Integrated optimization and energy-saving prediction method for cutting tool parameters and process parameters in side milling

Abstract

An integrated optimization and energy-saving prediction method for cutting tool parameters and process parameters in side milling. The prediction includes determining the integrated optimization varia

Description

TECHNICAL FIELD The present disclosure relates to the technical field of numerical control machining, in particular to an integrated optimization and energy-saving prediction method for cutting tool parameters and process parameters in side milling. BACKGROUND In modern manufacturing, numerical control technology has become an important means to improve production efficiency and product quality. As a common form of numerical control, side milling is widely used in the manufacturing of molds, aerospace, automotive, and other mechanical components. The processing quality and efficiency not only depend on equipment performance, but are also closely related to cutting tool parameters and process parameters. In traditional side milling, the optimization of cutting tool parameters and process parameters usually relies on experience and trial-and-error procedure, which not only takes time and effort, but may also lead to resource waste and low production efficiency. In recent years, with the development of computer technology and artificial intelligence technology, optimization methods based on numerical simulation and machine learning have gradually been applied in the manufacturing field. These methods simulate and optimize complex machining processes by establishing mathematical models and algorithms, providing theoretical guidance and technical support. However, most current research mainly adopts staged optimization methods, with some focusing on optimizing cutting tool parameters and the other focuses on optimizing process parameters, lacking integrated optimization methods for cutting tool parameters and process parameters. With the introduction and promotion of the concept of green manufacturing, manufacturing enterprises pay more and more attention to energy saving, emission reduction and sustainable development. In this context, how to integrate and optimize the cutting tool parameters and process parameters of side milling through scientific methods, and apply the optimization results to actual production to achieve effective energy-saving prediction and control, is still an urgent problem to be solved. SUMMARY In view of the problems existing in the existing technology, the present disclosure proposes an integrated optimization and energy-saving prediction method for cutting tool parameters and process parameters in side milling. By integrating and optimizing cutting tool parameters and process parameters, the energy-saving and efficiency improvement of the side milling process can be achieved, meeting the needs of modem manufacturing industry for efficient, high-quality, and green production. The present disclosure adopts the following technical solution: An integrated optimization and energy-saving prediction method for cutting tool parameters and process parameters in side milling, including the following steps: Step 1: determining integrated optimization variables of the cutting tool parameters and the process parameters in side milling; the integrated optimization variables of the cutting tool parameters include: cutting tool diameter d , teeth number of cutting tool z, and cutting tool material M the integrated optimization variables of the process parameters include spindle speed n, feed rate Fv, milling width ae, and milling depth a. Step 2: determining the integrated optimization objectives of the cutting tool parameters and the process parameters in side milling: cutting energy consumption per unit volume Ecutting , machining surface roughness Ra, and cutting time per unit volume Tcutting . Step 3: determining integrated optimization constraints of the cutting tool parameters and the process parameters in side milling, the integrated optimization constraint of the cutting tool parameters includes cutting tool diameter constraint, cutting tool teeth number constraint, and cutting tool material constraint, the integrated optimization constraint of process parameters includes spindle speed constraint, feed rate constraint, milling width constraint, and milling depth constraint. Step 4: establishing a multi-objective function model for integrated optimization of the cutting tool parameters and the process parameters in side milling; Step 5: performing normalization and weighting on the multi-objective function model. Step 6: solving optimization problems for the multi-objective function model to obtain an optimization solution. Step 7: predicting an energy-saving