CN117270457B - Data mechanism hybrid driving robot milling stability modeling method - Google Patents
Data mechanism hybrid driving robot milling stability modeling method Download PDFInfo
- Publication number
- CN117270457B CN117270457B CN202311250113.2A CN202311250113A CN117270457B CN 117270457 B CN117270457 B CN 117270457B CN 202311250113 A CN202311250113 A CN 202311250113A CN 117270457 B CN117270457 B CN 117270457B
- Authority
- CN
- China
- Prior art keywords
- milling
- domain
- discrete
- stability model
- model
- 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.)
- Active
Links
- 238000003801 milling Methods 0.000 title claims abstract description 101
- 238000000034 method Methods 0.000 title claims abstract description 20
- 230000007246 mechanism Effects 0.000 title claims abstract description 19
- 238000012545 processing Methods 0.000 claims abstract description 19
- 238000010586 diagram Methods 0.000 claims abstract description 9
- 238000005457 optimization Methods 0.000 claims abstract description 5
- 238000001514 detection method Methods 0.000 claims description 6
- 238000007637 random forest analysis Methods 0.000 claims description 6
- 238000013016 damping Methods 0.000 claims description 5
- 238000013507 mapping Methods 0.000 claims description 5
- 238000005316 response function Methods 0.000 claims description 5
- 238000013135 deep learning Methods 0.000 claims description 4
- 238000004422 calculation algorithm Methods 0.000 claims description 3
- 238000003754 machining Methods 0.000 description 14
- 230000008569 process Effects 0.000 description 9
- 230000004927 fusion Effects 0.000 description 3
- 238000007499 fusion processing Methods 0.000 description 2
- 230000005855 radiation Effects 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 230000006641 stabilisation Effects 0.000 description 1
- 238000011105 stabilization Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/18—Numerical control [NC], i.e. automatically operating machines, in particular machine tools, e.g. in a manufacturing environment, so as to execute positioning, movement or co-ordinated operations by means of programme data in numerical form
- G05B19/408—Numerical control [NC], i.e. automatically operating machines, in particular machine tools, e.g. in a manufacturing environment, so as to execute positioning, movement or co-ordinated operations by means of programme data in numerical form characterised by data handling or data format, e.g. reading, buffering or conversion of data
- G05B19/4086—Coordinate conversions; Other special calculations
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/35—Nc in input of data, input till input file format
- G05B2219/35356—Data handling
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Manufacturing & Machinery (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Numerical Control (AREA)
Abstract
The invention discloses a data mechanism hybrid driving robot milling stability modeling method, which comprises the following steps: s1, acquiring a continuous domain milling stability model; s2, converting a continuous stability lobe diagram of the continuous domain milling stability model into a theoretical discrete data point set R t; s3, obtaining a discrete domain milling stability model according to the theoretical discrete data point set; s4, obtaining a data set R r containing actual processing technological parameters and milling states according to the discrete domain milling stability model; s5, obtaining an optimized and updated discrete domain milling stability model according to R t and R r; and step S6, based on the optimized and updated discrete domain milling stability model, repeating the steps S4 to S5 until the discrete domain milling stability model subjected to multiple times of optimization in S5 is not changed. By adopting the technical scheme of the invention, the milling stability model of the robot can be accurately established, and the milling process planning of the robot can be effectively guided.
Description
Technical Field
The invention belongs to the technical field of robot processing, and particularly relates to a data mechanism hybrid driving robot milling stability modeling method.
Background
Compared with the traditional numerical control machining, the robot milling machining has the advantages of high flexibility, low cost and the like, is gradually applied to the machining of large-scale components in recent years, however, the robot body has the characteristic of weak rigidity, and is extremely easy to generate chatter in the milling machining to influence the machining quality.
