CN113534741A - Control method and system for milling thin-walled workpiece - Google Patents
Control method and system for milling thin-walled workpiece Download PDFInfo
- Publication number
- CN113534741A CN113534741A CN202110789254.6A CN202110789254A CN113534741A CN 113534741 A CN113534741 A CN 113534741A CN 202110789254 A CN202110789254 A CN 202110789254A CN 113534741 A CN113534741 A CN 113534741A
- Authority
- CN
- China
- Prior art keywords
- thin
- machining
- parameters
- wall part
- milling
- 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.)
- Pending
Links
- 238000003801 milling Methods 0.000 title claims abstract description 140
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000003754 machining Methods 0.000 claims abstract description 264
- 238000004088 simulation Methods 0.000 claims description 71
- 238000012545 processing Methods 0.000 claims description 22
- 238000013527 convolutional neural network Methods 0.000 claims description 10
- 238000012549 training Methods 0.000 claims description 9
- 238000013528 artificial neural network Methods 0.000 claims description 7
- 238000013507 mapping Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 8
- 238000004422 calculation algorithm Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000000605 extraction Methods 0.000 description 4
- 230000001276 controlling effect Effects 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000005520 cutting process Methods 0.000 description 2
- 238000006073 displacement reaction Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007123 defense Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
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
- G05B19/409—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 using manual data input [MDI] or by using control panel, e.g. controlling functions with the panel; characterised by control panel details or by setting parameters
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- G05B2219/31—From computer integrated manufacturing till monitoring
- G05B2219/31061—Selection of assembly process parameters
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Manufacturing & Machinery (AREA)
- Automation & Control Theory (AREA)
- Numerical Control (AREA)
Abstract
The invention provides a control method and a system for milling a thin-walled workpiece, wherein the method comprises the following steps: acquiring current operating parameters of a thin-wall part milling process and basic parameters of thin-wall part milling equipment; establishing a digital twin model of the milling process of the thin-wall part according to the basic parameters and the current operating parameters; inputting the current operation parameters into a machining deformation prediction model to obtain a machining deformation prediction value of the thin-wall part; and updating the machining parameters of the milling process of the thin-wall part according to the predicted value of the machining deformation and the digital twin model. The invention aims to provide a control method and a control system for milling a thin-walled workpiece, which can predict the milling deformation of the thin-walled workpiece in real time, further accurately control the machining precision of the thin-walled workpiece and shorten the machining period of the thin-walled workpiece.
Description
Technical Field
The invention relates to the technical field of thin-wall part machining, in particular to a control method and a control system for milling a thin-wall part.
Background
The thin-wall part has light weight and compact structure, and is widely applied to the fields of aerospace, national defense science and technology, nuclear power equipment, automobile manufacturing and the like. However, the thin-wall part has the characteristics of large size, complex structure and easy deformation, and the machining process is difficult to control accurately, so that the machining cost of the parts is high, and the manufacturing period is long, and therefore, the accurate prediction and control of the machining deformation of the thin-wall part are technological problems which need to be solved urgently.
At present, the control precision of the thin-wall part machining process is low for the following reasons: firstly, in the actual milling process, the milling force coefficient is continuously changed, and the milling force coefficient in the existing milling force model is a fixed value, so that the milling characteristic in the machining process cannot be comprehensively described; secondly, the simulation software is utilized to simulate the milling process, so that the simulation period is long, and the problem of non-convergence is easy to occur; thirdly, the existing thin-wall part machining deformation prediction and control only can analyze the last feed of finish machining, but the change of parameters in the whole process flow and the manufacturing period of the thin-wall part can affect the final deformation of the thin-wall part.
Therefore, a control method and a control system for milling a thin-walled workpiece are needed to improve the control precision of the thin-walled workpiece machining process.
Disclosure of Invention
The invention aims to provide a control method and a control system for milling a thin-walled workpiece, which can predict the deformation of the thin-walled workpiece during milling in real time, further improve the control precision of the thin-walled workpiece processing process and shorten the processing period of the thin-walled workpiece.
In order to achieve the purpose, the invention provides the following scheme:
a control method for milling a thin-walled part comprises the following steps:
acquiring current operating parameters of a thin-wall part milling process and basic parameters of thin-wall part milling equipment; the current operating parameters comprise a current milling force and a current vibration frequency; the basic parameters comprise machine tool parameters, tool parameters and clamp parameters;
establishing a digital twin model of the milling process of the thin-wall part according to the basic parameters and the current operating parameters;
inputting the current operation parameters into a machining deformation prediction model to obtain a machining deformation prediction value of the thin-walled workpiece; the machining deformation prediction model is obtained by training a convolution neural network by utilizing historical operating parameters of a thin-wall part in a milling process and historical machining deformation of the thin-wall part;
updating the machining parameters of the thin-wall part in the milling machining process according to the predicted machining deformation value and the digital twin model; the machining parameters comprise the feed multiplying power of the thin-wall part and the rotating speed of the cutter.
