Milling process multi-objective collaborative optimization method and system based on GA-SMA

Abstract

The invention relates to the technical field of numerical control machine tools, provides a GA-SMA-based milling process multi-objective collaborative optimization method and system, and constructs energy consumption, heat generation and main cutting force objective functions and machining constraint conditions based on collected process parameters. Setting the weight of a target function and the proportion of the GA in the GA-SMA mixed algorithm, initializing GA parameters, inputting process parameters and the target function, and iterating to obtain a Pareto non-dominated solution set; sMA parameters are initialized, local optimization is carried out on the solution set, and a first solution set is output; and combining the three kinds of solution sets into a second solution set, and screening an optimal solution through TOPSIS evaluation. And obtaining N groups of optimal solutions, and outputting an optimal objective function solution and process parameters through parameter fluctuation and variation coefficient evaluation. According to the method, GA global optimization and SMA local optimization capabilities are combined, collaborative optimization of milling energy consumption, heat generation and force can be achieved, and the purposes of saving energy and reducing heat generation and cutting force are achieved.

Description

Technical Field

[0001] This invention relates to the field of CNC machine tool technology, and in particular to a multi-objective collaborative optimization method and system for milling processes based on GA-SMA. Background Technology

[0002] As core equipment in the manufacturing industry, CNC machine tools have deeply penetrated various production fields such as aerospace, automobile manufacturing, and precision electronics, providing indispensable support for the efficient operation of industries and promoting technological upgrading. However, while the industry is developing rapidly, the global energy supply and demand imbalance and environmental pollution problems are becoming increasingly prominent. The CNC machine tool machining process involves multiple stages, including spindle drive, feed system, and auxiliary devices, resulting in a huge overall energy consumption. Moreover, some equipment suffers from low energy efficiency, which is becoming a core bottleneck restricting the manufacturing industry's transformation towards green and low-carbon practices.

[0003] CN119511943A discloses a method for predicting thermal errors in a high-speed precision machine tool spindle system under inclined conditions and a thermal error compensation system. The method includes the following steps: Step 1: Constructing a thermal-structural coupling characteristic model. A geometric model of the high-speed precision machine tool spindle system is constructed, including the spindle and bearings at both ends of the spindle. Based on the inclined working conditions, a heat source load model is constructed based on the geometric model of the high-speed spindle system, and heat dissipation boundary conditions are defined. The heat source load model includes a bearing heating model and a motor heating model. The heat dissipation boundary conditions include the convection coefficient, bearing contact thermal resistance, and material thermal conductivity. Step 2: Analyzing thermal-structural interaction. The thermal-structural coupling characteristic model is used to analyze the influence of heat generation on the deformation of the high-speed precision machine tool spindle system, and the contact stiffness of each contact area is calculated. Step 3: Adjusting the parameters of the thermo-structural coupling characteristic model based on the simulated and measured data of temperature field distribution and thermal stress field; Step 4: Predicting steady-state thermal error and time constant through thermo-structural coupling analysis to predict the steady-state thermal error of the high-speed precision machine tool spindle system under different tilting conditions and the time constant required to reach thermal equilibrium, and constructing a thermal error model; Step 5: Predicting thermal error based on the constructed thermal error model to obtain the thermal error value of the high-speed spindle system under different tilting conditions.

[0004] CN119337765B discloses a cooling element for a precision worm gear grinding machine and its multi-objective thermal-fluid topology design optimization method. The cooling element is applied to a ball screw feed drive system, which includes a screw shaft and a movable nut cooperating with the screw shaft. The movable nut includes a nut and a nut housing, and the cooling element is disposed between the nut and the nut housing. The method includes the following steps: Step 1: Defining the design domain. The cooling element is unfolded into a plane, and a two-dimensional design domain representing the geometry of the cooling element is defined and discretized using the finite element method. Step 2: Numerical modeling. The cooling element is modeled as a porous medium. Under laminar incompressible flow conditions, the fluid dynamics are controlled by dimensionless forms of the continuity equation and momentum equation; flow... The bulk-solid coupled heat transfer model is controlled by a dimensionless energy conservation equation; Step 3: Construct the objective function. To improve cooling performance and reduce flow resistance, the optimization objective is defined as a weighted function of heat transfer and fluid dissipation power, and a fluid-solid heat transfer topology optimization model is constructed; Step 4: Solve the objective function. The adjoint method is used to solve the sensitivity, and the gradient calculated by the adjoint method forms a quadratic subproblem of the sequential quadratic programming method. By solving the quadratic subproblem, the design variables are updated to ensure that the solution moves towards the optimal configuration until the set iterative convergence condition is met, and the topology design channel is designed in the cooling element; Step 5: Restore the shape and structure of the cooling element.

