Production line simulation reproduction system and method

Abstract

The invention relates to a production line simulation reproduction system and method, and belongs to the technical field of production line simulation reproduction. The basic architecture of the production line simulation reproduction system comprises four core modules, and the running state of a production line in a specific time period can be dynamically displayed in a dynamic reproduction module through a three-dimensional model and historical data records, so that engineers and managers are helped to carry out production process optimization and fault analysis; the main steps of the production line simulation reproduction method comprise three-dimensional model establishment, data acquisition, data processing and analysis and dynamic reproduction, an advanced algorithm is adopted, the historical operation state of a production line is dynamically reproduced in a three-dimensional model according to a time period and parameters selected by a user, and a machine learning algorithm is introduced for fault prediction and performance optimization.

Description

Technical Field

[0001] The invention relates to a production line simulation reproduction system and method, and belongs to the technical field of production line simulation reproduction. Background Art

[0002] In existing technologies, computer simulation and digital twin technology have been applied to the monitoring and optimization of production lines. These systems usually include the following key components:

[0003] 3D modeling: Existing digital twin systems use 3D modeling software to create virtual models of production lines. These models are usually created during the design and planning stages to simulate the layout and equipment configuration of the production line.

[0004] Data collection: Sensors and monitoring equipment deployed on the production line are used to collect real-time data such as equipment status, production progress, material flow, etc. They are used to monitor the real-time operating status of the production line.

[0005] Data storage and processing: The collected data is stored in the database. When production abnormalities occur, historical data can be viewed and the causes of the abnormalities can be analyzed.

[0006] User interface: Users interact with the system through the user interface and can view real-time data, alarm information, adjust production parameters, etc.

[0007] In the existing field of industrial production line monitoring and analysis, most systems focus on the collection and processing of real-time data to ensure immediate optimization and fault response of the production line. These systems usually include sensor networks, real-time data processing platforms and user interfaces, which can provide the current status and performance indicators of the production line. However, these systems have the following limitations in processing historical data and reproducing historical status:

[0008] Static display of historical data: Existing production line monitoring systems can only provide static queries and reports on historical data. They lack the ability to combine these data with the three-dimensional model of the production line and cannot intuitively display the operating status of the production line at a specific historical moment.

[0009] Lack of dynamic reproduction capability: Although some systems can store historical data, they usually do not support dynamic reproduction based on this data. This means that users cannot interactively observe the detailed operation of the production line at a certain point in the past. Existing systems mainly focus on real-time monitoring, but have limited dynamic reproduction capabilities for historical data. Users cannot intuitively see the detailed operation status of the production line at a specific point in the past.

[0010] Lack of 3D models: In the existing technology, the 3D model of the production line is usually used in the design and planning stage, rather than for monitoring and analysis during the production process. Therefore, the combination of the 3D model of the production line with real-time or historical data is not widely used in the existing technology.

[0011] Data integration challenges: Existing production line monitoring systems may have challenges in data integration, especially when associating data from different sources and formats with 3D models. This limits the accuracy and reliability of the system when reproducing historical states.

[0012] For example, Chinese patent publication number CN116415386A discloses a digital twin production line visualization system driven by real-time data, which includes the following steps: sensing the underlying information data of the production line through sensing technology; using modeling software to model the production line with high fidelity and restore the three-dimensional features of the production line; using the simulation platform to build a digital twin model driven by production site data; establishing an effective data integration and transmission channel, and receiving the production data of the physical entity production line in real time through the twin production line system; using the mapping relationship between digital space and physical space to complete the process control of real-time production. Realize transparent production and promote the development of intelligent manufacturing. However, there is a lack of intuitive display and reproduction of historical status.

