Tire curved surface two-dimensional code laser dynamic compensation engraving method guided by three-dimensional vision

Abstract

The invention belongs to the technical field of laser precision machining, and discloses a three-dimensional vision guided tire curved surface two-dimensional code laser dynamic compensation engraving method. The method comprises the steps that area curvature parameters are obtained based on a preset tire curvature database, the overall structure of the curved surface two-dimensional code is dynamically designed, and a laser engraving path is dynamically planned in combination with the area curvature parameters; curved surface two-dimensional code engraving is carried out based on the laser engraving path, and local point cloud data are collected in real time; performing curved surface fitting on the local point cloud data, calculating a local curvature parameter, and performing curvature correction on the corresponding regional curvature parameter to obtain a local corrected curvature; based on the local correction curvature, the focus compensation amount and the delay compensation amount are calculated in real time, and dynamic compensation is carried out on the engraving process of the curved surface two-dimensional code; according to the method, area self-adaption and depth precise control of the curved surface two-dimensional code can be realized, and local curvature change of the tire surface is compensated in real time in the laser engraving process, so that the recognition stability and the overall visual effect of the curved surface two-dimensional code are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of laser precision machining, and more specifically, to a method for laser dynamic compensation engraving of a two-dimensional code on a tire curved surface guided by three-dimensional vision. Background Art

[0002] With the growing demand for digital management of tire products, QR code laser engraving technology is widely used on tire sidewalls for product anti-counterfeiting, traceability, and automatic identification. The QR code on the tire surface must not only contain product information but also maintain a high recognition rate and stability under complex environmental conditions. However, the tire sidewall surface typically exhibits a complex spatial curved surface structure, with its curvature radius varying significantly in different areas, extending from a relatively flat central area to a high-curvature edge area. This geometric characteristic places higher demands on the laser engraving process, while traditional QR code engraving methods have obvious limitations when adapting to such complex surfaces.

[0003] Currently, mainstream QR code engraving technologies generally lack high-precision three-dimensional visual guidance and real-time compensation mechanisms, making it difficult to dynamically adjust the laser focus during laser processing, and unable to achieve high-precision timing synchronization between the laser and the three-dimensional vision system, thereby limiting the quality consistency and processing efficiency of QR code engraving on the tire surface; in addition, the existing QR code structure generally adopts an equal-depth and equal-size unit design, which cannot match the local curvature of different areas of the sidewall surface, and is prone to focus offset, uneven engraving depth, pattern deformation and other problems in the edge area, which seriously affects the recognition rate and reliability of the QR code.

[0004] In view of this, the present invention proposes a three-dimensional vision-guided tire surface two-dimensional code laser dynamic compensation engraving method to solve the above problems. Summary of the Invention

[0005] In order to overcome the above-mentioned defects of the prior art and achieve the above-mentioned objectives, the present invention provides the following technical solution: a method for laser dynamic compensation engraving of a QR code on a tire curved surface guided by three-dimensional vision, comprising: Step S1: Based on a preset tire curvature database, regional curvature parameters of the target tire are obtained, and based on the regional curvature parameters, the overall structure of the curved QR code is dynamically designed; Step S2: Dynamically planning the laser engraving path based on the regional curvature parameters and the overall structure of the curved QR code; Step S3: Carve a curved QR code on the target tire based on the laser engraving path, and collect local point cloud data of the QR code marking area on the target tire surface in real time; Step S4: performing surface fitting on the local point cloud data, calculating the local curvature parameters, and performing curvature correction on the corresponding regional curvature parameters to obtain the local corrected curvature; Step S5: Based on the local corrected curvature, the focus compensation amount and the delay compensation amount are calculated in real time, and the engraving process of the curved QR code is dynamically compensated based on the focus compensation amount and the delay compensation amount.

[0006] Furthermore, the method for dynamically designing the overall structure of a curved QR code includes: The units in the curved QR code are designed to be regular hexagonal shapes and marked as hexagonal units; the hexagonal units are used for pattern design to obtain the curved QR code pattern; Based on the regional curvature parameters, the engraving depth and unit size of each hexagonal unit in the curved QR code pattern are dynamically adjusted to complete the dynamic design of the overall structure of the curved QR code; The regional curvature parameter includes the curvature radius corresponding to each position coordinate in the QR code marking area. The QR code marking area is a target area preset on the tire sidewall surface for engraving a curved QR code.

[0007] Furthermore, the method for dynamically adjusting the engraving depth includes: Map the curved QR code pattern to the QR code marking area, obtain the position coordinates corresponding to each hexagonal unit in the curved QR code pattern, and mark them as unit coordinates; obtain the curvature radius corresponding to each unit coordinate based on the regional curvature parameter, and mark them as unit curvature; compare the unit curvatures corresponding to the same hexagonal unit, and use the unit coordinates with the largest unit curvature as the center coordinates of the corresponding hexagonal unit, and use the unit coordinates with the smallest unit curvature as the edge coordinates of the corresponding hexagonal unit; A depth threshold is preset, which includes an upper depth limit and a lower depth limit. The upper depth limit is used as the engraving depth of the center coordinate, and the lower depth limit is used as the engraving depth of the edge coordinate. A curvature interval is constructed based on the unit curvature of the center coordinate and the edge coordinate. For unit coordinates that are not used as center coordinates and edge coordinates, a differentiated engraving depth is assigned to each unit coordinate based on the relative numerical ratio of the corresponding unit curvature in the curvature interval.

[0008] Furthermore, the method of dynamically adjusting the unit size includes: The unit coordinates corresponding to each hexagonal unit are averaged to obtain the unit center coordinates corresponding to each hexagonal unit; the coordinate distance between each unit coordinate and the corresponding unit center coordinate is calculated, and the corresponding coordinate weight is assigned to each unit coordinate according to the coordinate distance; all coordinate weights are normalized to obtain the standard weight; Based on the standard weight, the unit curvatures corresponding to the same hexagonal unit are weighted summed to obtain the overall curvature corresponding to each hexagonal unit; the product between each overall curvature and the preset size adjustment coefficient is calculated in turn to obtain the unit size of each hexagonal unit.