Optionally, before the obtaining of the current operating parameters of the milling process of the thin-wall part and the basic parameters of the milling equipment of the thin-wall part, the method further includes:
acquiring historical operating parameters of a thin-wall part in a milling process and historical machining deformation of the thin-wall part; the historical operating parameters comprise a plurality of groups of historical milling forces and historical vibration frequencies under the same thickness;
and taking the historical operating parameters as input and the historical machining deformation as output to obtain a trained convolutional neural network as the machining deformation prediction model.
Optionally, the updating of the machining parameters of the milling process of the thin-wall part specifically includes:
acquiring current machining parameters of a thin-wall part in a milling process, and stopping milling the thin-wall part;
taking the current machining parameters as simulated machining parameters of the digital twin model;
inputting the simulated machining parameters into the digital twin model to obtain simulated operation parameters of the milling process of the thin-wall part;
inputting simulation operation parameters of the milling process of the thin-wall part into the machining deformation prediction model to obtain a machining deformation simulation value;
and when the machining deformation simulation value is greater than or equal to the machining deformation threshold value, updating the simulation machining parameters and executing the step of inputting the simulation machining parameters into the digital twin model to obtain simulation operation parameters of the milling process of the thin-wall part until the machining deformation simulation value is less than the machining deformation threshold value, taking the updated simulation machining parameters as current machining parameters, and continuing milling the thin-wall part.
Optionally, before the updating of the machining parameters of the milling process of the thin-wall part, the method further includes:
judging whether the predicted value of the machining deformation is larger than a machining deformation threshold value or not to obtain a first judgment result;
if the first judgment result is negative, displaying the predicted value of the machining deformation amount at the digital twin model;
and if the first judgment result is yes, executing the step of updating the machining parameters of the thin-wall part milling process.
A control system for milling a thin-walled part, comprising:
the first data acquisition module is used for acquiring the current operating parameters of the thin-wall part milling process and the basic parameters of the thin-wall part milling equipment; the current operating parameters comprise a current milling force and a current vibration frequency; the basic parameters comprise machine tool parameters, tool parameters and clamp parameters;
the digital twin model establishing module is used for establishing a digital twin model of the milling process of the thin-wall part according to the basic parameters and the current operating parameters;
the machining deformation predicted value determining module is used for inputting the current operation parameters into a machining deformation prediction model to obtain a machining deformation predicted value of the thin-wall part; the machining deformation prediction model is obtained by training a convolution neural network by utilizing historical operating parameters of a thin-wall part in a milling process and historical machining deformation of the thin-wall part;
the machining parameter updating module is used for updating the machining parameters of the thin-wall part in the milling machining process according to the machining deformation prediction value and the digital twin model; the machining parameters comprise the feed multiplying power of the thin-wall part and the rotating speed of the cutter.
Optionally, the system further includes:
the second data acquisition module is used for acquiring historical operating parameters of the thin-wall part in the milling process and historical machining deformation of the thin-wall part; the historical operating parameters comprise a plurality of groups of historical milling forces and historical vibration frequencies under the same thickness;
and the machining deformation prediction model determining module is used for taking the historical operating parameters as input and the historical machining deformation as output to obtain a trained convolutional neural network as the machining deformation prediction model.
Optionally, the processing parameter updating module specifically includes:
the third data acquisition unit is used for acquiring the current processing parameters of the thin-wall part in the milling process and stopping milling the thin-wall part;
the simulation machining parameter determining unit is used for taking the current machining parameters as simulation machining parameters of the digital twin model;
the simulation operation parameter determining unit is used for inputting the simulation machining parameters into the digital twin model to obtain simulation operation parameters of the milling machining process of the thin-wall part;
the machining deformation simulation value determining unit is used for inputting simulation operation parameters of the milling process of the thin-wall part into the machining deformation prediction model to obtain a machining deformation simulation value;
and when the machining deformation simulation value is greater than or equal to the machining deformation threshold value, updating the simulation machining parameters and calling the simulation operation parameter determination unit until the machining deformation simulation value is less than the machining deformation threshold value, taking the updated simulation machining parameters as current machining parameters, and continuing to mill the thin-walled workpiece.