[0005] In machine tool energy consumption optimization practices, the rational selection of machining parameters has a significant impact on reducing energy consumption. However, actual machining requires comprehensive consideration of energy consumption targets along with other core machining characteristics such as machining efficiency, machining accuracy, and surface quality. Since there are generally contradictory coupling relationships between multiple key machining parameters such as spindle speed, feed rate, depth of cut, and cutting fluid consumption—such as energy consumption and efficiency, and accuracy and energy consumption—how to construct a unified optimization objective function that takes into account both energy consumption and multiple machining characteristics, overcome the contradictory constraints between parameters, and achieve synergistic optimization of multiple machining parameters to maximize the reduction of machine tool energy consumption while ensuring machining quality and efficiency has become a core technical problem that urgently needs to be solved. Summary of the Invention

[0006] Long-term practice has shown that milling, as one of the most widely used cutting processes in the mechanical manufacturing field, directly determines the energy consumption level, thermal characteristics, mechanical properties, and overall efficiency of the machining system through its machining parameters. In actual production, how to minimize machining energy consumption and achieve reasonable control of milling heat and milling force by scientifically configuring milling parameters while strictly ensuring machining quality and efficiency has become an urgent technical problem to be solved in promoting the green upgrading of the manufacturing industry. Meanwhile, in CNC milling, milling energy consumption, milling heat, and milling force are core research objects, and excessive milling heat and force can significantly shorten tool life and degrade part surface quality. Currently, optimization of these three factors is mostly fragmented and lacks systematic collaborative design. How to construct a collaborative optimization mechanism that balances reduced milling energy consumption and reasonable control of milling heat and milling force, ensuring tool life and part surface quality while reducing energy consumption, has become a key technical problem that urgently needs to be solved in the field of CNC milling.

[0007] In view of this, the present invention aims to propose a multi-objective collaborative optimization method for milling processes based on GA-SMA, comprising:

[0008] Step S1: Establish the milling energy consumption E based on the machining process parameters collected during the milling process. m Milling heat generation Q θ and the main cutting force F c Milling machining energy consumption E m Milling heat generation Q θ and the main cutting force F c The objective function is set as the optimization objective function for the machining process parameters, and constraints are established for the milling process.

[0009] Step S2: Set the weights of the objective function and the proportion of GA in the GA-SMA hybrid algorithm, and initialize the number of iterations and population size of GA. Take the processing parameters and objective function as inputs, and obtain the Pareto non-dominated solution set through iterative calculation.

[0010] Step S3: Initialize SMA and set the number of SMA iterations and population size. Perform SMA local optimization on each solution in the Pareto non-dominated solution set and output the optimized first solution set.

[0011] Step S4: Merge the Pareto non-dominated solution set, the first solution set, and the elite-preserving solution set into a second solution set; evaluate the second solution set using TOPSIS to select the optimal solution;

[0012] Step S5: Repeat steps S2 to S4 to obtain N sets of optimal solutions. Through parameter fluctuation and COV evaluation, output the optimal objective function solution and processing parameters.

[0013] In one embodiment, the energy consumption per unit material removal is established as milling specific energy (SEC) and milling material removal rate (MRR), then the milling energy consumption E m for,

[0014]

[0015] Among them, E m Energy consumption for milling operations, expressed in J; The power loss factor is SEC, and the specific energy of milling is SEC, in J / mm². 3 MRR stands for Material Removal Rate, measured in mm. 3 / min; T m This refers to the processing time.

[0016] In one embodiment, the milling material removal rate (MRR) is:

[0017] MRR=C m a p a e v f

[0018] Among them, C m As a correction factor, a p a is the axial cutting depth. e For radial cutting depth, v f This refers to the feed rate.

[0019] In one embodiment, milling generates heat Q. θ for,

[0020]

[0021] Among them, C θ v is the milling temperature coefficient. c f is the milling speed. z a is the feed per tooth. e a is the radial cutting depth. p Let u, v, h, and w be the axial depth of cut, and v be the milling parameter. c f z a e a p The corresponding index.

[0022] In one embodiment, the objective function and the constraints of the milling process are as follows:

[0023]

[0024] stn min ≤n≤n max

[0025] vfmin ≤v f ≤v fmax

[0026] a pmin ≤a p ≤a pmax

[0027] P c <η×P max

[0028] F c <F c max

[0029] F c <F s

[0030] Where, n max and n min These are the maximum and minimum spindle speeds, respectively, where n is the spindle speed; v fmax and v fmin These are the maximum feed rate and the minimum feed rate, v f For feed rate; a pmax and a pmin These are the maximum and minimum depths of cut, a p P is the depth of cut; η is the effective power coefficient of the machine tool. c For machine tool power, P max F is the maximum power of the machine tool. c The main cutting force, F cmax It is the maximum milling force that the machine tool can provide; F s This is the maximum milling force that the spindle stiffness allows.

