Aluminum plate cutting path planning method and system, and storage medium

Abstract

This invention relates to the field of aluminum plate processing control technology, and particularly to an aluminum plate cutting path planning method, system, and storage medium. The method includes: acquiring an image of the aluminum plate surface, extracting texture direction vectors, and constructing a heat conduction simulation model based on anisotropic parameters introduced according to the texture direction, generating a heat distribution matrix; calculating the temperature gradient and internal stress distribution of the material based on the heat distribution matrix, identifying high-risk deformation areas, and mapping these areas to the cutting path; adaptively correcting the path by analyzing the angle between the path and the texture direction; obtaining the deviation distribution through processing simulation, constructing a compensation matrix and integrating it into CNC system parameters to achieve dynamic optimization of the cutting path; and adjusting the compensation matrix based on real-time monitoring of thermal deformation during processing. This invention solves the problem of uncontrollable thermal deformation caused by neglecting the material texture direction in existing technologies, and achieves precise optimization of the cutting path and improved processing accuracy.

Description

Technical Field

[0001] This invention relates to the field of aluminum plate processing control technology, and in particular to an aluminum plate cutting path planning method, system and storage medium. Background Technology

[0002] In the field of aluminum sheet processing, the accuracy of cutting path planning directly affects the dimensional accuracy, edge quality, and subsequent assembly stability of the parts. This is especially true in applications such as aerospace structural components, automotive body panels, electronic device housings, and high-precision industrial panels, where aluminum sheets often require thin walls, lightweight construction, and high surface quality. Therefore, the cutting process demands not only accurate cutting trajectories but also high geometric stability under heat input. In existing aluminum sheet cutting processes, CNC equipment typically performs linear or curvilinear interpolation control based on preset trajectories. Path planning focuses more on processing efficiency, tool travel optimization, and obstacle avoidance control, while relatively little consideration is given to the local deformation of the material after heating during the cutting process, stress redistribution, and the resulting trajectory deviation.

[0003] Meanwhile, while some existing thermal deformation control schemes can correct processing errors to some extent through temperature field simulation, stress analysis, or empirical compensation, their technical approaches mostly remain at the level of single-time prediction before processing or error correction after processing, lacking pre-optimization of the cutting path planning itself and real-time dynamic adjustment during processing. Relying solely on empirical compensation is insufficient to adapt to the thermal deformation changes caused by multiple uncertainties such as batch differences in aluminum sheet materials, fluctuations in ambient temperature, and changes in cutting speed. Therefore, under current technological conditions, aluminum sheet cutting paths still generally suffer from problems such as a disconnect between path planning and material thermal response, static compensation strategies, insufficient identification of local high-risk areas, and inadequate real-time correction capabilities.

[0004] Therefore, how to fully consider the anisotropic characteristics of heat conduction caused by the texture direction of aluminum plate in the specific processing scenario of aluminum plate cutting, introduce texture recognition, heat distribution modeling, stress analysis and compensation correction mechanism in the path planning stage, and combine real-time feedback in the processing to dynamically adjust the cutting path and compensation parameters, so as to reduce the adverse effects of thermal deformation on cutting accuracy and improve processing stability and path execution accuracy, has become an urgent technical problem to be solved in this field. Summary of the Invention

[0005] This invention provides a method, system, and storage medium for aluminum plate cutting path planning, which effectively improves the processing accuracy of aluminum plate cutting by combining material physical properties, thermo-mechanical coupling simulation, and CNC system.

[0006] In a first aspect, the present invention provides a method for planning cutting paths for aluminum plates, the method comprising: Step S1: Acquire images of the aluminum plate surface using a scanning device, analyze the line distribution characteristics in the images, and determine the texture direction vector; construct a preliminary simulation model based on the texture direction vector, incorporate anisotropic parameters, simulate differences in heat propagation, and generate a heat distribution matrix; Step S2: Extract temperature gradient values ​​from the heat distribution matrix, calculate the internal stress distribution of the material using finite element analysis, and mark high-risk deformation areas; for the location information of the high-risk deformation areas, obtain cutting path data through data mapping method, calculate the angle between the path and the texture direction, and adjust the path coordinates to generate a corrected path sequence; Step S3: Simulate the machining process using the corrected path sequence, analyze the deviation distribution, and determine the compensation offset distribution; construct a compensation matrix based on the compensation offset distribution, incorporate the CNC system control parameters, update the machining instructions, and generate the final cutting path; Step S4: Perform thermal deformation monitoring through the final cutting path, obtain real-time feedback data, adjust the compensation matrix, and determine the final deviation compensation scheme.

[0007] Secondly, the present invention provides an aluminum plate cutting path planning system for implementing the above-mentioned method, the system comprising: The texture extraction unit is used to acquire images of the aluminum plate surface through a scanning device, analyze the line distribution characteristics in the image, and determine the texture direction vector. The heat propagation simulation unit is used to construct a preliminary simulation model based on the texture direction vector, incorporate anisotropic parameters, simulate differences in heat propagation, and generate a heat distribution matrix. The stress analysis unit is used to extract temperature gradient values ​​from the heat distribution matrix, calculate the internal stress distribution of the material using finite element analysis, and mark high-risk deformation areas. The path optimization unit is used to obtain cutting path data through a data mapping method based on the location information of the high-risk deformation area, calculate the angle between the path and the texture direction, and adjust the path coordinates to generate a corrected path sequence. The compensation calculation unit is used to simulate the machining process through the corrected path sequence, analyze the deviation distribution, determine the compensation offset distribution, construct a compensation matrix based on the compensation offset distribution, incorporate the CNC system control parameters, update the machining instructions, and generate the final cutting path. The feedback control unit is used to perform thermal deformation monitoring through the final cutting path, obtain real-time feedback data, adjust the compensation matrix, and determine the final deviation compensation scheme.

[0008] Thirdly, the present invention provides a computer-readable storage medium storing instructions that, when executed by a processor, implement the above-described method.

