CN119644917A

CN119644917A - Machine tool self-adaptive control system based on digital twin and implementation method thereof

Info

Publication number: CN119644917A
Application number: CN202411832423.XA
Authority: CN
Inventors: 聂晓根; 黄谦; 张钧哲; 任玲玉; 陈宏基
Original assignee: Fuzhou University
Current assignee: Fuzhou University
Priority date: 2024-12-12
Filing date: 2024-12-12
Publication date: 2025-03-18

Abstract

The invention relates to a machine tool self-adaptive control system based on digital twin and a realization method thereof, the machine tool self-adaptive control system comprises a numerical control machine tool, a data acquisition system, a digital twin model, a main shaft load self-adaptive control module and a man-machine interaction system, by constructing a digital twin model and a main shaft load self-adaptive control module of the numerical control machine tool, real-time monitoring and self-adaptive regulation and control of the machining process are realized. The machine tool self-adaptive control system and the implementation method thereof can realize the self-adaptive control of the numerical control machine tool, thereby improving the machining precision, efficiency and stability of the numerical control machine tool.

Description

Machine tool self-adaptive control system based on digital twin and implementation method thereof

Technical Field

The invention relates to the technical field of intelligent manufacturing, in particular to a machine tool self-adaptive control system based on digital twinning and an implementation method thereof.

Background

With the rapid development of smart manufacturing technology, digital twin (DIGITAL TWIN) technology is increasingly used in manufacturing. The digital twin technology synchronizes and monitors the state, behavior and performance of the physical machine tool in real time by creating a virtual model of the physical machine tool so as to realize accurate management and control of the production process. Currently, the application of the digital twin technology in the field of machine tools is mainly focused on the aspects of machine tool state monitoring, fault diagnosis, production optimization and the like. However, the prior art still has some problems, which limit its further application in the adaptive control of machine tools.

(1) Lack of unified standards and specifications

At present, the application of the digital twin technology in the field of machine tools does not form unified standards and specifications, and different research and application cases have obvious differences in the aspects of data acquisition, model construction, interaction modes and the like, so that the interoperability and expansibility of the system are poor. Meanwhile, the development of the digital twin model is often customized, and the digital twin model lacks versatility, so that the digital twin model is limited to be popularized and applied in different types of machine tools and processing technologies.

(2) Model accuracy and real-time are difficult to balance

The model of the existing digital twin technology usually adopts a refined physical model or a complex data driving model, can provide higher precision, but has large calculation amount and is difficult to meet the real-time requirement. Therefore, the dynamic change of the machine tool in the machining process cannot be effectively processed, so that the prediction and optimization result of the digital twin model is delayed from the actual machining state, and the real-time self-adaptive control of the machining process is difficult to realize.

(3) Insufficient adaptive control capability

The existing digital twin technology is mainly focused on machine tool state monitoring and production optimization, and the self-adaptive control capability is insufficient. When sudden conditions (such as workpiece material change, cutter abrasion and the like) occur in the machining process, the existing digital twin system cannot be adjusted in time, so that the machining precision and efficiency of the machine tool are affected. This is mainly because the existing digital twin system lacks a feedback-based closed-loop control mechanism, and cannot realize real-time adaptive regulation and control in virtual-real interaction.

(4) Multi-source heterogeneity of data and models is difficult to fuse

The data involved in the machining process of a machine tool is of a wide variety (e.g., vibration signals, temperature signals, force signals, etc.) and comes from different sensor devices, and often has heterogeneity and complexity. How to effectively fuse multi-source heterogeneous data and make full use of the multi-source heterogeneous data in a digital twin model is still a difficulty of the prior art. Meanwhile, when the data and the physical model are combined, the problems of low model updating speed, poor generalization capability of the data driving model and the like exist in the prior art, and the actual situation of the processing process cannot be accurately reflected.

Disclosure of Invention

The invention aims to provide a machine tool self-adaptive control system based on digital twinning and an implementation method thereof, which can realize self-adaptive control of a numerical control machine tool, thereby improving the machining precision, efficiency and stability of the numerical control machine tool.

In order to achieve the aim, the technical scheme adopted by the invention is that the machine tool self-adaptive control system based on digital twinning comprises a numerical control machine tool, a data acquisition system, a digital twinning model, a main shaft load self-adaptive control module and a man-machine interaction system, and real-time monitoring and self-adaptive regulation and control of a machining process are achieved by constructing the digital twinning model and the main shaft load self-adaptive control module of the numerical control machine tool.