effect based on the cutting tool parameters and the process parameters obtained by the optimization solution in step 6. Preferably, in step 2, a function model of an optimization objective for the cutting energy consumption per unit volume Ecutti is: „ 60 E =E x--- cutting cutting MRR In the formula, Ecutting is the cutting energy consumption per unit volume, with unit of J / mm3; Cutting *s miHing power, with unit of W; MRR is material removal rate, with unit of mm3 / s; The function model of an optimization objective of the machining surface roughness Ra is: a J z e p r In the formula, Ra is the machining surface roughness, with unit of Jim; K is a correction coefficient of the formula; CF is a cutting force coefficient, which depends on the workpiece material; al is an exponential term of the spindle speed, fz is feed rate per tooth, is an exponential term of feed rate per tooth, / 1 is an exponential term of the milling width ae, JI is an exponential term of the milling depth a cl is an exponential term of the cutting tool diameter d, is an exponential term of teeth number of cutting tool, CF is cutting force coefficient, 77I and is an exponential term of the cutting force coefficient CF , and can be obtained by fitting experimental data. The function model of the optimization objective of cutting time per unit volume Tcutting is: T =----—---- cutting r / X Z X 77 X 6Z X 6Z J z e p In the formula, Tcuttjng is the cutting time per unit volume, with unit of s / mm3. Preferably, a function model of the milling power Pcutting is represented by a polynomial regression model: In the formula, A is a coefficient term of the spindle speed n a2 is an exponential term of the spindle speed w; B is a coefficient term for the feed rate fz of per tooth, / 32 is an exponential term for the feed rate per tooth; C is a coefficient term of the milling width ae, / 2 is an exponential term of the milling width ; D is a coefficient term of the milling depth a, 82 is an exponential term of the milling depth ap \ E is a coefficient term of the cutting tool diameter d, c2 is an exponential term of the cutting tool diameter d \ F is a coefficient term for the teeth number of cutting tool z, £2 is an exponential term for the teeth number of cutting tool z; G is a coefficient term of the cutting force coefficient CF, r)2 is an exponential term of the cutting force coefficient CF, and H is the constant term of the formula, A, B, C, D, E, F, G, a2, / 32, / 2, 82, ^2, ^2 and t / 2 can be obtained by fitting experimental data. Preferably, the cutting tool diameter constraint is: de{d15d2,...X} In the formula, dvd2,...,dn are optional cutting tool diameters provided by a cutting tool manufacturer. The cutting tool teeth number constraint is: ze{z15z2,...,z„}_ In the formula, zi,z2,...,zn represent optional cutting tool tooth numbers provided by the cutting tool manufacturer. The cutting tool material constraint is: f e {CF1,CF2,...,CFn| In the formula, CF1,CF2,...,CFn are cutting force coefficients corresponding to the optional cutting tool materials provided by the cutting tool manufacturer. The spindle speed constraint is: n . <n <n min max In the formula, wmin and wmax respectively represent a minimum spindle speed and a maximum spindle speed recommended by the cutting tool manufacturer; The feed rate constraint is: F . <F<F v _ mm v v _ max In the formula, Fv min and Fv max respectively represent a minimum feed rate and a maximum feed rate recommended by the cutting tool manufacturer. The milling width constraint is: a ■ <a <a e _ mm e e _ max In the formula, ae min and ae max respectively represent a minimum milling width and a maximum milling width recommended by the cutting tool manufacturer. The milling depth constraint is: a ■ <a <a p_mm p p max In the formula, ap min and ap max respectively represent a minimum milling depth and a maximum milling depth recommended by the cutting tool manufacturer. Preferably, the multi-objective function model for the integrated optimization of the cutting tool parameters and the process parameters in side milling in step 4 is: mmF(d,z,M,n,Fv,ae,ap) = (min Ecuttmg, min Tcuttmg, min Ra) de{dr,d2,...,dn} z^{zvz2,...,zn} «mln n "max F . <F<F v _ min v v _ max a ■ <a <a e _ mm e e _ max a . <a <a p_mm p p max Preferably, the normalization method for the multi-objective function model is: mapping the values of the objective function to an interval of (0,1), the specific normalization process can be carried out by the following formula: In the formula, f* represents a normalized function expression, ft represents an i-th function value, f and f ■ represent a minimum value and a maximum value of the i-th 7 ji max j i min a function within the interval, respectively. The weighting method for a multi-objective function model is: setting different weight coefficients according to an importance of the objective function, and the weighted function model is: min F( d, z, M, n, Fv, ae, ap) = +c2Tcuttmg +c3Ra) '3 s.t. F2’- «min F ■ v mm a e mm max max max a / ?