Online monitoring system for electric arc additive and subtractive composite manufacturing process driven by digital twinning

Through the digital twin-driven arc accumulative material composite manufacturing online monitoring system, the problem of single data acquisition dimensions and lack of real-time monitoring in arc accumulative material manufacturing is solved, and comprehensive monitoring and real-time optimization of the arc accumulative material manufacturing process is achieved. Improve product quality and manufacturing efficiency.

CN118940439AInactive Publication Date: 2024-11-12NANJING UNIV OF SCI & TECH

Patent Information

Application Number
CN202411419076.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-10-12
Publication Date
2024-11-12
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The data acquisition dimensions in the existing arc addition and subtractive material manufacturing technology are single, and the lack of real-time monitoring and feedback mechanisms have led to the inability to comprehensively monitor the changes in key parameters in the manufacturing process, and it is difficult to achieve real-time optimization and intelligent regulation, resulting in unstable product quality.

Method used

The arc addition and feedback module is driven by digital twins, and the arc addition and reduction material composite manufacturing process is realized through multi-dimensional data acquisition module, online analysis and prediction module, intelligent optimization module, real-time monitoring and feedback module and human-computer interaction module. Comprehensive monitoring and real-time adjustment of the manufacturing process, and build a predictive mathematical correlation model for optimization of processing parameters.

Benefits of technology

It realizes multi-dimensional data acquisition and real-time monitoring of the arc-added and reduced material manufacturing process, improves product forming quality and processing efficiency, and meets the requirements of modern manufacturing for high precision, high efficiency and intelligence.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118940439A_ABST
    Figure CN118940439A_ABST
Patent Text Reader

Abstract

The invention belongs to the field of additive and subtractive manufacturing technologies, digital twinning and computer aided design, and particularly relates to a digital twinning driven arc additive and subtractive composite manufacturing process online monitoring system which comprises a multi-dimensional data acquisition module, a data storage and management module, an online analysis and prediction module and an intelligent optimization module. A real-time monitoring and feedback module; and a man-machine interaction module. The multi-dimensional data acquisition module is arranged on a physical machine tool, and the data storage and management module, the online analysis and prediction module, the intelligent optimization module, the real-time detection and feedback module and the man-machine interaction module are arranged at a PC terminal. Compared with the prior art, the digital twinning technology and the computer aided design are combined, various data in the electric arc additive and subtractive manufacturing process are comprehensively reflected, additive and subtractive manufacturing parameters are adjusted in real time, intelligent optimization of the manufacturing process is achieved, and the product quality and the production efficiency are improved; and the requirements of the modern manufacturing industry on high precision, high efficiency and intelligence are met.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention belongs to the fields of additive and subtractive composite manufacturing technology, digital twins, and computer-aided design, and in particular, it is an online monitoring system for an electric arc additive and subtractive composite manufacturing process driven by a digital twin. Background Technology

[0002] Additive manufacturing technology plays a crucial role in constructing geometrically and materially complex parts, enabling the rapid deposition of complex shapes and multiple materials. Compared to laser and electron beam additive manufacturing, arc additive manufacturing offers advantages such as high forming efficiency, high material utilization, less pollution, and lower equipment costs. However, most parts manufactured using this technology suffer from insufficient precision and surface quality, often failing to meet the requirements for high accuracy and surface quality. CNC machining, on the other hand, boasts advantages such as high precision and excellent surface quality, achieving high-precision and high-quality surfaces through precision cutting and machining processes, thus overcoming the aforementioned limitations of arc additive manufacturing. Therefore, arc additive-subtractive composite manufacturing technology, which combines the rapid prototyping capabilities of arc additive manufacturing with the high-precision machining capabilities of CNC machining, can fully leverage the advantages of both, significantly improving the overall quality and manufacturing efficiency of parts, and possesses broad application prospects.

[0003] While some existing electric arc subtractive manufacturing systems can manufacture complex parts, they still face challenges in data acquisition, process monitoring, and intelligent control, including limitations such as single-dimensional data acquisition, lack of real-time monitoring, and insufficient feedback mechanisms. They cannot comprehensively monitor various parameters during the subtractive manufacturing process (such as current, voltage, temperature, acceleration, acoustic waves, cutting force, and molten pool temperature distribution), lacking comprehensive monitoring of the process. They cannot promptly capture and adjust changes in key parameters during electric arc subtractive manufacturing, making real-time optimization and intelligent control difficult. Defects are often only discovered after the fact, leading to unstable product quality and failing to meet the high precision, high efficiency, and intelligent requirements of modern manufacturing.

[0004] Digital twin technology is a computer-aided design technology that integrates multiple technologies. It uses computer software to create a digital mirror image of a physical object or system to simulate and predict the real world. Combining sensors and data acquisition systems, digital twin technology enables real-time monitoring of various parameters in the additive and subtractive manufacturing process. Through synchronous interaction between the virtual model and the physical system, it can promptly report any anomalies in the manufacturing process. Furthermore, through real-time data analysis and model prediction, it can dynamically adjust manufacturing parameters, achieving intelligent control and optimization of the manufacturing process.

