An intelligent welding control method and intelligent control system in automobile processing

Abstract

The application provides an intelligent welding control method and an intelligent control system in automobile processing, and the method comprises the following steps: photographing an alignment position to obtain a first image; obtaining first parameter information of a first automobile workpiece and second parameter information of a second automobile workpiece; determining a first cleaning area image according to the first image, the first parameter information and the second parameter information; determining first cleaning parameters and second cleaning parameters according to the first cleaning area image, the first parameter information and the second parameter information; performing a cleaning operation according to the first cleaning parameters, the second cleaning parameters and the first cleaning area image; photographing the alignment position to obtain a second image; determining a first welding area and first welding parameters according to the second image, the first parameter information and the second parameter information; and performing a welding operation on the first automobile workpiece and the second automobile workpiece according to the first welding area and the first welding parameters. The application can improve the welding quality and the welding efficiency in automobile processing.

Description

Technical Field

[0001] This application relates to the field of intelligent manufacturing technology, specifically to an intelligent welding control method and intelligent control system in automobile processing. Background Technology

[0002] With the automotive manufacturing industry accelerating its transformation towards lightweight, high precision, multi-variety, and small-batch production, traditional welding methods in automotive processing often rely on manual experience. Therefore, it is difficult to meet the stringent requirements of welding aluminum alloys and dissimilar materials (such as aluminum / steel) for heat input, molten pool dynamics, and deformation control. Summary of the Invention

[0003] This application provides an intelligent welding control method and intelligent control system for automotive processing. It can first perform differentiated cleaning on the welding parts of the automotive workpieces to be welded, and then perform intelligent welding on the cleaned welding parts according to the characteristics of the automotive workpieces and the cleaning effect. This helps to improve welding quality and welding efficiency, and thus can achieve the following objectives, such as meeting the stringent requirements for heat input, molten pool dynamics, and deformation control in welding aluminum alloys and dissimilar materials (such as aluminum / steel).

[0004] In a first aspect, embodiments of this application provide an intelligent welding control method for automotive processing, applied to an intelligent control system in automotive processing. The intelligent control system includes: a vision module, a cleaning module, and a welding module. The method includes:

[0005] The first and second automotive workpieces are aligned and fixed using the first and second fixing devices.

[0006] The first image is obtained by taking a picture of the alignment position using the vision module;

[0007] Obtain the first parameter information of the first automotive workpiece and the second parameter information of the second automotive workpiece;

[0008] The first clean area image is determined based on the first image, the first parameter information, and the second parameter information;

[0009] The first cleaning parameter and the second cleaning parameter are determined based on the first clean area image, the first parameter information, and the second parameter information.

[0010] The cleaning module performs a cleaning operation according to the first cleaning parameters, the second cleaning parameters, and the first cleaning area image.

[0011] After the cleaning operation is completed, the vision module takes a picture of the aligned position to obtain a second image;

[0012] The first welding area and the first welding parameters are determined based on the second image, the first parameter information, and the second parameter information.

[0013] The welding module performs welding operations on the first automotive workpiece and the second automotive workpiece according to the first welding area and the first welding parameters.

[0014] Secondly, embodiments of this application provide an intelligent control system for automotive manufacturing, the intelligent control system comprising: a vision module, a cleaning module, and a welding module.

[0015] The vision module is configured to: after the first and second fixing devices align and fix the first and second automotive workpieces, take a picture at the alignment position to obtain a first image; acquire first parameter information of the first automotive workpiece and second parameter information of the second automotive workpiece; determine a first cleaning area image based on the first image, the first parameter information, and the second parameter information; and determine a first cleaning parameter and a second cleaning parameter based on the first cleaning area image, the first parameter information, and the second parameter information.

[0016] The cleaning module is used to perform cleaning operations according to the first cleaning parameters, the second cleaning parameters, and the first cleaning area image;

[0017] The vision module is also used to take a picture of the alignment position after the cleaning operation is completed to obtain a second image; and to determine the first welding area and the first welding parameters based on the second image, the first parameter information and the second parameter information.

[0018] The welding module is used to perform welding operations on the first automotive workpiece and the second automotive workpiece according to the first welding area and the first welding parameters.

[0019] Implementing the embodiments of this application has the following beneficial effects:

[0020] As can be seen, the intelligent welding control method and intelligent control system in automobile processing described in this application embodiment are applied to an intelligent control system, which includes a vision module, a cleaning module, and a welding module. First, after the first and second fixing devices align and fix the first and second automobile workpieces, the vision module takes a picture of the alignment position to obtain a first image, acquires the first parameter information of the first automobile workpiece and the second parameter information of the second automobile workpiece, and determines the first cleaning area image based on the first image, the first parameter information, and the second parameter information. That is, the cleaning area is planned specifically based on machine vision technology and the differences between automobile workpieces (the cleaning areas on the first and second automobile workpieces may be different). The first cleaning parameters and the second cleaning parameters are determined based on the first cleaning area image, the first parameter information, and the second parameter information. That is, the cleaning can be based on the alignment structure between automobile workpieces and related... The cleaning area is accurately assessed based on automotive workpiece parameters (such as material differences). Then, the cleaning module performs cleaning operations according to the first cleaning parameters, the second cleaning parameters, and the image of the first cleaning area. This not only accurately locates the cleaning area but also ensures cleaning efficiency. After the cleaning operation is completed, the vision module takes a picture of the alignment position to obtain a second image. Based on the second image, the first parameter information, and the second parameter information, the first welding area and the first welding parameters are determined. Finally, the welding module performs welding operations on the first and second automotive workpieces based on the first welding area and the first welding parameters. That is, after cleaning, in automotive processing, the corresponding welding area and welding parameters can be dynamically determined by combining the differences between automotive workpieces, which helps to improve welding quality and welding efficiency. In this way, it can achieve the following objectives, such as meeting the stringent requirements for heat input, molten pool dynamics, and deformation control in welding aluminum alloys and dissimilar materials (such as aluminum / steel).

