Composite sliding bearing laser cladding method and system based on image processing

Abstract

The invention provides a composite sliding bearing laser cladding method and system based on image processing, and relates to the technical field of image processing.The method comprises the steps that a surface image of a composite sliding bearing is collected; performing high-definition reconstruction on the surface image; performing cladding path planning in the reconstructed surface image; constructing a heat conduction model for describing metal heating temperature distribution in the laser cladding process; establishing a description model of the isotherm position changing along with the laser power by combining the heat conduction model; linearizing and discretizing the description model at an expected control point; establishing a state feedback controller with a steady-state error compensation item based on the discrete state space equation; laser cladding is conducted on the composite sliding bearing along the cladding path, and the real-time cladding temperature of a molten pool is collected; and according to the real-time cladding temperature, the heat conduction model and the state feedback controller are combined, target laser power is output, and cladding is conducted on the composite sliding bearing according to the target laser power. And the cladding uniformity and the cladding efficiency are improved.

Description

Technical Field

[0001] The invention relates to the technical field of image processing, and in particular to a composite sliding bearing laser cladding method and system based on image processing. Background Art

[0002] Composite sliding bearing laser cladding is a process method that uses laser technology to apply a covering layer on the surface of a sliding bearing. A specific material (usually metal powder or other wear-resistant material) is melted by a laser beam and then evenly coated on the surface of the bearing. This can form a hard protective layer to enhance the wear resistance and corrosion resistance of the bearing.

[0003] Laser cladding of composite sliding bearings is extremely necessary because this method can significantly improve the durability and performance of bearings. In high-load and high-friction working environments, bearing surfaces that have not been clad are prone to wear and damage, which greatly shortens the service life of bearings. Through laser cladding, not only can the worn bearing surface be repaired, but also similar wear can be prevented in the future operation of new bearings, thereby ensuring the continued reliable operation of mechanical equipment and reducing maintenance costs and downtime. In addition, this high-precision cladding technology allows precise control of the thickness and quality of the covering layer, ensuring the consistency and repeatability of processing quality.

[0004] However, the existing laser cladding process for sliding bearings often treats the bearing surface as a plane with the same properties and performs uniform cladding without considering the defects and cladding areas on the bearing surface. It is very easy to cause defect cladding or repeated cladding to damage the bearing surface properties during the cladding process, resulting in reduced cladding quality. In addition, using a fixed laser power during the cladding process cannot cope with the differences in the properties of the bearing surface, and thus cannot ensure the cladding consistency and uniformity of the bearing surface. Summary of the invention

[0005] In order to solve the problem that the laser cladding process of sliding bearings in the prior art often regards the bearing surface as a plane with the same properties and performs uniform cladding, without considering the defects and clad areas on the bearing surface, which can easily cause defect cladding or repeated cladding to damage the bearing surface properties during the cladding process, resulting in reduced cladding quality. In addition, the use of a fixed laser power during the cladding process cannot cope with the differences in the properties of the bearing surface, and thus cannot ensure the cladding consistency and uniformity of the bearing surface, the present invention provides a composite sliding bearing laser cladding method and system based on image processing.

[0006] The technical solution provided by the embodiment of the present invention is as follows:

[0007] First aspect

[0008] An embodiment of the present invention provides a composite sliding bearing laser cladding method based on image processing, comprising:

[0009] S1: collecting a surface image of the composite sliding bearing;

[0010] S2: reconstructing the surface image in high definition by using a bicubic interpolation algorithm;

[0011] S3: Cladding path planning in the reconstructed surface image;

[0012] S4: Based on the composite sliding bearing property parameters and ambient temperature, a heat conduction model describing the temperature distribution of metal during laser cladding is constructed;

[0013] S5: establishing a description model of the change of the isothermal line position with the laser power in combination with the heat conduction model;

[0014] S6: linearizing and discretizing the description model at the desired control point to obtain a discrete state space equation;

[0015] S7: establishing a state feedback controller with a steady-state error compensation term based on the discrete state space equation, wherein the input of the state feedback controller is the isotherm position and the output is the laser power;

[0016] S8: performing laser cladding on the composite sliding bearing along the cladding path, and collecting the real-time cladding temperature of the molten pool;

[0017] S9: Outputting a target laser power according to the real-time cladding temperature in combination with the heat conduction model and the state feedback controller, and cladding the composite sliding bearing according to the target laser power.

[0018] Second aspect

[0019] An embodiment of the present invention provides a composite sliding bearing laser cladding system based on image processing, comprising:

[0020] processor;

[0021] A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the composite sliding bearing laser cladding method based on image processing as described in the first aspect is implemented.

[0022] The third aspect

[0023] An embodiment of the present invention provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the composite sliding bearing laser cladding method based on image processing as described in the first aspect is implemented.

