A high-precision part processing path planning method optimized based on artificial intelligence

Abstract

The present invention discloses a high-precision part processing path planning method optimized based on artificial intelligence, comprising the following steps: generating a first three-dimensional geometric model of a part to be processed and performing surface division, and obtaining manufacturing feature points according to the division result; determining a processing placement surface for the first three-dimensional geometric model according to the manufacturing feature points, performing machining element positioning and shaping, and obtaining a second three-dimensional geometric model; performing preliminary planning of the processing path, and optimizing it based on the balance of mixing using a neural network, and outputting a second planned processing path; performing path optimization based on the Gaussian distribution function and cubic spline curve to obtain a third planned processing path; performing simulation verification, and performing path adjustment and optimization using a hierarchical optimization ant colony algorithm according to the verification result, and outputting a final planned processing path. The present invention improves the accuracy, efficiency, flexibility and adaptability in the processing of high-precision parts.

Description

Technical Field

[0001] The present invention relates to the technical field of computer-aided manufacturing, and in particular to a high-precision parts machining path planning method based on artificial intelligence optimization. Background Art

[0002] With the continuous improvement of the precision, efficiency and intelligence level of parts processing in modern manufacturing, how to achieve efficient processing of high-precision parts in complex processing environments has become an important challenge in the manufacturing field. Traditional part processing path planning methods usually rely on empirical rules and manual intervention, and there are problems such as low path planning efficiency, difficulty in ensuring processing accuracy and long processing time. Especially when facing parts with complex shapes, traditional methods often have difficulty in handling their complex geometric features, resulting in difficulties in optimizing the processing path, and may even cause collisions and errors during the processing process.

[0003] With the rapid development of artificial intelligence technology, path planning methods based on artificial intelligence have gradually attracted widespread attention. In particular, by using neural networks, optimization algorithms, simulation verification and other means, it is possible to automatically generate and optimize processing paths according to the geometric characteristics of the processed parts and the processing environment, which can not only improve the processing accuracy, but also significantly improve the efficiency of path planning and reduce manual intervention. However, the existing path planning methods based on artificial intelligence still have certain limitations. For example, traditional neural network optimization methods cannot effectively handle small errors in high-precision processing, and smoothness and collision detection in the path optimization process often face great challenges. In addition, the real-time and adaptive capabilities of path planning have not been fully improved, resulting in potential path planning errors in the processing of some high-precision parts.

[0004] Therefore, how to propose an efficient, intelligent and accurate part processing path planning method by combining artificial intelligence algorithms, optimization technology and high-precision processing characteristics has become an important issue that needs to be urgently solved in the current manufacturing field. Summary of the invention

[0005] In order to overcome the shortcomings of the prior art, the present invention provides a high-precision parts machining path planning method based on artificial intelligence optimization, which is used to solve the technical problems that the existing machining path planning method cannot effectively handle small errors, the real-time performance of path planning and the lack of adaptability, thereby improving the accuracy, efficiency, flexibility and adaptability of high-precision parts machining.

[0006] To solve the above problems, the technical solution adopted by the present invention is as follows:

[0007] A high-precision parts machining path planning method based on artificial intelligence optimization includes the following steps:

[0008] Generate the first three-dimensional geometric model of the part to be processed and perform surface division, and obtain manufacturing feature points according to the division result;

[0009] Determine the machining placement surface for the first three-dimensional geometric model according to the manufacturing feature points, perform machining element positioning and shaping, and obtain the second three-dimensional geometric model;

[0010] Conduct preliminary planning of the machining path, and use a neural network to optimize based on a mixed equilibrium to output the second planned machining path;

[0011] Based on the Gaussian distribution function and cubic spline curve for path optimization to obtain the third planned machining path;

[0012] Conduct simulation verification, and perform path adjustment and optimization according to the verification result using a hierarchical optimization ant colony algorithm to output the final planned machining path.

