Whole-process real-time monitoring and auxiliary decision-making method and system for digital twin additive manufacturing

Abstract

The invention provides a whole-process real-time monitoring and auxiliary decision-making method and system for digital twin additive manufacturing. The method comprises the steps that S1, data of equipment to be detected are collected; the to-be-tested equipment comprises robot polishing equipment, five-axis numerical control machining equipment and additive printing equipment; s2, processing the data of the equipment to be tested by using different types of data platforms; s3, data monitoring of the whole additive manufacturing process is completed based on the processing result; and S4, analyzing the processing result, and optimizing the monitoring process. According to the invention, through rapid modeling and data acquisition and fusion, a digital twin system oriented to the whole process of digital twin additive manufacturing is formed based on intelligent management and control and multi-system production data fusion; and the functions of equipment information checking, equipment state monitoring, equipment abnormity warning and equipment decision assisting are achieved for the three stages of printing, machining and grinding and polishing, and good practicability is achieved.

Description

Technical Field

[0001] The present invention relates to the field of constructing a digital twin system for additive manufacturing, and in particular, to a method and system for real-time monitoring and auxiliary decision-making of digital twin additive manufacturing throughout the entire process. Background Art

[0002] Additive manufacturing is a manufacturing technology that uses software and numerical control systems to stack special materials layer by layer in the form of extrusion, sintering, melting, photocuring, etc. to produce physical objects based on digital model files. Compared with traditional mechanical processing, additive manufacturing has the advantages of high design flexibility, short development time, less production waste and low cost. However, there are also various processing defects and inconsistent product quality (such as porosity caused by insufficient fusion between materials, and warping of printed parts caused by the rapid cooling characteristics of the additive manufacturing process), which still hinders its widespread application in industry. Machine learning has received increasing attention due to its outstanding performance in data tasks such as classification, regression and clustering, and machine learning has gradually been applied to the detection of additive manufacturing processes. However, building a machine learning model requires a large amount of data, and training a large data set is very time-consuming in terms of computation. There is no unified interface and platform for data collection and analysis. The data sets collected by each method cannot share information and become information islands, which cannot fully utilize the value of data, resulting in limitations in the application of machine learning algorithms in additive manufacturing.

[0003] Digital twins are virtual entities that create physical entities in a digital way. Based on historical data, real-time data, and algorithm models, they simulate, verify, predict, and control physical entities throughout their life cycle, ultimately achieving an optimized closed loop of intelligent decision-making. Using these characteristics of digital twins to perform real-time anomaly detection on the working process of equipment is also very effective. However, most of the previous twin models of 3D printers were limited to a 3D printing method, and there was little discussion on how to build a digital twin model for the entire additive manufacturing field. Moreover, the characteristics of digital twins that are mainly based on data and algorithm models have not been fully utilized, and few digital twins have been combined with cloud computing big data technology, thus ignoring the update and iteration issues of digital twin models.

[0004] Digital twin models are generally driven by multi-source heterogeneous data, and their data scale is usually very large. Unit-level digital twins may be able to meet computing and operation requirements on local servers, but complex system-level digital twins require greater computing and storage capabilities. Cloud computing has an on-demand use and distributed sharing model, and can be used as cloud computing resources and data centers for digital twins, thereby meeting the different computing, storage and application needs of digital twins. Therefore, how to effectively combine digital twins with cloud computing has become an inevitable trend in the development of digital twins. However, digital twins are rarely used in the field of additive manufacturing, and their overall framework and specific functions have not been widely discussed.

[0005] In the Chinese patent document with publication number CN115489125A, a method for building a digital twin system for additive manufacturing based on cloud services is disclosed, which includes the following steps: Step 1, obtain sensor data of the physical model and transmit it to the local server network service layer for data fusion; Step 2, data-driven digital twin model establishment; Step 3, the digital twin model feeds back the results to the physical layer and the human-computer interaction interface through data analysis and simulation; Step 4, the sensor data is sent to the cloud digital twin at the same time to analyze the results; Step 5, the local digital twin model detects the printing process through intelligent algorithms and simulation. Although this patent document can collect real-time data of parts in the additive manufacturing process and perform three-dimensional simulation based on the data, it does not add the post-processing part of the additive manufacturing technology, such as hole processing, grinding and polishing equipment, into the construction of the digital twin system to realize data monitoring of the entire process of part additive manufacturing technology. Summary of the invention

[0006] In view of the defects in the prior art, the purpose of the present invention is to provide a method and system for real-time monitoring and auxiliary decision-making of digital twin additive manufacturing throughout the process.