[0024] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0025] In the present invention, the surface image is reconstructed in high definition based on the bicubic interpolation algorithm and an accurate cladding path is planned, which provides an image basis for the subsequent accurate adjustment of the laser frequency. It can also effectively avoid the cladding area and the defect area, avoid the cladding process covering the defect area to cause potential safety hazards, improve the cladding quality, and perform detailed path planning for the uncladding area to improve the cladding efficiency and cladding quality. In view of the inconsistency of the bearing surface, a heat conduction model and a description model of the change of the isothermal line position with the laser power are established successively, and then they are linearized and discretized to obtain a discrete state space equation, so as to control the laser frequency in the linear space. Based on the discrete state space equation, a state feedback controller with a steady-state error compensation term is established to improve the accuracy of laser frequency control. The laser frequency can be adjusted according to the real-time temperature feedback data of the molten pool to control the stability of the molten pool state, thereby avoiding damage to the material properties due to uneven heating or overheating, ensuring the structural integrity and quality of the cladding layer, and the laser frequency can be quickly adjusted according to the difference in the properties of the bearing surface, thereby ensuring the stability and consistency of the cladding process and the uniformity of the cladding surface, and further improving the cladding quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0027] Figure 1 A schematic flow chart of a composite sliding bearing laser cladding method based on image processing provided in an embodiment of the present invention;

[0028] Figure 2 A schematic structural diagram of a composite sliding bearing laser cladding system based on image processing provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0029] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0030] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "example" is intended to present the concept in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either of the two.

[0031] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same. "of", "corresponding, relevant" and "corresponding" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same.

[0032] In the embodiments of the present invention, sometimes a subscript such as W1 may be mistakenly written as a non-subscript such as W1. When the difference is not emphasized, the meanings to be expressed are consistent.

[0033] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0034] Reference Manual Attached Figure 1 , showing a schematic flow chart of a composite sliding bearing laser cladding method based on image processing provided in an embodiment of the present invention.

[0035] The embodiment of the present invention provides a composite sliding bearing laser cladding method based on image processing, which can be implemented by a composite sliding bearing laser cladding device based on image processing, and the composite sliding bearing laser cladding device based on image processing can be a terminal or a server. The processing flow of the composite sliding bearing laser cladding method based on image processing may include the following steps:

[0036] S1: Acquisition of surface images of composite sliding bearings.

[0037] The surface image is a clad composite sliding bearing surface image or an unclad composite sliding bearing surface image. By analyzing the image, the cladding path and repair needs can be determined to ensure the accuracy and efficiency of the cladding process. This image acquisition provides the necessary visual information for subsequent image processing, path planning and quality control.

[0038] S2: High-definition reconstruction of surface images using the bicubic interpolation algorithm.

[0039] Among them, the bicubic interpolation algorithm is a widely used technique in digital image processing for image scaling and other image reconstruction tasks. It uses a cubic polynomial to interpolate the values ​​of 16 neighboring pixels, thereby providing smoother gradients when zooming in or out of the image. The bicubic interpolation algorithm uses a cubic polynomial function to predict the value of the target pixel based on the surrounding 16 pixels (4x4 neighborhood) by calculating weights in the x and y directions respectively. It not only considers the nearest four pixels, but also the neighbors of these pixels, making the interpolation result more accurate and smooth. Using the bicubic interpolation algorithm for high-definition reconstruction of surface images can greatly improve image quality, especially when the image is enlarged, it can effectively reduce aliasing and blurring, maintain edge clarity and detail integrity. In addition, the smooth gradient provided by the bicubic interpolation makes the reconstructed image more natural and realistic visually, which is crucial for subsequent laser cladding path planning and quality control, because clear images can more accurately identify areas that need to be clad or repaired.

[0040] In a possible implementation manner, S2 is specifically:

[0041] All pixels in the surface image are interpolated using the bicubic interpolation algorithm to obtain the reconstructed surface image:

[0042]

[0043] Where t represents the distance between the interpolation point (x′, y′) and the known sampling point, i.e., the pixel point of the expanded surface image, f(t) represents the distance kernel function, I′(x′, y′) represents the pixel value of the interpolation point after interpolation, (x, y) represents the coordinates of the upper left corner pixel closest to the interpolation point in the expanded surface image, i and j represent the distances to the interpolation point in the x and y directions, respectively, and I(x+i, y+j) represents the pixel value of the neighboring pixel point (x+i, y+j).

[0044] It should be noted that by interpolating all pixels of the surface image using the bicubic interpolation algorithm, the reconstructed surface image obtained will have higher resolution and finer details.

[0045] S3: Cladding path planning is performed in the reconstructed surface image.

[0046] It should be noted that the advantage of cladding path planning for the reconstructed surface image is that it allows precise control of the laser cladding process. Through high-precision path planning, it can ensure that the cladding material is accurately applied to the area that needs to be enhanced or repaired, effectively avoiding repeated cladding and damage to the clad area, while marking the defect location for subsequent manual repair. Such path planning not only improves cladding efficiency and quality, but also reduces material waste and minimizes potential safety hazards during the cladding process.

