CN115255555A - Welding process - Google Patents

Abstract

The invention discloses a welding process, which belongs to the technical field of automatic welding, and comprises the steps of firstly identifying an engineering drawing to determine various basic parameters; then planning the welding process, including calling the data of the welding process database to select and set process parameters; then, by a self-adaptive welding control method, images acquired by the visual equipment are identified, extracted and filtered according to a preset program, so that clear track points and groove geometric parameters are acquired and transmitted to a visual equipment controller; then, recombining the contour characteristics and the geometric parameters by adopting a preset program, and outputting the parameters to a position for controlling the industrial robot through a welding program; then, welding is performed by a welding unit; and finally, performing appearance detection on the welded weld joint by using visual equipment, and judging whether the welding process is finished. The invention solves the technical problems of limited non-standard batch products, welding deformation, frequent change of welding bead parameters and the like in the prior art.

Description

Welding process

Technical Field

The invention relates to the technical field of automatic welding, in particular to a welding process.

Background

With the development of the automatic welding technology, the application of the automatic welding technology in the manufacturing industry is more and more extensive, and great benefits are brought to the manufacturing industry. The welding machine has the advantages that the labor is liberated, the labor cost is reduced, and meanwhile, the welding quality and the welding production efficiency are improved. But the existing automatic welding technology has certain limitation that the automatic welding technology is only suitable for batch production; welding deformation cannot be avoided or reduced; the welding process parameters and the like cannot be adjusted in real time in the face of different welding conditions. Therefore, it is necessary to record various welding process data and establish a welding process database, which can cooperate with a welding robot, an auxiliary action tool, and the like to complete a welding task together. Based on this, chinese patent CN112861498A discloses an automatic compiling method for welding process files, which relates to a welding process automation technology and is used to solve the problems of low compiling efficiency and quality caused by manually compiling a set of welding process files. The automatic compiling method of the welding process file comprises the following steps: acquiring input information, wherein the input information comprises basic element information; determining welding element information according to the acquired basic element information and a preset logic matching rule; filling welding element information and basic element information into corresponding positions of a process file template according to a pre-acquired process template file; generating a welding process file based on a process file template containing welding process information; the welding process information includes welding element information and basic element information. The automatic compiling method of the welding process file is beneficial to reducing workload of manual compiling, improving compiling efficiency, avoiding quality problems of information inconsistency or information omission and the like caused by hand mistakes in the manual compiling process and guaranteeing welding quality.

However, the automatic compiling method for welding process files disclosed above cannot completely solve the technical problems of limited non-standard batch products, welding deformation, frequent change of welding bead parameters and the like encountered in practical application of the automatic welding technology. Specifically, through the automatic compiling method for the welding process file disclosed above, a user can automatically compile and store the welding process file through an entity device integrated or installed with a related computer program, but in practical application, the automatic welding quality is also related to factors such as a pre-design of a welding process, cooperative control of a welding robot, real-time parameters of non-standard products, real-time parameters of welding beads and the like. The reasonable welding process determines the welding quality and welding performance, but the welding process is complicated and complex in design due to the complexity, multifactorial nature and experience of the welding process. The automatic welding firstly solves the problem of how to enable a welding gun to find a welding bead so as to align the welding bead for welding, and if the welding bead cannot be accurately positioned, the result is that workpieces generated by welding are defective products. However, the weld bead position information includes the relative position of the weld bead with respect to the welding gun, and the relative position between the weld bead and the weld bead. Therefore, the robot must acquire the absolute position of the weld bead relative to the welding gun and the relative position between the weld bead and the welding gun, and can accurately find the weld bead position and perform welding. The technology for aligning the position of the weld bead is relatively mature, and a plurality of methods are available, but how to align the position information of the weld bead is a difficult point of the current automatic welding technology.

Disclosure of Invention

Based on this, it is necessary to provide a welding process for solving the technical problems of limited non-standard batch products, welding deformation, frequent change of welding bead parameters, and the like encountered in practical application of the automatic welding technology in the prior art.