[0031] In one embodiment, if both parameter fluctuation and COV meet the preset conditions, the evaluation result is deemed qualified, and the optimal objective function solution and processing parameters are output; if the parameter fluctuation or COV does not meet the preset conditions, the process proceeds to step S2.

[0032] In one embodiment, the preset conditions include parameter fluctuation percentage ≤ 8% and COV ≤ 12%.

[0033] In one embodiment, the proportion of GA in the GA-SMA hybrid algorithm is set to 0.6, the proportion of SMA in the GA-SMA hybrid algorithm is set to 0.3, and the elite retention ratio is set to 0.1.

[0034] This invention also discloses a system for the multi-objective collaborative optimization method of the milling process based on GA-SMA as described above, the system comprising,

[0035] The initialization unit is used to establish the milling energy consumption E based on the machining process parameters collected during the milling process. m Milling heat generation Q θ and the main cutting force F c Milling machining energy consumption E m Milling heat generation Q θ and the main cutting force F c The objective function is set as the optimization objective function for the machining process parameters, and constraints are established for the milling process.

[0036] The GA unit is used to set the weights of the objective function and the proportion of GA in the GA-SMA hybrid algorithm, and to initialize the number of iterations and population size of GA. It takes the processing parameters and objective function as inputs and obtains the Pareto non-dominated solution set through iterative calculation.

[0037] The SMA unit is used to initialize SMA and set the number of SMA iterations and population size. It performs SMA local optimization on each solution in the Pareto non-dominated solution set and outputs the optimized first solution set.

[0038] The evaluation unit is used to merge the Pareto non-dominated solution set, the first solution set, and the elite-preserving solution set into a second solution set; and to evaluate the second solution set through TOPSIS to select the optimal solution.

[0039] The output unit is used to repeat steps S2 to S4 to obtain N sets of optimal solutions. Through parameter fluctuation and COV evaluation, it outputs the optimal objective function solution and processing parameters.

[0040] The present invention also discloses an electronic device, comprising at least one processor; and

[0041] A memory communicatively connected to the at least one processor; wherein,

[0042] The memory stores instructions that can be executed by the at least one processor, which enables the at least one processor to perform the above-described GA-SMA-based multi-objective collaborative optimization method for the milling process.

[0043] The present invention also discloses a machine-readable storage medium storing instructions for causing a machine to execute the multi-objective collaborative optimization method for milling processes based on GA-SMA as described above.

[0044] This invention discloses a multi-objective collaborative optimization method for milling processes based on GA-SMA. Through steps S1-S5, objective functions for milling energy consumption, milling heat generation, and main cutting force are constructed based on the machining process parameters collected during the milling process. These functions serve as the core objectives for optimizing the machining process parameters, and constraints during the milling process are established simultaneously. First, the weights of each objective function and the proportion of GA in the GA-SMA hybrid algorithm are set. Simultaneously, the iteration count and population size of GA are initialized. Then, the machining process parameters and objective functions are used as input, and the Pareto non-dominated solution set is obtained through iterative calculation. SMA is initialized, and its iteration count and population size are determined. Local optimization operations are performed on each solution in the Pareto non-dominated solution set using SMA, resulting in an optimized first solution set. The Pareto non-dominated solution set, the first solution set, and the elite-retained solution set are merged to form a second solution set. The TOPSIS evaluation method is then used to analyze the second solution set and select the optimal solution for the current stage. By obtaining N sets of optimal solutions and evaluating parameter fluctuations and coefficients of variation, the optimal objective function solution and corresponding machining parameters that meet the requirements are finally output. This invention also discloses a system for the multi-objective collaborative optimization method for milling processes based on GA-SMA as described above. The method and system can obtain optimal machining parameters through the global optimization capability of GA and the local optimization capability of SMA, achieving collaborative optimization of energy consumption, heat generation, and force characteristics in the milling process, thereby achieving energy saving while minimizing milling heat generation and milling force.

[0045] Other features and advantages of the present invention will be described in detail in the following detailed description section. Attached Figure Description

[0046] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an undue limitation of the invention. In the drawings:

[0047] Figure 1 This is a schematic diagram of a multi-objective collaborative optimization method for milling processes based on GA-SMA according to one embodiment of the present invention.

