Real-time monitoring method and device for surfacing of wear-resistant layer of blade, electronic equipment and storage medium

Abstract

The invention discloses a real-time monitoring method and device for surfacing of a blade wear-resistant layer, electronic equipment and a storage medium, the method and device are applied to the electronic equipment and used for monitoring the surfacing process of the blade wear-resistant layer in real time, and the scheme specifically comprises the steps that prediction processing is conducted according to the surfacing material technology of the blade in welding, and the blade wear-resistant layer surfacing is obtained. Obtaining a target surfacing model; collecting a surfacing image of the blade; constructing a blade three-dimensional model based on the blade three-dimensional coordinate points of the surfacing image; and monitoring the surfacing process of the blade according to a relationship between a difference value between the target surfacing model and the three-dimensional model of the blade and a preset threshold value. According to the scheme, surfacing is monitored in real time on the basis of the machine vision principle, the welding parameters can be adjusted in real time on the basis of the obtained monitoring result, real-time monitoring of robot welding can be met, and therefore the welding quality of the blade wear-resisting layer can be controlled according to the surfacing state.

Description

Technical Field

[0001] The present application relates to the field of welding technology, and more specifically, to a real-time monitoring method, device, electronic equipment and storage medium for blade wear-resistant layer surfacing. Background Art

[0002] Existing manual cladding techniques suffer from shortcomings such as uneven weld bead overlap, low welding efficiency, and poor bonding. Furthermore, these uneven welds can easily lead to quality issues such as false welds and cold welds. With the development of intelligent manufacturing, welding robots are gradually replacing manual welding due to their high precision and repeatability. However, the "eye-brain-hand" quality control method used in manual welding cannot meet the real-time and closed-loop control requirements of robots in automated welding, making it impossible to effectively control welding quality. Summary of the Invention

[0003] In view of this, the present application provides a real-time monitoring method, device, electronic device and storage medium for the surfacing of the blade wear-resistant layer, which is used to monitor the surfacing of the blade wear-resistant layer in real time so as to control the welding quality of the blade wear-resistant layer according to the state of the surfacing.

[0004] In order to achieve the above objectives, the following solutions are proposed:

[0005] A real-time monitoring method for surfacing welding of a blade wear-resistant layer is applied to an electronic device and is used to implement real-time monitoring of the surfacing welding process of the blade wear-resistant layer. The real-time monitoring method comprises the following steps:

[0006] Perform prediction processing based on the surfacing material process of the blade being welded to obtain a target surfacing model;

[0007] collecting a surfacing image of the blade;

[0008] Constructing a three-dimensional model of the blade based on the three-dimensional coordinate points of the blade in the surfacing image;

[0009] The surfacing process of the blade is monitored according to the relationship between the difference between the target surfacing model and the three-dimensional model of the blade and a preset threshold.

[0010] Optionally, the collecting of the surfacing image of the blade includes the steps of:

[0011] An industrial camera is used to collect the surfacing images of the blade under different camera parameters, and the surfacing images include a color image and a depth image.

[0012] Optionally, constructing a three-dimensional blade model based on the three-dimensional coordinate points of the blade in the surfacing image comprises the steps of:

[0013] Extracting a plurality of three-dimensional coordinate points based on the surfacing image and the camera parameters;

[0014] Model construction is performed based on the multiple three-dimensional coordinate points to obtain the three-dimensional model of the blade.

[0015] Optionally, monitoring the surfacing process of the blade according to the relationship between the difference between the target surfacing model and the three-dimensional model of the blade and a preset threshold value comprises the steps of:

[0016] Calculating a difference between the target surfacing model and the blade three-dimensional model;

[0017] comparing the difference with the preset threshold;

[0018] If the difference is less than the preset threshold, the blade is determined to be qualified;

[0019] If the difference is not less than the preset threshold, the parameters of the welding process are adjusted.

[0020] Optionally, the following steps are also included:

[0021] collecting a molten pool image of the blade;

[0022] extracting melt pool feature points from the melt pool image;

[0023] Whether the molten pool on the blade is within a normal operating range is determined based on the molten pool feature point pair.