[0013] In modern manufacturing, production line optimization and fault analysis are crucial to improving production efficiency and product quality. Traditional production line monitoring and analysis methods often rely on real-time data and lack the intuitive display and reproduction of historical status. Therefore, a system that can dynamically reproduce the status of the production line based on historical data is needed to better perform production analysis and fault diagnosis. Summary of the invention

[0014] The technical problem to be solved by the present invention is: to overcome the shortcomings of the prior art and provide a production line simulation reproduction system and method, which can combine a three-dimensional model and a dynamic reproduction system of historical data, so that users can more intuitively and effectively analyze the historical operating status of the production line, thereby providing stronger support for production optimization and fault diagnosis.

[0015] A production line simulation and reproduction system according to the present invention comprises:

[0016] 3D modeling module: used to create a 3D model of the production line;

[0017] Data acquisition module: used to collect the operation data of the production line in real time;

[0018] Data processing and analysis module: used to store the collected historical operation data;

[0019] Dynamic reproduction module: used to dynamically display the historical operating status of the production line based on the time period and three-dimensional model selected by the user and combined with historical data.

[0020] The basic architecture of the production line simulation and reproduction system is defined, including four core modules. In the dynamic reproduction module, the operating status of the production line in a specific time period can be dynamically displayed through three-dimensional models and historical data records, thereby helping engineers and managers to optimize production processes and analyze faults.

[0021] Preferably, it also includes:

[0022] User interaction module: used to integrate the user interface with backend data and 3D models.

[0023] A production line simulation and reproduction method according to the present invention comprises:

[0024] 3D model establishment: Use 3D modeling technology and tools to establish a 3D model of the production line based on the actual layout and equipment configuration of the production line;

[0025] Data collection: Based on the establishment of a 3D model, sensors and monitoring equipment are deployed to collect real-time operation data of the production line;

[0026] Data processing and analysis: collect the operation data of the production line and store the collected historical operation data;

[0027] Dynamic Reproduction: Dynamically reproduce the historical status of the production line through a 3D model based on the selected time period, and provide data-driven fault prediction and performance optimization suggestions through machine learning algorithms.

[0028] The main steps of the method are outlined, namely three-dimensional model building, data acquisition, data processing and analysis, and dynamic reproduction, and machine learning algorithms are introduced for fault prediction and performance optimization.

[0029] in:

[0030] High-precision 3D modeling technology: The 3D modeling technology used can accurately create a digital twin model of the production line, including the detailed geometry and properties of all relevant components such as equipment, tools, material flow, etc.

[0031] Real-time data collection and synchronization mechanism: The system can collect operation data in real time through sensors and monitoring equipment deployed on the production line, and synchronize this data with the 3D model to ensure that the virtual model can reflect the actual status of the production line in real time.

[0032] Historical data storage and retrieval technology: provides an efficient data storage solution that can preserve the historical operation data of the production line for a long time and support rapid retrieval of data in a specific time period for reproduction.

[0033] Dynamic Reproduction Algorithm: Using advanced algorithms, the historical operating status of the production line is dynamically reproduced in the 3D model according to the time period and parameters selected by the user, including equipment actions, production processes and abnormal events.

[0034] Preferably, the dynamic reproduction specifically includes the following steps:

[0035] Step S41, data preprocessing: extract historical operation data, clean the data, remove outliers and missing values, and format the data into a unified model input format;

[0036] Step S42, data and model synchronization: associating the preprocessed data with the corresponding equipment and process flow nodes in the three-dimensional model, and setting the data update frequency to match the dynamic display requirements of the three-dimensional model;

[0037] Step S43, state mapping: assigning historical data to a specific time point according to the timestamp, and mapping the equipment state and process parameters to the entities in the three-dimensional model;

[0038] Step S44, dynamic recurrence calculation: using interpolation or extrapolation algorithms, calculate intermediate states based on historical data to smoothly display state changes, and dynamically adjust equipment actions and production processes in the three-dimensional model using calculation results;

[0039] Step S45, animation and visual effect generation: generating corresponding animation effects according to changes in equipment status and process parameters;

[0040] Step S46, user interaction control: dynamically adjusting the reproduction process and displayed content according to user input;

[0041] Step S47, fault diagnosis and optimization suggestions: Analyze the abnormal status and performance bottlenecks in the reproduction process, combine machine learning algorithms, identify the cause of the fault and put forward optimization suggestions.

