] When the welding knowledge included in the welding knowledge base does not meet the preset conditions, re-determine multiple parameter groups;

[0012] The welding knowledge base is updated according to the re-determined plurality of parameter groups until the welding knowledge included in the updated welding knowledge base meets the preset conditions.

[0013] In an embodiment of the present application, the method further includes: after establishing a welding knowledge base, determining the total amount of welding knowledge included in the welding knowledge base; when the total amount is less than a preset value, redetermining multiple parameter groups; updating the welding knowledge base according to the redetermined multiple parameter groups until the total amount of welding knowledge included in the updated welding knowledge base is greater than or equal to the preset value.

[0014] In an embodiment of the present application, the method also includes: when the total amount of welding knowledge included in the welding knowledge base is greater than or equal to a preset value, classifying the welding knowledge included in the welding knowledge base according to the type of welding indicator; determining a first amount of welding knowledge of the first type and a second amount of welding knowledge of the second type in the welding knowledge base; determining a quantity ratio between the first quantity and the second quantity; when the quantity ratio does not reach a preset ratio, determining that the welding knowledge included in the welding knowledge base does not meet a preset condition; when the quantity ratio reaches a preset ratio, determining that the welding knowledge included in the welding knowledge base meets the preset condition.

[0015] In an embodiment of the present application, the method also includes: after establishing a welding knowledge base, determining the sub-welding data corresponding to each type of welding indicator; for each type of welding indicator, obtaining the real-time factor value of each welding factor in the sub-welding data corresponding to the welding indicator; for each type of welding indicator, determining the value range of each welding factor corresponding to the welding indicator based on the real-time factor value of each welding factor.

[0016] In an embodiment of the present application, when the welding knowledge included in the welding knowledge base does not meet the preset conditions, redetermining multiple parameter groups includes: determining the number of welding knowledge corresponding to each type of welding indicator in the welding knowledge base; for any type of welding indicator, when it is determined that the number of welding knowledge corresponding to the welding indicator does not meet the preset quantity conditions, redetermining multiple parameter groups according to the value range of each welding factor in the sub-welding data corresponding to the welding indicator.

[0017] In an embodiment of the present application, for each type of welding indicator, determining the value range of each welding factor in the sub-welding data corresponding to the welding indicator according to the real-time factor value of each welding factor includes: combining the real-time factor values ​​of the welding factors in any number of sub-welding data to generate a plurality of sub-welding data to be predicted; sequentially inputting the sub-welding data to be predicted into the trained classification model to output the predicted welding indicator value for the sub-welding data to be predicted through the trained classification model, wherein the trained classification model is obtained by training the sub-welding data in the welding knowledge base; determining the type of welding indicator corresponding to each sub-welding data to be predicted according to the predicted welding indicator value; for each type of welding indicator, determining the value range of each welding factor corresponding to the welding indicator according to the factor value of each welding factor in the sub-welding data to be predicted and the sub-welding data in the welding knowledge base.

[0018] In an embodiment of the present application, for each welding data, the welding data is cut to obtain multiple sub-welding data, including: for each welding data, obtaining the welding segment data between the start time and the end time of the welding; and cutting the welding segment data according to the preset welding length to obtain sub-welding data corresponding to each preset welding length.

[0019] In an embodiment of the present application, each indicator type of the welding indicator includes multiple levels, each level corresponds to a different indicator score, and determining the welding indicator value of each sub-welding data includes: obtaining all indicator types corresponding to the welding indicators of each sub-welding data; determining the total indicator score corresponding to all indicator types according to the indicator score corresponding to each indicator type; and determining the welding indicator value of each sub-welding data according to the total indicator score and the number of all indicator types.

[0020] A second aspect of the present application provides a machine-readable storage medium having instructions stored thereon. When the instructions are executed by a processor, the processor is configured to execute the above-mentioned data processing method for a welding knowledge base.

[0021] A third aspect of the present application provides a processor configured to execute the above-mentioned data processing method for a welding knowledge base.

[0022] A fourth aspect of the present application provides a data processing device for a welding knowledge base, comprising the above-mentioned processor.

[0023] Through the above technical solution, a welding knowledge base can be quickly constructed, the welding knowledge in the welding knowledge base can be analyzed, and the overall distribution of welding knowledge in the welding knowledge base can be adjusted by re-determining the parameter group, thereby greatly improving the quality and reliability of the welding knowledge base. At the same time, it also provides a good data acquisition environment for the subsequent use of welding knowledge training models.

[0024] Other features and advantages of the embodiments of the present application will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the following detailed description, they are used to explain the embodiments of the present application but do not constitute a limitation on the embodiments of the present application. In the accompanying drawings:

[0026] Figure 1 The following schematically shows a flow chart of a data processing method for a welding knowledge base according to an embodiment of the present application;

[0027] Figure 2 The internal structure diagram of a computer device according to an embodiment of the present application is schematically shown. DETAILED DESCRIPTION

[0028] To make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the specific implementation methods described herein are only used to illustrate and explain the embodiments of the present application and are not used to limit the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0029] Figure 1 The following schematically shows a flow chart of a data processing method for a welding knowledge base according to an embodiment of the present application. Figure 1 As shown, in one embodiment of the present application, a data processing method for a welding knowledge base is provided, comprising the following steps:

[0030] Step 101: Acquire multiple preset parameter groups, each parameter group including multiple welding factors and a factor value of each welding factor.

