Intelligent welding control method for a pipe

Abstract

The application discloses an intelligent welding control method for pipe fittings, and relates to the technical field of data automatic control, which comprises the following steps: establishing a pipe fitting feature database and a welding action database, mapping each pipe fitting feature element in the pipe fitting feature database with feasible welding modes, welding parameters and welding codes according to the pipe fitting feature database and the welding action database, and combining the pipe fitting feature element with the welding modes, the welding parameters and the welding codes to form a pipe fitting welding mapping correlation matrix; analyzing the pipe fitting feature matching degree of the pipe fitting to be welded and the pipe fitting in the pipe fitting welding mapping correlation matrix, determining several welding modes and welding parameters corresponding to the pipe fitting to be welded, and generating a preselected welding scheme; and based on the preselected welding scheme, determining a final welding scheme according to the preferred direction of the pipe fitting to be welded, and intelligently controlling a welding mechanical arm. The method has the advantages that the welding quality and the welding efficiency are improved, the manual intervention is reduced, and the stability of the welded pipe fitting is ensured.

Description

Technical Field

[0001] This invention relates to the field of automation control technology, specifically to an intelligent welding control method for pipe fittings. Background Technology

[0002] Pipe welding refers to the process of connecting pipes (such as steel pipes, stainless steel pipes, aluminum pipes, etc.) using welding technology. It is a common manufacturing method in industries such as manufacturing, construction, and automotive, used to construct piping systems, structural frames, and fluid transport systems. Various welding techniques can be used, including arc welding, gas shielded welding, and laser welding. The appropriate welding method and parameters are selected based on the pipe's material, diameter, wall thickness, welding location, and application scenario.

[0003] Although the welding methods are quite advanced, the welding quality may be affected by factors such as equipment condition and operator skills, leading to fluctuations in welding quality. Complex welding structures still require manual intervention, resulting in low welding efficiency. Furthermore, the stability of welded pipe fittings varies greatly due to the influence of human technical skills. Summary of the Invention

[0004] To address the aforementioned technical problems, an intelligent welding control method for pipe fittings is provided. This technical solution solves the problems that, although the welding method is quite advanced, the welding quality may be affected by factors such as equipment status and operator skills, leading to fluctuations in welding quality. Complex welding structures still require manual intervention, resulting in low welding efficiency. Furthermore, the stability of welded pipe fittings varies greatly due to the influence of human skill level.

[0005] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0006] A method for intelligent welding control of pipe fittings, comprising:

[0007] Collect characteristic information on several types of pipe fittings and establish a pipe fitting characteristic database;

[0008] A welding action database is established based on several welding methods, welding parameters, and welding codes.

[0009] Based on the pipe fitting feature database and the welding action database, each pipe fitting feature element in the pipe fitting feature database is mapped to the feasible welding method, welding parameters and welding code, and combined into a pipe fitting welding mapping association matrix;

[0010] Based on the data of the pipe fittings to be welded collected by the sensors on the welding robotic arm, the matching degree of pipe fitting features in the pipe fitting feature-to-weld mapping correlation matrix is ​​analyzed.

[0011] Based on the matching degree of pipe feature in the pipe feature and the pipe welding mapping correlation matrix, several welding methods and welding parameters corresponding to the pipe to be welded are determined, and a pre-selected welding scheme is generated.

[0012] Based on the pre-selected welding scheme, the final welding scheme is determined according to the preferred direction of the pipe to be welded, and the welding robotic arm is intelligently controlled.

[0013] Preferably, based on the pipe fitting feature database and the welding action database, each pipe fitting feature element in the pipe fitting feature database is mapped to feasible welding methods, welding parameters, and welding codes, forming a pipe fitting welding mapping association matrix. Specifically, this includes:

[0014] Based on each pipe fitting feature element in the pipe fitting feature database, each pipe fitting feature element is quantized to obtain the quantization parameters of the pipe fitting feature elements.

[0015] Based on the quantitative parameters of pipe fitting feature elements, and according to welding process knowledge and welding technology requirements, several welding methods, welding parameters and welding codes are associated and bound to the quantitative parameters of each pipe fitting feature element.

[0016] A welding mapping correlation matrix A is established based on several welding methods, welding parameters and welding codes corresponding to the quantization parameters of each pipe fitting feature element;

[0017]

[0018] in, For the pipe fitting welding mapping correlation matrix, For the first The first welded pipe fitting The first feature corresponds to the first The welding method of the first One welding parameter, Welding codes for welding methods associated with pipe fitting features. This represents the total number of pipe fitting features. is the total number of welding parameters, and k is the total number of welding codes.