[0024] Optionally, the extracting the melt pool feature points of the melt pool image comprises the steps of:

[0025] A region of interest is set by defining a molten pool width and a molten pool length, and an enhanced molten pool image is obtained by performing enhancement processing on the region of interest;

[0026] Extracting the enhanced molten pool image to obtain a head contour and a tail contour;

[0027] Combining the head contour and the tail contour to obtain an outer rectangular contour;

[0028] Feature extraction is performed based on the molten pool width, the molten pool length and the outer rectangular outline to obtain the molten pool feature points.

[0029] A real-time monitoring device for surfacing welding of a blade wear-resistant layer is applied to an electronic device and is used to implement real-time monitoring of the surfacing welding process of the blade wear-resistant layer. The real-time monitoring device includes:

[0030] A model prediction module is configured to perform prediction processing based on the surfacing material process of the blade being welded to obtain a target surfacing model;

[0031] A first acquisition module is configured to acquire an image of the surfacing of the blade;

[0032] a model building module configured to build a three-dimensional blade model based on the three-dimensional coordinate points of the blade in the surfacing image;

[0033] The monitoring execution module is configured to monitor the surfacing process of the blade according to the relationship between the difference between the target surfacing model and the three-dimensional model of the blade and a preset threshold.

[0034] Optionally, also include:

[0035] a second acquisition module, configured to acquire an image of the molten pool of the blade;

[0036] a feature extraction module, configured to extract melt pool feature points from the melt pool image;

[0037] The molten pool judgment module is configured to judge whether the molten pool on the blade is within a normal working range according to the molten pool feature point pair.

[0038] An electronic device comprising at least one processor and a memory connected to the processor, wherein:

[0039] The memory is used to store computer programs or instructions;

[0040] The processor is used to execute the computer program or instruction to enable the electronic device to implement the real-time monitoring method for blade wear-resistant layer surfacing as described above.

[0041] A computer-readable storage medium is applied to an electronic device, wherein the storage medium carries one or more computer programs, and the one or more computer programs can be executed by the electronic device, thereby enabling the electronic device to implement the real-time monitoring method of blade wear-resistant layer surfacing as described above.

[0042] As can be seen from the above technical solutions, the present application discloses a real-time monitoring method, device, electronic device and storage medium for the surfacing welding of the blade wear-resistant layer. The method and device are applied to electronic devices for real-time monitoring of the surfacing welding process of the blade wear-resistant layer. The solution specifically includes predicting and processing the surfacing material process of the blade being welded to obtain a target surfacing model; collecting a surfacing image of the blade; constructing a three-dimensional model of the blade based on the three-dimensional coordinate points of the blade in the surfacing image; and monitoring the surfacing welding process of the blade based on the relationship between the difference between the target surfacing model and the blade three-dimensional model and a preset threshold. The present solution monitors the surfacing welding in real time based on the principle of machine vision, and can adjust the welding parameters in real time based on the monitoring results obtained, which can meet the real-time monitoring of robot welding, and thus can control the welding quality of the blade wear-resistant layer according to the state of the surfacing welding. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0044] Figure 1 This is a flow chart of a real-time monitoring method for blade wear-resistant layer surfacing according to an embodiment of the present application;

[0045] Figure 2 This is a flow chart of another method for real-time monitoring of blade wear-resistant layer surfacing according to an embodiment of the present application;

[0046] Figure 3 This is a block diagram of a real-time monitoring device for blade wear-resistant layer surfacing according to an embodiment of the present application;

[0047] Figure 4 This is a block diagram of a real-time monitoring device for blade wear-resistant layer surfacing according to an embodiment of the present application;

[0048] Figure 5 This is a block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0049] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0050] This application is used to monitor the cladding and molten pool of blades such as aircraft engine blades, gas turbine blades, steam turbine blades, or water turbine blades in real time to ensure stable and qualified quality during the cladding process. Before monitoring the cladding of the blades, the base material of the blades is determined, the base material is cleaned, and an ultrasonic sensor and an industrial camera are set. The ultrasonic sensor is used to perform ultrasonic testing on the weld seam of the blade to determine whether there are cracks therein, and the industrial camera is used to capture images of the cladding and molten pool of the cladding.