_min In the formula, q, c2 and q are weight coefficients of three optimization objective functions, respectively. Preferably, a solution method for the multi-objective function model in step 6 adopts a black hole-continuous ant colony optimization algorithm. Preferably, the specific step of the step 7 is : inputting cutting tool parameter values and process parameter values (d,z,M,n,Fv,ae,a ) obtained by the optimization solution in step 6 into the function models of the cutting energy consumption per unit volume Ecutting , machining surface roughness Ra, and cutting time per unit volume Tcutting , and predicting energy-saving effects by comparing with empirical machining schemes. The advantageous effects of the present disclosure are: In traditional side milling, the optimization research of cutting tool parameters and process parameters mainly adopts a staged optimization method, lacking research on integrated optimization of the cutting tool parameters and process parameters. Through integrating optimization methods, cutting tool parameters and process parameters are treated as a whole for global parameter optimization, resulting in more practical optimization results. In addition, compared to staged optimization, integrating optimization of cutting tool parameters and process parameters can more comprehensively explore potential optimization space, achieve better processing solutions, thereby promoting energy conservation and emission reduction, which is more in line with the requirements of green manufacturing. BRIEF DESCRIPTION OF THE DRAWINGS FIG. 1 is a schematic diagram of side milling. FIG. 2 is a flow chart of the method of the present disclosure. FIG. 3 is a flow chart of the optimization solution process for multi-objective function model based on the black hole-continuous ant colony optimization algorithm. Reference numbers in the drawings: 1-cutting tool; 2-workpiece. DETAILED DESCRIPTION OF THE EMBODIMENTS The specific embodiments of the present disclosure will be further illustrated below in conjunction with the accompanying drawings and specific examples: Embodiment 1: taking the side milling of a rectangular workpiece in VMC650L high-speed vertical machining center as an example, the integrated optimization of cutting tool parameters and process parameters during machining is carried out, and energy-saving prediction is made based on the optimization results. The schematic diagram of side milling is shown in FIG. 1, which includes cutting tool 1 and workpiece 2. During the machining process, different types of cutting tools can be selected based on different combinations of parameters such as cutting tool material, cutting tool diameter, and teeth number of cutting tool. The specific detailed parameter information is shown in Table 1. Table 1 Detailed Parameters of cutting tools cutting tool material cutting tool diameter teeth number of cutting tool cutting tool material cutting tool diameter teeth number of cutting tool cutting tool material cutting tool diameter teeth number of cutting tool 2 2 2 high speed 10 4 cobalt 10 4 hard metal 10 4 12 2 high 12 2 12 2 steel 4 speed 4 4 14 2 steel 14 2 14 2 4 4 4 Combining FIG. 1 and FIG. 2, this embodiment provides a detailed introduction to an integrated optimization and energy-saving prediction method for cutting tool parameters and process parameters in side milling, including the following steps: Step 1: determining the integrated optimization variables of the cutting tool parameters and the process parameters in side milling; the integrated optimization variables of the cutting tool parameters include: cutting tool diameter d, teeth number of cutting tool z, and cutting tool material M \ the integrated optimization variables of the process parameters include spindle speed n, feed rate Fv, milling width ae, and milling depth a. Step 2: determining the integrated optimization objectives of cutting tool parameters and process parameters in side milling: cutting energy consumption per unit volume Ecutting , machining surface roughness Ra, and cutting time per unit volume Tcutting . The function model of the optimization objective for the cutting energy consumption per unit volume Ecuttmg is: ^cutting Pcuttms X MRR ' In the formula, Ecutting is the cutting energy consumption per unit volume, with unit of J / mm3; ^cutting *s miHing power, with unit of W; MRR is material removal rate, with unit of mm3 / s. The function model of the milling power Pcutting is represented by a polynomial regression model: ^.,„B=(xlx»“2)X(BX / / 