A welding process, comprising the steps of:

s1: identifying an engineering drawing, including determining the type of each welding bead, the material quality of the parent metal, the thickness of the parent metal, the structural characteristics and the parameters of the size and the position;

s2: planning a welding process, which comprises calling the data of a welding process database to automatically select and set process parameters of welding materials, welding current, arc voltage, welding speed, welding mode and welding sequence;

s3: self-adaptive welding control, namely identifying, extracting and filtering an image acquired by visual equipment according to a preset program to acquire a clear track point and a groove geometric parameter and transmitting the clear track point and the groove geometric parameter to a visual equipment controller; secondly, recombining the profile characteristics and the geometric parameters by adopting a preset program, and outputting the parameters to a position for controlling the industrial robot through a welding program;

s4: the welding unit carries out welding, a welding program controls the welding unit to carry out welding, welding bead change information is collected by the vision equipment, and welding parameters are fed back to the vision equipment control module in real time;

s5: and (5) appearance detection, namely, visual equipment performs appearance detection on the welded seam and judges whether the welding process is finished.

Specifically, in the step S1, the engineering drawing applied to the automatic welding process is identified by a BP network structure.

Further, the BP neural network structure is a multi-layer feedforward network trained according to an error back propagation algorithm, and comprises an input layer, a hidden layer and an output layer.

Furthermore, the input layer is a welding result expected to be achieved in the welding process; and the parameters of the output layer are calculated by the data transmitted from the input layer to the hidden layer through preset function conjecture.

Specifically, in the step S2, the welding base material and the corresponding welding material are matched according to an equal strength matching method, an equal toughness matching method, or an equal composition matching method.

Specifically, the adaptive control step is realized by an adaptive control sensing system; the self-adaptive control sensing system comprises a robot welding module, a visual device and visual device control module, an input and output interface module, a process parameter acquisition module and a program module.

Further, the program module comprises a first preset program, a second preset program and a third preset program; the first preset program is responsible for controlling the visual equipment; the second preset program is responsible for image processing; and the third preset program is a programmable image post-processing module.

Furthermore, the preset program one is responsible for controlling the operation of the camera and calibrating the distance image in real time in the rectangular coordinate system.

Furthermore, the second preset program obtains features from the contour of the target image, detects the given contour and measures the geometric feature vector of the given contour.

Furthermore, the characteristic data extracted in the third preset program can be recombined to be used in the adaptive control of the welding equipment position and the welding process parameters.

In summary, the welding process of the present invention firstly identifies the engineering drawing to determine the type of each welding pass, the material quality of the base metal, the thickness of the base metal, the structural characteristics, the size and the position of the base metal, and other parameters; then planning a welding process, wherein the welding process comprises calling the data of a welding process database to automatically select and set process parameters such as welding materials, welding current, arc voltage, welding speed, welding mode, welding sequence and the like; then, by a self-adaptive welding control method, an image acquired by the visual equipment is identified, extracted and filtered according to a preset program to obtain a clear track point and a groove geometric parameter, and the clear track point and the groove geometric parameter are transmitted to a visual equipment controller; secondly, recombining the profile characteristics and the geometric parameters by adopting a preset program, and outputting the parameters to a position for controlling the industrial robot through a welding program; then, the welding unit carries out welding, a welding program controls the welding unit to carry out welding, welding bead change information is collected by the vision equipment, and welding parameters are fed back to the vision equipment control module in real time; and finally, performing appearance detection on the welded weld joint by using visual equipment, and judging whether the welding process is finished. In the self-adaptive control process, under the condition that the groove gap is continuously increased, the welding current, the welding speed and the wire feeding speed are correspondingly changed, so that the forming effect of the front side and the back side of the welding line is better. Therefore, the welding process solves the technical problems of limited non-standard batch products, welding deformation, frequent change of welding bead parameters and the like in the practical application of the automatic welding technology in the prior art.

