Self-adaptive control method and system for digital twin-driven machine tool

Abstract

The invention discloses a digital twin-driven machine tool adaptive control method and system and a machine tool control system, and the machine tool control system comprises a data collection unit, a data transmission unit, a twin model unit, a data processing unit, a control decision unit, an adaptive algorithm unit, a control execution unit, a machine tool execution unit and a feedback monitoring unit. The output ends of the data acquisition unit, the twin model unit and the data processing unit are connected with the input end of the data transmission unit; the output end of the data transmission unit is connected with the input end of the control decision unit; according to the method, the control strategy is adjusted in real time through the self-adaptive control algorithm to cope with the change of system parameters and external disturbance, and the advantages of dynamic response capability, robustness enhancement, performance optimization, manual intervention reduction, nonlinear system processing, safety improvement, complex task implementation and the like are provided. The advantages enable the adaptive control algorithm to become an important control means in many modern engineering applications.

Description

Technical Field

[0001] The present invention relates to the technical field of digital twin driven machine tool control systems, and specifically to a digital twin driven machine tool adaptive control method and system. Background Art

[0002] The application of digital twin technology in the field of machine tools has gradually attracted attention. Digital twin-driven machine tools refer to real-time synchronization of the physical entity of the machine tool with its digital model to achieve more efficient management, monitoring and optimization. Digital twin technology can closely integrate the physical operation of the machine tool with the virtual world, bringing a higher level of intelligence and efficiency improvement to the manufacturing industry.

[0003] However, the currently existing digital twin-driven machine tool adaptive control methods and systems are not able to efficiently control the digital twin-driven machine tools when in use, and are unable to quickly adaptively control and adjust complex tasks, so the overall processing efficiency is low when processing complex tasks. Summary of the invention

[0004] The purpose of the present invention is to provide a digital twin driven machine tool adaptive control method and system to solve the problems raised in the above background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A digital twin driven machine tool adaptive control method and system, a machine tool control system, the machine tool control system includes a data acquisition unit, a data transmission unit, a twin model unit, a data processing unit, a control decision unit, an adaptive algorithm unit, a control execution unit, a machine tool execution unit and a feedback monitoring unit, the output ends of the data acquisition unit, the twin model unit and the data processing unit are all connected to the input end of the data transmission unit, the output end of the data transmission unit is connected to the input end of the control decision unit, the control decision unit and the adaptive algorithm unit are bidirectionally connected, the output end of the control decision unit is connected to the input end of the control execution unit, the output end of the control execution unit is connected to the input end of the machine tool execution unit, the feedback monitoring unit is installed and connected to one end of the machine tool execution unit, and the output end of the feedback monitoring unit is connected to the input end of the data acquisition unit.

[0007] As a further solution of the present invention: the data acquisition unit includes a temperature sensor, a pressure sensor, a displacement sensor, an acceleration sensor and a photoelectric sensor, and the data acquisition unit also includes a PLC controller module. The temperature sensor monitors the machine tool temperature, the pressure sensor monitors the pressure of the cutting fluid or liquid, the displacement sensor accurately measures the position of machine tool parts, the acceleration sensor monitors the machine vibration and determines the status, and the photoelectric sensor detects the clamping status of the workpiece.

[0008] As a further solution of the present invention: the data transmission unit includes industrial Ethernet, a wireless communication module and a cloud platform, the industrial Ethernet transmits data to the cloud platform in real time, and the wireless communication module provides remote data access.

[0009] As a further solution of the present invention: the twin model unit includes a modeling software module, a simulation software module and an update algorithm module. The modeling software module creates a two-dimensional or three-dimensional model of the digital twin of the machine tool, the simulation software module simulates the machining process, and the update algorithm module updates the model according to real-time data.

[0010] As a further solution of the present invention: the control decision unit includes a decision control module, an optimization algorithm module and an artificial intelligence module. The decision control module recommends operations based on data analysis results, the optimization algorithm module dynamically adjusts processing parameters and paths, and the artificial intelligence module optimizes control strategies through machine learning.

[0011] As a further solution of the present invention: the adaptive algorithm unit includes a controller module, a PID controller, an MPC controller and a fuzzy controller. The PID controller adjusts the control amount by calculating the values ​​of proportion P, integral I and differential D to reduce the error. The MPC controller uses a system model to predict future states and optimizes control inputs to achieve optimal performance. The fuzzy controller uses fuzzy logic to make decisions on imprecise or uncertain information and provides flexible control.