[0042] The dynamic reproduction steps are further refined, and each sub-step from data preprocessing to user interactive control is explained in detail, especially how to dynamically reproduce the status of the production line based on historical data, and the concepts of fault diagnosis and optimization suggestions are introduced.

[0043] Preferably, the dynamic recurrence calculation in step S44 adopts an extrapolation algorithm, which specifically includes the following steps:

[0044] Step S441, selecting an extrapolation model: selecting an extrapolation model according to data characteristics;

[0045] Step S442, model fitting: fitting the selected extrapolation model using known data to determine model parameters;

[0046] Step S443, verifying the model: verifying the accuracy and effectiveness of the model by comparing the extrapolated results of the model with known data;

[0047] Step S444, data extrapolation: using the fitted extrapolation model to perform extrapolation on the basis of known data to estimate the continuous state of the data;

[0048] Step S445, state smoothing: using continuous state data obtained by data extrapolation calculation to smoothly display state changes;

[0049] Step S446, dynamically adjusting the three-dimensional model: applying the extrapolated calculation results to the three-dimensional model to dynamically adjust the equipment action and production process;

[0050] Step S447, real-time rendering: using three-dimensional rendering technology to render the dynamically adjusted model into an image or animation;

[0051] Step S448, user interaction: allowing the user to select different time periods and viewing angles for observation through interface operations.

[0052] Preferably, the dynamic reproduction calculation in step S44 adopts an interpolation algorithm, which specifically includes the following steps:

[0053] Step S441, selecting an interpolation method: selecting an interpolation method according to the characteristics and requirements of the data;

[0054] Step S442, defining an interpolation function: constructing an interpolation function for predicting the value of an unknown data point based on known data points;

[0055] Step S443, calculating interpolation: using the interpolation function to calculate the value of the unknown data point;

[0056] Step S444, verifying the interpolation result: checking the rationality and accuracy of the interpolation result;

[0057] Step S445, smoothing: if necessary, smoothing the interpolation result to eliminate oscillation or discontinuity;

[0058] Step S446, result analysis: analyzing the interpolation results to determine whether the requirements for production line simulation reproduction are met;

[0059] Step S447, visual display: display the interpolation result in the form of graphics or animation in the three-dimensional model;

[0060] Step S448, user interaction: allowing the user to select different time periods and viewing angles for observation through interface operations.

[0061] Preferably, the step S47 specifically includes the following steps:

[0062] Step S471, collecting the operation data of the production line, including data of normal and abnormal states;

[0063] Step S472: training a machine learning model to identify patterns and trends in production line performance;

[0064] Step S473: Apply the trained model to historical data to predict potential failure points and performance bottlenecks, and provide data-driven failure prediction and performance optimization suggestions.

[0065] It can not only reproduce historical status, but also provide fault diagnosis and production optimization suggestions based on the reproduction results, helping enterprises improve production efficiency and product quality.

[0066] Preferably, the machine learning model adopts a support vector machine or a random forest algorithm.

[0067] Preferably, the method further comprises the following steps:

[0068] Step S48, result recording and sharing: Provides a function to allow users to save screenshots or videos of the reproduction process, and supports exporting the reproduction results into different formats.

[0069] The introduction of result recording and sharing functions increases the practicality and user experience of the system, allowing users to save and share reproduction results.