[0051] Blade cleaning is mainly to clean the dust on the blade, the pits and bulges left after casting, so that the blade is in a flat and clean state. The cleaning requirements are to use wire brushes, polishing sheets and other processing products to remove debris on the blade surface. The flatness of the workpiece is less than 2mm.

[0052] The specific scheme for implementing the monitoring method in this application is as follows.

[0053] Figure 1 This is a flow chart of a real-time monitoring method for blade wear-resistant layer surfacing according to an embodiment of the present application.

[0054] like Figure 1 As shown, the real-time monitoring method for surfacing welding on the blade wear-resistant layer provided in this embodiment is applied to an electronic device, which can be understood as a computer, server or cloud platform with data computing and information processing capabilities. The real-time monitoring method includes the following steps:

[0055] S1. Predict the target surfacing model based on the surfacing material process of the blade.

[0056] Specifically, the target surfacing model is generated according to the surfacing base material of the blade and combined with a sequential thermal-mechanical coupling model.

[0057] The temperature field control method of the transient conduction process of the blade involved in this application can be expressed as:

[0058]

[0059] Among them, ρ is the material density; c is the material specific heat capacity; T is the temperature; k is the thermal conductivity coefficient; Q is the internal heat source density per unit volume; x, y, z are the coordinate components; t is the calculation time. Then, in solving the heat conduction process, it is necessary to give the initial temperature field, heat dissipation boundary conditions and heat input boundary conditions. Only the radiation heat dissipation of the component to the external environment is considered, and the radiation coefficient is q rad =0.2; the heat input boundary condition is determined by the heat source. Gaussian heat source is used to simulate welding heat input. The Gaussian heat source equation can be expressed as:

[0060]

[0061] Among them, qm is the maximum heat flux density at the center of the heat source; R is the effective heating radius of the heat source; r is the distance from a point on the heat source to the center of the heat source; after obtaining the corresponding temperature field results, the deformation and stress values ​​are simulated and calculated. In the calculation, the total strain increment dε of the material within the time increment step is calculated by the elastic strain increment dε e , plastic strain increment dε p and thermal strain increment dε T Composition can be expressed as:

[0062] dε=dε e +dε p +dε T ,

[0063] Therefore, the exponential notation of thermal stress can be expressed as:

[0064]

[0065] Where, ν is Poisson's ratio; E is elastic modulus; δ ij is the Kronecker function; ΔT is the temperature increment; ε kk , ε jj The strain component is used, the surfacing height is determined based on the length of the original blade, and the target surfacing model is determined by combining the heat source in the sequential thermal-mechanical coupling model.

[0066] S2. Collecting the surfacing image of the blade.

[0067] That is, an image obtained by photographing the butt welding position of the blade through an industrial camera is obtained, namely, a butt welding image, which includes a color image and a depth image.

[0068] Before data collection, the center point is determined and marked based on the blade's curvature and specifications. The blade is then moved and clamped based on the center point. Mobile clamping of the workpiece based on the center point of the workpiece involves emitting infrared light from the center point of the cladding equipment onto the workpiece, and then moving the workpiece so that its center point is aligned with the infrared irradiation point.

[0069] Specifically, a triangular approximation method is used to construct an inscribed polyhedron with a triangle as the basic shape. The position of each vertex of the polyhedron is used as the camera coordinate position, and the center of the sphere is used as the target point position of the camera to obtain the color image and depth map of the three-dimensional object under each camera perspective.

[0070] In addition, the present application also includes using ultrasonic equipment to perform ultrasonic testing on the surfacing parts. The ultrasonic images generated by the ultrasonic testing can enable users to find out whether there are cracks therein. If there are cracks, it indicates that the surfacing is unqualified. Otherwise, it at least indicates that there are no cracks.

[0071] S3. Construct a three-dimensional model of the blade based on the three-dimensional coordinate points of the blade in the surfacing image.

[0072] The specific process is:

[0073] First, multiple three-dimensional coordinate points are extracted based on the surfacing image and camera parameters.

[0074] Then, a model is constructed based on multiple three-dimensional coordinate points to obtain a three-dimensional model of the blade.

[0075] S4. Perform monitoring based on the target surfacing model and the blade three-dimensional model.