[0019] Preferably, based on the data of the pipe fittings to be welded collected by sensors on the welding robotic arm, the analysis of the pipe fitting feature matching degree in the pipe fitting welding mapping correlation matrix specifically includes:

[0020] Based on the data of the pipe fittings to be welded collected by the sensors on the welding robotic arm, feature extraction is performed on the data of the pipe fittings to be welded, and the feature of each pipe fitting to be welded is quantified to obtain the quantified feature parameters of the pipe fittings to be welded.

[0021] Standardization is performed on each element in the correlation matrix between the quantified feature parameters of the pipe fitting to be welded and the welding mapping of the pipe fitting;

[0022] Based on the quantification of the characteristic parameters of the pipe fitting to be welded and the correlation matrix of the pipe fitting welding mapping, the similarity between the characteristic parameters of the pipe fitting to be welded and each characteristic parameter of the pipe fitting in the correlation matrix of the pipe fitting welding mapping is calculated by the similarity formula.

[0023] The similarity formula is as follows:

[0024]

[0025] In the formula, The similarity of the characteristic parameters of the pipe fittings. Let i be the characteristic parameter of the i-th pipe fitting to be welded. Let be the characteristic parameter of the i-th pipe fitting in the pipe fitting welding mapping correlation matrix.

[0026] Preferably, based on the pipe feature matching degree in the pipe-to-pipe welding mapping correlation matrix, several welding methods and welding parameters corresponding to the pipe to be welded are determined, and a pre-selected welding scheme is generated, specifically including:

[0027] Based on the similarity of each feature parameter of the pipe fitting in the correlation matrix between the pipe fitting to be welded and the pipe fitting welding, the pipe fitting features with a similarity of 1 are selected.

[0028] Based on several pipe fitting features with a similarity of 1, the features of the pipe fitting to be welded are used as secondary screening conditions to determine the welding method, welding parameters and welding code of the pipe fitting to be welded.

[0029] Based on several pipe fitting features after secondary screening, and the welding method, welding parameters and welding code of the pipe fitting to be welded, a pre-selected welding mapping correlation matrix B is formed. ,in After secondary screening, c represents the j-th welding parameter of the y-th welding method corresponding to the ith feature of the x-th welded pipe fitting to be welded, where c is the welding code.

[0030] Based on the pre-selected welding mapping association matrix, the pre-selected welding mapping association matrix is ​​packaged into a welding dataset;

[0031] Based on the welding dataset, a classification model is established, with the pipe fitting to be welded as the root node, each pipe fitting feature in the pre-selected welding matrix as an internal node, and several welding methods, welding parameters and welding codes associated with the pipe fitting features as leaf nodes. The pre-selected welding matrix is ​​classified to determine several pre-selected schemes.

[0032] The classification model expression is as follows:

[0033]

[0034] In the formula, For conditional entropy, For welding datasets, Let be the i-th pipe fitting feature in the welding dataset, and n be the total number of pipe fitting features.

[0035] Preferably, based on the pre-selected welding scheme, the final welding scheme is determined according to the preferred direction of the pipe to be welded, and the welding robotic arm is intelligently controlled, specifically including:

[0036] Based on several pre-selected welding schemes, a comprehensive analysis is conducted on factors such as welding quality, production efficiency, and welding cost in the welding schemes to determine the overall capability of several pre-selected welding schemes.

[0037] Based on the welding requirements and processes of the pipe fittings to be welded, the preferred direction of the pipe fittings to be welded is analyzed;

[0038] The comprehensive capabilities of several pre-selected welding schemes are characterized according to the preferred directions that can be satisfied. The preferred direction of the pipe to be welded is used as a condition requirement to establish an intelligent welding analysis model. The optimal welding scheme is selected to meet the preferred direction of the pipe to be welded. The welding method, welding parameters and welding code in the optimal welding scheme are applied to the welding robot arm to complete the intelligent welding control of the welding robot arm.

[0039] The expression for the intelligent welding analysis model is as follows:

[0040]

[0041] In the formula, S represents the optimal welding scheme. For better welding quality of the pipe fittings to be welded, The production efficiency preference direction for the pipe fittings to be welded For the welding cost preference direction of the pipe fittings to be welded, , , The weights are, in order: welding quality, production efficiency, and welding cost.