Drawings

FIG. 1 is a process flow diagram of a welding process of the present invention;

FIG. 2 is a schematic diagram of a BP neural network structure of a welding system for use in a welding process according to the present invention;

FIG. 3 is a schematic view of a welding module according to an embodiment of the welding process of the present invention;

FIG. 4 is an architecture diagram of a further refinement of the vision sensor module in the embodiment shown in FIG. 3;

FIG. 5 is a functional flow diagram of a vision equipment control module of a welding process of the present invention;

fig. 6 shows the number of cracks experimentally recorded under different welding control methods. .

Detailed Description

In order to make the aforementioned objects, features and advantages of the present invention more comprehensible, embodiments accompanying figures are described in detail below. In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein.

In the description of the present invention, it is to be understood that the terms "central," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," "counterclockwise," "axial," "radial," "circumferential," and the like are used in the orientations and positional relationships indicated in the drawings for convenience in describing the invention and to simplify the description, and are not intended to indicate or imply that the referenced device or element must have a particular orientation, be constructed and operated in a particular orientation, and are not to be considered limiting of the invention.

Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or to implicitly indicate the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "a plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.

In the present invention, unless otherwise expressly stated or limited, the terms "mounted," "connected," "secured," and the like are to be construed broadly and can, for example, be fixedly connected, detachably connected, or integrally formed; can be mechanically or electrically connected; they may be directly connected or indirectly connected through intervening media, or they may be interconnected within two elements or in a relationship where two elements interact with each other unless otherwise specifically limited. The specific meanings of the above terms in the present invention can be understood according to specific situations by those of ordinary skill in the art.

In the present invention, unless otherwise expressly stated or limited, the first feature "on" or "under" the second feature may be directly contacting the first and second features or indirectly contacting the first and second features through an intermediate. Also, a first feature "on," "above," and "over" a second feature may be directly on or obliquely above the second feature, or simply mean that the first feature is at a higher level than the second feature. A first feature "under," "beneath," and "under" a second feature may be directly under or obliquely under the second feature, or may simply mean that the first feature is at a lesser elevation than the second feature.

It will be understood that when an element is referred to as being "secured to" or "disposed on" another element, it can be directly on the other element or intervening elements may also be present. When an element is referred to as being "connected" to another element, it can be directly connected to the other element or intervening elements may also be present. The terms "vertical," "horizontal," "upper," "lower," "left," "right," and the like as used herein are for illustrative purposes only and do not denote a unique embodiment.

Referring to fig. 1, fig. 1 is a process flow diagram of a welding process according to the present invention. As shown in fig. 1, a welding process of the present invention comprises the steps of:

s1: identifying an engineering drawing, including determining parameters such as the type, the base material, the base material thickness, the structural characteristics, the size and the position of each welding bead;

s2: planning a welding process, which comprises calling the data of a welding process database to automatically select and set process parameters such as welding materials, welding current, arc voltage, welding speed, welding mode, welding sequence and the like;

s3: the self-adaptive welding control comprises a visual device and a visual device control module; firstly, identifying, extracting and filtering an image acquired by the vision equipment according to a preset program to acquire a clear track point and a groove geometric parameter and transmit the clear track point and the groove geometric parameter to a vision equipment controller; secondly, recombining the profile characteristics and the geometric parameters by adopting a preset program, and outputting the parameters to a position for controlling the industrial robot through a welding program;

s4: the welding unit carries out welding, a welding program controls the welding unit to carry out welding, welding bead change information is collected by the vision equipment, and welding parameters are fed back to the vision equipment control module in real time;

s5: and (5) appearance detection, namely performing appearance detection on the welded seam by using visual equipment, and judging whether the welding process is finished.

