CN111859566A - Surface roughness stabilizing method based on digital twinning - Google Patents
Surface roughness stabilizing method based on digital twinning Download PDFInfo
- Publication number
- CN111859566A CN111859566A CN202010692248.4A CN202010692248A CN111859566A CN 111859566 A CN111859566 A CN 111859566A CN 202010692248 A CN202010692248 A CN 202010692248A CN 111859566 A CN111859566 A CN 111859566A
- Authority
- CN
- China
- Prior art keywords
- surface roughness
- parameters
- prediction model
- machining
- processing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 230000003746 surface roughness Effects 0.000 title claims abstract description 187
- 238000000034 method Methods 0.000 title claims abstract description 51
- 230000000087 stabilizing effect Effects 0.000 title claims abstract description 16
- 238000012545 processing Methods 0.000 claims abstract description 82
- 238000003754 machining Methods 0.000 claims abstract description 56
- 238000011478 gradient descent method Methods 0.000 claims abstract description 8
- 238000013507 mapping Methods 0.000 claims abstract description 6
- 238000004422 calculation algorithm Methods 0.000 claims description 17
- 238000005520 cutting process Methods 0.000 claims description 14
- 230000008859 change Effects 0.000 claims description 12
- 238000012360 testing method Methods 0.000 claims description 12
- 238000012549 training Methods 0.000 claims description 11
- 241000272201 Columbiformes Species 0.000 claims description 10
- 238000010606 normalization Methods 0.000 claims description 9
- 238000012706 support-vector machine Methods 0.000 claims description 9
- 230000006641 stabilisation Effects 0.000 claims description 5
- 238000011105 stabilization Methods 0.000 claims description 5
- 230000006870 function Effects 0.000 description 29
- 238000002474 experimental method Methods 0.000 description 9
- 239000000463 material Substances 0.000 description 5
- 238000013528 artificial neural network Methods 0.000 description 4
- 238000000227 grinding Methods 0.000 description 4
- 230000009467 reduction Effects 0.000 description 4
- 238000004088 simulation Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000003050 experimental design method Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 101100483039 Arabidopsis thaliana TT8 gene Proteins 0.000 description 1
- OYPRJOBELJOOCE-UHFFFAOYSA-N Calcium Chemical compound [Ca] OYPRJOBELJOOCE-UHFFFAOYSA-N 0.000 description 1
- 208000013586 Complex regional pain syndrome type 1 Diseases 0.000 description 1
- 101100136092 Drosophila melanogaster peng gene Proteins 0.000 description 1
- 229910000831 Steel Inorganic materials 0.000 description 1
- 229910001069 Ti alloy Inorganic materials 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 229910045601 alloy Inorganic materials 0.000 description 1
- 239000000956 alloy Substances 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- BTCSSZJGUNDROE-UHFFFAOYSA-N gamma-aminobutyric acid Chemical compound NCCCC(O)=O BTCSSZJGUNDROE-UHFFFAOYSA-N 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000005461 lubrication Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000003801 milling Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000003908 quality control method Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012876 topography Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/17—Mechanical parametric or variational design
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Geometry (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Computer Hardware Design (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Analysis (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Computational Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Numerical Control (AREA)
Abstract
The invention discloses a surface roughness stabilizing method based on digital twinning, which comprises the following steps: 1) establishing a digital twin system of a virtual world based on a mechanical processing system of a physical world, and establishing a surface roughness prediction model in the digital twin system; 2) mapping the mechanical processing system by using a digital twin system, collecting processing parameters influencing surface roughness in the mechanical processing system in real time and inputting the processing parameters into the digital twin system; 3) predicting the surface roughness under the current processing condition by using a surface roughness prediction model; if predicted, the resulting surface roughness
Within the range of the set threshold value, the surface roughness is stable, the current processing parameters are proved to meet the requirements, and the step 5 is executed)(ii) a Otherwise, executing step 4); 4) solving by gradient descent method
Feeding back the machining parameters within the set threshold range to the machining system, and executing the step 5); 5) and (5) circulating the step 2) and the step 3) until the workpiece is machined.
Description
Technical Field
The invention belongs to the technical field of machining surface quality control, and particularly relates to a surface roughness stabilizing method based on digital twinning.
Background
Surface quality generally directly affects the physical, chemical and mechanical properties of the workpiece, such as friction properties, fatigue properties, wear resistance, lubrication properties, etc. Surface roughness is the most important indicator for assessing surface quality and is therefore chosen as a key specification for workpiece production. In actual machining processes, the surface roughness is often unstable and often tends to increase due to factors such as tool vibration, tool wear, and plastic deformation of the workpiece material. Therefore, an effective surface roughness stabilization method is required in order to obtain better surface properties. In recent years, a large amount of research on the establishment of surface roughness prediction models has been conducted by scholars at home and abroad, and the surface roughness prediction models can be roughly classified into three categories: theoretical methods, experimental design methods and artificial intelligence methods.