[0042] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0043] This invention proposes an intelligent welding control scheme for pipe fittings. By constructing a database of pipe fitting features and welding actions, data from the pipe fittings to be welded is collected using sensors, and matching degree analysis is performed to generate pre-selected welding schemes. Finally, the final welding scheme is determined based on the preferred direction of the pipe fittings, and the welding robotic arm is intelligently controlled to achieve intelligent welding control of the pipe fittings. The advantages of this scheme are: improved welding quality and efficiency, reduced manual intervention, and ensured stability of the welded pipe fittings. Attached Figure Description

[0044] Figure 1 A flowchart of an intelligent welding control method for pipe fittings;

[0045] Figure 2 Flowchart of the method for establishing the welding mapping correlation matrix for pipe fittings;

[0046] Figure 3 Flowchart for analyzing the feature matching degree of pipe fittings;

[0047] Figure 4 Flowchart for generating pre-selected welding schemes

[0048] Figure 5 Flowchart of a method for intelligent control of a welding robotic arm. Detailed Implementation

[0049] The following description is intended to disclose the invention and enable those skilled in the art to implement it. The preferred embodiments described below are merely examples, and other obvious variations will occur to those skilled in the art.

[0050] Reference Figure 1 As shown, an intelligent welding control method for pipe fittings includes:

[0051] A method for intelligent welding control of pipe fittings, comprising:

[0052] Collect characteristic information on several types of pipe fittings and establish a pipe fitting characteristic database;

[0053] A welding action database is established based on several welding methods, welding parameters, and welding codes.

[0054] Based on the pipe fitting feature database and the welding action database, each pipe fitting feature element in the pipe fitting feature database is mapped to the feasible welding method, welding parameters and welding code, and combined into a pipe fitting welding mapping association matrix;

[0055] Based on the data of the pipe fittings to be welded collected by the sensors on the welding robotic arm, the matching degree of pipe fitting features in the pipe fitting feature-to-weld mapping correlation matrix is ​​analyzed.

[0056] Based on the matching degree of pipe feature in the pipe feature and the pipe welding mapping correlation matrix, several welding methods and welding parameters corresponding to the pipe to be welded are determined, and a pre-selected welding scheme is generated.

[0057] Based on the pre-selected welding scheme, the final welding scheme is determined according to the preferred direction of the pipe to be welded, and the welding robotic arm is intelligently controlled.

[0058] This solution constructs a database of pipe fitting features and welding actions, uses sensors to collect data from the pipe fittings to be welded, performs matching degree analysis, and generates pre-selected welding schemes. Finally, based on the preferred direction of the pipe fittings to be welded, the final welding scheme is determined, and the welding robotic arm is intelligently controlled to achieve intelligent welding control of the pipe fittings.

[0059] It should be noted that the various pipe fitting characteristics mentioned in this solution include, but are not limited to: pipe fitting size characteristics, pipe fitting shape characteristics, and pipe fitting material characteristics; furthermore, the various welding methods include, but are not limited to: electric arc welding, gas shielded welding, and laser welding; secondly, the welding parameters refer to welding current, welding voltage, welding speed, welding wire diameter, and preheating temperature; and the welding code is the program code that controls the welding robot arm during welding operations for various welding methods and welding parameters corresponding to different pipe fitting characteristics.

[0060] Reference Figure 2 As shown, based on the pipe fitting feature database and the welding action database, each pipe fitting feature element in the feature database is mapped to feasible welding methods, welding parameters, and welding codes, forming a pipe fitting welding mapping association matrix. Specifically, this includes:

[0061] Based on each pipe fitting feature element in the pipe fitting feature database, each pipe fitting feature element is quantized to obtain the quantization parameters of the pipe fitting feature elements.

[0062] Based on the quantitative parameters of pipe fitting feature elements, and according to welding process knowledge and welding technology requirements, several welding methods, welding parameters and welding codes are associated and bound to the quantitative parameters of each pipe fitting feature element.

[0063] A welding mapping correlation matrix A is established based on several welding methods, welding parameters and welding codes corresponding to the quantization parameters of each pipe fitting feature element;

[0064]

[0065] in, For the pipe fitting welding mapping correlation matrix, For the first The first welded pipe fitting The first feature corresponds to the first The welding method of the first One welding parameter, Welding codes for welding methods associated with pipe fitting features. This represents the total number of pipe fitting features. is the total number of welding parameters, and k is the total number of welding codes.