[0021] For example, in automotive manufacturing, if two automotive parts are made of different materials, not only can they be cleaned differently based on their materials, but the cleaning effect after the different cleaning can also be used to further accurately determine the welding area and welding parameters to meet the welding quality requirements between dissimilar automotive parts. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1This is a schematic diagram of the architecture of an intelligent control system in automobile manufacturing provided in an embodiment of this application;

[0024] Figure 2 This is a schematic diagram of the architecture of another intelligent control system in automobile manufacturing provided in the embodiments of this application;

[0025] Figure 3 This is a flowchart illustrating an intelligent welding control method in automotive manufacturing provided in an embodiment of this application;

[0026] Figure 4 This is a schematic diagram of a scenario for an intelligent welding control method in automobile manufacturing provided in an embodiment of this application;

[0027] Figure 5 This is another scenario diagram illustrating an intelligent welding control method in automotive manufacturing provided in this application embodiment;

[0028] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0029] The terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that comprises a series of steps or units is not limited to the listed steps or units, but in one possible example includes steps or units not listed, or in one possible example includes other steps or units inherent to these processes, methods, products, or apparatuses.

[0030] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0031] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present application.

[0032] In this embodiment of the application, the robot may include robots used in automobile processing, such as intelligent robotic arms, intelligent machine tools, humanoid robots, automobile processing robots, etc., and is not limited thereto.

[0033] The electronic device may include any of the following devices with computer functions, such as the robot mentioned above, smartphones, servers (edge ​​servers, cloud servers), tablets, smart cars, humanoid robots, etc., without limitation.

[0034] Please see Figure 1 , Figure 1 This is a schematic diagram of the architecture of an intelligent control system in automotive processing, provided in an embodiment of this application. The intelligent control system includes a vision module, a cleaning module, and a welding module. The intelligent control system can be configured in automotive processing environments, such as automotive processing plants, automotive production lines, automotive repair shops, etc.

[0035] The vision module may include at least one of the following: a camera, a laser sensor, a radar sensor, an ultrasonic sensor, etc., without limitation. The vision module may also include a robot.

[0036] The cleaning module may include a cleaning robot, which can be used to clean the welding surface, specifically, to remove oil, rust, coatings, scale, etc., to ensure the cleanliness of the welding surface. The cleaning module may include a robot.

[0037] The welding module may include a welding robot, which is mainly used to perform welding functions. For example, the welding robot can select appropriate welding materials and equipment, and can select welding rods, welding wires, shielding gases, etc., according to the material type (e.g., low carbon steel, aluminum alloy, etc.) and thickness to ensure welding quality. The welding module may include a robot.

[0038] The vision module, cleaning module, and welding module can communicate with each other.

[0039] Among them, such as Figure 2 As shown, the intelligent control system may also include a control module, which communicates with the vision module, cleaning module, and welding module. The control module may also be a robot, a processor, a control platform, etc. The function of the control module is equivalent to the "brain" of the "intelligent control system", which can be used to command the vision module, cleaning module, and welding module to complete the corresponding functions.

[0040] In practice, the intelligent control system can be used to achieve the following functions:

[0041] The vision module is configured to: after the first and second fixing devices align and fix the first and second automotive workpieces, take a picture at the alignment position to obtain a first image; acquire first parameter information of the first automotive workpiece and second parameter information of the second automotive workpiece; determine a first cleaning area image based on the first image, the first parameter information, and the second parameter information; and determine a first cleaning parameter and a second cleaning parameter based on the first cleaning area image, the first parameter information, and the second parameter information.

[0042] The cleaning module is used to perform cleaning operations according to the first cleaning parameters, the second cleaning parameters, and the first cleaning area image;

[0043] The vision module is also used to take a picture of the alignment position after the cleaning operation is completed to obtain a second image; and to determine the first welding area and the first welding parameters based on the second image, the first parameter information and the second parameter information.

[0044] The welding module is used to perform welding operations on the first automotive workpiece and the second automotive workpiece according to the first welding area and the first welding parameters.

[0045] In this embodiment, machine vision technology and the differences between automotive parts are used to plan cleaning areas specifically (the cleaning areas on the first and second automotive parts may differ). First and second cleaning parameters are determined based on the first cleaning area image, first parameter information, and second parameter information. This allows for precise evaluation of the cleaning area based on the alignment structure between automotive parts and relevant automotive part parameters (such as material differences). Then, the cleaning module performs cleaning operations according to the first and second cleaning parameters and the first cleaning area image. This not only accurately locates the cleaning area but also ensures cleaning efficiency. Next, in the cleaning... After the cleaning operation is completed, the vision module is used to take a picture of the alignment position to obtain a second image. Based on the second image, the first parameter information, and the second parameter information, the first welding area and the first welding parameters are determined. Finally, the welding module is used to perform welding operations on the first and second automotive workpieces based on the first welding area and the first welding parameters. That is, after the cleaning is completed, the corresponding welding area and welding parameters can be dynamically determined by combining the differences between the automotive workpieces, which helps to improve welding quality and welding efficiency. In this way, it can achieve the following objectives, such as meeting the stringent requirements for heat input, molten pool dynamics, and deformation control in welding aluminum alloys and dissimilar materials (such as aluminum / steel).

[0046] Optionally, the first cleaning area image includes a first area image located on the first automotive workpiece and a second area image located on the second automotive workpiece; in determining the first cleaning parameter and the second cleaning parameter based on the first cleaning area image, the first parameter information, and the second parameter information, the vision module is specifically used for:

[0047] The first cleaning parameters are determined based on the first region image and the first parameter information;

[0048] The second cleaning parameter is determined based on the second region image, the first parameter information, and the second parameter information.

[0049] Please see Figure 3 , Figure 3 This is a flowchart illustrating an intelligent welding control method in automotive manufacturing, provided in an embodiment of this application. It is applied to an intelligent control system in automotive manufacturing, which includes a vision module, a cleaning module, and a welding module. The intelligent welding control method in automotive manufacturing includes:

[0050] S301: Align and fix the first automobile workpiece and the second automobile workpiece using the first fixing device and the second fixing device.

