Battery production method and system

Abstract

This application discloses a battery manufacturing method and system. The method includes acquiring actual battery manufacturing process control parameters and actual battery manufacturing result data for different battery manufacturing steps; acquiring reference battery manufacturing process control parameters for the different battery manufacturing steps under different production conditions; adjusting the actual battery manufacturing process control parameters based on the reference battery manufacturing process control parameters and the actual battery manufacturing result data to obtain adjusted actual battery control process parameters; and controlling battery production based on the adjusted actual battery control process parameters. This solution can improve battery manufacturing efficiency.

Description

Technical Field

[0001] This application relates to the field of battery manufacturing technology, and in particular to a battery manufacturing method and system. Background Technology

[0002] With the rapid development of intelligent manufacturing technology, modern factories are required to accelerate production cycles and improve production efficiency as much as possible.

[0003] Currently, the factory mainly uses programmable logic controllers (PLCs) to control each piece of equipment individually. Each piece of equipment automatically performs corresponding operations according to pre-set logic.

[0004] However, the current production control method has low production efficiency. Summary of the Invention

[0005] This application provides a battery manufacturing method and system that can improve battery manufacturing efficiency.

[0006] In a first aspect, this application provides a battery manufacturing method, comprising:

[0007] Obtain actual battery production process control parameters and actual battery production result data for different battery production processes;

[0008] Obtain reference battery production process control parameters for the different battery production processes under different production conditions;

[0009] Based on the reference battery production process control parameters and the actual battery production result data, the actual battery production process control parameters are adjusted to obtain the adjusted actual battery control process parameters.

[0010] Battery production is controlled based on the adjusted actual battery control process parameters.

[0011] In this technical solution, by aggregating the actual battery control process parameters and actual battery production result data from different battery production processes, it is beneficial to promptly identify problems that arise during production and adjust the actual battery control process parameters in the process in a timely manner to prevent a decline in the product yield. This ensures that the battery production result data can meet production target requirements as much as possible, thereby improving battery production efficiency.

[0012] In one possible design of the first aspect, adjusting the actual battery production process control parameters based on the reference battery production process control parameters and the actual battery production result data to obtain adjusted actual battery control process parameters includes:

[0013] Obtain reference battery production process control parameters for the target process and actual battery production result data for the upstream processes of the target process;

[0014] Based on the actual battery production results data of the upstream process, the reference battery production process control parameters of the target process are adjusted to obtain the adjusted reference battery production process control parameters.

[0015] Based on the adjusted reference battery production process control parameters and the actual battery production result data of the target process, the actual battery production process parameters of the target process are adjusted to obtain the adjusted actual battery production process control parameters of the target process.

[0016] In this technical solution, by acquiring actual battery production result data from upstream processes, it is beneficial to promptly identify problems in the production process and provide actual battery production process parameter adjustment strategies for the next target process, thereby preventing a decrease in the yield of products in the next target process and improving battery production efficiency.

[0017] Another possible design for the first aspect also includes:

[0018] Check for any abnormalities in the actual battery production process control parameters and / or actual battery production result data for each battery production step;

[0019] In the event of an anomaly, output an anomaly message and / or determine the cause of the anomaly.

[0020] In this technical solution, by performing anomaly monitoring, timely alarms can be issued to notify on-site personnel to investigate the problem promptly and avoid large-scale work stoppages.

[0021] In another possible design of the first aspect, the detection of whether there are anomalies in the actual battery production process control parameters and / or actual battery production result data of each battery production step includes:

[0022] Obtain the first actual battery production result data of the battery production process at the first moment and the second actual battery production result data of the battery production process at the second moment;

[0023] Determine the amount of fluctuation between the first actual battery production result data and the second actual battery production result data;

[0024] Based on the fluctuation amount, determine whether there are any abnormalities in the actual battery production process control parameters and / or actual battery production result data of the battery production process.

[0025] In this technical solution, by collecting and comparing actual battery production results data at two different times, when fluctuations are found in the actual battery production results data through comparison, anomalies in the battery production process can be quickly identified, improving the timeliness of anomaly detection, so as to facilitate rapid problem handling and ensure battery production quality and efficiency.

[0026] Another possible design for the first aspect also includes:

[0027] In the event of a failure in the first process, priority is given to acquiring the associated data related to the failure; the first process can be any of the different battery production processes.

[0028] Based on the associated data, the cause of the failure in the first process is determined.

[0029] In this technical solution, by prioritizing the acquisition of relevant data associated with the fault and determining the cause of the fault, a fault solution can be provided, which can quickly resolve the problem, prevent the problem from escalating and causing large-scale downtime, and improve production efficiency.