[0009] The beneficial effects of this invention are as follows: This invention analyzes images of aluminum plate surfaces to extract texture direction vectors and incorporates this information into a heat conduction model. This allows the heat distribution matrix to accurately reflect the differences in thermal conductivity across different directions, improving the accuracy of thermal field calculations from the outset. Furthermore, gradient analysis of the heat distribution is performed, combined with the finite element method to calculate stress distribution, thereby achieving a conversion from a temperature field to a stress field and accurately identifying high-risk deformation areas. These areas are then spatially mapped to the cutting path, and the path is specifically modified based on the angle between the path direction and the texture direction, enabling the path planning to adapt to material properties. Subsequently, processing simulations are conducted on the modified path to obtain… The machining deviation distribution is analyzed, and a compensation matrix is ​​constructed to transform the predicted deviation into executable CNC parameters, realizing the transformation from prediction error to active compensation, thereby further reducing machining error. Finally, by monitoring thermal deformation during the actual machining process and introducing a real-time feedback mechanism, the compensation matrix is ​​dynamically adjusted, so that path optimization no longer depends on the result of a single calculation, but forms a closed-loop control, improving the system's adaptability to environmental changes and uncertainties. Through the synergistic cooperation between the above steps, the cutting path can fully consider the influence of the aluminum plate texture direction on heat conduction and deformation behavior, thereby effectively reducing thermal stress concentration and deformation risk, and significantly improving machining accuracy, stability and consistency. Attached Figure Description

[0010] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0011] Figure 1 This is a flowchart of an aluminum plate cutting path planning method in one embodiment; Figure 2 This is a graph showing the difference between predicted thermal deformation and real-time feedback in the example. Figure 3 This is a structural diagram of an aluminum plate cutting path planning system in one embodiment. Detailed Implementation

[0012] This invention provides a method, system, and storage medium for planning aluminum plate cutting paths. The terms "first," "second," "third," "fourth," etc. (if present) in the specification, claims, and accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" or "having" and any variations thereof are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0013] For ease of understanding, the specific process of the embodiments of the present invention will be described below, such as... Figure 1 As shown, an aluminum plate cutting path planning method in an embodiment of the present invention includes: Step S1: Acquire images of the aluminum plate surface using a scanning device, analyze the line distribution characteristics in the images, and determine the texture direction vector; construct a preliminary simulation model based on the texture direction vector, incorporate anisotropic parameters, simulate differences in heat propagation, and generate a heat distribution matrix; In step S1, determining the texture direction vector includes: High-resolution image data of the aluminum plate surface is acquired by scanning equipment, and grayscale image is generated by grayscale conversion processing. For the grayscale image, the line distribution information is extracted using edge detection method to determine the continuity and direction of the lines. If the line distribution information shows continuous lines, the angle of the main lines is calculated by directional analysis to determine the preliminary texture direction. Based on the initial texture direction, a straight line is fitted using the Hough transform algorithm to generate a texture direction vector; if the direction angle corresponding to the texture direction vector exceeds a preset range threshold, the edge detection parameters are adjusted, the line distribution features are re-extracted, and a corrected texture direction vector is generated.

[0014] Specifically, to transform the microscopic texture structure of the aluminum plate surface into directional parameters that can participate in numerical calculations, high-resolution image data of the aluminum plate surface is acquired using a scanning device. The scanning device is preferably an industrial camera, whose acquisition area covers a representative surface range of the area to be processed, ensuring that the acquired image accurately reflects the rolling texture characteristics of the material. After image acquisition, the original color image data undergoes grayscale conversion processing. By mapping multi-channel color information to single-channel grayscale intensity values, the data dimensionality is reduced while preserving the contrast of texture boundary information in the grayscale space, generating a corresponding grayscale image data matrix. After obtaining the grayscale image, it is preprocessed to eliminate noise interference with texture recognition. The system employs a convolution-based smoothing filtering method to denoise the image. By introducing a weighted averaging mechanism within the local neighborhood of the image, high-frequency noise components are weakened while preserving the structural features of texture edges from excessive smoothing. The denoised image is then input into an edge detection module, where a gradient-based edge detection method is used to extract line distribution information from the image. By calculating the gray-level change rate of each pixel in different directions, regions of abrupt gray-level changes are identified, thereby constructing an edge set representing texture boundaries. Furthermore, a dual-threshold mechanism is used to filter edge responses to distinguish between strong and weak edges, and connectivity analysis is used to preserve spatially continuous line structures, thus obtaining directional line distribution feature data.

[0015] After obtaining the line distribution information, the continuity and spatial direction of the lines are determined. When a linear structure satisfying a preset continuity condition is detected in the image, a directional analysis process is initiated. Specifically, this involves statistically analyzing the directional angle distribution of each line segment to construct a directional angle histogram, thereby obtaining the angular distribution features reflecting the overall texture direction. The directional angle of a line segment is the angle between the line direction vector and a preset reference coordinate axis, preferably the positive horizontal direction of the image coordinate system. Based on this, angle intervals with high distribution density are selected as the main line angles, and the weighted sum of the directional angles within this interval is calculated, with the weight of each directional angle being 1. The longer the corresponding line segment, the greater the weight of the directional angle, and vice versa. A preliminary texture direction angle is obtained. To further improve the accuracy of texture direction extraction, after obtaining the preliminary texture direction, the edge point set is input into the Hough transform algorithm, a line detection algorithm based on parameter space mapping, for processing. Specifically, the edge points in the image space are mapped to the parameter space, which is a coordinate space composed of the parameters of the lines, such as polar coordinates. Points that satisfy the collinear relationship are accumulated and statistically analyzed to identify the dominant line set in the image. The line set is then filtered to remove line segments that are too short or have strong discontinuities. By performing direction angle statistics on the filtered line set, the dominant angle is obtained, and a texture direction vector is generated based on the dominant angle, where the texture direction vector is a unit vector.

[0016] The orientation angle corresponding to the texture orientation vector is compared with a preset reasonable range threshold to determine if there is any abnormal deviation. If the result shows that the orientation angle of the orientation vector does not exceed the preset reasonable range threshold, it is considered that there is no deviation. If it exceeds the preset reasonable range threshold, it is considered that the current texture extraction result may be affected by noise or parameter settings. At this time, the process returns to the edge detection step, the edge detection parameters are adaptively adjusted, and the line extraction and orientation analysis process is re-executed to obtain the corrected texture orientation vector. Through the above technical solution, the original difficult-to-quantify structural feature of aluminum plate surface texture is transformed into a key parameter that can participate in numerical modeling and control decision-making, and provides a reliable data foundation for subsequent processing.