In the theoretical method, a surface roughness prediction model (usually, a mathematical equation of a machined surface) is established based on a machining theory by considering factors such as a tool shape, workpiece material characteristics, mounting errors, machining dynamics and the like. For any workpiece and tool combination, Munoz-Escalona and Maropoulos propose surface roughness prediction models based on geometric analysis of tool trajectories. Also, Lu et al established a cutting force-based tool flexible deformation model, and established a surface topography simulation model for predicting surface roughness using the model. To reduce surface roughness non-uniformity, Sun et al propose a surface roughness Relative Standard Deviation (RSDS) method based on relative tool sharpness to predict surface non-uniformity. Peng et al established a theoretical model describing the cutting edge trajectory taking into account tool pose, chatter, run-out, cutting forces and material deformation, and predicted surface roughness on this basis.
In the experimental design method, surface roughness models under different processing modes are established. Common experimental design methods include Taguchi method, full-factor design method, surface response method (RSM), etc. The RSM method is generally applied to the prediction of surface roughness because it requires only a small amount of experiments, compared to other methods. Karkalos et Al studied the optimum processing parameters for Ti-6Al-4v titanium alloys at minimum surface roughness with RSM. Dikshit et al optimally select the minimum surface roughness parameter in high-speed ball head milling by using a RSM-based center composite design method. Noordin et al investigated the properties (mainly surface roughness and cutting force) of cemented carbide tools by RSM. It was found that the feed rate is the main factor affecting the surface roughness. Mansour and Abdalla [13] also used RSM to establish a predictive model for EN32 material surface roughness.
Besides the above two methods, the artificial intelligence method is also widely applied to surface roughness prediction as a strong prediction tool with self-learning and self-adaptive capabilities. In EN 24T steel turning under high pressure cooling conditions, Mia et al proposed an Artificial Neural Network (ANN) -based mean surface roughness prediction model. Ghosh et al propose a surface roughness prediction model based on an artificial neural network, and search for optimal cutting conditions by using a genetic algorithm and a particle swarm optimization algorithm.
The surface roughness predicted by the model is constant under the same machining conditions (including tool, workpiece, machining parameters, etc.). However, in actual machining, the surface roughness of the workpiece is unstable due to the influence of factors such as tool wear, vibration, material property non-uniformity, stability of the process system, and the like. Therefore, dynamic factors should be considered to accurately predict the surface roughness, for example, a grinding surface roughness prediction method based on an improved support vector machine algorithm disclosed in chinese patent publication No. CN110348075A, a surface roughness prediction method under a condition of considering dynamic grinding is proposed, however, although the grinding surface roughness prediction method considers the dynamic factors and predicts the surface roughness under the condition of the dynamic factors, since there are many factors influencing the surface roughness in the machining process, when the surface roughness in a real machining scene does not meet the requirement, the grinding surface roughness prediction method cannot find one or more factors influencing the surface roughness most under the current machining condition, and thus cannot guide the real machining scene to achieve the technical purpose of stabilizing the surface roughness. In addition, the surface roughness typically fluctuates in a short time, which may make the processed workpiece fail to meet practical requirements, thereby increasing manufacturing costs and processing time. Therefore, a real-time and efficient surface roughness control method is very important.
Disclosure of Invention
In view of the above, the present invention provides a method for stabilizing surface roughness based on digital twinning, which can adjust the processing parameters affecting the surface roughness on line when the surface roughness is unstable, so as to rapidly stabilize the surface roughness and stabilize it within a set threshold range.
In order to achieve the purpose, the invention provides the following technical scheme:
a surface roughness stabilization method based on digital twinning comprises the following steps:
1) establishing a digital twin system of a virtual world based on a mechanical processing system of a physical world, and establishing a surface roughness prediction model in the digital twin system;
2) mapping the mechanical processing system by using a digital twin system, collecting processing parameters influencing surface roughness in the mechanical processing system in real time and inputting the processing parameters into the digital twin system;
3) predicting the surface roughness under the current processing condition by using a surface roughness prediction model; if predicted, the resulting surface roughness
If the surface roughness is within the set threshold range, the surface roughness is stable, the current processing parameters are proved to meet the requirements, and the step 5) is executed; otherwise, executing step 4);
4) solving by gradient descent method
Feeding back the machining parameters within the set threshold range to a machining system, machining the workpiece by the machining system according to the machining parameters obtained by solving, and executing the step 5);
5) And (5) circulating the step 2) and the step 3) until the workpiece is machined.