[0030] In another possible design of the first aspect, obtaining reference battery production process control parameters for the different battery production processes under different production conditions includes:

[0031] Based on the production process control parameter determination model, the actual battery production process control parameters of the second process, and the actual battery production result data, reference battery production process control parameters for the second process under different production conditions are obtained. The second process can be any one of the different battery production processes. The production process control parameter determination model is trained using the actual battery production result data of the battery production process under different production conditions as input and the production process control parameters of the battery production process under different production conditions as output.

[0032] In this technical solution, by aggregating actual battery production process control parameters and actual battery production result data from different processes as training data, a production process control parameter determination model is trained, thereby continuously optimizing and adjusting the actual battery production process control parameters and improving the accuracy of parameter adjustment.

[0033] In another possible design of the first aspect, the step of determining the model based on the production process control parameters, the actual battery production process control parameters of the second process, and the actual battery production result data, and obtaining the reference battery production process control parameters of the second process under different production conditions, includes:

[0034] Summarize the actual production process control parameters and actual battery production results data for the second process on each production line in each production base;

[0035] Based on the production process control parameters, the model is determined, along with the actual production process control parameters and actual battery production result data for the second process on each production line in each production base. Reference battery production process control parameters for the second process under different production conditions are then obtained.

[0036] In this technical solution, by utilizing the actual production process control parameters and actual battery production result data of the same process on each production line in each production base, the training data can be enriched, the training effect of the production process control parameter determination model can be improved, and thus it can predict more accurate reference battery production process control parameters.

[0037] Another possible design for the first aspect also includes:

[0038] In response to an application update request, determine whether the application update request carries authentication information;

[0039] If the authentication information matches the preset authentication information, the encrypted application software update package is obtained according to the application update request.

[0040] The encrypted application software update package is sent to the battery production process control equipment on each production line in each production base. The encrypted application software update package is used by the battery production process control equipment to update the application software to control battery production after being decrypted according to a preset encryption algorithm.

[0041] In this technical solution, by distributing the encrypted application software update package to the battery production process control equipment on each production line in each production base, maintenance personnel can remotely access and control the industrial control computer, eliminating the need for on-site personnel to travel, thus reducing maintenance costs and improving maintenance efficiency. Furthermore, remote data transmission allows for real-time updates and upgrades to the software in the industrial control computer, enhancing the flexibility and responsiveness of the production system.

[0042] Another possible design for the first aspect also includes:

[0043] The battery production process control equipment obtains the application software version information before and after each application software update.

[0044] Application logs are generated based on the version information before and after the update.

[0045] In this technical solution, by recording the version information of the application software during the update, it is easier to conduct subsequent troubleshooting and rollback operations, thereby improving the stability of the application software during the update process.

[0046] In another possible design of the first aspect, after obtaining the actual battery production process control parameters and actual battery production result data in different battery production processes, the method further includes:

[0047] Preprocessing is performed on the actual battery production process control parameters and actual battery production result data in the different battery production processes.

[0048] The pre-processed actual battery production process control parameters and actual battery production results data are encrypted and stored in the database.

[0049] In this technical solution, data is preprocessed and then encrypted before being stored in the database. This prevents the leakage of core process parameters in the actual battery production process and facilitates subsequent process production analysis. Based on the analysis results, targeted process optimization can be carried out to improve production efficiency.

[0050] In another possible design of the first aspect, the preprocessing of the actual battery production process control parameters and actual battery production result data in the different battery production processes includes:

[0051] When the actual battery production process control parameters and actual battery production result data are unstructured data, the actual battery production process control parameters and actual battery production result data are compressed.

[0052] When the actual battery production process control parameters and actual battery production result data are structured data, multiple key data are extracted from the actual battery production process control parameters and actual battery production result data, and the data format of each key data is adjusted to the target format.

[0053] In this technical solution, the performance of the data processing system is improved and the consumption of computing resources is reduced by optimizing the data format. Furthermore, by compressing unstructured data, high-fidelity data can be obtained, supporting more accurate and reliable production decisions.

[0054] Another possible design for the first aspect also includes:

[0055] Obtain the actual battery production process parameters and actual battery production result data of the third process in the different battery production processes at each moment; the third process is any one of the different battery production processes.

[0056] Based on the actual battery production process parameters and actual battery production result data at each moment of the third process, the data change trend of the third process is obtained.

[0057] In this technical solution, by analyzing the actual battery production process parameters and actual battery production results data of the third process at each moment, a data change trend is formed, which can more intuitively grasp the changes in the process, and facilitate problem investigation and process optimization.

