A new type of AC argon arc welding machine

Abstract

The present invention provides a novel AC argon arc welding machine, comprising a main control module, a waveform generation module, a waveform correction module, and a power supply module, wherein the waveform generation module is used to generate a standard square wave; the waveform correction module is used to generate a correction scheme and transmit the correction scheme to the waveform generation module; the main control module is used to generate a first instruction and a second instruction, wherein the first instruction triggers the waveform generation module to generate the standard square wave, and the second instruction triggers the waveform correction module to generate the correction scheme; the waveform generation module corrects the standard square wave according to the correction scheme. The novel AC argon arc welding machine provided by the present invention can overcome the problems of traditional square waves, such as bubbles easily appearing, resulting in uneven welding surfaces, and arc breaking, and significantly improves the performance of the AC argon arc welding machine.

Description

Technical Field

[0001] The invention relates to the technical field of welding, in particular to a novel AC argon arc welding machine. Background Art

[0002] Argon arc welding machine is a machine that uses argon arc welding, which uses high-voltage breakdown to start the arc. Argon arc welding is tungsten inert gas shielded arc welding, which refers to a welding method that uses industrial tungsten or active tungsten as a non-melting electrode and inert gas (argon) as protection, referred to as TIG. The arc starting of argon arc welding uses high-voltage breakdown to start the arc. First, high frequency and high voltage are applied between the electrode needle (tungsten needle) and the workpiece to break through the argon gas to make it conductive, and then a continuous current is supplied to ensure the stability of the arc. The working principle of the argon arc welding machine in terms of the main circuit, auxiliary power supply, drive circuit, protection circuit, etc. is the same as that of the manual arc welding machine.

[0003] Traditional AC argon arc welding machines usually use square waves as the AC current output waveform. Figure 1 In practice, it is found that when using the above-mentioned traditional square wave for welding, bubbles are prone to appear, resulting in uneven welding surfaces and arc breaking, which cannot meet the requirements of high-standard welding scenarios and urgently needs to be improved. Summary of the invention

[0004] In order to at least solve the technical problems existing in the above-mentioned background technology, the present invention provides a multifunctional AC argon arc welding machine.

[0005] A first aspect of the present invention provides a novel AC argon arc welding machine, comprising a main control module (101), a waveform generation module (102), a waveform correction module (103), and a power supply module (104), wherein the main control module (101) is connected to the waveform generation module (102) and the waveform correction module (103); wherein:

[0006] The waveform generation module (102) is used to generate a standard square wave;

[0007] The waveform correction module (103) is used to generate a correction scheme and transmit the correction scheme to the waveform generation module (102);

[0008] The main control module (101) is used to generate a first instruction and a second instruction, wherein the first instruction is transmitted to the waveform generation module (102) to trigger it to generate the standard square wave, and the second instruction is transmitted to the waveform correction module (103) to trigger it to generate the correction solution;

[0009] The power supply module (104) provides power to the main control module (101), the waveform generation module (102), and the waveform correction module (103);

[0010] The waveform generation module (102) is further used to correct the standard square wave according to the correction scheme.

[0011] As a preferred embodiment, the correction scheme includes a first sub-scheme, which includes: setting the current value of the standard square wave in the negative half cycle to be greater than that in the positive half cycle by a first value, and setting the current value in the positive half cycle to remain unchanged.

[0012] As a preference, the first value is 5%-25%.

[0013] As a preferred embodiment, the correction scheme further includes a second sub-scheme, and the second sub-scheme includes: setting current switching points in the positive half cycle and the negative half cycle of the current.

[0014] As a preferred embodiment, the correction scheme also includes a third sub-scheme, and the third sub-scheme includes: setting a bump in the negative half cycle of the current.

[0015] As a preferred embodiment, the duration of the convex point is 10%-25% of the duration of the negative half cycle, and the current magnitude is 5-25% of the current of the negative half cycle.

[0016] As a preference, the waveform generation module (102) adopts software code to implement when generating the standard square wave and correcting the standard square wave according to the correction scheme.