Further, in the step 1), the method for constructing the surface roughness prediction model includes:
21) processing the workpiece by using a mechanical processing system to obtain the surface roughness under different processing parameters;
22) dividing the data obtained in the step 21) into a training set and a testing set, carrying out normalization processing, and respectively taking the processing parameters and the surface roughness after the normalization processing as an input sample and an output sample of a surface roughness prediction model;
23) and establishing a surface roughness prediction model based on the PIO-SVM.
Further, in the step 23), a method for establishing a surface roughness prediction model based on the PIO-SVM includes:
231) initializing parameters of a pigeon swarm algorithm model, taking a mean square error corresponding to each group of penalty function C and kernel function parameter g as a fitness function, and iteratively searching C and g corresponding to the minimum mean square error in the pigeon swarm algorithm, namely the optimal penalty function C and kernel function parameter g;
232) substituting the solved optimal punishment function C and the kernel function parameter g into the support vector machine algorithm model to further construct a surface roughness prediction model, and utilizing the normalized test set to test the accuracy of the model.
Further, in the step 4), a point corresponding to the current processing condition is found in the surface roughness prediction model, a direction in which the surface roughness changes fastest is found in the surface roughness prediction model based on the point, a target point is taken in the direction in which the surface roughness changes fastest, the surface roughness at the target point is made to be within a set threshold range, and the processing parameter corresponding to the target point is fed back to the mechanical processing system.
Further, the machining system is a five-axis machining system, and the machining parameters affecting the surface roughness include a lead angle, a tilt angle, a cutting depth, a spindle rotation speed, a feed speed, and an average cutting force.
Further, dividing machining parameters influencing the surface roughness into online adjustable parameters and non-online adjustable parameters, wherein the online adjustable parameters comprise tool attitude parameters and spindle rotation speed, and the tool attitude parameters comprise lead angles and tilt angles; the non-online adjustable parameters include depth of cut, feed rate, and average cutting force.
Further, in the step 4), a point corresponding to the current processing condition is found in the surface roughness prediction model, a direction in which the surface roughness corresponding to the online adjustable parameter changes fastest is found in the surface roughness prediction model based on the point, a target point is taken in the direction in which the surface roughness changes fastest, the surface roughness at the target point is made to be within a set threshold range, and the processing parameter corresponding to the target point is fed back to the mechanical processing system.
Furthermore, if the parameters can be adjusted on line more than N times in continuous adjustment, the parameters cannot be satisfiedIf the position is within the range of the set threshold value, the condition that only the tool attitude parameter and the spindle rotating speed are adjusted can not meet the current machining requirement is shown, at the moment, all machining parameters influencing the surface roughness are taken as the adjusting objects, and the adjusting method comprises the following steps: finding a point corresponding to the current processing condition in a surface roughness prediction model, finding a direction with the fastest surface roughness change in the surface roughness prediction model on the basis of the point, taking a target point in the direction with the fastest surface roughness change, enabling the surface roughness at the target point to be within a set threshold range, and feeding back processing parameters corresponding to the target point to a mechanical processing system, wherein N is a positive integer greater than or equal to 1.
The invention has the beneficial effects that:
the surface roughness stabilizing method based on the digital twinning realizes the real-time mapping of a physical world machining system by establishing the digital twinning system, so that the machining state of the machining system can be reflected in real time by the digital twinning system; the surface roughness of the physical world machining system under the current machining condition can be accurately predicted based on dynamic factors through a surface roughness prediction model of a component in a digital twin system, and when the predicted surface roughness exceeds a range beyond a set threshold value, namely the surface roughness is unstable, the surface roughness prediction model can be solved based on a gradient descent method, so that new machining parameters can be quickly obtained and fed back to the physical world machining system, and the surface roughness is kept in a stable state until the machining of a workpiece is completed; in summary, the method for stabilizing the surface roughness based on the digital twinning realizes the prediction of the surface roughness under the action of considering dynamic factors, and can adjust parameters (such as tool attitude parameters and spindle rotation speed) which can be adjusted online when the surface roughness is unstable, thereby quickly realizing the stabilization of the surface roughness and stabilizing the surface roughness in a set threshold range.
Drawings
In order to make the object, technical scheme and beneficial effect of the invention more clear, the invention provides the following drawings for explanation:
FIG. 1 is a schematic diagram of a mapping relationship and an interaction relationship between a machining system of a physical world and a digital twin system of a virtual world;
FIG. 2 is a flow chart of the construction of a surface roughness prediction model based on a PIO-SVM in the embodiment;
FIG. 3 is a flow chart of adjusting processing parameters by a gradient descent method to stabilize surface roughness;
FIG. 4 is a training set containing 40 sets of experimental data;
FIG. 5 is a test set containing 10 sets of experimental data;
fig. 6 is a simulation result of changing the spindle rotation speed and the tool posture to stabilize and control the surface roughness.