Specifically, in the step S1, the engineering drawing applied to the automatic welding process may be identified through the BP network structure. The BP neural network is a multi-layer feedforward network trained according to error back propagation, namely error back propagation for short, the algorithm is called as BP algorithm, the basic idea is a gradient descent method, and a gradient search technology is utilized so as to minimize the mean square error between the actual output value and the expected output value of the network. The basic BP algorithm includes two processes of forward propagation of a signal and back propagation of an error. That is, the error output is calculated in the direction from input to output, and the weight and threshold are adjusted in the direction from output to input. During forward propagation, an input signal acts on an output node through a hidden layer, an output signal is generated through nonlinear transformation, and if actual output does not accord with expected output, the process of backward propagation of errors is carried out. The error back transmission is to back transmit the output error to the input layer by layer through the hidden layer, and to distribute the error to all units of each layer, and to use the error signal obtained from each layer as the basis for adjusting the weight of each unit. The error is reduced along the gradient direction by adjusting the connection strength of the input node and the hidden node, the connection strength of the hidden node and the output node and the threshold value, and the training is stopped by determining the network parameters corresponding to the minimum error, such as the weight and the threshold value, through repeated learning and training. At the moment, the trained neural network can process and output the information which is subjected to nonlinear conversion and has the minimum error to the input information of similar samples. More specifically, as shown in fig. 2, fig. 2 is a schematic structural diagram of a BP neural network of a welding system applied to a welding process of the present invention. In the embodiment shown in fig. 2, the BP neural network structure of the welding system is a multi-layer feedforward network trained by an error back propagation algorithm, and mainly comprises an input layer, a hidden layer and an output layer; the input layer is often a welding result expected to be achieved in the welding process, such as fusion depth, fusion width, base material information, joint information and the like; the output layer parameters, which are typically welding process parameters such as welding current, welding voltage, etc., are calculated by function inference of the hidden layer design. A large amount of numerical simulation and experimental data are adopted, different hidden element numbers and function curves are taken to respectively train the neural network, and the type and the coefficient of the hidden layer function are continuously adjusted along the hidden element numbers, so that the output error is reduced, and the self-adaptive control of the welding process is completed.

Further, in step S2, a welding process database needs to be established before planning the welding process. The welding process database records relatively perfect welding process information in a preset time period, and can be continuously updated according to field production. Thus, the welding process database is the basis and core of the welding process data store. After the welding process database is established, the user can further plan the specific process information of the current welding construction according to the relevant parameters identified in the step S1. For example, the welding parent metal and the corresponding welding material may be matched according to the preset welding process database. Specifically, the welding base material and the corresponding welding material may be matched according to an equal strength matching method, an equal toughness matching method, or an equal composition matching method, respectively. The equal strength matching method is mainly suitable for welding structural members, the strength of a welding seam cannot be higher than that of a base metal theoretically, otherwise the quality of a welding joint is reduced due to poor crack resistance of the welding seam or stress concentration and the like. The said equal toughness matching method is mainly suitable for welding low alloy high strength steel to prevent joint from being damaged by stress caused by insufficient plasticity or toughness of the joint when the base metal has great structural rigidity and complicated stress. The chemical components of the deposited metal of the welding rod selected by the same component matching principle are the same as those of the welded parent metal. The method is mainly suitable for welding stainless steel, weathering steel or heat-resistant steel, thereby ensuring that the corrosion resistance of the welding seam is the same as that of the parent metal and the welding seam can be well fused and matched with the parent metal. In addition, according to the requirements of conditions such as design, workpiece strength, welding process and the like, the types of welding seams of different weldments and different positions of the same weldment are different; for example, common weld types include: no groove, a Y-shaped groove, an X-shaped groove, a U-shaped groove or a double U-shaped groove, etc. The welding processes corresponding to different welding seam types are different, and the walking path and the movement posture of the welding gun are different. Therefore, the welding process database needs to record the welding attitude information corresponding to the relevant welding seam, so that the planned welding process is applicable. In addition, the welding deformation can be effectively controlled by selecting a proper welding sequence, so that the welding process database records that the basic welding sequence principle is followed, and a welding robot can be guided to carry out welding according to the basic welding sequence principle. For example, basic principles of the welding sequence include: the welding method comprises the steps of reducing heat input and filling metal as much as possible during welding, reasonably distributing each group unit for a group welding structure, performing reasonable group welding, welding symmetrically from the middle to two sides at the position with the highest rigidity of a component, welding a butt weld, welding a fillet weld, welding a short weld, welding a long weld, welding a butt weld, welding a ring weld, or welding a tensile stress area, a shear stress area, a compressive stress area and the like when welding stress exists. In addition, the welding process database should also receive and record major process parameters, including: welding current, arc voltage, welding speed, power type and polarity, electrode diameter, welding layer number and the like. In addition, the thickness of the base material, the width of the weld joint, the height of the weld, the material of the base material, etc. also affect the selection of the welding process parameters. For example: the diameter of a welding material used for welding the thin plate is larger than that of a thick plate, and when the base metal is thick and the groove is wide, multilayer multi-pass welding is adopted; the welding current needs to be adjusted to be small in the 1 st welding seam backing welding of multilayer multi-pass welding.