[0005] Existing digital twin applications are often limited to single-dimensional data monitoring and lack real-time feedback and dynamic adjustment capabilities. Currently, digital twins have not been applied to online monitoring of metal additive and subtractive manufacturing processes, especially digital twin-driven online monitoring systems for arc-based additive and subtractive manufacturing. Therefore, there is an urgent need to develop a digital twin-driven online monitoring system and method for arc-based additive and subtractive manufacturing processes. Summary of the Invention

[0006] This invention relates to an online monitoring system for the arc-assisted subtractive manufacturing process driven by a digital twin. It aims to solve the problems of single data acquisition dimensions and lack of real-time monitoring and feedback mechanisms in existing arc-assisted subtractive manufacturing technologies. The system provides a comprehensive system that can reflect various data in the arc-assisted subtractive manufacturing process, adjust the processing parameters in real time, and achieve intelligent optimization of the manufacturing process, thereby improving product quality and production efficiency and meeting the requirements of modern manufacturing for high precision, high efficiency, and intelligence.

[0007] The technical solution provided by this invention is: an online monitoring system for an arc-driven additive-subtractive composite manufacturing process driven by a digital twin, the online monitoring system comprising:

[0008] The multi-dimensional data acquisition module is installed on a physical machine tool to collect various data during the additive and subtractive manufacturing process;

[0009] The data storage and management module stores the data information collected in real time by the multi-dimensional data acquisition module as historical data and transmits the real-time data information to the online analysis and prediction module.

[0010] The online analysis and prediction module processes and analyzes the received historical data, constructs a predictive mathematical correlation model related to the quality of arc additive manufacturing, and constructs a predictive mathematical correlation model related to the degree of tool wear; through the predictive mathematical correlation model, it analyzes real-time data to obtain prediction results; and compares the three-dimensional contour dimensions of the formed component with the design contour dimensions through point cloud alignment and geometric comparison algorithms.

[0011] The intelligent optimization module trains and optimizes the predictive mathematical correlation model related to the quality of electric arc additive manufacturing, which is constructed in the online analysis and prediction module based on historical data, to obtain the optimized predictive mathematical correlation model related to the quality of electric arc additive manufacturing. By setting the forming quality target, the model is used to predict the processing parameters corresponding to the processing end of electric arc additive manufacturing.

[0012] The real-time monitoring and feedback module displays the data collected by the multi-dimensional data acquisition module in real time, and judges the prediction results of the prediction mathematical correlation model in the online analysis and prediction module and the intelligent optimization module. Based on the judgment results, it gives decisions on adjusting additive processing parameters and whether to change tools.

[0013] The human-computer interaction module needs to establish a virtual machine tool based on the physical machine tool, the actual environment, and behavioral logic; the virtual machine tool will feed back the decisions from the real-time monitoring and feedback module to the physical machine tool;

[0014] The data storage and management module, online analysis and prediction module, intelligent optimization module, real-time monitoring and feedback module, and human-computer interaction module are located on the PC.

[0015] Compared with the prior art, the significant advantages of this invention are:

[0016] (1) The multi-dimensional data acquisition module of the present invention realizes comprehensive and real-time acquisition of current, voltage, cutting force, acceleration, acoustic signal, additive forming size, molten pool temperature distribution and machine tool information data of the entire process of addition and subtraction in the electric arc addition and subtraction process. It solves the problems of single data acquisition dimension, lack of comprehensive monitoring of the addition and subtraction manufacturing process and inability to capture changes in key parameters in the electric arc addition and subtraction manufacturing process in the existing electric arc addition and subtraction manufacturing technology.

[0017] (2) This invention processes and analyzes the data collected by the multi-dimensional data acquisition module through the online analysis and prediction module, constructs a predictive mathematical correlation model between various data and additive forming quality and tool wear value, and compares the three-dimensional model of the formed component collected by the three-dimensional laser contour scanner with the three-dimensional model of the target part designed by the designer through point cloud alignment and geometric comparison algorithm. Using real-time data, the additive forming quality is predicted through the predictive mathematical correlation model, the forming size of the component is compared and the tool wear is judged. This can greatly improve the forming quality and forming size accuracy of the arc additive manufacturing parts in the welding process, and effectively improve the processing efficiency of the subtractive cutting process, and ultimately improve the quality of the product.

[0018] (3) The intelligent optimization module of the present invention constructs and trains a correlation model between optimized processing parameters and additive forming quality based on historical data. By setting forming quality targets, the model is used to predict the processing parameters corresponding to the arc additive and subtractive manufacturing process. The optimization model is continuously improved and updated by accumulating and analyzing new arc additive and subtractive processing data.

[0019] (4) The real-time monitoring and feedback module of the present invention determines whether it is necessary to adjust the additive manufacturing process parameters and execute the tool change decision in the milling process based on the prediction results of the online analysis and prediction module. The module predicts the manufacturing parameters corresponding to the arc additive manufacturing process parameters and the additive forming quality correlation model of the intelligent optimization module, and feeds back the manufacturing parameters and tool change decision to the arc additive manufacturing process for real-time control. This realizes closed-loop control of the entire process of component additive and subtractive manufacturing.