[0076] That is, whether the surfacing is qualified is judged based on the target surfacing model and the blade three-dimensional model obtained above.

[0077] The specific process is as follows:

[0078] First, the difference between the target surfacing model and the blade three-dimensional model is calculated.

[0079] Then, the obtained difference is compared with a preset threshold to determine whether the difference is less than the preset threshold. The preset threshold can be determined based on actual experimental observation results or the required accuracy of the workpiece.

[0080] Finally, determine whether the blade is qualified based on the comparison results.

[0081] If the difference is less than the preset threshold, the blade is judged to be qualified. If the difference is not less than the preset threshold, it indicates that the blade is unqualified. At this time, the parameters of the welding process are adjusted to ensure that the subsequent re-welding meets the requirements.

[0082] As can be seen from the above technical solution, this embodiment provides a real-time monitoring method for the surfacing welding of the blade wear-resistant layer. The method is applied to electronic equipment and is used to implement real-time monitoring of the surfacing welding process of the blade wear-resistant layer. The solution specifically includes predicting and processing the surfacing material process of the blade being welded to obtain a target surfacing model; collecting a surfacing image of the blade; constructing a three-dimensional model of the blade based on the three-dimensional coordinate points of the blade in the surfacing image; and monitoring the surfacing welding process of the blade based on the relationship between the difference between the target surfacing model and the blade three-dimensional model and a preset threshold. This solution monitors the surfacing welding in real time based on the principle of machine vision, and can adjust the welding parameters in real time based on the monitoring results obtained, which can meet the real-time monitoring of robot welding, thereby being able to control the welding quality of the blade wear-resistant layer according to the state of the surfacing welding.

[0083] In addition, in a specific embodiment of the present application, the following steps are also included: Figure 2 shown.

[0084] S5. Collect the melt pool image of the blade.

[0085] Specifically, a CMOS industrial camera with a lens and filter system was installed coaxially with the welding machine's end effector, positioned relative to the welding torch. The camera was positioned at a 40-degree angle to the welding plane, pointing diagonally downward toward the molten pool, and 20 cm from the center. The camera's exposure time was set to 150 μs and the exposure compensation to 10 dB using an industrial computer. This process captured images of the molten pool.

[0086] S6. Extracting melt pool feature points from the melt pool image.

[0087] The specific process is:

[0088] First, the molten pool width and length are defined, the region of interest is set, and the region is Gaussian filtered and enhanced using the Retinex algorithm to obtain the enhanced molten pool image.

[0089] The melt pool width is defined as the parallel distance from the leftmost point to the rightmost point, the melt pool length is defined as the vertical distance from the topmost point to the bottommost point, the aspect ratio is the ratio of the above two factors, and the trailing angle is the vertex of the triangle formed by the leftmost point, the rightmost point, and the bottommost point. The Retinex algorithm believes that the world is colorless and that the world seen by the human eye is the result of the interaction between light and matter. In other words, the image mapped to the human eye is related to the long wave (R), medium wave (G), and short wave (B) of light, as well as the reflective properties of the object. The reflective component of the object is calculated by estimating the ambient light illumination component. Specifically, the ambient light illumination component can be obtained by convolving the image seen by the human eye with Gaussian blur.

[0090] Then, the enhanced melt pool image is partitioned into light and dark areas and the bright area contour of the melt pool is extracted as the head contour, and the dark area contour is extracted as the tail contour.

[0091] Firstly, the OTSU adaptive threshold segmentation method is used to obtain the optimal segmentation threshold, and the area filter is used to filter out the noise. At this time, the head area is obtained by threshold segmentation; secondly, the horizontal line where the lowest point of the head area is located is used as the basis for light and dark partitioning, and the area is divided into bright area and dark area. The optimal segmentation threshold is used as the high threshold in the non-maximum suppression in the CANNY algorithm, and the low threshold is half of the high threshold; then, the contour extracted from the CANNY algorithm is extracted to the contour corresponding to the maximum length through the length filter, and then the dark area is subjected to a single OTSU segmentation to obtain the tail contour of the molten pool. The two areas with the largest area are obtained through the area filter, and the contours of the two parts are fitted respectively; finally, the contours of the two parts are mapped to the dark area through the position relationship.