Detailed Description
The present invention is further described with reference to the following drawings and specific examples so that those skilled in the art can better understand the present invention and can practice the present invention, but the examples are not intended to limit the present invention.
The present embodiment is a surface roughness stabilization method based on digital twinning, including the following steps.
1) A digital twin system of a virtual world is established based on a mechanical processing system of a physical world, and a surface roughness prediction model is established in the digital twin system. Specifically, the machining system of the present embodiment is a five-axis machining system, and the machining parameters affecting the surface roughness include a lead angle (L), a tilt angle (T), and a depth of cut (a) p) Spindle speed (n), feed rate (f) and average cutting force
21) And processing the workpiece by using a mechanical processing system to obtain the surface roughness under different processing parameters. In this example, 50 sets of experiments were designed and performed, including two sets of two-factor four-level full-factor experiments and two sets of three-factor three-level orthogonal experiments. For each set of experiments, repeated twice, which measured the surface roughness RaAre substantially the same. Final measured surface roughness RaIs the average of the results of two experiments.
22) Dividing the data obtained in the step 21) into a training set and a testing set, carrying out normalization processing, and respectively taking the processing parameters and the surface roughness after the normalization processing as an input sample and an output sample of the surface roughness prediction model.
Specifically, in this embodiment, 40 groups of experiments are randomly selected as a training set, as shown in fig. 4; the remaining 10 experiments were included as a test set, see fig. 5. After normalization processing, training time can be shortened, prediction accuracy of the regression model is improved, and normalization processing needs to be carried out on a training sample set. The training set is normalized to [0,1] herein. The calculation formula is as follows:
in formula (II), x'iAnd xiRespectively, the sample data before and after normalization,
and 
The maximum and minimum values of the surface roughness influencing factor i.
23) And establishing a surface roughness prediction model based on the PIO-SVM. Specifically, the method for establishing the surface roughness prediction model based on the PIO-SVM comprises the following steps:
231) initializing parameters of a pigeon swarm algorithm model, taking the mean square error corresponding to each group of penalty function C and kernel function parameter g as a fitness function, and iteratively searching C and g corresponding to the minimum mean square error in the pigeon swarm algorithm, namely the optimal penalty function C and kernel function parameter g. Under different C, g, the training set is used for training the surface roughness prediction model, then the test set is used for checking the accuracy rate of the prediction model, and the C, g corresponding to the minimum mean square error is found, namely the optimal C, g. The selection of the penalty function C and the kernel function parameter g has an important influence on the accuracy of the regression prediction model, and compared with a PSO algorithm and a GA algorithm, the PIO (Pigeon swarm algorithm) has the advantages of higher convergence speed, higher accuracy and stability. Therefore, this embodiment uses PIO to select the best C and g.
The PIO algorithm model consists of a map, a compass operator and a landmark operator. The mathematical model of each part is described as follows:
Vm(k)＝Vm(k-1)·e-fk+rand·(Lb-Lm(k-1))
Lm(k)＝Lm(k-1)+Vm(k)
Lm(k)＝Lm(k-1)+rand·(LC(k)-Lm(k-1))
wherein L is mAnd VmRespectively the position and velocity of the mth pigeon, k the number of iterations, f the map and compass operators, rand [0, 1%]Random number of Li, LbRepresents the global optimal position, L, of the current iterationC(k) Representing the central position of the remaining pigeons, Nt,1Representing the number of iterations of the map and compass operators, Nt,2Representing the number of iterations of the landmark operator, the fit is the quality function of each solution, here the mean square error of the prediction model, N, corresponding to each penalty function C and kernel parameter ggRepresenting the number of pigeon groups.
232) Substituting the solved optimal punishment function C and the kernel function parameter g into the support vector machine algorithm model to further construct a surface roughness prediction model, and utilizing the normalized test set to test the accuracy of the model.
A Support Vector Machine (SVM) is a statistical learning method proposed by Vapnik based on the principle of minimizing structural risk. Compared with the traditional machine learning method represented by a neural network, the support vector machine has obvious advantages in the aspects of theoretical basis, training process, node number, weight vector, global optimal solution and the like. The basic idea of the support vector machine is to simplify the search for the optimal linear hyperplane into a convex programming problem. The sample space is non-linearly mapped to a high-dimensional or infinite-dimensional feature space. In this way, a linear learning machine can be used to solve non-linear problems (including classification and regression) in a high-dimensional feature space.
The regression function of the vector machine algorithm model of the present embodiment is:
wherein f (x) is a regression function, alphaiAnd
is a pullGrenarian multiplier, C is a penalty function, K (x)i,xj) Is a kernel function, ωiIs a normal vector, xi,xjIs arbitrary
And
is an insensitive loss factor, b is a bias, y isiThe function value is mapped to the support vector.