[0066] It's important to note that this involves converting the characteristics of pipe fittings, such as size, material, and wall thickness, into quantifiable values. For example, size can be quantified as diameter or length, material as metal or plastic, and wall thickness as a specific number of millimeters. These quantified fitting parameters are then correlated with various welding methods, welding parameters, and welding codes. For instance, if the fitting is made of stainless steel, welding parameters might include using TIG welding and specific current and voltage settings. This correlation ensures that the welding system can select the appropriate welding method based on the characteristics of the fitting.

[0067] Reference Figure 3 As shown, based on the data of the pipe fittings to be welded collected by the sensors on the welding robotic arm, the analysis of the pipe fitting feature matching degree in the pipe fitting welding mapping correlation matrix specifically includes:

[0068] Based on the data of the pipe fittings to be welded collected by the sensors on the welding robotic arm, feature extraction is performed on the data of the pipe fittings to be welded, and the feature of each pipe fitting to be welded is quantified to obtain the quantified feature parameters of the pipe fittings to be welded.

[0069] Standardization is performed on each element in the correlation matrix between the quantified feature parameters of the pipe fitting to be welded and the welding mapping of the pipe fitting;

[0070] Based on the quantification of the characteristic parameters of the pipe fitting to be welded and the correlation matrix of the pipe fitting welding mapping, the similarity between the characteristic parameters of the pipe fitting to be welded and each characteristic parameter of the pipe fitting in the correlation matrix of the pipe fitting welding mapping is calculated by the similarity formula.

[0071] The similarity formula is as follows:

[0072]

[0073] In the formula, The similarity of the characteristic parameters of the pipe fittings. Let i be the characteristic parameter of the i-th pipe fitting to be welded. Let be the characteristic parameter of the i-th pipe fitting in the pipe fitting welding mapping correlation matrix.

[0074] Reference Figure 4 As shown, based on the pipe feature matching degree in the pipe-to-pipe welding mapping correlation matrix, several welding methods and welding parameters corresponding to the pipe to be welded are determined, and a pre-selected welding scheme is generated, specifically including:

[0075] Based on the similarity of each feature parameter of the pipe fitting in the correlation matrix between the pipe fitting to be welded and the pipe fitting welding, the pipe fitting features with a similarity of 1 are selected.

[0076] Based on several pipe fitting features with a similarity of 1, the features of the pipe fitting to be welded are used as secondary screening conditions to determine the welding method, welding parameters and welding code of the pipe fitting to be welded.

[0077] Based on several pipe fitting features after secondary screening, and the welding method, welding parameters and welding code of the pipe fitting to be welded, a pre-selected welding mapping correlation matrix B is formed. ,in After secondary screening, c represents the j-th welding parameter of the y-th welding method corresponding to the ith feature of the x-th welded pipe fitting to be welded, where c is the welding code.

[0078] Based on the pre-selected welding mapping association matrix, the pre-selected welding mapping association matrix is ​​packaged into a welding dataset;

[0079] Based on the welding dataset, a classification model is established, with the pipe fitting to be welded as the root node, each pipe fitting feature in the pre-selected welding matrix as an internal node, and several welding methods, welding parameters and welding codes associated with the pipe fitting features as leaf nodes. The pre-selected welding matrix is ​​classified to determine several pre-selected schemes.

[0080] The classification model expression is as follows:

[0081]

[0082] In the formula, For conditional entropy, For welding datasets, Let be the i-th pipe fitting feature in the welding dataset, and n be the total number of pipe fitting features.

[0083] It is understandable that the size, shape, and material characteristics of pipe fittings have a significant impact on the welding process, determining the choice of welding method and the adjustment of welding parameters. For example, pipe fitting size characteristics include: pipe diameter, which affects the selection of weld width and welding speed; pipe wall thickness, which determines the required welding current and voltage, as well as whether preheating or post-heat treatment is required; and pipe length, which affects the arrangement of welding layout and welding sequence.

[0084] Pipe shape characteristics: straight pipes, welded along a straight line; bent or irregularly shaped pipes, argon arc welding or laser welding; pipe joints, such as T-joints, Y-joints, etc.