[0047] In a possible implementation, the cladding path planning is performed in the reconstructed surface image by using the A-star algorithm.

[0048] S3 specifically includes:

[0049] S301: Locate defect points and cladding areas in the reconstructed surface image.

[0050] S302: Determine the cladding start point and the cladding end point, and use the defect point and the cladding area as obstacles, and define the obstacle cost as positive infinity.

[0051] S303: Define the heuristic cost describing the distance from the current node to the cladding end point:

[0052]

[0053] Among them, h(n) represents the heuristic cost from the current node n to the cladding end point, (x n ,y n ),(x G ,y G ) represent the current node coordinates and the cladding end point coordinates respectively.

[0054] S304: Determine the total cost of the current node by combining the heuristic cost and the path cost of the current node:

[0055] φ(n)=g(n)+h(n)

[0056] Among them, φ(n) represents the total cost of the current node, and g(n) represents the path cost from the cladding starting point to the current node.

[0057] The path cost refers to the actual cumulative path cost from the starting point to a node. Each time you move from one node to another, the distance cost is added to the path cost.

[0058] S305: Calculate the total cost of each point in the reconstructed surface image, and use the point with the minimum total cost as the path point until the cladding end point is searched, wherein the cladding start point, the path point and the cladding end point are sequentially connected to obtain a cladding path.

[0059] Specifically, the process of cladding path planning in the reconstructed surface image through the A-star algorithm is meticulous and efficient, ensuring the maximum accuracy and efficiency of the laser cladding process. First, by locating the defect points and cladding areas in the image, these areas are used as obstacles in path planning to ensure that the new cladding path avoids these problem areas, thereby optimizing the repair effect and cladding quality. Then, the algorithm accurately plans a cladding path with the lowest cost by comprehensively considering the path cost and heuristic cost to reach each node. This method not only significantly improves the cladding efficiency, but also avoids repeated cladding, reduces material waste, and effectively controls the accuracy of the cladding process, ultimately achieving high-quality cladding effects. In addition, by calculating the total cost of each node in real time and selecting the optimal path, the A-star algorithm ensures the optimality of path planning and improves the systematicity and predictability of the entire cladding process.

[0060] S4: Based on the composite sliding bearing property parameters and ambient temperature, a heat conduction model describing the temperature distribution of metal during laser cladding is constructed.

[0061] It should be noted that based on the specific physical properties of the composite sliding bearing (such as thermal conductivity, density and specific heat capacity) and ambient temperature parameters, a heat conduction model describing the temperature distribution of the metal during the laser cladding process is constructed, which can accurately predict the temperature changes in the cladding area and the surrounding area, help adjust and optimize the laser cladding parameters, and ensure that the temperature of the material is controlled within the optimal range during the cladding process, thereby avoiding damage to the material properties due to uneven heating or overheating, and ensuring the structural integrity and quality of the cladding layer. This model is crucial to achieving high-quality laser cladding and can effectively guide the optimization and control strategy of the cladding process.

[0062] In a possible implementation manner, the composite sliding bearing property parameters include laser energy absorption coefficient, thermal conductivity, density and specific heat capacity.

[0063] The specific heat conduction model is:

[0064]

[0065] Where T represents the temperature of the target point o, T a represents the ambient temperature, A represents the laser energy absorption coefficient, P represents the laser power, k represents the thermal conductivity, r o represents the radial distance between the target point o and the laser point, (ξ,η) represents the spatial coordinates of the target point, ξ represents the coordinate along the laser scanning direction, η represents the coordinate perpendicular to the laser scanning direction, L represents the characteristic length of the heat affected zone, α represents the thermal diffusion coefficient, ρ represents the density, and C p represents specific heat capacity, U represents the scanning speed of the laser head, exp represents exponential function, and π represents pi.

[0066] The characteristic length specifically refers to the length range of heat conduction in the material. If the laser scanning speed is too fast, the heat will not have enough time to diffuse fully, resulting in a reduced characteristic length and a smaller heat-affected zone. During the laser cladding process, the characteristic length of the heat-affected zone determines the spatial range of heat diffusion in the material and depends on the thermal properties of the material and the scanning speed of the laser.

[0067] Among them, the heat conduction model combines the key attribute parameters of the composite sliding bearing, such as laser energy absorption coefficient, thermal conductivity, density and specific heat capacity, which are crucial to predicting and controlling the temperature distribution of the metal during the laser cladding process. With this detailed model, the thermal effect at different laser powers can be accurately calculated, and the cladding parameters can be optimized to achieve the ideal heat treatment effect. Such a model helps to ensure that the cladding layer has a uniform microstructure and superior mechanical properties, prevent defects such as cracks or thermal stress concentration during the cladding process, and significantly improve the overall quality and life of the cladding parts. In addition, precise temperature control can also reduce material waste and improve the economy and efficiency of the cladding process.

[0068] S5: Combined with the heat conduction model, a descriptive model is established to describe the change of isothermal line position with laser power.