[0013] As a preferred embodiment of the present invention, when generating the first three-dimensional geometric model, it includes:

[0014] Obtain the geometry of the part to be processed and all its edges, and put them into the edge set ;

[0015] Obtain the edges with the arc type in the edge set and put them into the arc edge subset ;

[0016] Obtain the arc center points of all the edges in the arc edge subset and put them into the center point set , and the number of center points is ;

[0017] Provide a temporary maximum center point set , maximum center point set , parameter , parameter ;

[0018] If , then execute the parallel judgment step;

[0019] If , then execute the first three-dimensional geometric model generation step.

[0020] As a preferred embodiment of the present invention, when performing surface division, it includes:

[0021] Obtain the surface area in the first three-dimensional geometric model and perform spline surface configuration;

[0022] According to The spline surface configuration obtains the first-order and second-order partial derivatives of the surface area;

[0023] Regard the area where both the first-order and second-order partial derivative deviations are less than the threshold as a region set, thereby dividing the surface area into several surface sub-regions.

[0024] As a preferred embodiment of the present invention, when obtaining the manufacturing feature points, it includes:

[0025] Perform convex edge decomposition based on several surface sub-regions, and match with the base surface and the predefined manufacturing template to obtain the manufacturing feature points , and assign the geometric surface mapping attribute at the same time;

[0026] When determining the machining placement surface, it includes:

[0027] Obtain the surface set of the manufacturing feature points , and obtain the adjacent surface set from the first three-dimensional geometric model for the surface set ; ;

[0028] If there is a unique surface in the surface set , then use the unique surface as the machining placement surface ;

[0029] If there are multiple surfaces in the surface set , then obtain the surface parallel to the base surface among the multiple surfaces, and take the surface with the largest distance from the base surface as the machining placement surface .

[0030] As a preferred embodiment of the present invention, when performing machining element positioning, it includes:

[0031] Obtain the positioning surface , positioning surface from the manufacturing feature points , and identify the types of the positioning surface , positioning surface , and construct the corresponding machining element coordinate system according to the identification result;

[0032] When performing machining element shaping, it includes:

[0033] Traverse the parameter variable set of the manufacturing feature points , determine the meaning of the parameter variable by the name of the parameter variable in the parameter variable set , obtain the geometric surface associated with the parameter variable according to the association relationship between the parameter variable and the attribute adjacency graph, and determine the value of the parameter variable.

[0034] As a preferred embodiment of the present invention, when initially planning the machining path, it includes:

[0035] Construct a road network 0-1 matrix for the machining path according to the second three-dimensional geometric model;

[0036] Obtain the connection degree index of the manufacturing feature points and obtain the matrix of the shortest path between any two manufacturing feature points through an algorithm, obtain the betweenness of all manufacturing feature points , and analyze the betweenness index to obtain the first planned machining path.

[0037] As a preferred embodiment of the present invention, when outputting the second planned machining path, it includes:

[0038] Divide the first planned machining path into several equal parts at preset time intervals , , where

[0039] are the start and end times of the machining path; Obtain the position of the machining tool at , and the position of the manufacturing feature point closest to the machining tool at at ;

[0040] Obtain the standby position of the machining tool when starting machining , and the position of the first manufacturing feature point on the first planned machining path at ;

[0041] Construct a rectangular coordinate system with and as the origin based on time and position.

[0042] As a preferred embodiment of the present invention, when outputting the second planned machining path, it further includes:

[0043] Input the coordinates at as the training samples of the neural network, and use the error function of the neural network and to obtain the gain coefficient as the output by using the position difference corresponding to time and time; Input the position change at the next moment back into the neural network and output the real-time updated gain coefficient for adaptive optimization until reaching the hybrid-based

[0044] ​Balance and output the second planned machining path.

[0045] As a preferred embodiment of the present invention, when performing path optimization, it includes:

[0046] Define a Gaussian distribution function in the machining environment, perform random sampling within a preset range near the obstacle to generate random sampling points , select the point which is away from the random sampling point and located on the second planned machining path ;

[0047] Judge whether the collision situations of and are the same. If they are the same, discard the corresponding . If they are not the same, retain the corresponding to obtain a collision-free point planned machining path;

[0048] Smooth the collision-free point planned machining path through a cubic spline curve to obtain the third planned machining path;

[0049] wherein, is a preset distance.