[0009] Furthermore, the laser engraving path includes trajectory coordinates and focus coordinates corresponding to different time points; The local point cloud data is the 3D point cloud data of the local area in the QR code marking area that has not been engraved. The local area is the area adjacent to the current coordinates and has not been laser engraved, which includes The post-position coordinates and the adjacent post-position coordinates on the target tire surface Position coordinates; Methods for calculating local curvature parameters include: Divide the local area into sub-local areas, each of which includes a post-coordinate and a corresponding Position coordinates; for each sub-local area, the B-spline surface fitting algorithm is used to construct the corresponding B-spline surface; the partial derivatives of each B-spline surface are calculated to obtain the first-order derivative information and second-order derivative information of each B-spline surface; based on the first-order derivative information and the second-order derivative information, the curvature radius of each B-spline surface is calculated and used as the curvature radius of the corresponding post-coordinate; according to The curvature radius of the post-coordinate constitutes the local curvature parameter.

[0010] Furthermore, the method for obtaining the local corrected curvature includes: Each curvature radius in the regional curvature parameter is respectively compared with the corresponding Adjacent radii are combined to obtain multiple groups of radius sets; for each group of radius sets, the difference between the curvature radius and each adjacent radius is calculated to obtain the radius difference; the radius differences of the same radius set are averaged to obtain the average difference corresponding to each curvature radius in the regional curvature parameter; Each curvature radius in the regional curvature parameter and the corresponding average difference are used as a set of analysis data. Each set of analysis data is input into the trained threshold setting model to predict the corresponding modified evaluation threshold. Each curvature radius in the local curvature parameter is subtracted from the corresponding curvature radius in the regional curvature parameter, and the absolute value is taken to obtain the curvature difference. Each curvature difference is compared with the corresponding modified evaluation threshold. If the curvature difference is greater than the correction evaluation threshold, the corresponding curvature radius in the local curvature parameter is marked as the actual radius; If the curvature difference is less than or equal to the modified evaluation threshold, the corresponding curvature radius in the regional curvature parameter is marked as the actual radius; All actual radii are combined to form the local corrected curvature.

[0011] Furthermore, the step of calculating the focus compensation amount and the delay compensation amount in real time includes: Step S501: randomly selecting a curvature radius from the local corrected curvature, and marking the corresponding trajectory coordinates as real-time coordinates; Step S502: Build Group candidate compensation, constructed based on candidate compensation pulses; Step S503: using the coupling mechanism between mode-locked laser pulses to update the phase of each pulse; Step S504: calculating the compensation effect of each pulse, and updating the amplitude of each pulse based on the compensation effect; Step S505: Calculate the phase synchronization between different pulses and update the candidate compensation amount for each pulse; Step S506: Calculation The overall synchronization between pulses; Step S507: Compare the overall synchronization level with the preset synchronization threshold to determine Whether the pulses are in a highly synchronized state; Step S508: If the system is not in a highly synchronized state, the process returns to step S503. If the system is in a highly synchronized state, the pulse with the largest amplitude is selected as the optimal pulse, and the focus compensation amount and the delay compensation amount among the candidate compensation amounts corresponding to the optimal pulse are obtained, and the process proceeds to step S509. Step S509: looping steps S501 to S508 until the trajectory coordinates corresponding to all curvature radii in all local corrected curvatures are marked as real-time coordinates, and then the loop ends.

[0012] Furthermore, in step S502, the candidate compensation amounts include a focus compensation amount and a delay compensation amount; Each pulse is represented as a triplet, which contains the candidate compensation amount, phase and amplitude; In step S503, the method for updating the phase of each pulse includes: Marking the pulse to be updated as the first pulse and marking the pulse not marked as the first pulse as the reference pulse; sequentially calculating the phase coupling value and coupling strength between the first pulse and each reference pulse; calculating the phase change based on the phase coupling value and the coupling strength; updating the phase of the first pulse according to the sum of the phase change and the phase corresponding to the first pulse; Similarly, each pulse is marked as the first pulse in turn, completing the phase update of each pulse.

[0013] Furthermore, in step S504, the method for updating the amplitude of each pulse includes: Calculate the growth term and loss term corresponding to each pulse respectively, and calculate the amplitude change of each pulse based on the growth term and the loss term; update the amplitude of each pulse according to the product of the amplitude of each pulse and the corresponding amplitude change; In step S505, the method for calculating the phase synchronization degree is: calculating the cosine value of the updated phase difference between each two pulses to obtain the phase synchronization degree between each two pulses; The method of updating the candidate compensation amount for each pulse includes: Calculating the compensation difference and actual learning rate between the first pulse and each reference pulse respectively; multiplying each compensation difference by the actual learning rate of the corresponding reference pulse, the updated amplitude, and the cosine value of the updated phase to obtain a sub-compensation change between the first pulse and each reference pulse; calculating the sum of all sub-compensation changes to obtain a compensation change; and updating the candidate compensation amount for the first pulse based on the sum of the compensation change and the candidate compensation amount for the first pulse; Similarly, each pulse is marked as the first pulse in turn, completing the update of the candidate compensation amount for each pulse; In step S506, the calculation Methods for overall synchronization between pulses include: The updated phase corresponding to each pulse is mapped to a complex vector on the unit circle, and the mean of all complex vectors is calculated to obtain an average complex vector; the modulus of the average complex vector is taken as the overall synchronization degree.

[0014] Furthermore, after the curved QR code is engraved, diffraction micro-patterns are embedded in the dark area of ​​the curved QR code.