[0007] A method for real-time monitoring and auxiliary decision-making of digital twin additive manufacturing throughout the process provided by the present invention includes:

[0008] Step S1: Collecting data of the device under test;

[0009] The equipment to be tested includes a robot grinding device, a five-axis CNC machining device, and an additive printing device;

[0010] Step S2: using different types of data platforms to process the data of the device under test;

[0011] Step S3: completing data monitoring of the entire additive manufacturing process based on the processing results;

[0012] Step S4: Analyze the processing results and optimize the monitoring process.

[0013] Preferably, step S2 includes the following sub-steps:

[0014] Step S2.1: Upload the data of the device under test to the data acquisition platform;

[0015] Step S2.2: The data collection platform uploads the data of the device under test to the data governance platform based on the MQTT service;

[0016] Step S2.3: Upload the data of the additive printing device to the data management platform;

[0017] Step S2.4: After the data governance platform processes the received data, it uploads it to the hidden surface data visualization platform;

[0018] Step S2.5: Enable the digital twin platform to build a three-dimensional scene, and the hidden surface data visualization platform to build a data visualization interface, and combine the three-dimensional scene and the data visualization interface.

[0019] Preferably, the step S2.1 includes the following sub-steps:

[0020] Step S2.1.1: Establish communication between the three hardware devices of the ABB robot, Siemens PLC, and Beckhoff PLC of the robot polishing equipment, and realize real-time data collection;

[0021] Step S2.1.2: Install a camera on the five-axis CNC machining equipment to capture the main interface of the equipment, use OCR technology to extract the required data, and realize real-time data collection.

[0022] Preferably, the step S2.4 includes the following sub-steps:

[0023] Step S2.4.1: Process the data obtained by the data governance platform;

[0024] Step S2.4.2: Store the processed data in the MYSQL database deployed on the server;

[0025] Step S2.4.3: transmitting the processed data to the hidden surface data visualization platform;

[0026] Step S2.4.4: Select an appropriate chart type for data display according to the acquired real-time data type of the device.

[0027] Preferably, the step S2.5 includes the following sub-steps:

[0028] Step S2.5.1: Obtain the three-dimensional model of the robot grinding equipment, the five-axis CNC machining equipment, and the additive printing equipment by means of point cloud rapid modeling;

[0029] Step S2.5.2: Place the three-dimensional model into the digital twin platform to build a three-dimensional scene;

[0030] Step S2.5.3: Integrate the three-dimensional scene in the digital twin platform with the electronic signboard of the hidden surface data visualization platform to realize an interactive digital twin system.

[0031] A system for real-time monitoring and decision-making assistance of digital twin additive manufacturing throughout the process provided by the present invention includes:

[0032] Module M1: collect data of the device under test;

[0033] The equipment to be tested includes a robot grinding device, a five-axis CNC machining device, and an additive printing device;

[0034] Module M2: Use different types of data platforms to process the data of the device under test;

[0035] Module M3: Complete data monitoring of the entire additive manufacturing process based on the processing results;

[0036] Module M4: Analyze the processing results and optimize the monitoring process.

[0037] Preferably, the module M2 includes the following submodules:

[0038] Module M2.1: Upload the data of the device under test to the data acquisition platform;

[0039] Module M2.2: The data collection platform uploads the data of the device under test to the data governance platform based on the MQTT service;

[0040] Module M2.3: Upload the data of the additive printing equipment to the data management platform;

[0041] Module M2.4: After the data governance platform processes the received data, it uploads it to the hidden data visualization platform;

[0042] Module M2.5: Enable the digital twin platform to build a three-dimensional scene, the hidden surface data visualization platform to build a data visualization interface, and combine the three-dimensional scene and the data visualization interface.

[0043] Preferably, the module M2.1 includes the following submodules:

[0044] Module M2.1.1: Establish communication between the three hardware devices of the robot polishing equipment, namely the ABB robot, Siemens PLC and Beckhoff PLC, and realize real-time data collection;

[0045] Module M2.1.2: Install a camera on the five-axis CNC machining equipment to capture the main interface of the equipment, use OCR technology to extract the required data, and realize real-time data collection.

[0046] Preferably, the module M2.4 includes the following submodules:

[0047] Module M2.4.1: Process the data obtained by the data governance platform;

[0048] Module M2.4.2: Store the processed data in the MYSQL database deployed on the server;

[0049] Module M2.4.3: Transmit the processed data to the hidden surface data visualization platform;

[0050] Module M2.4.4: Select appropriate chart types for data display based on the real-time data type obtained from the device.

[0051] Preferably, the module M2.5 includes the following submodules:

[0052] Module M2.5.1: Obtain three-dimensional models of robot grinding equipment, five-axis CNC machining equipment, and additive printing equipment through point cloud rapid modeling;

[0053] Module M2.5.2: Place the 3D model into the digital twin platform to build a 3D scene;

[0054] Module M2.5.3: Integrate the three-dimensional scene in the digital twin platform with the electronic signboard of the invisible surface data visualization platform to realize an interactive digital twin system.

[0055] Compared with the prior art, the present invention has the following beneficial effects:

[0056] 1. The present invention forms a digital twin system for the entire process of digital twin additive manufacturing through rapid modeling, data collection and fusion, based on intelligent management and control and multi-system production data fusion, and realizes the functions of equipment information viewing, equipment status monitoring, equipment abnormality alarm, and equipment decision assistance for the three stages of printing, machining, and grinding and polishing, and has good practicality.

[0057] 2. The system provided by the present invention also integrates industrial Internet of Things technologies such as video recording, 3D scanning, and equipment monitoring, further enhancing the image reproduction, global perception, and intelligent management and control capabilities of additive manufacturing equipment.

[0058] 3. The present invention solves the problems of missing real-time operation data of each device, inability to trace device data, and difficulty in monitoring device status by realizing real-time data collection of additive manufacturing equipment and data storage in MYSQL database, and realizes the traceability of problems in the processing process of additive manufacturing equipment.

[0059] 4. The present invention solves the problem of the inability to uniformly manage various devices and the difficulty in finding real-time data by constructing a digital twin system for additive equipment. Through data-driven, it realizes the functions of viewing equipment information, implementing monitoring, alarm information, and assisting decision-making within a single system.

[0060] Other beneficial effects of the present invention will be explained in the specific implementation manner through the introduction of specific technical features and technical solutions. Through the introduction of these technical features and technical solutions, those skilled in the art should be able to understand the beneficial technical effects brought about by the technical features and technical solutions. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings:

[0062] Figure 1 The present invention is a flow chart of the method.

[0063] Figure 2 It is a system structure diagram of the present invention.

[0064] Figure 3 Schematic diagram of a flow chart of an embodiment of the present invention. DETAILED DESCRIPTION

[0065] The present invention is described in detail below in conjunction with specific embodiments. The following embodiments will help those skilled in the art to further understand the present invention, but are not intended to limit the present invention in any form. It should be noted that, for those of ordinary skill in the art, several changes and improvements can also be made without departing from the concept of the present invention. These all belong to the protection scope of the present invention.

[0066] The present invention forms a digital twin system for the entire process of digital twin additive manufacturing through rapid modeling, data collection and fusion, intelligent management and control, and multi-system production data fusion, and realizes the functions of equipment information viewing, equipment status monitoring, equipment abnormality alarm, and equipment decision-making assistance for the three stages of printing, machining, and grinding and polishing. The system also integrates industrial Internet of Things technologies such as video camera, 3D scanning, and equipment monitoring, further strengthening the mirror reproduction, global perception, and intelligent management and control capabilities of additive manufacturing equipment.

[0067] Reference Figure 1 and Figure 2 As shown, a method for real-time monitoring and auxiliary decision-making of digital twin additive manufacturing throughout the process includes:

[0068] Step 1: Collect the data of robot grinding equipment and five-axis CNC machining equipment during operation, and upload it to the data acquisition platform DS-DccS.

[0069] First, establish communication between the three hardware devices of the robot polishing equipment, namely the ABB robot, Siemens PLC, and Beckhoff PLC, and realize real-time data collection. Then, realize real-time data collection for the five-axis CNC machining equipment by installing a camera to shoot the main interface of the equipment and using OCR technology to extract the required data.

[0070] Step 2: Transfer the data collected in the data collection platform CS-DccS to the data governance platform DS-DaaS through the MQTT service.

[0071] Step 3: Add MQTT protocol support to the edge host software of the additive printing device to send the data in its host software to the data governance platform DS-DaaS through the MQTT protocol.

[0072] Step 4: Upload the processed data in the data governance platform DS-DaaS to the hidden surface data visualization platform DS-Interface.

[0073] Process the data obtained by the data governance platform DS-DaaS:

[0074] Clean the collected data to remove duplicate, missing, erroneous or inconsistent data to ensure data consistency and accuracy. For data with low real-time performance, adjust the data sampling frequency to ensure a balance between system data volume and real-time performance.

[0075] Convert the collected data from the original format to a standardized format, such as date conversion, unit conversion, base conversion, etc., to ensure the correct display of the data on the hidden data visualization platform DS-Interface;

[0076] Identify the collected data and distinguish outliers, and monitor the data in real time by using numerical comparison and numerical analysis. Use machine learning algorithms to mine the inherent trends and associations in the collected data, and predict the equipment operation time, maintenance cycle of equipment parts, etc.

[0077] Store the processed data in the MYSQL database deployed on the server;

[0078] The processed data is transmitted to the hidden surface data visualization platform DS-Interface.

[0079] Select appropriate chart types for data display based on the real-time data type of the device obtained;

[0080] Comparison of data from different devices, such as the operating time, power consumption, and number of completed jobs of different devices, is displayed using bar charts and pie charts;

[0081] A line graph is used to display the data change trend of the same data of the same device within a continuous time interval, such as the substrate temperature, optical system temperature, laser power, etc. of the device;

[0082] The time and content of production tasks for each equipment are displayed using a Gantt chart;

[0083] Design and implement electronic data dashboards for robot polishing equipment, five-axis CNC machining equipment, and additive printing equipment, and display the data on the electronic data dashboards.

[0084] Step 5: Combine the three-dimensional scene built by the digital twin platform DS-Insight with the data visualization interface built by the hidden surface data visualization platform DS-Interface.

[0085] Obtain 3D models of robot grinding equipment, five-axis CNC machining equipment, and additive printing equipment through point cloud rapid modeling;

[0086] Place the 3D model into the digital twin platform DS-Insight to build a 3D scene;

[0087] The three-dimensional scene in the digital twin platform DS-Insight is integrated with the electronic signboard of the hidden surface data visualization platform DS-Interface to realize an interactive digital twin system.

[0088] Further research, development and improvement will be carried out based on the actual conditions of each equipment.

[0089] The present invention forms a digital twin system for the entire process of digital twin additive manufacturing through rapid modeling, data collection and fusion, and intelligent management and control and multi-system production data fusion. It also realizes the functions of equipment information viewing, equipment status monitoring, equipment abnormality alarm, and equipment decision assistance for the three stages of printing, machining, and grinding and polishing, and has good practicality.

[0090] The present invention also provides a system for real-time monitoring and auxiliary decision-making of digital twin additive manufacturing throughout the entire process. The system for real-time monitoring and auxiliary decision-making of digital twin additive manufacturing throughout the entire process can be realized by executing the process steps of the method for real-time monitoring and auxiliary decision-making of digital twin additive manufacturing throughout the entire process. That is, technical personnel in this field can understand the method for real-time monitoring and auxiliary decision-making of digital twin additive manufacturing throughout the entire process as an optimal implementation mode of the system for real-time monitoring and auxiliary decision-making of digital twin additive manufacturing throughout the entire process.