The kernel function is an important component for establishing a regression prediction model of the support vector machine, and the reasonable selection of the kernel function is beneficial to improving the accuracy of the prediction model. The role of the kernel function is to transform the linear inseparable problem in the low-dimensional space into the linear separable and linear regression problem in the high-dimensional space. The radial basis kernel function (RBF) has the advantages of relatively simple calculation form, less input parameters, strong learning capability and the like. Thus, the selection of RBFs as the kernel function of the regression prediction model can be described as follows:
K(xi,xj)＝exp{-g|xi-xj|2},(g＞0)
wherein g is a kernel function parameter.
As can be seen from fig. 5, to verify the validity of the proposed model, the prediction error of each set of experiments was calculated using the following formula:
wherein the content of the first and second substances,
represents the surface roughness calculated by the predictive model, and RaIndicating the measured surface roughness. Can be seen as predicted
With measured RaSubstantially uniform, the Average Prediction Error (APE) is only 8.69%.
2) And mapping the mechanical processing system by using the digital twin system, acquiring the processing parameters influencing the surface roughness in the mechanical processing system in real time, and inputting the processing parameters into the digital twin system.
3) Predicting the surface roughness under the current processing condition by using a surface roughness prediction model; if predicted, the resulting surface roughness
If the surface roughness is within the set threshold range, the surface roughness is stable, the current processing parameters are proved to meet the requirements, and the step 5) is executed; otherwise, step 4) is executed.
4) Solving by gradient descent method
And 5) feeding back the machining parameters within the set threshold range to a machining system, machining the workpiece by the machining system according to the machining parameters obtained by solving, and executing the step 5). Specifically, a general solution method of the gradient descent method is as follows: and finding a point corresponding to the current processing condition in the surface roughness prediction model, finding a direction with the fastest surface roughness change in the surface roughness prediction model on the basis of the point, taking a target point in the direction with the fastest surface roughness change, enabling the surface roughness of the target point to be within a set threshold range, and feeding back the processing parameter corresponding to the target point to the mechanical processing system.
The threshold range of this embodiment is such that the surface roughness is not more than
I.e., surface roughness of not more than
Then, it is in a stable state and has a surface roughness greater than that of the alloy
Is in an unstable state. Of course, the threshold range of the surface roughness may be set according to the actual processing requirementsThe surface roughness is positioned between the maximum value and the minimum value, and the surface roughness is in a stable state; the threshold range of the surface roughness may be such that the surface roughness is equal to or greater than a certain minimum value, and a steady state is assumed when the surface roughness is greater than the minimum value, which will not be described again.
The surface roughness of the workpiece is also unstable due to the instability of the cutting force. Thus, at a given processing parameter (derived from the worker's processing experience), the surface roughness may not meet the process requirements. According to the prediction model, the change trend of the surface roughness can be monitored on line, and the stability of the surface roughness can be judged. Meanwhile, the rotation speed of the main shaft and the tool posture can be adjusted on line in the machining process in consideration of the feasibility of machine tool operation. Therefore, the surface roughness can be stabilized and controlled by adjusting the spindle rotation speed and the tool posture. To verify the effectiveness of this method, a set of simulation experiments was performed. The simulation results are shown in fig. 6. According to the experimental results, the surface roughness was significantly reduced from 0.4882 μm to 0.2995 μm by adjusting the adjustable parameters (tool attitude and spindle speed). At the same time, satisfactory surface roughness can be achieved with a variety of adjustable parameter combinations, which means that an efficient and simple selection of the optimum parameter combination is required. Therefore, in the embodiment, the machining parameters affecting the surface roughness are divided into online adjustable parameters and non-online adjustable parameters, the online adjustable parameters include tool attitude parameters and spindle rotation speed, and the tool attitude parameters include lead angle and tilt angle; parameters that are not adjustable online include depth of cut, feed rate, and average cutting force. In this case, the solution method of the gradient descent method is: finding out a point corresponding to the current processing condition in the surface roughness prediction model, finding out a direction with the fastest surface roughness reduction corresponding to the online adjusting parameter in the surface roughness prediction model on the basis of the point, and taking a target point in the direction with the fastest surface roughness reduction to ensure that the surface roughness at the target point is less than or equal to the set maximum value of the surface roughness 
And feeding back the processing parameters corresponding to the target point to the machineA processing system. If the parameters can be continuously adjusted for more than N times, the parameters can not be adjusted on line
Then, it is indicated that only adjusting the tool attitude parameter and the spindle rotation speed cannot meet the current processing requirements, and all processing parameters affecting the surface roughness need to be taken as the adjustment objects, and the adjustment method is as follows: finding out the point corresponding to the current processing condition in the surface roughness predicting model, finding out the direction with the fastest surface roughness reduction in the surface roughness predicting model based on the point, taking a target point in the direction with the fastest surface roughness reduction, and enabling the surface roughness at the target point to be less than or equal to the set maximum value of the surface roughness
And feeding back the machining parameters corresponding to the target point to the machining system, where N is a positive integer greater than or equal to 1, and N in this embodiment is 4.