Further, the numerical control machine tool is a controlled object, the basic structure of the numerical control machine tool comprises a main shaft, a cutter, a workpiece and a machine tool body, and the main shaft load and the processing parameter data are all derived from the numerical control machine tool and are collected in real time through a data collection system;

The data acquisition system comprises a plurality of sensors, a data processing unit, a database and a data transmission unit, wherein the sensors, the data processing unit, the database and the data transmission unit are used for acquiring real-time data of the numerical control machine tool, the acquired data are stored in the database, and the digital twin model realizes communication by reading the data of the database;

The digital twin model consists of a physical model and a data driving model; the data driving model is based on the collected multi-source data, establishes the mapping relation between the spindle load and the processing parameters by adopting a support vector machine algorithm, combines the two models of the physical model and the data driving model to form a digital twin model updated in real time, and realizes the monitoring and simulation of the processing process;

when the main shaft load is detected to exceed a set threshold or abnormal fluctuation occurs, the main shaft load self-adaptive control module carries out self-adaptive adjustment on processing parameters through a feedback mechanism so as to ensure the stability and the processing quality of the processing process;

The man-machine interaction system comprises a visual monitoring interface and a simulation panel, so that the real-time state of the machine tool, the cutting force prediction result of the machining process and the self-adaptive control adjustment process are checked through the visual monitoring interface.

Further, each sensor of the data acquisition system is respectively arranged at different positions on the numerical control machine tool to acquire main shaft current voltage, temperature change and related operation data in the machining process of the machine tool, the acquired real-time data are sent to the data processing unit, and the data acquisition equipment uploads the acquired data to the database;

The digital twin model is in data communication with a database through a data transmission unit to acquire the operation data of the machine tool in real time, and maps the machining process in real time by utilizing a physical model and a data driving model;

When abnormal fluctuation of the spindle load occurs or exceeds a set threshold value, the spindle load self-adaptive control module adopts a fuzzy self-adaptive control algorithm according to feedback information of the digital twin model to carry out self-adaptive adjustment on the feeding speed of the machine tool;

The man-machine interaction system performs multi-directional three-dimensional visual display on the machine tool through a visual monitoring interface, and realizes remote monitoring on the running state of the machine tool by utilizing the Unity WebGL technology.

The invention also provides a realization method of the machine tool self-adaptive control system based on digital twin, which comprises the following steps:

S1, constructing a geometric model of a numerical control machine based on geometric features of the numerical control machine and constraint relations of all components;

S2, acquiring data of a machine tool spindle during cutting, preprocessing the acquired data and constructing a proxy model;

step S3, constructing a data acquisition system of machine tool running state, current voltage and temperature data;

S4, establishing a digital twin model of the main shaft, the cutter and the workpiece;

Step S5, a main shaft load self-adaptive control module is established, and the feeding speed of the machine tool is adjusted in real time according to real-time data of the machine tool and the digital twin model;

And S6, building a man-machine interaction system.

Further, the implementation method of the step S1 is as follows:

Firstly, acquiring geometric data of key parts and workpieces of a machine tool by utilizing a three-dimensional scanning technology or a CAD model importing mode, and ensuring that the geometric precision of a model is consistent with that of an actual machine tool;

secondly, three-dimensional modeling software is used for establishing a three-dimensional geometric model of the machine tool and the workpiece, wherein the model comprises various components of the machine tool and can represent the contact point of the tool and the workpiece, the position of a main shaft and the position of the workpiece;

And finally, converting the three-dimensional geometric model into an STP format, importing the STP format into three-dimensional rendering software, lightening the three-dimensional geometric model, setting materials for each part of the three-dimensional geometric model, performing appearance rendering, setting father-son relations of each part according to the motion form of a machine tool, and exporting the father-son relations into an FBX format.

Further, the implementation method of step S2 is as follows:

the method comprises the steps of obtaining cutting force of a spindle at different cutting depths, feeding speeds and spindle rotating speeds by carrying out dynamic simulation on the cutting process of the spindle or collecting machine tool operation data, dividing the obtained data into training data and verification data, and carrying out normalization processing on the data in order to reduce influence caused by different dimension and accelerate the training speed:

Then, a proxy model is constructed by using a support vector machine model taking RBF as a kernel function, the proxy model is trained by normalizing the processed data, the super-parameters of the SVM are optimized by using a K-means optimization algorithm (KO), and the proxy model for cutting force prediction is obtained after training is completed.

Further, the implementation method of step S3 is as follows:

Firstly, selecting a corresponding sensor and a development method according to the specific condition of a data machine tool and signals to be acquired;

Secondly, installing the sensor at a key position of a machine tool according to the working principle of the sensor and the data acquisition requirement, and after the installation is finished, debugging the sensitivity, response speed and sampling frequency of the sensor to ensure the accuracy and instantaneity of data acquisition;

and the data processing unit carries out filtering, denoising and feature extraction on the acquired data, and uploads the processed data to a database, wherein the database realizes communication with a digital twin model through the data transmission unit.

Further, the implementation method of step S4 is as follows:

Importing the FBX file of the geometric model of the numerical control machine tool generated in the step S1 into Unity3D software, developing scripts of the machine tool x, y, z axis linear motion and tool rotary motion based on DOTween animation plug-ins, optimizing the tool workpiece cutting effect through a dynamic mesh modification technology, adding a mesh collision device to parts of the machine tool, wherein the collision detection mode is continuous detection, simultaneously reading database data in real time, driving the motion of a digital twin model so as to realize the real-time mapping of the digital twin model to the physical machine tool, and reserving a development editing interface by the scripts so as to facilitate the popularization and secondary development of the scripts;

And secondly, analyzing codes operated by the machine tool through the script, converting commands in the G codes into Unity coordinates, acquiring feed speed, spindle rotating speed and cutting depth data of the machine tool, and simulating the machining process of the machine tool and predicting the cutting force of the spindle in real time by utilizing the agent model obtained by training in the step S2, so that a basis is provided for optimizing the machining process of the machine tool.

Further, the implementation method of step S5 is as follows:

The Fuzzy control method comprises the steps of adopting a two-dimensional Fuzzy controller to realize a Fuzzy self-adaptive processing control algorithm, constructing the Fuzzy controller in a Fuzzy tool box of MATLAB, wherein Fuzzy sets of Ep, cp and Deltau are (NB, NM, NS,0,PS,PM,PB), the Fuzzy subset range is (-3, -2, -1,0,1,2,3), membership functions are triangle functions and trapezoid functions, setting a Fuzzy rule table, carrying out Fuzzy reasoning by using a Mamdani method, carrying out anti-Fuzzy operation by using a gravity center method, comparing predicted cutting moment with target moment, and obtaining data of how much feeding speed can reach the target moment after changing through the Fuzzy controller, thereby realizing the stability and high efficiency of a processing process.

Further, the implementation method of step S6 is as follows:

And a man-machine interaction system is built by using a UI tool and XCharts plug-ins in the Unity3D software, so that three-dimensional visualization and real-time display of operation data of a machining process are realized, and meanwhile, remote monitoring is realized based on the Unity WebGL technology.

Compared with the prior art, the invention has the following beneficial effects:

(1) Stability and precision of the processing process are improved

According to the invention, by introducing a main shaft load self-adaptive control technology, the main shaft load can be monitored in real time, and the feeding speed can be dynamically adjusted according to the change of the load. When the load of the main shaft fluctuates or changes abnormally, the system can respond quickly, the processing parameters are adjusted to the optimal values, and the stability of the load of the main shaft is maintained, so that the processing errors and the surface defects of the workpiece caused by the fluctuation of the load are effectively reduced, and the stability and the accuracy of the processing process are improved.

(2) The response speed and the robustness of the system are improved

By introducing fuzzy self-adaptive control, the invention can rapidly respond to the abrupt change of the spindle load in the processing process, dynamically adjust the processing parameters, and ensure that the system has stronger robustness. In addition, by combining the real-time feedback of the agent model and the actual processing data, the system can quickly correct the prediction error and ensure that the processing process is always in an optimal state.

(3) Improves the processing efficiency and the equipment utilization rate

According to the invention, the processing parameters can be adaptively adjusted according to the real-time conditions of the processing state and the spindle load, the feeding speed parameter is optimized, and the machine tool halt, cutter abrasion or workpiece damage caused by improper setting of the processing parameters are avoided, so that the overall processing efficiency and the equipment utilization rate of the machine tool are improved, the service lives of the equipment and the cutter are prolonged, and the maintenance cost is reduced.

(4) Good human-computer interaction experience and intelligent level

The visual interface and the man-machine interaction system are provided by the invention, an operator can check the running state of the machine tool through the interface, remote monitoring can be realized, and the intelligent and flexible functions are high.

Drawings

FIG. 1 is a block diagram of a digital twinning-based adaptive control system for a machine tool according to an embodiment of the present invention;

FIG. 2 is a functional block diagram of an implementation of a digital twinning-based machine tool adaptive control system according to an embodiment of the present invention;

FIG. 3 is a flow chart of an implementation method of a digital twin-based machine tool adaptive control system according to an embodiment of the present invention;

FIG. 4 is a three-dimensional model diagram of a machine tool in an embodiment of the invention;

FIG. 5 is a diagram of a three-dimensional rendering model of a machine tool in an embodiment of the invention;

FIG. 6 is a flow chart of proxy model construction in an embodiment of the invention;

FIG. 7 is a block diagram of a data acquisition system in accordance with an embodiment of the present invention;

FIG. 8 is a diagram of an interactive interface of a data acquisition system in an embodiment of the invention;

FIG. 9 is a schematic diagram of an implementation of a fuzzy adaptive control algorithm in an embodiment of the present invention;

fig. 10 is a diagram of a visual monitoring interface of a man-machine interaction system in an embodiment of the invention.

Detailed Description

The invention will be further described with reference to the accompanying drawings and examples.

It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the application. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the present application. As used herein, the singular is also intended to include the plural unless the context clearly indicates otherwise, and furthermore, it is to be understood that the terms "comprises" and/or "comprising" when used in this specification are taken to specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof.

As shown in fig. 1, the embodiment provides a machine tool self-adaptive control system based on digital twin, which comprises a numerical control machine tool, a data acquisition system, a digital twin model, a spindle load self-adaptive control module and a man-machine interaction system, wherein the real-time monitoring and self-adaptive regulation and control of a machining process are realized by constructing the digital twin model and the spindle load self-adaptive control module of the numerical control machine tool.

(1) Numerical control machine tool

The numerical control machine tool is a controlled object and comprises a main shaft, a cutter, a workpiece, a machine tool body and other basic structures. The data of the spindle load change, the processing parameters and the like are all derived from the numerical control machine tool and are acquired in real time through a data acquisition system.

(2) Data acquisition system

The data acquisition system comprises a plurality of sensors of various types, such as a current sensor, a voltage sensor and the like, and a data processing unit, a database and a data transmission unit, and is used for acquiring real-time data (such as spindle load, temperature change and the like) of the numerical control machine tool. The acquired data are stored in a database, and the digital twin model realizes communication by reading the data of the database.

(3) Digital twin model

The digital twin model consists of a physical model and a data driven model. The physical model combines the machine tool structure and the dynamics characteristic to reflect the physical behavior of the machine tool in the machining process. The data driving model establishes the mapping relation between the spindle load and the processing parameters by adopting a support vector machine algorithm based on the collected multi-source data. Combining the two models of the physical model and the data driving model to form a digital twin model updated in real time, and realizing the monitoring and simulation of the processing process.

(4) Main shaft load self-adaptive control module

The main shaft load self-adaptive control module is used for adjusting the feeding speed of the machine tool by monitoring the main shaft load and the processing state in real time and adopting a fuzzy self-adaptive control algorithm. When the spindle load is detected to exceed a set threshold or abnormal fluctuation occurs, the spindle load self-adaptive control module carries out self-adaptive adjustment on processing parameters through a feedback mechanism so as to ensure the stability and the processing quality of the processing process.

(5) Man-machine interaction system

The man-machine interaction system comprises a visual monitoring interface and a simulation panel, and an operator can check the real-time state of the machine tool and the cutting force prediction result of the machining process through the visual monitoring interface and the self-adaptively controlled adjustment process.

As shown in fig. 2, the implementation principle of the machine tool adaptive control system in this embodiment is as follows:

each sensor of the data acquisition system is respectively arranged at different positions on the numerical control machine tool so as to acquire main shaft current voltage, temperature change and related operation data in the machining process of the machine tool, and transmit the acquired real-time data to the data processing unit, and the data acquisition equipment uploads the acquired data to the database.

The digital twin model is in data communication with the database through the data transmission unit to acquire the operation data of the machine tool in real time, and maps the machining process in real time by utilizing the physical model and the data driving model, and sends the real-time data and the prediction result of the cutting force to the spindle load self-adaptive control module.

When the main shaft load abnormally fluctuates or exceeds a set threshold value, the main shaft load self-adaptive control module adopts a fuzzy self-adaptive control algorithm to carry out self-adaptive adjustment on the feeding speed of the machine tool according to the feedback information of the digital twin model, and dynamically adjusts the processing parameters of the numerical control machine tool, including the feeding speed, the main shaft rotating speed and the cutting depth, according to the digital twin model and the feedback information of the real-time acquisition data, and the adjusted processing parameters act on the machine tool through an executing mechanism to realize the self-adaptive control of the processing process.

As shown in fig. 3, the embodiment also provides a method for implementing the machine tool adaptive control system based on digital twin, which includes the following steps:

Step S1, constructing a geometric model of the numerical control machine based on geometric features of the numerical control machine and constraint relations of all components.

In this embodiment, the implementation method of step S1 is as follows:

Firstly, the geometric data of key parts (such as a main shaft, a cutter, a workbench and the like) of a machine tool and a workpiece are acquired by utilizing a three-dimensional scanning technology or a CAD model importing mode, so that the geometric precision of a model is ensured to be consistent with that of an actual machine tool.

Next, three-dimensional modeling software (e.g., solidWorks, UG, etc.) is used to build a three-dimensional geometric model of the machine tool and workpiece, as shown in FIG. 4. The model comprises various components of the machine tool, and can represent key points such as contact points of a tool and a workpiece, positions of a main shaft, positions of the workpiece and the like.

Finally, the three-dimensional geometric model is converted into STP format and is imported into three-dimensional rendering software (such as Blender, 3DMax and the like), as shown in FIG. 5, the three-dimensional geometric model is lightened, materials are arranged for each part of the three-dimensional geometric model, appearance rendering is carried out, meanwhile, father-son relations of each part are arranged according to the motion form of a machine tool, and the three-dimensional geometric model is exported into the FBX format.

And S2, acquiring data of a machine tool spindle during cutting, preprocessing the acquired data and constructing a proxy model.

In this embodiment, the implementation method of step S2 is as follows:

A proxy model building flow chart is shown in fig. 6. The method comprises the steps of obtaining cutting force of a spindle at different cutting depths, feeding speeds and spindle rotating speeds by carrying out dynamic simulation (such as Ansys, form and other software) on the cutting process of the spindle or collecting machine tool operation data, dividing the obtained data into training data and verification data, and carrying out normalization processing on the data in order to reduce influence caused by different dimensions and accelerate the training speed:

And step S3, constructing a data acquisition system of machine tool running state, current voltage and temperature data.

In this embodiment, the implementation method of step S3 is as follows:

Firstly, selecting corresponding sensors and development methods according to specific conditions of a data machine tool and signals to be acquired.

And secondly, installing the sensor at a key position (such as a main shaft, a feed shaft and the like) of the machine tool according to the working principle of the sensor and the data acquisition requirement, and after the installation is finished, debugging the sensitivity, the response speed and the sampling frequency of the sensor to ensure the accuracy and the instantaneity of data acquisition.

And the data processing unit filters, denoises and extracts features of the acquired data, and uploads the processed data to a database (such as MySQL, SQL SERVER and the like), wherein the database realizes communication with a digital twin model through the data transmission unit.

In this embodiment, for the Series Oi-MF numerical control system of FANUC, the architecture of the data acquisition system is shown in fig. 7, and the development steps are as follows:

The second development was first performed by Focas development kit offered by FANUC corporation. Communication with the machine tool is established by using the cnc allclibhndl3 function, and then the running data of the feed speed, the spindle rotation speed, the running program and the like of the machine tool are obtained by using the cnc acts, cnc actf, pmc_rdpmcrng, cnc_ rdspmeter and the like.

And secondly, acquiring various sensor data by utilizing an OPC UA server so as to realize unified acquisition of sensor data of different brands and types.

Finally, the collected machine tool data and sensor data are stored in a MySQL database, and an interactive interface of a data collection system is developed in a VS2022, as shown in fig. 8, so that unified management and query of the data are realized.

And S4, establishing a digital twin model of the spindle, the cutter and the workpiece.

In this embodiment, the implementation method of step S4 is as follows:

Importing the FBX file of the geometric model of the numerical control machine tool generated in the step S1 into Unity3D software, developing scripts of the linear motion of the x, y and z axes and the rotary motion of the tool based on DOTween animation plug-ins, optimizing the workpiece cutting effect of the tool through a dynamic mesh grid modification technology, and adding a grid collision device to the tool, the workpiece and other parts of the twin machine tool, wherein the collision detection mode is continuous detection. And simultaneously, the database data is read in real time, and the motion of the digital twin model is driven, so that the real-time mapping of the digital twin model to the physical machine tool is realized. And the script reserves a development editing interface so as to facilitate popularization and secondary development of the script.

And secondly, analyzing a code operated by the machine tool by writing a script, converting a command in the G code into a Unity coordinate, acquiring data such as the feeding speed, the spindle rotating speed, the cutting depth and the like of the machine tool, and utilizing the agent model obtained by training in the step S2, so that the machining process of the machine tool can be simulated, the cutting force of the spindle can be predicted in real time, and a basis is provided for optimizing the machining process of the machine tool.

And S5, establishing a main shaft load self-adaptive control module, and adjusting the feeding speed of the machine tool in real time according to the real-time data and the digital twin model of the machine tool.

And setting a target value and a threshold range of the spindle load according to the prediction result of the digital twin model and the spindle load data acquired in real time. When the spindle load deviates from the target value or exceeds the threshold range, an adaptive control strategy is triggered.

And selecting a proper self-adaptive control algorithm (such as fuzzy self-adaptive control or PID control), dynamically adjusting machining parameters such as feed speed, cutting depth, spindle rotating speed and the like according to load change, and ensuring that the spindle load is in a stable range.

In this embodiment, the implementation method of step S5 is as follows:

The Fuzzy self-adaptive machining control algorithm shown in fig. 9 is realized by adopting a two-dimensional Fuzzy controller, the Fuzzy controller is constructed in a Fuzzy tool box of MATLAB, wherein Fuzzy sets of Ep, cp and Deltau are (NB, NM, NS,0,PS,PM,PB), the range of Fuzzy subsets is (-3, -2, -1,0,1,2,3), membership functions are triangle functions and trapezoid functions, after a Fuzzy rule table is set, fuzzy reasoning is carried out by using a Mamdani method, inverse Fuzzy operation is carried out by using a gravity center method, the predicted cutting moment is compared with the target moment, and data of how much feed speed can reach the target moment is changed after the Fuzzy controller is obtained, so that the stability and the high efficiency of the machining process are realized.

And S6, building a man-machine interaction system.

In this embodiment, the implementation method of step S6 is as follows:

And a human-computer interaction system is built by using a UI tool and XCharts plug-ins in the Unity3D software, a visual monitoring interface is shown in fig. 10, three-dimensional visualization and real-time display of operation data of a processing process are realized, and meanwhile, remote monitoring is realized based on the Unity WebGL technology.

Specifically, a UI tool in Unity3D software is utilized to build a human-computer interaction function, so that an operator can input processing parameters, adjust a control strategy and set an optimization target through an interface, and input content is transmitted to an adaptive control system to guide the adaptive regulation and control of the processing process.

And dynamically displaying the collected data and the prediction result of the twin model in the forms of a chart, a curve, an instrument panel and the like by utilizing XCharts plug-ins.

In order to facilitate the display of the UI interface and the dynamic observation of the machine tool, a double camera is arranged in the embodiment. One of the cameras is used to display the machine tool and the camera can rotate or zoom the field of view around the machine tool and then map the screen onto the UI interface to enable multi-angle viewing of the machine tool operating conditions and the other camera is used to display the UI interface.

The application process of the machine tool self-adaptive control system based on digital twin provided by the embodiment is as follows:

1. System initialization

(1) Checking hardware device connections

And checking whether the connection of hardware equipment such as machine tool equipment, a sensor, a data acquisition card, a control module and the like is good, and ensuring the connection stability and the normal data transmission of all the equipment.

(2) Starting data acquisition system

And (3) turning on a power supply of the data acquisition system, starting various sensors (such as a vibration sensor and a temperature sensor), ensuring that the sensors are in a normal working state, and acquiring real-time data.

(3) Starting machine tool equipment and digital twin model

And starting the actual machine tool equipment, and checking whether the functions of the machine tool, such as movement, spindle operation and the like are normal. And starting a digital twin model system, and checking whether the twin model can realize data synchronization and real-time interaction with a physical machine tool.

(4) System parameter initialization and configuration

The initialization parameters of the system are configured in the man-machine interaction interface, including spindle rotation speed, feeding speed, cutting depth, cutter type, workpiece material characteristics and the like. And setting a target value and a threshold range of the spindle load, and configuring target requirements and optimization targets of the machining task.

2. Data acquisition and calibration

(1) Collecting initial state data

Under the condition of no load and load of the machine tool, state data such as main shaft current and temperature are collected, and the data and a digital twin model are subjected to preliminary calibration so as to ensure that the model can accurately reflect the state of an actual machine tool.

(2) Calibrating twin model parameters

And calibrating and adjusting parameters of the digital twin model according to the acquired initial data.

(3) Verification data transmission

Checking all data transmission lines from the physical machine tool to the data acquisition system and then to the twin model and the control module, and ensuring the real-time performance and accuracy of data transmission.

3. Starting digital twin model and main shaft load self-adaptive control module

(1) Starting digital twin model

And starting the digital twin model in the man-machine interaction interface, and enabling the model to enter a real-time updating and state predicting mode. At the moment, the digital twin model continuously updates the state of the digital twin model through real-time data acquired by the sensor, and predicts the spindle load in the machining process.

(2) Starting main shaft load self-adaptive control module

And starting a main shaft load self-adaptive control module, and configuring a control strategy according to the target value and the threshold range of the main shaft load and the processed workpiece.

4. Setting and executing processing tasks

And starting the actual machining task of the machine tool. At this time, the spindle load self-adaptive control module dynamically adjusts the processing parameters according to the data acquired in real time.

5. Real-time monitoring and man-machine interaction operation

(1) Real-time monitoring of processing status

On a man-machine interaction interface, various parameters of the processing state are checked in real time, including information such as spindle load, temperature change and the like.

(2) Abnormality alert and handling

When the digital twin model prediction or self-adaptive control system detects that key parameters such as spindle load exceed a set threshold, the system sends out an abnormal alarm signal.

6. System maintenance and extension

(1) Periodic maintenance and calibration

And the hardware equipment such as the sensor, the data acquisition card and the control module are regularly maintained and calibrated, so that the accuracy and stability of system data acquisition are ensured. Meanwhile, the digital twin model and the adaptive control module are checked and updated to cope with the influence of the processing technology change and the equipment aging.

(2) System extension and function upgrade

And further expanding and upgrading the system according to actual processing requirements and technical development conditions. For example, new sensor types (such as stress sensors, thermal deformation monitoring sensors and the like) are added, control algorithms (such as self-adaptive neural network control, reinforcement learning and the like) are optimized, and the sensor types are integrated with other intelligent manufacturing systems (such as workshop management systems and manufacturing execution systems), so that the overall intelligence and application scenes of the system are improved.