[0015] The technical effects and advantages of the three-dimensional vision-guided tire surface QR code laser dynamic compensation engraving method of the present invention are as follows: By presetting the tire curvature database and dynamically designing the overall structure of the curved QR code, it is possible to achieve adaptive matching of the curved QR code pattern in different areas and precise control of the engraving depth based on the complex spatial curvature characteristics of the tire surface, effectively solving the geometric distortion problem of traditional QR codes when engraved on complex tire curved surfaces, and improving the recognition stability and overall visual effect of the QR code on the tire sidewall; integrating three-dimensional visual acquisition and real-time curvature correction technology, dynamically adjusting the laser focus position and time compensation, and being able to continuously track and compensate for local curvature changes on the tire surface during the laser engraving process, ensuring that the laser can accurately align with the target engraving position, effectively avoiding It eliminates focus deviation and time synchronization errors caused by surface geometry factors, further improving the engraving quality and information integrity of the QR code; embedding diffraction micro-textures in the dark area of ​​the curved QR code, with the help of the unique optical diffraction effect, not only enhances the anti-counterfeiting performance and improves the recognition stability under complex environmental conditions, but also expands the information capacity and improves the overall aesthetics, comprehensively improving the comprehensive application value of the tire QR code; fully utilizes technical means such as surface design, visual perception, and dynamic compensation to achieve high-precision and high-quality curved QR code manufacturing on complex surfaces, providing innovative solutions for application scenarios such as tire product traceability and anti-counterfeiting identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a flow chart of the method for laser dynamic compensation engraving of a QR code on a tire surface guided by three-dimensional vision according to Example 1 of the present invention. DETAILED DESCRIPTION

[0017] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0018] Example 1 See also Figure 1 As shown, the three-dimensional vision-guided tire surface QR code laser dynamic compensation engraving method described in this embodiment includes: Step S1: Based on a preset tire curvature database, regional curvature parameters of the target tire are obtained, and based on the regional curvature parameters, the overall structure of the curved QR code is dynamically designed.

[0019] The tire curvature database contains regional curvature parameters corresponding to the QR code marking area for different tire models (such as Michelin Pilot Sport 4, Bridgestone Turanza T005A, Goodyear Assurance TripleMax 2, etc.). These parameters are pre-set by technicians in this field after actually measuring the geometric features of the tire sidewalls of different models. The QR code marking area is a preset target area on the tire sidewall surface for engraving a curved QR code. It is planned and determined by relevant engineering personnel based on factors such as the tire's structure, safety, and readability. The regional curvature parameter includes the curvature radius corresponding to each position coordinate within the QR code marking area, which is used to characterize the spatial curvature variation characteristics of the QR code marking area. The target tire is the tire on which the curved surface QR code laser engraving is to be performed.

[0020] Methods for dynamically designing the overall structure of a curved QR code include: The cells within the curved QR code are designed to be regular hexagonal in shape and are labeled as hexagonal cells. A person skilled in the art uses hexagonal cells to design a pattern based on the information to be encoded (e.g., product batch number, production date, serial number, etc.) and QR code encoding rules (e.g., QR Code, DataMatrix standard) to obtain a curved QR code pattern. Specifically, the information to be encoded is converted into a two-dimensional matrix pattern composed of black and white modules (i.e., black modules and white modules) using the QR code encoding rules, and the rectangular cells in the two-dimensional matrix pattern are converted one by one into hexagonal cells, thereby forming a curved QR code pattern based on a honeycomb structure. Based on the regional curvature parameters, the engraving depth and unit size of each hexagonal unit in the curved QR code pattern are dynamically adjusted to complete the dynamic design of the overall structure of the curved QR code; that is, the overall structure of the curved QR code is designed as a gradient depth honeycomb structure to achieve adaptive matching of the QR code in different curvature areas to ensure engraving quality and recognition stability.

[0021] Methods for dynamically adjusting engraving depth include: Using methods such as parametric mapping (such as minimum stretching and angular conformal expansion) and projection mapping (such as orthographic projection and projective projection), the curved QR code pattern is mapped to the QR code marking area, and the position coordinates corresponding to each hexagonal unit in the curved QR code pattern are obtained and marked as unit coordinates. According to the regional curvature parameter, the curvature radius corresponding to each unit coordinate is obtained and marked as the unit curvature. The unit curvatures corresponding to the same hexagonal unit are compared, and the unit coordinates with the largest unit curvature are used as the center coordinates of the corresponding hexagonal unit, and the unit coordinates with the smallest unit curvature are used as the edge coordinates of the corresponding hexagonal unit. A depth threshold is preset, and the depth threshold includes an upper depth limit and a lower depth limit. The depth threshold is preset by those skilled in the art according to actual conditions. In this embodiment, the upper depth limit is preferably 80 μm and the lower depth limit is 50 μm. The upper depth limit is used as the engraving depth of the center coordinate, and the lower depth limit is used as the engraving depth of the edge coordinate. According to the unit curvature of the center coordinate and the edge coordinate, a curvature interval is constructed, that is, the unit curvature of the center coordinate is used as the maximum value of the curvature interval, and the unit curvature of the edge coordinate is used as the minimum value of the curvature interval. For unit coordinates that are not used as center coordinates and edge coordinates, a differentiated engraving depth is allocated to each unit coordinate according to the relative numerical ratio of the corresponding unit curvature in the curvature interval.

[0022] The expression for engraving depth distribution is: ; Where, For engraving depth, is the lower limit of depth, is the upper limit of depth, is the unit curvature, is the minimum value of the curvature interval, is the maximum value of the curvature interval.

[0023] Methods for dynamically adjusting cell size include: The unit coordinates corresponding to each hexagonal unit are averaged to obtain the unit center coordinates corresponding to each hexagonal unit; the coordinate distance between each unit coordinate and the corresponding unit center coordinate is calculated, and the corresponding coordinate weight is assigned to each unit coordinate according to the coordinate distance; all coordinate weights are normalized to obtain the standard weight; Based on the standard weight, the unit curvatures corresponding to the same hexagonal unit are weighted summed to obtain the overall curvature corresponding to each hexagonal unit; the product between each overall curvature and the preset size adjustment coefficient is calculated in turn to obtain the unit size of each hexagonal unit.

[0024] The expression of coordinate weight is: ; Where, is the coordinate weight, is an exponential function, is the coordinate distance, is the weight decay coefficient.