[0058] Another possible design for the first aspect also includes:

[0059] In response to a data access request from a target object, determine whether the access permissions of the target object match preset permissions;

[0060] If the access permissions of the target object match the preset permissions, the encrypted actual battery production process control parameters and actual battery production result data stored in the database are sent to the target object.

[0061] In this technical solution, by setting access permissions, it is possible to prevent other unauthorized users from accessing the actual battery production process control parameters and actual battery production result data in the database, thereby improving data security and preventing the leakage of process production data.

[0062] In another possible design of the first aspect, after obtaining the actual battery production process control parameters and actual battery production result data for different battery production steps, the method further includes:

[0063] Acquire the identification information of each actual battery production process control parameter and actual battery production result data in the battery production process, wherein the battery production process includes at least one actual battery production process control parameter and at least one actual battery production result data.

[0064] Based on the identification information, verify whether there are any missing data in the battery production process;

[0065] If data is missing, output a data anomaly message.

[0066] In this technical solution, data loss can be prevented and data integrity can be ensured by using identification information to detect data.

[0067] Secondly, this application provides a battery production system, including a cloud server and at least one edge device that is communicatively connected to the cloud server, with each edge device connected to an industrial control computer set up in different battery production processes on the battery production line.

[0068] The edge device is used to obtain actual battery production process control parameters and actual battery production result data for different battery production processes from the industrial control computer.

[0069] The edge device is further configured to obtain reference battery production process control parameters for different battery production processes under different production conditions from the cloud server; adjust the actual battery production process control parameters according to the reference battery production process control parameters and the actual battery production result data to obtain adjusted actual battery control process parameters; and send the adjusted actual battery control process parameters to the corresponding industrial control computer so that the industrial control computer produces batteries according to the adjusted actual battery control process parameters.

[0070] The cloud server is used to send reference battery production process control parameters for different battery production processes under different production conditions to the edge device. Attached Figure Description

[0071] The features, advantages, and technical effects of exemplary embodiments of this application will now be described with reference to the accompanying drawings.

[0072] Figure 1 This is a functional architecture diagram of a battery production system provided in an embodiment of this application;

[0073] Figure 2 This is a functional architecture diagram of a battery production system provided in another embodiment of this application;

[0074] Figure 3 This is a schematic diagram of remote data interaction provided in an embodiment of this application;

[0075] Figure 4 This is a schematic diagram of the data transmission process provided in an embodiment of this application;

[0076] Figure 5 A schematic diagram of a data transmission process provided in another embodiment of this application;

[0077] Figure 6 A schematic flowchart of a battery manufacturing method provided in an embodiment of this application;

[0078] Figure 7 A schematic flowchart of a battery manufacturing method provided in yet another embodiment of this application;

[0079] Figure 8 This is a schematic diagram of the data architecture of a battery production system provided in an embodiment of this application;

[0080] Figure 9 This is a schematic diagram of the security architecture of a battery production system provided in an embodiment of this application;

[0081] Figure 10 A schematic flowchart of a battery manufacturing method provided in an embodiment of this application;

[0082] Figure 11A schematic flowchart of a battery manufacturing method provided in yet another embodiment of this application;

[0083] Figure 12 A schematic flowchart of a battery manufacturing method provided in yet another embodiment of this application;

[0084] Figure 13 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0085] The accompanying drawings are not necessarily drawn to scale. Detailed Implementation

[0086] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0087] With the rapid development of intelligent manufacturing technologies, modern factories face the challenge of ever-increasing production speeds. This necessitates that production equipment and systems on production lines possess higher responsiveness and processing capabilities. Simultaneously, the large-scale application of Customizable Tooling Systems (CTS) makes production lines more flexible and adaptable, enabling them to quickly meet the manufacturing needs of different products. Furthermore, the introduction of machine vision technology further enhances the accuracy and efficiency of product quality inspection. Against this backdrop, modern factories require production systems capable of improving both production efficiency and quality.

[0088] In related technologies, factories employ Programmable Logic Controllers (PLCs), Industrial Personal Computers (IPCs), and machine vision systems to achieve production control. A PLC is a computer system specifically designed for industrial control, used for data acquisition, logical operations, and other tasks in automated control processes. It can execute a series of control operations according to preset programs and is one of the core components of factory automation. An IPC is a personal computer specifically designed for industrial environments. Compared to ordinary computers, IPCs have better anti-interference capabilities and stability, making them suitable for industrial environments with long-term continuous operation. Machine vision systems utilize cameras and other imaging devices to acquire image information and analyze and process the images using specialized software algorithms to detect product quality, locate part positions, and other tasks, thereby improving the level of automation in the production process.