[0017] Further, in step S1, generating the heat distribution matrix includes: The heat conduction simulation framework is initialized based on the texture direction vector, the physical property parameters of the aluminum plate are loaded, and a preliminary simulation model is constructed. For the preliminary simulation model, anisotropic parameters are introduced, and the heat conduction coefficients in the parallel and perpendicular directions are set. The heat conduction coefficients are used to simulate the propagation rate of heat in the parallel direction, and the components of the heat distribution matrix in the parallel direction are obtained. Based on the parallel direction heat distribution matrix components, the vertical direction heat propagation rate is simulated to generate the vertical direction heat distribution matrix components; the parallel and vertical direction heat distribution matrix components are integrated to generate a comprehensive heat distribution matrix; if the comprehensive heat distribution matrix exceeds a preset threshold range in some areas, the anisotropy parameter weights are adjusted and the heat distribution matrix components are recalculated.

[0018] Specifically, by transforming the obtained aluminum plate texture direction vector into constraints for thermal conduction behavior, and further constructing a numerical model that reflects the anisotropic thermal response characteristics of the material, a basic data support is provided for subsequent thermal deformation prediction and path compensation. Specifically, a thermal conduction simulation framework is initialized based on the texture direction vector. Physical property parameters of the aluminum plate material, including but not limited to thermal conductivity, density, and specific heat capacity, are loaded into this simulation framework. A two-dimensional thermal conduction model is established using the finite element analysis method, discretizing the actual processing area into regular mesh elements, transforming the continuous temperature field into discrete node temperature values, thus constructing a preliminary simulation model. Each mesh element corresponds one-to-one with the spatial position of the aluminum plate, used to describe local thermal state changes. After obtaining the preliminary simulation model, anisotropic parameters based on the texture direction vector are introduced, using the texture direction vector as a coordinate transformation reference. The texture direction vector is obtained in step S1 and is within a preset reasonable threshold range. Then, the thermal conductivity is decomposed directionally, thereby setting different thermal conductivity coefficients (i.e., the anisotropic parameters) in the parallel and perpendicular texture directions. These thermal conductivity coefficients can be obtained by looking up a table using the texture direction vector. This table shows the correspondence between the texture direction vector and the corresponding thermal conductivity coefficients in the parallel and perpendicular texture directions, thus reflecting the thermal conductivity differences of the material in different directions. In the specific implementation, the thermal conductivity equation in the global coordinate system is mapped to a local coordinate system with the texture direction as the main axis, making the thermal conductivity tensor exhibit anisotropic distribution characteristics. This tensor parameter is embedded in the finite element solution process, so that the heat propagation calculation can reflect the constraint effect of the texture structure on the heat diffusion path. The expression of the thermal conductivity equation in the global coordinate system is: Where T represents the temperature field, ρ represents the density of the aluminum plate material, c represents the specific heat capacity, t represents time, Q represents the heat source term applied to the local area of ​​the aluminum plate during the cutting process, and K represents the thermal conductivity tensor. The heat conduction equation, mapped to the aforementioned local coordinate system, is expressed as follows: Where ξ represents the parallel texture direction, η represents the perpendicular texture direction, k∥ represents the thermal conductivity in the parallel texture direction, and k⊥ represents the thermal conductivity in the perpendicular texture direction; After setting the anisotropic parameters, boundary conditions and initial conditions are applied to the simulation model. Specifically, a heat source condition is applied to one side of the aluminum plate boundary, and the ambient temperature is set as an external boundary constraint to simulate the heat input and dissipation process during actual cutting. Then, a numerical solver based on partial differential equations is invoked. Based on the aforementioned heat conduction equation, the temperature values ​​of each mesh node are gradually updated during the time step, thereby obtaining the heat propagation rate along the parallel texture direction and forming corresponding parallel direction heat distribution matrix components. These parallel direction heat distribution matrix components are indexed by mesh nodes, and their matrix element values ​​correspond to the temperature state at each spatial location at a specific time step, reflecting the relatively rapid and uniform heat diffusion along the texture direction. Based on the characteristics of the parallel direction heat distribution matrix components, and using the parallel direction heat distribution matrix components as initial conditions or reference benchmarks, the heat propagation process perpendicular to the texture direction is further simulated in the same simulation framework. By adjusting the thermal conductivity directional components, the heat diffusion rate in the vertical direction is suppressed, and the temperature distribution of each node over time is calculated using the same numerical solution method, thereby generating the vertical direction heat distribution matrix components. Due to the difference in thermal conductivity between the parallel and vertical directions, the two types of matrix components exhibit different characteristics in terms of temperature gradient distribution, heat diffusion rate, and spatial uniformity. The parallel direction shows a smaller temperature gradient and a larger diffusion range, while the vertical direction shows a larger temperature gradient and a higher degree of heat concentration.

[0019] Subsequently, the parallel and vertical heat distribution matrix components are fused. By weighting and superimposing the two components in a unified coordinate system, a comprehensive heat distribution matrix is ​​generated. This comprehensive heat distribution matrix stores the temperature field information of the entire processing area in a two-dimensional matrix form, with each matrix element corresponding to a mesh cell. It can simultaneously reflect the influence of thermal conductivity in different directions on the overall temperature distribution. During the fusion process, the weighting coefficients are determined based on the texture direction vector and anisotropy intensity. Components with higher thermal conductivity have larger weighting coefficients, and vice versa, thus ensuring the directional consistency of the heat distribution results. Consistency and physical rationality: After obtaining the comprehensive heat distribution matrix, the temperature distribution and temperature gradient of each region in the matrix are analyzed. When the temperature value or temperature gradient of some regions exceeds the preset temperature range, it is determined that the current anisotropic parameter setting may not accurately reflect the actual heat conduction behavior. At this time, the weight ratio of the anisotropic parameters is corrected, and the heat conduction calculation process is re-executed to obtain a heat distribution result that is more consistent with the actual processing state. Through the above technical solution, the obtained heat distribution matrix provides data basis for subsequent thermal stress distribution, laying the foundation for improving the accuracy of thermal deformation prediction and the cutting precision of aluminum plates.