5) And (5) circulating the step 2) and the step 3) until the workpiece is machined.
The above-mentioned embodiments are merely preferred embodiments for fully illustrating the present invention, and the scope of the present invention is not limited thereto. The equivalent substitution or change made by the technical personnel in the technical field on the basis of the invention is all within the protection scope of the invention. The protection scope of the invention is subject to the claims.
Claims (8)
1. A surface roughness stabilization method based on digital twinning is characterized in that: the method comprises the following steps:
1) establishing a digital twin system of a virtual world based on a mechanical processing system of a physical world, and establishing a surface roughness prediction model in the digital twin system;
2) mapping the mechanical processing system by using a digital twin system, collecting processing parameters influencing surface roughness in the mechanical processing system in real time and inputting the processing parameters into the digital twin system;
3) predicting current addition using surface roughness prediction modelSurface roughness under working conditions; if predicted, the resulting surface roughness
If the surface roughness is within the set threshold range, the surface roughness is stable, the current processing parameters are proved to meet the requirements, and the step 5) is executed; otherwise, executing step 4);
4) solving by gradient descent method
Feeding back the machining parameters within the set threshold range to a machining system, machining the workpiece by the machining system according to the machining parameters obtained by solving, and executing the step 5);
5) and (5) circulating the step 2) and the step 3) until the workpiece is machined.
2. The method of stabilizing surface roughness based on digital twinning as claimed in claim 1, wherein: in the step 1), the method for constructing the surface roughness prediction model comprises the following steps:
21) Processing the workpiece by using a mechanical processing system to obtain the surface roughness under different processing parameters;
22) dividing the data obtained in the step 21) into a training set and a testing set, carrying out normalization processing, and respectively taking the processing parameters and the surface roughness after the normalization processing as an input sample and an output sample of a surface roughness prediction model;
23) and establishing a surface roughness prediction model based on the PIO-SVM.
3. The method of stabilizing surface roughness based on digital twinning as claimed in claim 2, wherein: in the step 23), the method for establishing the surface roughness prediction model based on the PIO-SVM comprises the following steps:
231) initializing parameters of a pigeon swarm algorithm model, taking a mean square error corresponding to each group of penalty function C and kernel function parameter g as a fitness function, and iteratively searching a penalty function C and a kernel function parameter g corresponding to a minimum mean square error in the pigeon swarm algorithm to obtain an optimal penalty function C and kernel function parameter g;
232) substituting the solved optimal punishment function C and the kernel function parameter g into the support vector machine algorithm model to further construct a surface roughness prediction model, and utilizing the normalized test set to test the accuracy of the model.
4. The method of stabilizing surface roughness based on digital twinning as claimed in claim 1, wherein: in the step 4), a point corresponding to the current processing condition is found in the surface roughness prediction model, a direction with the fastest surface roughness change is found in the surface roughness prediction model on the basis of the point, a target point is selected from the direction with the fastest surface roughness change, the surface roughness of the target point is enabled to be within a set threshold range, and the processing parameter corresponding to the target point is fed back to the mechanical processing system.
5. The method for stabilizing surface roughness based on digital twinning as claimed in any one of claims 1 to 3, wherein: the machining system is a five-axis machining system, and machining parameters influencing surface roughness comprise a lead angle, a tilt angle, a cutting depth, a spindle rotating speed, a feeding speed and an average cutting force.
6. The method of stabilizing surface roughness based on digital twinning as claimed in claim 5, wherein: dividing machining parameters influencing surface roughness into online adjustable parameters and non-online adjustable parameters based on feasibility of machine tool operation, wherein the online adjustable parameters comprise tool attitude parameters and spindle rotation speed, and the tool attitude parameters comprise lead angles and tilt angles; the non-online adjustable parameters include depth of cut, feed rate, and average cutting force.
7. The method of stabilizing surface roughness based on digital twinning as claimed in claim 6, wherein: in the step 4), a point corresponding to the current processing condition is found in the surface roughness prediction model, a direction with the fastest surface roughness change corresponding to the online adjustable parameter is found in the surface roughness prediction model on the basis of the point, a target point is taken in the direction with the fastest surface roughness change, the surface roughness of the target point is enabled to be within a set threshold range, and the processing parameter corresponding to the target point is fed back to the mechanical processing system.
