A precision mold design method and system based on intelligent optimization algorithm

Abstract

This invention discloses a precision mold design method and system based on intelligent optimization algorithms. By constructing a multi-objective optimization framework, generating a candidate path set through iterative calculations, and introducing a Pareto optimal solution screening mechanism, it can effectively balance multiple key performance indicators such as path length, cutting load distribution, and surface quality. Furthermore, it dynamically adjusts path parameters using a process experience database and optimizes path inflection points and transition segments through a neighborhood perturbation strategy. This ensures that the final generated machining path not only meets the requirements of high efficiency and stability but also adapts to the actual machining needs under different process conditions. This method significantly improves the machining efficiency and surface consistency of complex mold parts, reduces trial-and-error costs, and realizes intelligent and adaptive precision mold design and machining path planning.

Description

Technical Field

[0001] This invention belongs to the field of mold design technology, specifically relating to a precision mold design method and system based on intelligent optimization algorithms. Background Technology

[0002] In the field of precision mold machining, traditional mold design and machining path planning mainly rely on manual experience combined with fixed rules. A geometry-driven approach is typically used, directly generating toolpaths from the part's 3D model. Common methods include contour cutting, offset circumferential cutting, and reciprocating toolpaths. While these methods are simple to implement and widely used for parts with relatively regular structures, they suffer from problems such as lengthy paths, uneven cutting forces, and unstable surface quality when dealing with mold parts with complex curved surfaces or high precision requirements.

[0003] In existing technologies, some solutions introduce optimization algorithms to improve the machining path, but most of them are single-objective optimizations, such as only optimizing the path length or only reducing cutting force fluctuations, lacking a comprehensive consideration of multiple performance indicators. In addition, traditional path optimization methods are difficult to dynamically adapt to changes in different materials, process parameters, and equipment conditions, resulting in a trade-off between machining efficiency and quality. Summary of the Invention

[0004] The purpose of this invention is to provide a precision mold design method and system based on intelligent optimization algorithms, which improves the processing efficiency and surface consistency of complex mold parts, reduces trial and error costs, and realizes intelligent and adaptive precision mold design and processing path planning. This solves the problem of how to simultaneously consider path length, cutting stability and surface quality in the processing of complex mold parts, and achieve adaptive adjustment to changes in process conditions, thereby improving overall processing efficiency and accuracy.

[0005] To achieve the above objectives, the present invention adopts the following technical solution: a precision mold design method based on intelligent optimization algorithms, comprising the following steps:

[0006] The process involves collecting 3D geometric data and machining constraints of mold parts to generate an initial dataset; extracting features from the initial dataset to identify geometric features and constraint boundaries in the machining path; constructing a multi-objective optimization framework based on these features and constraints; generating a set of candidate machining paths through iterative calculations within this framework; performing multi-dimensional comparative analysis on the candidate machining path set to select the Pareto optimal solution set; dynamically adjusting path parameters based on the Pareto optimal solution set and a process experience database to generate an improved path scheme; performing a local search on the improved path scheme; optimizing the smoothness of path inflection points and transition segments through a neighborhood perturbation strategy; verifying the feasibility of the improved path scheme; and finally outputting the final machining path and generating CNC code.

[0007] Preferably, the procedure includes the following steps:

[0008] Obtain the three-dimensional geometric model of the mold part and extract the curvature distribution information of each surface;

[0009] The curvature distribution information is discretized and divided into multiple curvature intervals, and the point density in each interval is calculated.

[0010] By combining the point density with the preset sampling step size, the distribution ratio of sampling points in each region is calculated;

[0011] Based on the sampling point allocation ratio, adaptive sampling is performed in each curvature interval to generate a spatial point cloud set.

[0012] Preferably, the identification of geometric features and constraint boundaries in the processing path includes:

[0013] Perform neighborhood topology analysis on the point cloud set in the initial dataset to determine the local surface change trend of each point;

[0014] Based on the local surface change trend, regions of abrupt curvature change are extracted as potential geometric feature boundaries;

[0015] By combining the geometric feature boundary with the projection relationship of the machining direction, the infeasible region affected by tool interference is calculated;

[0016] Based on the aforementioned infeasible regions and geometric feature boundaries, the range of constraints for practically usable processing paths is defined.