[0031] Step 102 : Welding the workpieces to be welded is performed according to each parameter group to determine welding data corresponding to each parameter group.

[0032] Step 103 : for each welding data, cutting the welding data to obtain a plurality of sub-welding data.

[0033] Step 104: Determine the welding index value of each sub-welding data.

[0034] Step 105 : generating welding knowledge corresponding to each sub-welding data according to each sub-welding data and the welding index value corresponding to each sub-welding data, so as to establish a welding knowledge base.

[0035] Step 106 : if the welding knowledge included in the welding knowledge base does not meet the preset conditions, redetermine multiple parameter groups.

[0036] Step 107 : updating the welding knowledge base according to the re-determined plurality of parameter groups until the welding knowledge included in the updated welding knowledge base meets a preset condition.

[0037] The processor can obtain multiple preset parameter groups. Each parameter group can include multiple welding factors and the factor value of each welding factor. Welding factors can refer to factors that can affect welding indicators. Welding indicators can include indicators before welding, indicators during welding, and indicators after welding. Specifically, the indicators before welding can be welding conditions. The indicators during welding can be welding experimental parameters. The indicators after welding can be welding quality. For example, if the welding indicator is welding quality, factors that can affect welding quality can include welding current, welding voltage, and welding speed. In other words, welding factors can include welding current, welding voltage, and welding speed.

[0038] The processor can weld the parts to be welded according to each preset parameter group respectively to determine the welding data corresponding to each parameter group. The welding data may include real-time factor values ​​corresponding to multiple welding factors in each parameter group. Due to the different welding conditions of the parts to be welded, when welding is performed using the preset parameter group, the factor values ​​of the welding factors in each preset parameter group are constantly changing. That is, the real-time factor values ​​corresponding to multiple welding factors in each preset parameter group determined by the processor may be different from the factor values ​​of the welding factors in the preset parameter group. The welding data may also include other data during the welding process. For example, other data during the welding process may include welding posture inclination, molten pool image, welding sound, set wire feed speed, TCP coordinates, welding material, plate thickness, etc.

[0039] After determining the welding data corresponding to each preset parameter group, for each welding data, the processor can cut the welding data to obtain multiple sub-welding data and determine the welding index value of each sub-welding data. The processor can generate welding knowledge corresponding to each sub-welding data based on each sub-welding data and the welding index value corresponding to each sub-welding data to establish a welding knowledge base. Each sub-welding data may include real-time factor values ​​of multiple welding factors. For example, when the welding index is welding quality, the quantified value (welding index value) of the welding quality of a certain sub-welding data is 3, and its corresponding real-time current is 3A, the real-time voltage is 10V, and the real-time welding speed is 1m / s. The generated welding knowledge may include (3A, 3), (10V, 3), and (1m / s, 3).

[0040] After establishing the welding database, the processor can determine whether the welding knowledge included in the welding knowledge base meets a preset condition. For example, this can be determined by determining whether the ratio of the number of welding knowledge items in each type meets a preset ratio. If the welding knowledge included in the welding knowledge base does not meet the preset condition, the processor can redefine multiple parameter groups. In other words, the factor value of each welding factor in the preset parameter group can be adjusted. The processor can then update the welding knowledge base based on the redefined multiple parameter groups until the welding knowledge included in the updated welding knowledge base meets the preset condition.

[0041] Through the above technical solution, a welding knowledge base can be quickly constructed, the welding knowledge in the welding knowledge base can be analyzed, and the overall distribution of welding knowledge in the welding knowledge base can be adjusted by re-determining the parameter group, thereby greatly improving the quality and reliability of the welding knowledge base. At the same time, it also provides a good data acquisition environment for the subsequent use of welding knowledge training models.

[0042] In one implementation, a uniform design principle can be employed to obtain multiple preset parameter groups, each of which includes multiple welding factors and their corresponding factor values. The uniform design principle requires that the test points are uniformly distributed within the test area according to a certain pattern, and each test point is representative. Specifically, a test range for each welding factor can be preset in advance, and a preset number of factor values ​​can be selected within the test range to construct a preset parameter group. For example, if the welding voltage range is 1V to 10V, two welding voltage values ​​can be selected from 1V to 5V, and two welding voltage values ​​can be selected from 5V to 10V. If the welding current range is 1A to 10A, two welding current values ​​can be selected from 1A to 5A, and two welding current values ​​can be selected from 5A to 10A. Subsequently, any one of the four selected welding voltage values ​​and any one of the four welding current values ​​can be combined to construct multiple preset parameter groups containing two welding factors and their corresponding factor values.

[0043] In one embodiment, for each welding data, the welding data is cut to obtain multiple sub-welding data, including: for each welding data, obtaining the welding segment data between the start time and the end time of the welding; and cutting the welding segment data according to the preset welding length to obtain sub-welding data corresponding to each preset welding length.

[0044] For each weld data set, the processor can retrieve weld segment data between the weld start and end times. Specifically, the processor can determine the weld start and end times based on a welding current threshold. After acquiring the weld segment data, the processor can also arrange each weld segment data set based on its position tag to associate the real-time factor values ​​of each welding factor corresponding to the same welding position. The processor can then segment the weld segment data based on preset weld lengths to obtain sub-weld data corresponding to each preset weld length. The sub-weld data can include the real-time factor values ​​corresponding to each welding factor.