[0051] In this design, both the first and second automotive workpieces can be automotive workpieces to be welded (such as parts to be welded), and can also be referred to as automotive machining welded parts. The materials of the first and second automotive workpieces can be the same or different. The first fixing device can be used to fix the first automotive workpiece, and the second fixing device is used to fix the second automotive workpiece. For example, this can be specifically applied to welding on the side panels, floor, roof, doors, frame, and chassis of the vehicle body. One of the two automotive workpieces to be welded can be designated as the first automotive workpiece, and the other as the second automotive workpiece. For instance, when welding fasteners such as nuts and bolts to the body sheet metal, the nuts and bolts can be considered the first automotive workpiece, and the body sheet metal can be considered the second automotive workpiece.

[0052] In practice, the first and second automotive workpieces can be aligned and fixed using a first fixing device and a second fixing device to facilitate welding. For example, the parts to be welded can be accurately aligned according to design requirements and fixed using fixtures or tooling to prevent displacement during welding. Specifically, the assembly gap can be controlled (e.g., required to be ≤0.5mm) to avoid weld defects caused by excessive gap.

[0053] S302: The vision module takes a picture of the aligned position to obtain a first image.

[0054] In a specific implementation, the vision module can adjust the distance and angle between itself and the alignment position, and can take a picture of the alignment position based on the adjusted distance and angle to obtain a first image. The first image can cover the image of the cleaning area that needs to be cleaned. The cleaning area that needs to be cleaned can include the welding area that needs to be welded, that is, the area of ​​the cleaning area that needs to be cleaned is greater than or equal to the area of ​​the welding area that needs to be welded.

[0055] S303: Obtain the first parameter information of the first automotive workpiece and the second parameter information of the second automotive workpiece.

[0056] The first parameter information of the first automobile workpiece may include at least one of the following: the name of the first automobile workpiece, the model of the first automobile workpiece, the material of the first automobile workpiece, the shape of the first automobile workpiece, the configuration position of the first automobile workpiece, the function of the first automobile workpiece, the size of the first automobile workpiece (e.g., thickness, width, length), etc., which are not limited here.

[0057] The second parameter information of the second automobile workpiece may include at least one of the following: the name of the second automobile workpiece, the model of the second automobile workpiece, the material of the second automobile workpiece, the shape of the second automobile workpiece, the configuration position of the second automobile workpiece, the function of the second automobile workpiece, the size of the second automobile workpiece (e.g., thickness, width, length), etc., which are not limited here.

[0058] Specifically, the first parameter information of the first automobile workpiece and the second parameter information of the second automobile workpiece can be obtained directly from the database. Alternatively, the vision module can be used to identify the first automobile workpiece to obtain its corresponding first parameter information, and the second automobile workpiece can be identified to obtain its corresponding second parameter information.

[0059] S304: Determine the first clean area image based on the first image, the first parameter information, and the second parameter information.

[0060] In this process, since not all areas in the first image require welding, only a certain range of the welding area needs to be cleaned. This area can be segmented to obtain a first clean area image, which includes the areas requiring cleaning, and these areas further include the welding areas. For example, the first image can be used to identify the gap between the first and second automotive parts. The contour of this gap can then be extracted to obtain a contour region (which may include two edge contours, one corresponding to the first automotive part and the other to the second automotive part). Based on this contour region (the two edge contours), a preset width is extended outwards to obtain an extended region. Image segmentation is then performed based on this extended region to obtain the first clean area image. The preset width can be pre-set or a system default, and can be determined based on both first and second parameter information. For example, the first parameter information corresponds to a width range, and the second parameter information corresponds to a width range; the preset width can be a width at the intersection of these two width ranges. For example, ... Figure 4 As shown, the gap area can be identified and its corresponding two edge contours can be extracted, such as the first edge contour on the side of the first automobile workpiece and the second edge contour on the side of the second automobile workpiece. The first virtual area can be obtained by expanding outward based on the preset width (width K) (i.e. towards the side of the first automobile workpiece). Similarly, the second virtual area can be obtained by expanding outward based on the preset width (width K) (i.e. towards the side of the second automobile workpiece).

[0061] Optionally, the above step of determining the first clean area image based on the first image, the first parameter information, and the second parameter information can be implemented in the following manner:

[0062] The first image is identified to obtain the gap area between the first automotive workpiece and the second automotive workpiece.

[0063] Extract the contour of the gap region to obtain the first edge contour located on the side of the first automotive workpiece and the second edge contour located on the side of the second automotive workpiece.

[0064] A first preset width is determined based on the first parameter information, and a second preset width is determined based on the second parameter information;

[0065] Based on the first edge contour and the first preset width, the first virtual region is obtained by expanding outwards;

[0066] Based on the second edge contour and the second preset width, the second virtual region is obtained by expanding outwards;

[0067] The first clean area image is determined based on the first virtual region, the second virtual region, and the first image.

[0068] In specific implementation, the first image can be recognized to obtain the gap region between the first and second automotive workpieces. The contour of the gap region is then extracted to obtain a contour region. Based on the contour region, a first edge contour and a second edge contour are determined. The first edge contour is located on the side of the first automotive workpiece, and the second edge contour is located on the side of the second automotive workpiece. A pre-stored mapping relationship between preset parameter information and width can be used to determine the first preset width corresponding to the first parameter information and the second preset width corresponding to the second parameter information. The first and second preset widths can be preset or defaulted to by the system. The first preset width is related to the first parameter information, and the second preset width is related to the second parameter information. The first preset width is then extended outward based on the first edge contour to obtain a first virtual region. Similarly, the second preset width is extended outward based on the second edge contour to obtain a second virtual region. The first and second virtual regions together constitute the extended region. Image segmentation is performed based on this extended region and the first image to obtain a first clean area image. This allows for accurate evaluation of the clean area based on the alignment structure between the automotive workpieces and relevant automotive workpiece parameters (such as material). This not only accurately locates the clean area but also ensures cleaning efficiency, contributing to improved subsequent welding quality and efficiency.

[0069] For example, in practical applications, considering that the materials of the first and second automotive workpieces may be different, the cleaning area can be accurately located based on the material differences and the alignment characteristics between the automotive workpieces.

[0070] For example, such as... Figure 5 As shown, the gap area can be identified and its corresponding two edge contours can be extracted, such as the first edge contour on the side of the first automobile workpiece and the second edge contour on the side of the second automobile workpiece. The first virtual area can be obtained by expanding outward based on the first preset width (width K1) (i.e. towards the side of the first automobile workpiece). Correspondingly, the second virtual area can be obtained by expanding outward based on the second preset width (width K2) (i.e. towards the side of the second automobile workpiece).

