Lithium battery material factory management method and system based on digital twinning technology

Abstract

The invention discloses a lithium battery material factory management method and system based on a digital twinning technology. The method comprises the steps that lithium battery material factory equipment facilities are decomposed step by step, an equipment file is established, a unique equipment ID is allocated to each piece of equipment, and a physical model is constructed; constructing a virtual factory model consistent with the layout of the lithium battery material factory by utilizing a BIM (Building Information Modeling) technology; establishing a mapping relationship between the lithium battery material factory and the virtual factory; the AI technology is used for simulating the operation behavior of the lithium battery material factory, the advantages and disadvantages of different setting schemes are evaluated according to the simulation result, and the optimal setting scheme is determined by comparing indexes under different schemes; through digital twinning of the real factory and the virtual factory, a brand new production management mode is provided for enterprises, and the enterprises can be helped to realize intelligent, digital and visual transformation, so that the aims of improving the production efficiency, reducing the cost and improving the product quality are fulfilled.

Description

Technical Field

[0001] The present invention relates to a lithium battery material factory management method and system, and in particular to a lithium battery material factory management method and system based on digital twin technology. Background Art

[0002] At present, the continuous iteration and update of Internet technology and the rise of big data and artificial intelligence technology have provided a foundation for the promotion of digital twin technology, and many application scenarios have appeared in the fields of building automation, power system control, aerospace, etc. As a rapidly developing industry in recent years, lithium battery materials need the support of high-tech to improve corporate competitiveness and profitability.

[0003] The existing lithium battery material factory production lines are controlled based on traditional DCS, WMS, and MES systems. There are many data islands, lack of big data support and the application of artificial intelligence technology, and the development bottleneck is very obvious. The use of digital twin related technologies can break through the barriers between systems on the existing basis, improve the factory's production efficiency, and enhance the profitability of the enterprise.

[0004] Due to the complex and ever-changing factory environment, the wide variety of equipment, and the fact that the production process involves the real-time collection, processing, and analysis of a large amount of data and information, traditional management methods are difficult to meet the requirements of efficiency and accuracy. Faced with the huge amount of data and the dynamic changes of the system, the past methods were unable to quickly generate accurate data models, resulting in low management efficiency in equipment maintenance, production scheduling, production forecasting, and other links, affecting overall production efficiency and economic benefits. Summary of the invention

[0005] Purpose of the invention: The purpose of the invention is to provide a lithium battery material factory management method based on digital twin technology to achieve comprehensive simulation and optimization management of the production process, improve the factory's production efficiency and product quality, and reduce energy consumption.

[0006] Technical solution: A lithium battery material factory management method based on digital twin technology, including the following steps:

[0007] S1. Decompose the equipment and facilities of the lithium battery material factory step by step, establish equipment files, assign a unique equipment ID to each equipment, obtain the three-dimensional data of the equipment through modeling tools, and build a physical model of the equipment;

[0008] S2. Use BIM technology to build a virtual factory model consistent with the factory layout;

[0009] S3, connect the control systems of the equipment and facilities of the factory to the server of the virtual factory and establish a mapping relationship;

[0010] S4. Install multiple types of sensors in the factory. The sensors collect the status of production equipment, environmental parameters, personnel operation data, and material quality data, and store the collected data in a database.

[0011] S5. Build a data model for describing the operation behavior of the factory in the virtual factory server. The data model is a related physical model, statistical model, and machine learning model established according to the production process, equipment characteristics, and process parameters of the factory.

[0012] S6. Use AI technology to simulate the operation behavior of the factory under different production parameters, process conditions, and external environments. According to the simulation results, evaluate the advantages and disadvantages of different setting schemes. By comparing the production efficiency, energy consumption, and product quality indicators under different schemes, determine the optimal setting scheme.

[0013] Preferably, the equipment in S1 can be decomposed into a single sensor and a drive unit.

[0014] Preferably, S1 further includes using intelligent algorithms to classify and label the equipment and generate an equipment decomposition diagram.

[0015] Preferably, the multiple types of sensors in S4 include pressure, temperature, flow, and displacement sensors. The environmental parameters include temperature, humidity, and dust concentration. The personnel operation data includes operation duration and operation frequency. The material quality data includes composition, purity, and particle size distribution.

[0016] Preferably, S4 further includes cleaning and preprocessing the data. The cleaning includes removing noise, missing values, and outliers in the data. The preprocessing includes data normalization, standardization, and data interpolation operations.

[0017] Preferably, S4 further includes transmitting the data to the edge computing device of the factory. The edge computing device performs preliminary processing of data compression and format conversion on the data. The processed data is sent to a remote server for storage through the network. The data is stored in the database and adopts a distributed storage architecture.