[0045] The preset welding length can be 1 mm. For example, for welding segment data M, the welding length of welding segment data M can be 10 mm. After the welding segment data M is divided into 1 mm welding length segments, 10 sub-welding data can be obtained. If each 1 mm welding data segment includes welding factor values ​​corresponding to multiple time points, the average of the factor values ​​corresponding to all time points can be determined as the real-time factor value corresponding to the welding factor.

[0046] In one embodiment, each indicator type of the welding indicator includes multiple levels, each level corresponds to a different indicator score, and determining the welding indicator value of each sub-welding data includes: obtaining all indicator types corresponding to the welding indicators of each sub-welding data; determining the total indicator score corresponding to all indicator types based on the indicator score corresponding to each indicator type; and determining the welding indicator value of each sub-welding data based on the total indicator score and the number of all indicator types.

[0047] The welding indicator may include multiple welding categories. Each welding category may include multiple levels. Each level may correspond to a different indicator score. After obtaining multiple sub-welding data, the processor may obtain all indicator categories corresponding to the welding indicator of each sub-welding data. The processor may then determine the total indicator score corresponding to all indicator categories based on the indicator score corresponding to each indicator category. The processor may determine the welding indicator value for each sub-welding data based on the total indicator score and the number of all indicator categories.

[0048] Taking welding quality as an example, the types of welding indicators can include cracks, pores, and reinforcement. For the indicator type of crack, the corresponding levels can be long cracks, short cracks, and no cracks, with the corresponding indicator score for long cracks being 1, the corresponding indicator score for short cracks being 0.3, and the corresponding indicator score for no cracks being 0. For the indicator type of porosity, the corresponding levels can be large pores, medium pores, small pores, and no pores, with the corresponding indicator score for large pores being 0, the corresponding indicator score for medium pores being 0.15, the corresponding indicator score for small pores being 0.4, and the corresponding indicator score for no pores being 1. For the indicator type of reinforcement, the corresponding levels can be large reinforcement, small reinforcement, and no reinforcement, with the corresponding indicator score for large reinforcement being 0, the corresponding indicator score for small reinforcement being 0.3, and the corresponding indicator score for no reinforcement being 1.

[0049] Specifically, the welding index value of each sub-welding data can be determined according to F=(f1+f2+f3) / 3. Among them, F refers to the welding index value of each sub-welding data, f1 can refer to the index score corresponding to the index type of the welding index of crack, f2 can refer to the index score corresponding to the index type of the welding index of porosity, and f3 can refer to the index score corresponding to the index type of the welding index of reinforcement. If f1 is 0.3, f2 is 0.15, and f3 is 0.3, then the total index score corresponding to all index types f1+f2+f3 is 0.75. When the total index score corresponding to all index types and all index types are determined, the processor can determine that the welding index value F of each sub-welding data is 0.25.

[0050] In one embodiment, the method further includes: after establishing a welding knowledge base, determining the total amount of welding knowledge included in the welding knowledge base; if the total amount is less than a preset value, redetermining multiple parameter groups; updating the welding knowledge base based on the redetermined multiple parameter groups until the total amount of welding knowledge included in the updated welding knowledge base is greater than or equal to the preset value.

[0051] After establishing a welding knowledge base, the processor may determine the total amount of welding knowledge included in the welding knowledge base and compare the total amount with a preset value. If the total amount of welding knowledge included in the welding knowledge base is less than the preset value, the processor may redefine multiple parameter groups and update the welding knowledge base based on the redefined parameter groups until the total amount of welding knowledge included in the updated welding knowledge base is greater than or equal to the preset value. The preset value can be customized based on actual conditions. Specifically, after redefining the multiple parameter groups, the processor may weld a weldment based on the redefined parameter groups to determine welding data corresponding to each redefined parameter group, and then divide each welding data into multiple sub-welding data. The processor may then determine a welding index value for each sub-welding data, thereby generating welding knowledge corresponding to each sub-welding data, and expand the welding knowledge base based on the welding knowledge. After expanding the welding knowledge base, the processor may continue to determine whether the total amount of welding knowledge included in the expanded welding knowledge base is greater than or equal to the preset value. If the total amount of welding knowledge is greater than or equal to the preset value, the processor may further balance the amount of each type of welding knowledge in the welding knowledge base.

[0052] In one embodiment, the method further includes: when the total amount of welding knowledge included in the welding knowledge base is greater than or equal to a preset value, classifying the welding knowledge included in the welding knowledge base according to the type of welding indicator; determining a first amount of welding knowledge of a first type and a second amount of welding knowledge of a second type in the welding knowledge base; determining a quantity ratio between the first amount and the second amount; when the quantity ratio does not reach a preset ratio, determining that the welding knowledge included in the welding knowledge base does not meet a preset condition; when the quantity ratio reaches a preset ratio, determining that the welding knowledge included in the welding knowledge base meets the preset condition.

[0053] After establishing the welding knowledge base, the processor may determine the total amount of welding knowledge included in the welding knowledge base and compare the total amount with a preset value. If the total amount of welding knowledge included in the welding knowledge base is greater than or equal to the preset value, the processor may classify the welding knowledge included in the welding knowledge base according to the type of welding indicator. For example, the type of welding indicator can be determined based on the welding indicator value of the sub-welding data in the welding knowledge base. The types of welding indicators can include multiple types. For example, a first type of welding indicator and a second type of welding indicator can be included.