[0091] Specifically, a system for real-time monitoring and decision-making support of digital twin additive manufacturing includes:

[0092] Module M1: collect data of the device under test;

[0093] The equipment to be tested includes a robot grinding device, a five-axis CNC machining device, and an additive printing device;

[0094] Module M2: Use different types of data platforms to process the data of the device under test;

[0095] Module M3: Complete data monitoring of the entire additive manufacturing process based on the processing results;

[0096] Module M4: Analyze the processing results and optimize the monitoring process.

[0097] The module M2 includes the following submodules:

[0098] Module M2.1: Upload the data of the device under test to the data acquisition platform;

[0099] Module M2.2: The data collection platform uploads the data of the device under test to the data governance platform based on the MQTT service;

[0100] Module M2.3: Upload the data of the additive printing equipment to the data management platform;

[0101] Module M2.4: After the data governance platform processes the received data, it uploads it to the hidden data visualization platform;

[0102] Module M2.5: Enable the digital twin platform to build a three-dimensional scene, the hidden surface data visualization platform to build a data visualization interface, and combine the three-dimensional scene and the data visualization interface.

[0103] The module M2.1 includes the following submodules:

[0104] Module M2.1.1: Establish communication between the three hardware devices of the robot polishing equipment, namely the ABB robot, Siemens PLC and Beckhoff PLC, and realize real-time data collection;

[0105] Module M2.1.2: Install a camera on the five-axis CNC machining equipment to capture the main interface of the equipment, use OCR technology to extract the required data, and realize real-time data collection.

[0106] The module M2.4 includes the following submodules:

[0107] Module M2.4.1: Process the data obtained by the data governance platform;

[0108] Module M2.4.2: Store the processed data in the MYSQL database deployed on the server;

[0109] Module M2.4.3: Transmit the processed data to the hidden surface data visualization platform;

[0110] Module M2.4.4: Select appropriate chart types for data display based on the real-time data types obtained from the equipment.

[0111] The module M2.5 includes the following submodules:

[0112] Module M2.5.1: Obtain three-dimensional models of robot grinding equipment, five-axis CNC machining equipment, and additive printing equipment through point cloud rapid modeling;

[0113] Module M2.5.2: Place the 3D model into the digital twin platform to build a 3D scene;

[0114] Module M2.5.3: Integrate the three-dimensional scene in the digital twin platform with the electronic signboard of the invisible surface data visualization platform to realize an interactive digital twin system.

[0115] Those skilled in the art know that, in addition to realizing the system and its various devices, modules, and units provided by the present invention in a purely computer-readable program code, it is entirely possible to realize the same functions in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers by logically programming the method steps. Therefore, the system and its various devices, modules, and units provided by the present invention can be considered as a hardware component, and the devices, modules, and units included therein for realizing various functions can also be regarded as structures within the hardware component; the devices, modules, and units for realizing various functions can also be regarded as both software modules for realizing the method and structures within the hardware component.

[0116] In the description of the present application, it should be understood that the terms "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0117] The above describes the specific embodiments of the present invention. It should be understood that the present invention is not limited to the above specific embodiments, and those skilled in the art can make various changes or modifications within the scope of the claims, which does not affect the essence of the present invention. In the absence of conflict, the embodiments of the present application and the features in the embodiments can be combined with each other arbitrarily.

Claims

1. A method for real-time monitoring and decision-making assistance of digital twin additive manufacturing, characterized in that: include: Step S1: Collecting data of the device under test; The equipment to be tested includes a robot grinding device, a five-axis CNC machining device, and an additive printing device; Step S2: using different types of data platforms to process the data of the device under test; Step S3: completing data monitoring of the entire additive manufacturing process based on the processing results; Step S4: Analyze the processing results and optimize the monitoring process.

2. The method for real-time monitoring and decision-making assistance of digital twin additive manufacturing according to claim 1 is characterized in that: The step S2 comprises the following sub-steps: Step S2.1: Upload the data of the device under test to the data acquisition platform; Step S2.2: The data collection platform uploads the data of the device under test to the data governance platform based on the MQTT service; Step S2.3: Upload the data of the additive printing device to the data management platform; Step S2.4: After the data governance platform processes the received data, it uploads it to the hidden surface data visualization platform; Step S2.5: Enable the digital twin platform to build a three-dimensional scene, and the hidden surface data visualization platform to build a data visualization interface, and combine the three-dimensional scene and the data visualization interface.