[0020] (5) The human-computer interaction module of the present invention simulates the physical characteristics, process parameters and environmental conditions of the actual additive and subtractive manufacturing process in a virtual environment in real time, and constructs a virtual simulation model that is highly consistent with the actual electric arc additive and subtractive manufacturing system, so as to realize the dynamic simulation of virtual and real synchronization.

[0021] (6) This invention significantly improves the comprehensive monitoring and intelligent optimization capabilities of the electric arc additive and subtractive manufacturing process through comprehensive data acquisition and monitoring, real-time online analysis and prediction, intelligent optimization and dynamic adjustment, virtual and real synchronous simulation model and closed-loop control system, overcomes the limitations of the prior art, and improves the manufacturing efficiency and product quality of electric arc additive and subtractive materials. Attached Figure Description

[0022] Figure 1 This is a schematic diagram of the overall layout of the digital twin-driven online monitoring system for the electric arc additive and subtractive manufacturing process proposed in this invention.

[0023] Figure 2 This is a schematic diagram of the structure of the digital twin-driven online monitoring system for the electric arc additive and subtractive manufacturing process proposed in this invention.

[0024] Figure 3 This is a schematic diagram of the data acquisition process of the online monitoring system for arc-driven additive and subtractive manufacturing processes proposed in this invention.

[0025] Figure 4 This is a schematic diagram of the machine tool information acquisition process of the online monitoring system for arc-driven additive and subtractive manufacturing processes proposed in this invention.

[0026] Figure 5 This is a schematic diagram of the online analysis and prediction module of the online monitoring system for arc-driven additive and subtractive manufacturing processes proposed in this invention.

[0027] Figure 6 This is a schematic diagram of the intelligent optimization module of an online monitoring system for arc additive and subtractive manufacturing processes driven by digital twins, as proposed in this invention.

[0028] Figure 7 This is a schematic diagram of the real-time monitoring and feedback module of an online monitoring system for arc-driven additive and subtractive manufacturing processes proposed in this invention.

[0029] Figure 8 This is a schematic diagram of the human-machine interaction module of the online monitoring system for arc-driven additive and subtractive manufacturing processes proposed in this invention, which is driven by a digital twin.

[0030] In the diagram: 1. Acoustic sensor; 2. Machine tool frame; 3. Accelerometer; 4. Spindle; 5. Cutting force sensor; 6. Current sensor; 7. Voltage sensor; 8. 3D laser profile scanner; 9. Ultrasonic detector; 10. Infrared thermal imager; 11. Data acquisition card; 12. PC terminal; 13. Ultra-depth-of-field microscope; 14. Machining area. Detailed Implementation

[0031] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0032] like Figure 1 As shown, the digital twin-driven online monitoring system for arc-assisted additive and subtractive manufacturing processes (hereinafter referred to as the digital twin online monitoring system) includes a multi-dimensional data acquisition module, a data storage and management module, an online analysis and prediction module, an intelligent optimization module, a real-time detection and feedback module, and a human-computer interaction module.

[0033] The digital twin online monitoring system, based on a physical machine tool, incorporates a multi-dimensional data acquisition module. This module collects various data from the additive manufacturing process and transmits them to a data storage and management module via a data acquisition card. The data storage and management module stores the real-time data collected by the multi-dimensional data acquisition module as historical data and transmits the real-time data to an online analysis and prediction module. The online analysis and prediction module preprocesses, extracts features, and analyzes the received historical data to construct predictive mathematical correlation models related to the quality of arc additive forming and to tool wear. It then uses real-time data to obtain prediction results through these models and compares the three-dimensional contour dimensions of the formed component with the designed contour dimensions in real time. The intelligent optimization module trains and optimizes the predictive mathematical correlation models related to the quality of arc additive forming constructed in the online analysis and prediction module based on historical data. It sets forming quality targets and obtains the additive processing parameters corresponding to the arc additive manufacturing process through the predictive mathematical correlation models. The real-time monitoring and feedback module displays the data collected by the multi-dimensional data acquisition module in real time, and judges the prediction results of the predictive mathematical correlation model in the online analysis and prediction module. Based on the judgment results, it provides decisions on adjusting additive manufacturing process parameters and whether to change tools. The human-machine interaction module establishes a virtual machine tool based on the physical machine tool, the actual environment, and behavioral logic; the virtual machine tool feeds back the decisions from the real-time monitoring and feedback module to the physical machine tool, such as... Figure 2 As shown.