Optionally, the processing parameter updating module further includes:
the first judgment unit is used for judging whether the predicted value of the machining deformation is larger than a threshold value of the machining deformation or not to obtain a first judgment result; if the first judgment result is negative, calling a machining deformation predicted value display unit; if the first judgment result is yes, calling a third data acquisition unit;
and the machining deformation predicted value display unit is used for displaying the machining deformation predicted value at the digital twin model.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
the invention provides a control method and a system for milling a thin-walled workpiece, wherein the method comprises the following steps: acquiring current operating parameters of a thin-wall part milling process and basic parameters of thin-wall part milling equipment; establishing a digital twin model of the milling process of the thin-wall part according to the basic parameters and the current operating parameters; inputting the current operation parameters into a machining deformation prediction model to obtain a machining deformation prediction value of the thin-wall part; and updating the machining parameters of the milling process of the thin-wall part according to the predicted value of the machining deformation and the digital twin model. The invention aims to provide a control method and a control system for milling a thin-walled workpiece, which can predict the milling deformation of the thin-walled workpiece in real time, further accurately control the machining precision of the thin-walled workpiece and shorten the machining period of the thin-walled workpiece.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
FIG. 1 is a flowchart of a control method for milling a thin-walled workpiece according to an embodiment of the present invention;
FIG. 2 is an overall flowchart of a control method for milling a thin-walled workpiece according to an embodiment of the present invention;
FIG. 3 is a data classification diagram according to an embodiment of the present invention;
FIG. 4 is a flow chart of a method for establishing a digital twin model according to an embodiment of the present invention;
FIG. 5 is a flow chart of the thin-wall part machining deformation prediction in the embodiment of the invention;
FIG. 6 is a schematic structural diagram of a control system for milling a thin-walled workpiece according to an embodiment of the present invention;
FIG. 7 is a flowchart illustrating a method for controlling process parameters according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention aims to provide a control method and a control system for milling a thin-walled workpiece, which can predict the deformation of the thin-walled workpiece during milling in real time, further improve the control precision of the thin-walled workpiece processing process and shorten the processing period of the thin-walled workpiece.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
Fig. 1 is a flowchart of a control method for milling a thin-walled workpiece according to an embodiment of the present invention, and as shown in fig. 1, the present invention provides a control method for milling a thin-walled workpiece, including:
step 101: acquiring current operating parameters of a thin-wall part milling process and basic parameters of thin-wall part milling equipment; the current operation parameters comprise the current milling force and the current vibration frequency; the basic parameters comprise machine tool parameters, tool parameters and clamp parameters;
step 102: establishing a digital twin model of the milling process of the thin-wall part according to the basic parameters and the current operating parameters;
step 103: inputting the current operation parameters into a machining deformation prediction model to obtain a machining deformation prediction value of the thin-wall part; the machining deformation prediction model is obtained by training a convolution neural network by utilizing historical operating parameters of the thin-wall part in the milling process and the historical machining deformation of the thin-wall part;
step 104: updating the machining parameters of the milling process of the thin-wall part according to the predicted value of the machining deformation and the digital twin model; the machining parameters comprise the feed multiplying power of the thin-wall part and the rotating speed of the cutter.
Before step 101, further comprising:
acquiring historical operating parameters of a thin-wall part in a milling process and historical machining deformation of the thin-wall part; the historical operating parameters comprise a plurality of groups of historical milling forces and historical vibration frequencies under the same thickness;
and taking the historical operating parameters as input and the historical machining deformation as output to obtain a trained convolutional neural network as a machining deformation prediction model.
acquiring current machining parameters of the thin-wall part in the milling process, and stopping milling the thin-wall part;
taking the current machining parameters as simulation machining parameters of the digital twin model;
inputting the simulation machining parameters into a digital twin model to obtain simulation operation parameters of the milling process of the thin-wall part;
inputting simulation operation parameters of the milling process of the thin-wall part into a machining deformation prediction model to obtain a machining deformation simulation value;
and when the machining deformation simulation value is greater than or equal to the machining deformation threshold value, updating the simulation machining parameters and executing the steps of inputting the simulation machining parameters into the digital twin model to obtain the simulation operation parameters of the milling process of the thin-wall part until the machining deformation simulation value is less than the machining deformation threshold value, taking the updated simulation machining parameters as the current machining parameters, and continuing to mill the thin-wall part.