[0048] Figure 2 Pareto nondominated solution set graph of a multi-objective collaborative optimization method for milling process based on GA-SMA according to one embodiment of the present invention;

[0049] Figure 3 Milling energy consumption E based on a GA-SMA-based multi-objective collaborative optimization method for the milling process, as described in one embodiment of the present invention. m Optimization results graph of optimized variables;

[0050] Figure 4Milling heat generation Q, a multi-objective collaborative optimization method for milling process based on GA-SMA according to one embodiment of the present invention. θ Optimization results graph of optimized variables;

[0051] Figure 5 This invention provides an embodiment of a multi-objective collaborative optimization method for milling processes based on GA-SMA and the main cutting force F. c Optimization results graph of the optimized variables. Detailed Implementation

[0052] The specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0053] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0054] It should be noted that the terms "first," "second," "third," etc., in the specification, claims, and accompanying drawings of this invention 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 for the embodiments of the invention described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover 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.

[0055] Currently, optimization of milling energy consumption, milling heat generation, and milling force is mostly fragmented and lacks systematic collaborative design. How to construct a collaborative optimization mechanism that balances energy reduction, heat generation, and force control, while ensuring tool life and part surface quality, has become a pressing technical problem in CNC milling. This invention provides a multi-objective collaborative optimization method for the milling process based on GA-SMA, such as... Figure 1-5 The diagram illustrates a multi-objective collaborative optimization method for milling processes based on GA-SMA, according to one embodiment of the present invention. The GA-SMA-based multi-objective collaborative optimization method for milling processes includes...

[0056] Step S1: Establish the milling energy consumption E based on the machining process parameters collected during the milling process. m Milling heat generation Q θ and the main cutting force F c Milling machining energy consumption E m Milling heat generation Q θ and the main cutting force F c The objective function is set as the optimization objective function for the machining process parameters, and constraints are established for the milling process.

[0057] Step S2: Set the weights of the objective function and the proportion of GA in the GA-SMA hybrid algorithm, and initialize the number of iterations and population size of GA. Using the processing parameters and the objective function as input, iterative calculations yield the Pareto non-dominated solution set. Genetic Algorithm (GA) is a heuristic optimization algorithm that simulates the process of biological evolution. It gradually optimizes candidate solutions by simulating the mechanisms of natural selection, heredity, and mutation.

[0058] Step S3: Initialize SMA and set the number of SMA iterations and population size. Perform SMA local optimization on each solution in the Pareto non-dominated solution set and output the optimized first solution set. The Slime Mould Algorithm (SMA) is an emerging intelligent optimization algorithm that simulates the behavior of slime molds during foraging, finding the optimal solution through iterative search.

[0059] Step S4: Merge the Pareto non-dominated solution set, the first solution set, and the elite-reserved solution set into a second solution set; evaluate the second solution set using TOPSIS to select the optimal solution. The Technique for Order Preference by Similarity to an Ideal Solution (TOPSIS) is a multi-attribute decision analysis method that determines the relative proximity of each alternative to the positive and negative ideal solutions by calculating the distance between each alternative and the positive and negative ideal solutions, thereby ranking all alternatives and ultimately selecting the optimal solution.

[0060] Step S5: Repeat steps S2 to S4 to obtain N sets of optimal solutions. Evaluate the solutions based on parameter fluctuations and COV, and output the optimal objective function solution and processing parameters. The coefficient of variation (COV) is a statistical indicator that measures the dispersion of data; it is the ratio of the standard deviation to the mean of the data.

[0061] This invention discloses a multi-objective collaborative optimization method for milling processes based on GA-SMA. Through steps S1-S5, objective functions for milling energy consumption, milling heat generation, and main cutting force are constructed based on the machining process parameters collected during the milling process. These functions serve as the core objectives for optimizing the machining process parameters, and constraints during the milling process are established simultaneously. First, the weights of each objective function and the proportion of GA in the GA-SMA hybrid algorithm are set. Simultaneously, the iteration count and population size of GA are initialized. Then, the machining process parameters and objective functions are used as input, and the Pareto non-dominated solution set is obtained through iterative calculation. SMA is initialized, and its iteration count and population size are determined. Local optimization operations are performed on each solution in the Pareto non-dominated solution set using SMA, resulting in an optimized first solution set. The Pareto non-dominated solution set, the first solution set, and the elite-retained solution set are merged to form a second solution set. The TOPSIS evaluation method is then used to analyze the second solution set and select the optimal solution for the current stage. By obtaining N optimal solutions and conducting parameter fluctuation analysis and coefficient of variation evaluation, the optimal objective function solution and corresponding machining parameters that meet the requirements are finally output. This method leverages the global optimization capability of GA and the local optimization capability of SMA to obtain optimal machining parameters, achieving synergistic optimization of energy consumption, heat generation, and force characteristics during the milling process. This results in energy savings while minimizing milling heat generation and milling force.