[0025] It should be noted that the coordinate distance is the Euclidean distance; The size adjustment coefficient and the weight attenuation coefficient are both preset by those skilled in the art according to actual conditions. In this embodiment, the preferred size adjustment coefficient is 0.3; The method to obtain the standard weight is: add the same coordinate weights of the corresponding hexagonal units in sequence to obtain the sum of the weights corresponding to each hexagonal unit, calculate the ratio of each coordinate weight to the corresponding weight sum in sequence, and obtain the standard weight corresponding to each coordinate weight; the standard weight is used to ensure that the relative contribution of each unit coordinate in the weighted summation process is in the The sum of all standard weights within the range and corresponding to the same hexagon is equal to 1.

[0026] It should be understood that the purpose of the overall structure of the dynamically designed curved QR code is to: Improve the structural uniformity and visual stability of curved QR codes during surface mapping. Hexagonal cells have good filling and isotropy. Compared with traditional rectangular cells, hexagonal structures can more naturally adapt to the curved shape of the surface in areas with large curvature changes, reduce pattern distortion, and help maintain the overall consistency and information integrity of the pattern, making them suitable for information encoding on surfaces with complex curvatures. Based on the curvature variations in different areas of the target tire surface, the depth of each hexagonal unit is differentially controlled. This allows the engraving depth to be appropriately increased in areas with larger curvature radii to ensure information clarity, while the engraving depth to be appropriately reduced in areas with smaller curvature radii to avoid over-cutting, thereby achieving visual balance and recognition stability across the entire curved surface. Based on the overall curvature distribution of the target tire surface, the sizes of hexagonal cells at different positions are optimized, so that the cell size can be appropriately reduced in high-curvature areas to reduce deformation and distortion, and the cell size can be appropriately increased in low-curvature areas to increase information density, thereby balancing the geometric distortion of the curved QR code on the irregular surface and improving the overall recognition rate and anti-interference ability.

[0027] Step S2: Dynamically plan the laser engraving path based on the regional curvature parameters and the overall structure of the curved QR code.

[0028] The laser engraving path includes the trajectory coordinates, focus coordinates, and laser parameters corresponding to different time points. The trajectory coordinates are the position coordinates of the dynamic focus laser head in space, and the focus coordinates are the position coordinates of the laser focus point (i.e., the actual contact point between the laser and the target tire surface) on the target tire surface. Laser parameters include but are not limited to laser power and pulse frequency. The laser engraving path is dynamically planned through an adaptive contour tracking algorithm, combining regional curvature parameters with the overall structure of the curved QR code, to achieve precise processing control of different curvature areas within the QR code marking area. The adaptive contour tracking algorithm is a prior art, and the specific process will not be described in detail here.

[0029] Step S3: Carve a curved QR code on the target tire based on the laser engraving path, and collect local point cloud data of the QR code marking area on the target tire surface in real time.

[0030] Local point cloud data is the 3D point cloud data of the unengraved area within the QR code marking area. It is collected in real time by the SICK RulerXR 300G custom camera integrated into the laser engraving equipment. The local area is the area adjacent to the current coordinates and has not been laser engraved yet, which includes The post-position coordinates and the adjacent post-position coordinates on the target tire surface Position coordinates, is an integer greater than 1, is an integer greater than 8; The current coordinates are the track coordinates of the laser engraving in the QR code marking area; the rear coordinates are the coordinates behind the current coordinates in the laser engraving path and have the smallest distance to the current coordinates. trajectory coordinates.

[0031] Step S4: performing surface fitting on the local point cloud data, calculating the local curvature parameters, and performing curvature correction on the corresponding regional curvature parameters to obtain the local corrected curvature.

[0032] Methods for calculating local curvature parameters include: Divide the local area into sub-local areas, each of which includes a post-coordinate and a corresponding Position coordinates; for each sub-local area, the B-spline surface fitting algorithm is used to construct the corresponding B-spline surface; the partial derivatives of each B-spline surface are calculated to obtain the first-order derivative information and second-order derivative information of each B-spline surface; based on the first-order derivative information and the second-order derivative information, the curvature radius of each B-spline surface is calculated and used as the curvature radius of the corresponding post-coordinate; according to The curvature radius of the post-coordinates constitutes the local curvature parameter;

[0033] Among them, the calculation method of the first-order derivative information, the second-order derivative information and the curvature radius, and the B-spline surface fitting algorithm are all existing technologies, and the specific process will not be described in detail here.

[0034] Methods for obtaining local corrected curvature include: Each curvature radius in the regional curvature parameter is respectively compared with the corresponding Adjacent radii are combined to obtain multiple sets of radius sets; wherein a set of radius sets includes a curvature radius and the corresponding adjacent radii, is an integer greater than 1, and the position coordinates of adjacent radii are adjacent to the position coordinates corresponding to the corresponding curvature radius; for each set of radii, the difference between the curvature radius and each adjacent radius is calculated to obtain the radius difference; the radius differences of the same radius set are averaged to obtain the average difference corresponding to each curvature radius in the regional curvature parameter; Each curvature radius in the regional curvature parameter and the corresponding average difference are used as a set of analysis data. Each set of analysis data is input into the trained threshold setting model to predict the corresponding modified evaluation threshold. Each curvature radius in the local curvature parameter is subtracted from the corresponding curvature radius in the regional curvature parameter, and the absolute value is taken to obtain the curvature difference. Each curvature difference is compared with the corresponding modified evaluation threshold. If the curvature difference is greater than the correction evaluation threshold, the corresponding curvature radius in the local curvature parameter is marked as the actual radius; If the curvature difference is less than or equal to the modified evaluation threshold, the corresponding curvature radius in the regional curvature parameter is marked as the actual radius; All actual radii are combined to form the local corrected curvature.

[0035] It should be noted that the threshold setting model is a deep neural network model, which includes an input layer, a hidden layer, and an output layer; each hidden layer includes multiple neurons, each neuron is connected to the neurons in the next layer, and the connection contains weights, which determine the importance and influence of data transmission in the neural network; an activation function is applied to each neuron between the hidden layer and the output layer, and the activation function introduces nonlinearity, allowing the network to learn more complex patterns and features; the deep neural network model is an existing technology, and the specific training process will not be described in detail here.