[0069] It should be noted that the established heat conduction model is used to develop a descriptive model that can show the change in the position of the isotherms when the laser power changes, which can help understand how the laser power affects the temperature distribution in the cladding area, thereby making the laser cladding process more accurate and controllable. Through a deep understanding of the relationship between laser power and the position of the isotherms, the laser cladding parameters can be optimized to ensure the cladding quality, avoid the generation of thermal stress and structural defects, and improve the overall performance and life of the product.

[0070] In a possible implementation, the description model is specifically:

[0071]

[0072] T i =T a +(N-i+1)ΔT

[0073] S=2L / U

[0074] Among them, η i represents the isotherm position of the ith isotherm, N represents the total number of isotherms, T i represents the temperature value corresponding to the i-th isotherm, and They represent the isotherm position change rates of the 1st isotherm, the ith isotherm and the Nth isotherm respectively, e represents a natural constant, ΔT represents the isotherm temperature difference, S represents a time constant reflecting the coupling relationship between thermal diffusion in space and time, and T1 represents the laser temperature peak.

[0075] The time constant reflects the coupling relationship between thermal diffusion in space and time. The total number of isotherms can be customized, but it needs to be determined in combination with the laser temperature peak. Optionally, a larger N value means a finer temperature division, a smaller temperature difference ΔT between each isotherm, and higher control accuracy, but the calculation complexity will also increase. When the isotherm temperature difference is determined, the total number of isotherms is calculated as follows: Melting temperature T of composite sliding bearing m The corresponding isotherm number m is calculated by solving the equation T m =T a +(N-m+1)ΔT.

[0076] It should be noted that the laser cladding process has been significantly improved in terms of accuracy and efficiency by using a model that accurately describes the changes in the position of isotherms. The model allows the operator to adjust the laser power according to the real-time cladding temperature to ensure that the cladding layer is formed at the optimal temperature and avoid cladding defects such as cracks and holes. By setting different isotherms and corresponding temperature values, the temperature distribution can be more finely controlled to optimize the microstructure and mechanical properties of the material. In addition, the ability to customize the number and temperature difference of isotherms provides greater control flexibility and accuracy, making the cladding process more predictable and controllable, greatly improving the cladding quality and the performance of the composite sliding bearing. This model is particularly suitable for laser cladding applications with complex shapes or high performance requirements because it allows the process parameters to be adjusted according to specific needs and material properties.

[0077] S6: Linearize and discretize the description model at the desired control points to obtain the discrete state space equations.

[0078] It should be noted that the model is linearized and discretized at a specific control point (expected control point) to obtain a discrete state space equation. This step is to simplify the complexity of the model and convert the continuous dynamic process into an easy-to-handle discrete form, so as to facilitate accurate numerical calculation and control system design. Through this linearization and discretization process, the dynamic changes of the isothermal position during the laser cladding process can be more accurately simulated and predicted, so that the control of the laser cladding process is more accurate and effective, ensuring the cladding quality and efficiency.

[0079] In a possible implementation, S6 specifically includes:

[0080] S601: Discretize the isotherm position into a linear state vector and rewrite the description model into a state space equation:

[0081]

[0082] in, represents the state space equation, f represents the value function describing the rate of change of the isotherm position, x represents the state vector, represents the rate of change of the state vector, and u represents the control input of the laser power.

[0083] Among them, f represents the value function describing the rate of change of the isotherm position, that is, and It contains the dynamic relationship of the system. In other words, f contains how the position of the isotherm changes with the laser power u and the current state x.

[0084] S602: The state space equation is linearized at the desired control point through the Jacobian matrix to obtain a discrete state space equation, wherein the desired control point is the desired molten pool width, i.e., the coordinate perpendicular to the laser scanning direction and the corresponding desired laser power:

[0085] x n+1 =A d x n +B d u n

[0086] A d =exp(A c T s )

[0087]

[0088] 0=f(x0,u0)

[0089]

[0090]

[0091] Among them, x n+1 =A d x n +B d u n represents the discrete state space equation, (x0,u0) represents the desired control point including the desired molten pool width x0 and the desired laser frequency u0, n represents the discrete time index, T s Indicates the preset sampling time, x n+1 represents the state vector at time n+1, x n ,u n Represent the state vector and control input at time n, Ad ,B d denote the discrete-time state transfer matrix and discrete-time control input matrix, A c ,B c They represent the state transfer matrix and control input matrix before discretization, Indicates finding the i-th state f at the desired control point (x0,u0) i For the jth state variable x j The partial guide, Indicates finding the i-th state f i The partial derivative of the control input u.

[0092] The discrete-time state transfer matrix describes how the system state changes from time n to time n+1 without considering the external input u, which reflects the internal dynamic characteristics of the system. The discrete-time control input matrix describes the influence of the control input on the change of the system state, which reflects how the control input (such as laser power) acts on the system at the current time n, thereby affecting the state at the next time n+1.