[0017] As a preferred embodiment, the novel AC argon arc welding machine further comprises a camera module (105) for capturing images of the welding scene;

[0018] The main control module (101) is also used to determine whether to generate the second instruction based on the welding scene image.

[0019] Preferably, the main control module (101) is further used to determine whether to generate the second instruction according to the welding scene image, including:

[0020] The main control module (101) processes the welding scene image to extract the roughness of the welding object, and determines whether the roughness is greater than a preset value. If so, the second instruction is not generated, otherwise the second instruction is generated.

[0021] As a preferred embodiment, the main control module (101) processes the welding scene image to extract the roughness of the welding object, including:

[0022] Processing the welding scene image to obtain feature data;

[0023] The feature data is input into a depth recognition model, the depth recognition model outputs scene attributes, and the roughness of the welding object is determined according to the scene attributes.

[0024] Compared with the prior art, the novel AC argon arc welding machine provided by the present invention can overcome the problems of the traditional square wave, such as bubbles easily appearing, resulting in uneven welding surface, easy arc breaking, etc., and significantly improves the performance of the AC argon arc welding machine. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0026] Figure 1 is a schematic diagram of a standard square wave in the prior art;

[0027] Figure 2 It is a structural schematic diagram of a novel AC argon arc welding machine disclosed in an embodiment of the present invention;

[0028] Figure 3 is a schematic diagram of a modified square wave disclosed in an embodiment of the present invention;

[0029] Figure 4 is another schematic diagram of the modified square wave disclosed in the embodiment of the present invention;

[0030] Figure 5 It is another structural schematic diagram of a novel AC argon arc welding machine disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0031] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0032] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0033] In the description of the present invention, it should be noted that if the terms "upper", "lower", "inside", "outside", etc. appear to indicate an orientation or position relationship, it is based on the orientation or position relationship shown in the accompanying drawings, or is the orientation or position relationship in which the product of the invention is usually placed when used. It is only for the convenience of describing the present invention and simplifying the description, and does not indicate or imply that the system or component referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention.

[0034] The terms "first", "second", "third", and "fourth" in the specification and claims of the present invention are used to distinguish different objects rather than to describe a specific order of the objects. For example, the first input, the second input, the third input, and the fourth input are used to distinguish different inputs rather than to describe a specific order of the inputs.

[0035] In the embodiments of the present invention, words such as "exemplarily" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "exemplarily" or "for example" in the embodiments of the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplarily" or "for example" is intended to present related concepts in a specific way.

[0036] In the description of the embodiments of the present invention, unless otherwise specified, “multiple” means two or more than two. For example, multiple processing units refer to two or more processing units; multiple elements refer to two or more elements, etc.

[0037] It should be noted that, in the absence of conflict, the features in the embodiments of the present invention may be combined with each other.

[0038] Embodiment 1

[0039] See also Figure 2 , Figure 2 Schematic diagram of the structure of a novel AC argon arc welding machine disclosed in an embodiment of the present invention. Figure 2 As shown, a novel AC argon arc welding machine according to an embodiment of the present invention comprises a main control module (101), a waveform generation module (102), a waveform correction module (103), and a power supply module (104), wherein the main control module (101) is connected to the waveform generation module (102) and the waveform correction module (103); wherein,

[0040] The waveform generation module (102) is used to generate a standard square wave;

[0041] The waveform correction module (103) is used to generate a correction scheme and transmit the correction scheme to the waveform generation module (102);

[0042] The main control module (101) is used to generate a first instruction and a second instruction, wherein the first instruction is transmitted to the waveform generation module (102) to trigger it to generate the standard square wave, and the second instruction is transmitted to the waveform correction module (103) to trigger it to generate the correction solution;

[0043] The power supply module (104) provides power to the main control module (101), the waveform generation module (102), and the waveform correction module (103);

[0044] The waveform generation module (102) is further used to correct the standard square wave according to the correction scheme.