[0017] Preferably, a multi-objective optimization framework is constructed based on the geometric features and constraint boundaries, including:

[0018] Based on the geometric feature boundaries and constraint range, the processing area is divided into multiple sub-regions, and the surface tilt angle and contact risk level of each sub-region are marked.

[0019] For each sub-region, a path planning priority is set, and based on the path planning priority, three parallel optimization objectives are set: minimizing the idle travel distance, balancing the cutting load distribution, and reducing the number of inflection points;

[0020] The priority of each sub-region is mapped to the corresponding target weight to form a target-oriented optimization space structure.

[0021] Preferably, the step of generating a candidate processing path set through iterative calculation includes:

[0022] Within the optimized spatial structure, a set of initial path sequences is randomly generated as the first generation of path population;

[0023] Fitness assessment is performed on each path in the initial path population, and the score is based on the weighted sum of path length, load fluctuation amplitude and number of inflection points;

[0024] Based on the fitness score results, high-scoring paths are selected, and a new batch of paths is generated through cross splicing and mutation operations. The position sequence of the new path is generated by a weighted combination of the position sequence of the parent path and the weight coefficient.

[0025] Repeat the fitness evaluation and path update process until the preset number of iterations is reached, and finally output a set of candidate processing paths.

[0026] Preferably, the process of selecting the Pareto optimal solution set includes:

[0027] For each path in the candidate machining path set, perform multi-objective performance ranking and record the independent ranking of each path under the three indicators of path length, cutting force fluctuation and surface quality.

[0028] Calculate the overall advantage index for each path;

[0029] The paths are sorted from high to low according to the comprehensive advantage index, and a threshold is set to select the top N items as the preliminary preferred path group;

[0030] The preliminary preferred path group is compared pairwise to exclude completely dominated paths and retain non-dominated paths to form a Pareto optimal solution set.

[0031] Preferably, the method for generating the improved path scheme includes:

[0032] Each path in the Pareto optimal solution set is matched with historical processing parameters in the process experience database to find historical cases with similarity higher than a set threshold.

[0033] Based on the tool compensation value and feed rate settings in the historical cases, parameter mapping is adjusted for local areas of the current path. The adjusted feed rate is determined by the ratio between the original set rate and the old and new tool compensation values.

[0034] The path is re-arranged into segments based on the adjusted parameters, prioritizing the merging of adjacent path segments with consistent processing conditions;

[0035] In the rearranged path structure, transition arcs are introduced to replace sharp corner connections, forming a continuous and stable improved path scheme.

[0036] Preferably, the smoothness of the optimized path inflection points and transition segments includes:

[0037] Identify the inflection points and direction vectors of adjacent path segments in the improved path scheme;

[0038] Set up a local disturbance area around the inflection point and adjust the displacement of the path points within the area, with the displacement direction perpendicular to the path forward direction.

[0039] The curvature change rate of the transition segment is calculated based on the position of the path point after the disturbance. If the curvature change rate exceeds the set threshold, the disturbance amplitude is reduced and the adjustment is repeated until the inflection point connection tends to be a natural transition and the path continuity meets the processing requirements.

[0040] Preferably, verifying the feasibility of the improved path scheme includes:

[0041] The improved path scheme is imported into the simulation environment to simulate the actual trajectory of the tool moving along the path.

[0042] During the simulation, the contact state between the tool and the workpiece is detected, and areas where overcutting or undercutting occurs are marked.

[0043] Calculate the deviation volume for the regions where overcutting or undercutting occurs. If the deviation volume is less than the upper limit of the allowable error, the path is deemed feasible; otherwise, return to adjust the path parameters and repeat the verification process.

[0044] On the other hand, this invention proposes a precision mold design system based on an intelligent optimization algorithm, comprising:

[0045] The preprocessing module is used to collect the three-dimensional geometric data and machining constraints of the mold parts and generate the initial dataset;

[0046] The boundary recognition module is used to extract features from the initial dataset and identify geometric features and constraint boundaries in the processing path.

[0047] The path generation module is used to construct a multi-objective optimization framework based on the geometric features and constraint boundaries, and generate a set of candidate processing paths through iterative calculation under the multi-objective optimization framework.