[0034] The multi-dimensional data acquisition module includes: a multi-dimensional sensor module, a three-dimensional laser contour scanner 8, an ultrasonic detector 9, an infrared thermal imager 10, a data acquisition card 11, and a super depth-of-field microscope 13;

[0035] The multi-dimensional sensor module includes a current sensor 6, a voltage sensor 7, a cutting force sensor 5, an acceleration sensor 3, and an acoustic sensor 1. The current sensor 6 and voltage sensor 7 are installed on the power lines of the additive / subtractive manufacturing system to monitor and record changes in current and voltage. The cutting force sensor 5 is installed at the front end of the machine tool spindle 4 to monitor the cutting force generated during the subtractive cutting process. The acceleration sensor 3 is installed on the machine tool spindle 4 to monitor changes in the spindle 4's acceleration. The acoustic sensor 1 is fixed to the machine tool frame 2 to capture acoustic signals during the cutting process. By acquiring current, voltage, cutting force, acceleration, and acoustic data in real time during the arc additive / subtractive manufacturing process through the multi-dimensional sensor module, the system comprehensively monitors changes in various parameters during the manufacturing process and transmits the data to the data storage and management module, providing fundamental data support for optimizing the arc additive / subtractive manufacturing process.

[0036] The three-dimensional laser profile scanner 8 is installed on the side above the machine tool processing area 14 and is used to scan and measure the forming dimensions of arc additive welding in real time to generate a three-dimensional profile map.

[0037] The ultrasonic testing instrument 9 is used to detect defects such as pores, cracks and material delamination inside the additively formed component, thereby determining the forming quality of the additively formed component.

[0038] The infrared thermal imager 10 is installed above and to the side of the machining area 14 of the machine tool to collect real-time visual images of the molten pool and its temperature distribution, monitoring the heat distribution and cooling rate during the arc additive welding process. The ultra-depth-of-field microscope 13 is used to measure the wear of the cutting tool's flank face. It collects tool feed data through a multi-dimensional data acquisition module, measuring the flank face wear value of the cutting tool at regular intervals until the tool reaches a state of rapid wear, at which point the tool is replaced and the wear data is recorded.

[0039] The data acquisition card 11 connects the multi-dimensional sensor module and the data storage and management module, and is used to transmit the acquired data information to the data storage and management module.

[0040] The PC terminal 12 is equipped with a data storage and management module, an online analysis and prediction module, an intelligent optimization module, a real-time monitoring and feedback module, and a human-computer interaction module; and is connected to a 3D laser contour scanner 8, an infrared thermal imager 10, an ultra-depth-of-field microscope 13, and a data acquisition card 11.

[0041] The data storage and management module is used to store historical data from the multi-dimensional data acquisition module at the machining site during the additive and subtractive manufacturing process, as well as data stored internally by the machine tool. Furthermore, it can transmit data acquired by the multi-dimensional data acquisition module to the online analysis and prediction module in real time.

[0042] The data storage and management module stores the data collected by the multi-dimensional data acquisition module as historical data. The data acquisition card acquisition process is as follows: Figure 3 As shown:

[0043] (1) Data is collected through the multi-dimensional data acquisition module and the data collected by the sensor is received in real time through the multi-channel data acquisition card 11.

[0044] (2) Initialize the data acquisition card through the PC, including initializing parameters such as the sampling frequency of the acquisition card. Determine the working status of the data acquisition card based on the status information returned by the data acquisition card. If the working status is correct, continue to the next step; otherwise, return to initialize the data acquisition card.

[0045] (3) The data packet of the acquisition command is sent through the PC. After the acquisition card receives the data, it sends the acquired data to the PC in 16-bit data packet. After receiving the data, the PC parses and encapsulates it into an object and puts it into a queue so that it can be stored in the database later and saved as historical data.

[0046] Machine tool information collection process as follows Figure 4 As shown, register an OPC-UA server and establish a TCP / IP network layer communication connection through the Socket interface (network programming interface) to read internal machine tool information data. The internal machine tool information data includes machine tool system information, working mode, NC (standby) status, alarm information, machine coordinates, absolute coordinates, relative coordinates, remaining coordinates, feed rate, spindle speed, cutting time, etc.

[0047] like Figure 5 As shown, the online analysis and prediction module is used to preprocess, extract and analyze the received historical data, construct a predictive mathematical correlation model related to the quality of arc additive manufacturing, and construct a predictive mathematical correlation model related to the degree of tool wear. Then, the received real-time data is used to predict the forming quality of arc additive components and the degree of tool wear through the predictive mathematical correlation model.

[0048] In arc additive manufacturing, changes in arc voltage and arc current affect the arc force acting on the transition droplet, thereby altering the droplet size and droplet transition frequency, ultimately influencing the droplet deposition process and impacting the component forming quality. In arc subtractive manufacturing, collisions and friction between the cutting tool and the workpiece cause tool wear. The cutting edge of the tool has a significant impact on the surface quality of the milled material; excessively worn tools are more likely to cause surface deterioration during milling, leading to burrs, micro-defects, etc.