[0092] Then, the head contour and the tail contour are combined to form a contour set, and the outer rectangular contour is generated using the minimum vertical rectangle fitting method based on the contour set;

[0093] Finally, feature points are extracted based on the outer rectangular contour and the molten pool width and length to obtain the molten pool feature points.

[0094] S7. Determine whether the molten pool is normal based on the molten pool characteristic points.

[0095] When the weld pool is functioning properly, its characteristic points will be distributed in a normal state. This distribution allows us to determine whether the weld pool is within its normal operating range. If it is not, the welding parameters should be adjusted to bring the weld pool within normal operating range. This normal distribution can be constructed based on samples collected during a normal welding process.

[0096] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0097] Although the operations are depicted in a particular order, this should not be understood as requiring that the operations be performed in the particular order shown or in a sequential order.Multitasking and parallel processing may be advantageous under certain circumstances.

[0098] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0099] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages, or a combination thereof, including, but not limited to, object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as C or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer.

[0100] Figure 3 This is a block diagram of a real-time monitoring device for blade wear-resistant layer surfacing according to an embodiment of the present application.

[0101] like Figure 3 As shown, the device for real-time monitoring of the surfacing welding on the wear-resistant layer of a blade provided in this embodiment is applied to an electronic device, which can be understood as a computer, server, or cloud platform with data computing and information processing capabilities. The real-time monitoring device includes a model prediction module 10, a first acquisition module 20, a model construction module 30, and a monitoring execution module 40.

[0102] The model prediction module is used to predict the target surfacing model according to the surfacing material process of the blade.

[0103] Specifically, the target surfacing model is generated according to the surfacing base material of the blade and combined with a sequential thermal-mechanical coupling model.

[0104] The temperature field control method of the transient conduction process of the blade involved in this application can be expressed as:

[0105]

[0106] Among them, ρ is the material density; c is the material specific heat capacity; T is the temperature; k is the thermal conductivity coefficient; Q is the internal heat source density per unit volume; x, y, z are the coordinate components; t is the calculation time. Then, in solving the heat conduction process, it is necessary to give the initial temperature field, heat dissipation boundary conditions and heat input boundary conditions. Only the radiation heat dissipation of the component to the external environment is considered, and the radiation coefficient is q rad =0.2; the heat input boundary condition is determined by the heat source. Gaussian heat source is used to simulate welding heat input. The Gaussian heat source equation can be expressed as:

[0107]

[0108] Among them, q mis the maximum heat flux density at the center of the heat source; R is the effective heating radius of the heat source; r is the distance from a point on the heat source to the center of the heat source; after obtaining the corresponding temperature field results, the deformation and stress values ​​are simulated and calculated. In the calculation, the total strain increment dε of the material within the time increment step is calculated by the elastic strain increment dε e , plastic strain increment dε p and thermal strain increment dε T Composition can be expressed as:

[0109] dε=dε e +dε p +dε T ,

[0110] Therefore, the exponential notation of thermal stress can be expressed as:

[0111]

[0112] Where, ν is Poisson's ratio; E is elastic modulus; δ ij is the Kronecker function; ΔT is the temperature increment; ε kk , ε jj The strain component is used, the surfacing height is determined based on the length of the original blade, and the target surfacing model is determined by combining the heat source in the sequential thermal-mechanical coupling model.

[0113] The first acquisition module is used to acquire the surfacing image of the blade.

[0114] That is, an image obtained by photographing the butt welding position of the blade through an industrial camera is obtained, namely, a butt welding image, which includes a color image and a depth image.

[0115] Before data collection, the center point is determined and marked based on the blade's curvature and specifications. The blade is then moved and clamped based on the center point. Mobile clamping of the workpiece based on the center point of the workpiece involves emitting infrared light from the center point of the cladding equipment onto the workpiece, and then moving the workpiece so that its center point is aligned with the infrared irradiation point.

[0116] Specifically, a triangular approximation method is used to construct an inscribed polyhedron with a triangle as the basic shape. The position of each vertex of the polyhedron is used as the camera coordinate position, and the center of the sphere is used as the target point position of the camera to obtain the color image and depth map of the three-dimensional object under each camera perspective.