[0048] The parameter adjustment module is used to perform multi-dimensional comparative analysis on the candidate processing path set, screen out the Pareto optimal solution set, and dynamically adjust the path parameters based on the Pareto optimal solution set and the process experience database to generate an improved path scheme.

[0049] The path optimization verification and output module is used to perform local search on the improved path scheme, optimize the smoothness of path inflection points and transition segments through a neighborhood perturbation strategy, verify the feasibility of the improved path scheme, output the final machining path and generate CNC code.

[0050] Technical effects and advantages of the present invention: The precision mold design method and system based on intelligent optimization algorithm proposed in this invention have the following advantages compared with the prior art:

[0051] This invention constructs a multi-objective optimization framework, generates a candidate path set through iterative calculations, and introduces a Pareto optimal solution screening mechanism to effectively balance multiple key performance indicators such as path length, cutting load distribution, and surface quality. Based on this, it further dynamically adjusts path parameters using a process experience database and optimizes path inflection points and transition segments through a neighborhood perturbation strategy. This ensures that the final generated machining path not only meets the requirements of high efficiency and stability but also adapts to actual machining needs under different process conditions. This method significantly improves the machining efficiency and surface consistency of complex mold parts, reduces trial-and-error costs, and realizes intelligent and adaptive precision mold design and machining path planning. Attached Figure Description

[0052] Figure 1 This is a flowchart of the precision mold design method based on intelligent optimization algorithm of the present invention;

[0053] Figure 2 This is a block diagram of the precision mold design system based on intelligent optimization algorithms of the present invention. Detailed Implementation

[0054] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The specific embodiments described herein are merely used to explain the present invention and are not intended to limit the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0055] This invention provides, for example Figure 1 The precision mold design method based on intelligent optimization algorithm shown includes the following steps:

[0056] Step 1: Collect the 3D geometric data and machining constraints of the mold parts to generate an initial dataset; this includes the following steps:

[0057] The three-dimensional geometric model of the mold part is obtained by laser scanning or CAD modeling system, and the curvature distribution information of each surface is extracted, including the principal curvature and Gaussian curvature of each point on the model surface, forming a continuous curvature distribution map.

[0058] The curvature distribution information is discretized and divided into multiple curvature intervals (e.g., low curvature, medium curvature, high curvature), and the point density in each interval is calculated.

[0059] Combining the sampling density and the preset sampling step size, the distribution ratio of sampling points in each region is calculated using the formula: Sp i =D i / ΣDi Sp i D represents the sampling ratio of the i-th curvature interval. i This represents the point density within the interval; the formula embodies the "density-driven" sampling concept, meaning that regions with denser geometric features (higher point density) should be allocated more sampling resources to ensure the accuracy of key region representation. Based on the sampling point allocation ratio, adaptive sampling is performed within each curvature interval to generate a representative spatial point cloud set.

[0060] Step 2: Extract features from the initial dataset to identify geometric features and constraint boundaries in the processing path; including the following steps:

[0061] Perform neighborhood topology analysis on the point cloud set in the initial dataset to determine the local surface change trend of each point; specifically: in the generated spatial point cloud set, construct a local neighborhood region (e.g., K-nearest neighbor or fixed radius spherical neighborhood) for each point as the center, and determine the surface change trend of the region where the point is located by calculating the geometric relationship between points in the region (e.g., normal vector consistency, rate of curvature change, etc.).

[0062] Based on the local surface change trend, curvature change regions are extracted as potential geometric feature boundaries. Specifically, regions with significantly inconsistent local surface change trends (such as the angle between the normal vectors of adjacent points exceeding a set threshold) are marked as curvature change regions. These regions usually represent key geometric features such as edges, corners, or parting lines on the part.

[0063] By combining the geometric feature boundaries with the projection relationship of the machining direction, the infeasible region affected by tool interference can be calculated using the formula: I = S × (1 - cosθ), where I represents the interference intensity, S represents the contact area, and θ represents the angle between the tool axis direction and the surface normal. The larger the angle between the tool axis direction and the surface normal (i.e., the smaller cosθ), the more severe the tool tilt and the higher the interference risk. Simultaneously, if the contact area S is large, the actual interference effect is more significant. Therefore, this formula can be used to quantitatively assess the interference probability of each region. By combining the infeasible region with the geometric feature boundaries, the actual usable machining path constraint range is delineated.

