Multi-level modeling method based on multi-source virtual-real fusion superspeed optical module production line

Abstract

The invention discloses a multi-level modeling method based on a multi-source virtual-real fusion ultra-high-speed optical module production line, and the method comprises the steps: building a virtual ultra-high-speed optical module production line in unity 3D, and simulating various scenes and technologies in a production process; collecting multi-source data in the production process of the ultra-high-speed optical module; preprocessing and standardizing the multi-source data; constructing a multi-level model of the ultra-high-speed optical module production line, wherein the multi-level model comprises a data layer, an information layer and a decision-making layer; the data layer is used for normalizing and storing data; the information layer comprises a prediction unit, a deep learning technology is adopted to construct a prediction model, and the prediction model predicts operation parameters of each virtual device in unity 3D according to the normalized multi-source data; the decision-making layer comprises a control unit, and the control unit carries out production optimization and control decision-making. According to the method, data from different sources are integrated through a multi-level modeling strategy, and model parameters and structures can be adaptively adjusted by means of a deep learning technology so as to adapt to production requirements of different levels.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence and data processing technology, and in particular to a multi-level modeling method based on a multi-source virtual-real fusion ultra-high-speed optical module production line. Background Art

[0002] With the rapid development of information technology, the global demand for data transmission rate and capacity is increasing. As the core components in optical fiber communication systems, ultra-high-speed optical modules are becoming increasingly important. Especially in data centers, 5G networks, and high-speed broadband, ultra-high-speed optical modules have become the key to achieving efficient data transmission. Due to the complexity and diversity of ultra-high-speed optical module production lines, production management and quality control face huge challenges. There is an urgent need for a method that can integrate multi-source data and perform multi-level modeling to improve production efficiency and product quality.

[0003] The production of ultra-high-speed optical modules involves multiple links, including chip packaging, optical device assembly, electronic circuit welding and final testing. The process parameters and operating conditions of each link will affect the performance and quality of the final product. For example, in the chip packaging process, parameters such as temperature, pressure, and time need to be precisely controlled; in the optical device assembly process, the alignment accuracy and bonding process directly affect the transmission quality of the optical signal; in the electronic circuit welding process, the welding temperature and time affect the reliability of the solder joints; in the final test process, it is necessary to test various performance indicators of ultra-high-speed optical modules, including insertion loss, return loss, bandwidth, eye diagram, etc. Such a complex production process requires precise control and real-time monitoring of parameters in each link. A large amount of multi-source heterogeneous data will be generated during the production process, including equipment operation data, process parameters, environmental monitoring data, product testing data, etc. These data come from a wide range of sources, are of various types, and have temporal and spatial correlations. For example, the equipment operation status data can reflect the real-time status of the production line, the process parameters record the specific operation steps, the environmental monitoring data includes external conditions such as temperature, humidity, and cleanliness, and the product testing data is a direct reflection of the performance of the final product.

[0004] At present, most research and applications focus on the optimization of a single level or a single link of the ultra-high-speed optical module production line, lacking a systematic, multi-level modeling method. This single-level optimization method cannot fully and accurately describe the overall picture of the production line, making it difficult to achieve global optimization and real-time monitoring of the entire production process. For example, the optimization of a single device may improve local production efficiency, but it may not necessarily improve overall production efficiency; the optimization of a single process parameter may improve the product quality of a certain link, but it cannot ensure the consistency and reliability of the entire production process. This limitation often leads to low production efficiency and unstable product quality in actual production, making it difficult to meet the market demand for high-performance, high-reliability ultra-high-speed optical modules. These drawbacks limit the intelligent and efficient operation of ultra-high-speed optical module production lines. Summary of the invention

[0005] The purpose of the present invention is to provide a multi-level modeling method based on a multi-source virtual-real fusion ultra-high-speed optical module production line. Through a multi-level modeling strategy, data from different sources are integrated. With the help of deep learning technology, model parameters and structures can be adaptively adjusted to meet production needs at different levels. This can not only improve the accuracy and robustness of the model, but also enhance the scalability and flexibility of the system.