[0036] It should be understood that the purpose of setting the revised evaluation threshold based on the average difference is to: The modified evaluation threshold can reflect the actual fluctuation of the local curvature radius; the average difference reflects the overall difference between the current curvature radius and its neighboring curvature radius, reflecting the smoothness or complexity of the local surface; When the average difference is large, it means that the curvature radius in the area changes dramatically and the surface morphology is more complex. In this case, the correction evaluation threshold should be set more strictly (i.e., smaller) to more sensitively capture the actual change of the curvature radius and make corrections in time. When the average difference is small, it means that the curvature radius of the area is relatively stable and the surface is relatively smooth. The correction evaluation threshold can be appropriately relaxed to reduce unnecessary corrections and improve calculation efficiency. Therefore, dynamically adjusting the correction evaluation threshold based on the average difference can make the correction process of the curvature radius more flexible and accurate, adapt to the characteristics of different local curvature changes, achieve more flexible and accurate curvature radius correction, and improve the correction effect.

[0037] Step S5: Based on the local corrected curvature, the focus compensation amount and the delay compensation amount are calculated in real time, and the engraving process of the curved QR code is dynamically compensated based on the focus compensation amount and the delay compensation amount.

[0038] The steps of calculating the focus compensation amount and the delay compensation amount in real time include: Step S501: randomly selecting a curvature radius from the local corrected curvature, and marking the corresponding trajectory coordinates as real-time coordinates; Step S502: Build Group candidate compensation, constructed based on candidate compensation pulses; Step S503: using the coupling mechanism between mode-locked laser pulses to update the phase of each pulse; Step S504: calculating the compensation effect of each pulse, and updating the amplitude of each pulse based on the compensation effect; Step S505: Calculate the phase synchronization between different pulses and update the candidate compensation amount for each pulse; Step S506: Calculation The overall synchronization between pulses; Step S507: Compare the overall synchronization level with the preset synchronization threshold to determine Whether the pulses are in a highly synchronized state, the synchronization threshold is pre-set by those skilled in the art according to actual conditions; Step S508: If the system is not in a highly synchronized state, the process returns to step S503. If the system is in a highly synchronized state, the pulse with the largest amplitude is selected as the optimal pulse, and the focus compensation amount and the delay compensation amount among the candidate compensation amounts corresponding to the optimal pulse are obtained, and the process proceeds to step S509. Step S509: looping steps S501 to S508 until the trajectory coordinates corresponding to all curvature radii in all local corrected curvatures are marked as real-time coordinates, and then the loop ends.

[0039] In the above step S502, The candidate compensation amounts are pre-constructed by a person skilled in the art based on the curvature characteristics of the target tire, the performance parameters of the laser engraving system, and historical processing experience; the candidate compensation amounts include focus compensation amounts and delay compensation amounts; Focus compensation is the amount of adjustment to the focal position. Due to the complex three-dimensional curvature of the tire surface, the laser focus point may deviate from the intended position, resulting in reduced engraving depth and pattern accuracy. Focus compensation can be used to correct the laser focus position in real time, accurately aligning it with the intended engraving point on the target tire, thereby ensuring the engraving quality and information legibility of the curved QR code. Delay compensation is the adjustment amount for the laser time delay. Due to the time difference between laser emission and the action or control signal of the dynamic focus laser head in the laser engraving system, if delay compensation is not performed, it may cause laser pulse misalignment, affecting the continuity and accuracy of the engraving. Delay compensation can synchronize the laser pulse with the focus position and control action of the dynamic focus laser head, ensuring that the laser pulse is released accurately at the target position, thereby achieving high-precision, high-quality laser engraving effects.

[0040] Each pulse is represented as a triplet, which contains the candidate compensation amount, phase and amplitude; the phase of each pulse is Random numbers within the interval, the amplitude of each pulse is ; is an integer greater than 0, and this embodiment preferably .

[0041] In step S503, the method for updating the phase of each pulse includes: Marking the pulse to be updated as the first pulse and marking the pulse not marked as the first pulse as the reference pulse; sequentially calculating the phase coupling value and coupling strength between the first pulse and each reference pulse; calculating the phase change based on the phase coupling value and the coupling strength; updating the phase of the first pulse according to the sum of the phase change and the phase corresponding to the first pulse; Similarly, each pulse is marked as the first pulse in turn, completing the phase update of each pulse.

[0042] The phase coupling value is calculated by calculating the sine value of the phase difference between the first pulse and each reference pulse to obtain the phase coupling value between the first pulse and each reference pulse.

[0043] The coupling strength is calculated by: calculating the compensation effect corresponding to each pulse and adding them up in sequence to obtain the compensation sum; calculating the ratio of the compensation effect of each reference pulse to the compensation sum in sequence to obtain the compensation weight of each reference pulse; calculating the distance weight between the first pulse and each reference pulse in sequence, and multiplying each distance weight by the corresponding compensation weight and the preset maximum coupling strength in sequence to obtain the coupling strength between the first pulse and each reference pulse; Among them, the form of the expression for calculating the distance weight is consistent with the form of the expression for calculating the coordinate weight mentioned above. The difference is that the coordinate distance is replaced by the compensation distance, and the weight attenuation coefficient is replaced by the distance attenuation coefficient; the compensation distance is the Euclidean distance between the candidate compensation amount corresponding to the first pulse and the candidate compensation amount corresponding to the reference pulse; the maximum coupling strength and the distance attenuation coefficient are pre-set by technical personnel in this field according to actual conditions.

[0044] The phase variation is calculated by multiplying each phase coupling value by the corresponding coupling strength to obtain the phase coupling drive between the first pulse and each reference pulse; and the sum of all phase coupling drive values ​​is calculated to obtain the phase variation.