[0045] In the embodiment of the present invention, as described in the background art, conventional square waves for welding are all standard. Figure 1 As shown, this traditional square wave has the problem of bubbles easily appearing, resulting in uneven welding surface and arc breaking, and cannot meet the high-standard welding scene requirements. In view of this, the present invention provides a new AC argon arc welding machine, in which the main control module (101) controls the waveform generation module (102) to generate a standard square wave, and also controls the waveform correction module (103) to generate a correction scheme, so that the waveform generation module (102) corrects the standard square wave according to the correction scheme, thereby obtaining an improved square wave, thereby at least partially overcoming the defects mentioned in the background technology, and finally improving the performance of the AC argon arc welding machine.

[0046] As a preferred embodiment, the correction scheme includes a first sub-scheme, which includes: setting the current value of the standard square wave in the negative half cycle to be greater than that in the positive half cycle by a first value, and setting the current value in the positive half cycle to remain unchanged.

[0047] In the embodiment of the present invention, the negative half cycle and the positive half cycle of the current of the conventional square wave in the prior art are the same, and the present invention makes improvements thereto. Specifically, referring to Figure 3 , set the current of the negative half cycle of the standard square wave to a first value greater than that of the positive half cycle, wherein the instantaneous large current of the negative half cycle is conducive to cleaning the oxide film on the surface of the workpiece; at the same time, the current of the positive half cycle remains unchanged, so that the tungsten electrode can emit enough electrons without overheating, which is conducive to the stability of the sub-arc. This setting takes into account the cathode cleaning effect and the effect of less tungsten electrode burning and good arc stability.

[0048] As a preference, the first value is 5%-25%.

[0049] In the embodiment of the present invention, it has been verified through experiments that setting the first value to 5%-25% can better clean the oxide film on the surface of the workpiece, thereby making the weld smoother.

[0050] As a preferred embodiment, the correction scheme further includes a second sub-scheme, and the second sub-scheme includes: setting current switching points in the positive half cycle and the negative half cycle of the current.

[0051] In the embodiment of the present invention, refer to Figure 3 The present invention sets current switching points in the positive half cycle and the negative half cycle of the current. Then, the current is switched at the set switching points, so that the corrected square wave can reduce the loss during IGBT switching, thereby protecting the IGBT. At the same time, it can also effectively prevent arc breaking caused by AC / DC switching.

[0052] As a preferred embodiment, the correction scheme also includes a third sub-scheme, and the third sub-scheme includes: setting a bump in the negative half cycle of the current.

[0053] In the embodiment of the present invention, refer to Figure 3 In order to further enhance the cleaning effect, the present invention further sets a convex point in the negative half cycle of the current. At the same time, since the duration of the convex point current is short, it will not cause excessive loss to the tungsten rod of the argon arc welding gun.

[0054] As a preferred embodiment, the duration of the convex point is 10%-25% of the duration of the negative half cycle, and the current magnitude is 5-25% of the current of the negative half cycle.

[0055] In the embodiment of the present invention, it has been verified through experiments that setting the duration of the bump to 10%-25% of the duration of the negative half cycle can achieve a better cleaning effect.

[0056] As a preference, the waveform generation module (102) adopts software code to implement when generating the standard square wave and correcting the standard square wave according to the correction scheme.

[0057] In the embodiments of the present invention, the waveform generation in the prior art is usually implemented by a pre-designed hardware circuit, which has a high implementation cost and poor flexibility, and is difficult to meet diverse needs. In view of this, the square wave waveform effect in the present invention is implemented by software code, that is, the corresponding waveform is generated by a pre-set waveform generation and correction code.

[0058] For example:

[0059] Reference Figure 4 As shown, it represents an enlarged view of a cycle. In the figure, 0-7 represent the segmentation points of the waveform. The waveform is divided into 7 segments. The new waveform can be realized by giving corresponding given values ​​in these seven segments. Among them, T = 1 / f, negative half cycle time = duty cycle * T, positive half cycle time = T-negative half cycle time, and the time of the switching point (0-1) is determined by the falling time from the maximum current to the switching point current.

[0060] It should be noted that accuracy is the minimum time interval of a given value, and accuracy also determines the minimum period.

[0061] As a preferred embodiment, the novel AC argon arc welding machine further comprises a camera module (105) for capturing images of the welding scene;

[0062] The main control module (101) is also used to determine whether to generate the second instruction based on the welding scene image.