Further, in the step S3, the adaptive control step is mainly implemented by an adaptive control sensing system. The self-adaptive control sensing system comprises a robot welding module, a visual device and visual device control module, an input/output interface module, a process parameter acquisition module and a program module; the program modules comprise a first preset program for vision equipment control and distance image calibration, a second preset program for image processing for processing joint geometry, a third preset program for calculating image characteristics and adaptive process parameters, and a fourth preset program for generating welding tool trajectories. Specifically, the robot welding module mainly comprises a welding robot unit, a welding power supply unit, a welding gun unit, a wire feeding mechanism, a clamp unit, a positioner and auxiliary devices related to water, gas and the like. Further, as shown in fig. 3, fig. 3 is a schematic structural diagram of a welding module according to an embodiment of the welding process of the present invention. In the present embodiment, the welding gun unit is controlled by a driving system, i.e. a wire feeder, and the welding gun unit transmits the action state to the control module thereof in real time. Furthermore, in the adaptive control sensing system, the visual device and the visual device control module are the core of the sensing system. The self-adaptive control sensing system has the main functions of detecting the geometric information of the groove to be welded and completing the self-adaptive adjustment of the neutralization height of the welding gun; meanwhile, welding parameters are optimized in a self-adaptive mode based on the groove gap or the sectional area obtained through detection, and meanwhile, online adjustment is conducted. The hardware components of the system are mainly a laser vision sensor, a controller, a servo controller and an input and output control unit. As shown in fig. 4, fig. 4 is a schematic diagram of a further detailed architecture of the vision sensor module in the embodiment shown in fig. 3. Further, the vision equipment control module also includes several functionally distinct program parts, which are used in the firmware functions in process control and its on-line and off-line system processing programs, as shown in fig. 5. In the functional flow chart of the vision device control module shown in fig. 5, a first preset program is responsible for controlling the operation of the camera, and simultaneously, the distance image is calibrated in real time in a rectangular coordinate system. The second preset program is mainly responsible for image processing. It acquires features from the contours of the target image, detects the given contour and measures its geometric feature vectors. The module provides various connectors and is configured with a special image processing method, so that the robustness of the module is guaranteed. The third preset program is a programmable image post-processing module in which the extracted feature data can be recombined for use in adaptive control of robot position and welding process parameters. The joint library is a database storing parameters specific to the vision equipment, and the database can be incorporated into the process database, so that the vision equipment control module can process different types of applications. The graphical user interface operates on the user control terminal and is primarily used to display data collected by the vision equipment and to configure various parameters of the vision equipment. Therefore, in the adaptive welding step, the core process is the vision equipment and the vision equipment control module. And the control unit is connected with the automatic welding equipment, namely the robot. The robot connection obtains a clear track point related image and groove geometric parameters through recognition, extraction and filtration of a preset program according to an image collected by a visual device and transmits the clear track point related image and the groove geometric parameters to a controller; then, the outline characteristics and the geometric parameters are recombined through a preset program, so that the position of the industrial robot and the output parameter control of the welding program are realized, and the self-adaptive control of the welding process is further completed.