[0045] The calculation method of the compensation effect is: the candidate compensation amount corresponding to each pulse is respectively compared with the regional curvature parameters corresponding to the real-time coordinates and the curvature radius in the local corrected curvature, as well as the focus coordinates corresponding to the real-time coordinates, as a set of effect analysis data; that is, a set of effect analysis data includes a candidate compensation amount corresponding to a pulse, the regional curvature parameters corresponding to the real-time coordinates and the curvature radius in the local corrected curvature, as well as the focus coordinates corresponding to the real-time coordinates; each set of effect analysis data is input into the trained effect prediction model to predict the corresponding compensation effect; wherein the effect prediction model is a deep neural network model, and the compensation effect is the correction effect of the laser engraving error, which indicates the degree to which the accuracy and consistency of the curved QR code are improved after the position error and time error caused by the lack of synchronization between the laser emission and the dynamic focusing laser head are corrected by the candidate compensation amount.

[0046] In the above step S504, the method for updating the amplitude of each pulse includes: Calculate the product of the compensation effect of each pulse and the preset gain coefficient to obtain the growth term of each pulse; calculate the product of the amplitude of each pulse and the preset loss coefficient to obtain the loss term of each pulse; subtract the corresponding loss term from each growth term and add one to obtain the amplitude change of each pulse; update the amplitude of each pulse according to the product of the amplitude of each pulse and the corresponding amplitude change; the gain coefficient and the loss coefficient are pre-set by technical personnel in this field according to actual conditions.

[0047] In the above step S505, the method for calculating the phase synchronization degree is: calculating the cosine value of the updated phase difference between every two pulses to obtain the phase synchronization degree between every two pulses; The method of updating the candidate compensation amount for each pulse includes: Calculating the difference between the candidate compensation amount of the first pulse and the candidate compensation amount of each reference pulse to obtain a compensation amount difference; multiplying the phase synchronization between the first pulse and each reference pulse by a preset basic learning rate in sequence to obtain an actual learning rate; multiplying each compensation amount difference by the actual learning rate of the corresponding reference pulse, the updated amplitude, and the cosine value of the updated phase in sequence to obtain a sub-compensation change between the first pulse and each reference pulse; calculating the sum of all sub-compensation changes to obtain a compensation change; and updating the candidate compensation amount for the first pulse based on the sum of the compensation change and the candidate compensation amount for the first pulse;

[0048] Similarly, each pulse is marked as the first pulse in sequence, completing the update of the candidate compensation amount for each pulse.

[0049] In the above step S506, the calculation Methods for overall synchronization between pulses include: The updated phase corresponding to each pulse is mapped to a complex vector on the unit circle, and the mean of all complex vectors is calculated to obtain the average complex vector. The modulus of the average complex vector is taken as the overall synchronization degree. The form of the complex vector is: ;in, is a natural constant, is the imaginary unit, is the updated phase.

[0050] In the above step S507, it is determined Methods for determining whether the pulses are in a highly synchronized state include: If the overall synchronization degree is greater than the synchronization threshold, then the The pulses are in a highly synchronized state; If the overall synchronization degree is less than or equal to the synchronization threshold, then judge The pulses are not in a highly synchronized state.

[0051] After the curved QR code is engraved, diffraction micro-patterns are embedded in the dark area of ​​the curved QR code; the dark area is the black module of the curved QR code, and the period of the diffraction micro-patterns is 200nm (that is, the repetition spacing of the diffraction micro-patterns is 200nm).

[0052] It should be noted that the purpose of embedding diffraction micro-patterns in the dark area of ​​the curved QR code is: The unique optical diffraction effect enhances anti-counterfeiting performance and improves the recognition stability of curved QR codes at different angles and lighting conditions. It also expands information capacity and enhances overall aesthetics, giving curved QR codes greater security and practical value while maintaining basic recognition functions.

[0053] It should be understood that this embodiment uses nanosecond-level on-the-fly dynamic compensation technology to dynamically compensate for the curved QR code engraving process. Simultaneously, a phase synchronization trigger integrated into the SICK RulerXR 300G custom camera is used to control the error between the camera clock and the laser clock to within 10 nanoseconds. These two methods together achieve high-precision timing synchronization between 3D scanning and laser engraving, ensuring laser positioning and marking accuracy during the curved QR code engraving process.

[0054] This embodiment, by presetting the tire curvature database and dynamically designing the overall structure of the curved surface QR code, can achieve adaptive matching of the curved surface QR code pattern in different areas and precise control of the engraving depth according to the complex spatial curvature characteristics of the tire surface, effectively solving the geometric distortion problem of traditional QR codes when engraved on complex tire curved surfaces, and improving the recognition stability and overall visual effect of the QR code on the tire sidewall; integrating three-dimensional visual acquisition and real-time curvature correction technology, dynamically adjusting the laser focus position and time compensation, and being able to continuously track and compensate for local curvature changes on the tire surface during the laser engraving process, ensuring that the laser can be accurately aligned with the target engraving position, effectively It avoids focus deviation and time synchronization errors caused by curved surface geometry factors, further improving the engraving quality and information integrity of the QR code; embedding diffraction micro-patterns in the dark area of ​​the curved QR code, with the help of the unique optical diffraction effect, not only enhances the anti-counterfeiting performance and improves the recognition stability under complex environmental conditions, but also expands the information capacity and improves the overall aesthetics, comprehensively improving the comprehensive application value of the tire QR code; fully utilizes technical means such as curved surface design, visual perception, and dynamic compensation to achieve high-precision and high-quality curved QR code manufacturing on complex curved surfaces, providing innovative solutions for application scenarios such as tire product traceability and anti-counterfeiting identification.

[0055] Example 2 This application also provides an electronic device. The electronic device may include one or more processors and one or more memories. The memories may store computer-readable code that, when executed by the one or more processors, may implement the above-described method for laser dynamic compensation engraving of a QR code on a curved tire surface guided by 3D vision.