[0071] S305: Determine the first cleaning parameter and the second cleaning parameter based on the first cleaning area image, the first parameter information, and the second parameter information.

[0072] The first cleaning parameter may include at least one of the following: cleaning method, cleaning duration, cleaning intensity, cleanliness level, cleaning strategy, etc., without limitation.

[0073] The second cleaning parameter may include at least one of the following: cleaning method, cleaning duration, cleaning intensity, cleanliness level, cleaning strategy, etc., without limitation.

[0074] The first cleaning area image may include a first area image located on the first automotive workpiece and a second area image located on the second automotive workpiece. Due to the differences between the first and second automotive workpieces, cleaning can be carried out in a targeted manner based on their characteristics. That is, the first cleaning parameters corresponding to the first area image and the second cleaning parameters corresponding to the second area image can be determined based on the first parameter information and the second parameter information, so that the cleanliness of both meets the corresponding welding conditions. Since the cleanliness requirements of different materials during welding are usually different, it mainly depends on the chemical properties, physical properties (such as melting point, thermal conductivity, etc.), oxidation tendency, and sensitivity of the welding process of the material. Therefore, in specific implementation, corresponding cleaning strategies can be adopted for different materials to meet the corresponding cleaning requirements.

[0075] Optionally, the first cleaning area image includes a first area image located on the first automotive workpiece and a second area image located on the second automotive workpiece; the above step of determining the first cleaning parameter and the second cleaning parameter based on the first cleaning area image, the first parameter information, and the second parameter information includes:

[0076] The first cleaning parameters are determined based on the first region image and the first parameter information;

[0077] The second cleaning parameter is determined based on the second region image, the first parameter information, and the second parameter information.

[0078] The first cleaning area image may include a first area image located on the first automotive workpiece (i.e., the image of the area where the first virtual area is located) and a second area image located on the second automotive workpiece (i.e., the image of the area where the second virtual area is located). In other words, considering the differences between the first automotive workpiece and the second automotive workpiece, differentiated cleaning can be performed on the first automotive workpiece and the second automotive workpiece.

[0079] Specifically, for example, the corresponding first surface impurity type and first cleanliness level can be determined based on the first region image. Specifically, feature extraction can be performed on the first region image to obtain corresponding features, and surface impurity type identification can be performed based on these features to obtain the first surface impurity type. For example, the features can be input into a neural network model to obtain the corresponding first surface impurity type. Alternatively, the first cleanliness level can be determined based on these features, for example, by inputting the features into a corresponding neural network model to obtain the corresponding first cleanliness level. Then, based on the first parameter information, the first cleaning method and first preset cleanliness level (i.e., the required cleaning level) corresponding to the first surface impurity type can be determined. Specifically, a preset mapping relationship between surface impurity types and cleaning methods can be pre-stored, meaning the first cleaning method corresponding to the first surface impurity type can be determined based on this mapping relationship. Similarly, a preset mapping relationship between surface impurity types and cleanliness levels can be pre-stored, meaning the first preset cleanliness level corresponding to the first surface impurity type can be determined based on this mapping relationship. The first preset cleanliness level can be preset or set by system default.

[0080] Next, the difference between the first cleanliness level and the first preset cleanliness level can be determined. Based on this difference and the first cleaning method, other corresponding cleaning parameters can be determined, such as cleaning duration, cleaning intensity, cleaning strategy, etc. For example, the difference between the first cleanliness level and the first preset cleanliness level can be determined to obtain the first difference. The mapping relationship between the preset difference and the cleaning parameter set of the first cleaning method can also be stored in advance. Then, based on the mapping relationship, the first cleaning parameter set corresponding to the first difference can be determined. The cleaning parameter set can include at least one cleaning parameter, such as cleaning duration, cleaning intensity, cleaning strategy, etc., which are not limited here. The first cleaning method and the first cleaning parameter set (other cleaning parameters) together constitute the first cleaning parameter.

[0081] Next, in the specific implementation, the first preset cleanliness level and the second preset cleanliness level can be related or unrelated. For example, if the first preset cleanliness level and the second preset cleanliness level are related, after determining the first preset cleanliness level, the corresponding second preset cleanliness level can be determined based on the first preset cleanliness level. The first preset cleanliness level and the second preset cleanliness level can be the same or different. For example, a mapping relationship between preset cleanliness levels and reference cleanliness level ranges can be stored in advance, that is, the first cleanliness level range corresponding to the first preset cleanliness level can be determined based on the mapping relationship. The first cleanliness level range can include at least one cleanliness level, and a cleanliness level is selected from the first cleanliness level range as the second preset cleanliness level. In this way, the cleanliness levels of the first automotive workpiece and the second automotive workpiece can be coupled with each other, which helps to ensure the welding effect. As another example, if the first preset cleanliness level and the second preset cleanliness level are unrelated, the first preset cleanliness level can be related to the surface impurity type of the first automotive workpiece, and the second preset cleanliness level can be related to the surface impurity type of the second automotive workpiece.

[0082] The surface impurity type can be preset or set by system default. For example, the surface impurity type can include any of the following: oil stains, rust, coating, scale, etc., without limitation.

[0083] Optionally, the above steps, in which the first cleaning parameters are determined based on the first region and the first parameter information, can be implemented in the following manner:

[0084] Determine the first area of ​​the first region image;

[0085] When the first area is greater than a preset area, the first region image is divided into multiple independent region images;

[0086] The first cleaning parameter is determined based on the multiple independent region images and the first parameter information;

[0087] When the first area is less than or equal to the preset area, the first cleaning parameter is determined based on the first area image and the first parameter information.

[0088] The preset area can be set in advance or set by the system default.