[0063] In the embodiment of the present invention, the welding scenes are diverse, and different welding scenes represent different welding requirements. For example, scene A has a lower requirement for welding accuracy, and only the standard square wave can meet the requirement, while scene B has a higher requirement for welding accuracy, and a customized square wave is required. Figure 5 The novel AC argon arc welding machine of the present invention further comprises a camera module (105), wherein the main control module (101) determines the corresponding welding requirements based on the recognition of the welding scene image, thereby deciding whether to generate a second instruction, that is, whether to correct the standard square wave. Therefore, the solution of the present invention can determine the welding requirements based on the recognition of the welding scene, and then generate a more accurate square wave waveform.

[0064] Preferably, the main control module (101) is further used to determine whether to generate the second instruction according to the welding scene image, including:

[0065] The main control module (101) processes the welding scene image to extract the roughness of the welding object, and determines whether the roughness is greater than a preset value. If so, the second instruction is not generated, otherwise the second instruction is generated.

[0066] In the embodiment of the present invention, generally speaking, the roughness of the welding object can more accurately reflect the level of welding standards. Therefore, the present invention determines the roughness of the welding object through the welding scene image, and then decides whether to use standard square wave or modified square wave for welding.

[0067] It should be noted that the roughness of the welding object involved in the present invention may be the surface flatness of the steel plate to be welded or the size of the weld. Therefore, the present invention can automatically determine the welding scene in which the new AC argon arc welding machine is currently located through image recognition technology, and then predict the level of the welding standard of the current welding task, and finally determine whether to generate a corrected square wave, which can effectively reduce the tediousness of the user to set the target waveform through manual operation.

[0068] In addition, after the target waveform is automatically determined by image recognition technology, in order to avoid generating an inappropriate square wave waveform due to incorrect recognition of the welding scene, the new AC argon arc welding machine in the present invention may also include an interactive module. On the one hand, the interactive module can allow the user to set the square wave waveform through manual operation (that is, choose to use a standard square wave or a modified square wave). On the other hand, the modified square wave to be generated that is automatically predicted based on the image recognition technology can be displayed to the user for confirmation. After obtaining the user's confirmation instruction, the waveform generation module (102) can be triggered to modify the standard square wave according to the correction scheme.

[0069] As a preferred embodiment, the main control module (101) processes the welding scene image to extract the roughness of the welding object, including:

[0070] Processing the welding scene image to obtain feature data;

[0071] The feature data is input into a depth recognition model, the depth recognition model outputs scene attributes, and the roughness of the welding object is determined according to the scene attributes.

[0072] In the embodiment of the present invention, the accuracy of determining the roughness according to the surface flatness of the steel plate to be welded or the size of the weld is poor, because the flatness of the steel plate surface is not necessarily the first welding standard scene, and the size of the weld is also easily affected by human factors. In view of this, the present invention further determines the scene attributes of the welding scene according to the welding scene image to determine the aforementioned roughness, that is, by determining that the corresponding welding scene is a high-precision mechanical equipment according to the welding scene image, the roughness can be determined to be low; when the welding scene is steel plate welding in an ordinary factory building, the roughness is determined to be high; when the welding scene is a special workshop in a shipyard, the roughness is determined to be low.

[0073] It should be noted that for the deep recognition model, the accuracy of recognition can only be ensured after it has been fully trained. To this end, pictures of various welding scenes (including close-ups, mid-shots, and long shots) can be collected in advance, and the scene attributes of these pictures can be annotated to construct a training set, and the pictures in the training set can be used to train the deep recognition model. In addition, the deep recognition model can be constructed by convolutional neural network (CNN), DBN, and stacked auto-encoder network models. Since the construction method is generally known in the art, the present invention will not be repeated here.

[0074] As an improvement, when training the deep recognition model, the present invention designs an optimization of the training set, namely:

[0075] During the training process, the reliability of each image in the training set is calculated by the following formula:

[0076]

[0077] In the formula, Tru i is the reliability value of the i-th trained image in the training set; L k is the kth th The network loss calculation function for sample i at the iteration; θ is the learning parameter of the network; mean(·) is the mean loss of the i-th trained image during the entire training process; L(·) is the objective function of the network classification; x i is the feature data of the i-th picture, y i Label for annotation;

[0078] If the reliability is lower than a threshold, the image is deleted from the training set.