[0089] Despite the adoption of PLCs, IPCs, and machine vision systems in the production system, it is still difficult to meet the production efficiency requirements of modern factories. The main problems of this production system are as follows: (1) As the amount of data to be processed during the production process increases, the storage capacity of PLCs becomes insufficient, making it difficult to store large amounts of data. Moreover, in a high-speed production environment, the amount and frequency of data that PLCs need to process increase, leading to insufficient processing capacity and potential lag or crashes. (2) Under certain extreme conditions (such as when processing a large number of concurrent data streams), IPCs may encounter performance bottlenecks. (3) In a smart manufacturing environment, frequent data exchange and sharing are required between different processes, and single-machine intelligence is unable to handle such complex collaborative work. In summary, the above-mentioned technologies still have significant shortcomings in terms of high-performance computing requirements, data processing capabilities, and global collaborative control. The root cause of these problems is that the current technical architecture of the production system has failed to keep up with the pace of data growth and lacks an effective cross-device collaboration mechanism.

[0090] To address the aforementioned issues, this application provides a battery production method and system. By utilizing cloud servers, edge devices, and industrial control computers to build a battery production system, it deeply integrates production data involved in various processes during battery production (specifically including various control parameters of the industrial control computer during battery production and the production result data of the corresponding control parameters of the industrial control computer during battery production). Combined with the high-precision manufacturing requirements of batteries, it enables the flow of production data across processes and production bases between different devices, thereby achieving efficient collaborative operation, improving the yield rate of battery production, and increasing battery production efficiency.

[0091] The technical solution of this application will now be described in detail through specific embodiments. It should be noted that the following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments.

[0092] First, we will introduce the battery production system in this plan. Figure 1 The functional architecture diagram of the battery production system provided in the embodiments of this application is as follows: Figure 1 As shown, one or more industrial control computers are deployed at different stages of the battery production line. These industrial control computers are mainly used to execute the actual battery production operations. During the production process, the industrial control computers acquire the actual battery production process control parameters and actual battery production result data in real time at the corresponding stages.

[0093] For example, battery manufacturing processes may include at least one of stirring, coating, cold pressing, die cutting, and winding.

[0094] For example, actual battery production result data may include at least one of the following: raw material status, process parameters, and industrial control computer status.

[0095] For example, actual battery production process control parameters can refer to the parameters required to control the industrial control computer, such as the aforementioned process parameters. For instance, taking the stirring process as an example, process parameters can refer to the stirring time and stirring speed, etc. Additionally, actual battery production process control parameters can also include equipment parameters.

[0096] In this embodiment, the industrial control computer can be a PLC or other intelligent manufacturing equipment. The industrial control computer is used to execute battery production-related processes, such as key processes like stirring, coating, cold pressing, die cutting, and winding. One or more industrial control computers can be deployed to work together to complete a single process. For example, in the stirring process, there are industrial control computers A and B. Edge devices can control industrial control computers A and B to work together to complete the stirring process.

[0097] Each step in the battery production process has corresponding control parameters. For example, during the mixing process, the mixing speed and time need to be controlled. Edge devices collect the actual battery production process control parameters from industrial computers A and B during the mixing process, allowing for real-time monitoring of the mixing process. Based on changes in these control parameters, the edge devices can adjust them promptly. For instance, if the edge devices detect a sudden increase in the mixing speed of industrial computer A, they can issue an adjustment strategy to reduce its mixing speed. This ensures process quality and solves the problem of reduced production efficiency caused by the lack of unified coordination mechanisms among automated equipment in current factories.

[0098] Coating is a process of uniformly applying a layer of liquid or slurry to the surface of a substrate and then curing it through drying or other methods to form a thin film. Cold pressing is a process of making materials denser and smoother by applying high pressure without heating. In battery production, cold pressing is mainly used for pressing electrode materials. By precisely controlling parameters such as pressure and speed, the density and smoothness of the electrodes can be significantly improved, thereby improving the electrochemical performance of the battery. Cold pressing can improve key performance indicators such as energy density and cycle life of batteries, making it an indispensable step in lithium battery production. Die-cutting is a process of cutting materials into a predetermined shape. Die-cutting technology is widely used in many industries, including packaging, printing, electronics, and lithium battery production. Winding is a process of winding materials into a roll in a specific way. In lithium battery production, winding refers to the process of winding the positive electrode, negative electrode, and separator materials into a battery cell in a certain order and manner.