[0050] As a preferred embodiment of the present invention, when performing path adjustment and optimization, it includes:

[0051] Divide the manufacturing feature points on the third planned machining path into several sub-regions according to the axis coordinate values;

[0052] Take each sub-region as a small-scale and optimize it using the ant colony algorithm to obtain an optimized data set for each sub-region;

[0053] Take the optimized data set of each sub-region as a new small-scale , and use the ant colony algorithm for optimization again to obtain the final planned machining path;

[0054] wherein, the ant colony algorithm includes: each ant starts from the starting point of the third planned machining path, moves along the third planned machining path, and gradually adjusts and optimizes the path according to the pheromone concentration and heuristic information.

[0055] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0056] (1) Improve machining accuracy and efficiency

[0057] The present invention realizes the precise planning of the machining path for high-precision parts through an optimization method based on artificial intelligence (including neural networks and ant colony algorithms). Compared with traditional path planning methods, the present invention can dynamically adjust the machining path according to the geometric features of the parts and the machining environment, thereby effectively reducing errors and improving the dimensional accuracy, surface roughness, and shape accuracy of the parts. The optimized path not only reduces the machining time but also effectively avoids collisions and unnecessary machining in the path, significantly improving the machining efficiency.

[0058] (2) Intelligent path optimization and real-time adaptive adjustment

[0059] The present invention combines neural networks with hybrid equilibrium technology and can adjust the machining path according to real-time feedback. Especially in complex machining environments, it can perform adaptive optimization of the path based on the real-time position and state of the machining tool. This intelligent path planning method makes the machining process more efficient and flexible, and can meet the requirements of different working conditions and part complexities.

[0060] (3) Applicability in various machining scenarios

[0061] By introducing the Gaussian distribution function and cubic spline curve optimization technology into the machining path planning, the present invention can provide the optimal machining path in various complex machining scenarios (such as the machining of high-precision and high-complexity parts, difficult-to-machine materials, etc.). Especially in the case of more obstacles or special machining requirements, it can effectively avoid collisions with obstacles and ensure the continuity and smoothness of the machining path through smooth optimization processing, thereby improving the machining quality and tool life.

[0062] (4) Simulation verification and comprehensive evaluation mechanism

[0063] The present invention ensures the practical feasibility and machining effect of the planned path through a multi-dimensional verification mechanism of tool path simulation and surface roughness, dimensional accuracy, shape error, etc. Using advanced measurement technologies such as high-precision probes, coordinate measuring machines, and optical scanners, it comprehensively evaluates the accuracy of the parts after machining, provides a scientific basis for the subsequent machining process, and further optimizes the machining process to reduce the defect rate and rework rate.

[0064] (5) Optimized calculation method and path accuracy

[0065] The present invention uses the ant colony algorithm to perform hierarchical optimization of the machining path. By intelligently optimizing the machining path of each small block, it improves the accuracy and optimization degree of the path planning. The dynamic adjustment of the pheromone concentration on the path ensures the effectiveness of the optimization process, making the finally planned path not only accurate but also considering various constraint factors in actual machining, such as the characteristics of the machining tool and the rationality of the machining sequence.

[0066] (6)Ability to adapt to complex geometric features

[0067] By introducing technologies such as three-dimensional geometric model construction based on arc recognition, surface division, acquisition of manufacturing feature points, determination of machining placement surfaces, positioning of machining elements, and shaping of machining elements, the present invention can process parts with complex shapes, especially those containing multiple different surface types (such as concave-convex shapes, ellipses, cylindrical surfaces, etc.). When processing these parts, it can provide the most suitable machining path for each different geometric feature and minimize machining errors to the greatest extent through intelligent optimization.