[0006] The first aspect of the present invention provides a multi-level modeling method based on a multi-source virtual-real fusion ultra-high-speed optical module production line, the method comprising:

[0007] Establish a virtual ultra-high-speed optical module production line in Unity3D to simulate various scenes and processes in the production process;

[0008] Collect multi-source data during the production process of real ultra-high-speed optical modules, including equipment status, production parameters, and environmental conditions;

[0009] Preprocess and standardize multi-source data;

[0010] A multi-level model of an ultra-high-speed optical module production line is constructed, including a data layer, an information layer, and a decision layer. The data layer includes a data processing unit and a data storage unit. The data processing unit is used to normalize multi-source data, and the data storage unit is used to store the normalized multi-source data. The information layer includes a prediction unit. The prediction unit uses deep learning technology to build a prediction model. The prediction model predicts the operating parameters of each virtual device in unity3D based on the normalized multi-source data. The decision layer includes a control unit. The control unit performs production optimization and control decisions based on the predicted operating parameters of each virtual device in unity3D to adapt to changes and uncertainties in the production environment.

[0011] In some of the embodiments, an ultra-high-speed optical module production line is established in Unity3D to simulate various scenes and processes in the production process, including:

[0012] A virtual scene of an ultra-high-speed optical module production line is constructed in Unity3D, and each device used for production in the ultra-high-speed optical module production line is 3D modeled. The 3D model of the device is placed in the corresponding virtual scene to achieve a one-to-one correspondence between the real ultra-high-speed optical module production line and the virtual ultra-high-speed optical module production line.

[0013] In some embodiments, multi-source data is collected during the production process of an actual ultra-high-speed optical module, including:

[0014] Collect temperature, pressure, humidity, vibration and image data of production equipment and environment in the real ultra-high-speed optical module production line. Furthermore, obtain real-time data of production equipment and environment through temperature sensors, pressure sensors, humidity sensors and vibration sensors deployed at key nodes of the ultra-high-speed optical module production line; obtain image and video data of the production site through cameras deployed in the ultra-high-speed optical module production line.

[0015] In some embodiments, preprocessing and standardizing the multi-source data includes:

[0016] The collected multi-source data is cleaned to remove noise and outliers, and irrelevant or redundant data. Then the data is standardized to convert data from different sources into data in a unified format.

[0017] In some of the embodiments, the prediction model is a multi-layer FNN network, which predicts the operating parameters of each virtual device in unity3D according to changes in the production environment: when the production environment of the actual ultra-high-speed optical module production line changes, the prediction model predicts the operating parameters of each virtual device in unity3D, and maps the results to each virtual device in unity3D, thereby dynamically adjusting the operating parameters of each virtual device in unity3D;

[0018] Among them, the production environment includes equipment status, production parameters and environmental conditions, and the operating parameters of virtual equipment include equipment operating temperature, operation duration, number of available machines and operation efficiency.

[0019] In some of the embodiments, production optimization and control decisions are made based on the predicted operating parameters of each virtual device in Unity3D, including:

[0020] The operation duration, number of available machines, operation efficiency and processing rules are used as inputs of the ant colony algorithm to generate a specific production scheduling plan.

[0021] According to a second aspect of the present invention, a multi-level modeling system based on a multi-source virtual-real fusion ultra-high-speed optical module production line is provided for implementing the multi-level modeling method based on a multi-source virtual-real fusion ultra-high-speed optical module production line according to any one of the first aspects, and the system comprises:

[0022] Digital twin module, used to build a virtual ultra-high-speed optical module production line in Unity3D and simulate various scenes and processes in the production process;

[0023] Data acquisition module, used to collect multi-source data in the actual ultra-high-speed optical module production process, including equipment status, production parameters and environmental conditions;

[0024] Data processing module, used to preprocess and standardize multi-source data;

[0025] The multi-level modeling module is used to build a multi-level model of the ultra-high-speed optical module production line, including a data layer, an information layer and a decision layer; the data layer includes a data processing unit and a data storage unit, the data processing unit is used to normalize multi-source data, and the data storage unit is used to store the normalized multi-source data; the information layer includes a prediction unit, the prediction unit uses deep learning technology to build a prediction model, and the prediction model predicts the operating parameters of each virtual device in unity3D based on the normalized multi-source data; the decision layer includes a control unit, and the control unit performs production optimization and control decisions based on the predicted operating parameters of each virtual device in unity3D to adapt to changes and uncertainties in the production environment.

[0026] According to a third aspect of the present invention, there is provided a computer device comprising: a processor and a memory, the memory storing programs or instructions executable on the processor, and the programs or instructions, when executed by the processor, implementing the steps of the multi-level modeling method based on a multi-source virtual-real fusion ultra-high-speed optical module production line described in any one of the first aspects.

[0027] According to a fourth aspect of the present invention, a readable storage medium is provided, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of the multi-level modeling method based on a multi-source virtual-real fusion ultra-high-speed optical module production line described in any one of the first aspects are implemented.

[0028] In general, the above technical solutions conceived by the present invention can achieve the following beneficial effects compared with the prior art:

[0029] (1) By integrating the three core parts of data acquisition, data processing and model building, the intelligence level and operational efficiency of the ultra-high-speed optical module production line have been significantly improved.

[0030] (2) Vision systems and sensors are used to obtain production data and visual information in real time at key nodes of the ultra-high-speed optical module production line, ensuring the comprehensiveness and real-time nature of the data.

[0031] (3) The model is constructed using a multi-level modeling approach. Through the hierarchical structure of the data layer, information layer, and decision layer, it achieves adaptive adjustment and optimization of the production process, solving the problem that the production environment and process conditions are constantly changing, and a single static model cannot adapt to these changes, resulting in model failure or reduced accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 A flowchart of a multi-level modeling method based on a multi-source virtual-real fusion ultra-high-speed optical module production line provided in an embodiment of the present application;

[0033] Figure 2 An architecture diagram of a multi-level modeling system based on a multi-source virtual-real fusion ultra-high-speed optical module production line provided in an embodiment of the present application;

[0034] Figure 3 A schematic diagram of a multi-source data collection and processing process provided in an embodiment of the present application;

[0035] Figure 4 A schematic diagram of the hardware structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0036] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention. Based on the embodiments provided in this application, all other embodiments obtained by ordinary technicians in this field without making creative work belong to the scope of protection of the present invention.

[0037] Obviously, the drawings described below are only some examples or embodiments of the present application. For ordinary technicians in this field, the present application can also be applied to other similar scenarios based on these drawings without creative work. In addition, it can also be understood that although the efforts made in this development process may be complicated and lengthy, for ordinary technicians in this field related to the content disclosed in this application, some changes in design, manufacturing or production based on the technical content disclosed in this application are just conventional technical means, and should not be understood as insufficient content disclosed in this application.

[0038] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those of ordinary skill in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0039] Unless otherwise defined, the technical terms or scientific terms involved in this application should be understood by people with ordinary skills in the technical field to which this application belongs. The words "one", "a", "a", "the" and the like involved in this application do not indicate a quantitative limitation, and may represent the singular or plural. The terms "include", "comprise", "have" and any of their variations involved in this application are intended to cover non-exclusive inclusions; for example, a process, method, system, product or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may also include steps or units that are not listed, or may also include other steps or units inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The "multiple" involved in this application refers to two or more. "And / or" describes the association relationship of associated objects, indicating that there may be three relationships, for example, "A and / or B" can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the objects before and after are in an "or" relationship. The terms "first", "second", "third", etc. involved in this application are only used to distinguish similar objects and do not represent a specific ordering of the objects.

[0040] The single-level, system-less modeling method cannot fully and accurately describe the overall picture of the production line, making it difficult to achieve global optimization and real-time monitoring of the entire production process. The present invention provides a multi-level modeling method for an ultra-high-speed optical module production line based on multi-source data fusion. Considering the complexity of the production environment (such as equipment failure, process condition changes, etc.) that will cause the parameters of some models to change dynamically and become unavailable, the model constructed by the multi-level modeling method for an ultra-high-speed optical module production line based on multi-source data fusion fuses multi-source data and uses deep learning technology to improve the real-time and dynamic adaptability of the model, enhance the robustness and scalability of the model in a complex and changeable production environment, and optimize the fusion effect of the data, thereby improving the intelligence level and production efficiency of the ultra-high-speed optical module production line.

[0041] The present application embodiment provides a multi-level modeling method for an ultra-high-speed optical module production line based on multi-source data fusion, such as Figure 1 and Figure 3 As shown, the following steps are included:

[0042] Step 1: Use multiple data sources such as sensors and vision systems to collect multi-dimensional data in the actual ultra-high-speed optical module production process, including equipment status, production parameters, environmental conditions, etc.

[0043] Step 2: Clean the collected multi-source data, remove noise and outliers, and eliminate irrelevant or redundant data. Then perform data standardization to convert data from different sources into a unified format.

[0044] Step 3: Use the processed multi-source data to build a multi-level model, such as Figure 1 As shown in the figure, it includes data layer, information layer and decision layer. Data layer: responsible for processing and storing fused data and providing basic data support. Information layer: analyzes and models data to extract valuable information and patterns. Decision layer: makes production optimization and control decisions based on model results.

[0045] Step 4: Use deep learning technology to build a prediction model. According to the changes in the production environment (equipment status, production parameters, environmental conditions, etc.), predict the changes in the virtual model parameters in Unity3D (equipment operating temperature, operation duration, etc.), so as to dynamically adjust the virtual model parameters in Unity3D. Obtain the processed multi-source data (equipment operating temperature, energy consumption data, equipment production efficiency, etc.) from the data layer and normalize the data. Design a multi-layer network (FNN) to extract features and define a mean square error function to quantify the model error. In the model training stage, the pre-processed data of the data layer is divided into a training set and a validation set. The Adam optimization algorithm is used to iteratively update the model weights, and the hyperparameters (learning rate and network depth) are optimized to obtain the best performance model.

[0046] Step 5: Create a virtual ultra-high-speed optical module production line in Unity3D to simulate various scenes and processes in the production process. Based on multi-source data fusion and multi-level modeling, multi-source data collection and multi-level models are integrated into the ultra-high-speed optical module production line to form a coordinated and efficient overall system.

[0047] It should be noted that the steps shown in the above process or the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0048] The embodiments of the present application also provide a multi-level modeling system based on a multi-source virtual-real fusion ultra-high-speed optical module production line. These systems are used to implement the above embodiments and preferred implementations, and those that have been described will not be repeated. As used below, the terms "module", "unit", "sub-unit", etc. can implement a combination of software and / or hardware for predetermined functions. Although the systems described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived.

[0049] The multi-level modeling system based on the multi-source virtual-real fusion ultra-high-speed optical module production line of the embodiment of the present application is as follows: Figure 2 and Figure 3 As shown, it includes the following modules:

[0050] Digital twin module: used to build a virtual scene of the ultra-high-speed optical module production line. Based on this, 3D modeling is performed on each device used for production, and the 3D model of the device is placed in the corresponding virtual scene to achieve a one-to-one correspondence between the real ultra-high-speed optical module production line and the virtual ultra-high-speed optical module production line.