[0070] Preferably, a production line simulation reproduction method specifically comprises the following steps:

[0071] Step S1, three-dimensional model establishment: using 3D modeling technology and tools, according to the actual layout and equipment configuration of the production line, establish a three-dimensional model of the production line;

[0072] Step S2, data collection: on the basis of establishing a three-dimensional model, by deploying sensors and monitoring equipment, real-time collection of production line operation data;

[0073] Step S3, data processing and analysis: collecting the operation data of the production line and storing the collected historical operation data;

[0074] Step S4, dynamic reproduction: dynamically reproduce the historical status of the production line through the three-dimensional model according to the selected time period, and provide data-driven fault prediction and performance optimization suggestions through machine learning algorithms;

[0075] Step S5, user interaction: design a user interface so that the user can select the time point and parameters of the reproduction by dragging and clicking, thereby realizing the integration of the user interface with the backend data and the three-dimensional model.

[0076] A production line simulation reproduction method is described in detail, the order of the steps is reorganized, and special emphasis is placed on the design of user interaction and the integration of the user interface with back-end data and three-dimensional models, thus improving the interactivity and ease of use of the system.

[0077] Compared with the prior art, the present invention has the following beneficial effects:

[0078] High degree of visualization: The historical status of the production line is dynamically reproduced through the three-dimensional model, allowing users to intuitively understand the historical operation process of the production line, thereby improving the degree of visualization.

[0079] High analysis accuracy: Based on the reproduction of actual operation data, it can accurately reflect the historical status of the production line and provide accurate data support for analysis and optimization.

[0080] Wide range of applications: The system and method of the present invention are applicable to production lines of various types and sizes and have broad application prospects.

[0081] Easy to operate: The system has a friendly interface and is easy to operate. Users do not need to have professional computer modeling knowledge to operate it. BRIEF DESCRIPTION OF THE DRAWINGS

[0082] Figure 1 It is a structural block diagram of a production line simulation and reproduction system according to the present invention;

[0083] Figure 2 The present invention is a flowchart of a production line simulation and reproduction method. DETAILED DESCRIPTION

[0084] In order to make the objectives, technical solutions and advantages of the present invention more clear, the embodiments of the present invention will be described in further detail below.

[0085] Example 1

[0086] like Figure 1 As shown, this embodiment 1 discloses a production line simulation and reproduction system, including:

[0087] 3D Modeling Module: Used to create a detailed 3D model of the production line, including equipment, tools, materials, etc.

[0088] Data acquisition module: used to collect real-time operation data of the production line, such as equipment status, production progress, material flow, etc.

[0089] Data processing and analysis module: used to store the collected historical operation data, including timestamps, equipment parameters, operation logs, etc.

[0090] Dynamic reproduction module: dynamically displays the historical operation status of the production line based on the time period and 3D model selected by the user and combined with historical data;

[0091] User interaction module: used to integrate the user interface with backend data and 3D models.

[0092] The basic architecture of the production line simulation and reproduction system is defined, including four core modules. In the dynamic reproduction module, the operating status of the production line in a specific time period can be dynamically displayed through three-dimensional models and historical data records, thereby helping engineers and managers to optimize production processes and analyze faults.

[0093] Example 2

[0094] like Figure 2 As shown, this embodiment 2 discloses a production line simulation reproduction method, including:

[0095] 1. 3D model establishment

[0096] The 3D model building process in the present invention is a key link. Using advanced 3D modeling technology and tools, the 3D model of the production line is accurately built according to the actual layout and equipment configuration of the production line. This model should include all the key equipment, process flow and production line environment of the production line to ensure a high degree of consistency between the model and the actual production line.

[0097] The model includes the precise size, location and operation interface of the equipment, ensuring a high degree of consistency with the actual production line.

[0098] Compared with traditional 3D modeling, the present invention adopts high-precision scanning technology to ensure the accuracy and richness of details of the model.

[0099] Of course, you can consider using more advanced simulation software to build a 3D model of the production line and perform simulation reproduction. These software may provide more advanced functions and algorithms, and can more accurately simulate the actual operation of the production line. However, these advanced simulation software may be expensive and require professional technicians to model and run.

[0100] 2. Data Collection

[0101] Based on the establishment of the three-dimensional model, this embodiment deploys sensors and monitoring equipment to collect real-time operation data of the production line. These data include but are not limited to equipment status, process parameters, production speed, product quality, etc. High-sensitivity sensors and RFID systems are deployed to monitor the equipment status and material flow of the production line in real time.

[0102] 3. Data Processing and Analysis

[0103] The collected data will be recorded and stored in the database for subsequent analysis and reproduction. The time series database stores timestamps and device parameters to optimize data retrieval efficiency.

[0104] Introduce edge computing for data preprocessing to reduce the burden on central servers and improve data processing speed and real-time performance.

[0105] Of course, more advanced data collection and analysis tools can be considered to improve the accuracy and real-time nature of the data. These tools may use more advanced sensors and data processing algorithms to more accurately capture the operating status of the production line and provide more detailed data analysis functions. However, these advanced tools may be costly and require professional technicians to operate and maintain.

[0106] Machine learning algorithms can also be introduced to process and analyze production line data. By training models to identify patterns and trends in the production line, production line performance can be more accurately predicted and more precise simulation results can be provided. However, machine learning algorithms require a large amount of data for training and may require professional data scientists to develop and optimize the model.

[0107] 4. Dynamic Reproduction

[0108] One of the core functions of this embodiment is to be able to dynamically reproduce the historical status of the production line through the 3D model according to the selected time period. The user can select a specific time period through the system interface, and the system will dynamically adjust the equipment status, process parameters, etc. in the 3D model according to the data in the time period, and dynamically reproduce the historical status of the production line in the 3D model, thereby restoring the actual operation of the production line in the time period.

[0109] This historical status reproduction function is of great significance for production line optimization and fault analysis. By reproducing the historical status, users can gain a deeper understanding of the operation process of the production line, identify potential problems and bottlenecks, and propose targeted optimization measures. At the same time, the reproduction function can also be used for fault simulation and employee training to improve the reliability and flexibility of the production line.

[0110] Develop dynamic recurrence algorithms to retrieve corresponding historical data from the database based on the selected time period and parameters.

[0111] Synchronize historical data with the 3D model to dynamically adjust equipment status and process parameters in the model.

[0112] Use animation and visual effects to display the historical operating status of the production line in a 3D model.

[0113] Of course, we can consider combining physical models and simulation models to simulate the production line. The physical model can simulate the actual physical environment and equipment of the production line, while the simulation model can provide more flexible data analysis and simulation functions. By combining the two, more accurate and comprehensive simulation results can be obtained. However, the implementation of this method may be complicated and requires professional technicians to integrate and run.

[0114] 4.1 Dynamic Recurrence Algorithm

[0115] The dynamic reproduction algorithm is the core part of this invention, which aims to combine historical data with the three-dimensional model to dynamically display the status of the production line at a specific historical moment. The following is the specific process of the dynamic reproduction algorithm:

[0116] 1. Data preprocessing

[0117] Purpose: To clean and format historical data to ensure data quality and make it suitable for reproduction.

[0118] step:

[0119] Extract historical operation data from the data storage module, including equipment status, process parameters, timestamps, etc.

[0120] Clean the data to remove outliers and missing values.

[0121] Format the data into a uniform model input format.

[0122] 2. Data and model synchronization

[0123] Purpose: To ensure that the 3D model can be updated synchronously with historical data.

[0124] step:

[0125] Associate the preprocessed data with the corresponding equipment and process nodes in the 3D model.

[0126] Set the data update frequency to match the dynamic display requirements of the 3D model.

[0127] 3. State Mapping

[0128] Purpose: To map historical data to corresponding equipment and processes in the 3D model.

[0129] step:

[0130] Based on the timestamp, historical data is assigned to a specific point in time.

[0131] Map equipment status and process parameters to entities in the 3D model.

[0132] 4. Dynamic Recurrence Calculation

[0133] Purpose: To calculate and display the dynamic operating status of the production line at a historical moment.