In numerical control machining, a machining stability model can be established according to a cutting mechanism and according to modal parameters of a tool tip point and represented by a stability lobe diagram. The cutting machining stability lobe diagram can accurately represent the specific technological parameters, namely the cutting state corresponding to the spindle rotating speed and the cutting depth, judges whether chatter can occur, and can effectively guide the selection of the machining technological parameters. However, for robot machining, on one hand, the serial structure of the robot body causes different modal parameters of the tool tip point under different machining positions, and on the other hand, the weak rigidity of the body causes inaccuracy of the robot machining stability model established according to the cutting mechanism, so that the stability model established by only relying on the cutting mechanism cannot accurately express the relationship between the technological parameters and the cutting state.
Therefore, aiming at the milling processing of the robot, the invention provides a data mechanism hybrid-driven modeling method for the milling stability of the robot.
Disclosure of Invention
Aiming at the problem that a milling stability model established based on a cutting mechanism is inaccurate in a robot milling process, the invention provides a data mechanism hybrid driving robot milling stability modeling method, which converts a continuous domain milling stability model established according to the cutting mechanism into a data driving discrete domain milling stability model, and further fuses actual process data with theoretical data, so that iterative optimization of the robot milling stability model is realized, and a more accurate stability model is obtained.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
A data mechanism hybrid driving robot milling stability modeling method comprises the following steps:
S1, acquiring a continuous domain milling stability model;
s2, converting a continuous stability lobe diagram of the continuous domain milling stability model into a theoretical discrete data point set R t;
s3, obtaining a discrete domain milling stability model according to the theoretical discrete data point set;
S4, obtaining a data set R r containing actual processing technological parameters and milling states according to the discrete domain milling stability model;
step S5, obtaining an optimized and updated discrete domain milling stability model according to the theoretical discrete data point set R t and the data set R r containing actual processing technological parameters and milling states;
And step S6, based on the optimized and updated discrete domain milling stability model, repeating the steps S4 to S5 until the discrete domain milling stability model subjected to multiple times of optimization in S5 is not changed.
Preferably, step S1 includes:
According to the frequency response function of the tool tip of the processing robot under a specific pose, calculating the modal frequency, the damping ratio and the modal rigidity;
and obtaining a continuous domain milling stability model according to the modal frequency, the damping ratio and the modal rigidity, wherein the continuous domain milling stability model comprises a stability lobe diagram.
Preferably, in step S3, a mapping model of the spindle rotation speed, the cutting depth and the milling state, that is, a discrete domain milling stability model is established by using a random forest algorithm with the theoretical discrete data point set as a data set.
Preferably, in step S4, appropriate process parameters are selected according to the discrete domain milling stability model to perform milling, processing vibration data is collected, a deep learning-based chatter detection method is adopted, the processing vibration data is taken as input, a milling state is output, and a dataset R r including actual processing process parameters and the milling state is obtained.
Preferably, in step S5, the dataset R t obtained in S2 and the dataset R r obtained in S4 are fused to obtain a virtual-real fusion dataset R f, and a mapping model based on the spindle rotation speed, the cutting depth and the milling state of the random forest, that is, an optimized and updated discrete domain milling stability model is re-established based on the dataset R f.
The invention has the following technical effects:
the method aims at the problem that a milling stability model established based on a cutting mechanism in a robot milling process is inaccurate, and converts a mechanism model into a theoretical data driven model by converting a continuous domain milling stability model into a discrete domain milling stability model.
The invention utilizes the advantages of the data driving model, merges the actual process data, realizes the fusion of the actual process data and the theoretical data, and establishes a more accurate robot milling stability model.
The invention has simple operation process, and no additional assistance of operators is needed in the implementation process of the specific process.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the drawings that are needed in the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for modeling milling stability of a robot driven by a data mechanism in an embodiment of the invention;
FIG. 2 is a continuous domain and discrete domain milling stability model in an embodiment of the present invention; wherein (a) represents a continuous domain milling stability model and (b) represents a discrete domain milling stability model corresponding to the continuous domain milling stability model;
FIG. 3 is actual milling status data of a robot in an embodiment of the present invention;
FIG. 4 is a fusion process of theoretical, radiated, and actual data points in an embodiment of the invention.