[0099] In this embodiment, refer to Figure 1 Edge devices are deployed in production facilities (e.g.) Figure 1 The system includes production bases 1 and 2, each of which can be configured with one or more edge devices. Edge devices within the same production base can collect data from industrial control computers (specifically, this data collection can be achieved by calling relevant interfaces). This allows the edge devices to aggregate the actual battery production process control parameters and actual battery production results data from each industrial control computer in that production base. Then, through edge computing, the edge devices can process these actual battery production process control parameters and actual battery production results data in a timely manner, thereby promptly identifying any problems that may exist in the production process of each industrial control computer.

[0100] The edge device can obtain reference battery production process control parameters for different processes under different production conditions from the cloud server; based on the reference battery production process control parameters and actual battery production result data, it adjusts the actual battery production process control parameters to obtain the adjusted actual battery control process parameters; and sends the adjusted actual battery control process parameters to the corresponding industrial control computer so that the industrial control computer can produce batteries according to the adjusted actual battery control process parameters.

[0101] In this embodiment, since the cloud server is located remotely, while the edge devices and workstations are located in the production base, the aforementioned production system can form a distributed system architecture. This allows for collaborative work among multiple devices using distributed computing and intelligent control technologies. Through intelligent algorithms and a distributed architecture, this production system can achieve efficient data sharing, decision-making, and control execution among multiple devices.

[0102] In this embodiment, reference continues to be made to Figure 1 In the entire battery production system, a cloud server can be remotely deployed at headquarters. Through communication with edge devices in various production bases, it can aggregate the actual battery production process control parameters and actual battery production results data from the industrial control computers at each stage of the process. Furthermore, the edge devices in each production base communicate with the industrial control computers there, allowing for real-time monitoring of the production process and thus achieving comprehensive monitoring of the entire battery production process.

[0103] In this embodiment, the cloud server is able to obtain the actual battery production process control parameters and actual battery production result data of each industrial control computer through edge devices. It can then analyze these actual battery production process control parameters and actual battery production result data to determine the reference battery production process control parameters that can maximize the production efficiency of the industrial control computer.

[0104] For example, by analyzing the actual battery production process control parameters and actual battery production result data of all industrial control computers in the entire battery production process, a cloud server can provide a reference stirring time and a reference stirring speed. When industrial control computer A works at the reference stirring time and reference stirring speed, the efficiency of the stirring process and other processes on the entire production line can be maximized.

[0105] In this embodiment of the application, by building a battery production system consisting of cloud servers, edge devices and industrial control computers, the actual battery control process parameters and actual battery production result data of each industrial control computer in different processes can be aggregated during the battery production process. This is beneficial for timely detection of problems in the production process and timely adjustment of the actual battery control process parameters of the industrial control computers in the process, so as to prevent the decline in the yield of high-quality products and ensure that the battery production result data can meet the production target requirements as much as possible, thereby improving battery production efficiency.

[0106] For example, Figure 2 This is a functional architecture diagram of a battery production system provided in another embodiment of this application, as shown below. Figure 2 As shown, cloud server 25 can be deployed in a regional or headquarters location, and a process intelligent control system is deployed on the cloud server. This process intelligent control system includes functions such as core process parameter protection and process intelligent control application management, used to deploy process intelligent control applications to edge devices 24. The cloud server can interact with edge devices deployed in the production base 23 through message queues (e.g., Kafka). Multiple industrial control computers can be deployed on the production line, such as industrial control computers 20, 21, and 22. Additionally, PLCs can be deployed on the production line to assist the industrial control computers in performing production tasks.

[0107] In some embodiments, after the edge device uploads the actual battery production process control parameters and actual battery production result data of different processes to the cloud server, the cloud server can adjust the actual battery production process control parameters according to the actual battery production process control parameters and actual battery production result data of different processes, obtain the adjusted actual battery control process parameters, send the adjusted actual battery control process parameters to the edge device, and then the edge device forwards them to the corresponding industrial control computer to realize the adjustment and update of the battery control process parameters.

[0108] The cloud server, after retrieving data from edge devices via message queues, can store it in a database. Furthermore, because the cloud server can communicate with edge devices across multiple production bases, it can obtain actual battery production process control parameters and actual battery production results data from each industrial control computer in each production base, making the data in the cloud server more complete and comprehensive. When the cloud server performs in-depth analysis of the stored historical battery production process control parameters and actual battery production results data, it can develop sophisticated adaptive control algorithms based on artificial intelligence technology, enabling intelligent decision-making and process optimization across multiple battery production processes. For example, historical battery production process control parameters and actual battery production results data can be used as training data to train a production process control parameter determination model. This trained model can then be deployed on the cloud server to predict the reference battery production process control parameters for each industrial control computer in each battery production process.

[0109] Among them, the production process control parameter determination model is trained by the cloud server using actual battery production result data samples of different processes under different production conditions as input and battery production process control parameter labels as output.