[0049] Therefore, specifically, during the arc additive manufacturing process, the online analysis and prediction module preprocesses, extracts features, and analyzes various historical data collected by the multi-dimensional sensor module, infrared thermal imager, and ultrasonic detector 9 to identify key parameters and trends in the arc additive manufacturing process. Through machine learning methods, it constructs a predictive mathematical correlation model between current, voltage, molten pool temperature, molten pool image, and arc additive forming quality. Based on this model, it analyzes the real-time collected data to predict the surface quality of the arc additive formed component. Furthermore, a 3D laser contour scanner is used to acquire the 3D contour of the arc additive formed component. Point cloud alignment and geometric comparison algorithms are used to compare the 3D contour dimensions of the arc additive formed component with the design contour dimensions. Errors are detected and timely adjustments are made to ensure that the formed component contour matches the design contour.

[0050] Therefore, specifically, during the arc subtractive machining (i.e., milling) process, the online analysis and prediction module preprocesses, extracts features, and analyzes historical data of tool cutting force, spindle acceleration, acoustic signals, and tool wear data measured by ultra-depth-of-field microscopes collected by the multi-dimensional sensor module. Through deep learning methods, it then constructs a predictive mathematical correlation model relating tool cutting force, spindle acceleration, acoustic signals, and tool wear degree. Based on the predictive mathematical correlation model, it analyzes the real-time collected data to predict the tool wear value.

[0051] like Figure 6 As shown, the intelligent optimization module trains and optimizes the predictive mathematical correlation model related to the quality of arc additive manufacturing, constructed in the online analysis and prediction module, based on historical data. This results in an optimized predictive mathematical correlation model for arc additive manufacturing quality. By setting a forming quality target, this model predicts the processing parameters corresponding to the arc additive manufacturing process. Through continuous accumulation and analysis of new arc additive manufacturing data, the production results are evaluated, and the optimization model is continuously improved and updated.

[0052] The training and optimization steps for the predictive mathematical correlation model are as follows:

[0053] (1) Extract historical data from the data storage and management module and preprocess the data. Extract historical data of arc additive manufacturing current, voltage and forming quality stored in the data storage and management module from the database, and clean the data to remove noise data and outliers. Normalize data of different magnitudes to the same scale to avoid large-scale data dominating model training and extract key features through signal processing.

[0054] (2) Establish the relationship between processing parameters and the forming quality of additive components using a deep learning model. By defining a loss function suitable for regression or classification tasks, the gradient descent method is used to minimize the loss function. In each iteration, the weight parameters of the model are adjusted according to the loss value. The mini-batch gradient descent method is used to train the process parameters and forming quality data in batches. At the same time, by dividing the training set and the validation set, the validation set is used regularly to test the performance of the model, ensuring that the model can effectively learn the relationship between process parameters and forming quality, and improving its generalization ability by preventing overfitting.

[0055] (3) Adjust the parameters that need to be set before training the model by optimizing the hyperparameters.

[0056] (4) After the model training is completed, the model is evaluated and tuned using the validation set. K-fold cross-validation is used to reduce bias caused by insufficient data, and evaluation metrics are used to detect model performance. L1 regularization is used to reduce model complexity, and early stopping is used to stop training when the validation set error no longer decreases. Based on the feedback of model performance, parameters and training process are gradually tuned to improve the model's generalization ability and prediction accuracy.

[0057] The real-time monitoring and feedback module displays the data collected by the multi-dimensional data acquisition module in real time, and judges the prediction results of the prediction mathematical correlation model in the online analysis and prediction module and the intelligent optimization module. Based on the judgment results, it provides decisions on adjusting additive processing parameters and whether to change tools for milling.

[0058] Data collected by multi-dimensional sensor modules, 3D laser contour scanners, and infrared thermal imagers is presented in the form of charts, images, and alarms through data visualization tools. This allows for real-time display of the changing trends of various additive and subtractive manufacturing data during the arc additive and subtractive manufacturing process, providing comprehensive monitoring of the entire process.

[0059] like Figure 7 As shown, the specific construction method of the real-time monitoring and feedback module is as follows;

[0060] (1) In Visual Studio, the current, voltage, cutting force, acceleration and acoustic signals in the electric arc additive and subtractive manufacturing process are displayed in real time in the form of charts using the Chart control;

[0061] (2) Set thresholds for various data. If a certain data in the electric arc additive and subtractive manufacturing process exceeds the set threshold, the operator will be promptly alerted through graphical and audio warnings.

[0062] (3) Based on the analysis and prediction results of the online analysis and prediction module, make a judgment and, based on the judgment results, give the decision on setting and adjusting the parameters of electric arc additive manufacturing and the decision on whether to change the tool in subtractive manufacturing.

[0063] like Figure 8 As shown, this is the human-computer interaction module. A virtual machine tool is established based on the physical machine tool, the actual environment, and behavioral logic; the virtual machine tool feeds back the decisions from the real-time monitoring and feedback module to the physical machine tool.

[0064] Specifically, a machine tool digital space is constructed through geometric modeling, scene building, and behavioral logic modeling. Using computer-aided design tools, a 3D model is drawn in UG NX software according to the physical machine tool's dimensions and exported as an STL file. This file is then imported into 3ds Max software for rendering. The rendered FBX file is then exported to Unity3D, where the virtual space is arranged and its functions are designed in conjunction with the actual scene, completing scene building. Real-time data acquisition from a multi-dimensional data acquisition module and the machine tool's OPC-UA server is used to bind and associate model variables and preset behavioral actions, establishing the virtual machine tool's behavioral logic. This determines the specific behaviors and logical relationships of the model's movement in the virtual space, completing the mapping of the virtual space and establishing the virtual machine tool. This achieves dynamic simulation of the virtual machine tool and the physical machine tool in sync.