[0089] In specific implementation, the first area of the first area image can be determined. When the first area is greater than the preset area, it indicates that the area to be cleaned is relatively large, and there may be significant differences in the impurity conditions within the area. To ensure the cleaning consistency within the area, the first area image can be divided into multiple independent area images. For example, the area sizes of the multiple independent area images can be the same or different. Specifically, when the areas of the multiple independent area images are the same, the ratio between the first area and the preset area can be determined. When the ratio is greater than 1, the ratio can be rounded up to obtain a reference ratio. The area of the independent area image = the first area / the reference ratio. For example, if the first area is s and the preset area is a, and a < s < 2a, then the area of the independent area image can be s / 2. When the areas of the multiple independent area images are different, the size of each area can be limited to be within a certain area range.

[0090] Next, the first cleaning parameter can be determined based on the multiple independent area images and the first parameter information. Conversely, when the first area is less than or equal to the preset area, the first cleaning parameter is determined based on the first area image and the first parameter information. In this way, dynamic area division can be performed based on the area of the area to be cleaned to ensure the cleaning effect consistency within the area where the first area image is located, which helps to ensure the subsequent welding effect.

[0091] Optionally, the above step of determining the first cleaning parameter according to the first area image and the first parameter information can be implemented as follows:

[0092] Feature extraction is performed on the first area image to obtain a first feature set, and the first surface impurity type and the first cleanliness are determined based on the first feature set;

[0093] The first cleaning method and the first preset cleanliness are determined based on the first surface impurity type and the first parameter information;

[0094] The first cleaning parameter is determined based on the first cleanliness, the first cleaning method, and the first preset cleanliness.

[0095] Among them, the first feature set can include at least one feature, and the feature can include at least one of the following: feature points, feature patterns, feature values, color features, feature vectors, etc., which are not limited here.

[0096] Among them, feature extraction can be performed on the first area image to obtain a first feature set, and then the first feature set is input into a first preset neural network model to obtain the first surface impurity type. Also, the first feature set can be input into a second preset neural network model to obtain the first cleanliness, and the first cleanliness can be used to reflect the cleanliness of the first automotive workpiece at the position where the first area image is located.

[0097] The first preset neural network model can be pre-set or a system default; for example, the first preset neural network model may include a convolutional neural network model or a recurrent neural network model. The second preset neural network model can also be pre-set or a system default; for example, the second preset neural network model may include a convolutional neural network model or a recurrent neural network model. The first preset neural network model and the second preset neural network model can be the same or different.

[0098] Specifically, a first cleaning method and a first preset cleanliness level (i.e., the required cleaning level) corresponding to the first surface impurity type can be determined based on the first parameter information. Specifically, a preset mapping relationship between surface impurity types and cleaning methods can be stored in advance, meaning the first cleaning method corresponding to the first surface impurity type can be determined based on this mapping relationship. Similarly, a preset mapping relationship between surface impurity types and cleanliness levels can be stored in advance, meaning the first preset cleanliness level corresponding to the first surface impurity type can be determined based on this mapping relationship. Alternatively, a first preset cleanliness level corresponding to the first parameter information can be determined (e.g., a preset mapping relationship between parameter information and cleanliness levels can be stored in advance, meaning the first preset cleanliness level corresponding to the first parameter information can be determined based on this mapping relationship). Or, a first preset cleanliness level corresponding to both the first parameter information and the first surface impurity type can be determined (e.g., multiple mapping relationships can be obtained, each mapping relationship corresponding to one parameter information, and each mapping relationship is a preset mapping relationship between surface impurity types and cleanliness levels; specifically, a reference mapping relationship corresponding to the first parameter information can be obtained, and then the first preset cleanliness level corresponding to the first surface impurity type can be determined based on this reference mapping relationship). The first preset cleanliness level can be preset or set by system default.

[0099] Next, the difference between the first cleanliness level and the first preset cleanliness level can be determined. Based on the difference and the first cleaning method, other corresponding cleaning parameters can be determined, such as cleaning time, cleaning intensity, cleaning strategy, etc. The first cleaning method and the other cleaning parameters together constitute the first cleaning parameter.

[0100] In this embodiment, image recognition technology can be used to identify the corresponding surface impurity type and the corresponding cleanliness level. The first parameter information reflects the characteristics of the first automotive workpiece. That is, the corresponding cleaning method and the required cleanliness level (first preset cleanliness level) can be determined based on the characteristics of the first automotive workpiece and the surface impurity type. Furthermore, the corresponding first cleaning parameters can be accurately determined using this information, which helps to ensure cleaning efficiency and cleaning effect, and helps to ensure the quality of subsequent welding.

[0101] Optionally, the above step of determining the first cleaning parameter based on the multiple independent regions and the first parameter information can be implemented in the following manner:

[0102] Feature extraction is performed on the multiple independent region images to obtain multiple reference feature sets, and multiple reference surface impurity types and multiple reference cleanliness levels are determined based on the multiple reference feature sets.

[0103] Based on the multiple reference surface impurity types and the first parameter information, multiple reference cleaning methods and multiple reference preset cleanliness levels are determined;

[0104] The first cleaning parameter is determined based on the plurality of reference cleanliness levels, the plurality of reference cleaning methods, and the plurality of reference preset cleanliness levels.

[0105] The reference feature set may include at least one feature, which may include at least one of the following: feature points, feature textures, feature values, color features, feature vectors, etc., without limitation.

[0106] In this process, features can be extracted from each of the multiple independent region images to obtain multiple reference feature sets, with each independent region image corresponding to one reference feature set. The multiple reference feature sets are then input into a first preset neural network model to obtain multiple reference surface impurity types, with each independent region image corresponding to one reference surface impurity type. Alternatively, the multiple reference feature sets can be input into a second preset neural network model to obtain multiple reference cleanliness levels. The reference cleanliness levels can be used to reflect the cleanliness level of the first automotive workpiece at the location of the corresponding independent region image.

[0107] Specifically, multiple reference cleaning methods and multiple reference preset cleanliness levels (i.e. the required cleanliness level) corresponding to the multiple reference surface impurity types can be determined based on the first parameter information. Specifically, a preset mapping relationship between surface impurity types and cleaning methods can be stored in advance, that is, multiple reference cleaning methods corresponding to multiple surface impurity types can be determined based on the mapping relationship. In addition, a preset mapping relationship between surface impurity types and cleanliness levels can be stored in advance, that is, multiple reference preset cleanliness levels corresponding to multiple reference surface impurity types can be determined based on the mapping relationship.