8. The method of stabilizing surface roughness based on digital twinning as claimed in claim 7, wherein: if the parameters can be continuously adjusted for more than N times, the parameters can not be adjusted on line
If the position is within the range of the set threshold value, the condition that only the tool attitude parameter and the spindle rotating speed are adjusted can not meet the current machining requirement is shown, at the moment, all machining parameters influencing the surface roughness are taken as the adjusting objects, and the adjusting method comprises the following steps: finding a point corresponding to the current processing condition in a surface roughness prediction model, finding a direction with the fastest surface roughness change in the surface roughness prediction model on the basis of the point, taking a target point in the direction with the fastest surface roughness change, enabling the surface roughness at the target point to be within a set threshold range, and feeding back processing parameters corresponding to the target point to a mechanical processing system, wherein N is a positive integer greater than or equal to 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010692248.4A CN111859566B (en) | 2020-07-17 | 2020-07-17 | Digital twinning-based surface roughness stabilization method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010692248.4A CN111859566B (en) | 2020-07-17 | 2020-07-17 | Digital twinning-based surface roughness stabilization method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111859566A true CN111859566A (en) | 2020-10-30 |
| CN111859566B CN111859566B (en) | 2023-11-17 |
Family
ID=73001836
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010692248.4A Active CN111859566B (en) | 2020-07-17 | 2020-07-17 | Digital twinning-based surface roughness stabilization method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111859566B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112859739A (en) * | 2021-01-15 | 2021-05-28 | 天津商业大学 | Digital twin-driven multi-axis numerical control machine tool contour error suppression method |
| CN113095195A (en) * | 2021-04-03 | 2021-07-09 | 西北工业大学 | Part unique identification method based on surface appearance self-features |
| CN114453630A (en) * | 2022-01-20 | 2022-05-10 | 湖北文理学院 | Method and device for controlling machine tool to mill non-stick tool, electronic equipment and storage medium |
| CN114643496A (en) * | 2020-12-21 | 2022-06-21 | 财团法人工业技术研究院 | Machining monitoring method and system for machine tool |
| CN116089818A (en) * | 2023-01-10 | 2023-05-09 | 南京航空航天大学 | Workpiece surface roughness prediction method, system and product in machining process |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103761429A (en) * | 2014-01-10 | 2014-04-30 | 大连理工大学 | Milling workpiece surface roughness predicting method |
| CN110045608A (en) * | 2019-04-02 | 2019-07-23 | 太原理工大学 | Based on the twin mechanical equipment component structural dynamic state of parameters optimization method of number |
| CN110348075A (en) * | 2019-06-20 | 2019-10-18 | 湖南科技大学 | A kind of grinding surface roughness prediction technique based on improvement algorithm of support vector machine |
| CN110705882A (en) * | 2019-09-30 | 2020-01-17 | 江苏科技大学 | Twin data driven ship assembly product quality control system and configuration method |
| US20200089826A1 (en) * | 2018-09-14 | 2020-03-19 | Northwestern University | Integrated process-structure-property modeling frameworks and methods for design optimization and/or performance prediction of material systems and applications of same |
| CN110900307A (en) * | 2019-11-22 | 2020-03-24 | 北京航空航天大学 | Numerical control machine tool cutter monitoring system driven by digital twin |
| CN111008502A (en) * | 2019-11-25 | 2020-04-14 | 北京航空航天大学 | Fault prediction method for complex equipment driven by digital twin |
| CN111161410A (en) * | 2019-12-30 | 2020-05-15 | 中国矿业大学(北京) | Mine digital twinning model and construction method thereof |
| CN111210359A (en) * | 2019-12-30 | 2020-05-29 | 中国矿业大学(北京) | Intelligent mine scene oriented digital twin evolution mechanism and method |
| CN111365158A (en) * | 2020-03-02 | 2020-07-03 | 东方电气集团东方电机有限公司 | Real-time state evaluation and life cycle management prediction system for water turbine runner |
-
2020
- 2020-07-17 CN CN202010692248.4A patent/CN111859566B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103761429A (en) * | 2014-01-10 | 2014-04-30 | 大连理工大学 | Milling workpiece surface roughness predicting method |
| US20200089826A1 (en) * | 2018-09-14 | 2020-03-19 | Northwestern University | Integrated process-structure-property modeling frameworks and methods for design optimization and/or performance prediction of material systems and applications of same |
| CN110045608A (en) * | 2019-04-02 | 2019-07-23 | 太原理工大学 | Based on the twin mechanical equipment component structural dynamic state of parameters optimization method of number |
| CN110348075A (en) * | 2019-06-20 | 2019-10-18 | 湖南科技大学 | A kind of grinding surface roughness prediction technique based on improvement algorithm of support vector machine |