[0093] It should be noted that those skilled in the art can set the size of the preset sampling time according to actual needs, and the present invention is not limited here. Specifically, during the laser cladding process, the width of the molten pool will change over time, especially when parameters such as laser power and scanning speed change, the molten pool width will increase or decrease, and the growth rate of the molten pool width refers to the rate of change of the molten pool width per unit time. The faster the growth rate of the molten pool, the more frequently the system needs to collect data and adjust the control input (such as laser power) to ensure that the molten pool width always remains within the target range. If the molten pool width changes very quickly, the control system must sample and adjust frequently to ensure that it can respond to changes in width in a timely manner. Therefore, the sampling time needs to be selected to be smaller in order to maintain the reaction speed of the system. If the molten pool width changes slowly, the system does not need to sample frequently, and a longer sampling time can be selected to reduce the burden of control calculations.

[0094] In practical applications, discretizing the isotherm position into a state vector and simulating its dynamic behavior through state-space equations has significant advantages. This approach allows for fine control and adjustment by accurately describing how the isotherm position changes with laser power and system state. Through linearization and discretization, the laser power can be adjusted in real time to ensure the stability and uniformity of the cladding process, thereby reducing defects and improving the quality of the cladding layer. In addition, a deep understanding and prediction of the system dynamics makes the cladding process more efficient and predictable, and can respond quickly to real-time changes in the molten pool width to optimize cladding efficiency and quality.

[0095] S7: A state feedback controller with a steady-state error compensation term is established based on the discrete state space equation, wherein the input of the state feedback controller is the isotherm position and the output is the laser power.

[0096] Among them, the state feedback controller is a controller that controls the system output by feedback adjustment of the system state variables. It continuously monitors the system state and compares it with the target state (such as the desired isotherm position) to generate a feedback signal for adjusting the control input (such as laser power). This controller can adjust the input in real time during the dynamic process to ensure that the system reaches and maintains the desired state. The purpose of the state feedback controller is to adjust the laser power in real time to ensure that the isotherm is maintained at the desired position, and to optimize the cladding quality and efficiency by accurately controlling the temperature distribution during the cladding process, thereby reducing cladding defects caused by temperature fluctuations. In addition, by introducing a steady-state error compensation term, the controller can effectively adjust the continuous deviation in the system to ensure performance stability and reliability during long-term operation.

[0097] In a possible implementation, the state feedback controller is specifically:

[0098]

[0099] (C d ) i =δ im

[0100] in, represents the steady-state error compensation term, represents the state feedback controller, K0 represents the gain coefficient, K p , K i denote the proportional gain and integral gain of the PI controller respectively, z denotes the discrete time threshold complex variable, represents the expected isotherm position, x m represents the actual isotherm position, Kx represents the state feedback control term associated with the state feedback matrix K and the state vector x, and C d represents the row vector matrix, δ im represents the Kronecker delta function that takes the value 1 when the i-th element of the row vector matrix is ​​equal to the desired isotherm position number m, and takes the value 0 otherwise.

[0101] Among them, the discrete time threshold complex variable reflects the dynamic change behavior of the system over time. The specific calculation method is: Where e represents a natural constant, s represents a Laplace transform complex variable, T s Indicates the sampling time.

[0102] It should be noted that the controller combines the PI controller and the state feedback matrix to accurately control the position of the isotherms during the laser cladding process, so that the laser power can be dynamically adjusted according to the actual temperature feedback. Its advantage is that it can significantly reduce the quality problems caused by temperature fluctuations, avoid overheating or insufficient cladding during the cladding process, and thus improve the quality and uniformity of the cladding layer. In addition, the state feedback controller can eliminate long-term deviations in the system by introducing a steady-state error compensation term, making the cladding process more stable and reliable, and improving the control accuracy and response speed.

[0103] S8: Laser cladding the composite sliding bearing along the cladding path, and collect the real-time cladding temperature of the molten pool.

[0104] It should be noted that the composite sliding bearing is laser clad along the pre-planned cladding path, and the temperature of the molten pool is collected in real time. In this process, real-time temperature monitoring is key because it allows the operator to instantly adjust the power and scanning speed of the laser to ensure that the temperature of the metal during the cladding process is always kept within the optimal range. By accurately controlling the molten pool temperature, the quality of the cladding layer can be significantly improved, and cladding defects such as cracks and pores can be reduced, thereby enhancing the mechanical properties and durability of the clad bearing.

[0105] In a possible real-time method, collecting the real-time cladding temperature specifically includes:

[0106] The spectrum wavelength of the molten pool is collected by a spectrometer.

[0107] Calculate the real-time cladding temperature based on Planck's theorem:

[0108]

[0109] Among them, E(λ,T rt ) represents the spectrum wavelength λ and the real-time cladding temperature T rt The radiation energy density, ε represents the object emissivity of the composite sliding bearing, h represents the Planck constant, c represents the speed of light, k B represents the Boltzmann constant.