[0108] Next, the average of multiple preset cleanliness levels can be determined to obtain the average preset cleanliness level. Furthermore, the difference between each of the multiple preset cleanliness levels and the average preset cleanliness level can be determined. Based on this difference and multiple reference cleaning methods, other corresponding cleaning parameters can be determined, such as cleaning duration, cleaning intensity, cleaning strategy, etc. The multiple reference cleaning methods and their corresponding other cleaning parameters together constitute the first cleaning parameter. For example, taking the first preset cleanliness level as an example, the first preset cleanliness level is any of the multiple preset cleanliness levels. The difference between the first preset cleanliness level and the average preset cleanliness level can be determined to obtain the first reference difference. A pre-stored mapping relationship between preset differences and the cleaning parameter set of the reference cleaning method corresponding to the first preset cleanliness level can also be stored. Then, based on this mapping relationship, the first reference cleaning parameter set corresponding to the first reference difference can be determined. This cleaning parameter set can include at least one cleaning parameter, such as cleaning duration, cleaning intensity, cleaning strategy, etc., which are not limited here. The first reference cleaning method and the first reference cleaning parameter set (other cleaning parameters) together constitute the first cleaning parameter.

[0109] In this embodiment, image recognition technology and independent region segmentation technology can be used to identify the corresponding surface impurity types and corresponding cleanliness levels. The first parameter information reflects the characteristics of the first automotive workpiece. That is, the corresponding cleaning method and the required cleanliness level (first preset cleanliness level) can be determined based on the characteristics of the first automotive workpiece and the surface impurity type. Furthermore, by using this information to accurately determine the corresponding first cleaning parameters, it is helpful to ensure cleaning efficiency and cleaning effect while ensuring the consistency of cleaning effect within the area where the first region image is located, which helps to ensure the quality of subsequent welding.

[0110] Optionally, the above step of determining the second cleaning parameter based on the second region image, the first parameter information, and the second parameter information can be implemented in the following manner:

[0111] The second preset cleanliness level is determined based on the first parameter information, the second parameter information, and the first preset cleanliness level;

[0112] Feature extraction is performed on the second region image to obtain a second feature set, and the type of impurities and the degree of cleanliness of the second surface are determined based on the second feature set.

[0113] The second cleaning method is determined based on the type of surface impurities and the second parameter information;

[0114] The second cleaning parameters are determined based on the second cleanliness level, the second cleaning method, and the second preset cleanliness level.

[0115] In practice, the first preset cleanliness level and the second preset cleanliness level can be correlated. After determining the first preset cleanliness level, a corresponding second preset cleanliness level can be determined based on it. The first preset cleanliness level and the second preset cleanliness level can be the same or different. For example, a mapping relationship between preset cleanliness levels and reference cleanliness level ranges can be stored in advance. That is, the first cleanliness level range corresponding to the first preset cleanliness level can be determined based on the mapping relationship, and a cleanliness level can be selected from the first cleanliness level range as the second preset cleanliness level. In this way, the cleanliness levels of the first automotive workpiece and the second automotive workpiece can be coupled, which helps to ensure the welding effect.

[0116] Specifically, a mapping relationship between a preset cleanliness level and a reference cleanliness level range between two different materials can be stored in advance. A target mapping relationship between a preset cleanliness level and a reference cleanliness level range corresponding to the first parameter information and the second parameter information can be obtained. Based on the target mapping relationship, a second preset cleanliness level corresponding to the first preset cleanliness level can be determined.

[0117] The second feature set may include at least one feature, which may include at least one of the following: feature points, feature patterns, feature values, color features, feature vectors, etc., without limitation.

[0118] In this process, features can be extracted from the second region image to obtain a second feature set. The type of impurities on the second surface and the degree of cleanliness can be determined based on the second feature set. For example, the second feature set can be input into a first preset neural network model to obtain the type of impurities on the second surface. Alternatively, the second feature set can be input into a second preset neural network model to obtain the degree of cleanliness. The degree of cleanliness can be used to reflect the cleanliness of the second automotive workpiece at the location of the second region image.

[0119] Specifically, a second cleaning method and a second preset cleanliness level (i.e. the required cleaning level) corresponding to the second surface impurity type can be determined based on the second parameter information. Specifically, a preset mapping relationship between surface impurity types and cleaning methods can be stored in advance, that is, the second cleaning method corresponding to the second surface impurity type can be determined based on the mapping relationship. In addition, a preset mapping relationship between surface impurity types and cleanliness levels can be stored in advance, that is, the second preset cleanliness level corresponding to the second surface impurity type can be determined based on the mapping relationship.

[0120] Next, the difference between the second cleanliness level and the second preset cleanliness level can be determined. Based on this difference and the second cleaning method, other corresponding cleaning parameters can be determined, such as cleaning time, cleaning intensity, cleaning strategy, etc. The second cleaning method and the other cleaning parameters together constitute the second cleaning parameters.

[0121] S306: The cleaning module performs a cleaning operation according to the first cleaning parameters, the second cleaning parameters, and the first cleaning area image.

[0122] Specifically, the cleaning module can perform cleaning operations on the corresponding cleaning area on the first automotive workpiece according to the first cleaning parameters, and perform cleaning operations on the cleaning area on the second automotive workpiece based on the second cleaning parameters. Since the differences between automotive workpieces are taken into account during cleaning, it helps to ensure the quality of subsequent welding.

[0123] S307: After the cleaning operation is completed, the vision module takes a picture of the aligned position to obtain a second image.

[0124] After the cleaning operation is completed, since the gap position may change due to vibration during the cleaning process, the vision module can take another picture of the alignment position to obtain a second image. Then, the welding area to be welded and the corresponding welding parameters can be accurately determined from the second image to achieve high-quality welding.

[0125] S308: Determine the first welding area and the first welding parameters based on the second image, the first parameter information and the second parameter information.

[0126] Specifically, the first welding parameter may include at least one of the following: welding method, welding trajectory, welding material, welding temperature, welding time, etc., which are not limited here.