[0056] The method or system according to the embodiment of the present application can also be implemented with the aid of the architecture of the electronic device shown in this application. The electronic device may include a bus, one or more CPUs, ROM, RAM, a communication port connected to a network, input / output, a hard disk, etc. The storage device in the electronic device, such as a ROM or a hard disk, can store the three-dimensional vision-guided tire surface QR code laser dynamic compensation engraving method provided in this application. Furthermore, the electronic device may also include a user interface. Of course, the architecture shown in this application is only exemplary. When implementing different devices, one or more components in the electronic device shown in this application may be omitted according to actual needs.

[0057] Example 3 As shown, one embodiment of the present application discloses a computer-readable storage medium. The computer-readable storage medium stores computer-readable instructions. When executed by a processor, the computer-readable instructions can execute the 3D vision-guided laser dynamic compensation engraving method for a tire curved surface QR code according to the embodiment of the present application described with reference to the above figures. The storage medium includes, but is not limited to, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory. Non-volatile memory may include, for example, read-only memory (ROM), a hard disk, flash memory, etc.

[0058] Furthermore, according to embodiments of the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the present application provides a non-transitory machine-readable storage medium storing machine-readable instructions capable of being executed by a processor to perform the steps corresponding to the methods provided herein, such as the method for dynamically compensating laser engraving of a QR code on a curved tire surface using 3D vision guidance. When executed by a central processing unit (CPU), this computer program performs the functions defined in the methods of the present application.

[0059] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art will be able to modify the technical solutions described in the foregoing embodiments or to substitute equivalents for some of the technical features. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

[0060] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or apparatus comprising 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 apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or apparatus comprising the element.

[0061] In the description of the present invention, it should be understood that the terms "first", "second", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0062] In the description of the present invention, unless otherwise specified, "plurality" means two or more.

[0063] In the description of the present invention, “several” means one or more, and “a large number” means two or more.

[0064] Throughout this specification, reference to terms such as "one embodiment," "some embodiments," "examples," "specific examples," or "some examples" means that a specific feature, structure, material, or characteristic described in conjunction with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0065] The formulas in this manual are all dimensionless and calculated using numerical values. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters and thresholds in the formulas are set by technicians in this field based on actual conditions.

[0066] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to the embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the claims and their equivalents.

Claims

1. A three-dimensional vision-guided laser dynamic compensation engraving method for a tire curved surface QR code, characterized in that: include: Step S1: Based on a preset tire curvature database, regional curvature parameters of the target tire are obtained, and based on the regional curvature parameters, the overall structure of the curved QR code is dynamically designed; Step S2: Dynamically planning the laser engraving path based on the regional curvature parameters and the overall structure of the curved QR code; Step S3: Carve a curved QR code on the target tire based on the laser engraving path, and collect local point cloud data of the QR code marking area on the target tire surface in real time; Step S4: performing surface fitting on the local point cloud data, calculating the local curvature parameters, and performing curvature correction on the corresponding regional curvature parameters to obtain the local corrected curvature; Step S5: Based on the local corrected curvature, the focus compensation amount and the delay compensation amount are calculated in real time, and the engraving process of the curved QR code is dynamically compensated based on the focus compensation amount and the delay compensation amount.

2. The method for laser dynamic compensation engraving of a QR code on a tire curved surface guided by three-dimensional vision according to claim 1, characterized in that: Methods for dynamically designing the overall structure of a curved QR code include: The units in the curved QR code are designed to be regular hexagonal shapes and marked as hexagonal units; the hexagonal units are used for pattern design to obtain the curved QR code pattern; Based on the regional curvature parameters, the engraving depth and unit size of each hexagonal unit in the curved QR code pattern are dynamically adjusted to complete the dynamic design of the overall structure of the curved QR code; The regional curvature parameter includes the curvature radius corresponding to each position coordinate in the QR code marking area. The QR code marking area is a target area preset on the tire sidewall surface for engraving a curved QR code.

3. The method for laser dynamic compensation engraving of a two-dimensional code on a tire curved surface guided by three-dimensional vision according to claim 2, characterized in that: Methods for dynamically adjusting engraving depth include: Map the curved QR code pattern to the QR code marking area, obtain the position coordinates corresponding to each hexagonal unit in the curved QR code pattern, and mark them as unit coordinates; obtain the curvature radius corresponding to each unit coordinate based on the regional curvature parameter, and mark them as unit curvature; compare the unit curvatures corresponding to the same hexagonal unit, and use the unit coordinates with the largest unit curvature as the center coordinates of the corresponding hexagonal unit, and use the unit coordinates with the smallest unit curvature as the edge coordinates of the corresponding hexagonal unit; A depth threshold is preset, which includes an upper depth limit and a lower depth limit. The upper depth limit is used as the engraving depth of the center coordinate, and the lower depth limit is used as the engraving depth of the edge coordinate. A curvature interval is constructed based on the unit curvature of the center coordinate and the edge coordinate. For unit coordinates that are not used as center coordinates and edge coordinates, a differentiated engraving depth is assigned to each unit coordinate based on the relative numerical ratio of the corresponding unit curvature in the curvature interval.

4. The method for laser dynamic compensation engraving of a QR code on a tire curved surface guided by three-dimensional vision according to claim 3, characterized in that: Methods for dynamically adjusting cell size include: The unit coordinates corresponding to each hexagonal unit are averaged to obtain the unit center coordinates corresponding to each hexagonal unit; the coordinate distance between each unit coordinate and the corresponding unit center coordinate is calculated, and the corresponding coordinate weight is assigned to each unit coordinate according to the coordinate distance; all coordinate weights are normalized to obtain the standard weight; Based on the standard weight, the unit curvatures corresponding to the same hexagonal unit are weighted summed to obtain the overall curvature corresponding to each hexagonal unit; the product between each overall curvature and the preset size adjustment coefficient is calculated in turn to obtain the unit size of each hexagonal unit.