[0110] It should be noted that the spectrometer collects the spectral wavelength of the molten pool and calculates the real-time cladding temperature based on Planck's law. This method can accurately obtain the temperature distribution of the cladding area without contact. Its advantage is that it can monitor temperature changes in real time to avoid excessively high or low temperatures, ensuring the temperature uniformity and quality stability of the cladding process. In addition, this method can capture the complex thermal behavior of the cladding process, provide an accurate basis for laser power adjustment, improve the overall cladding effect and reduce defects.

[0111] S9: According to the real-time cladding temperature, combined with the heat conduction model and the state feedback controller, the target laser power is output, and the composite sliding bearing is clad according to the target laser power.

[0112] Specifically, the real-time cladding temperature is input into the heat conduction model, and the coordinates perpendicular to the laser scanning direction are output, which is equivalent to finding the actual isotherm position, and then it is input into the state feedback controller as a state variable to obtain the control input, that is, the required target laser frequency. This ensures that the laser power is closely matched with the actual cladding temperature, and the temperature of the molten pool is controlled by adjusting the laser power, optimizing the cladding quality, reducing defects, and ensuring the uniformity and mechanical properties of the cladding layer. In this way, precise control of the cladding process can be achieved, and production efficiency and product reliability can be improved.

[0113] In the actual application process, from image acquisition to final cladding, advanced image processing, thermodynamic simulation and real-time control technology are systematically combined to provide a highly accurate and efficient cladding solution. Through high-definition reconstruction and sophisticated path planning, the precise placement of cladding materials is ensured, greatly reducing material waste and processing time. At the same time, the heat conduction model and real-time temperature monitoring are used to accurately control the laser power to avoid overheating or insufficient melting, ensuring the uniformity and mechanical properties of the cladding layer. In addition, the use of a state feedback controller further improves the response speed and accuracy of the cladding process, making the entire cladding process more controllable and reliable, greatly improving the cladding quality and product life, not only optimizing the cladding efficiency, but also significantly improving the quality and performance of the product, making the composite sliding bearing more competitive in high-performance applications.

[0114] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0115] In the present invention, the surface image is reconstructed in high definition based on the bicubic interpolation algorithm and an accurate cladding path is planned, which provides an image basis for the subsequent accurate adjustment of the laser frequency. It can also effectively avoid the cladding area and the defect area, avoid the cladding process covering the defect area to cause potential safety hazards, improve the cladding quality, and perform detailed path planning for the uncladding area to improve the cladding efficiency and cladding quality. In view of the inconsistency of the bearing surface, a heat conduction model and a description model of the change of the isothermal line position with the laser power are established successively, and then they are linearized and discretized to obtain a discrete state space equation, so as to control the laser frequency in the linear space. Based on the discrete state space equation, a state feedback controller with a steady-state error compensation term is established to improve the accuracy of laser frequency control. The laser frequency can be adjusted according to the real-time temperature feedback data of the molten pool to control the stability of the molten pool state, thereby avoiding damage to the material properties due to uneven heating or overheating, ensuring the structural integrity and quality of the cladding layer, and the laser frequency can be quickly adjusted according to the difference in the properties of the bearing surface, thereby ensuring the stability and consistency of the cladding process and the uniformity of the cladding surface, and further improving the cladding quality.

[0116] Reference Manual Attached Figure 2 , showing a structural schematic diagram of a composite sliding bearing laser cladding system based on image processing provided by the present invention.

[0117] The present invention further provides a composite sliding bearing laser cladding system 20 based on image processing, which is applied to the composite sliding bearing laser cladding method based on image processing, comprising:

[0118] Processor 201.

[0119] The memory 202 stores computer-readable instructions. When the computer-readable instructions are executed by the processor 201, the composite sliding bearing laser cladding method based on image processing as in the method embodiment is implemented.

[0120] The composite sliding bearing laser cladding system 20 based on image processing provided by the present invention can execute the above-mentioned composite sliding bearing laser cladding method based on image processing and achieve the same or similar technical effects. To avoid repetition, the present invention will not go into details.

[0121] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0122] In the present invention, the surface image is reconstructed in high definition based on the bicubic interpolation algorithm and an accurate cladding path is planned, which provides an image basis for the subsequent accurate adjustment of the laser frequency. It can also effectively avoid the cladding area and the defect area, avoid the cladding process covering the defect area to cause potential safety hazards, improve the cladding quality, and perform detailed path planning for the uncladding area to improve the cladding efficiency and cladding quality. In view of the inconsistency of the bearing surface, a heat conduction model and a description model of the change of the isothermal line position with the laser power are established successively, and then they are linearized and discretized to obtain a discrete state space equation, so as to control the laser frequency in the linear space. Based on the discrete state space equation, a state feedback controller with a steady-state error compensation term is established to improve the accuracy of laser frequency control. The laser frequency can be adjusted according to the real-time temperature feedback data of the molten pool to control the stability of the molten pool state, thereby avoiding damage to the material properties due to uneven heating or overheating, ensuring the structural integrity and quality of the cladding layer, and the laser frequency can be quickly adjusted according to the difference in the properties of the bearing surface, thereby ensuring the stability and consistency of the cladding process and the uniformity of the cladding surface, and further improving the cladding quality.