Before updating the machining parameters of the milling process of the thin-wall part, the method further comprises the following steps:
judging whether the predicted value of the machining deformation is larger than a machining deformation threshold value or not to obtain a first judgment result;
if the first judgment result is negative, displaying the predicted value of the machining deformation amount at the digital twin model;
and if the first judgment result is yes, executing the step of updating the machining parameters of the thin-wall part milling process.
Specifically, fig. 2 is an overall flowchart of a control method for milling a thin-walled workpiece according to an embodiment of the present invention, and as shown in fig. 2, the present invention includes the following steps:
(1) constructing a physical space: the physical space comprises thin-wall part processing equipment, various signal acquisition sensors, hardware, software, auxiliary equipment and the like for processing and analyzing signals.
(2) Data acquisition: the method comprises the steps of collecting data of a thin-wall part processing site in real time, collecting relevant data of cutting force, processing deformation, vibration and the like in real time through a rotary dynamometer, a laser displacement sensor, a sound emission sensor and the like, and collecting data according to specified frequency in the thin-wall part processing process.
Firstly, transmitting collected data of cutting force, vibration and the like to the machining deformation prediction model in the step (4); and verifying the accuracy of the machining deformation prediction model according to the machining deformation obtained by the laser displacement sensor and the predicted deformation in the machining deformation prediction model at the position corresponding to the workpiece. Secondly, the collected data are stored in a database, and more data samples are added for training the machining deformation prediction model. Fig. 3 is a data classification diagram in the embodiment of the present invention, and as shown in fig. 3, the data classification diagram used in the present invention includes static data, dynamic data, and intermediate data.
(3) Constructing a digital twin mapping model: the method comprises the steps of carrying out digital modeling on a thin-wall part machining site, generating a simulation model of the thin-wall part machining site in a computer virtual space, forming a one-to-one mapping relation with real objects in a physical space, and establishing a digital twin mapping model. The digital twin mapping model comprises: a digital twinning machine tool model, a digital twinning tool model and a digital twinning clamp model;
FIG. 4 is a flow chart of a method for establishing a digital twin model according to an embodiment of the present invention; as shown in fig. 4, the digital twin model establishment process is as follows:
performing model mapping on a physical space, drawing a model by using three-dimensional software UG and exporting an STL file; and importing the STL file and the FBX format into a Unity 3D engine to complete the establishment of the digital twin model.
The machine tool movement in the virtual space can be realized through C # language programming;
inputting a machining code (NC code) into a machine tool in a physical space, and transmitting the NC code to a virtual machine tool through an OPC-UA (Unified Architecture) communication protocol so as to realize a mapping relation between the virtual machine tool and the physical machine tool.
(4) Predicting the machining deformation of the thin-wall part: and establishing a machining deformation prediction model by using the historical machining data as a training sample of a convolutional neural network algorithm. Inputting a signal acquired in real time into a machining deformation prediction model, performing real-time simulation calculation by using a digital twin model to obtain the machining deformation of a thin-wall part, and visually displaying a predicted machining deformation value in a visual window of a virtual scene, wherein the specific steps are as shown in fig. 5:
obtaining corresponding physical quantity data, such as milling force, processing deformation and the like, of the thin-wall part in the processing process by utilizing three-dimensional finite element simulation software;
training a convolutional nerve by using physical quantities obtained by simulation and data obtained by a sensor as historical data, and fitting milling force and milling vibration by using a convolutional neural network algorithm to obtain a machining deformation prediction model; convolutional neural network algorithms are one type of intelligent algorithms. In step 5, a signal is sent out after the deformation exceeds a threshold value, and the deformation is controlled by the feed multiplying power and the rotating speed of the machine tool through plc
The digital twin model is synchronously executed with the actual machining process, so that the machining deformation prediction of the thin-wall part can be quickly realized, and the deformation monitoring of the thin-wall part in the whole machining process can also be realized; arranging a sensor on a machine tool, performing dimensionality reduction, local feature extraction and time sequence feature extraction on a signal acquired in real time (performing dimensionality reduction, local feature extraction and time sequence feature extraction), then entering a mapping layer of a convolutional neural network, entering a machining deformation prediction model to obtain machining deformation, comparing the machining deformation with the design requirement of a workpiece, uploading machining process parameters and deformation data to a database if the deformation is within a required range, and updating twin model parameters of the machine tool in a physical space.
(5) And (3) controlling the processing deformation of the thin-wall part, as shown in FIG. 7: the method comprises the following steps that a physical space and a digital twin mapping model synchronously execute a machining process, the physical space obtains a predicted value of machining deformation according to the digital twin model and compares the predicted value with a machining precision requirement (a machining deformation analog value is smaller than a machining deformation threshold), if the machining precision requirement is met, a workpiece is continuously machined, if the precision requirement is not met, a virtual scene sends a signal, the machining deformation of a thin-wall part is controlled by regulating and controlling the feed multiplying power and the rotating speed of a machine tool, and the workpiece meets the machining precision requirement, and the method comprises the following specific steps:
when the predicted value of the machining deformation exceeds the threshold value of the machining deformation, an alarm signal is sent out in a virtual scene, and the output voltage analog quantity is transmitted to a machine tool control system, so that the actual machine tool suspends machining of the thin-walled workpiece. And (3) performing thin-wall part machining simulation on the twin machine tool model, obtaining the optimal feeding multiplying power and rotating speed through iterative circulation, and transmitting the optimal feeding multiplying power and rotating speed to an actual machine tool so as to guide actual machining. After machining is completed, the optimized feed rate and rotational speed are recorded for use as historical machining data.
Fig. 6 is a schematic structural diagram of a control system for milling a thin-walled workpiece according to an embodiment of the present invention, and as shown in fig. 6, the present invention provides a control system for milling a thin-walled workpiece, including:
the first data acquisition module 601 is used for acquiring current operating parameters of a thin-wall part milling process and basic parameters of thin-wall part milling equipment; the current operation parameters comprise the current milling force and the current vibration frequency; the basic parameters comprise machine tool parameters, tool parameters and clamp parameters;
a digital twinning model establishing module 602, configured to establish a digital twinning model of the thin-walled workpiece in the milling process according to the basic parameters and the current operating parameters;
the machining deformation prediction value determining module 603 is configured to input the current operating parameter into the machining deformation prediction model to obtain a machining deformation prediction value of the thin-walled workpiece; the machining deformation prediction model is obtained by training a convolution neural network by utilizing historical operating parameters of the thin-wall part in the milling process and the historical machining deformation of the thin-wall part;
the machining parameter updating module 604 is used for updating the machining parameters of the thin-wall part in the milling machining process according to the machining deformation prediction value and the digital twin model; the machining parameters comprise the feed multiplying power of the thin-wall part and the rotating speed of the cutter.
The invention provides a control system for milling thin-walled parts, which further comprises:
the second data acquisition module is used for acquiring historical operating parameters of the thin-wall part in the milling process and historical machining deformation of the thin-wall part; the historical operating parameters comprise a plurality of groups of historical milling forces and historical vibration frequencies under the same thickness;
and the machining deformation prediction model determining module is used for taking the historical operating parameters as input and the historical machining deformation as output to obtain a trained convolutional neural network as a machining deformation prediction model.
The processing parameter updating module 604 specifically includes:
the third data acquisition unit is used for acquiring the current processing parameters of the thin-walled workpiece in the milling process and stopping milling the thin-walled workpiece;
the simulation machining parameter determining unit is used for taking the current machining parameters as simulation machining parameters of the digital twin model;
the simulation operation parameter determining unit is used for inputting the simulation machining parameters into the digital twin model to obtain the simulation operation parameters of the thin-wall part in the milling machining process;
the machining deformation simulation value determining unit is used for inputting simulation operation parameters of the milling process of the thin-wall part into the machining deformation prediction model to obtain a machining deformation simulation value;
and when the machining deformation simulation value is greater than or equal to the machining deformation threshold value, updating the simulation machining parameters and calling the simulation operation parameter determination unit until the machining deformation simulation value is less than the machining deformation threshold value, taking the updated simulation machining parameters as the current machining parameters, and continuing to mill the thin-walled workpiece.
The processing parameter updating module 604 further includes:
the first judgment unit is used for judging whether the predicted value of the machining deformation is larger than the threshold value of the machining deformation or not to obtain a first judgment result; if the first judgment result is negative, calling a machining deformation predicted value display unit; if the first judgment result is yes, calling a third data acquisition unit;
and the machining deformation predicted value display unit is used for displaying the machining deformation predicted value at the digital twin model.