The machine tool self-adaptive control system based on digital twin provided by the embodiment has wide application, and comprises:

(1) Application in high-precision machining task

In high-precision machining tasks (such as aerospace parts, precision die manufacturing and the like), workpiece materials are various, machining precision requirements are high, and spindle loads and cutting forces in the machining process easily fluctuate severely. By utilizing the system provided by the invention, the stability of the load and the cutting force of the main shaft can be ensured through real-time monitoring and self-adaptive control, so that higher machining precision and surface quality are achieved.

(2) Application in intelligent manufacturing workshop and intelligent factory

The system can be integrated with other devices and systems (such as a workshop management system and a manufacturing execution system) of an intelligent manufacturing workshop or an intelligent factory, realizes global optimization control and management, and provides effective support for the construction of the intelligent manufacturing workshop and the intelligent factory.

(3) Application in multi-material processing

In the multi-material processing scene (such as aluminum alloy, titanium alloy, composite material and the like), the strong fluctuation of the load and the cutting moment of the main shaft is easy to be caused due to the large difference of the mechanical characteristics of different materials. By utilizing the system provided by the invention, the processing parameters can be adaptively adjusted according to the characteristics of different materials, so that the efficient control and management of the multi-material processing process can be realized.

It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

The above description is only a preferred embodiment of the present invention, and is not intended to limit the invention in any way, and any person skilled in the art may make modifications or alterations to the disclosed technical content to the equivalent embodiments. However, any simple modification, equivalent variation and variation of the above embodiments according to the technical substance of the present invention still fall within the protection scope of the technical solution of the present invention.

Claims

1. A machine tool adaptive control system based on digital twin, characterized in that it includes a CNC machine tool, a data acquisition system, a digital twin model, a spindle load adaptive control module and a human-computer interaction system. By constructing a digital twin model of the CNC machine tool and a spindle load adaptive control module, real-time monitoring and adaptive regulation of the machining process are realized.

2. According to the digital twin-based machine tool adaptive control system of claim 1, it is characterized in that the CNC machine tool is the controlled object, and its basic structure includes a spindle, a tool, a workpiece and a machine bed, and the spindle load and processing parameter data are derived from the CNC machine tool and collected in real time by a data acquisition system;

The data acquisition system includes multiple sensors of various types, a data processing unit, a database and a data transmission unit, which are used to collect real-time data of the CNC machine tool and store the collected data in the database. The digital twin model realizes communication by reading the data in the database;

The digital twin model consists of a physical model and a data-driven model; the physical model combines the structure and dynamic characteristics of the machine tool to reflect the physical behavior of the machine tool during the processing; the data-driven model uses a support vector machine algorithm based on the collected multi-source data to establish a mapping relationship between the spindle load and the processing parameters; combining the physical model and the data-driven model to form a real-time updated digital twin model to realize the monitoring and simulation of the processing process;

The spindle load adaptive control module monitors the spindle load and processing status in real time and uses a fuzzy adaptive control algorithm to adjust the feed speed of the machine tool; when it is detected that the spindle load exceeds the set threshold or abnormal fluctuation occurs, the spindle load adaptive control module adaptively adjusts the processing parameters through a feedback mechanism to ensure the stability of the processing process and the processing quality;

The human-machine interaction system includes a visual monitoring interface and a simulation panel, so as to view the real-time status of the machine tool and the cutting force prediction results of the machining process, as well as the adjustment process of the adaptive control through the visual monitoring interface.

3. According to claim 2, a machine tool adaptive control system based on digital twins is characterized in that the sensors of the data acquisition system are respectively installed at different positions of the CNC machine tool to collect the spindle current and voltage, temperature changes and related operation data during the machine tool processing, and send the collected real-time data to the data processing unit, and the data acquisition device uploads the collected data to the database;

The digital twin model communicates with the database through a data transmission unit to obtain the operation data of the machine tool in real time, and uses the physical model and the data-driven model to map the machining process in real time; the digital twin model sends the real-time data and the predicted results of the cutting force to the spindle load adaptive control module;

When the spindle load fluctuates abnormally or exceeds the set threshold, the spindle load adaptive control module uses a fuzzy adaptive control algorithm to adaptively adjust the feed speed of the machine tool according to the feedback information of the digital twin model; the spindle load adaptive control module dynamically adjusts the processing parameters of the CNC machine tool, including feed speed, spindle speed, and cutting depth, according to the feedback information of the digital twin model and real-time collected data. The adjusted processing parameters act on the machine tool through the actuator to achieve adaptive control of the processing process;

The human-machine interaction system performs a multi-directional three-dimensional visualization display of the machine tool through a visualization monitoring interface, and uses Unity's WebGL technology to realize remote monitoring of the machine tool's operating status.