[0051] Data acquisition module: used to collect data such as temperature, pressure, humidity, vibration, and images of real-time production equipment and environment. Real-time data of production equipment and environment can be obtained through temperature sensors, pressure sensors, humidity sensors, and vibration sensors deployed at key nodes of the ultra-high-speed optical module production line. Images and video data of the production site can be obtained through cameras deployed on the ultra-high-speed optical module production line.

[0052] Data processing module: used to perform data cleaning, noise filtering, anomaly detection and data standardization on the multi-source data collected by the data acquisition module, and finally generate data in a unified format (JSON).

[0053] Neural network module: used to build a prediction model. The data in the data layer is normalized and used as the model input, and the parameters of the virtual equipment in unity3D are used as the prediction model output. When the equipment on the real production line suddenly encounters certain conditions (equipment failure, changes in operating temperature and energy consumption, etc.), the prediction model outputs the results and maps the results to the virtual equipment in unity3D. At this time, the output results of the prediction model include changes in the corresponding virtual equipment in unity3D (changes in available machine parameters, changes in work efficiency parameters, etc.). Finally, the decision-making layer will use the corresponding output results (number of available machines, processing time, processing efficiency, processing rules, etc.) as the input of the ant colony algorithm based on the output results of the prediction model to generate a specific production scheduling plan.

[0054] Multi-level modeling module: used to dynamically adjust model parameters to adapt to changes and uncertainties in the production environment. This module enables the system to dynamically adapt to changes in the production environment by building a multi-level model architecture of data layer, information layer and decision layer, and adjusts the virtual equipment model parameters (equipment operating temperature, operation duration, etc.) in Unity3D in real time to cope with various uncertainties, and finally produces a specific production plan. The information layer uses machine learning and deep learning technology to analyze data and provide accurate optimization suggestions, which helps the decision-making layer to formulate effective production optimization and control strategies.

[0055] In addition, combined Figure 1 The multi-level modeling method based on the multi-source virtual-real fusion ultra-high-speed optical module production line of the described embodiments of the present application can be implemented by a computer device. Figure 4 Schematic diagram of the hardware structure of the computer device of the embodiment of the present application. Figure 4 As shown, the device may include a processor 301 and a memory 302 storing computer program instructions.

[0056] Specifically, the processor 301 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0057] Among them, the memory 302 may include a large capacity memory for data or instructions. For example, but not limitation, the memory 302 may include a hard disk drive (HDD), a floppy disk drive, a solid state drive (SSD), a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, the memory 302 may include a removable or non-removable (or fixed) medium. In appropriate cases, the memory 302 may be inside or outside the data processing device. In a specific embodiment, the memory 302 is a non-volatile memory. In a specific embodiment, the memory 302 includes a read-only memory (ROM) and a random access memory (RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (Programmable Read-Only Memory, PROM for short), an erasable PROM (Erasable Programmable Read-Only Memory, EPROM for short), an electrically erasable PROM (Electrically Erasable Programmable Read-Only Memory, EEPROM for short), an electrically alterable ROM (Electrically Alterable Read-Only Memory, EAROM for short) or a flash memory (FLASH) or a combination of two or more of these. Under appropriate circumstances, the RAM can be a static random access memory (SRAM) or a dynamic random access memory (DRAM), wherein the DRAM can be a fast page mode dynamic random access memory (FPMDRAM), an extended data output dynamic random access memory (EDODRAM), a synchronous dynamic random access memory (SDRAM), etc.

[0058] The memory 302 may be used to store or cache various data files that need to be processed and / or used for communication, as well as possible computer program instructions executed by the processor 301 .

[0059] The processor 301 reads and executes computer program instructions stored in the memory 302 to implement any one of the multi-level modeling methods based on a multi-source virtual-real fusion ultra-high-speed optical module production line in the above embodiments.

[0060] In some embodiments, the point cloud generation device may further include a communication interface 303 and a bus 300. Figure 4 As shown, the processor 301, the memory 302, and the communication interface 303 are connected via a bus 300 and communicate with each other.