[0117] In addition, the present application also includes using ultrasonic equipment to perform ultrasonic testing on the surfacing parts. The ultrasonic images generated by the ultrasonic testing can enable users to find out whether there are cracks therein. If there are cracks, it indicates that the surfacing is unqualified. Otherwise, it at least indicates that there are no cracks.

[0118] The model building module is used to build a three-dimensional model of the blade based on the three-dimensional coordinate points of the blade in the surfacing image.

[0119] The specific process is:

[0120] First, multiple three-dimensional coordinate points are extracted based on the surfacing image and camera parameters.

[0121] Then, a model is constructed based on multiple three-dimensional coordinate points to obtain a three-dimensional model of the blade.

[0122] The monitoring execution module is used to perform monitoring according to the target surfacing model and the blade three-dimensional model.

[0123] That is, whether the surfacing is qualified is judged based on the target surfacing model and the blade three-dimensional model obtained above.

[0124] The specific process is as follows:

[0125] First, the difference between the target surfacing model and the blade three-dimensional model is calculated.

[0126] Then, the obtained difference is compared with a preset threshold to determine whether the difference is less than the preset threshold. The preset threshold can be determined based on actual experimental observation results or the required accuracy of the workpiece.

[0127] Finally, determine whether the blade is qualified based on the comparison results.

[0128] If the difference is less than the preset threshold, the blade is judged to be qualified. If the difference is not less than the preset threshold, it indicates that the blade is unqualified. At this time, the parameters of the welding process are adjusted to ensure that the subsequent re-welding meets the requirements.

[0129] As can be seen from the above technical solution, this embodiment provides a real-time monitoring device for the surfacing welding of the blade wear-resistant layer. The device is applied to electronic equipment and is used to implement real-time monitoring of the surfacing welding process of the blade wear-resistant layer. The solution specifically includes predicting and processing the surfacing material process of the blade being welded to obtain a target surfacing model; collecting a surfacing image of the blade; constructing a three-dimensional model of the blade based on the three-dimensional coordinate points of the blade in the surfacing image; and monitoring the surfacing welding process of the blade based on the relationship between the difference between the target surfacing model and the blade three-dimensional model and a preset threshold. This solution monitors the surfacing welding in real time based on the principle of machine vision, and can adjust the welding parameters in real time based on the monitoring results obtained, which can meet the real-time monitoring of robot welding, thereby being able to control the welding quality of the blade wear-resistant layer according to the state of the surfacing welding.

[0130] In addition, in a specific embodiment of the present application, a second acquisition module 50, a feature extraction module 60 and a molten pool judgment module 70 are also included. Figure 4 shown.

[0131] The second acquisition module is used to acquire the melt pool image of the blade.

[0132] Specifically, a CMOS industrial camera with a lens and filter system was installed coaxially with the welding machine's end effector, positioned relative to the welding torch. The camera was positioned at a 40-degree angle to the welding plane, pointing diagonally downward toward the molten pool, and 20 cm from the center. The camera's exposure time was set to 150 μs and the exposure compensation to 10 dB using an industrial computer. This process captured images of the molten pool.

[0133] The feature extraction module is used to extract the melt pool feature points of the melt pool image.

[0134] The specific process is:

[0135] First, the molten pool width and length are defined, the region of interest is set, and the region is Gaussian filtered and enhanced using the Retinex algorithm to obtain the enhanced molten pool image.

[0136] The melt pool width is defined as the parallel distance from the leftmost point to the rightmost point, the melt pool length is defined as the vertical distance from the topmost point to the bottommost point, the aspect ratio is the ratio of the above two factors, and the trailing angle is the vertex of the triangle formed by the leftmost point, the rightmost point, and the bottommost point. The Retinex algorithm believes that the world is colorless and that the world seen by the human eye is the result of the interaction between light and matter. In other words, the image mapped to the human eye is related to the long wave (R), medium wave (G), and short wave (B) of light, as well as the reflective properties of the object. The reflective component of the object is calculated by estimating the ambient light illumination component. Specifically, the ambient light illumination component can be obtained by convolving the image seen by the human eye with Gaussian blur.

[0137] Then, the enhanced melt pool image is partitioned into light and dark areas and the bright area contour of the melt pool is extracted as the head contour, and the dark area contour is extracted as the tail contour.

