Intelligent digital-twin factory control system for multi-dimensional visualization management, and method

Abstract

An intelligent digital-twin factory control system for multi-dimensional visualization management, and a method, which system and method belong to the field of digital factories. The intelligent digital-twin factory control system for multi-dimensional visualization management comprises: a three-dimensional construction unit, a comprehensive management unit and a monitoring end. A three-dimensional model of a factory is constructed by means of the three-dimensional construction unit; the comprehensive management unit obtains various pieces of data of a factory area by means of a plurality of data collection tools, and combines the pieces of data of the factory area with the constructed three-dimensional model, so as to form a three-dimensional model having a dynamic three-dimensional visualization effect; moreover, the monitoring end uses a visualization tool to generate visualization charts from the pieces of data of the factory area, and the generated visualization charts are displayed together with the three-dimensional model; and on the basis of the three-dimensional model and the visualization charts displayed by the monitoring end, a worker can take corresponding control measures. By means of the combination of a three-dimensional model and visualization charts, various pieces of data of a factory, workshops, production lines and employees can be comprehensively monitored and displayed in real time, thereby effectively improving the decision-making efficiency of a manager.

Description

A Smart Control System and Method for Digital Twin Factory Oriented to Multi-Dimensional Visual Management Technical Field

[0001] This invention relates to the field of smart factory technology, specifically to a digital twin factory smart control system and method for multi-dimensional visual management. Background Technology

[0002] A digital factory is a new production organization method that simulates, evaluates, and optimizes the entire production process in a computer virtual environment, extending to the entire product lifecycle. It is a product of the combination of modern digital manufacturing technology and computer simulation technology, primarily serving as a bridge between product design and manufacturing. The application of digital factories not only improves production efficiency but also optimizes product quality.

[0003] However, existing factories have the following problems in actual use: some enterprises have large-scale factory areas and complex operating equipment such as data monitoring platforms and monitoring devices. There are often multiple independently operating data management platforms in the factory area. Staff need to access each one to collect complete data and conduct analysis. This decentralized management model will greatly reduce the decision-making efficiency of managers. Therefore, it does not meet the existing needs. In response, we propose a digital twin factory intelligent control system and method for multi-dimensional visualization management. Summary of the Invention

[0004] The purpose of this invention is to provide a digital twin factory intelligent control system and method for multi-dimensional visualization management. By collecting external environmental data, internal structural data, and equipment operation data, a three-dimensional model of the factory is constructed. Various data acquisition tools are used to collect temperature and humidity data, air quality data, employee data, and inspection data from the factory area, obtaining various data points. These processed data points are combined with the constructed three-dimensional model to form a dynamic, visualized three-dimensional model. Simultaneously, visualization tools are used to generate visual charts from the various data points and display them along with the three-dimensional model. Based on the three-dimensional model and visual charts displayed on the monitoring terminal, staff can take corresponding control measures, thus solving the problems mentioned in the background section.

[0005] To achieve the above objectives, the present invention provides the following technical solution: a digital twin factory intelligent control system for multi-dimensional visual management, comprising:

[0006] 3D building blocks, used for

[0007] Collects and processes factory data, and constructs a 3D model of the factory based on the processed data; a comprehensive management unit is used for...

[0008] The system monitors the air environment, employees, and inspection areas within the factory, collects various data from the factory, processes the collected data, and combines the processed data with a 3D model to create a dynamic 3D visualization effect.

[0009] Monitoring terminal, used for

[0010] The system displays a dynamic, three-dimensional visualization model and generates visualization charts from collected factory data. These charts are then displayed alongside the three-dimensional model. Based on the three-dimensional model and visualization charts displayed on the monitoring terminal, staff can take corresponding control measures for the factory.

[0011] Furthermore, the three-dimensional building unit specifically performs the following operations:

[0012] Data Acquisition: Collect factory data, including external environmental data, internal structural data, and equipment operation data.

[0013] Data processing: Cleaning, classifying, and integrating the collected factory data to form data for 3D modeling;

[0014] 3D modeling: Based on the processed factory data, a 3D model of the factory is constructed. The 3D model includes the factory's external environment, internal structure, and equipment and facilities.

[0015] Furthermore, 3D modeling includes:

[0016] The data acquisition module is used to acquire the processed factory data and split the factory data based on the data representation object to obtain a three-dimensional object dataset;

[0017] The data analysis module is used for:

[0018] Extract data representations from the 3D object dataset and determine the acquisition angles of the 3D objects corresponding to the 3D object dataset based on the data representations;

[0019] Simultaneously, based on the acquisition angle, the corresponding three-dimensional object dataset is dimension-mapped to obtain the local three-dimensional object data corresponding to each acquisition angle, and the data features of the local three-dimensional object data are extracted.

[0020] Based on data features, determine the pose characteristics and target size of the 3D object at the corresponding acquisition angle, and construct the local 3D structure of the 3D object based on the pose characteristics and target size;

[0021] Based on the relative positional relationship of the acquisition angle, the first feature connection point between the local three-dimensional structures under different acquisition angles is determined according to the posture characteristics and target size. Based on the first feature connection point, the local three-dimensional structures corresponding to different acquisition angles are spliced ​​together to obtain an independent three-dimensional object structure.

[0022] Extract the position parameters from the processed factory data, and determine the relative positions between independent 3D object structures based on the position parameters;

[0023] The second feature connection point between independent three-dimensional object structures is determined based on their relative positions, and the independent three-dimensional object structures are associated based on the second feature connection point. The position association result is evaluated and processed to obtain the initial three-dimensional model of the factory.

[0024] The model optimization module is used for:

[0025] Multi-angle scene images of the factory are acquired based on the acquisition angle, and these multi-dimensional scene images are superimposed on the surface of the initial 3D model based on the acquisition angle.

[0026] The initial 3D model is textured based on the overlay result, and the 3D model of the factory is obtained based on the texture mapping result.

[0027] Furthermore, the integrated management unit includes:

[0028] Integrated detection module, used for

[0029] It integrates multiple data acquisition tools to collect various data from the factory area, including temperature and humidity data, air quality data, employee data, and inspection data.

[0030] Data processing module, used for

[0031] The collected data from the factory area are cleaned, classified, and integrated to form data for 3D visualization.

[0032] 3D visualization module, used for

[0033] By combining the processed data of the plant area with the constructed 3D model, the data of the plant area is displayed in 3D on the 3D model, thereby creating a dynamic 3D visualization effect of the 3D model and displaying it on the monitoring terminal.

[0034] Furthermore, the data acquisition tool includes:

[0035] Temperature and humidity sensor, used for

[0036] Detecting temperature and humidity in the factory's air environment;

[0037] PM2.5 sensor, used for

[0038] To detect the dust concentration in the air environment of the factory area;

[0039] Smart bracelet, used for

[0040] Wearing it on the employee's wrist, the smart bracelet can collect the employee's personal information and monitor the employee's vital signs data in real time.

[0041] Inspection robots, used for

[0042] Visual inspections of the factory area are conducted to obtain inspection data from inspection robots, thereby gaining an understanding of the actual situation in the inspection area.

[0043] Furthermore, the temperature and humidity sensor and the PM2.5 sensor form a set of environmental data collection tools. Multiple sets of environmental data collection tools are set up, and each set is set up within the detection area of ​​the factory. The air environment of the detection area is detected based on the multiple sets of environmental data collection tools. The smart bracelet contains the personal information of the employees. Based on the personal information, the smart bracelet corresponds to the employee whose personal information matches the personal information. Employees are required to wear the smart bracelet on their wrist when working in the factory. The smart bracelet has positioning and health detection functions.

[0044] Furthermore, the inspection robot specifically performs the following operations:

[0045] Set the inspection time and route for the inspection robot;

[0046] The inspection robot performs regular visual inspections of the inspection route based on the inspection time.

[0047] The inspection route includes factory workshops, warehouses, and fire-fighting facilities.

[0048] Furthermore, the monitoring terminal uses visualization tools to generate visual charts from the collected data of the factory area. The generated visual charts and 3D models are displayed on the monitoring terminal together. Based on the 3D model and visual charts displayed on the monitoring terminal, staff can take corresponding control measures for the factory area's air environment, employees, and inspection areas.

[0049] Furthermore, the monitoring terminal includes:

[0050] Acquire the collected factory data and determine the test dimensions of different items in the factory based on the factory data;

[0051] At the same time, based on the model building requirements, the data update requirements for building the 3D model of the factory are determined, and based on the data update requirements, the sensitivity of synchronous updating of the 3D model is determined.

[0052] The accuracy of 3D model construction is calculated based on the test dimensions of different items in the factory and the sensitivity of synchronous updating of the 3D model. The decision efficiency of controlling the digital twin factory is then calculated based on the accuracy of the 3D model construction.

[0053] The accuracy of the 3D model construction is calculated using the following formula:

[0054] Where η represents the accuracy of the 3D model construction, and its value is in the range (0, 1); μ represents the error coefficient, and its value ranges from (0.05, 0.015); i represents the serial number of the items contained in the factory, and its value ranges from [1, n]; n represents the total number of items contained in the factory; d i D represents the test dimension value of the length of the i-th item, determined based on factory data; i This represents the actual length of the i-th item; l i L represents the width test dimension value of the i-th item determined based on factory data; i h represents the actual width dimension of the i-th item; i H represents the height test dimension value of the i-th item determined based on factory data; i σ represents the actual height of the i-th item; σ represents the sensitivity to synchronous updates of the 3D model, and its value ranges from (0, 1).

[0055] The decision-making efficiency for controlling a digital twin factory can be calculated using the following formula:

[0056] Where δ represents the time length used to make a decision-making strategy for the digital twin factory based on the 3D model; T represents the theoretical time length used to make a decision-making strategy for the digital twin factory; η represents the accuracy of the 3D model construction, and its value is in the unit (0, 1).

[0057] Compare the calculated decision efficiency with the preset decision efficiency;

[0058] If the calculated decision efficiency is lower than the preset decision efficiency, the accuracy of the 3D model of the factory is deemed unqualified, and the 3D model of the factory is adjusted until the decision efficiency is greater than or equal to the preset decision efficiency.

[0059] Otherwise, the accuracy of the 3D model of the factory is deemed acceptable, and the decision-making strategy for the digital twin factory is used to control the digital twin factory based on the 3D model.

[0060] An implementation method for a digital twin factory intelligent control system for multi-dimensional visualization management includes the following steps:

[0061] Step 1: Construct a 3D model of the factory based on its external environment data, internal structure data, and equipment operation data;

[0062] Step 2: Use various data acquisition tools to collect temperature and humidity data, air quality data, employee data, and inspection data of the factory area to obtain various data of the factory area;

[0063] Step 3: Combine the processed data of the factory area with the constructed 3D model to form a dynamic 3D visualization effect 3D model;

[0064] Step 4: The monitoring terminal uses visualization tools to generate visualization charts from the collected data of the factory area and displays them together with the 3D model. Staff take corresponding control measures based on the 3D model and visualization charts displayed on the monitoring terminal.

[0065] Compared with the prior art, the beneficial effects of the present invention are:

[0066] 1. This invention collects external environmental data, internal structural data, and equipment operation data of a factory through a three-dimensional construction unit, and uses the collected data to construct a three-dimensional model of the factory. The integrated management unit collects temperature and humidity data, air quality data, employee data, and inspection data of the factory area through various data acquisition tools, obtains various data of the factory area, processes the various data of the factory area and combines them with the constructed three-dimensional model to form a dynamic three-dimensional visualization effect. At the same time, the monitoring terminal uses visualization tools to generate visualization charts of various data of the factory area and displays them together with the three-dimensional model. Staff take corresponding control measures based on the three-dimensional model and visualization charts displayed on the monitoring terminal. The combination of the three-dimensional model and visualization charts can monitor and display various data of the factory, workshop, production line and employees in real time and comprehensively, without the need for staff to retrieve and analyze each data individually, avoiding the decentralized management mode, thereby effectively improving the decision-making efficiency of managers.

[0067] 2. By splitting the processed factory data, the system accurately and effectively identifies the 3D object datasets of different 3D objects within the factory. This dataset is then parsed to determine the acquisition angles of different 3D objects, enabling effective analysis based on these angles. This yields the local 3D structure, corresponding pose features, and target dimensions of the objects at different acquisition angles. Furthermore, based on these local 3D structures, features, and target dimensions, the data is stitched together to ensure the comprehensiveness and reliability of the obtained 3D objects. Simultaneously, the system determines the relative positions of the 3D objects within the factory, allowing for their association and accurate acquisition of the initial 3D model of the factory. Finally, by acquiring multi-angle scene images of the factory and performing texture mapping on the initial 3D model based on these images, the system accurately and reliably constructs the final 3D model of the factory, ensuring its accuracy and reliability.

[0068] 3. By calculating the accuracy of the 3D model construction and then calculating the decision-making efficiency for controlling the digital twin factory based on the calculated accuracy, it is easy to determine whether the requirements for intelligent management of the factory through the 3D model are met. This facilitates timely optimization of the factory's 3D model when management requirements are not met, ensuring reliable and effective support for digital twin factory management and guaranteeing the management effect of the digital twin factory oriented towards multi-dimensional visualization management. Attached Figure Description

[0069] Figure 1 is a schematic diagram of the structure of the intelligent control system for digital twin factories oriented towards multi-dimensional visualization management according to the present invention;

[0070] Figure 2 is a schematic diagram of the integrated management unit structure of the present invention. Detailed Implementation

[0071] 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 some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0072] To address the challenges posed by the large scale of existing factories and the complexity of their data monitoring platforms and equipment, which often result in multiple independently operating data management platforms within the factory area—requiring staff to access each platform individually to compile and analyze complete data—this decentralized management model significantly reduces the efficiency of managerial decision-making. (See Figures 1-2.) This embodiment provides the following technical solution:

[0073] A smart control system for a digital twin factory oriented towards multi-dimensional visual management includes:

[0074] 3D building blocks, used for

[0075] Collects and processes factory data, and constructs a 3D model of the factory based on the processed data; a comprehensive management unit is used for...

[0076] The system monitors the air environment, employees, and inspection areas within the factory, collects various data from the factory, processes the collected data, and combines the processed data with a 3D model to create a dynamic 3D visualization effect.

[0077] Monitoring terminal, used for

[0078] The system displays a dynamic, three-dimensional visualization model and generates visualization charts from collected factory data. These charts are then displayed alongside the three-dimensional model. Based on the three-dimensional model and visualization charts displayed on the monitoring terminal, staff can take corresponding control measures for the factory.

[0079] The three-dimensional building block performs the following operations:

[0080] Data Acquisition: Collect factory data, including external environmental data, internal structural data, and equipment operation data.

[0081] Data processing: Cleaning, classifying and integrating the collected factory data to form data for 3D modeling;

[0082] 3D modeling: Based on the processed factory data, a 3D model of the factory is constructed. The 3D model includes the factory's external environment, internal structure, and equipment and facilities.

[0083] The technical effects of the above content are as follows: The 3D building unit completes the 3D modeling of the factory through three steps: data acquisition, data processing, and 3D modeling. First, data acquisition is required to collect factory data, which needs to include external environment data, internal structure data, and equipment operation data. External environment data and internal structure data can realistically create the external environment and internal structure of the factory area, while equipment operation data can restore the factory equipment and facilities. Then, through data processing, the collected factory data is cleaned, classified, and integrated. The processed factory data is more convenient for 3D modeling. Finally, through 3D modeling, the processed factory data is used to construct a 3D model of the factory. The constructed 3D model includes the factory's external environment, internal structure, and equipment and facilities. By modeling the factory based on the real internal and external environment and equipment, the 3D building unit restores the factory environment and the original appearance of each equipment production line, which is beneficial for subsequent monitoring and decision-making by staff.

[0084] The integrated management unit includes:

[0085] Integrated detection module, used for

[0086] Using a variety of data acquisition tools, we collect various data from the factory area, including temperature and humidity data, air quality data, employee data, and inspection data.

[0087] Data processing module, used for

[0088] The collected data from the factory area are cleaned, classified, and integrated to form data for 3D visualization.

[0089] 3D visualization module, used for

[0090] By combining the processed data of the plant area with the constructed 3D model, the data of the plant area is displayed in 3D on the 3D model, thereby creating a dynamic 3D visualization effect of the 3D model and displaying it on the monitoring terminal.

[0091] The data acquisition tools include:

[0092] Temperature and humidity sensor, used for

[0093] Detecting temperature and humidity in the factory's air environment;

[0094] PM2.5 sensor, used for

[0095] To detect the dust concentration in the air environment of the factory area;

[0096] Smart bracelet, used for

[0097] Wearing it on the employee's wrist, the smart bracelet can collect the employee's personal information and monitor the employee's vital signs data in real time.

[0098] Inspection robots, used for

[0099] Visual inspections of the factory area are conducted to obtain inspection data from inspection robots, thereby gaining an understanding of the actual situation in the inspection area.

[0100] The system includes a set of environmental data collection tools consisting of temperature and humidity sensors and PM2.5 sensors. Multiple sets of these tools are set up, with each set positioned within a designated detection area of ​​the factory. The system monitors the air quality in the detection area based on the data collected from these multiple sets of tools. The smart bracelet contains the employees' personal information. Based on this information, the smart bracelet is associated with the employee whose information matches their personal information. Employees are required to wear the smart bracelet on their wrist while working in the factory. The smart bracelet also has location tracking and health monitoring functions.

[0101] The inspection robot specifically performs the following operations:

[0102] Set the inspection time and route for the inspection robot;

[0103] The inspection robot performs regular visual inspections of the inspection route based on the inspection time.

[0104] The inspection route includes factory workshops, warehouses, and fire-fighting facilities.

[0105] At the monitoring end, visualization tools are used to generate visual charts from the collected data of the factory area. The generated visual charts and 3D models are displayed on the monitoring end. Based on the 3D models and visual charts displayed on the monitoring end, staff can take corresponding control measures for the factory air environment, employees and inspection areas.

[0106] The technical effects of the above are as follows: The integrated detection module can collect various data from the factory area. This module utilizes multiple data acquisition tools for detection. Temperature and humidity sensors detect the temperature and humidity in the factory's air environment, while PM2.5 sensors detect the dust concentration. These sensors, along with the PM2.5 sensor, form a set of environmental acquisition tools. Multiple sets of these tools are deployed within the factory's detection area to monitor the air environment, thereby obtaining more comprehensive data. Smart bracelets, worn on employees' wrists, collect personal information and monitor their vital signs in real time. These bracelets contain employee information and are worn by employees while on duty. They also feature location tracking and health monitoring capabilities, allowing staff to monitor employee health status promptly. Inspection robots conduct visual inspections of the factory area, providing data to understand the actual conditions of the inspected area and enabling pre-programmed inspection robot functions. The inspection robot performs regular, visual inspections of the inspection route based on the inspection schedule, thereby obtaining inspection data. This avoids the need for manpower in daily inspections, which is time-consuming, labor-intensive, and has high maintenance costs. Furthermore, it addresses the issue of maintenance personnel being unable to promptly identify and address problems. The data collection tools mentioned above acquire temperature and humidity data, air quality data, employee data, and inspection data for the factory area. These acquired data are then cleaned, classified, and integrated by the data processing module to form data for 3D visualization. Finally, the 3D visualization module displays the processed data for the factory area. By combining the data with the constructed 3D model, various data from the factory area are displayed in 3D on the model, thus creating a dynamic 3D visualization effect that is displayed on the monitoring terminal. Based on the 3D model and visualization charts displayed on the monitoring terminal, staff can take corresponding control measures for the factory's air environment, employees, and inspection areas. The combination of the 3D model and visualization charts allows for real-time and comprehensive monitoring and display of various data from the factory, workshops, production lines, and employees. The visualization effect is excellent, making it easy for staff to understand and grasp the situation of the factory, production, and employees, avoiding a decentralized management model, and effectively improving the decision-making efficiency of managers.

[0107] Specifically, this embodiment also proposes an implementation method for a digital twin factory intelligent control system for multi-dimensional visualization management, including the following steps:

[0108] Step 1: Construct a 3D model of the factory based on its external environment data, internal structure data, and equipment operation data;

[0109] Step 2: Use various data acquisition tools to collect temperature and humidity data, air quality data, employee data, and inspection data of the factory area to obtain various data of the factory area;

[0110] Step 3: Combine the processed data of the factory area with the constructed 3D model to form a dynamic 3D visualization effect 3D model;

[0111] Step 4: The monitoring terminal uses visualization tools to generate visual charts from the collected data of the factory area and displays them together with the 3D model. Staff take corresponding control measures based on the 3D model and visual charts displayed on the monitoring terminal.

[0112] Working Principle: The system collects external environmental data, internal structural data, and equipment operation data from the factory using 3D building units. This data is then used to construct a 3D model of the factory. The integrated management unit utilizes various data acquisition tools for monitoring. Temperature and humidity sensors detect temperature and humidity in the factory's air environment, while PM2.5 sensors detect dust concentration. Smart bracelets worn on employees' wrists collect personal information and monitor their vital signs in real time. Inspection robots perform visual inspections of the factory area, providing data for the system. The aforementioned data acquisition tools can obtain various data from the factory area, process this data, and combine it with the constructed 3D model to form a dynamic 3D visualization. Simultaneously, the monitoring terminal uses visualization tools to generate visual charts of various data from the factory area and display them together with the 3D model. Staff can take corresponding control measures based on the 3D model and visual charts displayed on the monitoring terminal. The combination of the 3D model and visual charts allows for real-time and comprehensive monitoring and display of various data from the factory, workshops, production lines, and employees, eliminating the need for staff to access and analyze data individually, avoiding a decentralized management model, and thus effectively improving the decision-making efficiency of managers.

[0113] This invention provides a digital twin factory intelligent control system for multi-dimensional visual management, including 3D modeling, comprising:

[0114] The data acquisition module is used to acquire the processed factory data and split the factory data based on the data representation object to obtain a three-dimensional object dataset;

[0115] The data analysis module is used for:

[0116] Extract data representations from the 3D object dataset and determine the acquisition angles of the 3D objects corresponding to the 3D object dataset based on the data representations;

[0117] Simultaneously, based on the acquisition angle, the corresponding three-dimensional object dataset is dimension-mapped to obtain the local three-dimensional object data corresponding to each acquisition angle, and the data features of the local three-dimensional object data are extracted.

[0118] Based on data features, determine the pose characteristics and target size of the 3D object at the corresponding acquisition angle, and construct the local 3D structure of the 3D object based on the pose characteristics and target size;

[0119] Based on the relative positional relationship of the acquisition angle, the first feature connection point between the local three-dimensional structures under different acquisition angles is determined according to the posture characteristics and target size. Based on the first feature connection point, the local three-dimensional structures corresponding to different acquisition angles are spliced ​​together to obtain an independent three-dimensional object structure.

[0120] Extract the position parameters from the processed factory data, and determine the relative positions between independent 3D object structures based on the position parameters;

[0121] The second feature connection point between independent three-dimensional object structures is determined based on their relative positions, and the independent three-dimensional object structures are associated based on the second feature connection point. The position association result is evaluated and processed to obtain the initial three-dimensional model of the factory.

[0122] The model optimization module is used for:

[0123] Multi-angle scene images of the factory are acquired based on the acquisition angle, and these multi-dimensional scene images are superimposed on the surface of the initial 3D model based on the acquisition angle.

[0124] The initial 3D model is textured based on the overlay result, and the 3D model of the factory is obtained based on the texture mapping result.

[0125] In this embodiment, the data representation object refers to the items existing in the factory that the factory data can represent, including the factory's internal structure data and operating equipment data.

[0126] In this embodiment, the three-dimensional object dataset refers to the three-dimensional information data of each data representation object obtained after splitting the factory data according to the data representation object, that is, the three-dimensional information data of the internal structure of the factory and the three-dimensional information data of the equipment form, etc.

[0127] In this embodiment, data representation refers to the data features corresponding to the three-dimensional object dataset, including the shape of the object represented by the three-dimensional object dataset, in order to determine the acquisition angle of the three-dimensional object.

[0128] In this embodiment, the three-dimensional object refers to the various scene elements required for the construction of a three-dimensional model, including factory equipment and factory structural units.

[0129] In this embodiment, local 3D object data refers to breaking down the data in the 3D object dataset into specific data corresponding to each acquisition angle. The purpose is to determine the different states of the 3D object under different acquisition angles and to ensure the comprehensiveness of the actual structure of the obtained 3D object.

[0130] In this embodiment, data features refer to the specific value range corresponding to the local three-dimensional object data and the specific morphological characteristics of the three-dimensional object.

[0131] In this embodiment, pose features refer to the specific shape of a three-dimensional object at a corresponding acquisition angle.

[0132] In this embodiment, the local three-dimensional structure refers to the three-dimensional structure constructed according to the posture characteristics and target size determined by the acquisition angle, which is a part of the structure of the three-dimensional object.

[0133] In this embodiment, the first feature connection point refers to the connection point between the local three-dimensional structures obtained from different acquisition angles of the same three-dimensional object. The purpose is to splice the local three-dimensional structures obtained from different acquisition angles of the same three-dimensional object according to the first feature connection point, so as to obtain the complete three-dimensional structure, that is, the independent three-dimensional object structure.

[0134] In this embodiment, the position parameter refers to the specific location of different three-dimensional objects in the factory.

[0135] In this embodiment, the second feature connection point refers to the relationship between different independent three-dimensional object structures in space, such as the relative direction and distance between two operating devices.

[0136] The working principle and beneficial effects of the above technical solution are as follows: By splitting the processed factory data, the 3D object datasets of different 3D objects in the factory can be accurately and effectively determined. The obtained 3D object datasets are then parsed to effectively determine the acquisition angles of different 3D objects. Based on the acquisition angles, the 3D object datasets can be effectively analyzed to obtain the local 3D structure, corresponding posture features, and target dimensions of the 3D objects under different acquisition angles. Secondly, based on the local 3D structure, corresponding posture features, and target dimensions under different acquisition angles, the local 3D structures under different acquisition angles are feature-stitched together to ensure the comprehensiveness and reliability of the obtained 3D objects. Simultaneously, the relative positions of the 3D objects in the factory are determined, enabling the association of 3D objects based on their relative positions, thus achieving accurate and effective acquisition of the initial 3D model of the factory. Finally, by acquiring multi-angle scene images of the factory and performing texture mapping on the initial 3D model based on these images, the 3D model of the factory can be accurately and reliably constructed, ensuring the accuracy and reliability of the final 3D model.

[0137] This invention provides a smart control system for a digital twin factory oriented towards multi-dimensional visual management, wherein the monitoring terminal includes:

[0138] Acquire the collected factory data and determine the test dimensions of different items in the factory based on the factory data;

[0139] At the same time, based on the model building requirements, the data update requirements for building the 3D model of the factory are determined, and based on the data update requirements, the sensitivity of synchronous updating of the 3D model is determined.

[0140] The accuracy of 3D model construction is calculated based on the test dimensions of different items in the factory and the sensitivity of synchronous updating of the 3D model. The decision efficiency of controlling the digital twin factory is then calculated based on the accuracy of the 3D model construction.

[0141] The accuracy of the 3D model construction is calculated using the following formula:

[0142] Where η represents the accuracy of the 3D model construction, and its value is in the range (0, 1); μ represents the error coefficient, and its value ranges from (0.05, 0.015); i represents the serial number of the items contained in the factory, and its value ranges from [1, n]; n represents the total number of items contained in the factory; d i D represents the test dimension value of the length of the i-th item, determined based on factory data; i This represents the actual length of the i-th item; l i L represents the width test dimension value of the i-th item determined based on factory data;i h represents the actual width dimension of the i-th item; i H represents the height test dimension value of the i-th item determined based on factory data; i σ represents the actual height of the i-th item; σ represents the sensitivity to synchronous updates of the 3D model, and its value ranges from (0, 1).

[0143] The decision-making efficiency for controlling a digital twin factory can be calculated using the following formula:

[0144] Where δ represents the time length used to make a decision-making strategy for the digital twin factory based on the 3D model; T represents the theoretical time length used to make a decision-making strategy for the digital twin factory; η represents the accuracy of the 3D model construction, and its value is in the unit (0, 1).

[0145] Compare the calculated decision efficiency with the preset decision efficiency;

[0146] If the calculated decision efficiency is lower than the preset decision efficiency, the accuracy of the 3D model of the factory is deemed unqualified, and the 3D model of the factory is adjusted until the decision efficiency is greater than or equal to the preset decision efficiency.

[0147] Otherwise, the accuracy of the 3D model of the factory is deemed acceptable, and the decision-making strategy for the digital twin factory is used to control the digital twin factory based on the 3D model.

[0148] In this embodiment, the test size refers to the size corresponding to different items determined based on the collected factory data, rather than the size obtained after actual measurement, and there may be errors compared with the actual size.

[0149] In this embodiment, the data update requirements are known in advance and are used to characterize the real-time update frequency and update rate of the 3D model based on changes in the factory.

[0150] In this embodiment, sensitivity is used to characterize the timeliness of synchronous updates to the 3D model. It is affected by the data transmission rate, the timeliness of monitoring changes in the factory, and the efficiency of the 3D model response. The sensitivity of synchronous updates to the 3D model is obtained by performing a weighted average calculation on different types of data according to the influence weight of different influencing factors.

[0151] In this embodiment, decision efficiency is used to characterize the timeliness of formulating decision-making strategies when controlling or managing the data twin factory based on the constructed 3D model.

[0152] In this embodiment, the preset decision efficiency is set in advance and is a measurement parameter used to measure whether the current decision efficiency meets the requirements. It can be adjusted.

[0153] The working principle and beneficial effects of the above technical solution are as follows: by calculating the accuracy of the 3D model construction, and based on the calculated accuracy, the decision-making efficiency when controlling the digital twin factory is calculated. This facilitates determining whether the requirements are met when using the 3D model for intelligent factory management. In this way, if the management requirements are not met, the 3D model of the factory can be optimized in a timely manner, ensuring reliable and effective support for the management of the digital twin factory and ensuring the management effect of the digital twin factory oriented towards multi-dimensional visualization management.

[0154] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0155] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A digital twin factory intelligent control system for multi-dimensional visual management, characterized in that, include: 3D building blocks, used for Collect and process factory data, and construct a 3D model of the factory based on the processed factory data; Integrated management unit, used for The system monitors the air environment, employees, and inspection areas within the factory, collects various data from the factory, processes the collected data, and combines the processed data with a 3D model to create a dynamic 3D visualization effect. Monitoring terminal, used for The system displays a dynamic, three-dimensional visualization model and generates visualization charts from collected factory data. These charts are then displayed alongside the three-dimensional model. Based on the three-dimensional model and visualization charts displayed on the monitoring terminal, staff can take corresponding control measures for the factory.

2. The intelligent control system for a digital twin factory oriented towards multi-dimensional visual management according to claim 1, characterized in that: The three-dimensional building unit specifically performs the following operations: Data Acquisition: Collect factory data, including external environmental data, internal structural data, and equipment operation data. Data processing: Cleaning, classifying, and integrating the collected factory data to form data for 3D modeling; 3D modeling: Based on the processed factory data, a 3D model of the factory is constructed. The 3D model includes the factory's external environment, internal structure, and equipment and facilities.

3. The intelligent control system for a digital twin factory oriented towards multi-dimensional visual management according to claim 2, characterized in that: 3D modeling, including: The data acquisition module is used to acquire the processed factory data and split the factory data based on the data representation object to obtain a three-dimensional object dataset; The data analysis module is used for: Extract data representations from the 3D object dataset and determine the acquisition angles of the 3D objects corresponding to the 3D object dataset based on the data representations; Simultaneously, based on the acquisition angle, the corresponding three-dimensional object dataset is dimension-mapped to obtain the local three-dimensional object data corresponding to each acquisition angle, and the data features of the local three-dimensional object data are extracted. Based on data features, determine the pose characteristics and target size of the 3D object at the corresponding acquisition angle, and construct the local 3D structure of the 3D object based on the pose characteristics and target size; Based on the relative positional relationship of the acquisition angle, the first feature connection point between the local three-dimensional structures under different acquisition angles is determined according to the posture characteristics and target size. Based on the first feature connection point, the local three-dimensional structures corresponding to different acquisition angles are spliced ​​together to obtain an independent three-dimensional object structure. Extract the position parameters from the processed factory data, and determine the relative positions between independent 3D object structures based on the position parameters; The second feature connection point between independent three-dimensional object structures is determined based on their relative positions, and the independent three-dimensional object structures are associated based on the second feature connection point. The position association result is evaluated and processed to obtain the initial three-dimensional model of the factory. The model optimization module is used for: Multi-angle scene images of the factory are acquired based on the acquisition angle, and these multi-dimensional scene images are superimposed on the surface of the initial 3D model based on the acquisition angle. The initial 3D model is textured based on the overlay result, and the 3D model of the factory is obtained based on the texture mapping result.

4. The intelligent control system for a digital twin factory oriented towards multi-dimensional visual management according to claim 1, characterized in that: The integrated management unit includes: Integrated detection module, used for Using a variety of data acquisition tools, we collect various data from the factory area, including temperature and humidity data, air quality data, employee data, and inspection data. Data processing module, used for The collected data from the factory area are cleaned, classified, and integrated to form data for 3D visualization. 3D visualization module, used for By combining the processed data of the plant area with the constructed 3D model, the data of the plant area is displayed in 3D on the 3D model, thereby creating a dynamic 3D visualization effect of the 3D model and displaying it on the monitoring terminal.

5. The intelligent control system for a digital twin factory oriented towards multi-dimensional visual management according to claim 4, characterized in that: The data acquisition tool includes: Temperature and humidity sensor, used for Detecting temperature and humidity in the factory's air environment; PM2.5 sensor, used for To detect the dust concentration in the air environment of the factory area; Smart bracelet, used for Wearing it on the employee's wrist, the smart bracelet can collect the employee's personal information and monitor the employee's vital signs data in real time. Inspection robots, used for Visual inspections of the factory area are conducted to obtain inspection data from inspection robots, thereby gaining an understanding of the actual situation in the inspection area.

6. The intelligent control system for a digital twin factory oriented towards multi-dimensional visual management according to claim 5, characterized in that: The temperature and humidity sensor and the PM2.5 sensor form a set of environmental data collection tools. There are multiple sets of environmental data collection tools, and each set is set up in the detection area of ​​the factory. The air environment of the detection area is detected based on the multiple sets of environmental data collection tools. The smart bracelet contains the personal information of the employees. Based on the personal information, the smart bracelet is associated with the employee whose personal information matches the personal information. Employees must wear the smart bracelet on their wrist when working in the factory. The smart bracelet has the functions of positioning and health detection.

7. The intelligent control system for a digital twin factory oriented towards multi-dimensional visual management according to claim 5, characterized in that: The inspection robot specifically performs the following operations: Set the inspection time and route for the inspection robot; The inspection robot performs regular visual inspections of the inspection route based on the inspection time. The inspection route includes factory workshops, warehouses, and fire-fighting facilities.

8. The intelligent control system for a digital twin factory oriented towards multi-dimensional visual management according to claim 1, characterized in that: The monitoring terminal uses visualization tools to generate visual charts from the collected data of the factory area. The generated visual charts and 3D models are displayed on the monitoring terminal. Based on the 3D model and visual charts displayed on the monitoring terminal, staff can take corresponding control measures for the factory air environment, employees and inspection areas.

9. A digital twin factory intelligent control system for multi-dimensional visual management according to claim 8, characterized in that: The monitoring terminal includes: Acquire the collected factory data and determine the test dimensions of different items in the factory based on the factory data; At the same time, based on the model building requirements, the data update requirements for building the 3D model of the factory are determined, and based on the data update requirements, the sensitivity of synchronous updating of the 3D model is determined. The accuracy of 3D model construction is calculated based on the test dimensions of different items in the factory and the sensitivity of synchronous updating of the 3D model. The decision efficiency of controlling the digital twin factory is then calculated based on the accuracy of the 3D model construction. The accuracy of the 3D model construction is calculated using the following formula: Where η represents the accuracy of the 3D model construction, and its value is in the range (0, 1); μ represents the error coefficient, and its value ranges from (0.05, 0.015); i represents the serial number of the items contained in the factory, and its value ranges from [1, n]; n represents the total number of items contained in the factory; d i D represents the test dimension value of the length of the i-th item, determined based on factory data; i This represents the actual length of the i-th item; l i L represents the width test dimension value of the i-th item determined based on factory data; i h represents the actual width dimension of the i-th item; i H represents the height test dimension value of the i-th item determined based on factory data; i σ represents the actual height of the i-th item; σ represents the sensitivity of synchronously updating the 3D model, and its value ranges from (0, 1). The decision-making efficiency for controlling a digital twin factory can be calculated using the following formula: Where δ represents the time length used to make a decision-making strategy for the digital twin factory based on the 3D model; T represents the theoretical time length used to make a decision-making strategy for the digital twin factory; η represents the accuracy of the 3D model construction, and its value is in the unit (0, 1). Compare the calculated decision efficiency with the preset decision efficiency; If the calculated decision efficiency is lower than the preset decision efficiency, the accuracy of the 3D model of the factory is deemed unqualified, and the 3D model of the factory is adjusted until the decision efficiency is greater than or equal to the preset decision efficiency. Otherwise, the accuracy of the 3D model of the factory is deemed acceptable, and the decision-making strategy for the digital twin factory is used to control the digital twin factory based on the 3D model.

10. An implementation method of a digital twin factory intelligent control system for multi-dimensional visualization management as described in any one of claims 1-9, characterized in that: Includes the following steps: Step 1: Construct a 3D model of the factory based on its external environment data, internal structure data, and equipment operation data; Step 2: Use various data acquisition tools to collect temperature and humidity data, air quality data, employee data, and inspection data of the factory area to obtain various data of the factory area; Step 3: Combine the processed data of the factory area with the constructed 3D model to form a dynamic 3D visualization effect 3D model; Step 4: The monitoring terminal uses visualization tools to generate visualization charts from the collected data of the factory area and displays them together with the 3D model. Staff take corresponding control measures based on the 3D model and visualization charts displayed on the monitoring terminal.

Images