5. The method for laser dynamic compensation engraving of a two-dimensional code on a tire curved surface guided by three-dimensional vision according to claim 4, characterized in that: The laser engraving path includes the trajectory coordinates and focus coordinates corresponding to different time points; The local point cloud data is the 3D point cloud data of the local area in the QR code marking area that has not been engraved. The local area is the area adjacent to the current coordinates and has not been laser engraved, which includes The post-position coordinates and the adjacent post-position coordinates on the target tire surface Position coordinates; Methods for calculating local curvature parameters include: Divide the local area into sub-local areas, each of which includes a post-coordinate and a corresponding Position coordinates; for each sub-local area, the B-spline surface fitting algorithm is used to construct the corresponding B-spline surface; partial derivatives are calculated for each B-spline surface to obtain the first-order derivative information and second-order derivative information of each B-spline surface; Based on the first-order derivative information and the second-order derivative information, the curvature radius of each B-spline surface is calculated respectively and used as the curvature radius of the corresponding post-coordinate; according to The curvature radius of the post-coordinate constitutes the local curvature parameter.

6. The method for laser dynamic compensation engraving of a two-dimensional code on a tire curved surface guided by three-dimensional vision according to claim 5, characterized in that: Methods for obtaining local corrected curvature include: Each curvature radius in the regional curvature parameter is respectively compared with the corresponding Adjacent radii are combined to obtain multiple groups of radius sets; for each group of radius sets, the difference between the curvature radius and each adjacent radius is calculated to obtain the radius difference; the radius differences of the same radius set are averaged to obtain the average difference corresponding to each curvature radius in the regional curvature parameter; Each curvature radius in the regional curvature parameter and the corresponding average difference are used as a set of analysis data. Each set of analysis data is input into the trained threshold setting model to predict the corresponding modified evaluation threshold. Each curvature radius in the local curvature parameter is subtracted from the corresponding curvature radius in the regional curvature parameter, and the absolute value is taken to obtain the curvature difference. Each curvature difference is compared with the corresponding modified evaluation threshold. If the curvature difference is greater than the correction evaluation threshold, the corresponding curvature radius in the local curvature parameter is marked as the actual radius; If the curvature difference is less than or equal to the modified evaluation threshold, the corresponding curvature radius in the regional curvature parameter is marked as the actual radius; All actual radii are combined to form the local corrected curvature.

7. The method for laser dynamic compensation engraving of a two-dimensional code on a tire curved surface guided by three-dimensional vision according to claim 6, characterized in that: The steps of calculating the focus compensation amount and the delay compensation amount in real time include: Step S501: randomly selecting a curvature radius from the local corrected curvature, and marking the corresponding trajectory coordinates as real-time coordinates; Step S502: Build Group candidate compensation, constructed based on candidate compensation pulses; Step S503: using the coupling mechanism between mode-locked laser pulses to update the phase of each pulse; Step S504: calculating the compensation effect of each pulse, and updating the amplitude of each pulse based on the compensation effect; Step S505: Calculate the phase synchronization between different pulses and update the candidate compensation amount for each pulse; Step S506: Calculation The overall synchronization between pulses; Step S507: Compare the overall synchronization level with the preset synchronization threshold to determine Whether the pulses are in a highly synchronized state; Step S508: If the system is not in a highly synchronized state, the process returns to step S503. If the system is in a highly synchronized state, the pulse with the largest amplitude is selected as the optimal pulse, and the focus compensation amount and the delay compensation amount among the candidate compensation amounts corresponding to the optimal pulse are obtained, and the process proceeds to step S509. Step S509: looping steps S501 to S508 until the trajectory coordinates corresponding to all curvature radii in all local corrected curvatures are marked as real-time coordinates, and then the loop ends.

8. The method for laser dynamic compensation engraving of a two-dimensional code on a tire curved surface guided by three-dimensional vision according to claim 7, characterized in that: In step S502, the candidate compensation amounts include a focus compensation amount and a delay compensation amount; Each pulse is represented as a triplet, which contains the candidate compensation amount, phase and amplitude; In step S503, the method for updating the phase of each pulse includes: Marking the pulse to be updated as the first pulse and marking the pulse not marked as the first pulse as the reference pulse; sequentially calculating the phase coupling value and coupling strength between the first pulse and each reference pulse; calculating the phase change based on the phase coupling value and the coupling strength; updating the phase of the first pulse according to the sum of the phase change and the phase corresponding to the first pulse; Similarly, each pulse is marked as the first pulse in turn, completing the phase update of each pulse.

9. The method for laser dynamic compensation engraving of a two-dimensional code on a tire curved surface guided by three-dimensional vision according to claim 8, characterized in that: In step S504, the method for updating the amplitude of each pulse includes: Calculate the growth term and loss term corresponding to each pulse respectively, and calculate the amplitude change of each pulse based on the growth term and the loss term; update the amplitude of each pulse according to the product of the amplitude of each pulse and the corresponding amplitude change; In step S505, the method for calculating the phase synchronization degree is: calculating the cosine value of the updated phase difference between each two pulses to obtain the phase synchronization degree between each two pulses; The method of updating the candidate compensation amount for each pulse includes: Calculating the compensation difference and actual learning rate between the first pulse and each reference pulse respectively; multiplying each compensation difference by the actual learning rate of the corresponding reference pulse, the updated amplitude, and the cosine value of the updated phase to obtain a sub-compensation change between the first pulse and each reference pulse; calculating the sum of all sub-compensation changes to obtain a compensation change; and updating the candidate compensation amount for the first pulse based on the sum of the compensation change and the candidate compensation amount for the first pulse; Similarly, each pulse is marked as the first pulse in turn, completing the update of the candidate compensation amount for each pulse; In step S506, the calculation Methods for overall synchronization between pulses include: The updated phase corresponding to each pulse is mapped to a complex vector on the unit circle, and the mean of all complex vectors is calculated to obtain an average complex vector; the modulus of the average complex vector is taken as the overall synchronization degree.

10. The method for laser dynamic compensation engraving of a two-dimensional code on a tire curved surface guided by three-dimensional vision according to claim 9, characterized in that: After the curved QR code is engraved, diffraction micro-patterns are embedded in the dark area of ​​the curved QR code.

Images