[0110] In this embodiment, taking a battery production process including at least one of stirring, coating, cold pressing, die cutting, and winding as an example, the production process control parameter determination model in the aforementioned cloud server can predict the reference battery production process control parameters (i.e., optimal battery production control parameters) settings for each industrial control computer in each key process such as stirring, coating, cold pressing, die cutting, and winding. Furthermore, based on a large amount of historical battery production process control parameters and battery production result data, the cloud server can train the production process control parameter determination model to identify the optimal battery production control parameter combinations for each process under different operating conditions. This facilitates edge devices in real-time adjustment of the battery production control parameters of the industrial control computers in each process during battery production, thereby improving production efficiency and quality.

[0111] For example, the cloud server determines the model based on the trained production process control parameters, the actual battery production process results of the second process uploaded by each edge device, and outputs the reference battery production process control parameters of the second process under different production conditions.

[0112] The second process can be any one of the different processes.

[0113] For example, in the mixing process, the production process control parameter determination model deployed in the cloud server can predict the mixing speed and mixing time (equivalent to the target production parameters, i.e. the optimal production parameters) and send them to the edge device, which then adjusts the mixing speed and mixing time of the industrial control computer to ensure uniform mixing of materials.

[0114] For example, in the coating process, the cloud server and edge device mentioned above can be used to precisely control the coating thickness and speed of the industrial computer when performing the coating process, so as to improve the coating effect.

[0115] In this embodiment, when the battery production result data includes at least one of the following: raw material status, process parameters, and industrial control computer status, analysis of this data allows the production process control parameter determination model to form an adaptive control algorithm. This algorithm can continuously learn and adapt to changes in the production environment, including changes in raw material characteristics and fluctuations in equipment status, thereby further improving the robustness and stability of the production process. Furthermore, through continuous collection and analysis of battery production process control parameters and battery production result data, the adaptive control algorithm can continuously optimize itself, ensuring that every detail of the battery production process reaches its optimal state.

[0116] In this embodiment, the pre-trained production process control parameter determination model can provide the industrial control computer with a reasonable dynamic adjustment control strategy based on the real-time collected actual battery production process control parameters and actual battery production result data, thereby adjusting the battery production parameters of the industrial control computer and ensuring continuous optimization and efficiency improvement of the production process.

[0117] In this embodiment, the adaptive control algorithm described above can be deployed not only on a cloud server but also on an edge device. Through this adaptive control algorithm, dynamic adjustment of control strategies, optimization of process parameter settings, and multi-process collaborative optimization can be achieved in the battery production process.

[0118] The dynamic adjustment control strategy refers to using adaptive control algorithms to collect real-time control parameters of the battery production process (i.e., actual battery production process control parameters) and dynamically adjust the operating conditions based on these parameters. For example, in the mixing process, the adaptive control algorithm can dynamically adjust the mixing parameters based on the real-time monitored mixing speed and time to ensure uniform mixing of materials. Similarly, in the coating process, the adaptive control algorithm can precisely control the coating thickness and speed to improve the coating effect.

[0119] Among them, optimizing process parameter settings means that the adaptive control algorithm can determine the model through the production process control parameters obtained by the above training, learn and identify the optimal combination of battery production process control parameters for each industrial control computer in each process under different working conditions, so as to adjust the battery production process control parameters of these industrial control computers in real time during the production process, thereby improving production efficiency and product quality.

[0120] Multi-process collaborative optimization refers to the use of adaptive control algorithms to optimize the control parameters of a single battery production process. Furthermore, adaptive control algorithms can also achieve intelligent decision-making and process optimization across multiple processes. By comprehensively analyzing data from the entire production chain, adaptive control algorithms can find the optimal overall production plan, thereby improving production efficiency.

[0121] Adaptiveness can refer to the ability to automatically adjust its behavior or configuration according to changes in the external environment or internal state in order to maintain the achievement of predetermined goals.

[0122] In this embodiment, the cloud server can determine the rationality of the actual battery production process control parameters based on historical data and actual battery production results (judging rationality based on production efficiency and quality). If the parameters are deemed unreasonable, the cloud server can adjust them, providing an adjusted set of actual battery control process parameters. This adjusted parameter can then be forwarded from the edge device to the industrial control computer. Furthermore, as mentioned above, the edge device can adjust the actual battery production process control parameters in real time based on the actual battery production results. The difference lies in the fact that the cloud server, due to data analysis (integrating data from all production bases and processes, and involving model training and prediction), exhibits a lag in parameter adjustments. Edge device adjustments are more timely; once the edge device detects anomalies in the actual production process control parameters and actual battery production results (such as drastic fluctuations), it can immediately make adjustments.