FIG. 5 is a diffraction process of a discrete domain milling stability model under the influence of different numbers of actual data points in an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, not all embodiments of the present invention. All other embodiments obtained by those skilled in the art without making any inventive effort based on the embodiments of the present invention are within the scope of the present invention.
In order that the above-recited objects, features and advantages of the present invention will become more readily apparent, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description.
Example 1:
as shown in fig. 1, the embodiment of the invention provides a data mechanism hybrid driving robot milling stability modeling method, which comprises the following steps:
S1, acquiring a frequency response function of a tool tip point of the machining robot under a specific pose, calculating modal parameters, and calculating a stability lobe diagram according to a cutting mechanism to obtain a continuous domain milling stability model. The frequency response function of the tool tip point of the processing robot under a specific pose is obtained by adopting a hammering experiment, the modal frequency, the damping ratio and the modal rigidity are obtained by calculating according to the frequency response function, and a continuous domain milling stability lobe diagram is obtained by calculating by adopting a ZOA (zero order frequency domain analysis method), as shown in (a) in fig. 2, the upper part of the curve represents the flutter state, and the lower part of the curve represents the stable state.
Step S2, converting the continuous milling stability lobe map calculated in step S1 into a theoretical discrete data point set R t, as shown in (b) of fig. 2. Each data point in the data point set R t can be expressed as (a p, n, s), where a p is the depth of cut, n is the spindle rotation speed, s is the milling state, where the milling state is divided into the chatter state, the transition state, and the steady state in the present invention, and in fig. 2 (b), since the calculation result according to the cutting mechanism includes only two kinds of chatter state and steady state, the theoretical discrete data point set also has only two kinds of states.
And S3, taking the theoretical discrete data point set obtained in the step S2 as a training data set, adopting a random forest algorithm, inputting data into the model for milling the workpiece, namely, chatter, transition or stabilization, to obtain a discrete domain milling stability model M, wherein the model can give a milling state under the condition of designating any cutting depth and spindle rotation speed, and can be used for guiding the selection of the milling process parameters of the robot.
And S4, selecting proper technological parameters according to the discrete domain milling stability model obtained in the step S3 to perform milling, collecting processing vibration data, adopting a deep learning-based chatter detection method, establishing a chatter detection model, taking the processing vibration data as input, outputting a milling state, taking the cutting vibration data as input, taking the input data dimension as 4096,1, forming a data set R r as actual milling state data by using the chatter detection model based on the deep learning, wherein the model structure comprises 6 one-dimensional convolution layers, one maximum pooling layer and 4 full-connection layers, the channel number of the 6 one-dimensional convolution layers is (64, 64, 128, 256, 512, 1024), the neuron number of the 3 full-connection layers is (1024, 512, 256, 3), and recording the cutting depth and the spindle rotation speed corresponding to the processing vibration data and the output of the chatter detection model, namely the milling state, and the obtained result forms the data set R r as shown in FIG. 3.
Step S5, fusing the dataset R t obtained in step S2 with the dataset R r obtained in step S4, wherein the fusion process is shown in FIG. 4. First, based on each data point in the data set R r, a radiation data point set R r 'is generated, taking the data point P i∈Rr as an example, the spindle speed, cutting depth and milling state corresponding to P i are (a pi,ni,si), and the spindle speed, cutting depth and milling state corresponding to the corresponding radiation data point P j∈Rr' are (a pj,nj,sj), wherein the variables satisfy the conditionWhere S w represents a rotation speed range and S h represents a cutting depth range, R r' can be obtained. And then the union of the data sets R r and R r 'is adopted to obtain R r"＝Rr∪Rr'. Finally, the milling state of the corresponding data points in the theoretical discrete data point set R t and the corresponding data points in the R r 'is changed to be the same as the milling state in the R r', and a virtual-real fusion data set R f is obtained. And reestablishing a mapping model based on the spindle rotating speed, the cutting depth and the milling state of the random forest based on the data set, namely optimizing an updated discrete domain milling stability model M'.