| CN110705882A (en) * | 2019-09-30 | 2020-01-17 | 江苏科技大学 | Twin data driven ship assembly product quality control system and configuration method |
| CN110900307A (en) * | 2019-11-22 | 2020-03-24 | 北京航空航天大学 | Numerical control machine tool cutter monitoring system driven by digital twin |
| CN111008502A (en) * | 2019-11-25 | 2020-04-14 | 北京航空航天大学 | Fault prediction method for complex equipment driven by digital twin |
| CN111161410A (en) * | 2019-12-30 | 2020-05-15 | 中国矿业大学(北京) | Mine digital twinning model and construction method thereof |
| CN111210359A (en) * | 2019-12-30 | 2020-05-29 | 中国矿业大学(北京) | Intelligent mine scene oriented digital twin evolution mechanism and method |
| CN111365158A (en) * | 2020-03-02 | 2020-07-03 | 东方电气集团东方电机有限公司 | Real-time state evaluation and life cycle management prediction system for water turbine runner |
Non-Patent Citations (1)
| Title |
|---|
| 王时龙; 王彦凯; 杨波; 王四宝: "基于层次化数字孪生的工业互联网制造新范式——雾制造", 《计算机集成制造系统》, pages 3070 - 3080 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114643496A (en) * | 2020-12-21 | 2022-06-21 | 财团法人工业技术研究院 | Machining monitoring method and system for machine tool |
| CN112859739A (en) * | 2021-01-15 | 2021-05-28 | 天津商业大学 | Digital twin-driven multi-axis numerical control machine tool contour error suppression method |
| CN112859739B (en) * | 2021-01-15 | 2022-07-01 | 天津商业大学 | Digital twin-driven multi-axis numerical control machine tool contour error suppression method |
| CN113095195A (en) * | 2021-04-03 | 2021-07-09 | 西北工业大学 | Part unique identification method based on surface appearance self-features |
| CN113095195B (en) * | 2021-04-03 | 2023-04-07 | 西北工业大学 | Part unique identification method based on surface topography self-characteristics |
| CN114453630A (en) * | 2022-01-20 | 2022-05-10 | 湖北文理学院 | Method and device for controlling machine tool to mill non-stick tool, electronic equipment and storage medium |
| CN116089818A (en) * | 2023-01-10 | 2023-05-09 | 南京航空航天大学 | Workpiece surface roughness prediction method, system and product in machining process |
| CN116089818B (en) * | 2023-01-10 | 2023-10-27 | 南京航空航天大学 | Workpiece surface roughness prediction method, system and product in machining process |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111859566B (en) | 2023-11-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111859566B (en) | Digital twinning-based surface roughness stabilization method | |
| ES2939000T3 (en) | Method to optimize the productivity of a machining process of a CNC machine | |
| Zhao et al. | Surface roughness stabilization method based on digital twin-driven machining parameters self-adaption adjustment: A case study in five-axis machining | |
| Bouacha et al. | Hard turning behavior improvement using NSGA-II and PSO-NN hybrid model | |
| Altintas et al. | Virtual high performance milling | |
| CN110161963B (en) | Simulation model and verification method for milling cutter cutting error forming process | |
| Stemmler et al. | Model predictive control for force control in milling | |
| CN114925596A (en) | Method for optimizing casting platform finish milling parameters based on wafer test equipment | |
| CN109597355B (en) | Design method of curved surface micro-texture numerical control machining cutter shaft vector | |
| CN114509991B (en) | Numerical control machine tool cutting stability prediction and optimization method considering parameter uncertainty | |
| Ferry et al. | Virtual five-axis flank milling of jet engine impellers—part II: feed rate optimization of five-axis flank milling | |
| CN109656192A (en) | A kind of processing optimization method based on rose cutter Milling Force | |
| CN110402188A (en) | Drive system and its assessment | |
| Cai et al. | Cutter orientation planning in NC machining for surface similar to revolution body with considering kinematic characteristics | |
| CN103995979A (en) | Grinding force computing method for aspheric surface parallel grinding machining | |
| Huang et al. | Fuzzy logic for constant force control of end milling | |
| CN107850886A (en) | Method for orienting workpiece | |
| CN109933940A (en) | Hobbing processes parameter optimization method based on hobboing cutter spindle vibration response model | |
| Asiltürk et al. | Intelligent adaptive control and monitoring of band sawing using a neural-fuzzy system | |
| Vainer | Determining the parameters of the technological space in bilateral end grinding. | |
| Zhao et al. | Theoretical and experimental investigation of the effect of the machining process chain on surface generation in ultra-precision fly cutting | |
| CN114750146A (en) | Robot milling track precision compensation method | |
| CN112035978A (en) | Cutter parameter optimization design method and system | |
| CN108255133B (en) | Material removal rate calculation method for five-axis machining of circular blade type annular cutter | |
| Bilek et al. | Prediction and modeling of roughness in ball end milling with tool-surface inclination |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |