Digital twin scene configuration method

Abstract

The invention discloses a digital twinning scene configuration method, and particularly relates to the field of digital twinning, and the method comprises the steps: obtaining original data through a sensor in a notebook computer processing plant; establishing a data hierarchical management architecture, dividing data into a base layer, an aggregation layer and a scene layer, and establishing a digital twinborn model in the scene layer; the digital twinborn model is optimized, so that the operation efficiency of the processing plant is the highest, and the notebook computer processing plant reaches the optimal state; the multi-source data is input into the digital twinborn model in real time, scene configuration parameters are dynamically adjusted according to data changes, the multi-dimensional and multi-level requirements of complex scenes of the processing plant are met, automatic adjustment and optimal configuration of the notebook computer processing plant in a variable environment are achieved, and the management efficiency of the processing plant is improved.

Description

Technical Field

[0001] The present invention relates to the field of digital twin technology, and more specifically, to a digital twin scene configuration method. Background Art

[0002] During the configuration process of laptop processing plant scenarios, existing digital twin technology usually needs to process a large amount of data obtained from sensors and devices. When these data are processed in real time, the inconsistent format and low data flow efficiency lead to complex configuration process and response delay, which cannot meet the multi-dimensional and multi-level requirements of complex processing plant scenarios. In addition, existing technologies are difficult to automatically adjust and optimize configurations in a changing environment, affecting the efficiency of laptop processing plant management.

[0003] In order to solve the above problems, a technical solution is now provided. Summary of the invention

[0004] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a digital twin scene configuration method, which obtains raw data through sensors in a laptop computer processing plant, establishes a data hierarchical management architecture, divides the data into a basic layer, an aggregation layer and a scene layer, and establishes a digital twin model in the scene layer. Then, by optimizing the digital twin model, the operating efficiency of the processing plant is maximized and the laptop computer processing plant reaches the optimal state. Multi-source data is input into the digital twin model in real time, and the scene configuration parameters are dynamically adjusted according to data changes to solve the problems raised in the above-mentioned background technology.

[0005] In order to achieve the above object, the present invention provides the following technical solutions: A digital twin scene configuration method comprises the following steps: Get raw data from sensors in a laptop processing plant; Establish a hierarchical data management architecture, divide the data into the basic layer, aggregation layer and scenario layer, and establish a digital twin model in the scenario layer; Optimize the digital twin model to maximize the operating efficiency of the processing plant and achieve the optimal state of the laptop processing plant. The objective function is a function of the operating efficiency and overall performance of the processing plant. For the vector field in the digital twin model, update the parameters of the raw data obtained by the sensors in the laptop processing plant along the gradient direction to approximate the objective function The optimal solution of , the formula for updating parameters is: , Where: is the learning rate, which controls the step size of parameter updates, A parameter set to obtain raw data from sensors in a laptop processing plant that needs to be updated, A parameter set for acquiring raw data from sensors in an updated laptop factory. The parameter set for obtaining raw data from sensors in the laptop processing plant before the update, and after each parameter update, checking the objective function If the value of the objective function reaches the preset convergence threshold, the iteration is stopped, the current parameter value is the optimal solution, the operation efficiency of the laptop processing plant is the highest, and the laptop processing plant reaches the optimal state; Input multi-source data into the digital twin model in real time, and dynamically adjust scene configuration parameters based on data changes.

[0006] Furthermore, the raw data obtained through sensors in the laptop processing plant includes the following specific contents: The laser rangefinder obtains the dimensional data of the CNC equipment in the laptop computer processing plant, the laser rangefinder obtains the dimensional data of the laptop computer workpiece in the laptop computer processing plant, the temperature sensor obtains the temperature data in the processing plant during the laptop computer processing process, the humidity sensor obtains the humidity data in the processing plant during the laptop computer processing process, the pressure sensor obtains the pressure data generated by the laptop computer workpiece during the processing on the CNC equipment, the vibration sensor obtains the vibration data of the laptop computer workpiece during the processing on the CNC equipment, and the position sensor obtains the workpiece position data during the processing of the laptop computer on the CNC equipment.