[0054] If the welding indicator is welding quality, the welding knowledge corresponding to the sub-welding data with a welding indicator value of 0.8 or above can be determined as the first type of welding knowledge, and the welding knowledge corresponding to the sub-welding data with a welding indicator value of less than 0.8 can be determined as the second type of welding knowledge. Since the first type of welding knowledge includes welding indicator values ​​of 0.8 or above, indicating good welding quality, the first type of welding knowledge can be used as a positive sample in the welding knowledge base. However, since the second type of welding knowledge includes welding indicator values ​​of 0.8 or below, indicating poor welding quality, the second type of welding knowledge can be used as a negative sample in the welding knowledge base.

[0055] After classifying the welding knowledge in the welding knowledge base, the processor may determine a first quantity of welding knowledge of a first type and a second quantity of welding knowledge of a second type in the welding knowledge base. The processor may further determine a quantitative ratio between the first quantity of welding knowledge of the first type and the second quantity of welding knowledge of the second type. The processor may then compare the quantitative ratio with a preset ratio to determine whether the proportion of each type of welding knowledge in the welding knowledge base is balanced. If the quantitative ratio does not reach the preset ratio, the processor may determine that the welding knowledge included in the welding knowledge base does not meet the preset conditions. If the welding knowledge included in the welding knowledge base does not meet the preset conditions, the processor may re-determine multiple parameter groups. That is, the factor value of each welding factor in the preset parameter group may be adjusted. If the quantitative ratio reaches the preset ratio, the processor may determine that the welding knowledge included in the welding knowledge base meets the preset conditions.

[0056] In one implementation, the method further includes: after establishing a welding knowledge base, determining the sub-welding data corresponding to each type of welding indicator; for each type of welding indicator, obtaining the real-time factor value of each welding factor in the sub-welding data corresponding to the welding indicator; for each type of welding indicator, determining the value range of each welding factor corresponding to the welding indicator based on the real-time factor value of each welding factor.

[0057] After establishing a welding knowledge base, the processor may determine the sub-welding data corresponding to each type of welding indicator. Specifically, after establishing the welding knowledge base, the processor may compare the total amount of welding knowledge included in the welding knowledge base with a preset value. If the total amount of welding knowledge included in the welding knowledge base is greater than or equal to the preset value, the processor may classify the welding knowledge included in the welding knowledge base according to the type of welding indicator. The type of welding indicator can be determined based on the welding indicator value of the sub-welding data in the welding knowledge base. The type of welding indicator can include multiple types. For example, the type of welding indicator can include a first type of welding indicator and a second type of welding indicator. That is, the welding knowledge in the welding knowledge base can be divided into a first type of welding knowledge and a second type of welding knowledge according to the type of welding indicator.

[0058] After classifying the welding knowledge included in the welding knowledge base, the processor can determine the sub-welding data included in the welding knowledge for each type of welding indicator. Each sub-welding data may include real-time factor values ​​for multiple welding factors. Specifically, for each type of welding indicator, the processor can obtain the real-time factor value for each welding factor in the sub-welding data corresponding to that type of welding indicator. The processor can then further determine the value range of each welding factor corresponding to the welding indicator based on the real-time factor value of each welding factor.

[0059] Taking welding quality as an example, welding factors can be welding current, welding voltage, and welding speed. For sub-welding data A1, A2, and A3 with welding index values ​​of 0.8 or greater in the welding knowledge base, the real-time welding current, real-time welding voltage, and real-time welding speed in sub-welding data A1 are 10 mA, 18 V, and 1 m / s, respectively. The real-time welding current, real-time welding voltage, and real-time welding speed in sub-welding data A2 are 10.5 mA, 19 V, and 1.2 m / s, respectively. The real-time welding current, real-time welding voltage, and real-time welding speed in sub-welding data A3 are 11 mA, 20 V, and 1.5 m / s, respectively. That is, the welding knowledge base includes sub-welding data A1, A2 and A3, and the welding index values ​​of the three sub-welding data are all above 0.8 (the welding quality is good). The processor can determine that the welding current corresponding to this type of welding index has a value range of 10mA~11mA, a welding voltage has a value range of 18V~20V, and a welding speed has a value range of 1m / s~1.5m / s.

[0060] For the sub welding data A4, A5, A6, A7 and A8 in the welding knowledge base, the welding index value is below 0.8. The real-time welding current, real-time welding voltage and real-time welding speed in the sub welding data A4 are 15 mA, 10 V and 2 m / s respectively. The real-time welding current, real-time welding voltage and real-time welding speed in the sub welding data A5 are 16 mA, 12 V and 1.9 m / s respectively. The real-time welding current, real-time welding voltage and real-time welding speed in the sub welding data A6 are 15.5 mA, 11 V and 2 m / s respectively. The real-time welding current, real-time welding voltage and real-time welding speed in the sub welding data A7 are 16 mA, 11 V and 2.1 m / s respectively. The real-time welding current, real-time welding voltage and real-time welding speed in the sub welding data A8 are 15.5 mA, 10 V and 2 m / s respectively. That is, the welding knowledge base includes the sub welding data A4, A5, A6, A7 and A8, and the welding index value of the five sub welding data is below 0.8 (welding quality is poor). The processor can determine that the value range of the welding current corresponding to the welding index is 15 mA-16 mA, the value range of the welding voltage is 10 V-12 V, and the value range of the welding speed is 1.9 m / s-2.1 m / s.