[0062] In CNC machine tool machining, milling energy consumption data is a prerequisite for establishing an energy consumption model, so it is necessary to acquire milling energy consumption data. The power curve of a CNC machine tool in milling mainly consists of start-stop state, standby state, spindle acceleration and braking state, no-load state, and cutting state. When the machine tool enters the cutting state, the tool contacts the workpiece material surface, removing excess material, and the load on the spindle motor increases. During the cutting state, the power curve changes significantly; the difference between the measured cutting power and feed power at this time represents the amount of material removed. After the cutting state ends, the spindle stops, and the machine tool returns to the standby state. By analyzing the power curve of the machining process, it can be concluded that the power of the machine tool in the cutting state consists of auxiliary loss power, spindle system working power, feed power, and material removal power. The dynamic changes of these power components directly determine the energy consumption level in the milling process. In order to accurately quantify the intrinsic relationship between machining parameters and energy consumption, it is necessary to further establish mathematical relationships through key characteristic parameters. Specific Energy Consumption in Milling (SEC) is a key indicator for measuring energy consumption per unit of material removed, while Material Removal Rate in Milling (MRR) directly reflects processing efficiency and material removal rate. Together, they constitute the core parameters describing the energy consumption characteristics of milling. In a more preferred embodiment of the present invention, the energy consumption per unit of material removed is established as SEC and MRR. Therefore, the milling processing energy consumption E... m for,

[0063]

[0064] Among them, E m Energy consumption for milling operations, expressed in J; The power loss factor is SEC, and the specific energy of milling is SEC, in J / mm². 3 MRR stands for Material Removal Rate, measured in mm. 3 / min; T m This refers to the machining time. SEC directly reflects the economic efficiency of machine tool energy consumption under different machining parameters such as spindle speed, feed rate, and depth of cut.

[0065] MRR directly reflects the production efficiency of the machining process and is closely related to key indicators such as milling energy consumption, milling force, and tool life. However, improving MRR is usually accompanied by increased energy consumption and cutting force. In a more preferred embodiment of the present invention, the milling material removal rate (MRR) is...

[0066] MRR=C m a p a e v f

[0067] Among them, C m As a correction factor, a p a is the axial cutting depth. e For radial cutting depth, v f Let be the feed rate. The functional relationship between SEC and MRR is as follows:

[0068]

[0069] Where C0 and C1 are the correlation coefficients of the function, respectively.

[0070] A mathematical model for predicting cutting energy consumption during CNC milling was obtained.

[0071]

[0072] During the machining process, the time spent on the tool entry and retraction is extremely short and can be basically ignored. The cutting stage of the machining can be approximated as the cutting time T of the workpiece. c The cutting time is,

[0073]

[0074] Where L is the total length of the milling toolpath, and n is the spindle speed.

[0075] The machining process parameters in milling play a decisive role in the material removal rate of the workpiece. The relationship between the material removal rate and the machining process parameters is as follows:

[0076] MRR=C m a p a e v f

[0077] In CNC milling processes, milling heat generation is a significant factor that cannot be ignored. The interaction between the cutting tool and the workpiece material converts most of the milling work into heat. Excessive milling heat generation can affect the machining quality of parts and the service life of cutting tools. The generation of milling heat is related to the machining parameters. In a more preferred embodiment of the present invention, the milling heat generation Q... θ for,

[0078]

[0079] Among them, C θ v is the milling temperature coefficient. c f is the milling speed. z a is the feed per tooth. e a is the radial cutting depth. p Let u, v, h, and w be the axial depth of cut, and v be the milling parameter. cf z a e a p The corresponding indices. In a more preferred embodiment of the present invention, the material used is 45 steel. The relationship between processing parameters and milling heat is obtained, and the corresponding indices of u, v, h, and w are obtained by fitting experimental data, which are u = 0.4727, v = 0.2405, h = 0.2356, and w = 0.4373, respectively. Based on the milling speed v... c The relationship between the spindle speed n and the spindle rotation speed n is transformed to obtain Q. θ The relationship between the optimization variables and the optimization variables is as follows:

[0080]

[0081] Where n is the spindle speed and D is the tool diameter.

[0082] Cutting force is one of the key factors affecting tool life and machining quality. In milling, appropriate milling force can reduce heat generation and energy consumption. Total cutting energy consumption is the integral of cutting power over time, while cutting power is the product of the main cutting force and the cutting speed.

[0083] E m =P c ·T c =F c ·v c ·T c

[0084] Among them, P c T represents the total cutting power. c For cutting time, F c The main cutting force.