[0065] Simultaneously, based on the machining process parameters obtained from the intelligent optimization module, adjustment instructions are generated through the PLC and RTLinux system to adjust the machining process parameters of the physical machine tool.

[0066] Furthermore, the status data corresponding to each component of the machine tool are visualized in the form of charts on the human-machine interface, establishing a graphical human-machine interface. Control and operation elements are added to the user interface, and input devices are used to interact with the virtual model.

[0067] A line monitoring method for an online monitoring system of an arc-assisted subtractive material composite manufacturing process driven by a digital twin, based on a physical arc-assisted subtractive material manufacturing machine tool, includes the following specific steps:

[0068] S1: Install and arrange the sensor, 3D laser contour scanner and infrared thermal imager in a suitable position according to the above technical solution to collect multi-dimensional data in real time during the electric arc additive and subtractive manufacturing process.

[0069] S2: The data storage and management module stores the data information collected in real time by the multi-dimensional data acquisition module as historical data and transmits the real-time data information to the online analysis and prediction module.

[0070] S3: The online analysis and prediction module preprocesses, extracts and analyzes the received historical data, and then constructs a predictive mathematical correlation model related to the quality of arc additive manufacturing and a predictive mathematical correlation model related to the degree of tool wear; it uses the received real-time data to predict the quality of arc additive manufacturing and the degree of tool wear through the predictive mathematical correlation model; and it compares the three-dimensional contour dimensions of the formed component with the design contour dimensions in real time.

[0071] S4: The intelligent optimization module trains and optimizes the predictive mathematical correlation model related to the quality of arc additive manufacturing, which is constructed in the online analysis and prediction module, based on historical data, to obtain an optimized predictive mathematical correlation model related to the quality of arc additive manufacturing. By setting the forming quality target, this model is used to predict the processing parameters corresponding to the processing end of arc additive manufacturing.

[0072] S5: The real-time monitoring and feedback module displays the data collected by the multi-dimensional data acquisition module in real time, and responds to the prediction results of the prediction mathematical correlation model in the online analysis and prediction module and the intelligent optimization module to determine whether to adjust the additive processing parameters and whether to change the tool in the milling process (subtractive process).

[0073] S6: Establish a virtual machine tool to achieve synchronous dynamic simulation between the virtual machine tool and the physical machine tool;

[0074] S6.1: Use the OPC-UA server to read machine tool data and establish a TCP / IP network layer communication connection through the Socket interface;

[0075] S6.2: Draw a 3D model in UG NX software according to the actual machine tool size scale and export it as an STL file. Then import the file into 3ds Max software for rendering.

[0076] S6.3: Then export the rendered FBX file to Unity3D, combine it with the actual scene to arrange the virtual space and design its functions, and complete the scene construction;

[0077] S6.4: Data acquired in real time through a multi-dimensional data acquisition module and machine tool communication protocol is mapped to a virtual space to form twin data. The data is bound to associated model variables and preset with behavioral actions to determine the specific behaviors and logical relationships of the model's movement in the digital space. This establishes a virtual simulation model, completes the mapping of the virtual space, and achieves dynamic simulation of the virtual machine tool and the actual machine tool in sync.

[0078] S6.5: The additive manufacturing parameters and tool change decisions that need to be adjusted in the real-time monitoring and feedback module are generated by the PLC and RTLinux system and fed back to the physical machine tool.

Claims

1. A digital twin-driven online monitoring system for arc additive and subtractive composite manufacturing processes. It is characterized in that The online monitoring system comprises: In the multi-dimensional data acquisition module, it is installed on the physical machine tool to collect various data in the additive and subtractive manufacturing process; The data storage and management module stores the data information collected in real time by the multi-dimensional data collection module as historical data and transmits the real-time collected data information to the online analysis and prediction module; The online analysis and prediction module processes and analyzes the received historical data, and then constructs a prediction mathematical correlation model related to the quality of arc additive forming, as well as a prediction mathematical correlation model related to the degree of tool wear; analyzes real-time data through the prediction mathematical correlation model to obtain prediction results; and compares the three-dimensional contour size of the formed component with the design contour size in real time through point cloud alignment and geometric comparison algorithms; An intelligent optimization module trains and optimizes the prediction mathematical association model related to the arc additive forming quality constructed in the online analysis and prediction module based on historical data, obtains an optimized prediction mathematical association model related to the arc additive forming quality, and uses the model to predict the processing parameters corresponding to the arc additive manufacturing processing end by setting the forming quality target; The real-time monitoring and feedback module displays the data collected by the multi-dimensional data acquisition module in real time, and judges the prediction results of the prediction mathematical correlation model in the online analysis and prediction module and the intelligent optimization module. Based on the judgment results, it makes decisions on adjusting the additive machining parameters and whether to change the tool; The human-machine interaction module should establish a virtual machine tool based on the physical machine tool, the actual environment, and the behavior logic; the virtual machine tool will feed back the decisions made in the real-time monitoring and feedback module to the physical machine tool; The data storage and management module, the online analysis and prediction module, the intelligent optimization module, the real-time detection and feedback module, and the human-computer interaction module are arranged on the PC side.