Compared with the prior art, the invention has the following remarkable advantages: (1) the virtual simulation of the thin-wall part machining process through the twin model can reflect the state of the thin-wall part in the machining process in real time, accurately predict and control the machining quality of the thin-wall part, improve the milling efficiency and reduce the cost; (2) when the machining conditions in the physical space change, in the digital twin model, the machining strategies of different thin-wall parts can be automatically compared, and the optimal machining strategy is returned to the physical space, so that the machining state of a machine tool in the physical space is controlled; (3) the convolution neural network algorithm is combined with the digital twinning technology, the state of the whole thin-wall part machining process is simulated and monitored in real time, machining parameters and processes are verified virtually in advance, defects are found out according to data in the thin-wall part machining process, the machining process is optimized, the existing deformation can be compensated, and the deformation in the machining process can be reduced; and (4) iteratively upgrading the twin data, the historical data of the machining process and the digital twin.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. For the system disclosed by the embodiment, the description is relatively simple because the system corresponds to the method disclosed by the embodiment, and the relevant points can be referred to the method part for description.
The principles and embodiments of the present invention have been described herein using specific examples, which are provided only to help understand the method and the core concept of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In view of the above, the present disclosure should not be construed as limiting the invention.
Claims (8)
1. A method of controlling milling of a thin walled member, the method comprising:
acquiring current operating parameters of a thin-wall part milling process and basic parameters of thin-wall part milling equipment; the current operating parameters comprise a current milling force and a current vibration frequency; the basic parameters comprise machine tool parameters, tool parameters and clamp parameters;
establishing a digital twin model of the milling process of the thin-wall part according to the basic parameters and the current operating parameters;
inputting the current operation parameters into a machining deformation prediction model to obtain a machining deformation prediction value of the thin-walled workpiece; the machining deformation prediction model is obtained by training a convolution neural network by utilizing historical operating parameters of a thin-wall part in a milling process and historical machining deformation of the thin-wall part;
updating the machining parameters of the thin-wall part in the milling machining process according to the predicted machining deformation value and the digital twin model; the machining parameters comprise the feed multiplying power of the thin-wall part and the rotating speed of the cutter.
2. The control method for milling the thin-wall part according to claim 1, wherein before the obtaining of the current operating parameters of the milling process of the thin-wall part and the basic parameters of the milling equipment of the thin-wall part, the method further comprises:
acquiring historical operating parameters of a thin-wall part in a milling process and historical machining deformation of the thin-wall part; the historical operating parameters comprise a plurality of groups of historical milling forces and historical vibration frequencies under the same thickness;
and taking the historical operating parameters as input and the historical machining deformation as output to obtain a trained convolutional neural network as the machining deformation prediction model.
3. The method for controlling the milling of the thin-walled part according to claim 1, wherein the updating of the processing parameters of the milling process of the thin-walled part specifically comprises:
acquiring current machining parameters of a thin-wall part in a milling process, and stopping milling the thin-wall part;
taking the current machining parameters as simulated machining parameters of the digital twin model;
inputting the simulated machining parameters into the digital twin model to obtain simulated operation parameters of the milling process of the thin-wall part;
inputting simulation operation parameters of the milling process of the thin-wall part into the machining deformation prediction model to obtain a machining deformation simulation value;
and when the machining deformation simulation value is greater than or equal to the machining deformation threshold value, updating the simulation machining parameters and executing the step of inputting the simulation machining parameters into the digital twin model to obtain simulation operation parameters of the milling process of the thin-wall part until the machining deformation simulation value is less than the machining deformation threshold value, taking the updated simulation machining parameters as current machining parameters, and continuing milling the thin-wall part.
4. The method for controlling the milling of a thin-walled part according to claim 3, wherein before the updating of the machining parameters of the milling process of the thin-walled part, the method further comprises:
judging whether the predicted value of the machining deformation is larger than a machining deformation threshold value or not to obtain a first judgment result;
if the first judgment result is negative, displaying the predicted value of the machining deformation amount at the digital twin model;
and if the first judgment result is yes, executing the step of updating the machining parameters of the thin-wall part milling process.
5. A control system for milling a thin walled part, the system comprising:
the first data acquisition module is used for acquiring the current operating parameters of the thin-wall part milling process and the basic parameters of the thin-wall part milling equipment; the current operating parameters comprise a current milling force and a current vibration frequency; the basic parameters comprise machine tool parameters, tool parameters and clamp parameters;
the digital twin model establishing module is used for establishing a digital twin model of the milling process of the thin-wall part according to the basic parameters and the current operating parameters;
the machining deformation predicted value determining module is used for inputting the current operation parameters into a machining deformation prediction model to obtain a machining deformation predicted value of the thin-wall part; the machining deformation prediction model is obtained by training a convolution neural network by utilizing historical operating parameters of a thin-wall part in a milling process and historical machining deformation of the thin-wall part;
the machining parameter updating module is used for updating the machining parameters of the thin-wall part in the milling machining process according to the machining deformation prediction value and the digital twin model; the machining parameters comprise the feed multiplying power of the thin-wall part and the rotating speed of the cutter.