[0064] Step 3: Construct a multi-objective optimization framework based on the geometric features and constraint boundaries; including the following steps:

[0065] Based on geometric feature boundaries and constraint ranges, the processing area is divided into multiple sub-regions, and the surface tilt angle and contact risk level of each sub-region are marked. A path planning priority is assigned to each sub-region, with the priority value determined based on the inverse relationship between the contact risk level and the surface tilt angle, using the formula: Q i =1 / (R) i +Ai ), where Q i R represents the path planning priority of the i-th sub-region. i Indicates the exposure risk value for this area, A i This represents a quantified value of surface tilt; the formula reflects the principle that areas with "low risk + small tilt" should be prioritized for treatment. When the contact risk R of a certain area... i Smaller and tilt angle A i When it is also relatively small, its priority Q i A higher value means that the area is more suitable for arranging high-quality, efficient cutting paths.

[0066] Based on path planning priorities, three parallel optimization objectives are set: minimizing idle travel distance, balancing cutting load distribution, and reducing the number of inflection points. These three objectives are not equally important and can be optimized according to their priority Q in different sub-regions. i Dynamically adjust weight allocation to ensure optimal path configuration for key areas. Map the priority of each sub-region to its corresponding target weight to form a target-oriented optimization space structure. Based on the priority Q of each sub-region... i This is mapped to weighted coefficients for the three optimization objectives mentioned above, for example:

[0067] High-priority areas: focus on minimizing idle travel and reducing inflection points;

[0068] Medium priority areas: Focus on load balancing;

[0069] Low priority areas: focus on path feasibility.

[0070] Finally, these weighted objectives are integrated into a unified optimization space structure to guide the subsequent path search process.

[0071] Step 4: Within the multi-objective optimization framework, generate a set of candidate processing paths through iterative calculation; including the following steps:

[0072] A set of initial path sequences is randomly generated within the optimized spatial structure to serve as the first-generation path population; these paths satisfy basic geometric constraints and the priority distribution of each sub-region is initially considered.

[0073] Fitness is evaluated for each path in the initial path population, based on a weighted sum of path length, load fluctuation amplitude, and number of inflection points. A weighted scoring mechanism is used to evaluate the fitness of each path: Score = w1×L + w2×F + w3×T, where:

[0074] L: Total path length;

[0075] F: Cutting load fluctuation value, reflecting the degree of drastic change in cutting force between different areas on the path;

[0076] T: The number of inflection points in the path;

[0077] w1, w2, w3: These represent the weighting coefficients of the three indicators, which sum to 1 and are set according to process requirements.

[0078] This formula embodies the core idea of ​​multi-objective optimization, which is to find a balance among multiple performance indicators. For example, if efficiency is emphasized, then w1 is increased; if stability is emphasized, then w2 is increased.

[0079] Based on the fitness score, high-scoring paths are selected, and a new batch of paths is generated through cross-joining and mutation operations. The formula is: X new =(X parent1 *W1)+(X parent2 *W2), where X new X represents the position sequence of the newly generated path. parent1 、(X parent2 W1 and W2 represent the position sequence of the parent path, and W1 and W2 represent the weight coefficients of the parent path. This formula simulates the "gene recombination" process in biological heredity, and merges some segments of two paths through linear combination to form a new path with the advantages of both.

[0080] Repeat the fitness evaluation and path update process until the preset number of iterations (such as 50 or 100 times) is reached, and finally output a set of candidate processing paths.

[0081] Step 5: Perform multi-dimensional comparative analysis on the candidate processing path set to select the Pareto optimal solution set; including the following steps:

[0082] For each path in the candidate machining path set, perform multi-objective performance ranking and record the independent ranking of each path under three indicators: path length (the shorter the better), cutting force fluctuation (the smaller the better), and surface quality (the higher the better). Assign a ranking value (e.g., 1st, 2nd, etc.) to each path in each indicator for subsequent comprehensive evaluation.

[0083] The formula for calculating the overall advantage index of each path is as follows:

[0084] Where S i This represents the overall advantage index of the i-th path. These represent the path's ranking among the three indicators. The core idea of ​​this formula is to sum the rankings of the three indicators and take the reciprocal, so that the path with the higher ranking receives a higher overall score. This design avoids subjective bias caused by manually setting weights and is suitable for comprehensive evaluation under multi-objective, unbiased conditions.