[0061] The communication interface 303 is used to implement communication between the modules, devices, units and / or equipment in the embodiment of the present application. The communication interface 303 can also implement data communication with other components such as: external devices, image / data acquisition equipment, databases, external storage, and image / data processing workstations.

[0062] The bus 300 includes hardware, software, or both, and couples the components of the point cloud generation device to each other. The bus 300 includes, but is not limited to, at least one of the following: a data bus, an address bus, a control bus, an expansion bus, and a local bus. By way of example and not limitation, bus 300 may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses or a combination of two or more of the above. Bus 300 may include one or more buses, where appropriate. Although embodiments of the present application describe and illustrate a particular bus, the present application contemplates any suitable bus or interconnect.

[0063] The computer device can be based on a three-dimensional visual measurement system and a high-precision six-degree-of-freedom displacement stage to execute the multi-level modeling method based on a multi-source virtual-real fusion ultra-high-speed optical module production line in the embodiment of the present application, thereby realizing the combination of Figure 1 A multi-level modeling method for an ultra-high-speed optical module production line based on multi-source virtual-real fusion is described.

[0064] In addition, in combination with the multi-level modeling method based on the multi-source virtual-real fusion ultra-high-speed optical module production line in the above embodiment, the embodiment of the present application can provide a computer-readable storage medium for implementation. The computer-readable storage medium stores computer program instructions; when the computer program instructions are executed by the processor, any of the multi-level modeling methods based on the multi-source virtual-real fusion ultra-high-speed optical module production line in the above embodiment is implemented.

[0065] In summary, the present invention adopts a multi-level modeling method to achieve adaptive adjustment and optimization of the production process through a hierarchical structure of data layer, information layer and decision layer, which solves the problem that the production environment and process conditions are constantly changing, and a single static model cannot adapt to these changes, resulting in model failure or reduced accuracy.

[0066] It should be pointed out that the technical features of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of the technical features in the above-mentioned embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification. In addition, according to the needs of implementation, the various steps / components described in this application can be split into more steps / components, and two or more steps / components or partial operations of steps / components can be combined into new steps / components to achieve the purpose of the present invention.

[0067] It is easy for a person skilled in the art to understand that the above-mentioned embodiments only express several implementation methods of the present application, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the invention patent. It should be pointed out that for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A multi-level modeling method based on a multi-source virtual-real fusion ultra-high-speed optical module production line, characterized in that: The method includes: Establish a virtual ultra-high-speed optical module production line in Unity3D to simulate various scenes and processes in the production process; Collect multi-source data during the production process of real ultra-high-speed optical modules, including equipment status, production parameters, and environmental conditions; Preprocess and standardize multi-source data; Construct a multi-level model of the ultra-high-speed optical module production line, including the data layer, information layer and decision layer; the data layer includes a data processing unit and a data storage unit. The data processing unit is used to normalize multi-source data, and the data storage unit is used to store the normalized multi-source data; the information layer includes a prediction unit, which uses deep learning technology to build a prediction model. The prediction model performs production optimization and control decisions based on the normalized multi-source data and predicts the operating parameters of each virtual device in unity3D to adapt to changes and uncertainties in the production environment. The decision layer includes a control unit, which performs production optimization and control decisions based on the predicted operating parameters of each virtual device in unity3D to adapt to changes and uncertainties in the production environment.

2. The multi-level modeling method based on multi-source virtual-real fusion ultra-high-speed optical module production line according to claim 1 is characterized in that: An ultra-high-speed optical module production line was established in Unity3D to simulate various scenes and processes in the production process, including: A virtual scene of an ultra-high-speed optical module production line is constructed in Unity3D, and each device used for production in the ultra-high-speed optical module production line is 3D modeled. The 3D model of the device is placed in the corresponding virtual scene to achieve a one-to-one correspondence between the real ultra-high-speed optical module production line and the virtual ultra-high-speed optical module production line.