[0068] (7)Applicable to multiple manufacturing environments

[0069] This method is applicable to multiple manufacturing environments and has strong versatility and scalability. In addition, combined with virtual simulation technology, it can be simulated and verified before actual machining to avoid potential problems during machining and improve the controllability and safety of the machining process.

[0070] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. Description of the drawings

[0071] Figure 1 is a step diagram of the high-precision part machining path planning method based on artificial intelligence optimization provided by the present invention;

[0072] Figure 2 is a schematic diagram of the hierarchical optimization ant colony algorithm provided by the present invention. Specific embodiments

[0073] The high-precision part machining path planning method based on artificial intelligence optimization provided by the present invention, as Figure 1 shown, includes the following steps:

[0074] Step S1: Generate a first three-dimensional geometric model of the part to be machined, divide the first three-dimensional geometric model into surfaces, and obtain manufacturing feature points according to the division results;

[0075] Step S2: Determine the machining placement surface for the first three-dimensional geometric model based on the manufacturing feature points, perform machining element positioning and machining element shaping to obtain a second three-dimensional geometric model;

[0076] Step S3: Perform preliminary machining path planning based on the second three-dimensional geometric model and the manufacturing feature points, and use a neural network to perform optimization based on a mixed equilibrium to output a second planned machining path;

[0077] Step S4: Optimize the second planned machining path based on the Gaussian distribution function and cubic spline curve to obtain a third planned machining path;

[0078] Step S5: Simulate and verify the third planned machining path to obtain verification results of collision, smoothness, stress, surface roughness, dimensional accuracy, and shape error;

[0079] Step S6: Adjust and optimize the path using the hierarchical optimization ant colony algorithm based on the verification results, and output the final planned machining path.

[0080] In the above Step S1, when generating the first three-dimensional geometric model of the part to be machined, it includes:

[0081] Obtain the geometry of the part to be machined, and based on the geometry, obtain all the edges of the part to be machined and put them into the edge set where, is an edge, is the number of edges;

[0082] Obtain all the edge types in the edge set and take out the edges with the edge type of arc type and put them into the arc edge subset ;

[0083] Obtain the arc center points of all the edges in the arc edge subset and put them into the center point set where, is the arc center point, is the number of center points;

[0084] Provide a temporary maximum center point set and a maximum center point set where, in the initial state, the temporary maximum center point set and the maximum center point set are both empty sets;

[0085] Provide parameters and parameter where, in the initial state, parameter and parameter ;

[0086] If , then execute the parallel judgment step. The parallel judgment step includes: Take out from the center point set and , and let , and judge whether the vector formed by the arc center point and is parallel to the vector and . If parallel, then the arc center point Add to the temporary maximum center point set If they are not parallel, then until is equal to Execute the assignment step;

[0087] If then execute the first three-dimensional geometric model generation step;

[0088] Among them, the assignment step includes: Let , , if the number of elements in the temporary maximum center point set is less than the number of elements in the maximum center point set , then continue to compare and , and execute the parallel judgment step or the first three-dimensional geometric model generation step according to the comparison result;

[0089] If the number of elements in the temporary maximum center point set is greater than or equal to the number of elements in the maximum center point set , then assign the temporary maximum center point set to the maximum center point set and then continue to compare and , and execute the parallel judgment step or the first three-dimensional geometric model generation step according to the comparison result;

[0090] The first three-dimensional geometric model generation step includes:

[0091] Take any two points from the maximum center point set and as the central axis vector of the part to be machined;

[0092] Take all the edges from the edge set , and obtain all the points on all the edges through the point set function, and put them into the point set ;

[0093] Obtain the perpendicular distance from each point in the point set to the central axis vector , and take the maximum value among them as the radius of the part to be machined;

[0094] Obtain the maximum projection distance of the vector formed by each point in the point set and along the central axis vector , the minimum projection distance , and take the maximum projection distance and the minimum projection distance The difference is used as the height of the part to be machined;

[0095] Increase the height and radius allowances, and create a sketch along the central axis vector Perform stretching to generate the first three-dimensional geometric model.