[0085] The paths are sorted from high to low based on the comprehensive advantage index, and a threshold is set to select the top N paths as the initial preferred path group; N can be set according to actual needs (such as taking the top 10% or a fixed number such as 10 paths).

[0086] Within the initially selected path group, pairwise comparisons are performed to exclude completely dominated paths and retain non-dominated paths to form a Pareto optimal solution set. This process can be achieved by constructing a dominance matrix or comparing each path individually, ultimately outputting a set of optimal paths that are mutually non-dominated and have balanced performance.

[0087] Step Six: Based on the Pareto optimal solution set and combined with the process experience database, dynamically adjust the path parameters to generate an improved path scheme; including the following steps:

[0088] Each path in the Pareto optimal solution set is matched with historical processing parameters in the process experience database to find historical cases with similarity higher than a set threshold.

[0089] Based on the tool compensation values ​​and feed rate settings from historical cases, parameter mapping adjustments are made to a local area of ​​the current path, using the formula: V adj =V base *(C new / C old ), where V adj V represents the adjusted feed rate. base C represents the original set speed. new With C old These represent the compensation values ​​for the old and new tools, respectively; this formula reflects the impact of tool compensation changes on cutting efficiency. When using a smaller radius tool (i.e., C... new <C old To ensure cutting stability, the feed rate should be appropriately reduced; conversely, the feed rate should be increased.

[0090] The path is re-arranged into segments based on the adjusted parameters, prioritizing the merging of adjacent path segments with consistent processing conditions. This merging operation reduces the number of path switching operations and mitigates the impact of frequent machine tool start-ups and shutdowns. Transitional arcs are introduced into the rearranged path structure to replace sharp-corner connections, creating a continuous and stable improved path scheme.

[0091] Step 7: Perform a local search on the improved path scheme, and optimize the smoothness of path inflection points and transition segments through a neighborhood perturbation strategy; including the following steps:

[0092] Identify the inflection points and direction vectors of adjacent path segments in the improved path scheme; an inflection point is defined as a point where the change in the tangent direction angle of the path exceeds a certain threshold; the direction vector can be obtained from the coordinate difference between two points, for example, for two points P on the path. i (x i ,y i) and P i+1 (x i+1 ,y i+1 Its direction vector is V = (x i+1 -x i ,y i+1 -y i ).

[0093] A local disturbance region is set around the inflection point, and small displacement adjustments are applied to the path points within the region, with the displacement direction perpendicular to the path's forward direction. The curvature change rate of the transition segment is calculated based on the position of the path points after the disturbance, using the formula: K = (θ2 - θ1) / L, where K represents the curvature change rate, θ2 and θ1 are the tangent angles of the path segment before and after the disturbance, and L represents the length of the disturbance segment. The curvature change rate is a key indicator for measuring path smoothness; a lower K value indicates a smoother turning transition, which helps reduce tool wear and workpiece surface defects. If the curvature change rate exceeds a set threshold, the disturbance amplitude is reduced and adjustments are repeated until the inflection point connection becomes a natural transition and the path continuity meets machining requirements.

[0094] Step 8: Verify the feasibility of the improved path scheme, output the final machining path, and generate CNC code; including the following steps:

[0095] Using CAM software or a dedicated simulation system, the improved path scheme is imported into the simulation environment. The system simulates the actual trajectory of the tool along the path based on the path coordinate sequence and the set tool parameters. During the simulation, the contact state between the tool and the workpiece is detected, and areas of overcutting or undercutting are marked. The geometric relationship between the tool and the workpiece model is detected in real time during the simulation: if the tool cuts into the workpiece beyond the design contour, it is marked as "overcutting"; if the tool does not completely remove the material that should be removed, it is marked as "undercutting".

[0096] The deviation volume is calculated for areas where overcutting or undercutting occurs, using the formula: V err =Σ(h i *A i ), where V err h represents the total deviation volume. i A represents the height difference of the i-th unit. i The formula represents the corresponding area. Based on the concept of the infinitesimal method, the entire error region is divided into multiple small units. The product of the height difference and the area is calculated separately and then summed to obtain a quantitative index of the overall error.