[0020] Step S2: Extract temperature gradient values ​​from the heat distribution matrix, calculate the internal stress distribution of the material using finite element analysis, and mark high-risk deformation areas; for the location information of the high-risk deformation areas, obtain cutting path data through data mapping method, calculate the angle between the path and the texture direction, and adjust the path coordinates to generate a corrected path sequence; In step S2, high-risk deformation areas are marked, including: Temperature gradient values ​​are extracted from the thermal distribution matrix, and gradient distribution data is constructed based on the temperature gradient values. The gradient distribution data is used as input parameters, and the internal stress distribution of the material is calculated using the finite element analysis method to obtain preliminary stress data corresponding to the temperature gradient values. Based on the correspondence between the temperature gradient values ​​and the preliminary stress data, a joint judgment is made. If the temperature gradient value exceeds a preset gradient range and the preliminary stress data exceeds a preset stress threshold, the corresponding area is marked as a high-risk deformation area.

[0021] Specifically, based on the generated heat distribution matrix, the temperature field of the processing area is analyzed spatially, and further combined with the material's thermo-mechanical coupling relationship, the transformation from temperature distribution to deformation risk identification is realized, thus providing a basis for subsequent cutting path optimization. Specifically, temperature gradient values ​​are extracted from the aforementioned heat distribution matrix, which describes the temperature state of each location within the processing area in a grid form. By performing differential operations on the temperature difference between adjacent grid nodes in the matrix and combining the corresponding spatial grid spacing to calculate the local temperature change rate, the spatial temperature gradient value of each node is obtained. In this process, by traversing the entire grid matrix, a temperature gradient matrix corresponding one-to-one with the heat distribution matrix is ​​formed, and a temperature gradient distribution map is further constructed to characterize the degree of thermal non-uniformity in different regions. Regions with larger gradient values ​​correspond to locations with concentrated and drastic heat input.

[0022] After obtaining the temperature gradient matrix, the finite element method is used to calculate the internal stress distribution of the material. The local temperature difference reflected by the temperature gradient is converted into thermal strain input. Combined with the thermal expansion coefficient and elastic mechanical parameters of the material, stress is calculated through thermo-mechanical coupling. The stress is solved for each node in a discrete mesh framework, thereby generating a stress distribution matrix corresponding to the temperature gradient matrix space. Each element in the stress distribution matrix represents the magnitude of the internal stress generated at the corresponding location under thermal action, reflecting the degree of influence of temperature non-uniformity on the mechanical response of the material. On this basis, the temperature gradient matrix and stress distribution matrix are jointly judged. Each mesh node is screened by preset gradient threshold and stress threshold. When the temperature gradient value at a certain location exceeds the preset gradient threshold, it is determined that there is significant thermal non-uniformity at that location and it is initially marked as a potential high-risk area. Further judgment is made by combining the stress value at the corresponding location. When the stress value at the same time exceeds the preset stress threshold, it is confirmed that the location is a high-risk deformation area, and its spatial coordinate information and corresponding gradient and stress parameters are recorded, thereby forming a high-risk area marking dataset.

[0023] Finally, the high-risk deformation areas and their spatial distribution relationships are integrated to generate a comprehensive distribution map of deformation types. Through the above technical solution, temperature field data that originally only reflected the thermal state can be transformed into deformation risk information, which not only improves the accuracy of identifying thermal deformation during aluminum plate cutting, but also provides precise spatial constraints for subsequent path optimization, thereby effectively reducing processing errors and improving overall processing quality and stability.

[0024] Further, in step S2, adjusting the path coordinates to generate a corrected path sequence includes: Extract the location information of the high-risk deformation area, associate the cutting path data with the data mapping method, and obtain the corresponding relationship; calculate the angle between the path and the texture direction according to the corresponding relationship, and determine the distribution range of the angle; if the distribution range of the angle is less than the preset angle threshold, trigger the path adjustment logic, obtain the anisotropy factor, adjust the path coordinate points, and generate the adjusted coordinate set; reconstruct the corrected path sequence according to the adjusted coordinate set.

[0025] Specifically, to reduce the risk of stress concentration and local deformation caused by differences in texture direction during the cutting process, the location information of the high-risk deformation areas is extracted. This location information includes the spatial coordinate range of the high-risk area, the area boundary, and the corresponding risk level marker. This location information is then input into the path planning module, and the original cutting path data corresponding to the current processing task is read from the path database. The cutting path data consists of multiple continuous path nodes, each stored in the form of a coordinate sequence and further represented as a path matrix to characterize the spatial connection relationship between the cutting start point, end point, and intermediate transition points. A data mapping method is used to associate the location information of the high-risk areas with the cutting path data. By judging the spatial overlap relationship between path nodes, path segments, and the boundary of the high-risk area, the correspondence between the high-risk area and the path segment is established, thereby determining which path segments traverse, adjoin, or cover the high-risk deformation area, and these path segments are extracted as path segments to be optimized.

[0026] After obtaining the correspondence between the path segment and the high-risk area, the angle between the path direction and the texture direction is calculated based on the above correspondence. The specific material texture direction is represented by the above texture direction vector. The original cutting path direction is constructed by the coordinate difference between adjacent path nodes to construct the path direction vector, and the path slope and direction angle are calculated based on the direction vector. By comparing the path direction angle with the texture direction angle, the angle value of each path segment to be optimized relative to the texture direction is obtained, and the corresponding angle distribution data is formed. Since different path segments may have different orientations in space, the above angle distribution data not only reflects the directional characteristics of a single path segment, but also can characterize the directional change law of the entire cutting path in the high-risk area.

[0027] Subsequently, the angle distribution data is compared with a preset angle threshold. If the angle is greater than or equal to the preset angle threshold, the coupling effect between the path segment and the texture direction is considered weak and insufficient to significantly increase the risk of thermal deformation. Therefore, compensation logic is not triggered, and the original path data is retained to reduce unnecessary computational overhead and improve path planning efficiency. When the angle of a path segment is less than the preset angle threshold, it is determined that the path segment is more susceptible to the influence of the material's anisotropic thermal conduction behavior during the cutting process, thereby triggering path adjustment. The anisotropy factor is obtained, preferably expressed as the ratio of thermal conductivity in the parallel texture direction to thermal conductivity in the perpendicular texture direction, which reflects the degree of influence of material directionality on thermal conduction and thermal deformation behavior. The path segment is adjusted based on the anisotropy factor, and the set of coordinates of the original path nodes corresponding to the path segment after adjustment is obtained. The specific correction expression is as follows: Where Δ is the offset magnitude determined based on the anisotropy factor lookup table, i.e., the relationship table between the anisotropy factor and the offset magnitude. Let be the direction vector. These are the coordinates of the original path nodes. These are the adjusted path node coordinates.