And step S6, based on the optimized and updated discrete domain milling stability model M' obtained in the step S5, repeating the steps S4 to S5 until the discrete domain milling stability model subjected to multiple optimization in the step S5 is not changed. As shown in fig. 5, the discrete domain milling stability model generated after the actual data points and the theoretical data points are fused with each other is shown, and the model tends to be stable and is similar to the milling state trend of the actual machining result in fig. 3 with the increase of the actual data points.
While the invention has been described in detail in connection with specific preferred embodiments thereof, it is not to be construed as limited thereto, but rather as a result of a simple deduction or substitution by a person having ordinary skill in the art without departing from the spirit of the invention, which is to be construed as falling within the scope of the invention defined by the appended claims.
Claims (1)
1. The data mechanism hybrid driving robot milling stability modeling method is characterized by comprising the following steps of:
S1, acquiring a continuous domain milling stability model;
s2, converting a continuous stability lobe diagram of the continuous domain milling stability model into a theoretical discrete data point set R t;
s3, obtaining a discrete domain milling stability model according to the theoretical discrete data point set;
S4, obtaining a data set R r containing actual processing technological parameters and milling states according to the discrete domain milling stability model;
step S5, obtaining an optimized and updated discrete domain milling stability model according to the theoretical discrete data point set R t and the data set R r containing actual processing technological parameters and milling states;
Step S6, based on the optimized and updated discrete domain milling stability model, repeating the steps S4 to S5 until the discrete domain milling stability model subjected to multiple times of optimization in S5 is not changed;
the step S1 comprises the following steps:
According to the frequency response function of the tool tip of the processing robot under a specific pose, calculating the modal frequency, the damping ratio and the modal rigidity;
obtaining a continuous domain milling stability model according to the modal frequency, the damping ratio and the modal rigidity, wherein the continuous domain milling stability model comprises a stability lobe diagram;
in the step S3, a mapping model of the spindle rotation speed, the cutting depth and the milling state, namely a discrete domain milling stability model is established by taking a theoretical discrete data point set as a data set and adopting a random forest algorithm;
In step S4, selecting proper technological parameters according to a discrete domain milling stability model for milling, collecting processing vibration data, and adopting a deep learning-based chatter detection method to take the processing vibration data as input and output a milling state to obtain a dataset R r containing actual processing technological parameters and the milling state;
In step S5, the dataset R t obtained in step S2 and the dataset R r obtained in step S4 are fused to obtain a virtual-real fused dataset R f, and a mapping model based on the spindle rotation speed, the cutting depth and the milling state of the random forest is reestablished based on the dataset R f, namely, the updated discrete domain milling stability model is optimized.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311250113.2A CN117270457B (en) | 2023-09-26 | 2023-09-26 | Data mechanism hybrid driving robot milling stability modeling method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311250113.2A CN117270457B (en) | 2023-09-26 | 2023-09-26 | Data mechanism hybrid driving robot milling stability modeling method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117270457A CN117270457A (en) | 2023-12-22 |
| CN117270457B true CN117270457B (en) | 2024-04-19 |
Family
ID=89211830
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311250113.2A Active CN117270457B (en) | 2023-09-26 | 2023-09-26 | Data mechanism hybrid driving robot milling stability modeling method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117270457B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE4218799A1 (en) * | 1992-06-06 | 1993-12-16 | Brandmeier Thomas Dr | Monitoring cutting edge wear in NC machine tool - using sensor to observe cutting operation and analysing signal spectrum in dependence on frequency changes and overall pattern |