[0127] Optionally, the first welding parameters include a first part of welding parameters and a second part of welding parameters; the above steps, determining the first welding area and the first welding parameters based on the second image, the first parameter information, and the second parameter information, can be implemented in the following manner:

[0128] The first part of the welding parameters is determined based on the first parameter information and the second parameter information; the reference gap area between the first automotive workpiece and the second automotive workpiece is obtained by identification based on the second image.

[0129] The second part of the welding parameters is determined based on the reference gap area and the first part of the welding parameters.

[0130] The first welding area is determined based on the welding parameters in the second part.

[0131] The first part of the welding parameters may include at least one of the following: welding method, welding material, welding temperature, welding current, welding voltage, welding process, etc., without limitation. For example, the first part of the welding parameters may include welding method, welding material, and welding temperature.

[0132] The second part of the welding parameters may include at least one of the following: welding trajectory, welding duration, etc., which are not limited here. For example, the second part of the welding parameters includes welding trajectory and welding duration.

[0133] The first and second parameter information reflect the characteristics of the first and second automotive workpieces, respectively. Based on these characteristics, the corresponding welding method can be determined, along with the welding material and welding temperature. This yields the first set of welding parameters. For example, a pre-stored mapping relationship between automotive workpiece parameter information pairs and welding methods can be used to determine the welding method corresponding to the first and second parameter information. Similarly, a pre-stored mapping relationship between automotive workpiece parameter information pairs and welding materials can be used to determine the welding material corresponding to the first and second parameter information. Likewise, a pre-stored mapping relationship between automotive workpiece parameter information pairs and welding temperatures can be used to determine the welding temperature corresponding to the first and second parameter information.

[0134] Once the welding method and welding materials are determined, the corresponding welding width can also be determined. Then, based on the second image, a reference gap area between the first and second automotive workpieces is obtained. Based on the reference gap area and the first part of the welding parameters, the second part of the welding parameters is determined. That is, the corresponding welding trajectory can be planned based on the reference gap area. Not only can the corresponding welding trajectory be obtained, but the corresponding welding time can also be determined based on the welding rate of the welding module. That is, the corresponding second part of the welding parameters can be determined based on the welding trajectory and welding time. Since the welding trajectory and welding width can be determined, the first welding area can be determined. That is, the welding can be constrained in the first welding area to ensure the welding effect.

[0135] In practical applications, the welding temperature can also be dynamically adjusted based on the cleanliness level. For example, the corresponding welding temperature can be configured based on different cleanliness levels to ensure the welding effect.

[0136] S309: The welding module performs welding operations on the first automotive workpiece and the second automotive workpiece according to the first welding area and the first welding parameters.

[0137] The welding module can perform welding operations on the first and second automobile workpieces according to the first welding area and the first welding parameters (e.g., welding method, welding material, welding temperature, welding trajectory, welding time, etc.).

[0138] As can be seen, the intelligent welding control method in automobile processing described in this application embodiment is applied to an intelligent control system, which includes a vision module, a cleaning module, and a welding module. First, after the first and second fixing devices align and fix the first and second automobile workpieces, the vision module takes a picture of the alignment position to obtain a first image, acquires the first parameter information of the first automobile workpiece and the second parameter information of the second automobile workpiece, and determines the first cleaning area image based on the first image, the first parameter information, and the second parameter information. That is, it combines machine vision technology and the differences between automobile workpieces to specifically plan the cleaning area (the cleaning areas on the first and second automobile workpieces may differ). And it determines the first cleaning parameters and the second cleaning parameters based on the first cleaning area image, the first parameter information, and the second parameter information. That is, it can be based on the alignment structure between automobile workpieces and related automobile... The cleaning area is accurately assessed based on workpiece parameters (such as material differences). Then, the cleaning module performs the cleaning operation according to the first cleaning parameters, the second cleaning parameters, and the image of the first cleaning area. This not only accurately locates the cleaning area but also ensures cleaning efficiency. After the cleaning operation is completed, the vision module takes a picture of the alignment position to obtain a second image. Based on the second image, the first parameter information, and the second parameter information, the first welding area and the first welding parameters are determined. Finally, the welding module performs welding operations on the first and second automotive workpieces based on the first welding area and the first welding parameters. That is, after cleaning is completed, the corresponding welding area and welding parameters can be dynamically determined by combining the differences between the automotive workpieces, which helps to improve welding quality and welding efficiency. In this way, it can achieve the following objectives, such as meeting the stringent requirements for heat input, molten pool dynamics, and deformation control in the welding of aluminum alloys and dissimilar materials (such as aluminum / steel) in automotive processing.

[0139] Consistent with the above embodiments, please refer to Figure 6 , Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device includes a processor, a memory, a communication interface, and one or more programs. The one or more programs are stored in the memory and configured to be executed by the processor. In this embodiment, the electronic device is applied to an intelligent control system in automotive processing. The intelligent control system includes a vision module, a cleaning module, and a welding module. The programs include instructions for performing the following steps:

[0140] The first and second automotive workpieces are aligned and fixed using the first and second fixing devices.

[0141] The first image is obtained by taking a picture of the alignment position using the vision module;

[0142] Obtain the first parameter information of the first automotive workpiece and the second parameter information of the second automotive workpiece;

[0143] The first clean area image is determined based on the first image, the first parameter information, and the second parameter information;

[0144] The first cleaning parameter and the second cleaning parameter are determined based on the first clean area image, the first parameter information, and the second parameter information.

[0145] The cleaning module performs a cleaning operation according to the first cleaning parameters, the second cleaning parameters, and the first cleaning area image.

[0146] After the cleaning operation is completed, the vision module takes a picture of the aligned position to obtain a second image;

[0147] The first welding area and the first welding parameters are determined based on the second image, the first parameter information, and the second parameter information.

[0148] The welding module performs welding operations on the first automotive workpiece and the second automotive workpiece according to the first welding area and the first welding parameters.

[0149] This application also provides a computer storage medium storing a computer program for electronic data interchange, which causes a computer to perform some or all of the steps of any of the methods described in the above method embodiments, wherein the computer includes an electronic device.

[0150] This application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps of any of the methods described in the above method embodiments. The computer program product may be a software installation package, and the computer may include an electronic device.

[0151] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0152] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0153] In the several embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical or other forms.