3. The method for real-time monitoring and decision-making assistance of digital twin additive manufacturing according to claim 2 is characterized in that: The step S2.1 comprises the following sub-steps: Step S2.1.1: Establish communication between the three hardware devices of the ABB robot, Siemens PLC, and Beckhoff PLC of the robot polishing equipment, and realize real-time data collection; Step S2.1.2: Install a camera on the five-axis CNC machining equipment to capture the main interface of the equipment, use OCR technology to extract the required data, and realize real-time data collection.

4. The method for real-time monitoring and decision-making assistance of digital twin additive manufacturing according to claim 2 is characterized in that: The step S2.4 comprises the following sub-steps: Step S2.4.1: Process the data obtained by the data governance platform; Step S2.4.2: Store the processed data in the MYSQL database deployed on the server; Step S2.4.3: transmitting the processed data to the hidden surface data visualization platform; Step S2.4.4: Select an appropriate chart type for data display according to the acquired real-time data type of the device.

5. The method for real-time monitoring and decision-making assistance of digital twin additive manufacturing according to claim 2 is characterized in that: The step S2.5 includes the following sub-steps: Step S2.5.1: Obtain the three-dimensional model of the robot grinding equipment, the five-axis CNC machining equipment, and the additive printing equipment by means of point cloud rapid modeling; Step S2.5.2: Place the three-dimensional model into the digital twin platform to build a three-dimensional scene; Step S2.5.3: Integrate the three-dimensional scene in the digital twin platform with the electronic signboard of the hidden surface data visualization platform to realize an interactive digital twin system.

6. A system for real-time monitoring and decision-making support of digital twin additive manufacturing, characterized in that: include: Module M1: collect data of the device under test; The equipment to be tested includes a robot grinding device, a five-axis CNC machining device, and an additive printing device; Module M2: Use different types of data platforms to process the data of the device under test; Module M3: Complete data monitoring of the entire additive manufacturing process based on the processing results; Module M4: Analyze the processing results and optimize the monitoring process.

7. The system for real-time monitoring and decision-making support of digital twin additive manufacturing according to claim 6, characterized in that: The module M2 Includes the following submodules: Module M2.1: Upload the data of the device under test to the data acquisition platform; Module M2.2: The data collection platform uploads the data of the device under test to the data governance platform based on the MQTT service; Module M2.3: Upload the data of the additive printing equipment to the data management platform; Module M2.4: After the data governance platform processes the received data, it uploads it to the hidden data visualization platform; Module M2.5: Enable the digital twin platform to build a three-dimensional scene, the hidden surface data visualization platform to build a data visualization interface, and combine the three-dimensional scene and the data visualization interface.

8. The system for real-time monitoring and decision-making support of digital twin additive manufacturing according to claim 7, characterized in that: The module M2.1 includes the following submodules: Module M2.1.1: Establish communication between the three hardware devices of the robot polishing equipment, namely the ABB robot, Siemens PLC and Beckhoff PLC, and realize real-time data collection; Module M2.1.2: Install a camera on the five-axis CNC machining equipment to capture the main interface of the equipment, use OCR technology to extract the required data, and realize real-time data collection.

9. The system for real-time monitoring and decision-making support of digital twin additive manufacturing according to claim 7, characterized in that: The module M2.4 includes the following submodules: Module M2.4.1: Process the data obtained by the data governance platform; Module M2.4.2: Store the processed data in the MYSQL database deployed on the server; Module M2.4.3: Transmit the processed data to the hidden surface data visualization platform; Module M2.4.4: Select appropriate chart types for data display based on the real-time data type obtained from the device.

10. A system for real-time monitoring and decision-making support of digital twin additive manufacturing according to claim 7, characterized in that: The module M2.5 includes the following submodules: Module M2.5.1: Obtain three-dimensional models of robot grinding equipment, five-axis CNC machining equipment, and additive printing equipment through point cloud rapid modeling; Module M2.5.2: Place the 3D model into the digital twin platform to build a 3D scene; Module M2.5.3: Integrate the three-dimensional scene in the digital twin platform with the electronic signboard of the invisible surface data visualization platform to realize an interactive digital twin system.

Images