[0096] In the above step S1, when dividing the surface of the first three-dimensional geometric model, it includes:

[0097] Obtain the surface area in the first three-dimensional geometric model and perform Spline surface configuration as shown in Formula 1:

[0098] (1);

[0099] In the formula, is the spline surface of the surface area, is the curve in the horizontal direction in the surface area, is the curve in the vertical direction in the surface area, is the control point after configuring the spline surface, is the weight corresponding to the control point after configuring the spline surface, is the spline in the horizontal direction of the configured spline surface, is the spline in the vertical direction of the configured spline surface, is the number of splines in the horizontal direction of the configured spline surface, is the number of splines in the vertical direction of the configured

[0100] According to the spline surface configuration, obtain the first-order partial derivative and second-order partial derivative of the surface area as shown in Formula 2 and Formula 3:

[0101] (2);

[0102] In the formula, is the first-order partial derivative of the surface area, is the first-order partial derivative result of the surface area along the horizontal direction, is the first-order partial derivative result of the surface area along the vertical direction, is the curve in the horizontal direction in the surface area, is the curve in the vertical direction in the surface area;

[0103] (3);

[0104] In the formula, is the second-order partial derivative of the curved surface area, is the result of the second-order partial derivative of the curved surface area along the horizontal direction, is the result of the second-order partial derivative of the curved surface area along the vertical direction, is the result of the second-order partial derivative of the curved surface area first along the vertical direction and then along the horizontal direction; is the result of the second-order partial derivative of the curved surface area first along the horizontal direction and then along the vertical direction;

[0105] Regard the regions where both the first-order partial derivative and the second-order partial derivative deviation are less than the threshold as a region set, so as to divide the curved surface area into several curved surface sub-regions;

[0106] Among them, the several curved surface sub-regions include: curved surface regions of the plane type, curved surface regions of the concave cylindrical surface type, curved surface regions of the concave elliptical surface type, curved surface regions of the concave saddle surface type, curved surface regions of the convex cylindrical surface type, curved surface regions of the convex elliptical surface type, and curved surface regions of the convex saddle surface type.

[0107] In the above step S1, when obtaining the manufacturing feature points, it includes:

[0108] Perform convex edge decomposition based on several curved surface sub-regions, and match with the base surface and the predefined manufacturing template to obtain the manufacturing feature points , and at the same time endow the geometric surface mapping attribute;

[0109] When determining the machining placement surface, it includes:

[0110] Obtain the surface set of the manufacturing feature points , and obtain the surface set adjacent to the surface set from the first three-dimensional geometric model ;

[0111] If the surface set has a unique surface, then regard the unique surface as the machining placement surface of the manufacturing feature points ; ;

[0112] If the surface set has multiple surfaces, then obtain the surfaces parallel to the base surface among the multiple surfaces, and take the surface with the largest distance from the base surface among all the parallel surfaces as the machining placement surface of the manufacturing feature points ; .

[0113] In the above step S2, when performing machining element positioning, it includes:

[0114] From the manufacturing feature points Obtain the positioning surface and the positioning surface , and identify the types of the positioning surface and the positioning surface ;

[0115] The recognition results include: the positioning surface and the positioning surface are both the same cylindrical surface; the positioning surface is a plane, and the positioning surface is a cylindrical surface; the positioning surface and the positioning surface are both planes;

[0116] If the positioning surface and the positioning surface are both the same cylindrical surface: then obtain the intersection point of the axis of the cylindrical surface and the machining placement surface as the origin of the machining element coordinate system; obtain the normal vector of the machining placement surface , and obtain the vector perpendicular to it according to the normal vector , and obtain the vectors and respectively perpendicular to the normal vector ; use the vector , the vector and the normal vector as the axis of the machining element coordinate system;