[0028] After obtaining the adjusted coordinate set, the corrected path sequence is reconstructed based on the new node coordinates. Specifically, according to the topological connection order of the original path, each adjusted node is reordered and connected to generate a continuous corrected path corresponding to the original cutting task, forming a corrected path sequence that can be directly used for CNC machining. The above technical solution enables the cutting path to adaptively correct the anisotropic thermal deformation characteristics caused by the texture direction of the aluminum plate, and ensures the matching relationship between machining accuracy and material properties.

[0029] Step S3: Simulate the machining process using the corrected path sequence, analyze the deviation distribution, and determine the compensation offset distribution; construct a compensation matrix based on the compensation offset distribution, incorporate the CNC system control parameters, update the machining instructions, and generate the final cutting path; In step S3, determining the compensation offset includes: A digital model of the processing flow is constructed using the corrected path sequence. Multiple sets of thermal deformation simulation scenarios are generated using the Monte Carlo method to obtain scenario datasets. For the scenario datasets, the distribution of thermal deformation deviations is analyzed to determine key intervals. Based on the key intervals, the average compensation offset is obtained. If the average compensation offset exceeds the preset compensation range, the adjusted offset data is obtained based on the average compensation offset and the standard deviation of the deviation distribution. Based on the adjusted offset data, the path sequence simulation scene is reconstructed until the key interval is smaller than the preset compensation range. The key interval is used as the compensation offset distribution, and it is determined whether the compensation offset distribution meets the processing flow constraints.

[0030] Specifically, based on the aforementioned corrected path sequence, the impact of heat input fluctuations, material parameter discreteness, and process parameter changes on path accuracy during the cutting process is considered to improve the accuracy of the cutting path. Specifically, the corrected path sequence is used as the processing trajectory input data to construct a digital processing flow model corresponding to the actual cutting process. In this model, the cutting path is discretized into multiple continuous path nodes, and each node is associated with the processing area mesh, temperature field distribution, and material property parameters, ensuring that subsequent simulation calculations can map data between the path dimension and the spatial dimension. After completing the construction of the digital processing flow model, the simulation module is used to solve the thermal deformation of the processing process corresponding to the corrected path. Specifically, the finite element analysis method is used to simulate the temperature changes and thermal stress distribution near each path node during the cutting process, and the initial deformation caused by thermal action is calculated based on the coefficient of thermal expansion, local temperature rise, and path motion state, thus obtaining the first set of deformation response data for the path under ideal working conditions. This initial deformation reflects the theoretical deviation trend of the corrected path under the current material and process conditions.

[0031] Based on this, the Monte Carlo method is introduced to generate multiple sets of thermal deformation simulation scenarios to characterize the path deviation fluctuations under the combined action of various uncertain factors in the actual processing. Specifically, parameters that have a significant impact on thermal deformation are selected as random variables. These random variables include at least ambient temperature fluctuations, cutting speed changes, and material thermal conductivity, i.e., thermal conductivity coefficients in different directions. Corresponding perturbation ranges and sampling rules are set for each random variable. Subsequently, multiple sets of parameter combinations are generated through random sampling. Each parameter combination is input one by one into the above-mentioned digital processing model for repeated simulation to obtain the path deviation values ​​under the corresponding scenarios. The resulting scenario dataset is preferably stored in the form of a deviation matrix, where each row of the matrix corresponds to a simulation scenario, and each column corresponds to the deviation result of a path node or path segment, thereby realizing a structured correspondence between random input parameters and path response results.

[0032] After obtaining the aforementioned scenario datasets, statistical analysis is performed on the thermal deformation deviation distribution under each scenario. Specifically, the central tendency and dispersion of the deviation values ​​in the deviation matrix are calculated to obtain the overall mean, standard deviation, and probability density distribution characteristics. Furthermore, based on the probability distribution results, key intervals for the deviation values ​​are determined, such as the deviation range within the 95% confidence interval. The average value of the deviation values ​​within these key intervals is calculated as the average compensation offset. If the average compensation offset exceeds the preset compensation range, it indicates that the current offset may lead to over-compensation or under-compensation of the path. In this case, an offset adjustment mechanism is triggered, and the sum of the average compensation offset and a set multiple of the standard deviation is used as the adjusted offset. The offset is fed back into the digital model of the processing flow, and the original corrected path sequence is simulated again to reconstruct the path sequence simulation scenario. The above process is repeated to re-acquire the key intervals and their corresponding average compensation offsets. The process ends when the average compensation offset is less than the preset compensation range. The corresponding key intervals are used as the compensation offset distribution, and it is determined whether the compensation offset distribution meets the processing flow constraints, including but not limited to path continuity constraints, processing equipment motion accuracy constraints, local overcut risk constraints, and overall dimensional tolerance constraints. If it does not meet the constraints, the process returns to the offset adjustment stage for re-optimization until the compensation offset distribution meets the processing flow constraints.

[0033] Finally, the determined compensation offset distribution and corresponding path correction scheme are written into the path optimization database, and a data interface is established with the subsequent CNC parameter adjustment module and machining accuracy verification module, so that the compensation results can directly participate in the generation of subsequent control commands. The above technical solution ensures that the aluminum plate can maintain high path accuracy and machining stability under thermal deformation disturbance during the cutting process.

[0034] Further, in step S3, the final cutting path is generated, including: The maximum value data is extracted from the compensation offset distribution to construct an initial compensation matrix. Data calibration is performed to obtain the calibrated matrix structure. The calibrated matrix structure is then integrated into the CNC system control parameters to adjust the parameter configuration. Based on the adjusted parameter configuration, real-time monitoring data streams during the simulation process are obtained, and fluctuation points are filtered. If a fluctuation point exceeds a preset offset range, a new instruction sequence is generated. Based on the new instruction sequence, a machining trajectory is constructed, and key node smoothing is performed. The final cutting path is generated using the smoothed trajectory data, and potential conflict points are detected. If a conflict exists, local path reconstruction is performed.