2. According to claim 1, the digital twin-driven arc additive and subtractive composite manufacturing process online monitoring system, It is characterized in that The multi-dimensional data acquisition module includes: a multi-dimensional sensor module, a three-dimensional laser profile scanner, an infrared thermal imager, an ultrasonic detector, an ultra-depth microscope and a data acquisition card; the multi-dimensional sensor module collects the current, voltage, cutting force, acceleration, sound wave and quality data of the additively formed component in the arc additive manufacturing process in real time, comprehensively monitors the changes of various parameters in the additive manufacturing process, and transmits the data to the data storage and management module, so as to provide basic data support for the optimization of the arc additive manufacturing process; the three-dimensional laser profile scanner is installed on the upper side of the machine tool processing area, and is used to scan and measure the arc additive welding forming size in real time to generate a three-dimensional profile map; the infrared thermal imager is installed on the upper side of the machine tool processing area, and collects the visual image of the molten pool and the temperature distribution of the molten pool in real time to monitor the heat distribution and cooling rate in the arc additive welding process; the ultrasonic detector is used to detect the pores, cracks and material delamination defects inside the additive forming structure, so as to judge the forming quality of the additive forming component; the ultra-depth microscope is used to measure the wear of the tool back face; the acquisition card is connected to the multi-dimensional sensor module and the data storage and management module, and is used to transmit the collected data information to the data storage and management module.

3. According to claim 2, the digital twin-driven arc additive and subtractive composite manufacturing process online monitoring system, It is characterized in that The multi-dimensional sensor module includes current sensors, voltage sensors, cutting force sensors, acceleration sensors and acoustic wave sensors; the current sensors and voltage sensors are installed on the power lines of the additive and subtractive systems to monitor and record the changes in current and voltage; the cutting force sensor is installed at the front end of the machine tool spindle to monitor the cutting force generated during the subtractive cutting process; the acceleration sensor is installed on the spindle of the machine tool to monitor the acceleration changes of the spindle; the acoustic wave sensor is fixed on the machine tool frame to capture the acoustic wave signals during the cutting process.

4. According to claim 2, the digital twin-driven arc additive and subtractive composite manufacturing process online monitoring system, It is characterized in that The method by which the data storage and management module stores the data collected by the multi-dimensional data collection module as historical data is as follows: Collect data through multi-dimensional data acquisition module, and receive data collected by sensors in real time through multi-channel data acquisition card; Initialize the data acquisition card through the PC, and judge the working status information of the data acquisition card according to the status information returned by the data acquisition card. If the working status information is correct, proceed to the next step, otherwise return to initialize the data acquisition card; The data packet of the acquisition command is sent through the PC. After the acquisition card receives it, the acquired data is sent to the PC in the form of a 16-bit data packet. After receiving the data, the PC parses and encapsulates it into an object and puts it into a queue so that it can be stored in the database later and saved as historical data.

5. According to claim 2, the digital twin-driven arc additive and subtractive composite manufacturing process online monitoring system, It is characterized in that During the arc additive manufacturing process, the online analysis and prediction module preprocesses, extracts features and analyzes various historical data collected by the multi-dimensional sensor module, infrared thermal imager and ultrasonic detector to identify the key parameters and change trends in the arc additive manufacturing process. Through machine learning methods, a predictive mathematical correlation model between current, voltage, molten pool temperature and molten pool image and arc additive forming quality is constructed. According to the predictive mathematical correlation model, the real-time collected data is analyzed to predict the forming surface quality of the arc additive formed component.

6. The digital twin-driven arc additive and subtractive composite manufacturing process online monitoring system according to claim 2, It is characterized in that During the arc reduction process, the online analysis and prediction module preprocesses, extracts features and analyzes the historical data of tool cutting force, spindle acceleration, acoustic wave signal and tool wear data measured by super-depth-of-field microscope. Through deep learning methods, a predictive mathematical association model related to tool cutting force, spindle acceleration, acoustic wave signal and tool wear degree is constructed. The real-time collected data is analyzed according to the predictive mathematical association model to predict the tool wear value.

7. The digital twin-driven arc additive and subtractive composite manufacturing process online monitoring system according to claim 3, It is characterized in that The specific construction method of the real-time monitoring and feedback module is: (1) In Visual Studio, the current, voltage, cutting force, acceleration, and acoustic wave signals in the arc additive manufacturing process are displayed in real time in the form of charts using the Chart control; (2) Setting thresholds for various data. If the data in the arc additive manufacturing process exceeds the set threshold, timely feedback will be given to the operator through graphical and audible warnings; (3) Make a judgment based on the analysis and prediction results of the online analysis and prediction module, and make a decision on the adjustment of arc additive machining parameter settings and whether to change the tool for subtractive machining based on the judgment results.