[0097] If the deviation volume is less than the upper limit of the allowable error, the path is considered feasible; otherwise, return to adjust the path parameters and repeat the verification process. A maximum allowable deviation volume threshold, Vmax, is set as the criterion for whether the path is qualified.

[0098] If V errIf the value is less than or equal to Vmax, then the current path is considered to meet the machining requirements, and the process can proceed to the next step of generating CNC code.

[0099] If V err If Vmax is greater than the maximum value, you need to return to the path optimization stage (such as step six or seven), adjust the relevant parameters (such as feed rate and path smoothness), and then re-verify.

[0100] By constructing a closed-loop verification mechanism, we can ensure that the final output path meets the engineering accuracy requirements, significantly reduce trial cutting costs and scrap rates, and improve processing efficiency and finished product quality consistency.

[0101] On the other hand, this invention proposes a precision mold design system based on an intelligent optimization algorithm, comprising:

[0102] The preprocessing module is used to collect the three-dimensional geometric data and machining constraints of the mold parts and generate the initial dataset;

[0103] The boundary recognition module is used to extract features from the initial dataset and identify geometric features and constraint boundaries in the processing path.

[0104] The path generation module is used to construct a multi-objective optimization framework based on the geometric features and constraint boundaries, and generate a set of candidate processing paths through iterative calculation under the multi-objective optimization framework.

[0105] The parameter adjustment module is used to perform multi-dimensional comparative analysis on the candidate processing path set, screen out the Pareto optimal solution set, and dynamically adjust the path parameters based on the Pareto optimal solution set and the process experience database to generate an improved path scheme.

[0106] The path optimization verification and output module is used to perform local search on the improved path scheme, optimize the smoothness of path inflection points and transition segments through a neighborhood perturbation strategy, verify the feasibility of the improved path scheme, output the final machining path and generate CNC code.

[0107] In addition, the modules mentioned above are also used to implement other steps of the aforementioned precision mold design method based on intelligent optimization algorithms, as follows:

[0108] Step 1: Generate the initial dataset

[0109] Input data: Obtain the 3D model of the mold. The surface curvature distribution shows that there are 3 main curvature ranges (low, medium, and high).

[0110] Discretization: Calculate the point density for each interval D1=100, D2=200, D3=300, and the total density ΣD. j =600.

[0111] Calculate the sampling ratio:

[0112] Sp1 = 100 / 600 = 0.1667 (sampling ratio in the low curvature region);

[0113] Sp2 = 200 / 600 = 0.3333 (medium curvature region);

[0114] Sp3 = 300 / 600 = 0.5 (high curvature region);

[0115] Adaptive sampling: Generates point cloud sets proportionally, with more sampling points in high curvature areas (e.g., out of a total of 6000 points, 3000 are in high curvature areas).

[0116] Step 2: Identify geometric features and constraint boundaries

[0117] Neighborhood analysis: Abrupt curvature changes were found at corners and marked as potential feature boundaries.

[0118] Interference calculation: Contact area S = 50 mm² 2 Given that the angle between the tool axis and the normal is θ = 30° and cosθ = 0.866, the interference intensity I = 50 × (1 - 0.866) = 6.7 mm. 2 This area was determined to be infeasible.

[0119] Constraint range: After excluding the interference area, determine the boundary of the available processing path.

[0120] Step 3: Construct a multi-objective optimization framework

[0121] Zoning priority: If the contact risk of a certain sub-region is R=0.5 and the surface slope is A=0.2, then Q=1 / (0.5+0.2)=1.4286.

[0122] Optimization objectives: Minimize idle travel (weight 40%), balance load (30%), and reduce inflection points (30%).

[0123] Optimization space: Map priority Q to target weight to generate priority-driven path planning space.

[0124] Step 4: Generate a set of candidate paths

[0125] Initial paths: 100 paths are randomly generated (first generation population).

[0126] Fitness assessment: Path length = 500mm, load fluctuation = 15%, number of inflection points = 8, weighted score = 500×0.4 + 15×0.3 + 8×0.3 = 200 + 4.5 + 2.4 = 206.9.

[0127] Crossover and mutation: Parent path 1 (X) parent1 ) and parent path 2 (X parent2With weights W1 = 0.6 and W2 = 0.4, the new path X... new =X parent1 ×0.6+X parent2 ×0.4.