[0154] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0155] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0156] If the aforementioned integrated units are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0157] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage device, which may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, etc.

[0158] The embodiments of this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. An intelligent welding control method in automobile manufacturing, characterized in that, An intelligent control system applied in automotive manufacturing, comprising: a vision module, a cleaning module, and a welding module, wherein the method includes: The first and second automotive workpieces are aligned and fixed using the first and second fixing devices. The first image is obtained by taking a picture of the alignment position using the vision module; Obtain the first parameter information of the first automotive workpiece and the second parameter information of the second automotive workpiece; The first clean area image is determined based on the first image, the first parameter information, and the second parameter information; The first cleaning parameter and the second cleaning parameter are determined based on the first clean area image, the first parameter information, and the second parameter information. The cleaning module performs a cleaning operation according to the first cleaning parameters, the second cleaning parameters, and the first cleaning area image. After the cleaning operation is completed, the vision module takes a picture of the aligned position to obtain a second image; The first welding area and the first welding parameters are determined based on the second image, the first parameter information, and the second parameter information. The welding module performs welding operations on the first automotive workpiece and the second automotive workpiece according to the first welding area and the first welding parameters. The step of determining the first clean area image based on the first image, the first parameter information, and the second parameter information includes: The first image is identified to obtain the gap area between the first automotive workpiece and the second automotive workpiece. Extract the contour of the gap region to obtain the first edge contour located on the side of the first automotive workpiece and the second edge contour located on the side of the second automotive workpiece. A first preset width is determined based on the first parameter information, and a second preset width is determined based on the second parameter information; Based on the first edge contour and the first preset width, the first virtual region is obtained by expanding outwards; Based on the second edge contour and the second preset width, the second virtual region is obtained by expanding outwards; The first clean area image is determined based on the first virtual region, the second virtual region, and the first image; The first welding parameters include a first part of welding parameters and a second part of welding parameters; the step of determining the first welding area and the first welding parameters based on the second image, the first parameter information, and the second parameter information includes: The first part of the welding parameters is determined based on the first parameter information and the second parameter information; Based on the second image, a reference gap area between the first automotive workpiece and the second automotive workpiece is obtained; The second part of the welding parameters is determined based on the reference gap area and the first part of the welding parameters. The first welding area is determined based on the welding parameters in the second part.

2. The method as described in claim 1, characterized in that, The first clean area image includes a first area image located on the first automotive workpiece and a second area image located on the second automotive workpiece; The step of determining the first cleaning parameter and the second cleaning parameter based on the first clean area image, the first parameter information, and the second parameter information includes: The first cleaning parameters are determined based on the first region image and the first parameter information; The second cleaning parameter is determined based on the second region image, the first parameter information, and the second parameter information.

3. The method as described in claim 2, characterized in that, Determining the first cleaning parameter based on the first region image and the first parameter information includes: Determine the first area of ​​the first region image; When the first area is greater than a preset area, the first region image is divided into multiple independent region images; The first cleaning parameter is determined based on the multiple independent region images and the first parameter information; When the first area is less than or equal to the preset area, the first cleaning parameter is determined based on the first area image and the first parameter information.

4. The method as described in claim 3, characterized in that, Determining the first cleaning parameter based on the first region image and the first parameter information includes: Feature extraction is performed on the first region image to obtain a first feature set, and the first surface impurity type and first cleanliness level are determined based on the first feature set; The first cleaning method and the first preset cleanliness level are determined based on the first surface impurity type and the first parameter information; The first cleaning parameters are determined based on the first cleanliness level, the first cleaning method, and the first preset cleanliness level.

5. The method as described in claim 3, characterized in that, Determining the first cleaning parameter based on the multiple independent region images and the first parameter information includes: Feature extraction is performed on the multiple independent region images to obtain multiple reference feature sets, and multiple reference surface impurity types and multiple reference cleanliness levels are determined based on the multiple reference feature sets. Based on the multiple reference surface impurity types and the first parameter information, multiple reference cleaning methods and multiple reference preset cleanliness levels are determined; The first cleaning parameter is determined based on the plurality of reference cleanliness levels, the plurality of reference cleaning methods, and the plurality of reference preset cleanliness levels.

6. The method as described in claim 4, characterized in that, Determining the second cleaning parameter based on the second region image, the first parameter information, and the second parameter information includes: The second preset cleanliness level is determined based on the first parameter information, the second parameter information, and the first preset cleanliness level; Feature extraction is performed on the second region image to obtain a second feature set, and the type of impurities and the degree of cleanliness of the second surface are determined based on the second feature set. The second cleaning method is determined based on the type of surface impurities and the second parameter information; The second cleaning parameters are determined based on the second cleanliness level, the second cleaning method, and the second preset cleanliness level.

7. An intelligent control system for automobile manufacturing, characterized in that, The intelligent control system is used to perform the method as described in any one of claims 1-6, and the intelligent control system includes: a vision module, a cleaning module, and a welding module. The vision module is configured to: after the first and second fixing devices align and fix the first and second automotive workpieces, take a picture at the alignment position to obtain a first image; acquire first parameter information of the first automotive workpiece and second parameter information of the second automotive workpiece; determine a first cleaning area image based on the first image, the first parameter information, and the second parameter information; and determine a first cleaning parameter and a second cleaning parameter based on the first cleaning area image, the first parameter information, and the second parameter information. The cleaning module is used to perform cleaning operations according to the first cleaning parameters, the second cleaning parameters, and the first cleaning area image; The vision module is also used to take a picture of the alignment position after the cleaning operation is completed to obtain a second image; and to determine the first welding area and the first welding parameters based on the second image, the first parameter information and the second parameter information. The welding module is used to perform welding operations on the first automotive workpiece and the second automotive workpiece according to the first welding area and the first welding parameters.

8. The system as described in claim 7, characterized in that, The first cleaning area image includes a first area image located on the first automotive workpiece and a second area image located on the second automotive workpiece; in determining the first cleaning parameter and the second cleaning parameter based on the first cleaning area image, the first parameter information, and the second parameter information, the vision module is specifically used for: The first cleaning parameters are determined based on the first region image and the first parameter information; The second cleaning parameter is determined based on the second region image, the first parameter information, and the second parameter information.

Images