2)x(CXaf)x(Dxa‘2)x(£X<r2M^ In the formula, A is the coefficient term of the spindle speed n and a2 is the exponential term of the spindle speed n \ B is the coefficient term for the feed rate fz of per tooth, and ^2 is the exponential term for the feed rate per tooth; C is the coefficient term of milling width ae, and / 2 is the exponential term of milling width / 2; D is the coefficient term of the milling depth a and 82 is the exponential term of milling depth ap, E is the coefficient term of the cutting tool diameter d, and e2 is the exponential term of the cutting tool diameter d \ F is the coefficient term for the teeth number of cutting tool z, and ^2 is the exponential term for the teeth number of cutting tool z; G is the coefficient term of the cutting force coefficient CF, r / 2 is the exponential term of the cutting force coefficient CF, and H is the constant term of the formula. A, B, C, D, E, F, G, a2, / 32, / 2, 82, s2, ^2 and z / 2 can be obtained by fitting experimental data. The function model of the optimization objective of the machining surface roughness Ra is: Ra=Kxnalxfflxa^xaplxdelxzclxCf In the formula, Ra is the machining surface roughness, with unit of Jim; K is the correction coefficient of the formula; CF is the cutting force coefficient, which depends on the workpiece material; al is the exponential term of the spindle speed, fz is feed rate per tooth, is the exponential term of feed rate per tooth, / 1 is the exponential term of the milling width ae, <51 is the exponential term of the milling depth a el is the exponential term of the cutting tool diameter d , is the exponential term of teeth number of cutting tool, CF is cutting force coefficient, 77I and is the exponential term of the cutting force coefficient CF, and can be obtained by fitting experimental data. The function model of the optimization objective of cutting time per unit volume Tcutting is: T =----—---- cutting r jzxzxnxaexap In the formula, Tcuttjng is the cutting time per unit volume, with unit of s / mm3. In order to obtain the coefficients in each objective function model, this embodiment uses Taguchi orthogonal table L27 (37) to design the experiment, which can obtain the experimental data required for fitting the coefficients. The experimental results are shown in Table 2. According to the experimental results shown in Table 2, nonlinear polynomial fitting was performed, and the function model of milling power Pcutting obtained by fitting is: Pcuttmg = (2-823 x w0 008) x (2.3 11 x ) x (2.633 x «e0128) x (2.477 x ^0221) x(2.391 x J 024)x (2.385xz0014)x(2.359xC / 820) +140.352 Therefore, the function model of the optimization objective of cutting energy consumption per unit volume Ecutting can be further expressed as: 000 0.008\ 011 ^-0.023^ 0.128x (2.823xw )x(2.311x jz )x(2.633x6 / e ) Ecutting = x(2.477xaf221)x(2.391x J-°02^ x(2.359xC / 820) + 140.352 (2.823 x w0008) x (2.311 x / / 0 023) x (2.633 x ae0128) x(2.477 x a / 221) x (2.391 x ^0024) x (2.385 x z0014) x(2.359xC / 820) + 140.352 60 MRR 60 x---------------- fxzxnxa xa J z e p The function model of the optimization objective of the machining surface roughness Ra obtained by fitting is: Ra = 19118x(W-°-8503)x( / / 2^^ x (a -°^336^^16^ Table 2 orthogonal experimental results d z n NO [numb M [r / min] [mm] er] high speed 4000 1 10 2 steel high speed 2 10 2 4000 steel high speed 3 10 2 4000 steel cobalt high 4 12 2 5000 speed steel cobalt high 5 12 2 5000 speed steel cobalt high 6 12 2 5000 speed steel 7 14 2 hard metal 6000 8 14 2 hard metal 6000 9 14 2 hard metal high speed 6000 10 12 4 6000 6000 steel high speed 11 12 4 steel high speed 12 12 4 6000 steel cobalt high 13 14 4 4000 speed steel cobalt high 14 14 4 4000 speed steel cobalt high 15 14 4 4000 speed steel 16 10 4 hard metal 5000 17 10 4 hard metal 5000 18 10 4 hard metal high speed 5000 5000 19 14 4 steel 20 14 4 high speed 5000 Fv [mm / min] ap [mm] ae [mm] P cutting [W] Ra [pm] 660 5 0.6 1045.04 2.777 700 10 0.8 1265.68 2.175 740 15 1.0 1459.32 2.159 660 5 0.6 1073.77 1.429 700 10 0.8 1223.82 1.301 740 15 1.0 1423.32 0.811 660 5 0.6 1030.39 0.364 700 10 0.8 1134.00 0.228 740 15 1.0 1313.79 0.215 660 10 1.0 1227.65 0.816 700 15 0.6 1259.36 0.512 740 5 0.8 1037.66 0.711 660 10 1.0 1277.79 0.667 700 15 0.6 1294.17 0.712 740 5 0.8 1092.17 1.368 660 10 1.0 1210.41 0.412 700 15 0.6 1202.53 0.230 740 5 0.8 1087.48 0.298 660 15 0.8 1533.75 2.126 700 5 1.0 1116.88 1.064 21 14 4 steel high speed 740 10 0.6 1247.03 0.958 steel 5000 cobalt high 0.8 0.658 22 10 4 6000 660 15 1.0 1304.94 1.601 speed steel cobalt high 23 10 4 6000 700 5 0.6 1207.55 2.079 speed steel cobalt high 24 10 4 6000 740 10 1376.42 speed steel 25 12 4 hard metal 4000 660 15 0.8 1352.63 0.545 26 12 4 hard metal 4000 700 5 1.0 1091.63 0.953 27 12 4 hard