[0128] Iterative optimization: After 50 iterations, 20 candidate paths are generated.

[0129] Step 5: Select the Pareto optimal solution set

[0130] Multi-objective ranking: A certain path ranks 1st, 2nd, and 3rd in length, cutting force, and quality index, respectively.

[0131] Overall advantage index: S = 1 / (1+2+3) = 0.1667. The top 5 paths after sorting are selected as the preferred path group.

[0132] Non-dominated selection: Exclude the 3 paths that are completely dominated by other paths, and finally retain the 2 Pareto optimal paths.

[0133] Step Six: Generate an Improved Path Solution

[0134] Historical matching: A historical case with a similarity > 85% was found, and its tool compensation value C was set. old =1.2, C new =1.5.

[0135] Parameter adjustment: Original feed rate V base =1000mm / min, V after adjustment adj =1000×(1.5 / 1.2)=1250mm / min.

[0136] Route rearrangement: Merge adjacent path segments to reduce empty trips by 15%.

[0137] Transition optimization: Inserting transition arcs improves the smoothness of inflection point connections by 30%.

[0138] Step 7: Optimize the smoothness of the inflection point

[0139] Disturbance area: The tangent angles before and after the disturbance at a certain inflection point are θ1 = 45° and θ2 = 60°, and the length of the disturbance segment is L = 5mm.

[0140] Curvature change rate: K = (60-45) / 5 = 3° / mm. If the threshold is 2° / mm, then reduce the disturbance amplitude to L = 7.5mm and K = 2° / mm.

[0141] Step 8: Verify Feasibility

[0142] Simulation detection: Three overcut regions were marked, with a height difference h. i =0.1mm, area A i =20mm2 (5 units in total)

[0143] Deviation volume: V err =5 × 0.1 × 20 = 10 mm 3 The maximum allowable thickness is 15mm. 3 The path is deemed feasible.

[0144] Output results: Generates CNC code (G code), improves machining efficiency by 20%, and achieves surface roughness Ra≤1.6μm.

[0145] In summary, through the above process, the machining path of this mold ensures accuracy while reducing idle strokes, improving cutting stability, and eliminating the need for multiple trial cuts, thus significantly shortening the development cycle.