[0079] In the embodiment of the present invention, the present invention can divide the training of the deep recognition model into stages, that is, first trial training, so as to filter out the pictures with low reliability in the training set (for example, the picture clarity is too low, the scene is too complex, etc.), so that the pictures in the training set are more suitable, which is conducive to improving the training results of the deep recognition model. After that, the deep recognition model is formally trained using the screened training set.

[0080] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input system, and at least one output system, and transmit data and instructions to the storage system, the at least one input system, and the at least one output system.

[0081] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing system, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine as a stand-alone software package and partially on a remote machine, or entirely on a remote machine or server.

[0082] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, system, or device. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, system, or device, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0083] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display system (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing system (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of systems can also be used to provide interaction with a user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0084] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0085] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0086] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0087] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A new type of AC argon arc welding machine, characterized by: It comprises a main control module (101), a waveform generation module (102), a waveform correction module (103), and a power supply module (104), wherein the main control module (101) is connected to the waveform generation module (102) and the waveform correction module (103); wherein: The waveform generation module (102) is used to generate a standard square wave; The waveform correction module (103) is used to generate a correction plan and transmit the correction plan to the waveform generation module (102); The main control module (101) is used to generate a first instruction and a second instruction, wherein the first instruction is transmitted to the waveform generation module (102) to trigger it to generate the standard square wave, and the second instruction is transmitted to the waveform correction module (103) to trigger it to generate the correction solution; The power supply module (104) provides power to the main control module (101), the waveform generation module (102), and the waveform correction module (103); The waveform generation module (102) is further used to correct the standard square wave according to the correction scheme; The novel AC argon arc welding machine also includes a camera module (105) for capturing images of the welding scene; The main control module (101) is also used to determine whether to generate the second instruction according to the welding scene image; The main control module (101) is also used to determine whether to generate the second instruction according to the welding scene image, including: The main control module (101) processes the welding scene image to extract the roughness of the welding object, and determines whether the roughness is greater than a preset value, and if so, does not generate the second instruction, otherwise generates the second instruction; The main control module (101) processes the welding scene image to extract the roughness of the welding object, including: Processing the welding scene image to obtain feature data; Inputting the feature data into a depth recognition model, the depth recognition model outputs scene attributes, and determining the roughness of the welding object according to the scene attributes; When training the above-mentioned deep recognition model, the training set is optimized, namely: During the training process, the reliability of each image in the training set is calculated by the following formula: In the formula, Tru i is the reliability value of the i-th trained image in the training set; L k is the loss calculation function of the network for sample i at the kth iteration during training; θ is the learning parameter of the network; mean(·) is the mean loss of the i-th trained image during the entire training process; x i is the feature data of the i-th picture, y i Label for annotation; If the reliability is lower than a threshold, the image is deleted from the training set.

2. A novel AC argon arc welding machine according to claim 1, characterized in that: The correction scheme includes a first sub-scheme, which includes: setting the current value of the standard square wave in the negative half cycle to be greater than that in the positive half cycle by a first value, and the current value in the positive half cycle remains unchanged.

3. A novel AC argon arc welding machine according to claim 2, characterized in that: The first value is 5%-25%.

4. A novel AC argon arc welding machine according to claim 1 or 3, characterized in that: The modified scheme also includes a second sub-scheme, which includes: setting current switching points in the positive half cycle and the negative half cycle of the current.

5. A novel AC argon arc welding machine according to claim 4, characterized in that: The modified solution also includes a third sub-solution, and the third sub-solution includes: setting a bump in the negative half cycle of the current.

6. A novel AC argon arc welding machine according to claim 5, characterized in that: The duration of the convex point is 10%-25% of the duration of the negative half cycle, and the current magnitude is 5-25% of the current of the negative half cycle.

7. A novel AC argon arc welding machine according to claim 1 or 6, characterized in that: The waveform generation module (102) is implemented using software code when generating a standard square wave and correcting the standard square wave according to the correction scheme.

Images