[0061] In one embodiment, in the case that the welding knowledge included in the welding knowledge base does not reach the preset condition, the plurality of parameter groups are re-determined by: determining the number of welding knowledge corresponding to each type of welding index in the welding knowledge base; and in the case that the number of welding knowledge corresponding to any one type of welding index does not reach the preset number condition, re-determining the plurality of parameter groups according to the value range of each welding factor in the sub welding data corresponding to the welding index.

[0062] The processor can determine the amount of welding knowledge corresponding to each type of welding indicator in the welding knowledge base. For any type of welding indicator, if it is determined that the amount of welding knowledge corresponding to that type of welding indicator does not meet a preset number requirement, the processor can redefine multiple parameter groups based on the value range of each welding factor in the sub-welding data corresponding to that type of welding indicator. For example, the amount of welding knowledge corresponding to a first type of welding indicator and the amount of welding knowledge corresponding to a second type of welding indicator in the welding knowledge base are unbalanced. If the amount of welding knowledge corresponding to the first type of welding indicator is less than the amount of welding knowledge corresponding to the second type of welding indicator, it can be determined that the amount of welding knowledge corresponding to the first type of welding indicator does not meet the preset number requirement. In this case, the processor can redefine the value range of each welding factor in the sub-welding data corresponding to the first type of welding indicator into multiple parameter groups. If the amount of welding knowledge corresponding to the first type of welding indicator is greater than the amount of welding knowledge corresponding to the second type of welding indicator, it can be determined that the amount of welding knowledge corresponding to the second type of welding indicator does not meet the preset number requirement. In this case, the processor can redefine the value range of each welding factor in the sub-welding data corresponding to the second type of welding indicator into multiple parameter groups.

[0063] Taking welding quality as an example, if the welding indicator is three pieces of welding knowledge with good welding quality, and their corresponding sub-welding data are A1, A2, and A3, respectively. If the welding knowledge with poor welding quality is five pieces, and their corresponding sub-welding data are A4, A5, A6, A7, and A8, respectively, the ratio of the number of welding knowledge pieces with good welding quality to the number of welding knowledge pieces with poor welding quality is 3:5, which does not meet the preset ratio. In this case, the processor can determine that the welding knowledge in the welding knowledge base does not meet the preset conditions and can redefine multiple parameter groups.

[0064] Because the number of each type of welding knowledge in the welding knowledge base is uneven, and the number of welding knowledge with good welding quality is relatively small, that is, the number of welding knowledge with good welding quality does not meet the preset quantity requirement, the processor can redefine multiple parameter groups based on the value ranges of welding current, welding voltage, and welding speed in the sub-welding data included in the welding knowledge with good welding quality. If the corresponding welding current value range is 10mA to 11mA, the welding voltage value range is 18V to 20V, and the welding speed value range is 1m / s to 1.5m / s, the processor can adjust the welding current in the preset parameter group to any current between 10mA and 11mA, the welding voltage in the parameter group to any voltage between 18V and 20V, and the welding speed in the parameter group to any speed between 1m / s and 1.5m / s, thereby redefining multiple parameter groups.

[0065] In one implementation, for each type of welding index, determining the value range of each welding factor in the sub-welding data corresponding to the welding index according to the real-time factor value of each welding factor includes: combining the real-time factor values of the welding factors in any number of sub-welding data to generate a plurality of to-be-predicted sub-welding data; sequentially inputting the to-be-predicted sub-welding data into the trained classification model to output, by the trained classification model, a predicted welding index value for the to-be-predicted sub-welding data, wherein the trained classification model is obtained by training the sub-welding data in the welding knowledge base; determining the type of the welding index corresponding to each to-be-predicted sub-welding data according to the predicted welding index value; and for each type of welding index, determining the value range of each welding factor corresponding to the welding index according to the factor values of each welding factor in the to-be-predicted sub-welding data and the sub-welding data in the welding knowledge base.

[0066] The processor can obtain the real-time factor value of each welding factor included in the sub-welding data in the welding knowledge base, and can input the real-time factor value of each welding factor into the classification model to train the classification model and obtain the trained classification model. That is, the trained classification model is obtained by training the sub-welding data in the welding knowledge base. The classification model can be an SVM or a tree model. In the case of obtaining the trained classification model, the processor can combine the real-time factor values of the welding factors in any number of sub-welding data to generate a plurality of to-be-predicted sub-welding data. For example, the real-time welding current and the real-time welding voltage in the sub-welding data C1 are 10 mA and 18 V, respectively. The real-time welding current and the real-time welding voltage in the sub-welding data C2 are 10.5 mA and 19 V, respectively. After combining the real-time factor values of the welding factors in the sub-welding data C1 and the sub-welding data C2, the to-be-predicted sub-welding data D1 and D2 are obtained. The real-time welding current and the real-time welding voltage in the to-be-predicted sub-welding data D1 can be 10 mA and 19 V, respectively. The real-time welding current and the real-time welding voltage in the to-be-predicted sub-welding data D2 can be 10.5 mA and 18 V, respectively.

[0067] The processor can further input the to-be-predicted sub-welding data into the trained classification model to output, by the trained classification model, a predicted welding index value for the to-be-predicted sub-welding data. The processor can determine the type of the welding index corresponding to each to-be-predicted sub-welding data according to the predicted welding index value. For example, the type of the welding index can include a first type and a second type. Specifically, the processor can determine the type of the welding index of the to-be-predicted sub-welding data whose predicted welding index value is above 0.8 as the first type. The processor can determine the type of the welding index of the to-be-predicted sub-welding data whose predicted welding index value is below 0.8 as the second type.