[0035] Specifically, based on the aforementioned compensation offset distribution, the statistically significant compensation data is further transformed into spatial compensation parameters that can be directly called by the CNC system. Specifically, the maximum value is extracted from the aforementioned compensation offset distribution and used as the benchmark value of the compensation intensity within the current machining area. An initial compensation matrix is ​​generated using the matrix construction module. This initial compensation matrix describes the spatial distribution of the compensation amount within the machining area. The center of the matrix corresponds to the core compensation area with strong thermal deformation influence, and the edge of the matrix corresponds to the compensation attenuation area. The values ​​of each matrix element are proportionally allocated according to the spatial distance relationship based on the aforementioned maximum compensation offset, and a continuously changing compensation gradient is formed through interpolation to avoid abrupt changes in the compensation value in space that could lead to discontinuities in the machining trajectory.

[0036] After constructing the initial compensation matrix, the matrix is ​​calibrated to obtain a calibrated matrix structure that matches the actual processing area. Specifically, this calibration involves aligning the spatial distribution of the compensation matrix with the region division results in the processing coordinate system. Furthermore, based on the actual dimensions of the processing area and the locations of the high-risk areas, scale conversion and boundary correction are performed on each element value in the matrix, ensuring that each element in the matrix can establish a mapping relationship with its corresponding position in the actual processing area. Subsequently, the calibrated matrix structure is loaded into the CNC system control parameters. The compensation values ​​corresponding to the matrix elements are mapped to the processing path coordinate system and processing control parameter configuration via an interface program. Specifically, based on the mesh division results of the processing area, a data correspondence is established between each mesh cell and its corresponding position in the compensation matrix. Based on this correspondence, corresponding compensation values ​​are assigned to each path node, path segment, or processing unit. This allows the CNC system to simultaneously consider the compensation requirements caused by spatial position differences when performing cutting operations, enabling a more precise reflection of thermal deformation compensation requirements.

[0037] After the control parameters are loaded, a real-time monitoring data stream is obtained according to the above parameter configuration. This real-time monitoring data stream preferably includes offset data collected during processing. The real-time monitoring data stream is continuously analyzed, and fluctuation points are screened based on the time series trend. Fluctuation points refer to abnormal data points exhibiting sudden increases or decreases during continuous monitoring. When the offset data corresponding to a fluctuation point is detected to be within a preset fluctuation range, it is determined that the existing compensation strategy can effectively match the processing state. At this time, a new cutting instruction sequence is generated to specifically transcribe the spatial compensation result corresponding to the compensation matrix into CNC instructions executable by the equipment. Conversely, if the offset data corresponding to a fluctuation point exceeds the preset fluctuation range... If the existing processing instructions cannot fully reflect the current thermal deformation state, the above steps need to be repeated to update the compensation matrix. After obtaining the new cutting instruction sequence, the processing trajectory is constructed based on the cutting instruction sequence. Specifically, the processing trajectory is obtained by reorganizing the updated path node set and its connection relationship. The positions of each key node have been corrected according to the compensation requirements. Since local node compensation may cause abrupt changes, abnormal curvature, or excessively dense local polylines between adjacent path segments, the key nodes in the above processing trajectory are further smoothed to eliminate trajectory abrupt changes caused by single-point compensation, thereby obtaining smoothed trajectory data.

[0038] The smoothed trajectory data is used as the final cutting path, and potential conflict points are detected on the final cutting path. These potential conflict points include, but are not limited to, path intersections, local overcut areas, points that exceed the processing boundary after compensation, and areas where the spacing between adjacent processing segments is insufficient due to path offset. If the detection results show that there are potential conflict points, local path reconstruction is performed on the local path segment corresponding to the conflict. By readjusting the node positions, changing the local connection method, or reducing the local compensation amplitude, the impact of the conflict is eliminated and the path continuity is re-verified until a final path output that meets the process constraints is formed. Through the above technical solution, the aluminum plate cutting path can maintain a matching relationship with the material state and equipment state under thermal deformation disturbance conditions, thereby improving processing stability, path accuracy, and system operation reliability.

[0039] Step S4: Perform thermal deformation monitoring along the final cutting path, obtain real-time feedback data, adjust the compensation matrix, and determine the final deviation compensation scheme; specifically including: The thermal deformation monitoring process is initiated through the final cutting path to track temperature changes in key areas and acquire dynamic data. Based on the dynamic data, a predictive loop mechanism is used to analyze the thermal deformation trend, map the simulation matrix, and obtain the prediction results. Through the prediction results, real-time feedback data from the temperature sensor is obtained, and the difference between the feedback data and the prediction results is calculated. If the difference exceeds the preset temperature difference range, deviation compensation adjustment is performed, and the final deviation compensation scheme is obtained through the corrected deviation compensation value.

[0040] Specifically, based on the aforementioned path optimization and compensation matrix construction, a real-time feedback and prediction model coupling mechanism is introduced to dynamically correct thermal deformation during processing, thereby improving cutting accuracy. Specifically, a thermal deformation monitoring process is initiated based on the generated optimized cutting path. The processing area is divided into multiple sub-regions according to spatial distribution, and these sub-regions serve as the basic units for thermal state analysis. In the built-in thermal deformation prediction model, the temperature changes of each sub-region during processing are dynamically simulated. The prediction model preferably employs a finite element analysis algorithm. By introducing the thermal input conditions, material thermal property parameters, and environmental boundary conditions corresponding to the optimized path into the model calculation, a temperature distribution matrix for each sub-region is generated. Furthermore, the corresponding deformation data is calculated based on the thermal expansion mechanism to obtain the thermal deformation prediction results. A one-to-one correspondence is established between the temperature peak value and deformation of each sub-region and its spatial location, forming a simulation matrix that can be used for subsequent comparison.