metal 4000 740 10 0.6 1195.33 0.446 Step 3: determining the integrated optimization constraints of cutting tool parameters and process parameters in side milling. The integrated optimization constraint of cutting tool parameters include cutting tool diameter constraint, cutting tool teeth number constraint, and cutting tool material constraint. The integrated optimization constraints of process parameters include spindle speed constraint, feed rate constraint, milling width constraint, and milling depth constraint. The cutting tool diameter constraint is: de{d15d2,...X} In the formula, dvd2,...,dn are the optional cutting tool diameters provided by the cutting tool manufacturer. The cutting tool teeth number constraint is: ^{v2,->4 In the formula, zi,z2,...,zn represent the optional cutting tool tooth numbers provided by the cutting tool manufacturer. The cutting tool material constraint is: f e {CF1,CF2,...,CFn| In the formula, CF1,CF2,...,CFn are the cutting force coefficients corresponding to the optional cutting tool materials provided by the cutting tool manufacturer. The spindle speed constraint is: In the formula, wmin and wmax respectively represent the minimum spindle speed and the maximum spindle speed recommended by the cutting tool manufacturer. The feed rate constraint is: F . <F<F v _ min v v _ max In the formula, Fv min and Fv max respectively represent the minimum feed rate and the maximum feed rate recommended by the cutting tool manufacturer. The milling width constraint is: a ■ <a <a e _ mm e e _ max In the formula, ae min and ae max respectively represent the minimum milling width and the maximum milling width recommended by the cutting tool manufacturer. The milling depth constraint is: a ■ <a <a p_mm p p max In the formula, ap min and ap max respectively represent the minimum milling depth and the maximum milling depth recommended by the cutting tool manufacturer. Among them, the cutting force coefficient is obtained according to the “Cutting Parameters Manual”, and the cutting force coefficients corresponding to the three materials of hard metal, cobalt high speed steel, and high speed steel are 1.07, 1.12, and 1.13, respectively; the value of milling width ae is generally not greater than one tenth of the cutting tool diameter, and the value of milling depth a is generally not greater than 1.5 times the cutting tool diameter. Therefore, the specific constraints of this embodiment are as follows: de {10,12,14} ze{2,4} CF e {1.07,1.12,1.13} s.t.< 0<n< 8000 0 <Fv <800 0<ae <1.4 0<ap <21 Step 4: establishing a multi-objective function model for integrated optimization of the cutting tool parameters and the process parameters in side milling. In this embodiment, the integrated optimization multi-objective function model of the cutting tool parameters and the process parameters in side milling is: min F( d, z,M,n,Fv,ae,ap) = (min Ecuttmg, min Tcuttmg, min Ra) de {10,12,14} ze{2,4} CF e {1.07,1.12,1.13} s.t.< 0<n< 8000 0 <Fv <800 0<ae <1.4 0<ap <21 Step 5: performing normalization and weighting on the multi-objective function model. The normalization method for multi-objective function models is to map the values of the objective function to the interval of (0,1), which can eliminate the dimensional influence of different objective functions and compare them at the same scale. The specific normalization process can be carried out by the following formula: _ fi J / min fi max fi min In the formula, f* represents the normalized function expression, ft represents the i-th function value, f and f ■ represent the minimum value and maximum value of the i-th 7 max i min a function within the interval, respectively. The weighting method for multi-objective function models is to set different weight coefficients based on the importance of the objective function. The larger the weight coefficient, the more emphasis is placed on a certain objective. In this embodiment, the weight of the cutting energy consumption per unit volume is 1 / 3, the weight of the machining surface roughness is 1 / 3, and the weight of the cutting time per unit volume is 1 / 3. Therefore, in this embodiment, the weighted function model is: minF(J, z,M, n, Fv, ae, = min(| Ecuttmg + Ecuttmg + de {10,12,14} ze{2,4} CF e {1.07,1.12,1.13} s.t.