[0012] As a further solution of the present invention: the control execution unit includes a CNC control module, a servo motor module and a drive control module, the CNC control module receives instructions to control the movement of the machine tool, the servo motor module accurately controls the movement of the machine tool, and the drive control module provides power for each mechanical component.

[0013] As a further solution of the present invention: the machine tool execution unit includes a CNC machine tool module, a fixture module and a cutting tool module, the CNC machine tool module performs actual processing operations, the fixture module fixes and supports the workpiece, and the cutting tool module removes material.

[0014] As a further solution of the present invention: the feedback monitoring unit includes a status monitoring module, an alarm module and a data feedback module. The status monitoring module monitors the operating status of the machine tool in real time, the alarm module alarms in real time for abnormal conditions, and the data feedback module feeds back the result data to the data acquisition layer.

[0015] As a further solution of the present invention: the steps of the machine tool adaptive control method and system driven by digital twin are as follows:

[0016] S1: First, install the sensors, such as temperature sensors, pressure sensors, displacement sensors, acceleration sensors and photoelectric sensors, to various parts of the machine tool to monitor various parameters of the machine tool during operation, and transmit the monitoring data to the PLC controller for data preprocessing;

[0017] S2: Then, the data is transmitted to the cloud platform in real time through industrial Ethernet, wireless communication module and cloud platform. At the same time, the wireless communication module provides remote data access, and the data is processed by the data processing unit. The data cleaning tool is used to remove inaccurate or abnormal data points to ensure data quality, and the data visualization tool is used to generate easy-to-understand reports and charts to help operators understand the status of the machine tool;

[0018] S3: Then, a digital twin model of the machine tool is created through the modeling software module, the simulation software module, and the update algorithm module, including the geometric model and the functional model, and simulation parameters are set to accurately reflect the real behavior of the machine tool. The real-time data is integrated with the digital twin model, and the model status is updated. The model is adjusted and optimized according to the data analysis results to better simulate the behavior of the actual machine tool;

[0019] S4: Then, based on the analysis results of the digital twin model, the decision support system is used to recommend the optimal operation strategy through the decision control module, the optimization algorithm module and the artificial intelligence module, and the optimization algorithm is applied to adjust the processing parameters and paths to improve the processing efficiency and quality. The artificial intelligence module is used to learn historical data to optimize the control strategy and decision-making process;

[0020] S5: Then through the controller module, PID controller, MPC controller and fuzzy controller;

[0021] S6: Then, the formulated control strategy is converted into specific control instructions through the CNC control module, servo motor module and drive control module, and sent to the machine tool through the CNC controller to set and adjust the processing parameters of the machine tool, such as cutting speed, feed speed, etc., drive the various moving parts of the machine tool, perform precise operations according to the instructions, and provide necessary power support for various mechanical parts of the machine tool;

[0022] S7: Then the CNC machine tool module performs actual processing operations such as cutting, drilling, milling, etc. according to the instructions. The fixture module fixes the workpiece to ensure that it is stable and does not change position during the processing. The cutting tool module performs the actual cutting and processing tasks;

[0023] S8: Then, the working status of the machine tool is observed in real time through the status monitoring system through the status monitoring module, the alarm module and the data feedback module, and the status data and results of the processing process are fed back to the data acquisition layer.

[0024] Compared with the prior art, the present invention has the following beneficial effects:

[0025] 1. The present invention uses an adaptive control algorithm to adjust the control strategy in real time to cope with changes in system parameters and external disturbances, providing multiple benefits such as dynamic response capability, enhanced robustness, optimized performance, reduced manual intervention, handling nonlinear systems, improved safety, and realization of complex tasks. These advantages make the adaptive control algorithm an important control method in many modern engineering applications.

[0026] 2. The present invention significantly improves processing accuracy and system reliability, reduces production costs, and improves operational flexibility and safety through precise real-time monitoring, intelligent optimization control, predictive maintenance, and flexible adjustment capabilities. These benefits make this control method an important tool in modern manufacturing, providing strong support for improving production efficiency and product quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 Schematic diagram of the overall structure of the machine tool adaptive control method and system driven by digital twins.

[0028] Figure 2 Schematic diagram of the structure of the data acquisition unit of the machine tool adaptive control method and system driven by digital twins.

[0029] Figure 3 A structural schematic diagram of the data transmission unit of the machine tool adaptive control method and system driven by digital twins.

[0030] Figure 4 Schematic diagram of the structure of the twin model unit of the digital twin driven machine tool adaptive control method and system.

[0031] Figure 5 Schematic diagram of the structure of the control decision unit of the machine tool adaptive control method and system driven by digital twin.

[0032] Figure 6 Schematic diagram of the structure of the adaptive algorithm unit of the machine tool adaptive control method and system driven by digital twins.

[0033] Figure 7 The schematic diagram of the structure of the control execution unit of the machine tool adaptive control method and system driven by digital twin.

[0034] Figure 8 A structural schematic diagram of a machine tool execution unit of a machine tool adaptive control method and system driven by a digital twin.

[0035] Fig. 9 Schematic diagram of the structure of the feedback monitoring unit of the machine tool adaptive control method and system driven by digital twin.

[0036] In the figure: 100, machine tool control system; 1, data acquisition unit; 2, data transmission unit; 3, twin model unit; 4, data processing unit; 5, control decision unit; 6, adaptive algorithm unit; 7, control execution unit; 8, machine tool execution unit; 9, feedback monitoring unit; 10, temperature sensor; 11, pressure sensor; 12, displacement sensor; 13, acceleration sensor; 14, photoelectric sensor; 15, PLC controller module; 20, industrial Ethernet; 21, wireless communication module; 22, cloud platform; 30, Modeling software module; 31. Simulation software module; 32. Update algorithm module; 50. Decision control module; 51. Optimization algorithm module; 52. Artificial intelligence module; 60. Controller module; 61. PID controller; 62. MPC controller; 63. Fuzzy controller; 70. CNC control module; 71. Servo motor module; 72. Drive control module; 80. CNC machine tool module; 81. Fixture module; 82. Cutting tool module; 90. Status monitoring module; 91. Alarm module; 92. Data feedback module. DETAILED DESCRIPTION

[0037] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0038] See also Figures 1 to 9 In an embodiment of the present invention, a digital twin-driven machine tool adaptive control method and system, a machine tool control system 100, the machine tool control system 100 includes a data acquisition unit 1, a data transmission unit 2, a twin model unit 3, a data processing unit 4, a control decision unit 5, an adaptive algorithm unit 6, a control execution unit 7, a machine tool execution unit 8 and a feedback monitoring unit 9, the output ends of the data acquisition unit 1, the twin model unit 3 and the data processing unit 4 are all connected to the input end of the data transmission unit 2, the output end of the data transmission unit 2 is connected to the input end of the control decision unit 5, the control decision unit 5 and the adaptive algorithm unit 6 are bidirectionally connected, the output end of the control decision unit 5 is connected to the input end of the control execution unit 7, the output end of the control execution unit 7 is connected to the input end of the machine tool execution unit 8, the feedback monitoring unit 9 is installed and connected to one end of the machine tool execution unit 8, and the output end of the feedback monitoring unit 9 is connected to the input end of the data acquisition unit 1.

[0039] See also Figure 2The data acquisition unit 1 includes a temperature sensor 10, a pressure sensor 11, a displacement sensor 12, an acceleration sensor 13 and a photoelectric sensor 14. The data acquisition unit 1 also includes a PLC controller module. The temperature sensor 10 monitors the machine tool temperature, the pressure sensor 11 monitors the pressure of the cutting fluid or liquid, the displacement sensor 12 accurately measures the position of the machine tool parts, the acceleration sensor 13 monitors the machine vibration and determines the state, and the photoelectric sensor 14 detects the clamping state of the workpiece.

[0040] See also Figure 3 The data transmission unit 2 includes an industrial Ethernet 20, a wireless communication module 21 and a cloud platform 22. The industrial Ethernet 20 transmits data to the cloud platform 22 in real time, and the wireless communication module 21 provides remote data access.

[0041] See also Figure 4 The twin model unit 3 includes a modeling software module 30, a simulation software module 31 and an update algorithm module 32. The modeling software module 30 creates a two-dimensional or three-dimensional model of the digital twin of the machine tool, the simulation software module 31 simulates the machining process, and the update algorithm module 32 updates the model according to real-time data.

[0042] See also Figure 5 The control decision unit 5 includes a decision control module 50, an optimization algorithm module 51 and an artificial intelligence module 52. The decision control module 50 recommends operations based on data analysis results, the optimization algorithm module 51 dynamically adjusts processing parameters and paths, and the artificial intelligence module 52 optimizes control strategies through machine learning.

[0043] See also Figure 6 The adaptive algorithm unit 6 includes a controller module 60, a PID controller 61, an MPC controller 62 and a fuzzy controller 63. The PID controller 61 adjusts the control amount by calculating the values ​​of the proportion P, the integral I and the differential D to reduce the error. The MPC controller 62 uses the system model to predict the future state and optimizes the control input to achieve the best performance. The fuzzy controller 63 uses fuzzy logic to make decisions on imprecise or uncertain information and provides flexible control.

[0044] See also Figure 7 The control execution unit 7 includes a CNC control module 70, a servo motor module 71 and a drive control module 72. The CNC control module 70 receives instructions to control the movement of the machine tool, the servo motor module 71 accurately controls the movement of the machine tool, and the drive control module 72 provides power for each mechanical component.

[0045] See also Figure 8The machine tool execution unit 8 includes a CNC machine tool module 80, a fixture module 81 and a cutting tool module 82. The CNC machine tool module 80 performs actual processing operations, the fixture module 81 fixes and supports the workpiece, and the cutting tool module 82 removes materials.

[0046] See also Fig. 9 The feedback monitoring unit 9 includes a status monitoring module 90, an alarm module 91 and a data feedback module 92. The status monitoring module 90 monitors the operating status of the machine tool in real time, the alarm module 91 gives a real-time alarm for abnormal conditions, and the data feedback module 92 feeds back the result data to the data acquisition layer.

[0047] The working principle of the present invention is: first, the sensors are installed, and the temperature sensor 10, the pressure sensor 11, the displacement sensor 12, the acceleration sensor 13 and the photoelectric sensor 14 are installed at various parts of the machine tool to monitor various parameters when the machine tool is working, and the monitoring data is transmitted to the PLC controller for data preprocessing, and then the data is transmitted to the cloud platform 22 in real time through the industrial Ethernet 20, the wireless communication module 21 and the cloud platform 22, and remote data access is provided through the wireless communication module 21, and the data is processed by the data processing unit 4, and the inaccurate data is removed using the data cleaning tool. or abnormal data points, ensure data quality, and use data visualization tools to generate easy-to-understand reports and charts to help operators understand the status of the machine tool. Then, through the modeling software module 30, the simulation software module 31 and the update algorithm module 32, a digital twin model of the machine tool is created, including a geometric model and a functional model, and simulation parameters are set to accurately reflect the real behavior of the machine tool. The real-time data is integrated with the digital twin model, the model status is updated, and the model is adjusted and optimized according to the data analysis results to better simulate the behavior of the actual machine tool. Then, through the decision control module 50, the optimization algorithm module 51 and the artificial intelligence module 52 Based on the analysis results of the digital twin model, the decision support system is used to recommend the optimal operation strategy, and the optimization algorithm is applied to adjust the processing parameters and paths to improve the processing efficiency and quality. The artificial intelligence module is used to learn the historical data, optimize the control strategy and decision-making process, and then the controller module 60, PID controller 61, MPC controller 62 and fuzzy controller 63, and then the CNC control module 70, servo motor module 71 and drive control module 72 are used to convert the formulated control strategy into specific control instructions, which are sent to the machine tool through the CNC controller to set and adjust the machine tool processing parameters, such as cutting Speed, feed speed, etc., drive the various moving parts of the machine tool, perform precise operations according to the instructions, and provide necessary power support for the various mechanical parts of the machine tool. Then, the CNC machine tool module 80 performs actual processing operations according to the instructions, such as cutting, drilling, milling, etc. The fixture module 81 fixes the workpiece to ensure that it is stable and does not change position during the processing. The cutting tool module 82 performs the actual cutting and processing tasks. Then, the state monitoring module 90, the alarm module 91 and the data feedback module 92 use the state monitoring system to observe the working status of the machine tool in real time, and transmit the status data and results of the processing process to the data acquisition layer.

[0048] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

[0049] In addition, it should be understood that although the present specification is described according to implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment may also be appropriately combined to form other implementation modes that can be understood by those skilled in the art.

Claims

1. Digital twin-driven machine tool adaptive control system, characterized by: include: A machine tool control system (100), the machine tool control system (100) comprises a data acquisition unit (1), a data transmission unit (2), a twin model unit (3), a data processing unit (4), a control decision unit (5), an adaptive algorithm unit (6), a control execution unit (7), a machine tool execution unit (8) and a feedback monitoring unit (9), wherein the output ends of the data acquisition unit (1), the twin model unit (3) and the data processing unit (4) are all connected to the input end of the data transmission unit (2), the output end of the data transmission unit (2) is connected to the input end of the control decision unit (5), the control decision unit (5) and the adaptive algorithm unit (6) are bidirectionally connected, the output end of the control decision unit (5) is connected to the input end of the control execution unit (7), the output end of the control execution unit (7) is connected to the input end of the machine tool execution unit (8), the feedback monitoring unit (9) is installed and connected to one end of the machine tool execution unit (8), and the output end of the feedback monitoring unit (9) is connected to the input end of the data acquisition unit (1).

2. The digital twin-driven machine tool adaptive control system according to claim 1, characterized in that: The data acquisition unit (1) comprises a temperature sensor (10), a pressure sensor (11), a displacement sensor (12), an acceleration sensor (13) and a photoelectric sensor (14); the data acquisition unit (1) also comprises a PLC controller module.

3. The digital twin-driven machine tool adaptive control system according to claim 1, characterized in that: The data transmission unit (2) comprises an industrial Ethernet (20), a wireless communication module (21) and a cloud platform (22).

4. The digital twin-driven machine tool adaptive control system according to claim 1, characterized in that: The twin model unit (3) comprises a modeling software module (30), a simulation software module (31) and an updating algorithm module (32).

5. The digital twin-driven machine tool adaptive control system according to claim 1, characterized in that: The control decision unit (5) comprises a decision control module (50), an optimization algorithm module (51) and an artificial intelligence module (52).

6. The digital twin-driven machine tool adaptive control system according to claim 1, characterized in that: The adaptive algorithm unit (6) comprises a controller module (60), a PID controller (61), an MPC controller (62) and a fuzzy controller (63).

7. The digital twin-driven machine tool adaptive control system according to claim 1, characterized in that: The control execution unit (7) comprises a CNC control module (70), a servo motor module (71) and a drive control module (72).

8. The digital twin-driven machine tool adaptive control system according to claim 1, characterized in that: The machine tool execution unit (8) comprises a numerical control machine tool module (80), a fixture module (81) and a cutting tool module (82).

9. The digital twin-driven machine tool adaptive control system according to claim 1, characterized in that: The feedback monitoring unit (9) comprises a status monitoring module (90), an alarm module (91) and a data feedback module (92).

10. The method for adaptive control of a machine tool driven by a digital twin according to any one of claims 1 to 9, characterized in that: The specific steps include: S1: First, the sensors are installed, and the temperature sensor (10), the pressure sensor (11), the displacement sensor (12), the acceleration sensor (13) and the photoelectric sensor (14) are installed at various parts of the machine tool to monitor various parameters of the machine tool when it is working, and the monitoring data is transmitted to the PLC controller for data preprocessing; S2: Then, the data is transmitted to the cloud platform (22) in real time through the industrial Ethernet (20), the wireless communication module (21) and the cloud platform (22), and remote data access is provided through the wireless communication module (21), and the data processing unit (4) is used to process the data, and inaccurate or abnormal data points are removed using a data cleaning tool to ensure data quality, and easy-to-understand reports and charts are generated using a data visualization tool to help operators understand the status of the machine tool; S3: Then, a digital twin model of the machine tool is created through a modeling software module (30), a simulation software module (31) and an update algorithm module (32), including a geometric model and a functional model, simulation parameters are set to accurately reflect the real behavior of the machine tool, real-time data is integrated with the digital twin model, the model state is updated, and the model is adjusted and optimized according to the data analysis results to better simulate the behavior of the actual machine tool; S4: Then, based on the analysis results of the digital twin model, the decision support system is used to recommend the optimal operation strategy through the decision control module (50), the optimization algorithm module (51) and the artificial intelligence module (52), and the optimization algorithm is used to adjust the processing parameters and paths to improve the processing efficiency and quality. The artificial intelligence module is used to learn historical data to optimize the control strategy and decision-making process; S5: Then through the controller module (60), PID controller (61), MPC controller (62) and fuzzy controller (63); S6: Then, the formulated control strategy is converted into specific control instructions through the CNC control module (70), the servo motor module (71) and the drive control module (72), and sent to the machine tool through the CNC controller to set and adjust the processing parameters of the machine tool, such as cutting speed, feed speed, etc., drive the various moving parts of the machine tool to perform precise operations according to the instructions, and provide necessary power support for various mechanical parts of the machine tool; S7: Then, the CNC machine tool module (80) performs actual processing operations such as cutting, drilling, milling, etc. according to the instructions, the fixture module (81) fixes the workpiece to ensure that it is stable and does not change position during the processing, and the cutting tool module (82) performs the actual cutting and processing tasks; S8: Then, the working state of the machine tool is observed in real time through the state monitoring system via the state monitoring module (90), the alarm module (91) and the data feedback module (92), and the state data and results of the processing process are fed back to the data acquisition layer.

Images