3. The multi-level modeling method based on multi-source virtual-real fusion ultra-high-speed optical module production line according to claim 1 is characterized in that: Collect multi-source data in the actual ultra-high-speed optical module production process, including: Collect temperature, pressure, humidity, vibration and image data of production equipment and environment in real ultra-high-speed optical module production lines.

4. The multi-level modeling method based on multi-source virtual-real fusion ultra-high-speed optical module production line according to claim 3 is characterized in that: By deploying temperature sensors, pressure sensors, humidity sensors, and vibration sensors at key nodes of the ultra-high-speed optical module production line, real-time data on production equipment and environment can be obtained; by deploying cameras on the ultra-high-speed optical module production line, image and video data of the production site can be obtained.

5. The multi-level modeling method based on multi-source virtual-real fusion ultra-high-speed optical module production line according to claim 1 is characterized in that: Preprocess and standardize multi-source data, including: The collected multi-source data is cleaned to remove noise and outliers, and irrelevant or redundant data. Then data standardization is performed to convert data from different sources into data in a unified format.

6. The multi-level modeling method based on multi-source virtual-real fusion ultra-high-speed optical module production line according to claim 1 is characterized in that: The prediction model is a multi-layer FNN network. It predicts the operating parameters of each virtual device in unity3D according to changes in the production environment. When the production environment of the real ultra-high-speed optical module production line changes, the prediction model predicts the operating parameters of each virtual device in unity3D and maps the results to each virtual device in unity3D, thereby dynamically adjusting the operating parameters of each virtual device in unity3D. Among them, the production environment includes equipment status, production parameters and environmental conditions, and the operating parameters of virtual equipment include equipment operating temperature, operation duration, number of available machines and operation efficiency.

7. The multi-level modeling method based on multi-source virtual-real fusion ultra-high-speed optical module production line according to claim 6 is characterized in that: Make production optimization and control decisions based on the predicted operating parameters of each virtual device in Unity3D, including: The operation duration, number of available machines, operation efficiency and processing rules are used as inputs of the ant colony algorithm to generate a specific production scheduling plan.

8. A multi-level modeling system based on a multi-source virtual-real fusion ultra-high-speed optical module production line for implementing the multi-level modeling method based on a multi-source virtual-real fusion ultra-high-speed optical module production line according to any one of claims 1 to 7, characterized in that: The system includes: Digital twin module, used to build a virtual ultra-high-speed optical module production line in Unity3D and simulate various scenes and processes in the production process; Data acquisition module, used to collect multi-source data in the actual ultra-high-speed optical module production process, including equipment status, production parameters and environmental conditions; Data processing module, used to preprocess and standardize multi-source data; The multi-level modeling module is used to build a multi-level model of the ultra-high-speed optical module production line, including a data layer, an information layer and a decision layer; the data layer includes a data processing unit and a data storage unit, the data processing unit is used to normalize multi-source data, and the data storage unit is used to store the normalized multi-source data; the information layer includes a prediction unit, the prediction unit uses deep learning technology to build a prediction model, and the prediction model predicts the operating parameters of each virtual device in unity3D based on the normalized multi-source data; the decision layer includes a control unit, and the control unit performs production optimization and control decisions based on the predicted operating parameters of each virtual device in unity3D to adapt to changes and uncertainties in the production environment.

9. A computer device, characterized in that: include: A processor and a memory, the memory storing programs or instructions that can be run on the processor, and when the programs or instructions are executed by the processor, the steps of the multi-level modeling method based on a multi-source virtual-real fusion ultra-high-speed optical module production line described in any one of claims 1 to 7 are implemented.

10. A readable storage medium, characterized in that: Programs or instructions are stored thereon, and when the programs or instructions are executed by the processor, the steps of the multi-level modeling method based on the multi-source virtual-real fusion ultra-high-speed optical module production line described in any one of claims 1 to 7 are implemented.

Images