[0007] Furthermore, a hierarchical data management architecture is established to divide the data into the basic layer, aggregation layer and scenario layer. The establishment of a digital twin model in the scenario layer includes the following specific contents: The basic layer stores data acquired by multiple sensors in the laptop processing plant, including the size data of CNC equipment in the laptop processing plant, the size data of laptop workpieces in the laptop processing plant, the humidity data in the processing plant, the temperature data in the processing plant, the pressure data generated on the processing equipment, the vibration data generated on the processing equipment, and the workpiece position data during the processing on the processing equipment; The real-time data stored in the base layer is transmitted to the aggregation layer through the data bus. After receiving the data transmitted by the base layer, the aggregation layer decodes the data and converts the data from different sources into the same format through the XML parser. While converting the format, the data is standardized and the data obtained by all sensors are scaled to the same range. For data with different sampling frequencies, time alignment is performed to ensure that all data have corresponding values ​​on the same time axis. Each sensor data has an independent feature extraction network branch. The long short-term memory network is used to extract features from the dimension data of CNC equipment in the notebook computer processing plant, the vibration data generated by the processing equipment, the pressure data generated by the processing equipment, and the workpiece position data during the processing. The fully connected layer is used to extract high-dimensional features from the humidity data and temperature data in the processing plant. The features extracted by the independent branches are fused in the shared layer. The shared layer uses a convolutional layer to further integrate the data features obtained from different sensors. The data processed by the aggregation layer forms a complete data chain and transmits the data to the scene layer in real time. The scene layer is the highest layer of the data hierarchical management architecture. Its function is to use the data processed by the aggregation layer for the scene configuration of the processing plant. The scene layer not only relies on the underlying data, but also needs to convert this data into intuitive and operational scene representations to support real-time monitoring, simulation, prediction and adjustment. Scene modeling is the foundation of the scene layer. The core of scene modeling is digital twin modeling, which associates the real-time data of physical entities with virtual models to achieve synchronous operation of physical and virtual spaces. Laser scanning technology is used to obtain the three-dimensional point cloud data of the processing plant. These point clouds can accurately reflect the equipment, workpieces and overall spatial layout in the processing plant. The total station is used to survey the spatial layout to obtain accurate size, angle and position data. Modeling is carried out based on existing three-dimensional CAD drawings. These drawings can be imported into the modeling software. The three-dimensional modeling software AutoCAD is used to create the basic geometric shapes of equipment and workpieces. According to the design requirements of the equipment and workpieces, the switches of the equipment, the rollers of the conveyor belt and the hollow details of the workpiece are added. These details make the model closer to the actual physical form and accurately measure the length, width, height of each equipment and workpiece as well as the relative position of each part. The layout of the model in the virtual space is ensured to be consistent with the layout of the actual processing plant. The path of the production line is determined, and the path of the laptop workpiece flowing from one station to the next is defined. 3D modeling is used to represent the conveyor belt and conveying channel. In the process of digital twin modeling, LOD technology is used to automatically adjust the detail level of the model according to the viewing angle and distance, and a simple model is displayed at a distance, and a high-precision model is switched when approaching to reduce system resource consumption. According to the actual layout of the processing plant, the 3D modeling of the completed equipment, workpieces and production lines is accurately placed in the three-dimensional space to ensure that the model is consistent with the actual processing plant location. The scene layout is verified by virtual simulation tools to check whether the relative position of the equipment and workpiece meets the design requirements. After digital twin modeling, the dimensional data of the CNC equipment, the dimensional data of the laptop workpiece, the temperature data in the processing plant, the humidity data in the processing plant, the pressure data on the CNC equipment, the vibration data on the CNC equipment and the workpiece position data collected by multiple sensors are mapped to the corresponding 3D model. The model can reflect the status changes of the equipment in real time. The interactive function of the model is designed so that the operator can view detailed information by clicking, rotating and scaling the model. The digital twin model can be established through a set of mathematical formulas to describe various types of data and their relationships in the processing plant. The formula of the digital twin model is: , Where: is the vector field of the digital twin model, For time point, is the geometric position of any point in three-dimensional space, is the spatial coordinate; For the dimensional data of CNC equipment, satisfy , To define the boundary of the CNC equipment in three-dimensional space; The dimension data of the laptop workpiece, satisfy , To define the boundary of the laptop computer artifact in three-dimensional space; Production line in time The path data below, where , The production line in three-dimensional space Axis position versus time Changing coordinate values; For processing plants in time Temperature data below; For processing plants in time Humidity data below; For the time during processing The pressure data generated under the condition of pressure changing with time can be expressed as , is the initial pressure, For changes in pressure; The time during processing The vibration data generated under It can be expressed as , is the amplitude, is the vibration frequency, is the phase angle; For The workpiece position data below.

[0008] Furthermore, the digital twin model is optimized to maximize the operating efficiency of the processing room. The laptop processing plant achieves the optimal state, including the following specific contents: The raw data collected by the sensor is standardized, all data are converted into a unified format, scaled to the same range, and for data with different sampling frequencies, data from different sources are integrated to ensure that the data have corresponding values ​​on the same time axis. These data are integrated into the digital twin model. The objective function is a function of the operating efficiency and overall performance of the processing plant, which depends on By combining these factors to calculate the optimal state of the processing plant, the objective function The expression is: , Where: is the vector field of the digital twin model, For time point, is the length of a production cycle, is the Lagrangian function, which is used to transform the vector field The various components are mapped to the objective function superior, The expression is: , Where: is the weight coefficient, which is used to balance the influence of various factors. The vector field of the digital twin model The dynamic changes will be Directly affects the objective function , calculate the objective function The formula for the partial derivative of each parameter is: , Where: is the gradient vector, is the objective function The rate of change of geometric position parameters relative to any point in three-dimensional space, is the objective function Relative to the rate of change of the dimensional data parameters of the CNC equipment, is the objective function Relative to the change rate of the dimensional data parameters of the laptop workpiece, is the objective function Relative to the production line in time The rate of change of the path data parameters under is the objective function Relative to the internal time of the processing plant The rate of change of the temperature data parameter under is the objective function Relative to the internal time of the processing plant The rate of change of humidity data parameters under is the objective function Relative to the time during processing The rate of change of the pressure data parameters generated under is the objective function Relative to the time during processing The rate of change of the vibration data parameters generated under is the objective function Relative to time The rate of change of the workpiece position data parameters under the gradient direction is updated to approximate the objective function. The optimal solution of .

[0009] Furthermore, multi-source data is input into the digital twin model in real time, and scene configuration parameters are dynamically adjusted according to data changes, including the following specific contents: The real-time data obtained from the base layer and the aggregation layer are input into the scene layer. The real-time data includes: the dimension data, temperature data, humidity data, pressure data, vibration data and workpiece position data of the CNC equipment. The data flow status is continuously monitored in real time, the anomalies and data delay problems that occur are captured, and the data flow path is optimized by adjusting the data flow path; the acquired data is analyzed in real time to identify the trend and anomalies of data changes. When an abnormal situation is detected, the feedback mechanism is triggered to adjust the configuration parameters in the scene layer according to the preset adaptive control algorithm to ensure that the scene configuration conforms to the actual operating status of the current processing plant. The adjusted configuration parameters are fed back to the digital twin model in real time to trigger the real-time update of the digital twin model so that the digital twin model can timely reflect the latest processing plant status, integrate the temperature data and humidity data in the processing plant into the digital twin model, simulate the actual temperature and humidity conditions in the processing plant, adjust the air conditioning system and the local heating system to keep the temperature of the processing area stable, and prevent the equipment from being damaged. In case of overheating of the equipment and changes in the properties of the workpiece material, adjust the dehumidification and humidification equipment to ensure that the humidity in the processing plant is maintained within an appropriate range to prevent changes in the size of the workpiece caused by moisture absorption or drying of the material. Integrate the pressure data generated during the processing and the vibration data generated during the processing in the digital twin model, adjust the cutting depth of the workpiece during the processing, ensure that the processing pressure remains within the allowable range of the equipment and materials, analyze the vibration of the equipment and workpiece during the processing, identify possible equipment failures, and perform preventive maintenance. According to the real-time changes of the workpiece position data during the processing on the processing equipment by the laptop and the temperature data and humidity data in the processing plant, dynamically adjust the production line layout and the operating status of the equipment. When the temperature or humidity exceeds the preset normal range, give priority to processing of environmentally sensitive workpieces. The dimensional data, environmental data and processing process data are integrated in multiple dimensions, and the machine learning algorithm is used to find the optimal combination of processing parameters through data analysis to minimize the impact of vibration and pressure on workpiece quality. The beneficial effects of the present invention are as follows: the present invention first obtains raw data through sensors in a laptop computer processing plant, then establishes a data hierarchical management architecture, divides the data into a basic layer, an aggregation layer, and a scene layer, establishes a digital twin model in the scene layer, and optimizes the digital twin model, so that the operating efficiency of the processing room is the highest, the laptop computer processing plant reaches the optimal state, and multi-source data is input into the digital twin model in real time to meet the multi-dimensional and multi-level requirements of complex scenes in the processing plant, dynamically adjusts scene configuration parameters according to data changes, and realizes automatic adjustment and optimization configuration of the laptop computer processing plant in a changing environment, thereby improving the management efficiency of the laptop computer processing plant. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 This is a flow chart of a digital twin scene configuration method of the present invention; Figure 2 It is a schematic diagram of the construction process of the data hierarchical management architecture of the present invention. DETAILED DESCRIPTION

[0011] 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.

[0012] Example 1 See also Figure 1 A flow chart of a digital twin scene configuration method is shown, and a digital twin scene configuration method includes the following steps: Get raw data from sensors in a laptop processing plant; Establish a hierarchical data management architecture, divide the data into the basic layer, aggregation layer and scenario layer, and establish a digital twin model in the scenario layer; Optimize the digital twin model to maximize the operating efficiency of the processing room and achieve the optimal state of the laptop processing plant; Input multi-source data into the digital twin model in real time, and dynamically adjust scene configuration parameters based on data changes.

[0013] In this embodiment, the raw data obtained through sensors in the notebook computer processing plant includes the following specific contents: The laser rangefinder obtains the dimensional data of the CNC equipment in the laptop computer processing plant, the laser rangefinder obtains the dimensional data of the laptop computer workpiece in the laptop computer processing plant, the temperature sensor obtains the temperature data in the processing plant during the laptop computer processing process, the humidity sensor obtains the humidity data in the processing plant during the laptop computer processing process, the pressure sensor obtains the pressure data generated by the laptop computer workpiece during the processing on the CNC equipment, the vibration sensor obtains the vibration data of the laptop computer workpiece during the processing on the CNC equipment, and the position sensor obtains the workpiece position data during the processing of the laptop computer on the CNC equipment.

[0014] Further, refer to Figure 2 As shown in the figure, a hierarchical data management architecture is established to divide the data into the basic layer, aggregation layer and scenario layer, and a digital twin model is established in the scenario layer, including: The basic layer stores data acquired by multiple sensors in the laptop processing plant, including the size data of CNC equipment in the laptop processing plant, the size data of laptop workpieces in the laptop processing plant, the humidity data in the processing plant, the temperature data in the processing plant, the pressure data generated on the processing equipment, the vibration data generated on the processing equipment, and the workpiece position data during the processing on the processing equipment; The real-time data stored in the base layer is transmitted to the aggregation layer through the data bus. After receiving the data transmitted by the base layer, the aggregation layer decodes the data and converts the data from different sources into the same format through the XML parser. While converting the format, the data is standardized and the data obtained by all sensors are scaled to the same range. For data with different sampling frequencies, time alignment is performed to ensure that all data have corresponding values ​​on the same time axis. Each sensor data has an independent feature extraction network branch. The long short-term memory network is used to extract features from the dimension data of CNC equipment in the notebook computer processing plant, the vibration data generated by the processing equipment, the pressure data generated by the processing equipment, and the workpiece position data during the processing. The fully connected layer is used to extract high-dimensional features from the humidity data and temperature data in the processing plant. The features extracted by the independent branches are fused in the shared layer. The shared layer uses a convolutional layer to further integrate the data features obtained from different sensors. The data processed by the aggregation layer forms a complete data chain and transmits the data to the scene layer in real time. The scene layer is the highest layer of the data hierarchical management architecture. Its function is to use the data processed by the aggregation layer for the scene configuration of the processing plant. The scene layer not only relies on the underlying data, but also needs to convert this data into intuitive and operational scene representations to support real-time monitoring, simulation, prediction and adjustment. Scene modeling is the foundation of the scene layer. The core of scene modeling is digital twin modeling, which associates the real-time data of physical entities with virtual models to achieve synchronous operation of physical and virtual spaces. Laser scanning technology is used to obtain the three-dimensional point cloud data of the processing plant. These point clouds can accurately reflect the equipment, workpieces and overall spatial layout in the processing plant. The total station is used to survey the spatial layout to obtain accurate size, angle and position data. Modeling is carried out based on existing three-dimensional CAD drawings. These drawings can be imported into the modeling software. The three-dimensional modeling software AutoCAD is used to create the basic geometric shapes of equipment and workpieces. According to the design requirements of the equipment and workpieces, the switches of the equipment, the rollers of the conveyor belt and the hollow details of the workpiece are added. These details make the model closer to the actual physical form and accurately measure the length, width, height of each equipment and workpiece as well as the relative position of each part. The layout of the model in the virtual space is ensured to be consistent with the layout of the actual processing plant. The path of the production line is determined, and the path of the laptop workpiece flowing from one station to the next is defined. 3D modeling is used to represent the conveyor belt and conveying channel. In the process of digital twin modeling, LOD technology is used to automatically adjust the detail level of the model according to the viewing angle and distance, and a simple model is displayed at a distance, and a high-precision model is switched when approaching to reduce system resource consumption. According to the actual layout of the processing plant, the 3D modeling of the completed equipment, workpieces and production lines is accurately placed in the three-dimensional space to ensure that the model is consistent with the actual processing plant location. The scene layout is verified by virtual simulation tools to check whether the relative position of the equipment and workpiece meets the design requirements. After digital twin modeling, the dimensional data of the CNC equipment, the dimensional data of the laptop workpiece, the temperature data in the processing plant, the humidity data in the processing plant, the pressure data on the CNC equipment, the vibration data on the CNC equipment and the workpiece position data collected by multiple sensors are mapped to the corresponding 3D model. The model can reflect the status changes of the equipment in real time. The interactive function of the model is designed so that the operator can view detailed information by clicking, rotating and scaling the model. The digital twin model can be established through a set of mathematical formulas to describe various types of data and their relationships in the processing plant. The formula of the digital twin model is: , Where: is the vector field of the digital twin model; is the geometric position of any point in three-dimensional space, is the spatial coordinate; For the dimensional data of CNC equipment, satisfy , To define the boundary of the CNC equipment in three-dimensional space; The dimension data of the laptop workpiece, satisfy , To define the boundary of the laptop computer workpiece in three-dimensional space; Production line in time The path data below, where , The production line in three-dimensional space Axis position versus time Changing coordinate values; For processing plants in time Temperature data below; For processing plants in time Humidity data below; For the time during processing The pressure data generated under the condition of pressure changing with time can be expressed as , is the initial pressure, For changes in pressure; The time during processing The vibration data generated under It can be expressed as , is the amplitude, is the vibration frequency, is the phase angle; For The workpiece position data below.

[0015] Furthermore, the digital twin model is optimized to maximize the operating efficiency of the processing room and achieve the optimal state of the laptop processing plant, including: The laser rangefinder is used to obtain the dimensional data of the CNC equipment in the laptop processing plant, the laser rangefinder is used to obtain the dimensional data of the laptop workpiece in the laptop processing plant, the temperature sensor is used to obtain the real-time temperature data in the processing plant, the humidity sensor is used to obtain the humidity data in the processing plant, the pressure sensor is used to obtain the pressure data generated by the laptop workpiece during the processing on the processing equipment, the vibration sensor is used to obtain the vibration data of the laptop workpiece during the processing on the processing equipment, and the position sensor is used to obtain the position data of the workpiece during the processing on the processing equipment. The scale of the collected data is standardized, all data is converted into a unified format, and scaled to the same range. For data with different sampling frequencies, data from different sources are integrated to ensure that the data has corresponding values ​​on the same timeline, and these data are integrated into the digital twin model in real time. The objective function is a function of the operating efficiency and overall performance of the processing plant, which depends on By combining these factors to calculate the optimal state of the processing plant, the objective function The expression is: , Where: is the vector field of the digital twin model, is the length of a production cycle, is the Lagrangian function, which is used to transform the vector field The various components are mapped to the objective function superior, The expression is: , Where: is the weight coefficient, which is used to balance the influence of various factors. The vector field of the digital twin model The dynamic changes will be Directly affects the objective function , calculate the objective function The formula for the partial derivative of each parameter is: , Where: is the gradient vector, is the objective function The rate of change of geometric position parameters relative to any point in three-dimensional space, is the objective function Relative to the rate of change of the dimensional data parameters of the CNC equipment, is the objective function Relative to the change rate of the dimensional data parameters of the laptop workpiece, is the objective function Relative to the production line in time The rate of change of the path data parameters under is the objective function Relative to the processing plant in time The rate of change of the temperature data parameter under Objective Function Relative to the internal time of the processing plant The rate of change of humidity data parameters under Objective Function Relative to the time during processing The rate of change of the pressure data parameters generated under Objective Function Relative to the time during processing The rate of change of the vibration data parameters generated under Objective Function Relative to time The rate of change of the workpiece position data parameters under the gradient direction is updated to approach the objective function. The optimal solution of , the formula for updating parameters is: , Where: is the learning rate, which controls the step size of parameter updates, is the parameter set that needs to be updated. , The updated parameter set, is the parameter set before updating. After each parameter update, check the objective function If the value of the objective function reaches the preset convergence threshold, the iteration is stopped, the current parameter value is the optimal solution, the operating efficiency of the laptop computer processing plant is the highest, and the laptop computer processing plant reaches the optimal state.

[0016] Furthermore, multi-source data is input into the digital twin model in real time, and scene configuration parameters are dynamically adjusted according to data changes, including the following specific contents: The real-time data obtained from the basic layer and the aggregation layer are input into the scene layer. The real-time data includes: the size data, temperature data, humidity data, pressure data, vibration data and workpiece position data of the CNC equipment. The state of data flow is continuously monitored in real time. The key indicators of data flow rate, delay and packet loss rate are quickly processed and analyzed by the stream processing framework to capture the abnormalities and data delay problems. The thresholds of data delay not exceeding 500ms and data loss rate not exceeding 0.1% are set. When an abnormality is detected, the alarm mechanism is automatically triggered and the data flow path and resource allocation are adjusted in real time to optimize the data transmission efficiency. At the same time, the monitoring strategy is continuously optimized through the feedback learning mechanism to ensure the stability and real-time performance of the data flow. The acquired data is analyzed in real time to identify the trend and abnormality of data changes. When an abnormality is detected, the feedback mechanism is triggered to adjust the configuration parameters in the scene layer according to the preset adaptive control algorithm to ensure that the scene configuration conforms to the actual operation status of the current processing plant. The adjusted configuration parameters are fed back to the digital twin model in real time to trigger the real-time update of the digital twin model so that the digital twin model can reflect the latest processing plant status in a timely manner. The temperature data and processing data in the processing plant are updated in real time. The humidity data in the factory is integrated into the digital twin model to simulate the actual temperature and humidity conditions in the processing plant. The air conditioning system and local heating system are adjusted to maintain the temperature of the processing area stable, prevent equipment overheating and changes in the properties of the workpiece material. The dehumidification and humidification equipment are adjusted to ensure that the humidity in the processing plant is maintained within an appropriate range to prevent changes in the size of the workpiece caused by moisture absorption or drying of the material. The pressure data and vibration data generated during the processing process are integrated into the digital twin model to adjust the cutting depth of the workpiece during the processing process to ensure that the processing pressure remains within the allowable range of the equipment and materials. The vibration of the equipment and workpiece during the processing process is analyzed to identify possible equipment failures and perform preventive maintenance. According to the workpiece position data of the laptop on the processing equipment during the processing and the real-time changes of the temperature data and humidity data in the processing plant, the production line layout and the operating status of the equipment are dynamically adjusted. When the temperature or humidity exceeds the preset normal range, the workpieces that are sensitive to the environment are given priority for processing. The size data, environmental data and processing process data are integrated in multiple dimensions, and the machine learning algorithm is used to find the optimal combination of processing parameters through data analysis to minimize the impact of vibration and pressure on the quality of the workpiece. The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0017] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A digital twin scene configuration method, characterized in that: The steps include: Get raw data from sensors in the notebook processing plant; Establish a hierarchical data management architecture, divide the data into the basic layer, aggregation layer and scenario layer, and establish a digital twin model; Optimize the digital twin model to maximize the operating efficiency of the notebook processing plant and achieve the optimal state of the notebook processing plant. The objective function is a function of the operating efficiency and overall performance of the processing plant. For the vector field in the digital twin model, update the parameters of the raw data obtained by the sensors in the notebook processing plant along the gradient direction to approximate the objective function The optimal solution of , the formula for updating parameters is: ， Where: is the learning rate, which controls the step size of parameter updates, Get the parameter set of raw data for the sensors in the notebook factory that need to be updated, The parameter set for obtaining raw data from sensors in the updated notebook factory, Get the parameter set of raw data for the sensors in the notebook factory before updating. After each parameter update, check the objective function When the value of the objective function reaches the preset convergence threshold, the iteration is stopped, the current parameter value is the optimal solution, the operation efficiency of the notebook processing plant is the highest, and the notebook processing plant reaches the optimal state; Input multi-source data into the digital twin model in real time, and dynamically adjust scene configuration parameters based on data changes.

2. A digital twin scene configuration method according to claim 1, characterized in that ,The specific steps for optimizing the construction of digital twin models are: The laser rangefinder is used to obtain the dimensional data of the CNC equipment in the notebook processing plant, the laser rangefinder is used to obtain the dimensional data of the notebook workpiece in the notebook processing plant in real time, the temperature sensor is used to obtain the temperature data in the processing plant, the humidity sensor is used to obtain the humidity data in the processing plant, the pressure sensor is used to obtain the pressure data generated by the notebook workpiece during the processing, the vibration sensor is used to obtain the vibration data of the notebook workpiece during the processing, and the position sensor is used to obtain the position data of the notebook workpiece during the processing. The above data are integrated into the digital twin model, and the objective function is a function of the operating efficiency and overall performance of the processing plant and depends on The various components of the objective function The expression is: ， Where: is the vector field of the digital twin model, For time point, is the length of a production cycle, is the Lagrangian function, which is used to transform the vector field The various components are mapped to the objective function superior, The expression is: ， Where: is the weight coefficient, which is used to balance the influence of various factors. , the vector field of the digital twin model The dynamic changes of Directly affects the objective function , is the geometric position of any point in three-dimensional space, is the spatial coordinate; For the dimensional data of CNC equipment, satisfy , To define the boundary of the CNC equipment in three-dimensional space; The dimension data of the laptop workpiece, satisfy , To define the boundary of the laptop computer workpiece in three-dimensional space; Production line in time The path data below, where , For the production line in three-dimensional space Axis position versus time The changing coordinate values, The production line in three-dimensional space Axis position versus time The changing coordinate values, For the production line in three-dimensional space Axis position versus time Changing coordinate values; For processing plants in time Temperature data below; For processing plants in time Humidity data below; For the time during processing The pressure data generated under the condition of pressure changing with time, Expressed as , is the initial pressure, For changes in pressure; The time during processing The vibration data generated under Expressed as , is the amplitude, is the vibration frequency, is the phase angle; For The workpiece position data under To measure artifacts at a point in time Location Ideal path for production line The deviation between .

3. A digital twin scene configuration method according to claim 2, characterized in that , calculate the objective function The formula for the partial derivative of each parameter is: ， Where: is the gradient vector, is the objective function The rate of change of geometric position parameters relative to any point in three-dimensional space, is the objective function Relative to the rate of change of the dimensional data parameters of the CNC equipment, is the objective function Relative to the change rate of the dimensional data parameters of the laptop workpiece, is the objective function Relative to the production line in time The rate of change of the path data parameters under is the objective function Relative to the internal time of the processing plant The rate of change of the temperature data parameter under is the objective function Relative to the internal time of the processing plant The rate of change of humidity data parameters under is the objective function Relative to the time during processing The rate of change of the pressure data parameters generated under is the objective function Relative to the time during processing The rate of change of the vibration data parameters generated under is the objective function Relative to time The rate of change of the workpiece position data parameters under the gradient direction is updated to approximate the objective function. The optimal solution of .

4. A digital twin scene configuration method according to claim 1, characterized in that , establish a data hierarchical management architecture, divide the data into the basic layer, aggregation layer and scenario layer, and establish a digital twin model, including: The basic layer is used to store real-time data acquired by multiple sensors in the laptop processing plant, including the size data of CNC equipment in the laptop processing plant, the size data of laptop workpieces in the laptop processing plant, the humidity data in the processing plant, the temperature data in the processing plant, the pressure data generated on the processing equipment, the vibration data generated on the processing equipment, and the workpiece position data during the processing of the processing equipment; The aggregation layer is used to receive real-time data stored in the base layer. After receiving the data transmitted by the base layer, the aggregation layer decodes the data. The data processed by the aggregation layer forms a complete data chain and transmits the data to the scene layer in real time. The scene layer uses the data processed by the aggregation layer for the scene configuration of the processing plant. Scenario modeling is the foundation of the scene layer, and the core of scene modeling is digital twin modeling.

Images