[0085] Due to the cutting speed v c = L / t. Based on the energy consumption model, the cutting force F is obtained. c The relationship between the processing parameters is as follows:

[0086]

[0087] The E obtained above m Q θ and F c The regression mathematical model is used as the objective function for cutting parameter optimization, and a joint optimization analysis of milling energy consumption, heat, and force is conducted. To ensure the optimization results better reflect actual machining requirements, constraints need to be established based on meeting machining process requirements and machine tool conditions. In a more preferred embodiment of the invention, the objective function and the constraints of the milling process are as follows:

[0088]

[0089] stn min ≤n≤n max

[0090] v fmin ≤v f ≤v fmax

[0091] a pmin ≤a p ≤a pmax

[0092] P c <η×P max

[0093] F c <F c max

[0094] F c <F s

[0095] Where, n max and n min These are the maximum and minimum spindle speeds, respectively, where n is the spindle speed; v fmax and v fmin These are the maximum feed rate and the minimum feed rate, v f For feed rate; a pmax and a pmin These are the maximum and minimum depths of cut, a p P is the depth of cut; η is the effective power coefficient of the machine tool. c For machine tool power, P max F is the maximum power of the machine tool. c The main cutting force, F cmax It is the maximum milling force that the machine tool can provide; F s This is the maximum milling force that the spindle stiffness allows.

[0096] For example, the established GA-SMA hybrid multi-objective optimization algorithm is used to optimize and solve the established objective function. The maximum number of iterations for GA is set to 10000, with a population size of 200; the maximum number of iterations for SMA is set to 3000, with a population size of 100; the proportion of GA in the hybrid algorithm is 0.6; the proportion of SMA in the hybrid algorithm is 0.3; and the elitist retention ratio is 0.1. The obtained three-dimensional Pareto front solution set is as follows: Figure 2 As shown. Considering the randomness of the optimization algorithm and the slight fluctuations in the optimal solution obtained from the 3D data, a quantitative evaluation is needed, and the optimal solution from each optimization run is taken after rounding. Finally, the optimization results of the 10 sets of optimization variables and objective functions are shown below. Figure 3 E is shown m The optimization results of 10 sets of optimization variables (collaborative optimization solutions) are shown, where the average energy consumption is displayed as the average of the results. Figure 4 For Q θ The optimization results of 10 sets of optimization variables, Figure 5 For F c The optimization results of 10 sets of optimization variables.

[0097] To ensure that the fluctuations of all optimization variables and objective function results conform to the standards for roughing-out machining scenarios, in a more preferred embodiment of the present invention, if both parameter fluctuations and COV meet preset conditions, the evaluation result is deemed qualified, and the optimal objective function solution and machining parameters are output; if the parameter fluctuations or COV do not meet the preset conditions, the process proceeds to step S2.

[0098] To ensure that the results of all optimization variables and objective functions, i.e., minor fluctuations, remain within a certain accuracy range, in a more preferred embodiment of the present invention, the preset conditions include parameter fluctuation percentage ≤ 8% and COV ≤ 12%. For example, the fluctuations of the optimization results of the 10 sets of objective functions and their optimization variables are as follows: n is 0.82%, v... f It is 1.18%, a p The percentage was 5.36%, and the RFI values ​​were all less than 8%; E m It is 0.21%, Q θ It is 2.08%, F c The percentage is 4.15%, and the COV values ​​are all less than 12%. Preferably, the average value of the results from 10 sets of co-optimization of the objective function is taken as the final optimization result, then: E m =63056J, Q θ =354℃, F c =1476N, and the matching optimization variable values ​​are: n = 1522r / min, v f =865mm / min, a p =0.55mm.

[0099] To ensure a balance between global search capability and local optimization accuracy, a GA (Global Arithmetic) ratio of 0.6 fully leverages its global traversal search advantage, effectively covering the broad optimization space of milling parameters and preventing the algorithm from getting trapped in local optima. A SMA (Small Modular Machining) ratio of 0.3 utilizes its efficient local optimization characteristics to perform fine iteration on the Pareto non-dominated solutions obtained from the GA search, improving the accuracy of the solutions. The synergy of both approaches balances the breadth and depth of optimization. In a more preferred embodiment of this invention, the ratio of GA in the GA-SMA hybrid algorithm is set to 0.6, the ratio of SMA in the GA-SMA hybrid algorithm is 0.3, and the elitist retention ratio is 0.1.

[0100] This invention also discloses a system for the multi-objective collaborative optimization method of the milling process based on GA-SMA as described above, the system comprising,

[0101] The initialization unit is used to establish the milling energy consumption E based on the machining process parameters collected during the milling process. m Milling heat generation Q θ and the main cutting force F c Milling machining energy consumption E m Milling heat generation Q θ and the main cutting force F c The objective function is set as the optimization objective function for the machining process parameters, and constraints are established for the milling process.