[0085] Pipe fitting material characteristics: Carbon steel, usually welded by electric arc, carbon equivalent needs to be considered; Stainless steel, may need to be welded by argon arc or laser welding; Aluminum alloy, requires welding method suitable for aluminum alloy; Plastic pipe fittings, usually welded by hot melt or ultrasonic welding.

[0086] By employing a series of steps including feature selection, data packaging, model building, and classification, the selection of welding solutions is automated. This automated method can significantly improve the efficiency and quality of the welding process, reduce human error, and quickly determine feasible welding solutions based on different pipe fitting characteristics.

[0087] Reference Figure 5 As shown, based on the pre-selected welding scheme and according to the preferred direction of the pipe to be welded, the final welding scheme is determined, and the intelligent control of the welding robotic arm specifically includes:

[0088] Based on several pre-selected welding schemes, a comprehensive analysis is conducted on factors such as welding quality, production efficiency, and welding cost in the welding schemes to determine the overall capability of several pre-selected welding schemes.

[0089] Based on the welding requirements and processes of the pipe fittings to be welded, the preferred direction of the pipe fittings to be welded is analyzed;

[0090] The comprehensive capabilities of several pre-selected welding schemes are characterized according to the preferred directions that can be satisfied. The preferred direction of the pipe to be welded is used as a condition requirement to establish an intelligent welding analysis model. The optimal welding scheme is selected to meet the preferred direction of the pipe to be welded. The welding method, welding parameters and welding code in the optimal welding scheme are applied to the welding robot arm to complete the intelligent welding control of the welding robot arm.

[0091] The expression for the intelligent welding analysis model is as follows:

[0092]

[0093] In the formula, S represents the optimal welding scheme. For better welding quality of the pipe fittings to be welded, The production efficiency preference direction for the pipe fittings to be welded For the welding cost preference direction of the pipe fittings to be welded, , , The weights are, in order: welding quality, production efficiency, and welding cost.

[0094] It should be noted that the weighting percentage is determined based on the customer's needs for the pipe fittings to be welded. For example, in order to complete the pipe fittings to be welded faster, it is necessary to consider faster welding methods, but this may lead to a decrease in welding quality. After comprehensive weighting analysis, the final weighting allocation is determined.

[0095] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the claimed invention. The scope of protection claimed by the appended claims and their equivalents is defined.

Claims

1. A method for intelligent welding control of pipe fittings, characterized in that, include: Collect characteristic information on several types of pipe fittings and establish a pipe fitting characteristic database; A welding action database is established based on several welding methods, welding parameters, and welding codes. Based on the pipe fitting feature database and the welding action database, each pipe fitting feature element in the pipe fitting feature database is mapped to the feasible welding method, welding parameters and welding code, and combined into a pipe fitting welding mapping association matrix; Based on the data of the pipe fittings to be welded collected by the sensors on the welding robotic arm, the matching degree of pipe fitting features in the pipe fitting feature-to-weld mapping correlation matrix is ​​analyzed. Based on the matching degree of pipe feature in the pipe feature and the pipe welding mapping correlation matrix, several welding methods and welding parameters corresponding to the pipe to be welded are determined, and a pre-selected welding scheme is generated. Based on the pre-selected welding scheme, the final welding scheme is determined according to the preferred direction of the pipe to be welded, and the welding robotic arm is intelligently controlled. Based on the pipe fitting feature database and the welding action database, each pipe fitting feature element in the feature database is mapped to feasible welding methods, welding parameters, and welding codes, forming a pipe fitting welding mapping association matrix. Specifically, this matrix includes: Based on each pipe fitting feature element in the pipe fitting feature database, each pipe fitting feature element is quantized to obtain the quantization parameters of the pipe fitting feature elements. Based on the quantitative parameters of pipe fitting feature elements, and according to welding process knowledge and welding technology requirements, several welding methods, welding parameters and welding codes are associated and bound to the quantitative parameters of each pipe fitting feature element. A welding mapping correlation matrix A is established based on several welding methods, welding parameters and welding codes corresponding to the quantization parameters of each pipe fitting feature element; ； in, For the pipe fitting welding mapping correlation matrix, For the first The first welded pipe fitting The first feature corresponds to the first The welding method of the first One welding parameter, Welding codes for welding methods associated with pipe fitting features. This represents the total number of pipe fitting features. is the total number of welding parameters, and k is the total number of welding codes.