[0138] Firstly, the OTSU adaptive threshold segmentation method is used to obtain the optimal segmentation threshold, and the area filter is used to filter out the noise. At this time, the head area is obtained by threshold segmentation; secondly, the horizontal line where the lowest point of the head area is located is used as the basis for light and dark partitioning, and the area is divided into bright area and dark area. The optimal segmentation threshold is used as the high threshold in the non-maximum suppression in the CANNY algorithm, and the low threshold is half of the high threshold; then, the contour extracted from the CANNY algorithm is extracted to the contour corresponding to the maximum length through the length filter, and then the dark area is subjected to a single OTSU segmentation to obtain the tail contour of the molten pool. The two areas with the largest area are obtained through the area filter, and the contours of the two parts are fitted respectively; finally, the contours of the two parts are mapped to the dark area through the position relationship.

[0139] Then, the head contour and the tail contour are combined to form a contour set, and the outer rectangular contour is generated using the minimum vertical rectangle fitting method based on the contour set;

[0140] Finally, feature points are extracted based on the outer rectangular contour and the molten pool width and length to obtain the molten pool feature points.

[0141] The monitoring execution module is used to determine whether the molten pool is normal based on the molten pool feature points.

[0142] When the weld pool is functioning properly, its characteristic points will be distributed in a normal state. This distribution allows us to determine whether the weld pool is within its normal operating range. If it is not, the welding parameters should be adjusted to bring the weld pool within normal operating range. This normal distribution can be constructed based on samples collected during a normal welding process.

[0143] The units involved in the embodiments described in this disclosure may be implemented in software or hardware. In some cases, the name of a unit does not limit the unit itself. For example, the first acquisition unit may also be described as a "unit for acquiring at least two Internet Protocol addresses."

[0144] The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, and without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chip (SOCs), complex programmable logic devices (CPLDs), and the like.

[0145] Figure 5 This is a block diagram of an electronic device according to an embodiment of the present application.

[0146] Reference below Figure 5 , which shows a schematic diagram of the structure of an electronic device suitable for implementing the embodiments of the present disclosure. The terminal device in the embodiments of the present disclosure may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (such as in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. This electronic device is merely an example and should not limit the functionality and scope of use of the embodiments of the present disclosure.

[0147] The electronic device may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory ROM 502 or a program loaded from an input device 506 into a random access memory RAM 503. Various programs and data required for the operation of the electronic device are also stored in the RAM. The processing device, ROM, and RAM are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0148] Typically, the following devices may be connected to the I / O interface: input devices such as a touch screen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; output devices 507 such as a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 508 such as a magnetic tape, hard disk, etc.; and communication devices 509. Communication devices 509 may allow the electronic device to communicate with other devices wirelessly or by wire to exchange data. Although the figures illustrate electronic devices with various devices, it should be understood that not all of the devices shown are required to be implemented or present. More or fewer devices may be implemented or present instead.

[0149] The present application also provides a computer-readable storage medium embodiment.

[0150] The computer-readable storage medium is applied to an electronic device and carries one or more computer programs. When the one or more computer programs are executed by the electronic device, the electronic device performs real-time monitoring of the surfacing process of the blade wear-resistant layer. Specifically, the solution includes predicting and processing the surfacing material process of the blade being welded to obtain a target surfacing model; collecting a surfacing image of the blade; constructing a three-dimensional model of the blade based on the three-dimensional coordinate points of the blade in the surfacing image; and monitoring the surfacing process of the blade based on the relationship between the difference between the target surfacing model and the blade three-dimensional model and a preset threshold. This solution monitors surfacing in real time based on the principle of machine vision and can adjust welding parameters in real time based on the monitoring results obtained. It can meet the real-time monitoring requirements of robot welding, and thus can control the welding quality of the blade wear-resistant layer according to the state of surfacing.

[0151] It should be noted that the computer-readable medium disclosed herein may be a computer-readable signal medium or a computer-readable storage medium or any combination thereof. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or component, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection with one or more wires, 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 thereof.

[0152] In the present disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.

[0153] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0154] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they become aware of the basic creative concepts. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention.