[0102] The GA unit is used to set the weights of the objective function and the proportion of GA in the GA-SMA hybrid algorithm, and to initialize the number of iterations and population size of GA. It takes the processing parameters and objective function as inputs and obtains the Pareto non-dominated solution set through iterative calculation.

[0103] The SMA unit is used to initialize SMA and set the number of SMA iterations and population size. It performs SMA local optimization on each solution in the Pareto non-dominated solution set and outputs the optimized first solution set.

[0104] The evaluation unit is used to merge the Pareto non-dominated solution set, the first solution set, and the elite-preserving solution set into a second solution set; and to evaluate the second solution set through TOPSIS to select the optimal solution.

[0105] The output unit is used to repeat steps S2 to S4 to obtain N sets of optimal solutions. Through parameter fluctuation and COV evaluation, it outputs the optimal objective function solution and processing parameters.

[0106] The CNC milling machining parameter optimization system disclosed in this invention comprises five functional units, each working together to complete the optimization process. First, the initialization unit constructs the milling machining energy consumption E based on the machining process parameters collected during the milling process. m Milling heat generation Qθ and main cutting force F c The objective function is defined, and constraints for the milling process are established simultaneously. Then, the GA unit sets the objective function weight and the proportion of GA in the GA-SMA hybrid algorithm, initializes the number of iterations and the population size of GA, and takes the machining parameters and objective function as inputs to iteratively calculate the Pareto non-dominated solution set. Subsequently, the SMA unit initializes SMA and sets its iteration number and population size, performs local optimization on each solution in the Pareto non-dominated solution set, and outputs the optimized first solution set. The evaluation unit then merges the Pareto non-dominated solution set, the first solution set, and the elite-retained solution set into a second solution set, and uses TOPSIS evaluation to select the current optimal solution. Finally, the output unit repeats the operations of the GA unit, SMA unit, and evaluation unit to obtain N sets of optimal solutions. Combining parameter fluctuation analysis and COV evaluation, the system finally outputs the optimal objective function solution that meets the requirements and the corresponding machining parameters. The system can construct a collaborative optimization mechanism by deeply integrating the global high-efficiency optimization capability of the genetic algorithm GA and the local fine-grained optimization characteristics of the slime mold algorithm SMA. On the one hand, it relies on GA to fully traverse the optimization space of the milling parameters, avoiding getting trapped in local optima. On the other hand, SMA is used to precisely iterate and optimize candidate parameters, ultimately obtaining the optimal machining parameters that take into account multiple objectives. This process enables the coordinated control of milling energy consumption, heat generation, and cutting force. While significantly reducing machining energy consumption to achieve energy-saving goals, it can reasonably control the numerical range of milling heat generation and milling force, effectively avoiding the adverse effects of excessive heat and cutting force on tool life and part surface quality, and providing technical support for the greening and high-quality production of milling.

[0107] The present invention also discloses an electronic device, comprising at least one processor; and

[0108] A memory communicatively connected to the at least one processor; wherein,

[0109] The memory stores instructions that can be executed by the at least one processor, which enables the at least one processor to perform the above-described GA-SMA-based multi-objective collaborative optimization method for the milling process.

[0110] The present invention also discloses a machine-readable storage medium storing instructions for causing a machine to execute the multi-objective collaborative optimization method for milling processes based on GA-SMA as described above.

[0111] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that the present invention is not limited to the described order of actions, because according to the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to the present invention.

[0112] As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that the present invention can be implemented by means of software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments of the present invention.

[0113] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, for system or system embodiments, since they are basically similar to method embodiments, the description is relatively simple, and relevant parts can be referred to the descriptions in the method embodiments. The systems and system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0114] The method and apparatus for providing service information provided by the present invention have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and concept of the present invention; furthermore, those skilled in the art will recognize that, based on the concept of the present invention, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A multi-objective collaborative optimization method for milling processes based on GA-SMA, characterized in that, The multi-objective collaborative optimization method for the milling process based on GA-SMA includes: Step S1: Establish the milling energy consumption E based on the machining process parameters collected during the milling process. m Milling heat generation Q θ and the main cutting force F c Milling machining energy consumption E m Milling heat generation Q θ and the main cutting force F c The objective function is set as the optimization objective function for the machining process parameters, and constraints are established for the milling process. Step S2: Set the weights of the objective function and the proportion of GA in the GA-SMA hybrid algorithm, and initialize the number of iterations and population size of GA. Take the processing parameters and objective function as inputs, and obtain the Pareto non-dominated solution set through iterative calculation. Step S3: Initialize SMA and set the number of SMA iterations and population size. Perform SMA local optimization on each solution in the Pareto non-dominated solution set and output the optimized first solution set. Step S4: Merge the Pareto non-dominated solution set, the first solution set, and the elite-preserving solution set into a second solution set; evaluate the second solution set using TOPSIS to select the optimal solution; Step S5: Repeat steps S2 to S4 to obtain N sets of optimal solutions. Through parameter fluctuation and COV evaluation, output the optimal objective function solution and processing parameters.