4. A method for implementing a machine tool adaptive control system based on digital twin according to any one of claims 1 to 3, characterized in that it comprises the following steps:

Step S1: constructing a geometric model of the CNC machine tool based on the geometric features of the CNC machine tool and the constraint relationship between each component;

Step S2: obtaining data of the machine tool spindle during cutting, preprocessing the obtained data and building an agent model;

Step S3: Building a data acquisition system for the machine tool operation status and current, voltage and temperature data;

Step S4: Establishing digital twin models of the spindle, tool, and workpiece;

Step S5: Establish a spindle load adaptive control module to adjust the machine tool feed speed in real time according to the real-time data of the machine tool and the digital twin model;

Step S6: Building a human-computer interaction system.

5. The method for implementing a machine tool adaptive control system based on digital twin according to claim 4 is characterized in that the implementation method of step S1 is:

First, use 3D scanning technology or CAD model import to obtain the geometric data of key machine tool components and workpieces to ensure that the geometric accuracy of the model is consistent with the actual machine tool;

Secondly, use 3D modeling software to build a 3D geometric model of the machine tool and workpiece; the model includes various components of the machine tool and can represent the contact point between the tool and the workpiece, the spindle position, and the workpiece position;

Finally, the 3D geometric model is converted into STP format and imported into the 3D rendering software. The 3D geometric model is lightweight, and materials are set for each component of the 3D geometric model for appearance rendering. At the same time, the parent-child relationship of each component is set according to the movement form of the machine tool and exported to FBX format.

6. The method for implementing a machine tool adaptive control system based on digital twin according to claim 4 is characterized in that the implementation method of step S2 is:

By performing dynamic simulation on the cutting process of the spindle or collecting machine tool operation data, the cutting force of the spindle at different cutting depths, feed speeds and spindle speeds is obtained, and the obtained data is divided into training data and verification data; in order to reduce the impact of different dimensions and speed up the training speed, the data is normalized:

Then, a proxy model was constructed using a support vector machine model with RBF as the kernel function. The proxy model was trained using normalized data, and the hyperparameters of the SVM were optimized using the K-means optimization algorithm. After training, a proxy model for cutting force prediction was obtained.

7. The method for implementing a machine tool adaptive control system based on digital twin according to claim 4 is characterized in that the implementation method of step S3 is:

First, select the appropriate sensor and development method based on the specific situation of the data machine tool and the signals to be collected;

Secondly, according to the working principle of the sensor and the data collection requirements, the sensor is installed at the key position of the machine tool; after the installation is completed, the sensitivity, response speed and sampling frequency of the sensor are debugged to ensure the accuracy and real-time performance of data collection;

Finally, the data collected by the sensor is transmitted to the data processing unit; the data processing unit filters, denoises and extracts features of the collected data, and uploads the processed data to the database, and the database communicates with the digital twin model through the data transmission unit.

8. The method for implementing a machine tool adaptive control system based on digital twin according to claim 4, characterized in that the implementation method of step S4 is:

Import the FBX file of the geometric model of the CNC machine tool generated in step S1 into the Unity3D software, develop scripts for the linear motion of the machine tool x, y, and z axes and the rotary motion of the tool based on the DOTween animation plug-in, optimize the tool cutting workpiece effect through dynamic mesh modification technology, and then add mesh colliders to the parts of the machine tool, and the collision detection method is continuous detection; at the same time, read the database data in real time to drive the movement of the digital twin model to realize the real-time mapping of the digital twin model to the physical machine tool; and the script retains the development and editing interface to facilitate the promotion and secondary development of the script;

Secondly, the script is used to parse the code running on the machine tool, convert the commands in the G code into Unity coordinates, and obtain the machine tool's feed speed, spindle speed, and cutting depth data. Then, the agent model trained in step S2 is used to simulate the machine tool processing process and predict the spindle cutting force in real time, providing a basis for optimizing the machine tool processing process.

9. The method for implementing a machine tool adaptive control system based on digital twin according to claim 4, characterized in that the implementation method of step S5 is:

A two-dimensional fuzzy controller is used to implement the fuzzy adaptive machining control algorithm; a fuzzy controller is constructed in the Fuzzy toolbox of MATLAB, in which the fuzzy sets of Ep, Cp and △u are (NB, NM, NS, 0, PS, PM, PB), the range of fuzzy subsets is (-3, -2, -1, 0, 1, 2, 3), and the membership functions are triangular function and trapezoidal function; after setting the fuzzy rule table, the Mamdani method is used for fuzzy reasoning, and the center of gravity method is used for anti-fuzzy operation; the predicted cutting torque is compared with the target torque, and the data of how much the feed speed can be changed to reach the target torque is obtained after the fuzzy controller, thereby achieving stability and efficiency of the machining process.

10. The method for implementing a machine tool adaptive control system based on digital twin according to claim 4, characterized in that the implementation method of step S6 is:

By using the UI tools and XCharts plug-ins in Unity3D software, a human-computer interaction system is built to achieve three-dimensional visualization of the processing process and real-time display of operating data. At the same time, remote monitoring is achieved based on Unity WebGL technology.