[0123] In some embodiments, as mentioned above, battery production processes may include stirring, coating, cold pressing, die-cutting, winding, etc., and each process may be configured with one or more industrial control computers to execute that process. The edge device can also acquire actual battery production result data from the industrial control computers in the upstream battery production processes of the target process, and determine adjusted actual battery control process parameters based on the actual battery production result data and the reference battery production process control parameters of the target process. Then, it sends the adjusted actual battery control process parameters to the industrial control computer corresponding to the target process, so that the industrial control computer produces batteries according to the adjusted actual battery control process parameters.

[0124] For example, taking the winding process as the target process, the industrial control computer can accurately calculate the optimal matching scheme of the anode and cathode film rolls through edge computing algorithms, and seamlessly transmit the relevant battery control process parameters in the optimal matching scheme to the industrial control computer in the subsequent process (such as the winding process). The industrial control computer in the winding process executes the winding process according to the relevant battery control process parameters in the optimal matching scheme, which can significantly improve the yield of bare cells.

[0125] In this embodiment, by aggregating the actual battery production process control parameters and actual battery production result data of each industrial control computer in different processes through edge devices, it is beneficial to promptly identify problems that occur in the production process and provide production strategies for the industrial control computers in the next process, so as to prevent the decline in the yield of high-quality products and improve battery production efficiency.

[0126] Continue to refer to the above. Figure 2 In some embodiments, edge devices can not only achieve cross-process matching and optimization, accurately calculating the optimal matching scheme for anode and cathode film rolls through edge computing algorithms and seamlessly transmitting these parameters to subsequent processes, but also dynamically adjust the battery production process control parameters of various industrial control computers in the same process. Specifically, after aggregating the actual battery production process control parameters and actual battery production result data of various industrial control computers in the same process, the edge device can monitor the real-time changes of these parameters and results. Based on these parameters and reference parameters provided by the cloud server, it can immediately obtain feedback on the production status and adjust the parameters of these industrial control computers. For example, in the coating process, changes in key indicators such as film width and thickness can be quickly captured and adjusted, thereby avoiding defects caused by data lag.

[0127] In addition, edge devices can also detect whether there are any abnormalities in the actual battery production process control parameters and / or actual battery production result data of each process. If there are abnormalities, they can output abnormality prompts and / or determine the cause of the abnormality.

[0128] For example, when the edge device detects drastic changes in the characteristics of raw materials or significant fluctuations in the status of the operating machine, it can output an anomaly alert. For instance, the anomaly alert may include audible and visual alarms and / or text prompts.

[0129] Continue to refer to the above. Figure 2 In this embodiment, the battery production system described above can be constructed using programming languages ​​(such as JAVA, Python, PLC, etc.) to provide a systematic solution for cross-process and cross-site collaboration.

[0130] Among them, the edge device uses edge computing algorithms to process the actual battery production process control parameters and / or actual battery production result data (such as key indicators such as film width and thickness in the coating process, and data in the die-cutting process (such as film width data of anode and cathode film rolls) in real time (real-time processing can include the above-mentioned anomaly monitoring and parameter adjustment, etc.).

[0131] In this embodiment, by performing anomaly monitoring, timely anomaly alarms can be issued to notify on-site personnel to investigate problems promptly and avoid large-scale work stoppages. In addition, by deploying edge computing algorithms in the edge devices of the base, key data in the battery production process can be aggregated and processed in real time, and feedback on the production status can be obtained immediately. The battery production parameters of the industrial control computer can be adjusted in a timely manner, thereby avoiding the generation of defective products due to data lag.

[0132] In other embodiments, in addition to mining and analyzing historical battery production process control parameters and battery production result data to form the aforementioned adaptive algorithm, the cloud server can also aggregate battery production result data (including raw material status, process parameters, equipment status, etc.) from different processes and bases in real time through edge devices. This allows the cloud server to investigate the real-time aggregated battery production result data. For example, when abnormal data appears in this battery production result data, the cloud server can immediately output prompt information (such as alarm prompts) and provide preliminary analysis results (such as which industrial control computer in which process is malfunctioning), assisting on-site employees in quickly locating the problem, thereby reducing the downtime and maintenance costs of the industrial control computers.

[0133] In this embodiment, the cloud server aggregates and analyzes battery production results data from different processes and production bases in real time. Once a problem is detected, it can assist on-site personnel in quickly locating the problem, thereby reducing downtime and maintenance costs. Through the cooperation between the cloud server, edge devices, and industrial control computers, battery production efficiency can be effectively improved.