< 0<n< 8000 0 <Fv <800 0<ae <1.4 0<ap <21 Step 6: solving optimization problems for the multi-objective function model to obtain an optimization solution. In this embodiment, the solution method for the multi-objective function model adopts a black hole-continuous ant colony optimization algorithm; the schematic diagram of the optimization solution process for multi-objective function models based on the black hole-continuous ant colony optimization algorithm is shown in FIG. 3; using Python 3.6 to write optimization programs, the computer uses the Windows 10 operating system, the processor is a quad-core Intel Core CPU, and the memory is 8GB. In this embodiment, the optimized cutting tool parameters and process parameters obtained by the optimization solution are: (J ~ 14S r ~ 4, Af ~ Hard metal, m “ 6000, Fv ~ 740, ~ 1.0, a? — 15) Step 7: predicting the energy-saving effect based on the cutting tool parameters and the process parameters obtained by the optimization solution in step 6. In this embodiment, the cutting tool parameters value and process parameter value obtained by the optimization solution in step 6 are input into the function model of cutting energy consumption per unit volume Ecutting , the function model of the machining surface roughness Ra, and the function model of the cutting time per unit volume Tcutting , and compared with empirical machining schemes to predict the energy-saving effect, as shown in Table 3. Table 3 optimization plan and experience plan process scheme d [m m] z [num ber] M n [r / min] Fv [mm / min] ae [mm] ap [mm] Ecutting [J / mm3] Ra [pm] T 1 cutting [s / mm3] optimiz ation 14 4 hard meta 6000 740 1.0 15 7.367 0.217 0.0054 plan 1 cob a It experie high nee 10 4 6000 700 1.0 5 22.140 1.601 0.0171 spee plan d steel From Table 3, it can be seen that compared with the experience scheme, the cutting energy consumption per unit volume of the optimization plan is reduced from 22.140 J / mm3 to 7.367 J / mm3 achieving an energy saving of 14.773 J / mm3. Besides, it can be seen from the table that the the machining surface roughness is reduced from 1.601 pm to 0.217 pm; the cutting time per unit volume is reduced from 0.0171 s / mm3 to 0.0054 s / mm3, achieving green, high-quality, and efficient production requirements. Of course, the above description is not a limitation of the present disclosure, and the present disclosure is not limited to the above embodiments. Any changes, modifications, additions, or substitutions made by those skilled in the art within the substantive scope of the present disclosure should also fall within the scope of the present disclosure.

Claims

1. An integrated optimization and energy-saving prediction method for cutting tool parameters and process parameters in side milling, comprising following steps:step 1: determining integrated optimization variables of cutting tool parameters and process parameters in side milling;the integrated optimization variables of the cutting tool parameters comprise: cutting tool diameter d, teeth number of cutting tool z, and cutting tool material Mthe integrated optimization variables of the process parameters comprise spindle speed n, feed rate Fv, milling width ae, and milling depth a \step 2: determining integrated optimization objectives of the cutting tool parameters and the process parameters in side milling: cutting energy consumption per unit volume Ecutting , machining surface roughness Ra, and cutting time per unit volume Tcutting \step 3: determining integrated optimization constraints of the cutting tool parameters and the process parameters in side milling, wherein the integrated optimization constraint of the cutting tool parameters comprises cutting tool diameter constraint, cutting tool teeth number constraint, and cutting tool material constraint, and the integrated optimization constraint of the process parameters comprises spindle speed constraint, feed rate constraint, milling width constraint, and milling depth constraint;step 4: establishing a multi-objective function model for integrated optimization of the cutting tool parameters and the process parameters in side milling;step 5: performing normalization and weighting on the multi-objective function model;step 6: solving optimization problems for the multi-objective function model to obtain an optimization solution;step 7: predicting an energy-saving effect based on the cutting tool parameters and the process parameters obtained by the optimization solution in step 6;in step 2, a function model of an optimization objective for the cutting energy consumption per unit volume Ecuttmg is:„ 60A „ = P x---- cutting cuttingMRR ■in the formula, E^ is the cutting energy consumption per unit volume, with unit of J / mm3; ^cutting *s miHing power, with unit of W; MRR is material removal rate, with unit of mm3 / s;a function model of an optimization objective of the machining surface roughness Ra is:a J z e p r .in the formula, Ra is the machining surface roughness, with unit of Jim; K is a correction coefficient of the formula; CF is a cutting force coefficient; al is an exponential term of the spindle speed, fz is feed rate per tooth, is an exponential term of feed rate per tooth, / 1 is an exponential term of the milling width ae, <51 is an exponential term of the milling