[0068] For each type of welding indicator, the processor can determine the value range of each welding factor corresponding to the welding indicator based on the real-time factor value of each welding factor in the sub-welding data to be predicted and the sub-welding data in the welding knowledge base. For example, if the indicator type of sub-welding data C1, sub-welding data C2, sub-welding data to be predicted D1, and sub-welding data to be predicted D2 are all of the first type, then the value range of the welding current corresponding to this welding indicator is 10mA to 10.5mA, and the value range of the welding voltage corresponding to this welding indicator is 18V to 19V. By traversing all combinations of real-time factor values ​​in any number of sub-welding data through the trained classification model, the amount of welding knowledge in the welding knowledge base can be expanded, and the value range of each welding factor corresponding to each type of welding indicator can be more accurately determined. This facilitates the welding knowledge base to meet the preset conditions and improves the efficiency of constructing a welding knowledge base that meets the preset conditions.

[0069] Through the above technical solution, a welding knowledge base can be quickly constructed, the efficiency of constructing the welding knowledge base can be improved, the welding knowledge in the welding knowledge base can be analyzed, and the overall distribution of welding knowledge in the welding knowledge base can be adjusted by re-determining the parameter group, thereby greatly improving the quality and reliability of the welding knowledge base. At the same time, it also provides a good data acquisition environment for the subsequent use of welding knowledge training models.

[0070] Figure 1 FIG. 1 is a flow chart of a data processing method for a welding knowledge base in one embodiment. Figure 1 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. In addition, Figure 1 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed 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 part of the sub-steps or stages of other steps.

[0071] In one embodiment, a storage medium is provided, on which a program is stored. When the program is executed by a processor, the data processing method for the welding knowledge base is implemented.

[0072] In one embodiment, a processor is provided, which is used to run a program, wherein the program executes the above-mentioned data processing method for a welding knowledge base when it is run.

[0073] In one embodiment, a data processing apparatus for a welding knowledge base is provided, comprising the processor described above.

[0074] In one embodiment, a computer device can be provided, which can be a server, and an internal structure diagram of the computer device can be as shown in Figure 2 The computer device comprises a processor A01, a network interface A02, a memory (not shown in the figure) and a database (not shown in the figure) connected through a system bus. Among them, the processor A01 of the computer device is used to provide computing and control capabilities. The memory of the computer device comprises an 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 in the figure). The internal memory A03 provides an environment for the operation of the operating system B01 and the computer program B02 in the non-volatile storage medium A04. The database of the computer device is used to store data such as parameter groups. The network interface A02 of the computer device is used to communicate with external terminals through network connection. The computer program B02 is executed by the processor A01 to implement a data processing method for a welding knowledge base.

[0075] Those skilled in the art can understand that Figure 2 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can comprise more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0076] The embodiments of the present application provide a device, which comprises a processor, a memory and a program stored in the memory and executable on the processor. When the processor executes the program, the following steps are implemented: a plurality of preset parameter groups are acquired, each parameter group comprising a plurality of welding factors and a factor value of each welding factor; each parameter group is used to weld a to-be-welded piece to determine welding data corresponding to each parameter group; each welding data is cut to obtain a plurality of sub-welding data; a welding index value of each sub-welding data is determined; welding knowledge corresponding to each sub-welding data is generated according to each sub-welding data and the welding index value corresponding to each sub-welding data to establish a welding knowledge base; in a case where the welding knowledge included in the welding knowledge base does not reach a preset condition, the plurality of parameter groups are re-determined; the welding knowledge base is updated according to the re-determined plurality of parameter groups until the welding knowledge included in the updated welding knowledge base reaches the preset condition.

[0077] In one embodiment, the method further includes: after establishing the welding knowledge base, determining the total amount of welding knowledge included in the welding knowledge base; if the total amount is less than a preset value, redetermining multiple parameter groups; updating the welding knowledge base according to the redetermined multiple parameter groups until the total amount of welding knowledge included in the updated welding knowledge base is greater than or equal to the preset value.

[0078] In one embodiment, the method also includes: when the total amount of welding knowledge included in the welding knowledge base is greater than or equal to a preset value, classifying the welding knowledge included in the welding knowledge base according to the type of welding indicator; determining a first amount of welding knowledge of the first type and a second amount of welding knowledge of the second type in the welding knowledge base; determining a quantity ratio between the first amount and the second amount; when the quantity ratio does not reach a preset ratio, determining that the welding knowledge included in the welding knowledge base does not meet a preset condition; when the quantity ratio reaches a preset ratio, determining that the welding knowledge included in the welding knowledge base meets the preset condition.

[0079] In one embodiment, the method further includes: after establishing a welding knowledge base, determining the sub-welding data corresponding to each type of welding indicator; for each type of welding indicator, obtaining the real-time factor value of each welding factor in the sub-welding data corresponding to the welding indicator; for each type of welding indicator, determining the value range of each welding factor corresponding to the welding indicator based on the real-time factor value of each welding factor.