[0117] If the positioning surface is a plane and the positioning surface is a cylindrical surface: then obtain the intersection point of the axis of the positioning surface and the machining placement surface as the origin of the machining element coordinate system; obtain the normal vector of the machining placement surface and the normal vector of the positioning surface , and obtain the vectors and respectively perpendicular to the normal vector ; use the normal vector , the vector and the normal vector as the axis of the machining element coordinate system;

[0118] If the positioning surface and the positioning surface are both planes: then obtain the positioning surface and the positioning surface The intersection point with the machining placement surface is used as the origin of the machining element coordinate system; obtain the normal vector of the machining placement surface , the normal vector of the positioning surface , the normal vector of the positioning surface ; use the normal vector , the vector and the normal vector as the axis of the machining element coordinate system;

[0119] When performing machining element shaping, it includes:

[0120] Traverse the parameter variable set of the manufacturing feature points , determine the meaning of the parameter variable through the name of the parameter variable in the parameter variable set . According to the association relationship between the parameter variable and the attribute adjacency graph, obtain the geometric surface associated with the parameter variable and determine the value of the parameter variable.

[0121] In step S3 above, when outputting the second planned machining path, it includes:

[0122] Construct a road network 0-1 matrix for the machining path according to the second 3D geometric model;

[0123] Use mathematical software to obtain the connectivity index of the manufacturing feature points . Through the algorithm, obtain the matrix of the shortest path between any two manufacturing feature points , obtain the betweenness of all manufacturing feature points , and analyze the betweenness index to obtain the first planned machining path;

[0124] Divide the first planned machining path into several equal parts at a preset time interval , is the start time of the machining path, is the end time of the machining path;

[0125] Obtain the position of the machining tool at the moment , , the position of the manufacturing feature point closest to the machining tool at the moment ;

[0126] Obtain the standby position of the machining tool when starting machining , the first manufacturing feature point on the first planned machining path​​​​​​ Position ;

[0127] Construct a rectangular coordinate system with the origin at and , where the abscissa is time and the ordinate is position;

[0128] Take the coordinates at the moment of and as the training samples input of the neural network, and use the error function of the neural network for the position difference corresponding to the moments of and to obtain the gain coefficient as the output; Output the gain coefficient after real-time update by re-inputting the position change at the next moment into the neural network for adaptive optimization until reaching the

[0129] hybrid-based equilibrium, ending the real-time planning, and outputting the second planned machining path;

[0130] Among them, the mathematical software includes: Software.

[0131] In the above step S4, when optimizing the path based on the Gaussian distribution function and the cubic spline curve, it includes:

[0132] Define a Gaussian distribution function in the machining environment, perform random sampling within a preset range near the obstacle to generate random sampling points , and select the point with a distance of from the random sampling point and located on the second planned machining path ;

[0133] Judge whether the collision situations of and are the same. If the collision situations are the same, discard the corresponding , and if the collision situations are different, retain the corresponding to finally obtain the collision-free point planned machining path within the range near the obstacle;

[0134] Smooth the collision-free point planned machining path through the cubic spline curve to obtain the third planned machining path, as shown in Formula 4:

[0135] (4);

[0136] In the formula, is the Equation of segment control points is a cubic basis function of spline is the third planned machining path;

[0137] Among them, is a preset distance.

[0138] In the above step S5, when performing simulation verification, it includes:

[0139] Let the second three-dimensional geometric model be , and the geometric model of the tool be ;

[0140] By the bounding box method, , are respectively represented by the packaging boxes , ;

[0141] Based on the third planned machining path, run the tool. If appears, it is considered that the third planned machining path will collide with the part to be machined;

[0142] Obtain the curvature change rate of the third planned machining path, as shown in Formula 5:

[0143] (5);

[0144] In the formula, is the curvature change rate, is the tangent angle of the third planned machining path, is the length of the third planned machining path;

[0145] Judge whether the curvature change rate is less than the preset value. If so, it is considered that the smoothness of the third planned machining path meets the requirements;

[0146] Use the tool path simulation software to simulate the force on the tool on the third planned machining path and identify whether there is an area where the tool stress exceeds the threshold;