[0134] step:

[0135] Interpolation or extrapolation algorithms are used to calculate intermediate states based on historical data to smoothly display state changes.

[0136] Apply calculation results to dynamically adjust equipment actions and production processes in the 3D model.

[0137] Among them, the specific steps of using the interpolation algorithm to calculate the intermediate state based on historical data to smoothly display the state change are as follows:

[0138] Step 1: Select an extrapolation model: Select an appropriate extrapolation model based on data characteristics, such as linear extrapolation, polynomial extrapolation, exponential extrapolation, etc.

[0139] Step 2: Model fitting: Use known data to fit the selected model and determine the model parameters.

[0140] Step 3: Verify the model: Verify the accuracy and effectiveness of the model by comparing the extrapolated results of the model with known data;

[0141] Step 4: Data extrapolation: Use the fitted model to perform extrapolation on the basis of known data to estimate the continuous state of the data;

[0142] Step 5: State smoothing: The continuous state data obtained by extrapolation calculation is used to smoothly display the state changes;

[0143] Step 6: Dynamically adjust the 3D model: Apply the extrapolated calculation results to the 3D model to dynamically adjust the equipment actions and production processes;

[0144] Step 7: Real-time rendering: Use 3D rendering technology to render the dynamically adjusted model into an image or animation;

[0145] Step 8: User interaction: Allow users to select different time periods and perspectives for observation through interface operations.

[0146] The specific steps of using the extrapolation algorithm to calculate the intermediate state based on historical data to smoothly display the state change are as follows:

[0147] Step 1: Select the interpolation method: Select the appropriate interpolation method according to the characteristics and requirements of the data, such as linear interpolation, polynomial interpolation, spline interpolation, etc.

[0148] Step 2: Define interpolation function: Construct an interpolation function that can predict the value of the intermediate point based on the known data points;

[0149] Step 3: Calculate interpolation: Use the interpolation function to calculate the value of the unknown data point;

[0150] Step 4: Verify the interpolation results: Check the rationality and accuracy of the interpolation results to ensure that they are physically and logically meaningful;

[0151] Step 5: Smoothing: If necessary, smooth the interpolation result to eliminate possible oscillations or discontinuities;

[0152] Step 6: Result analysis: Analyze the interpolation results to determine whether they meet the requirements for production line simulation reproduction;

[0153] Step 7: Visualization: Display the interpolation results in the form of graphics or animation in the 3D model;

[0154] Step 8: User interaction: Allow users to select different time periods and perspectives for observation through interface operations.

[0155] 5. Animation and visual effects generation

[0156] Purpose: To enhance the intuitiveness and understandability of the repetition process through animation and visual effects.

[0157] step:

[0158] Generate corresponding animation effects according to changes in equipment status and process parameters.

[0159] Apply visual elements such as color and brightness to highlight key state changes and potential problem areas.

[0160] 6. User interaction control

[0161] Purpose: Allow users to interactively control the reproduction process, including play, pause, replay, and parameter adjustment.

[0162] step:

[0163] Implement the user control interface, including the timeline, playback control buttons, and parameter adjustment options.

[0164] Dynamically adjust the reproduction process and displayed content based on user input.

[0165] 7. Fault diagnosis and optimization suggestions

[0166] Purpose: To provide suggestions for fault diagnosis and production optimization based on the reproduction results.

[0167] step:

[0168] Analyze abnormal conditions and performance bottlenecks during the reproduction process.

[0169] Combined with machine learning algorithms, it can identify the causes of failures and make optimization suggestions.

[0170] 8. Record and share results

[0171] Purpose: Allow users to save and share reproduction results for further analysis and discussion.

[0172] step:

[0173] Provide functionality to allow users to save screenshots or videos of the reproduction process.

[0174] Supports exporting reproduction results into different formats for easy sharing and archiving.

[0175] Improvements:

[0176] Compared with traditional static data display, the dynamic reproduction algorithm of the present invention can provide continuous, time-series dynamic display, allowing users to intuitively observe the changes in production line status over time.

[0177] The algorithm not only reproduces the equipment status, but also simulates the production process and abnormal events, providing a deeper understanding of the historical status.

[0178] The design of user interactive control makes the reproduction process more flexible and can be personalized according to the needs of different users.

[0179] IV.2 Application of Machine Learning Algorithms

[0180] Collect production line operation data, including normal and abnormal status data.

[0181] Train machine learning models, such as support vector machines (SVM) or random forests, to identify patterns and trends in production line performance.

[0182] Apply trained models to historical data to predict potential failure points and performance bottlenecks.

[0183] By introducing machine learning algorithms, the present invention can provide data-driven fault prediction and performance optimization suggestions, which are lacking in traditional monitoring systems.

[0184] 5. User interface design

[0185] The intuitive user interface allows users to select the time points and parameters for recurrence through simple operations such as dragging and clicking.

[0186] Achieve seamless integration of the user interface with backend data and 3D models to ensure smooth operation and responsiveness.

[0187] Provide personalized settings, allowing users to customize the interface layout and displayed information according to their needs.

[0188] The design of the user interface focuses on user experience and simplifies the operation process, allowing non-professionals to easily use the system to reproduce and analyze production line status.

[0189] The production line simulation and reproduction system and method described in the present invention have good compatibility and scalability, can adapt to production lines of different types and sizes, and can be integrated with other systems, such as ERP, MES, etc.

[0190] The above embodiments are merely descriptions of preferred embodiments of the present invention and are not restrictive. Therefore, the present invention is not limited to the embodiments described in the specific embodiments. Any other embodiments derived by those skilled in the art based on the technical solutions of the present invention also fall within the scope of protection of the present invention.

Claims

1. A production line simulation and reproduction system, characterized in that: include: 3D modeling module: used to create a 3D model of the production line; Data acquisition module: used to collect the operation data of the production line in real time; Data processing and analysis module: used to store the collected historical operation data; Dynamic reproduction module: used to dynamically display the historical operating status of the production line based on the time period and three-dimensional model selected by the user and combined with historical data.

2. A production line simulation and reproduction system according to claim 1, characterized in that: Also includes: User interaction module: used to integrate the user interface with backend data and 3D models.

3. A production line simulation and reproduction method, applied to a production line simulation and reproduction system according to claim 1 or 2, characterized in that: include: 3D model establishment: Use 3D modeling technology and tools to establish a 3D model of the production line based on the actual layout and equipment configuration of the production line; Data collection: Based on the establishment of a 3D model, sensors and monitoring equipment are deployed to collect real-time operation data of the production line; Data processing and analysis: collect the operation data of the production line and store the collected historical operation data; Dynamic Reproduction: Dynamically reproduce the historical status of the production line through a 3D model based on the selected time period, and provide data-driven fault prediction and performance optimization suggestions through machine learning algorithms.

4. A production line simulation and reproduction method according to claim 3, characterized in that: The dynamic reproduction specifically includes the following steps: Step S41, data preprocessing: extract historical operation data, clean the data, remove outliers and missing values, and format the data into a unified model input format; Step S42, data and model synchronization: associating the preprocessed data with the corresponding equipment and process flow nodes in the three-dimensional model, and setting the data update frequency to match the dynamic display requirements of the three-dimensional model; Step S43, state mapping: assigning historical data to a specific time point according to the timestamp, and mapping the equipment state and process parameters to the entities in the three-dimensional model; Step S44, dynamic recurrence calculation: using interpolation or extrapolation algorithms, calculate intermediate states based on historical data to smoothly display state changes, and dynamically adjust equipment actions and production processes in the three-dimensional model using calculation results; Step S45, animation and visual effect generation: generating corresponding animation effects according to changes in equipment status and process parameters; Step S46, user interaction control: dynamically adjusting the reproduction process and displayed content according to user input; Step S47, fault diagnosis and optimization suggestions: Analyze the abnormal status and performance bottlenecks in the reproduction process, combine machine learning algorithms, identify the cause of the fault and put forward optimization suggestions.