[0018] A lithium battery material factory management system based on digital twin technology according to the present invention includes:

[0019] An equipment module for providing the equipment and facilities of a lithium battery material factory. The equipment module includes production equipment and public auxiliary equipment.

[0020] A model module for building a virtual factory model and simulating the operation behavior of the factory. The model module includes a simulation module, a communication module, an alarm module, and a diagnosis module.

[0021] A connection module is used to establish a communication protocol, establish a mapping relationship between the factory and the virtual factory, complete clock synchronization between the factory and the virtual factory, and ensure that data can be exchanged between different systems and components. The connection module includes an interface module and a protocol module;

[0022] A data module is used to collect, store, analyze, clean and pre-process data, and uses encryption technology and backup mechanisms to prevent data leakage and loss. The data module includes a database module, a data security module and a data analysis module;

[0023] The service module is used to integrate intelligent algorithms and machine learning algorithms, provide user interfaces and access control, and deploy the optimal setting plan to the factory production line. The service module includes a visualization module, a model editing module, a decision management module, and a communication module.

[0024] Beneficial effects: Compared with the prior art, the present invention has the following significant advantages: 1. Through the digital twins of the real factory and the virtual factory, a complete virtual factory model is formed to achieve comprehensive simulation and optimization management of the production process to improve the factory's production efficiency and product quality; 2. Real-time processing of the factory's material balance, optimization of process formulas, saving adjustment time, reducing energy waste, and simulating the factory's operating status under different settings through AI technology to determine the optimal setting plan and improve the factory's profitability. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 It is a schematic diagram of the process of the present invention;

[0026] Figure 2 Schematic diagram of the system architecture of the present invention. DETAILED DESCRIPTION

[0027] The technical solution of the present invention is described in detail below in conjunction with the accompanying drawings.

[0028] S1. Decompose the existing equipment and facilities of the lithium battery material factory step by step, including the main equipment such as the batching system, sand mill, spray drying system, sintering system, crushing packaging and vertical warehouse in the workshop, as well as the main facilities such as air compressor, nitrogen generator, chiller, etc., to complete the main production process of each section;

[0029] Establish equipment files, assign a unique equipment ID to each device, perform 3D scanning on the equipment through modeling tools, obtain 3D data of factory equipment, build a realistic factory model based on the actual size and parameters of the equipment, manually input detailed equipment information, including functional characteristics, connection relationships, and installation locations, use intelligent algorithms to classify and mark equipment, generate equipment decomposition diagrams, and ensure that each equipment component has a unique identification.

[0030] The equipment breakdown can be refined down to individual sensors (such as encoders, proximity switches, gratings, etc.) and drive units (such as cylinders, motors, etc.).

[0031] S2. Use BIM technology to build a virtual factory model that is consistent with the layout of the real factory.

[0032] Model according to the actual layout of the real factory, including the layout of equipment and facilities, power pipelines, logistics channels, etc., to ensure consistency with the layout of the real workshop for subsequent data mapping and analysis. Use BIM technology to build a virtual factory model that is consistent with the layout of the real factory; manually draw model elements such as equipment outlines and pipelines, automatically generate models based on CAD design drawings or point cloud data, conduct multi-dimensional analysis such as model symmetry and space utilization, and perform optimization processing. Add visual elements such as lighting and materials to enhance the realism of the model.

[0033] S3. Use 5G technology to establish a mapping relationship between the real factory and the virtual factory.

[0034] Connect the control systems of various equipment and facilities in the factory to the server of the virtual factory for networking and configuration to achieve data exchange. Use mature 5G technology to add network devices to establish a mapping relationship between the real factory and the virtual factory, ensure real-time data transmission and synchronization, complete the clock synchronization between the real factory and the virtual factory, and ensure the real-time nature of their operating parameters. Through network devices and data protocols, accurately map and reproduce all state parameters of the real factory in the virtual factory.

[0035] S4. Install various types of sensors in the real factory, including pressure, temperature, flow, and displacement sensors. The sensors collect the status of production equipment, environmental parameters (such as temperature, humidity, dust concentration), personnel operation data (such as operation duration, operation frequency), and material quality data (such as composition, purity, particle size distribution) in real time. The collected data is stored in the database module, and the operation log data is also recorded through the equipment control system and the personnel operation interface.

[0036] These data are transmitted to the edge computing device of the real factory through communication methods such as industrial buses. The edge computing device performs preliminary processing on the data, such as data compression and format conversion, to reduce data transmission latency and bandwidth occupancy. The data after edge computing processing is sent to a remote server for storage through the network. The data is stored in a database or a data lake, adopting a distributed storage architecture to ensure data security and reliability.