[0147] Use the tool path simulation software to simulate the third planned machining path, and respectively use a high-precision probe, a coordinate measuring machine and an optical scanner to evaluate the surface roughness, dimensional accuracy and shape error of the machined part;

[0148] Among them, use a high-precision probe to measure the surface of the machined part, and evaluate the surface roughness with the average value of the absolute value of the deviation of the surface profile from the average line, as shown in Formula 6:

[0149] (6);

[0150] In the formula, is the height of each point on the surface of the machined part, is the average height of the surface of the machined part, is the number of sampling points of the height data of the part surface, is the average value of the absolute value of the deviation of the surface profile from the average line;

[0151] The machined part is precisely measured using a coordinate measuring machine, and the dimensional accuracy is evaluated based on the dimensional error obtained by comparing with the target dimensions in the CAD model, as shown in Formula 7:

[0152] (7);

[0153] In the formula, is the dimensional error, is the measured dimension of the machined part, is the target dimension;

[0154] The machined part is three-dimensionally scanned using an optical scanner, and the shape error is evaluated based on the shape error obtained by overlapping and comparing with the CAD model, as shown in Formula 8:

[0155] (8);

[0156] In the formula, is the surface point of the machined part, is the surface point of the CAD model.

[0157] In the above step S6, as Figure 2 shown, when performing path adjustment and optimization, it includes:

[0158] Dividing the manufacturing feature points on the third planned machining path by axis coordinate values into several sub-regions;

[0159] Regarding each sub-region as a small-scale Optimizing using the ant colony algorithm to obtain an optimized data set for each sub-region;

[0160] Regarding the optimized data set of each sub-region as a new small-scale and optimizing again using the ant colony algorithm to obtain the final planned machining path;

[0161] Among them, the ant colony algorithm includes:

[0162] Each ant starts from the starting point of the third planned processing path, moves along the third planned processing path, and gradually adjusts and optimizes the path according to the pheromone concentration and heuristic information; the update of the pheromone concentration on the path is shown in Equation (9):

[0163] (9);

[0164] In the formula, is the updated pheromone concentration on the path, is the current pheromone concentration on the path, is the newly added pheromone amount on the path, is the pheromone evaporation coefficient.

[0165] The above embodiments are only the preferred embodiments of the present invention, and the scope of protection of the present invention cannot be limited thereby. Any non-substantive changes and substitutions made by those skilled in the art based on the present invention fall within the scope of protection required by the present invention.

Claims

1. A high-precision parts machining path planning method based on artificial intelligence optimization, characterized in that: The following steps are involved: Generate a first three-dimensional geometric model of the part to be processed and perform surface division, and obtain manufacturing feature points according to the division results; Determine the processing placement surface for the first three-dimensional geometric model according to the manufacturing feature points, perform positioning and shaping of the processing elements, and obtain a second three-dimensional geometric model; Perform preliminary planning of machining paths and use neural networks based on hybrid Balanced optimization is performed and the second planned processing path is output; Based on Gaussian distribution function, cubic The spline curve is used to optimize the path and obtain the third planning processing path; Conduct simulation verification, and use the hierarchical optimization ant colony algorithm to adjust and optimize the path based on the verification results, and output the final planned processing path; Wherein, when generating the first three-dimensional geometric model, it includes: Get the geometry of the part to be processed and all its edges, and put them into the edge collection ; Get edge set The edges with arc type are put into the arc edge sub-collection middle; Get the arc edge subset The arc center points of all the edges in the circle are put into the center point set The center point number is ; Provides a temporary maximum circle center point set , the maximum circle center point set ,parameter ,parameter ; like , then execute the parallel judgment steps; like , then execute the first three-dimensional geometric model generation step; When performing path optimization, it includes: Define a Gaussian distribution function in the processing environment, perform random sampling within a preset range close to obstacles, and generate random sampling points , select random sampling points from the distance according to the Gaussian distribution function for , and the point located on the second planned processing path ; judge and Are the collision conditions the same? If so, the corresponding Discard, if not the same, then the corresponding Keep it and get the processing path without collision points; Through three times The spline curve is used to smooth the planned processing path without collision points to obtain the third planned processing path; in, is the preset distance; When adjusting and optimizing the path, include: The manufacturing feature points on the third planned processing path according to The axis coordinate values ​​are divided into several sub-areas; Treat each sub-area as a small Use ant colony algorithm to optimize and obtain optimized data sets for each sub-area; The optimized data set of each sub-area is used as a new small-scale , and the ant colony algorithm is used again for optimization to obtain the final planned processing path; The ant colony algorithm includes: each ant starts from the starting point of the third planned processing path, moves along the third planned processing path, and gradually adjusts the optimized path according to the pheromone concentration and heuristic information.