6. The control system for milling a thin wall part according to claim 5, further comprising:
the second data acquisition module is used for acquiring historical operating parameters of the thin-wall part in the milling process and historical machining deformation of the thin-wall part; the historical operating parameters comprise a plurality of groups of historical milling forces and historical vibration frequencies under the same thickness;
and the machining deformation prediction model determining module is used for taking the historical operating parameters as input and the historical machining deformation as output to obtain a trained convolutional neural network as the machining deformation prediction model.
7. The control system for milling a thin-walled part according to claim 5, wherein the processing parameter updating module specifically comprises:
the third data acquisition unit is used for acquiring the current processing parameters of the thin-wall part in the milling process and stopping milling the thin-wall part;
the simulation machining parameter determining unit is used for taking the current machining parameters as simulation machining parameters of the digital twin model;
the simulation operation parameter determining unit is used for inputting the simulation machining parameters into the digital twin model to obtain simulation operation parameters of the milling machining process of the thin-wall part;
the machining deformation simulation value determining unit is used for inputting simulation operation parameters of the milling process of the thin-wall part into the machining deformation prediction model to obtain a machining deformation simulation value;
and when the machining deformation simulation value is greater than or equal to the machining deformation threshold value, updating the simulation machining parameters and calling the simulation operation parameter determination unit until the machining deformation simulation value is less than the machining deformation threshold value, taking the updated simulation machining parameters as current machining parameters, and continuing to mill the thin-walled workpiece.
8. The control system for milling a thin walled part according to claim 7, wherein the processing parameter update module further comprises:
the first judgment unit is used for judging whether the predicted value of the machining deformation is larger than a threshold value of the machining deformation or not to obtain a first judgment result; if the first judgment result is negative, calling a machining deformation predicted value display unit; if the first judgment result is yes, calling a third data acquisition unit;
and the machining deformation predicted value display unit is used for displaying the machining deformation predicted value at the digital twin model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110789254.6A CN113534741A (en) | 2021-07-13 | 2021-07-13 | Control method and system for milling thin-walled workpiece |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110789254.6A CN113534741A (en) | 2021-07-13 | 2021-07-13 | Control method and system for milling thin-walled workpiece |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113534741A true CN113534741A (en) | 2021-10-22 |
Family
ID=78127616
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110789254.6A Pending CN113534741A (en) | 2021-07-13 | 2021-07-13 | Control method and system for milling thin-walled workpiece |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113534741A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114326580A (en) * | 2021-12-15 | 2022-04-12 | 国营芜湖机械厂 | Thin-wall part machining method and device based on workbench information monitoring |
| CN114311826A (en) * | 2022-03-15 | 2022-04-12 | 河北工业大学 | Fiber metal laminate hydroforming system based on digital twinning technology |
| CN114547759A (en) * | 2022-04-21 | 2022-05-27 | 中铁四局集团第三建设有限公司 | Creeping formwork construction monitoring method, creeping formwork construction monitoring system and computer readable storage medium |
| TWI808695B (en) * | 2022-03-24 | 2023-07-11 | 國立中正大學 | Milling real-time monitoring system |
| CN117161454A (en) * | 2023-11-03 | 2023-12-05 | 张家港Aaa精密制造股份有限公司 | Digital twinning-based bearing milling monitoring method and system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106338965A (en) * | 2016-10-25 | 2017-01-18 | 哈尔滨理工大学 | Error compensation based corner processing precision control method |
| CN109615113A (en) * | 2018-11-19 | 2019-04-12 | 江苏科技大学 | A kind of marine diesel important Parts processing quality prediction technique twin based on number |
| CN111964575A (en) * | 2020-07-06 | 2020-11-20 | 北京卫星制造厂有限公司 | Digital twin modeling method for milling of mobile robot |
| US20210157312A1 (en) * | 2016-05-09 | 2021-05-27 | Strong Force Iot Portfolio 2016, Llc | Intelligent vibration digital twin systems and methods for industrial environments |
-
2021