2. The multi-objective collaborative optimization method for milling process based on GA-SMA according to claim 1, characterized in that, If the unit material removal energy consumption index is established as milling specific energy (SEC) and milling material removal rate (MRR), then the milling processing energy consumption E m for, Among them, E m Energy consumption for milling operations, expressed in J; The power loss factor is SEC, and the specific energy of milling is J / mm. 3 MRR stands for Material Removal Rate, measured in mm. 3 / min; T m This refers to the processing time.

3. The multi-objective collaborative optimization method for milling process based on GA-SMA according to claim 2, characterized in that, The milling material removal rate (MRR) is: MRR=C m a p a e v f Among them, C m As a correction factor, a p a is the axial cutting depth. e For radial cutting depth, v f This refers to the feed rate.

4. The multi-objective collaborative optimization method for milling process based on GA-SMA according to claim 1, characterized in that, Milling heat generation Q θ for, Among them, C θ v is the milling temperature coefficient. c f is the milling speed. z a is the feed per tooth. e a is the radial cutting depth. p Let u, v, h, and w be the axial depth of cut, and v be the milling parameter. c f z a e a p The corresponding index.

5. The multi-objective collaborative optimization method for milling process based on GA-SMA according to claim 1, characterized in that, The objective function and the constraints of the milling process are as follows: s.t. n min ≤n≤n max in fmin ≤in f ≤in fmax a pmin ≤a p ≤a pmax P c <η×P max F c <F c max F c <F s Where, n max and n min These are the maximum and minimum spindle speeds, respectively, where n is the spindle speed; v fmax and v fmin These are the maximum feed rate and the minimum feed rate, v f For feed rate; a pmax and a pmin These are the maximum and minimum depths of cut, a p P is the depth of cut; η is the effective power coefficient of the machine tool. c For machine tool power, P max F is the maximum power of the machine tool. c The main cutting force, F cmax It is the maximum milling force that the machine tool can provide; F s This is the maximum milling force that the spindle stiffness allows.

6. The multi-objective collaborative optimization method for milling process based on GA-SMA according to any one of claims 1-5, characterized in that, If both parameter fluctuation and COV meet the preset conditions, the evaluation result is deemed qualified, and the optimal objective function solution and processing parameters are output; if the parameter fluctuation or COV does not meet the preset conditions, proceed to step S2.

7. The multi-objective collaborative optimization method for milling process based on GA-SMA according to claim 6, characterized in that, The preset conditions include parameter fluctuation percentage ≤ 8% and COV ≤ 12%.

8. The multi-objective collaborative optimization method for milling process based on GA-SMA according to claim 7, characterized in that, The proportion of GA in the GA-SMA hybrid algorithm is set to 0.6, the proportion of SMA in the GA-SMA hybrid algorithm is set to 0.3, and the elitist retention ratio is set to 0.

1.

9. A system for a multi-objective collaborative optimization method for milling processes based on GA-SMA as described in any one of claims 1-8, characterized in that, The system includes, The initialization unit is used to establish the milling energy consumption E based on the machining process parameters collected during the milling process. m Milling heat generation Q θ and the main cutting force F c Milling machining energy consumption E m Milling heat generation Q θ and the main cutting force F c The objective function is set as the optimization objective function for the machining process parameters, and constraints are established for the milling process. The GA unit is used to set the weights of the objective function and the proportion of GA in the GA-SMA hybrid algorithm, and to initialize the number of iterations and population size of GA. It takes the processing parameters and objective function as inputs and obtains the Pareto non-dominated solution set through iterative calculation. The SMA unit is used to initialize SMA and set the number of SMA iterations and population size. It performs SMA local optimization on each solution in the Pareto non-dominated solution set and outputs the optimized first solution set. The evaluation unit is used to merge the Pareto non-dominated solution set, the first solution set, and the elite-preserving solution set into a second solution set; and to evaluate the second solution set through TOPSIS to select the optimal solution. The output unit is used to repeat steps S2 to S4 to obtain N sets of optimal solutions. Through parameter fluctuation and COV evaluation, it outputs the optimal objective function solution and processing parameters.

10. A machine-readable storage medium, characterized in that, The machine-readable storage medium stores instructions for causing the machine to execute the multi-objective collaborative optimization method for milling processes based on GA-SMA as described in any one of claims 1-8.

Images