Further, in the intervention control of the adaptive control step, the welding unit performs welding on a product, wherein a preset welding program controls the welding unit to perform welding, welding bead change information is acquired by the vision equipment, and welding parameters are fed back to the vision equipment control module in real time; and finally, carrying out appearance detection on the welded welding line by using visual equipment, and judging whether the welding process is finished. And ending the welding process of the welding process until all the products are welded.

Further, the welding feasibility of the welding process described above was continued to be compared experimentally. Wherein, the geometric dimension of the sample required by the experiment is as follows: the length X width X thickness = (300X 100X 5) mm, the surfaces of all samples need to be subjected to acid pickling treatment before experiments, and then the samples are polished; and then, mounting and clamping the welding groove by using a welding jig to form the welding groove. Wherein the gap standard of the groove is as follows: the gap is ensured to be from small to large from the beginning end to the tail end of the welding line, and the variation range of the welding line is required to be less than 4mm. And then, aiming at a welding groove formed after the sample is assembled on the welding jig, manufacturing an engineering drawing. And then, inputting the engineering drawing into a preset system, acquiring corresponding welding process parameters under different clearance conditions according to a preset welding process database, and planning an actual welding process according to the welding process parameters. Then, the obtained welding process parameters are input into a preset program, the preset program can convert the input welding parameters into a program for outputting the welding parameters, and the program for outputting the welding parameters comprises related functions used in data operation and processing, such as operators, stack functions and the like. Furthermore, in an actual welding experiment, mean value processing is carried out on the welding seam gaps detected based on the visual equipment, and then various welding parameters output under different gaps are displayed on an interface of the user control terminal in real time. During processing, the user control terminal firstly collects the obtained groove gap value and then carries out mean value processing on the groove gap value, and the mean value obtained in the process is an actual numerical value required by calling process parameters in the welding process. On the basis of processing the acquired gap data, corresponding process parameters are called in a self-adaptive table in a preset program, and the process is the whole process of adaptive control. Specifically, each parameter is called in real time based on the acquired gap value, and from the aspect of current value change, the welding current value is gradually reduced under the condition that the gap is continuously increased, so as to reduce the heat input quantity during welding. When the clearance is increased continuously, the molten pool collapses due to the continuous high accumulation of heat, meanwhile, the welding penetration is caused by the non-forming groove below the molten pool as a support, the forming effect is deteriorated, and therefore, the heat accumulation amount can be effectively reduced by properly reducing the current during welding. From the aspect of wire feeding speed, under the condition that the clearance is continuously increased, the wire feeding speed also tends to be increased, so that the welding wire can efficiently fill the overlarge clearance, and the welding seam cannot be welded through. In terms of welding speed, the welding speed is reduced with increasing gap, so that the welding wire has sufficient time to provide the filling amount. Based on the welding experiment process, sampling inspection is carried out on the experimental welding seams, and the welding crack condition results prepared by different welding processes are compared, as shown in fig. 6.

Specifically, as can be seen from fig. 6, the number of weld cracks generated in different welding methods is also different. When the number of the check points is 100, the number of the cracks of the PLC welding control method is 26; the number of the cracks of the common visual sensor welding control method is 19; the number of cracks for adaptive weld control is only 3. When the number of the check points is 500, the number of the cracks of the PLC welding control method is 57, the number of the cracks of the common vision sensor welding control method is 43, and the number of the cracks of the welding control method is only 10. That is, the number of cracks in the adaptive control method is obviously lower than that in the other two methods, so that the adaptive control method can effectively reduce the generation of the cracks. The reason is that the parameter adaptive control is used in the whole welding control, and under the condition that the groove gap is continuously increased, the welding current, the welding speed and the wire feeding speed are correspondingly changed, so that the forming effect of the front surface and the back surface of the welding seam is better, and the number of cracks is obviously improved compared with that of the traditional method.