[0123] It should be understood that the processor in the embodiment of the present invention may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0124] It should also be understood that the memory in the embodiments of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0125] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0126] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0127] In the present invention, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can be represented by: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.

[0128] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0129] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0130] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described equipment, devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0131] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0132] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0133] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0134] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0135] An embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the composite sliding bearing laser cladding method based on image processing as described in the method embodiment is implemented.

[0136] A computer-readable storage medium provided by the present invention can implement the steps and effects of the composite sliding bearing laser cladding method based on image processing in the above method embodiment. To avoid repetition, the present invention will not go into details.

[0137] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0138] In the present invention, the surface image is reconstructed in high definition based on the bicubic interpolation algorithm and an accurate cladding path is planned, which provides an image basis for the subsequent accurate adjustment of the laser frequency. It can also effectively avoid the cladding area and the defect area, avoid the cladding process covering the defect area to cause potential safety hazards, improve the cladding quality, and perform detailed path planning for the uncladding area to improve the cladding efficiency and cladding quality. In view of the inconsistency of the bearing surface, a heat conduction model and a description model of the change of the isothermal line position with the laser power are established successively, and then they are linearized and discretized to obtain a discrete state space equation, so as to control the laser frequency in the linear space. Based on the discrete state space equation, a state feedback controller with a steady-state error compensation term is established to improve the accuracy of laser frequency control. The laser frequency can be adjusted according to the real-time temperature feedback data of the molten pool to control the stability of the molten pool state, thereby avoiding damage to the material properties due to uneven heating or overheating, ensuring the structural integrity and quality of the cladding layer, and the laser frequency can be quickly adjusted according to the difference in the properties of the bearing surface, thereby ensuring the stability and consistency of the cladding process and the uniformity of the cladding surface, and further improving the cladding quality.

[0139] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0140] There are a few points to note:

[0141] (1) The drawings of the embodiments of the present invention only relate to the structures related to the embodiments of the present invention, and other structures may refer to the general design.

[0142] (2) For the sake of clarity, in the drawings used to describe the embodiments of the present invention, the thickness of the layers or regions is exaggerated or reduced, that is, these drawings are not drawn according to the actual scale. It is understood that when an element such as a layer, film, region or substrate is referred to as being "on" or "under" another element, the element may be "directly" "on" or "under" the other element or there may be intermediate elements.

[0143] (3) In the absence of conflict, the embodiments of the present invention and the features therein may be combined with each other to obtain new embodiments.

[0144] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. The protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A composite sliding bearing laser cladding method based on image processing, characterized in that: include: S1: collecting a surface image of the composite sliding bearing; S2: reconstructing the surface image in high definition by using a bicubic interpolation algorithm; S3: Cladding path planning in the reconstructed surface image; S4: Based on the composite sliding bearing property parameters and ambient temperature, a heat conduction model describing the temperature distribution of metal during laser cladding is constructed; S5: establishing a description model of the change of the isothermal line position with the laser power in combination with the heat conduction model; S6: linearizing and discretizing the description model at the desired control point to obtain a discrete state space equation; S7: establishing a state feedback controller with a steady-state error compensation term based on the discrete state space equation, wherein the input of the state feedback controller is the isotherm position and the output is the laser power; S8: performing laser cladding on the composite sliding bearing along the cladding path, and collecting the real-time cladding temperature of the molten pool; S9: Outputting a target laser power according to the real-time cladding temperature in combination with the heat conduction model and the state feedback controller, and cladding the composite sliding bearing according to the target laser power.

2. The composite sliding bearing laser cladding method based on image processing according to claim 1 is characterized in that: The S2 is specifically: All pixels in the surface image are interpolated by the bicubic interpolation algorithm to obtain a reconstructed surface image: Where t represents the distance between the interpolation point (x′, y′) and the known sampling point, i.e., the pixel point of the expanded surface image, f(t) represents the distance kernel function, I′(x′, y′) represents the pixel value of the interpolation point after interpolation, (x, y) represents the coordinates of the upper left corner pixel closest to the interpolation point in the expanded surface image, i and j represent the distances to the interpolation point in the x and y directions, respectively, and I(x+i, y+j) represents the pixel value of the neighboring pixel point (x+i, y+j).