[0080] In one embodiment, when the welding knowledge included in the welding knowledge base does not meet the preset conditions, redetermining multiple parameter groups includes: determining the amount of welding knowledge corresponding to each type of welding indicator in the welding knowledge base; for any type of welding indicator, when it is determined that the amount of welding knowledge corresponding to the welding indicator does not meet the preset quantity conditions, redetermining multiple parameter groups according to the value range of each welding factor in the sub-welding data corresponding to the welding indicator.

[0081] In an embodiment, for each type of welding index, determining the value range of each welding factor in the sub-welding data corresponding to the welding index according to the real-time factor value of each welding factor comprises: combining the real-time factor values of the welding factors in any number of sub-welding data to generate a plurality of to-be-predicted sub-welding data; sequentially inputting the to-be-predicted sub-welding data into the trained classification model to output a predicted welding index value for the to-be-predicted sub-welding data by the trained classification model, wherein the trained classification model is trained by the sub-welding data in the welding knowledge base; determining the type of the welding index corresponding to each to-be-predicted sub-welding data according to the predicted welding index value; and for each type of welding index, determining the value range of each welding factor corresponding to the welding index according to the factor values of each welding factor in the to-be-predicted sub-welding data and the sub-welding data in the welding knowledge base.

[0082] In an embodiment, the cutting of the welding data to obtain a plurality of sub-welding data comprises: for each welding data, acquiring welding segment data between the start time and the end time of the welding; and cutting the welding segment data according to a preset welding length to obtain sub-welding data corresponding to each preset welding length.

[0083] In an embodiment, each index category of the welding index comprises a plurality of levels, each level corresponds to a different index score, and determining the welding index value of each sub-welding data comprises: acquiring all index categories corresponding to the welding index of each sub-welding data; determining an index total score corresponding to all index categories according to the index score corresponding to each index category; and determining the welding index value of each sub-welding data according to the index total score and the number of all index categories.

[0084] The application also provides a computer program product adapted to execute the program of the following method steps when executed on a data processing device: acquiring a plurality of preset parameter groups, each parameter group comprising a plurality of welding factors and factor values of each welding factor; welding the to-be-welded piece according to each parameter group respectively to determine welding data corresponding to each parameter group; cutting the welding data to obtain a plurality of sub-welding data for each welding data; determining the welding index value of each sub-welding data; generating welding knowledge corresponding to each sub-welding data according to each sub-welding data and the welding index value corresponding to each sub-welding data to establish a welding knowledge base; in the case that the welding knowledge included in the welding knowledge base does not reach a preset condition, redetermining a plurality of parameter groups; updating the welding knowledge base according to the redetermined plurality of parameter groups until the welding knowledge included in the updated welding knowledge base reaches the preset condition.

[0085] In one embodiment, the method further includes: after establishing the welding knowledge base, determining the total amount of welding knowledge included in the welding knowledge base; if the total amount is less than a preset value, redetermining multiple parameter groups; updating the welding knowledge base according to the redetermined multiple parameter groups until the total amount of welding knowledge included in the updated welding knowledge base is greater than or equal to the preset value.

[0086] In one embodiment, the method also includes: when the total amount of welding knowledge included in the welding knowledge base is greater than or equal to a preset value, classifying the welding knowledge included in the welding knowledge base according to the type of welding indicator; determining a first amount of welding knowledge of the first type and a second amount of welding knowledge of the second type in the welding knowledge base; determining a quantity ratio between the first amount and the second amount; when the quantity ratio does not reach a preset ratio, determining that the welding knowledge included in the welding knowledge base does not meet a preset condition; when the quantity ratio reaches a preset ratio, determining that the welding knowledge included in the welding knowledge base meets the preset condition.

[0087] In one embodiment, the method further includes: after establishing a welding knowledge base, determining the sub-welding data corresponding to each type of welding indicator; for each type of welding indicator, obtaining the real-time factor value of each welding factor in the sub-welding data corresponding to the welding indicator; for each type of welding indicator, determining the value range of each welding factor corresponding to the welding indicator based on the real-time factor value of each welding factor.

[0088] In one embodiment, when the welding knowledge included in the welding knowledge base does not meet the preset conditions, redetermining multiple parameter groups includes: determining the amount of welding knowledge corresponding to each type of welding indicator in the welding knowledge base; for any type of welding indicator, when it is determined that the amount of welding knowledge corresponding to the welding indicator does not meet the preset quantity conditions, redetermining multiple parameter groups according to the value range of each welding factor in the sub-welding data corresponding to the welding indicator.

[0089] In one embodiment, for each type of welding indicator, determining the value range of each welding factor in the sub-welding data corresponding to the welding indicator based on the real-time factor value of each welding factor includes: combining the real-time factor values ​​of the welding factors in any number of sub-welding data to generate a plurality of sub-welding data to be predicted; sequentially inputting the sub-welding data to be predicted into the trained classification model to output the predicted welding indicator value for the sub-welding data to be predicted through the trained classification model, wherein the trained classification model is obtained by training the sub-welding data in the welding knowledge base; determining the type of welding indicator corresponding to each sub-welding data to be predicted based on the predicted welding indicator value; for each type of welding indicator, determining the value range of each welding factor corresponding to the welding indicator based on the factor value of each welding factor in the sub-welding data to be predicted and the sub-welding data in the welding knowledge base.

[0090] In one embodiment, for each welding data, the welding data is cut to obtain multiple sub-welding data, including: for each welding data, obtaining the welding segment data between the start time and the end time of the welding; and cutting the welding segment data according to the preset welding length to obtain sub-welding data corresponding to each preset welding length.