- 2021-07-13 CN CN202110789254.6A patent/CN113534741A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20210157312A1 (en) * | 2016-05-09 | 2021-05-27 | Strong Force Iot Portfolio 2016, Llc | Intelligent vibration digital twin systems and methods for industrial environments |
| CN106338965A (en) * | 2016-10-25 | 2017-01-18 | 哈尔滨理工大学 | Error compensation based corner processing precision control method |
| CN109615113A (en) * | 2018-11-19 | 2019-04-12 | 江苏科技大学 | A kind of marine diesel important Parts processing quality prediction technique twin based on number |
| CN111964575A (en) * | 2020-07-06 | 2020-11-20 | 北京卫星制造厂有限公司 | Digital twin modeling method for milling of mobile robot |
Non-Patent Citations (3)
| Title |
|---|
| CAIXU YUE ET AL: "Modeling machining errors for thin-walled parts according", 《THE INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY》 * |
| 岳彩旭等: "薄壁件铣削过程加工变形研究进展", 《航空学报》 * |
| 陈聪: "基于数字孪生的船用柴油机活塞加工质量管控方法研究", 《中国优秀硕士学位论文全文数据库工程科技II辑》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114326580A (en) * | 2021-12-15 | 2022-04-12 | 国营芜湖机械厂 | Thin-wall part machining method and device based on workbench information monitoring |
| CN114326580B (en) * | 2021-12-15 | 2023-11-14 | 国营芜湖机械厂 | Thin-wall part machining method and device based on workbench information monitoring |
| CN114311826A (en) * | 2022-03-15 | 2022-04-12 | 河北工业大学 | Fiber metal laminate hydroforming system based on digital twinning technology |
| TWI808695B (en) * | 2022-03-24 | 2023-07-11 | 國立中正大學 | Milling real-time monitoring system |
| CN114547759A (en) * | 2022-04-21 | 2022-05-27 | 中铁四局集团第三建设有限公司 | Creeping formwork construction monitoring method, creeping formwork construction monitoring system and computer readable storage medium |
| CN114547759B (en) * | 2022-04-21 | 2022-09-23 | 中铁四局集团第三建设有限公司 | Creeping formwork construction monitoring method, creeping formwork construction monitoring system and computer readable storage medium |
| CN117161454A (en) * | 2023-11-03 | 2023-12-05 | 张家港Aaa精密制造股份有限公司 | Digital twinning-based bearing milling monitoring method and system |
| CN117161454B (en) * | 2023-11-03 | 2024-02-13 | 张家港Aaa精密制造股份有限公司 | Digital twinning-based bearing milling monitoring method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113534741A (en) | Control method and system for milling thin-walled workpiece | |
| CN110900307B (en) | Numerical control machine tool cutter monitoring system driven by digital twin | |
| CN114237155B (en) | Error prediction and compensation method, system and medium for multi-axis numerical control machining | |
| CN109615113A (en) | A kind of marine diesel important Parts processing quality prediction technique twin based on number | |
| US10520919B2 (en) | Systems and methods for receiving sensor data for an operating additive manufacturing machine and mapping the sensor data with process data which controls the operation of the machine | |
| CN112147950B (en) | Numerical control side milling system and accurate synchronization method of threshold value and signal to be monitored thereof | |
| CN114297912B (en) | Cutter abrasion prediction method based on deep learning | |
| CN114758064A (en) | Method for optimizing machine tool cutting process parameters based on digital twinning | |
| CN113496064A (en) | Compensation adjustment method for straightness of numerical control machine tool | |
| CN113569453B (en) | Migration method of digital twin product model oriented to processing | |
| CN117523146A (en) | System and method for quickly constructing digital twin scene based on target detection | |
| CN116915122A (en) | Self-adaptive control method and system for coal mine frequency conversion equipment | |
| CN116720442A (en) | Wear prediction method based on improved Fourier neural operator | |
| CN114800049B (en) | Grating ruler processing operation signal error compensation system | |
| Hallmann et al. | A method for analyzing the influence of process and design parameters on the build time of additively manufactured components | |
| CN113673166B (en) | Digital twin model working condition self-adaption method and system for processing quality prediction | |
| CN116929729A (en) | Workpiece measuring method and device and related equipment | |
| CN115344951A (en) | Cutter wear amount prediction method based on time convolution network and auxiliary learning | |
| CN112612782A (en) | MES system data online filling method and system based on LSTM network | |
| CN118192479B (en) | Factory workshop digital twin model correction method and system based on data acquisition | |
| CN118171475B (en) | Copper pipe internal thread expansion and contraction rate control method and system | |
| CN111723446B (en) | Finite element simulation method for milling process of aluminum alloy thin-wall part | |
| US11511380B2 (en) | Method for capturing tool path and device thereof | |
| CN115616978B (en) | SQ-LSTMA-based thermal error prediction model, prediction method and control system | |
| CN118180459A (en) | Thin-wall part deformation prediction method based on digital twinning |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20211022 |