8. The digital twin-driven arc additive and subtractive composite manufacturing process online monitoring system according to claim 1, It is characterized in that The human-computer interaction module constructs the digital space of the machine tool through geometric modeling, scene construction and behavioral logic model; uses computer-aided design tools to draw a three-dimensional model in UG NX software according to the size ratio of the physical machine tool and export the STL format file; imports the file into 3ds Max software for rendering; then exports the rendered FBX file to Unity3D, combines the actual scene to arrange the virtual space and design the function, and completes the scene construction; Through the multi-dimensional data acquisition module and the machine tool OPC-UA server, the internal data of the machine tool collected in real time is bound to the associated model variables and preset behavior actions to establish the behavior logic of the virtual machine tool and establish the virtual machine tool; thus, the dynamic simulation of the virtual machine tool and the physical machine tool can be realized synchronously; According to the processing parameters obtained in the intelligent optimization module, adjustment instructions are generated through the PLC and RTLinux system to adjust the processing parameters of the physical machine tool.

9. An online monitoring method for an online monitoring system of arc additive and subtractive composite manufacturing process driven by digital twins, It is characterized in that An online monitoring system comprising any one of claims 1 to 8; the specific steps are: S1: Use sensors, 3D laser profile scanners and infrared thermal imagers to collect multi-dimensional data in real time during arc additive and subtractive manufacturing; S2: The data information collected in real time by the multi-dimensional data collection module is stored as historical data through the data storage and management module, and the data information collected in real time is transmitted to the online analysis and prediction module; S3: The online analysis and prediction module preprocesses, extracts features and analyzes the received historical data, and then constructs a prediction mathematical association model related to the arc additive forming quality, and a prediction mathematical association model related to the tool wear degree; using real-time data, the prediction mathematical association model predicts the additive forming quality, compares the component forming dimensions and determines the tool wear; and compares the three-dimensional contour dimensions of the formed component with the design contour dimensions in real time; S4: The prediction mathematical association model related to the arc additive forming quality constructed in the online analysis and prediction module is trained and optimized according to historical data through the intelligent optimization module to obtain the optimized prediction mathematical association model related to the arc additive forming quality, set the forming quality target, and obtain the additive processing parameters corresponding to the arc additive manufacturing processing end through the prediction mathematical association model; S5: The real-time monitoring and feedback module displays the data collected by the multi-dimensional data acquisition module in real time, and responds to the prediction results of the prediction mathematical correlation model in the online analysis and prediction module and the intelligent optimization module to determine whether to adjust the additive processing parameters and decide whether to change the tool for milling processing; S6: Establish a virtual machine tool to realize synchronous dynamic simulation of the virtual machine tool and the physical machine tool.

10. The online monitoring method of the online monitoring system of the arc additive and subtractive composite manufacturing process driven by the digital twin according to claim 9, It is characterized in that The specific steps in S6 are: S6.1: Use the OPC-UA server to read machine tool data and establish a TCP / IP network layer communication connection through the Socket interface; S6.2: Draw a 3D model in UG NX software according to the actual machine tool size ratio and export the STL format file, and import the file into 3ds Max software for rendering; S6.3: Export the rendered FBX file to Unity3D, and combine the actual scene to arrange the virtual space and design its functions to complete the scene construction; S6.4: The data collected in real time through the multi-dimensional data acquisition module and the machine tool communication protocol is mapped to the virtual space to form twin data. The data is bound to the associated model variables and the behavior actions are preset to determine the specific behavior and logical relationship of the model movement in the digital space, thereby establishing a virtual simulation model, completing the mapping of the virtual space, and realizing the dynamic simulation of the virtual machine tool and the physical machine tool in synchronization. S6.5: The additive machining parameters and tool change decisions that need to be adjusted in the real-time monitoring and feedback module are fed back to the physical machine tool through the PLC and RTLinux system to generate adjustment instructions.

Citation Information

Patent Citations

  • Additive manufacturing system forming monitoring system and method based on digital twinning

    CN114372725A

  • Additive manufacturing digital twin system construction method based on cloud service

    CN115489125A

  • Laser additive manufacturing on-line monitoring system and method for constructing digital twinborn body of component

    CN115828654A

  • Complete-cycle data management additive manufacturing process digital twin system construction method

    CN118313274A

  • Electric arc additive manufacturing digital twinning visualization method

    CN118363502A

Cited By

  • Machine tool dynamic optimization motion variable measuring device

    CN119973725A

  • A measuring device for dynamically optimizing motion variables of a machine tool

    CN119973725B

  • Aero-engine blade laser shock remanufacturing method based on digital twinning

    CN120162728A

  • Special ceramic diamond composite grinding wheel of multi-axis linkage polishing machine tool and self-adaptive control method of special ceramic diamond composite grinding wheel

    CN120503124A