5. A production line simulation and reproduction method according to claim 4, characterized in that: The dynamic recurrence calculation in step S44 adopts an extrapolation algorithm, which specifically includes the following steps: Step S441, selecting an extrapolation model: selecting an extrapolation model according to data characteristics; Step S442, model fitting: fitting the selected extrapolation model using known data to determine model parameters; Step S443, verifying the model: verifying the accuracy and effectiveness of the model by comparing the extrapolated results of the model with known data; Step S444, data extrapolation: using the fitted extrapolation model to perform extrapolation on the basis of known data to estimate the continuous state of the data; Step S445, state smoothing: using continuous state data obtained by data extrapolation calculation to smoothly display state changes; Step S446, dynamically adjusting the three-dimensional model: applying the extrapolated calculation results to the three-dimensional model to dynamically adjust the equipment action and production process; Step S447, real-time rendering: using three-dimensional rendering technology to render the dynamically adjusted model into an image or animation; Step S448, user interaction: allowing the user to select different time periods and viewing angles for observation through interface operations.

6. A production line simulation and reproduction method according to claim 4, characterized in that: The dynamic reproduction calculation in step S44 adopts an interpolation algorithm, which specifically includes the following steps: Step S441, selecting an interpolation method: selecting an interpolation method according to the characteristics and requirements of the data; Step S442, defining an interpolation function: constructing an interpolation function for predicting the value of an unknown data point based on known data points; Step S443, calculating interpolation: using the interpolation function to calculate the value of the unknown data point; Step S444, verifying the interpolation result: checking the rationality and accuracy of the interpolation result; Step S445, smoothing: if necessary, smoothing the interpolation result to eliminate oscillation or discontinuity; Step S446, result analysis: analyzing the interpolation results to determine whether the requirements for production line simulation reproduction are met; Step S447, visual display: display the interpolation result in the form of graphics or animation in the three-dimensional model; Step S448, user interaction: allowing the user to select different time periods and viewing angles for observation through interface operations.

7. A production line simulation and reproduction method according to claim 4, characterized in that: The step S47 specifically includes the following steps: Step S471, collecting the operation data of the production line, including data of normal and abnormal states; Step S472: training a machine learning model to identify patterns and trends in production line performance; Step S473: Apply the trained model to historical data to predict potential failure points and performance bottlenecks, and provide data-driven failure prediction and performance optimization suggestions.

8. A production line simulation and reproduction method according to claim 7, characterized in that: The machine learning model adopts a support vector machine or a random forest algorithm.

9. A production line simulation and reproduction method according to claim 4, characterized in that: The following steps are also included: Step S48, result recording and sharing: Provides a function to allow users to save screenshots or videos of the reproduction process, and supports exporting the reproduction results into different formats.

10. A production line simulation and reproduction method according to claim 3, characterized in that: The specific steps include: Step S1, three-dimensional model establishment: using 3D modeling technology and tools, according to the actual layout and equipment configuration of the production line, establish a three-dimensional model of the production line; Step S2, data collection: on the basis of establishing a three-dimensional model, by deploying sensors and monitoring equipment, real-time collection of production line operation data; Step S3, data processing and analysis: collecting the operation data of the production line and storing the collected historical operation data; Step S4, dynamic reproduction: dynamically reproduce the historical status of the production line through the three-dimensional model according to the selected time period, and provide data-driven fault prediction and performance optimization suggestions through machine learning algorithms; Step S5, user interaction: design a user interface so that the user can select the time point and parameters of the reproduction by dragging and clicking, thereby realizing the integration of the user interface with the backend data and the three-dimensional model.

Images