In summary, the welding process of the present invention firstly identifies the engineering drawing to determine the type, material, thickness, structural characteristics, size and position of each welding pass; then planning a welding process, wherein the welding process comprises calling the data of a welding process database to automatically select and set process parameters such as welding materials, welding current, arc voltage, welding speed, welding mode, welding sequence and the like; then, by a self-adaptive welding control method, images acquired by the visual equipment are identified, extracted and filtered according to a preset program, so that clear track points and groove geometric parameters are acquired and transmitted to a visual equipment controller; secondly, recombining the profile characteristics and the geometric parameters by adopting a preset program, and outputting the parameters to a position for controlling the industrial robot through a welding program; then, welding is carried out by a welding unit, a welding program controls the welding unit to carry out welding, welding bead change information is collected by a visual device, and welding parameters are fed back to a visual device control module in real time; and finally, performing appearance detection on the welded seam by using visual equipment, and judging whether the welding process is finished. In the self-adaptive control process, under the condition that the groove gap is continuously increased, the welding current, the welding speed and the wire feeding speed are correspondingly changed, so that the forming effect of the front side and the back side of the welding line is better. Therefore, the welding process solves the technical problems of limited non-standard batch products, welding deformation, frequent change of welding bead parameters and the like in the practical application of the automatic welding technology in the prior art.

The technical features of the embodiments described above may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments described above are not described, but should be considered as being within the scope of the present specification as long as there is no contradiction between the combinations of the technical features.

The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.

Claims (10)

1. A welding process is characterized by comprising the following steps:

s1: identifying an engineering drawing, including determining parameters of the type, the material, the thickness, the structural characteristics and the size position of each welding bead;

s2: planning a welding process, which comprises calling the data of a welding process database to automatically select and set process parameters of welding materials, welding current, arc voltage, welding speed, welding mode and welding sequence;

s3: self-adaptive welding control, namely identifying, extracting and filtering an image acquired by visual equipment according to a preset program to acquire a clear track point and a groove geometric parameter and transmitting the clear track point and the groove geometric parameter to a visual equipment controller; then, recombining the contour characteristics and the geometric parameters by adopting a preset program, and outputting the parameters to a position for controlling the industrial robot through a welding program;

s4: the welding unit carries out welding, a welding program controls the welding unit to carry out welding, welding bead change information is collected by the vision equipment, and welding parameters are fed back to the vision equipment control module in real time;

s5: and (5) appearance detection, namely, visual equipment performs appearance detection on the welded seam and judges whether the welding process is finished.

2. A welding process according to claim 1, wherein: in the step S1, the engineering drawing applied to the automated welding process is identified by the BP network structure.

3. A welding process according to claim 2, wherein: the BP neural network structure is a multi-layer feedforward network trained according to an error back propagation algorithm and comprises an input layer, a hidden layer and an output layer.

4. A welding process according to claim 3, wherein: the input layer is a welding result expected to be achieved in the welding process; and calculating the parameters of the output layer by the data transmitted to the hidden layer by the input layer through preset function conjecture.

5. A welding process according to claim 1, wherein: in the step S2, the welding base material and the corresponding welding material are matched according to an equal strength matching method, an equal toughness matching method, or an equal composition matching method.

6. A welding process according to claim 1, wherein: the self-adaptive control step is realized by a self-adaptive control sensing system; the self-adaptive control sensing system comprises a robot welding module, a visual device and visual device control module, an input and output interface module, a process parameter acquisition module and a program module.

7. A welding process according to claim 6, wherein: the program module comprises a first preset program, a second preset program and a third preset program; the first preset program is responsible for controlling the visual equipment; the second preset program is responsible for image processing; and the third preset program is a programmable image post-processing module.

8. A welding process according to claim 7, wherein: and the first preset program is responsible for controlling the operation of the camera and calibrating the distance image in real time in the rectangular coordinate system.

9. A welding process according to claim 8, wherein: and a second preset program acquires features from the contour of the target image, detects the given contour and simultaneously measures a geometric feature vector of the given contour.

10. A welding process according to claim 9, wherein: the characteristic data extracted in the third preset program can be recombined and used in the adaptive control of the welding equipment position and the welding process parameters.

Images