2. The high-precision parts machining path planning method based on artificial intelligence optimization according to claim 1 is characterized in that: When performing surface division, it includes: Get the surface area in the first 3D geometric model and perform Spline surface configuration; according to The spline surface configuration obtains the first-order and second-order partial derivatives of the surface area; The regions where the deviations of the first-order and second-order partial derivatives are both smaller than a threshold are classified as a region set, thereby dividing the surface region into several surface sub-regions.

3. The high-precision parts machining path planning method based on artificial intelligence optimization according to claim 2 is characterized in that: When obtaining manufacturing feature points, include: Convex edge decomposition is performed based on several surface sub-regions, and the base surface is matched with the predefined manufacturing template to obtain the manufacturing feature points. , while giving the geometric surface mapping attributes; When determining the processing placement surface, include: Get manufacturing feature points The face collection , get the face set from the first 3D geometric model Adjacent face sets ; If the face collection If there is a unique surface, the unique surface is used as the processing placement surface ; If the face collection If there are multiple faces, obtain the faces parallel to the base face among the multiple faces, and take the face with the largest distance from the base face as the processing placement face .

4. The high-precision parts machining path planning method based on artificial intelligence optimization according to claim 3 is characterized in that: When positioning the processing element, it includes: From manufacturing feature points Get the positioning surface , positioning surface , and align the positioning surface , positioning surface The type is identified and the corresponding processing element coordinate system is constructed according to the identification result; When processing element shaping, including: Traversing manufacturing feature points The parameter variable set , through the parameter variable set The name of the parameter variable determines the meaning of the parameter variable. According to the association relationship between the parameter variable and the attribute adjacency graph, the geometric surface associated with the parameter variable is obtained, and the value of the parameter variable is determined.

5. The high-precision parts machining path planning method based on artificial intelligence optimization according to claim 4 is characterized in that: When making preliminary planning for the machining path, include: Constructing a road network 0-1 matrix for the processing path according to the second three-dimensional geometric model; Get manufacturing feature points The connectivity index is The algorithm obtains any two manufacturing feature points The matrix of the shortest path between them, obtaining all manufacturing feature points The betweenness is calculated and the betweenness index is analyzed to obtain the first planned processing path.

6. The high-precision parts machining path planning method based on artificial intelligence optimization according to claim 5 is characterized in that: When outputting the second planned processing path, it includes: Divide the first planned processing path into several equal parts according to the preset time interval , , The start and end time of the processing path; Get The position of the machining tool at the moment , The manufacturing feature point closest to the machining tool at the moment Location ; Get the waiting position of the machining tool when starting machining , the first manufacturing feature point on the first planned processing path Location ; Based on time and location and A rectangular coordinate system with the origin at .

7. The high-precision parts machining path planning method based on artificial intelligence optimization according to claim 6 is characterized in that: When outputting the second planned processing path, it also includes: Will Coordinates at the moment and As the training sample input of the neural network, Moment and The position difference corresponding to the moment uses the error function of the neural network The gain factor is obtained as output; The position change at the next moment is re-input into the neural network, and the gain coefficient updated in real time is output for adaptive optimization until the hybrid-based Balance and output the second planned processing path.

Images