[0155] Finally, it should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that includes a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or terminal device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or terminal device that includes the element.

[0156] The technical solution provided by the present invention is introduced in detail above. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A real-time monitoring method for blade wear-resistant layer surfacing, applied to electronic equipment, for implementing real-time monitoring of the surfacing process of the blade wear-resistant layer, characterized in that: The real-time monitoring method comprises the steps of: Perform prediction processing based on the surfacing material process of the blade being welded to obtain a target surfacing model; collecting a surfacing image of the blade; Constructing a three-dimensional model of the blade based on the three-dimensional coordinate points of the blade in the surfacing image; The surfacing process of the blade is monitored according to the relationship between the difference between the target surfacing model and the three-dimensional model of the blade and a preset threshold.

2. The real-time monitoring method according to claim 1, wherein: The collecting of the surfacing image of the blade comprises the steps of: An industrial camera is used to collect the surfacing images of the blade under different camera parameters, and the surfacing images include a color image and a depth image.

3. The real-time monitoring method according to claim 3, wherein: The method of constructing a three-dimensional blade model based on the three-dimensional coordinate points of the blade in the surfacing image comprises the following steps: Extracting a plurality of three-dimensional coordinate points based on the surfacing image and the camera parameters; Model construction is performed based on the multiple three-dimensional coordinate points to obtain the three-dimensional model of the blade.

4. The real-time monitoring method according to claim 1, wherein: The method of monitoring the blade surfacing process according to the relationship between the difference between the target surfacing model and the blade three-dimensional model and a preset threshold value comprises the following steps: Calculating a difference between the target surfacing model and the blade three-dimensional model; comparing the difference with the preset threshold; If the difference is less than the preset threshold, the blade is determined to be qualified; If the difference is not less than the preset threshold, the parameters of the welding process are adjusted.

5. The real-time monitoring method according to any one of claims 1 to 4, characterized in that: Also includes the steps: collecting a molten pool image of the blade; extracting melt pool feature points from the melt pool image; Whether the molten pool on the blade is within a normal operating range is determined based on the molten pool feature point pair.

6. The real-time monitoring method according to claim 5, wherein: The step of extracting the melt pool feature points from the melt pool image comprises the following steps: A region of interest is set by defining a molten pool width and a molten pool length, and an enhanced molten pool image is obtained by performing enhancement processing on the region of interest; Extracting the enhanced molten pool image to obtain a head contour and a tail contour; Combining the head contour and the tail contour to obtain an outer rectangular contour; Feature extraction is performed based on the molten pool width, the molten pool length and the outer rectangular outline to obtain the molten pool feature points.

7. A real-time monitoring device for blade wear-resistant layer surfacing, applied to electronic equipment, for real-time monitoring of the surfacing process of the blade wear-resistant layer, characterized in that: The real-time monitoring device comprises: A model prediction module is configured to perform prediction processing based on the surfacing material process of the blade being welded to obtain a target surfacing model; A first acquisition module is configured to acquire an image of the surfacing of the blade; a model building module configured to build a three-dimensional blade model based on the three-dimensional coordinate points of the blade in the surfacing image; The monitoring execution module is configured to monitor the surfacing process of the blade according to the relationship between the difference between the target surfacing model and the three-dimensional model of the blade and a preset threshold.

8. The real-time monitoring device according to claim 7, wherein: Also includes: a second acquisition module, configured to acquire an image of the molten pool of the blade; a feature extraction module, configured to extract melt pool feature points from the melt pool image; The molten pool judgment module is configured to judge whether the molten pool on the blade is within a normal working range according to the molten pool feature point pair.

9. An electronic device, characterized in that: The electronic device comprises at least one processor and a memory connected to the processor, wherein: The memory is used to store computer programs or instructions; The processor is used to execute the computer program or instruction, so that the electronic device can implement the real-time monitoring method for blade wear-resistant layer surfacing according to any one of claims 1 to 6.

10. A computer-readable storage medium, applied to an electronic device, characterized in that: The storage medium carries one or more computer programs, and the one or more computer programs can be executed by the electronic device, so that the electronic device can implement the real-time monitoring method of blade wear-resistant layer surfacing according to any one of claims 1 to 6.

Images