[0091] In one embodiment, each indicator type of the welding indicator includes multiple levels, each level corresponds to a different indicator score, and determining the welding indicator value of each sub-welding data includes: obtaining all indicator types corresponding to the welding indicators of each sub-welding data; determining the total indicator score corresponding to all indicator types according to the indicator score corresponding to each indicator type; and determining the welding indicator value of each sub-welding data according to the total indicator score and the number of all indicator types.

[0092] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0093] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0094] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0095] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0096] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0097] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0098] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules 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 technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0099] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0100] The above are merely embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. A data processing method for a welding knowledge base, characterized in that: The method comprises: Acquire multiple preset parameter groups, each parameter group including multiple welding factors and a factor value of each welding factor; Welding the workpieces to be welded according to each parameter group respectively to determine welding data corresponding to each parameter group; For each welding data, cutting the welding data to obtain a plurality of sub-welding data; Determine the welding index value of each sub-welding data; Generating welding knowledge corresponding to each sub-welding data according to each sub-welding data and a welding index value corresponding to each sub-welding data to establish a welding knowledge base; re-determining a plurality of parameter groups when the welding knowledge included in the welding knowledge base does not meet a preset condition; updating the welding knowledge base according to the re-determined plurality of parameter groups until the welding knowledge included in the updated welding knowledge base meets the preset condition; The step of cutting each welding data to obtain a plurality of sub-welding data includes: For each welding data, obtaining welding segment data between the start time and the end time of the welding; Cutting the welding segment data according to the preset welding length to obtain sub-welding data corresponding to each preset welding length; The preset condition at least includes: the total amount of the welding knowledge is greater than or equal to a preset value.

2. The data processing method for welding knowledge base according to claim 1, characterized in that: The method further comprises: After establishing a welding knowledge base, determining a total amount of welding knowledge included in the welding knowledge base; If the total number is less than a preset value, re-determine the plurality of parameter groups; The welding knowledge base is updated according to the re-determined plurality of parameter groups until the total amount of welding knowledge included in the updated welding knowledge base is greater than or equal to the preset value.

3. The data processing method for welding knowledge base according to claim 2, characterized in that: The method further comprises: When the total amount of welding knowledge included in the welding knowledge base is greater than or equal to the preset value, classifying the welding knowledge included in the welding knowledge base according to the type of welding index; Determining a first quantity of welding knowledge of the first type and a second quantity of welding knowledge of the second type in the welding knowledge base; determining a quantity ratio between the first quantity and the second quantity; When the quantity ratio does not reach the preset ratio, determining that the welding knowledge included in the welding knowledge base does not meet the preset condition; When the quantity ratio reaches the preset ratio, it is determined that the welding knowledge included in the welding knowledge base meets the preset condition.

4. The data processing method for a welding knowledge base according to claim 1, characterized in that: The method further comprises: After establishing the welding knowledge base, determine the sub-welding data corresponding to each type of welding index; For each type of welding index, obtaining a real-time factor value of each welding factor in the sub-welding data corresponding to the welding index; For each type of welding index, a value range of each welding factor corresponding to the welding index is determined according to the real-time factor value of each welding factor.

5. The data processing method for welding knowledge base according to claim 4, characterized in that: When the welding knowledge included in the welding knowledge base does not meet the preset conditions, re-determining the plurality of parameter groups includes: Determining the amount of welding knowledge corresponding to each type of welding indicator in the welding knowledge base; For any type of welding indicator, when it is determined that the amount of welding knowledge corresponding to the welding indicator does not meet the preset quantity condition, multiple parameter groups are re-determined according to the value range of each welding factor in the sub-welding data corresponding to the welding indicator.

6. The data processing method for welding knowledge base according to claim 4, characterized in that: For each type of welding index, determining the value range of each welding factor in the sub-welding data corresponding to the welding index according to the real-time factor value of each welding factor includes: Combining the real-time factor values ​​of the welding factors in any number of sub-welding data to generate a plurality of sub-welding data to be predicted; sequentially inputting the sub-welding data to be predicted into a trained classification model, so as to output a predicted welding index value for the sub-welding data to be predicted through the trained classification model, wherein the trained classification model is obtained by training the sub-welding data in the welding knowledge base; Determine the type of welding index corresponding to each sub-welding data to be predicted according to the predicted welding index value; For each type of welding index, a value range of each welding factor corresponding to the welding index is determined according to the factor value of each welding factor in the sub-welding data to be predicted and the sub-welding data in the welding knowledge base.

7. The data processing method for welding knowledge base according to claim 1, characterized in that: Each indicator type of welding indicators includes multiple levels, each level corresponds to a different indicator score, and determining the welding indicator value of each sub-welding data includes: Obtain all index types corresponding to the welding index of each sub-welding data; Determine the total score of all indicator types according to the score of each indicator type; The welding index value of each sub-welding data is determined according to the total index score and the number of all index types.

8. A machine-readable storage medium having instructions stored thereon, characterized in that: When the instruction is executed by a processor, the processor is configured to execute the data processing method for a welding knowledge base according to any one of claims 1 to 7.

9. A processor, characterized in that: The method is configured to execute the data processing method for a welding knowledge base according to any one of claims 1 to 7.

10. A data processing device for a welding knowledge base, characterized in that: The apparatus comprises a processor according to claim 9.

Images