| CN109909806A (en) * | 2019-03-22 | 2019-06-21 | 南京理工大学 | A kind of method of hoisting machine people milling stable region |
| CN113820999A (en) * | 2021-09-26 | 2021-12-21 | 南昌航空大学 | Stable milling process parameter optimization method based on neural network and genetic algorithm |
| WO2022051973A1 (en) * | 2020-09-10 | 2022-03-17 | 南京航空航天大学 | Milling robot multi-modal frequency response prediction method based on small-sample transfer learning |
| CN115890345A (en) * | 2022-11-04 | 2023-04-04 | 华中科技大学 | Robot milling low-frequency flutter stability prediction method and system |
| CN116484533A (en) * | 2023-04-24 | 2023-07-25 | 南昌航空大学 | Milling stability analysis method based on Bernoulli distribution and hybrid driving method |
-
2023
- 2023-09-26 CN CN202311250113.2A patent/CN117270457B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE4218799A1 (en) * | 1992-06-06 | 1993-12-16 | Brandmeier Thomas Dr | Monitoring cutting edge wear in NC machine tool - using sensor to observe cutting operation and analysing signal spectrum in dependence on frequency changes and overall pattern |
| CN109909806A (en) * | 2019-03-22 | 2019-06-21 | 南京理工大学 | A kind of method of hoisting machine people milling stable region |
| WO2022051973A1 (en) * | 2020-09-10 | 2022-03-17 | 南京航空航天大学 | Milling robot multi-modal frequency response prediction method based on small-sample transfer learning |
| CN113820999A (en) * | 2021-09-26 | 2021-12-21 | 南昌航空大学 | Stable milling process parameter optimization method based on neural network and genetic algorithm |
| CN115890345A (en) * | 2022-11-04 | 2023-04-04 | 华中科技大学 | Robot milling low-frequency flutter stability prediction method and system |
| CN116484533A (en) * | 2023-04-24 | 2023-07-25 | 南昌航空大学 | Milling stability analysis method based on Bernoulli distribution and hybrid driving method |
Non-Patent Citations (1)
| Title |
|---|
| 蔡永林等.基于双柔性系统的铣削加工稳定性分析.北京交通大学学报.(第04期),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117270457A (en) | 2023-12-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| De Silva | Intelligent control: fuzzy logic applications | |
| US7065420B1 (en) | Integrated real-time feature based costing | |
| JP3312154B2 (en) | Processing information determination system and method, and processing step information determination system and method | |
| DE102018211682A1 (en) | MACHINE LEARNING DEVICE, NUMERICAL CONTROL DEVICE, NUMERICAL CONTROL SYSTEM AND MASCHINAL LEARNING PROCESS | |
| US20120265331A1 (en) | Five-axis flank milling system for machining curved surface and the tool-path planning method thereof | |
| JP2009522682A (en) | Method of converting from G code to STEP-NC part program | |
| CN111857052A (en) | Machine learning device, numerical control system, and machine learning method | |
| TW202022652A (en) | Machining parameter adjustment system and maching parameter adjustment method | |
| CN114509991B (en) | Numerical control machine tool cutting stability prediction and optimization method considering parameter uncertainty | |
| Hosseini et al. | Prediction of cutting forces in broaching operation | |
| CN115494796B (en) | Edge cloud collaborative digital twin system based on STEP-NC | |
| Gadakh et al. | Selection of cutting parameters in side milling operation using graph theory and matrix approach | |
| CN117270457B (en) | Data mechanism hybrid driving robot milling stability modeling method | |
| CN107491036B (en) | Machine tool machining energy consumption control method and machine tool | |
| Hayes Jr et al. | A discrete variable approach to machine parameter optimization | |
| US6678575B1 (en) | Method and system for generating numerically controlled tool paths on a solid model | |
| CN116700149A (en) | Self-adaptive filtering optimization method for numerical control machining tool path | |
| WO2021029036A1 (en) | Machine learning device, data processing system, and machine learning method | |
| JP5441627B2 (en) | Optimal process determination device and optimal process determination method | |
| WO2023002627A1 (en) | Movement route determination device and computer program | |
| US11507058B2 (en) | Method for ascertaining a rough trajectory from a specified contour | |
| Huang et al. | Building prediction model for a machine tool with genetic algorithm optimization on a general regression neural network | |
| CN113192180A (en) | Elliptic gear parameterization accurate modeling method based on gear shaping machining principle | |
| Wang et al. | Optimization of the tool selection based on big data | |
| Chang et al. | Hybrid multi-object optimization method for tapping center machines |
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 |