3. The composite sliding bearing laser cladding method based on image processing according to claim 1 is characterized in that: The cladding path is planned in the reconstructed surface image by using the A-star algorithm; The S3 specifically includes: S301: locating defect points and cladding areas in the reconstructed surface image; S302: Determine the cladding start point and the cladding end point, and use the defect point and the cladding area as obstacles, and define the obstacle cost as positive infinity; S303: Define the heuristic cost describing the distance from the current node to the cladding end point: Among them, h(n) represents the heuristic cost from the current node n to the cladding end point, (x n ,y n ),(x G ,y G ) represent the current node coordinates and the cladding end point coordinates respectively; S304: Determine the total cost of the current node by combining the heuristic cost and the path cost of the current node: φ(n)=g(n)+h(n) Among them, φ(n) represents the total cost of the current node, g(n) represents the path cost from the cladding starting point to the current node; S305: Calculate the total cost of each point in the reconstructed surface image, and use the point with the minimum total cost as the path point until the cladding end point is searched, wherein the cladding starting point, the path point and the cladding end point are sequentially connected to obtain the cladding path.

4. The composite sliding bearing laser cladding method based on image processing according to claim 1 is characterized in that: The composite sliding bearing property parameters include laser energy absorption coefficient, thermal conductivity, density and specific heat capacity; The heat conduction model is specifically: Where T represents the temperature of the target point o, T a represents the ambient temperature, A represents the laser energy absorption coefficient, P represents the laser power, k represents the thermal conductivity, r o represents the radial distance between the target point o and the laser point, (ξ,η) represents the spatial coordinates of the target point, ξ represents the coordinate along the laser scanning direction, η represents the coordinate perpendicular to the laser scanning direction, L represents the characteristic length of the heat affected zone, α represents the thermal diffusion coefficient, ρ represents the density, and C p represents specific heat capacity, U represents the scanning speed of the laser head, exp represents exponential function, and π represents pi.

5. The composite sliding bearing laser cladding method based on image processing according to claim 4 is characterized in that: The description model is specifically: T i =T a +(N-i+1)ΔT S=2L / U Among them, η i represents the isotherm position of the ith isotherm, N represents the total number of isotherms, T i represents the temperature value corresponding to the i-th isotherm, and They represent the isotherm position change rates of the 1st isotherm, the ith isotherm and the Nth isotherm respectively, e represents a natural constant, ΔT represents the isotherm temperature difference, S represents a time constant reflecting the coupling relationship between thermal diffusion in space and time, and T1 represents the laser temperature peak.

6. The composite sliding bearing laser cladding method based on image processing according to claim 1 is characterized in that: The S6 specifically includes: S601: Discretize the isotherm position into a linear state vector, and rewrite the description model into a state space equation: u=P x=(η1,η2,…,η N ) T in, represents the state space equation, f represents the value function describing the rate of change of the isotherm position, x represents the state vector, represents the rate of change of the state vector, and u represents the control input of the laser power; S602: The state space equation is linearized at the desired control point through the Jacobian matrix to obtain the discrete state space equation, wherein the desired control point is the desired molten pool width, i.e., the coordinate perpendicular to the laser scanning direction and the corresponding desired laser power: x n+1 =A d x n +B d u n A d =exp(A c T s ) 0=f(x0,u0) Among them, x n+1 =A d x n +B d u n represents the discrete state space equation, (x0,u0) represents the desired control point including the desired molten pool width x0 and the desired laser frequency u0, n represents the discrete time index, T s Indicates the preset sampling time, x n+1 represents the state vector at time n+1, x n ,u n Represent the state vector and control input at time n, A d ,B d denote the discrete-time state transfer matrix and discrete-time control input matrix, A c ,B c They represent the state transfer matrix and control input matrix before discretization, Indicates finding the i-th state f at the desired control point (x0,u0) i For the jth state variable x j The partial guide, Indicates finding the i-th state f i The partial derivative of the control input u.

7. The composite sliding bearing laser cladding method based on image processing according to claim 1 is characterized in that: The state feedback controller is specifically: (C d ) i =d im in, represents the steady-state error compensation term, represents the state feedback controller, K0 represents the gain coefficient, K p , K i denote the proportional gain and integral gain of the PI controller respectively, z denotes the discrete time threshold complex variable, represents the expected isotherm position, x m represents the actual isotherm position, Kx represents the state feedback control term associated with the state feedback matrix K and the state vector x, and C d represents the row vector matrix, δ im represents the Kronecker delta function that takes the value 1 when the i-th element of the row vector matrix is ​​equal to the desired isotherm position number m, and takes the value 0 otherwise.

8. The composite sliding bearing laser cladding method based on image processing according to claim 1 is characterized in that: The collecting of real-time cladding temperature specifically includes: The spectrum wavelength of the molten pool is collected by a spectrometer; The real-time cladding temperature is calculated based on Planck's theorem: Among them, E(λ,T rt ) represents the spectrum wavelength λ and the real-time cladding temperature T rt The radiation energy density, ε represents the object emissivity of the composite sliding bearing, h represents the Planck constant, c represents the speed of light, k B represents the Boltzmann constant.

9. A composite sliding bearing laser cladding system based on image processing, characterized in that: include: processor; A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the composite sliding bearing laser cladding method based on image processing as described in any one of claims 1 to 8 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the composite sliding bearing laser cladding method based on image processing as described in any one of claims 1 to 8 is implemented.

Images