depth a fl is an exponential term of the cutting tool diameter d, is an exponential term of teeth number of cutting tool, CF is the cutting force coefficient, and 7 / 1 is an exponential term of the cutting force coefficient CF \a function model of an optimization objective of the cutting time per unit volume Tcutting is:T =----—----cutting r / X Z X 77 X 6Z X 6ZJ z e p .in the formula, Tcuttjng is the cutting time per unit volume, with unit of s / mm3;a function model of the milling power Pcutting is represented by a polynomial regression model:in the formula, A is a coefficient term of the spindle speed n a2 is an exponential term of the spindle speed w; B is a coefficient term for the feed rate fz per tooth, ^2 is an exponential term for the feed rate per tooth; C is a coefficient term of the milling width ae, / 2 is an exponential term of the milling width ae \ D is a coefficient term of the milling depth a §2 is an exponential term of the milling depth ap \ E is a coefficient term of the cutting tool diameter d, s2 is an exponential term of the cutting tool diameter d \ F is a coefficient term for the teeth number of cutting tool z, £2 is an exponential term for the teeth number of cutting tool z; G is a coefficient term of the cutting force coefficient CF, / / 2 is an exponential term of the cutting force coefficient Cw, and H is the constant term of the formula;the cutting tool diameter constraint is:d e{dr,d2,...,dnYin the formula, dvd2,...,dn are optional cutting tool diameters provided by a cutting toolmanufacturer;the cutting tool teeth number constraint is:in the formula, zx,z2,...,zn represent optional cutting tool tooth numbers provided by the cutting tool manufacturer;the cutting tool material constraint is:f e {CF1,CF2,...,CFn|.in the formula, CF1,CF2,...,CFn are cutting force coefficients corresponding to the optionalcutting tool materials provided by the cutting tool manufacturer;the spindle speed constraint is:n . <n <n min max •in the formula, wmin and wmax respectively represent a minimum spindle speed and amaximum spindle speed recommended by the cutting tool manufacturer;the feed rate constraint is:F . <F<F v min v vmax •in the formula, Fv min and Fv max respectively represent a minimum feed rate and amaximum feed rate recommended by the cutting tool manufacturer;the milling width constraint is:a ■ <a <a e _ mm e e _ max •in the formula, ae min and ae max respectively represent a minimum milling width and amaximum milling width recommended by the cutting tool manufacturer;the milling depth constraint is:a ■ <a <a p_mm p p max •in the formula, ap min and ap max respectively represent a minimum milling depth and amaximum milling depth recommended by the cutting tool manufacturer;the multi-objective function model for the integrated optimization of the cutting tool parameters and the process parameters in side milling in step 4 is:minF(d,z,M,n,Fv,ae,ap) = (min Ecuttmg,minTcuttmg,min Ra)de{dr,d2,...,dn}z^{zvz2,...,zn}v _ min v v _ maxa ■ <a <ae _ mm e e _ maxa . <a <ap_mm p p maxa normalization method for the multi-objective function model is:mapping values of the objective function to an interval of (0,1), the specific normalizationprocess is carried out by the following formula:in the formula, f* represents a normalized function expression, ft represents an i-thfunction value, f and f ■ represent a minimum value and a maximum value of the i-th 7 max »z i mm afunction within the interval, respectively;a weighting method for a multi-objective function model is:setting different weight coefficients according to an importance of the objective function, andthe weighted function model is:min F(d,z,M,n,Fv,ae,ap) = min^E^ + c2Tcuttmg +c3Ra)a ■ <a <ae _ mm e e _ maxa ■ <a <ap _ min p p _ maxin the formula, c1, c2 and c3 are weight coefficients of three optimization objectivefunctions, respectively.

2. The integrated optimization and energy-saving prediction method for cutting tool parameters and process parameters in side milling according to claim 1, wherein a solution method for the multi-objective function model in step 6 adopts a black hole-continuous ant colony optimization algorithm.

3. The integrated optimization and energy-saving prediction method for cutting tool parameters and process parameters in side milling machining according to claim 1, wherein the step 7 comprises :inputting cutting tool parameter values and process parameter values (d,z,M,n,Fv,ae,ap) obtained by the optimization solution in step 6 into the function model of the cutting energy consumption per unit volume Ecutting , the function model of machining surface roughness Ra, and the function model of cutting time per unit volume Tcutting , and predicting energy-saving effects by comparing with empirical machining schemes.A

Images