[0037] After the data is stored, data cleaning and preprocessing are carried out. Data cleaning mainly includes removing noise, missing values, and outliers from the data. Preprocessing includes operations such as data normalization, standardization, and data interpolation to ensure the accuracy and consistency of the data. Deploy data security-related measures to enhance the security of data storage. Use encryption technology to encrypt and store the data, and adopt a redundant backup mechanism to back up the data regularly to prevent data leakage and loss.

[0038] S5. Build a data model in the virtual factory server. The data model is a mathematical abstraction of the factory production process and equipment operating status. Based on factors such as the production process, equipment characteristics, and process parameters of the real factory, establish relevant physical models, statistical models, and machine learning models, etc., to describe the operating behavior of the factory.

[0039] Utilize AI technologies, such as machine learning algorithms (e.g., deep neural networks, reinforcement learning), to simulate the operating status of the factory under different settings. Use historical data and real-time data as the training set to adjust the model parameters to ensure that the model can accurately simulate the operating performance of the factory under different production parameters, process conditions, and external environments, including key indicators such as production efficiency, equipment failure rate, and product quality.

[0040] According to the simulation results, evaluate the advantages and disadvantages of different setting schemes. By comparing indicators such as production efficiency, energy consumption, and product quality under different schemes, determine the optimal setting scheme. At the same time, conduct a quantitative analysis of the uncertainties in the simulation process, such as equipment failure probability, raw material supply fluctuations, etc., to improve the reliability of the simulation results.

[0041] Use the latest sensor data, operation log data, and process data for the continuous optimization of the model. Through incremental learning and model update algorithms, continuously adjust the model parameters to make it better adapt to the changes in the factory production environment.

[0042] S6. The digital twin system can be used to verify process improvements without changing the actual production line configuration, such as adjusting the production rhythm, equipment upgrade and transformation, etc. Make corrections according to the results feedback by the system to achieve the expected effect. Deploy the optimized scheme into the real factory production line to achieve the improvement of production efficiency, reduction of energy consumption, and improvement of product quality, thus realizing the effect of maximizing benefits.

[0043] The virtual factory model can provide real-time data feedback and analysis results to support managers in making decisions and use the virtual factory model for product design and testing. Users can adjust the model parameters by themselves to quickly verify production improvement schemes without the need for downtime testing. The system uses big data analysis to quickly locate the root cause of production anomalies, enabling maintenance personnel to accurately troubleshoot the fault location.

[0044] The system can provide data support at all stages from the planning and design of the factory to the decommissioning of equipment. In the factory design stage, the factory layout is planned and equipment is selected through a virtual factory model. In the equipment procurement stage, the technical parameters and procurement costs of the equipment are optimized according to the simulation results of the virtual factory model. In the equipment installation and commissioning stage, the virtual factory model is used for pre-commissioning of equipment and optimization of the installation plan. In the production operation stage, the production efficiency and product quality are improved through real-time monitoring and optimization of the virtual factory model. In the equipment maintenance stage, a reasonable equipment maintenance plan is formulated according to the prediction and diagnosis results of the virtual factory model. In the equipment decommissioning stage, by analyzing the full life cycle data of the equipment, a basis is provided for the recycling and reuse of the equipment, realizing full life cycle management.

[0045] The lithium battery material factory management system based on digital twin technology includes:

[0046] The equipment module includes main equipment such as the batching system, sand mill, spray drying system, sintering system, crushing and packaging, and automated storage and retrieval system in the workshop, and also includes main facilities such as air compressors, nitrogen generators, and chillers, which complete the main production processes of each section. The equipment controller establishes data communication with the system server through methods such as OPC communication. The real factory installs sensors, intelligent meters, cameras and other devices to monitor and collect data on the status of production equipment, environment, personnel operations, material quality and other links, and sends the data to the remote server through industrial buses and other means.

[0047] The model module includes a simulation module, a communication module, an alarm module and a diagnosis module. Based on the design drawings and parameters of the real factory, a virtual factory model is established, and the model parameters are adjusted in a timely manner according to the actual data and feedback during the production process. The simulation module uses simulation software to simulate the behavior and performance of the real factory; the diagnosis module verifies the accuracy of the virtual factory model by comparing with the actual data of the real factory.

[0048] The connection module includes an interface module and a protocol module. The protocol module is used to establish communication protocols, integrate data from different sources into a unified platform, establish a mapping relationship between the real factory and the virtual factory, complete the clock synchronization between the real factory and the virtual factory, and ensure that data can be exchanged between different systems and components; the interface module develops application interfaces (APIs), develops APIs to support the interaction between applications, ensures the security of the APIs, and adopts authentication and authorization mechanisms to prevent unauthorized access.