[0146] Finally, it should be noted that the above description is only 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 can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A precision mold design method based on intelligent optimization algorithms, characterized in that, Includes the following steps: Collect the three-dimensional geometric data and machining constraints of the mold parts to generate an initial dataset; Feature extraction is performed on the initial dataset to identify geometric features and constraint boundaries in the processing path; A multi-objective optimization framework is constructed based on the geometric features and constraint boundaries. Under the multi-objective optimization framework, a set of candidate processing paths is generated through iterative calculation. A multidimensional comparative analysis is performed on the candidate processing path set to select the Pareto optimal solution set. Based on the Pareto optimal solution set and combined with the process experience database, the path parameters are dynamically adjusted to generate an improved path scheme. The improved path scheme is locally searched, and the smoothness of path inflection points and transition segments is optimized through a neighborhood perturbation strategy. The feasibility of the improved path scheme is verified, and the final machining path is output and CNC code is generated. The process of identifying geometric features and constraint boundaries in the machining path includes: performing neighborhood topology analysis on the point cloud set in the initial dataset to determine the local surface change trend of each point; extracting curvature abrupt change regions as potential geometric feature boundaries based on the local surface change trend; combining the geometric feature boundaries with the projection relationship of the machining direction to calculate infeasible regions affected by tool interference; and delineating the actually usable machining path constraint range by combining the infeasible regions with the geometric feature boundaries. A multi-objective optimization framework is constructed based on the geometric features and constraint boundaries, including: dividing the machining area into multiple sub-regions based on the geometric feature boundaries and constraint ranges, and marking the surface tilt angle and contact risk level of each sub-region; setting path planning priorities for each sub-region, and setting three parallel optimization objectives based on the path planning priorities: minimizing the idle travel distance, balancing the cutting load distribution, and reducing the number of inflection points; mapping the priorities of each sub-region to the corresponding objective weights to form an objective-oriented optimization space structure. The step of generating a candidate processing path set through iterative calculation includes: randomly generating a set of initial path sequences within the optimized spatial structure as a first-generation path population; evaluating the fitness of each path in the initial path population, with the scoring criteria being a weighted sum of path length, load fluctuation amplitude, and the number of inflection points; selecting high-scoring paths based on the fitness score results, and generating a new batch of paths through cross-joining and mutation operations, wherein the position sequence of the new paths is generated by a weighted combination of the position sequence of the parent paths and weight coefficients; repeating the fitness evaluation and path update process until a preset number of iterations is reached, and finally outputting the candidate processing path set. The process of selecting the Pareto optimal solution set includes: ranking each path in the candidate machining path set according to its multi-objective performance, and recording the independent ranking of each path under the three indicators of path length, cutting force fluctuation, and surface quality; calculating the comprehensive advantage index of each path; ranking the paths from high to low according to the comprehensive advantage index, and setting a threshold to select the top N paths as the preliminary preferred path group; performing pairwise comparisons within the preliminary preferred path group, excluding paths that are completely dominated, and retaining non-dominated paths to form the Pareto optimal solution set; The process of generating an improved path scheme includes: matching each path in the Pareto optimal solution set with historical machining parameters in the process experience database to identify historical cases with a similarity higher than a set threshold; adjusting the parameters of a local area of ​​the current path based on the tool compensation value and feed rate settings in the historical cases, wherein the adjusted feed rate is determined by the ratio between the original set rate and the old and new tool compensation values; re-arranging the path in segments based on the adjusted parameters, prioritizing the merging of adjacent path segments with consistent machining conditions; and introducing transition arcs to replace sharp corner connections in the rearranged path structure to form a continuous and stable improved path scheme. The optimization of the smoothness of inflection points and transition segments includes: identifying the inflection point positions and direction vectors of adjacent path segments in the improved path scheme; setting a local disturbance region around the inflection point and adjusting the displacement of path points within the region, with the displacement direction perpendicular to the path's forward direction; calculating the curvature change rate of the transition segment based on the position of the path points after the disturbance; if the curvature change rate exceeds a set threshold, reducing the disturbance amplitude and repeating the adjustment until the inflection point connection tends to be a natural transition and the path continuity meets the processing requirements; Verifying the feasibility of the improved path scheme includes: importing the improved path scheme into a simulation environment to simulate the actual trajectory of the tool moving along the path; detecting the contact state between the tool and the workpiece during the simulation process and marking areas where overcutting or undercutting occurs; calculating the deviation volume for the areas where overcutting or undercutting occurs; if the deviation volume is less than the upper limit of the allowable error, the path is determined to be feasible; otherwise, the process is returned to adjust the path parameters and the verification process is repeated.

2. The precision mold design method based on intelligent optimization algorithm according to claim 1, characterized in that: The process of acquiring the three-dimensional geometric data and machining constraints of the mold parts to generate the initial dataset includes the following steps: Obtain the three-dimensional geometric model of the mold part and extract the curvature distribution information of each surface; The curvature distribution information is discretized and divided into multiple curvature intervals, and the point density in each interval is calculated. By combining the point density with the preset sampling step size, the distribution ratio of sampling points in each region is calculated; Based on the sampling point allocation ratio, adaptive sampling is performed in each curvature interval to generate a spatial point cloud set.

3. A precision mold design system based on an intelligent optimization algorithm for implementing the method as described in any one of claims 1-2, characterized in that: include: The preprocessing module is used to collect the three-dimensional geometric data and machining constraints of the mold parts and generate the initial dataset; The boundary recognition module is used to extract features from the initial dataset and identify geometric features and constraint boundaries in the processing path. The path generation module is used to construct a multi-objective optimization framework based on the geometric features and constraint boundaries, and generate a set of candidate processing paths through iterative calculation under the multi-objective optimization framework. The parameter adjustment module is used to perform multi-dimensional comparative analysis on the candidate processing path set, screen out the Pareto optimal solution set, and dynamically adjust the path parameters based on the Pareto optimal solution set and the process experience database to generate an improved path scheme. The path optimization verification and output module is used to perform local search on the improved path scheme, optimize the smoothness of path inflection points and transition segments through a neighborhood perturbation strategy, verify the feasibility of the improved path scheme, output the final machining path and generate CNC code.

Images