[0041] After obtaining the aforementioned thermal deformation prediction results, real-time feedback data is acquired through a high-precision temperature sensor array deployed on the processing equipment. This temperature sensor array is arranged in a spatial layout consistent with the sub-region divisions, allowing the real-time collected temperature data to be directly mapped to the corresponding positions in the simulation matrix. Subsequently, the real-time feedback data is input to a data comparison module. By comparing the difference between the feedback temperature and the predicted temperature, the temperature deviation of each sub-region is calculated and judged based on a preset tolerance threshold. When the temperature difference of a certain sub-region exceeds the preset temperature difference range, it is determined that there is a prediction deviation or operating condition disturbance in that region, thereby triggering automatic adjustment. The mechanism is as follows: if the prediction result is not found, the current prediction result is considered to be consistent with the actual processing state, and the original compensation strategy is maintained. When the automatic adjustment mechanism is triggered, a temperature difference-deformation correction mapping table is established in advance through offline experiments, covering the compensation correction amount for different temperature difference ranges and different sub-region types (such as edge areas and heat source concentration areas). During processing, the compensation correction amount is obtained by looking up the table based on the real-time temperature difference and the predicted deformation data of the sub-region, and then superimposed on the current compensation matrix. For abnormal temperature differences that exceed the range of the mapping table, the correction amount is calculated by extrapolation, and the abnormal data is recorded for subsequent mapping table updates. The final deviation compensation scheme is obtained based on the superimposed compensation matrix, such as... Figure 2As shown, the horizontal axis represents processing time (unit: seconds), the vertical axis represents the temperature of the key area (unit: °C), the black solid line is the temperature curve corresponding to the predicted result, the black dashed line is the actual temperature curve, the gray scatter marks the moments when the temperature difference exceeds the preset temperature difference range, such as 2°C, and the gray semi-transparent strip further visually indicates the continuous time period when the temperature difference exceeds the threshold. That is, during the period from about 65 to 80 seconds of processing, the actual temperature is significantly higher than the temperature value corresponding to the predicted result, the temperature difference exceeds the preset temperature difference range, the automatic adjustment mechanism is automatically triggered, and the corrected deviation compensation value is output, thereby realizing dynamic control of thermal deformation, which can respond in a timely manner to abnormal thermal fluctuations during the processing and ensure that the cutting path is always in the optimal compensation state.

[0042] After obtaining the aforementioned final deviation compensation scheme, the deviation value is transmitted as the compensation result to the CNC control module through the system's internal interface. The processing parameters are adjusted in real time. Specifically, based on the compensation requirements of each sub-region, i.e., the aforementioned deviation value, the control parameters of the corresponding path segment are corrected to reduce the concentration of heat input and suppress the expansion of thermal deformation. At the same time, real-time temperature feedback data, prediction results, and compensation calculation data are recorded and synchronized to the cloud analysis platform after encryption processing to support subsequent parameter updates and algorithm optimization of the prediction model. Through the above technical solution, the consistency between thermal deformation prediction and actual processing state can be significantly improved, the impact of local temperature anomalies on processing accuracy can be reduced, and the robustness of the system to environmental disturbances and material fluctuations can be improved through the adaptive compensation mechanism, thereby ensuring the stability of the cutting process and the final processing accuracy.

[0043] This invention also provides an aluminum plate cutting path planning system for implementing the above-mentioned method, such as... Figure 3 As shown, the system includes: The texture extraction unit is used to acquire images of the aluminum plate surface through a scanning device, analyze the line distribution characteristics in the image, and determine the texture direction vector. The heat propagation simulation unit is used to construct a preliminary simulation model based on the texture direction vector, incorporate anisotropic parameters, simulate differences in heat propagation, and generate a heat distribution matrix. The stress analysis unit is used to extract temperature gradient values ​​from the heat distribution matrix, calculate the internal stress distribution of the material using finite element analysis, and mark high-risk deformation areas. The path optimization unit is used to obtain cutting path data through a data mapping method based on the location information of the high-risk deformation area, calculate the angle between the path and the texture direction, and adjust the path coordinates to generate a corrected path sequence. The compensation calculation unit is used to simulate the machining process through the corrected path sequence, analyze the deviation distribution, determine the compensation offset distribution, construct a compensation matrix based on the compensation offset distribution, incorporate the CNC system control parameters, update the machining instructions, and generate the final cutting path. The feedback control unit is used to perform thermal deformation monitoring through the final cutting path, obtain real-time feedback data, adjust the compensation matrix, and determine the final deviation compensation scheme.

[0044] The present invention also provides a computer-readable storage medium storing instructions that, when executed by a processor, implement the above-described method.

[0045] In summary, this invention analyzes aluminum plate surface images, extracts texture direction vectors, and incorporates this information into a heat conduction model. This allows the heat distribution matrix to accurately reflect the differences in thermal conductivity across different directions, improving the accuracy of thermal field calculations from the outset. Furthermore, gradient analysis of the heat distribution is performed, combined with the finite element method to calculate stress distribution, thereby achieving the conversion from a temperature field to a stress field and accurately identifying high-risk deformation areas. These areas are then spatially mapped to the cutting path, and the path is specifically modified based on the angle between the path direction and the texture direction, enabling path planning to adapt to material properties. Subsequently, processing simulations are conducted on the modified path. The processing deviation distribution is obtained, and a compensation matrix is ​​constructed to transform the predicted deviation into executable CNC parameters, realizing the transformation from prediction error to active compensation, thereby further reducing processing error. Finally, by monitoring the thermal deformation of the actual processing process and introducing a real-time feedback mechanism, the compensation matrix is ​​dynamically adjusted, so that path optimization no longer depends on the result of a single calculation, but forms a closed-loop control, improving the system's adaptability to environmental changes and uncertainties. Through the synergistic cooperation between the above steps, the cutting path can fully consider the influence of the aluminum plate texture direction on heat conduction and deformation behavior, thereby effectively reducing thermal stress concentration and deformation risk, and significantly improving processing accuracy, stability and consistency.

[0046] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0047] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0048] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An aluminum sheet cutting path planning method characterized by, The method includes: Step S1: Acquire images of the aluminum plate surface using a scanning device, analyze the line distribution characteristics in the images, and determine the texture direction vector; construct a preliminary simulation model based on the texture direction vector, incorporate anisotropic parameters, simulate differences in heat propagation, and generate a heat distribution matrix; Step S2: Extract temperature gradient values ​​from the heat distribution matrix, calculate the internal stress distribution of the material using finite element analysis, and mark high-risk deformation areas; for the location information of the high-risk deformation areas, obtain cutting path data through data mapping method, calculate the angle between the path and the texture direction, and adjust the path coordinates to generate a corrected path sequence; Step S3: Simulate the machining process using the corrected path sequence, analyze the deviation distribution, and determine the compensation offset distribution; construct a compensation matrix based on the compensation offset distribution, incorporate the CNC system control parameters, update the machining instructions, and generate the final cutting path; Step S4: Perform thermal deformation monitoring through the final cutting path, obtain real-time feedback data, adjust the compensation matrix, and determine the final deviation compensation scheme.