[0049] Data module, including database module, data security module and data analysis module. Collect data from sensors and operation logs, store the collected data in databases or data lakes, use data analysis tools to extract valuable information, and have the functions of data cleaning and preprocessing to ensure the accuracy and consistency of data. Deploy data security-related measures, strengthen the security of data storage, and adopt encryption technology and backup mechanisms to prevent data leakage and loss

[0050] Service module, including visualization module, model editing module, decision management module and communication module. Used to develop services and applications based on digital twins, integrate intelligent algorithms and machine learning algorithms to provide intelligent decision-making support, provide user interfaces and access control. With the digital twin system, process transformation verification, production rhythm adjustment, equipment upgrade and transformation, etc. can be carried out without changing the actual production line configuration. Amend according to the results feedback by the system to achieve the expected effect, and deploy the optimized plan into the actual factory production line to achieve the effect of maximizing benefits.

Claims

1. A management method for a lithium battery material factory based on digital twin technology, characterized in that, The following steps are involved: S1. Decompose the equipment and facilities of the lithium battery material factory step by step, establish equipment files, assign a unique equipment ID to each equipment, obtain the three-dimensional data of the equipment through modeling tools, and build a physical model of the equipment; S2. Use BIM technology to build a virtual factory model consistent with the factory layout; S3, connect the control systems of the equipment and facilities of the factory to the server of the virtual factory and establish a mapping relationship; S4. Install various types of sensors in the factory, which collect production equipment status, environmental parameters, personnel operation data and material quality data, and store the collected data in a database; S5. Constructing a data model for describing the operation behavior of the factory in the virtual factory server, wherein the data model is a related physical model, statistical model and machine learning model established according to the production process, equipment characteristics and process parameters of the factory; S6. Use AI technology to simulate the factory's operating behavior under different production parameters, process conditions and external environments. Based on the simulation results, evaluate the pros and cons of different setting schemes, and determine the optimal setting scheme by comparing the production efficiency, energy consumption and product quality indicators under different schemes.

2. The management method of the lithium battery material factory according to claim 1, characterized in that S1 The device can be decomposed into a single sensor and drive unit.

3. The management method of the lithium battery material factory according to claim 1, characterized in that S1 also includes the use of intelligent algorithms to classify and label equipment and generate equipment breakdown diagrams.

4. The management method of the lithium battery material factory according to claim 1, wherein S4 also includes edge computing devices that transmit data to the factory. The edge computing devices compress and convert the data. The processed data is sent to a remote server via the network for storage. The data is stored in a database and adopts a distributed storage architecture.

5. The management method of a lithium battery material factory according to claim 1, characterized in that The multiple types of sensors in S4 include pressure, temperature, flow and displacement sensors, the environmental parameters include temperature, humidity, and dust concentration, the personnel operation data include operation time and operation frequency, and the material quality data includes composition, purity, and particle size distribution.

6. The management method of the lithium battery material factory according to claim 1, characterized in that, S4 also includes cleaning and preprocessing the data, wherein the cleaning includes removing noise, missing values and outliers in the data, and the preprocessing includes data normalization, standardization and data interpolation operations.

7. A management system for a lithium battery material factory based on digital twin technology, characterized in that, include: Equipment module, used to provide equipment and facilities for lithium battery material factories, the equipment module includes production equipment and public auxiliary equipment; A model module is used to construct a virtual factory model and simulate the operation behavior of the factory. The model module includes a simulation module, a communication module, an alarm module and a diagnosis module; A connection module is used to establish a communication protocol, establish a mapping relationship between the factory and the virtual factory, complete clock synchronization between the factory and the virtual factory, and ensure that data can be exchanged between different systems and components. The connection module includes an interface module and a protocol module; A data module is used to collect, store, analyze, clean and pre-process data, and uses encryption technology and backup mechanisms to prevent data leakage and loss. The data module includes a database module, a data security module and a data analysis module; A service module, which is used to integrate intelligent algorithms and machine learning algorithms, provide a user interface and access control, and deploy the optimal setting scheme into the factory production line. The service module includes a visualization module, a model editing module, a decision management module, and a communication module.

8. The lithium battery material factory management system according to claim 7, wherein, The production equipment includes an in-plant batching system, a sand mill, a spray drying system, a sintering system, a crushing and packaging system, and an automated storage and retrieval system. The public auxiliary equipment includes an air compressor, a nitrogen generator, and a chiller.

9. A computer device, characterized in that, It includes one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors. When the program is executed by the processor, it implements the steps of a method for managing a lithium battery material factory based on digital twin technology as described in any one of claims 1-6.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of a method for managing a lithium battery material factory based on digital twin technology as described in any one of claims 1-6.

Images