2. The intelligent welding control method for pipe fittings according to claim 1, characterized in that, Based on the data of the pipe fittings to be welded collected by sensors on the welding robotic arm, the analysis of the pipe fitting feature matching degree in the pipe fitting welding mapping correlation matrix specifically includes: Based on the data of the pipe fittings to be welded collected by the sensors on the welding robotic arm, feature extraction is performed on the data of the pipe fittings to be welded, and the feature of each pipe fitting to be welded is quantified to obtain the quantified feature parameters of the pipe fittings to be welded. Standardization is performed on each element in the correlation matrix between the quantified feature parameters of the pipe fitting to be welded and the welding mapping of the pipe fitting; Based on the quantification of the characteristic parameters of the pipe fitting to be welded and the correlation matrix of the pipe fitting welding mapping, the similarity between the characteristic parameters of the pipe fitting to be welded and each characteristic parameter of the pipe fitting in the correlation matrix of the pipe fitting welding mapping is calculated by the similarity formula.

3. The intelligent welding control method for pipe fittings according to claim 2, characterized in that, The similarity formula is: ； In the formula, The similarity of the characteristic parameters of the pipe fittings. Let i be the characteristic parameter of the i-th pipe fitting to be welded. Let be the characteristic parameter of the i-th pipe fitting in the pipe fitting welding mapping correlation matrix.

4. The intelligent welding control method for pipe fittings according to claim 3, characterized in that, Based on the pipe feature matching degree in the pipe fitting-to-weld welding mapping correlation matrix, several welding methods and welding parameters corresponding to the pipe fitting to be welded are determined, and a pre-selected welding scheme is generated, specifically including: Based on the similarity of each feature parameter of the pipe fitting in the correlation matrix between the pipe fitting to be welded and the pipe fitting welding, the pipe fitting features with a similarity of 1 are selected. Based on several pipe fitting features with a similarity of 1, the features of the pipe fitting to be welded are used as secondary screening conditions to determine the welding method, welding parameters and welding code of the pipe fitting to be welded. Based on several pipe fitting features after secondary screening, and the welding method, welding parameters and welding code of the pipe fitting to be welded, a pre-selected welding mapping correlation matrix B is formed. ,in After secondary screening, c represents the j-th welding parameter of the y-th welding method corresponding to the ith feature of the x-th welded pipe fitting to be welded, where c is the welding code. Based on the pre-selected welding mapping association matrix, the pre-selected welding mapping association matrix is ​​packaged into a welding dataset; Based on the welding dataset, a classification model is established, with the pipe fitting to be welded as the root node, each pipe fitting feature in the pre-selected welding matrix as an internal node, and several welding methods, welding parameters and welding codes associated with the pipe fitting features as leaf nodes. The pre-selected welding matrix is ​​classified to determine several pre-selected schemes.

5. The intelligent welding control method for pipe fittings according to claim 4, characterized in that, The classification model expression is: ； In the formula, For conditional entropy, For welding datasets, Let be the i-th pipe fitting feature in the welding dataset, and n be the total number of pipe fitting features.

6. The intelligent welding control method for pipe fittings according to claim 5, characterized in that, Based on the pre-selected welding scheme, and according to the preferred direction of the pipe fitting to be welded, the final welding scheme is determined, and the welding robotic arm is intelligently controlled, specifically including: Based on several pre-selected welding schemes, a comprehensive analysis of welding quality, production efficiency, and welding cost factors in the welding schemes is conducted to determine the overall capability of several pre-selected welding schemes. Based on the welding requirements and processes of the pipe fittings to be welded, the preferred direction of the pipe fittings to be welded is analyzed; The capabilities of several pre-selected welding schemes are integrated, and features are marked according to the preferred directions that can be satisfied. The preferred direction of the pipe to be welded is used as a condition requirement to establish an intelligent welding analysis model. The optimal welding scheme is selected to meet the preferred direction of the pipe to be welded. The welding method, welding parameters and welding code in the optimal welding scheme are applied to the welding robot arm to complete the intelligent welding control of the welding robot arm.

7. The intelligent welding control method for pipe fittings according to claim 6, characterized in that, The expression for the intelligent welding analysis model is: ； In the formula, S represents the optimal welding scheme. For better welding quality of the pipe fittings to be welded, The production efficiency preference direction for the pipe fittings to be welded For the welding cost preference direction of the pipe fittings to be welded, , , The weights are, in order: welding quality, production efficiency, and welding cost.

Images