2. The method of claim 1, wherein, In step S1, the texture direction vector is determined, including: High-resolution image data of the aluminum plate surface is acquired by scanning equipment, and grayscale image is generated by grayscale conversion processing. For the grayscale image, the line distribution information is extracted using edge detection method to determine the continuity and direction of the lines. If the line distribution information shows continuous lines, the angle of the main lines is calculated by directional analysis to determine the preliminary texture direction. Based on the initial texture direction, a straight line is fitted using the Hough transform algorithm to generate a texture direction vector; if the direction angle corresponding to the texture direction vector exceeds a preset range threshold, the edge detection parameters are adjusted, the line distribution features are re-extracted, and a corrected texture direction vector is generated.

3. The method of claim 2, wherein, In step S1, the heat distribution matrix is ​​generated, including: The heat conduction simulation framework is initialized based on the texture direction vector, the physical property parameters of the aluminum plate are loaded, and a preliminary simulation model is constructed. For the preliminary simulation model, anisotropic parameters are introduced, and the heat conduction coefficients in the parallel and perpendicular directions are set. The heat conduction coefficients are used to simulate the propagation rate of heat in the parallel direction, and the components of the heat distribution matrix in the parallel direction are obtained. Based on the parallel direction heat distribution matrix components, the vertical direction heat propagation rate is simulated to generate the vertical direction heat distribution matrix components; the parallel and vertical direction heat distribution matrix components are integrated to generate a comprehensive heat distribution matrix; if the comprehensive heat distribution matrix exceeds a preset threshold range in some areas, the anisotropy parameter weights are adjusted and the heat distribution matrix components are recalculated.

4. The method according to claim 1, characterized in that, In step S2, high-risk deformation areas are marked, including: Temperature gradient values ​​are extracted from the thermal distribution matrix, and gradient distribution data is constructed based on the temperature gradient values. The gradient distribution data is used as input parameters, and the internal stress distribution of the material is calculated using the finite element analysis method to obtain preliminary stress data corresponding to the temperature gradient values. Based on the correspondence between the temperature gradient values ​​and the preliminary stress data, a joint judgment is made. If the temperature gradient value exceeds a preset gradient range and the preliminary stress data exceeds a preset stress threshold, the corresponding area is marked as a high-risk deformation area.

5. The method according to claim 4, characterized in that, In step S2, adjusting the path coordinates to generate a corrected path sequence includes: Extract the location information of the high-risk deformation area, associate the cutting path data with the data mapping method, and obtain the corresponding relationship; calculate the angle between the path and the texture direction according to the corresponding relationship, and determine the distribution range of the angle; if the distribution range of the angle is less than the preset angle threshold, trigger the path adjustment logic, obtain the anisotropy factor, adjust the path coordinate points, and generate the adjusted coordinate set; reconstruct the corrected path sequence according to the adjusted coordinate set.

6. The method according to claim 1, characterized in that, In step S3, the compensation offset is determined, including: A digital model of the processing flow is constructed using the corrected path sequence. Multiple sets of thermal deformation simulation scenarios are generated using the Monte Carlo method to obtain scenario datasets. For the scenario datasets, the distribution of thermal deformation deviations is analyzed to determine key intervals. Based on the key intervals, the average compensation offset is obtained. If the average compensation offset exceeds the preset compensation range, the adjusted offset data is obtained based on the average compensation offset and the standard deviation of the deviation distribution. Based on the adjusted offset data, the path sequence simulation scene is reconstructed until the key interval is smaller than the preset compensation range. The key interval is used as the compensation offset distribution, and it is determined whether the compensation offset distribution meets the processing flow constraints.

7. The method according to claim 1, characterized in that, In step S3, the final cutting path is generated, including: The maximum value data is extracted from the compensation offset distribution to construct an initial compensation matrix. Data calibration is performed to obtain the calibrated matrix structure. The calibrated matrix structure is then integrated into the CNC system control parameters to adjust the parameter configuration. Based on the adjusted parameter configuration, real-time monitoring data streams during the simulation process are obtained, and fluctuation points are filtered. If a fluctuation point exceeds a preset offset range, a new instruction sequence is generated. Based on the new instruction sequence, a machining trajectory is constructed, and key node smoothing is performed. The final cutting path scheme is generated using the smoothed trajectory data, and potential conflict points are detected. If a conflict exists, local path reconstruction is performed.

8. The method according to claim 1, characterized in that, In step S4, the final deviation compensation scheme is determined, including: The thermal deformation monitoring process is initiated through the final cutting path to track temperature changes in key areas and acquire dynamic data. Based on the dynamic data, a predictive loop mechanism is used to analyze the thermal deformation trend, map the simulation matrix, and obtain the prediction results. Through the prediction results, real-time feedback data from the temperature sensor is obtained, and the difference between the feedback data and the prediction results is calculated. If the difference exceeds the preset temperature difference range, deviation compensation adjustment is performed, and the final deviation compensation scheme is obtained through the corrected deviation compensation value.

9. An aluminum plate cutting path planning system for implementing the method as described in any one of claims 1-8, characterized in that, The system includes: The texture extraction unit is used to acquire images of the aluminum plate surface through a scanning device, analyze the line distribution characteristics in the image, and determine the texture direction vector. The heat propagation simulation unit is used to construct a preliminary simulation model based on the texture direction vector, incorporate anisotropic parameters, simulate differences in heat propagation, and generate a heat distribution matrix. The stress analysis unit is used to extract temperature gradient values ​​from the heat distribution matrix, calculate the internal stress distribution of the material using finite element analysis, and mark high-risk deformation areas. The path optimization unit is used to obtain cutting path data through a data mapping method based on the location information of the high-risk deformation area, calculate the angle between the path and the texture direction, and adjust the path coordinates to generate a corrected path sequence. The compensation calculation unit is used to simulate the machining process through the corrected path sequence, analyze the deviation distribution, determine the compensation offset distribution, construct a compensation matrix based on the compensation offset distribution, incorporate the CNC system control parameters, update the machining instructions, and generate the final cutting path. The feedback control unit is used to perform thermal deformation monitoring through the final cutting path, obtain real-time feedback data, adjust the compensation matrix, and determine the final deviation compensation scheme.

10. A computer-readable storage medium storing instructions thereon, characterized in that, When the instructions are executed by the processor, they implement the method as described in any one of claims 1-8.

Images