[0134] In some embodiments, in order to ensure that problems can be resolved in a timely manner, when an edge device detects a fault in a first process on the production line, it can promptly aggregate the actual battery production process control parameters and actual battery production result data that are abnormal in the industrial control computer of that first process to the edge data (specifically, it can refer to the associated data related to the fault), and then send the associated data to the cloud server first, so that the cloud server can determine the cause of the fault and provide a fault solution.

[0135] Furthermore, to ensure timely detection and rapid resolution of issues, the industrial control computer can upload actual battery production process control parameters and actual battery production result data to the edge data in real time. During the transmission of these parameters and data, network resources can be dynamically adjusted based on their priority, meaning the amount of network resources allocated to different priority levels can be adjusted to adapt to changes in the production process.

[0136] For example, the priorities of each actual battery production process control parameter and actual battery production result data can be determined, and the actual battery production process control parameters and actual battery production result data can be transmitted to edge devices in descending order of priority. For instance, when a failure occurs in a certain process, network resources can be immediately adjusted to prioritize the transmission of production data related to the failure in that process, helping to quickly diagnose and resolve the failure.

[0137] Furthermore, in some embodiments, when transmitting actual battery production process control parameters and actual battery production result data to the edge device, the industrial control computer can configure transmission sequence numbers for these actual battery production process control parameters and actual battery production result data according to the transmission order of each actual battery production process control parameter and actual battery production result data. When the edge device receives these actual battery production process control parameters and actual battery production result data, it reads the transmission sequence numbers in sequence. If one of the transmission sequence numbers is found to be missing, it can be determined that the data transmission is incomplete and there is a data loss.

[0138] Figure 3 This is a schematic diagram of remote data interaction provided in an embodiment of this application, such as... Figure 3 As shown, since the cloud server can be deployed in the remote central intelligent control system 30, in order to reduce the number of times battery production system maintenance personnel need to go to the base for on-site maintenance and improve maintenance efficiency, maintenance personnel can send application commands through the central intelligent control system on the cloud server to the remote update service 31 (i.e., the central OTA service) based on central over-the-air technology. Then, the relevant process intelligent control applications are deployed to edge devices (including devices 32, 33, and 34) through the central OTA service. Among them, the central intelligent control system calls the interface issued by the central OTA service software, and the central OTA service receives the issued commands to execute the actual application deployment process.

[0139] In other embodiments, the remote update service can also be used to update the software version in the industrial control computer. Specifically, the cloud server can send a software update package to the remote update service through the first interface of the remote update service; and if the software version in the industrial control computer and the version of the software update package do not match, the remote update service sends a software update package to the industrial control computer; the industrial control computer then updates its software according to the software update package to perform battery production operations based on the updated software.

[0140] In this embodiment, in the above Figure 3 Building upon this foundation, a highly secure remote encrypted operation and maintenance channel can be established as a pre-built encrypted channel to ensure the confidentiality and integrity of data transmission. For example, encryption algorithms and authentication mechanisms can be used to build this remote encrypted operation and maintenance channel.

[0141] In this embodiment, the cloud server can transmit control commands (such as the aforementioned software update package) to edge devices in the production base via the encrypted channel and the central OTA service. The industrial control computer can then request and execute these control commands from the edge devices. For example, the control command may be a software update command or an application deployment command.

[0142] For example, taking the control command as a software update command, the software in the industrial control computer can be updated and upgraded in real time without affecting the production operation of the industrial control computer.

[0143] Furthermore, in some implementations, when maintenance personnel remotely update and upgrade the software of the industrial control computer, each software update and upgrade operation can be marked by a version number. The version number enables version management and rollback mechanisms for software updates, accurately controls the scope of updates, and effectively avoids production interruptions or equipment failures caused by improper updates.

[0144] In addition, in some implementations, the cloud server can also access and control the industrial control computer through this remote encrypted operation and maintenance channel, thereby enabling remote operation and maintenance personnel to remotely deploy and configure the industrial control computer.

[0145] In addition, in some implementations, the battery production system can be configured with log recording and auditing functions to track and record every remote access and operation of the cloud server in real time, providing detailed data support for subsequent troubleshooting and tracing.

[0146] In this embodiment, by establishing a remote encrypted operation and maintenance channel, the confidentiality of data transmission can be improved. Simultaneously, operation and maintenance personnel can remotely access and control the industrial control computer, eliminating the need for on-site travel and reducing operation and maintenance costs while improving efficiency. Furthermore, data transmission via the remote encrypted operation and maintenance channel allows for real-time updates and upgrades of the software in the industrial control computer, enhancing the flexibility and responsiveness of the production system. Version numbers enable precise version management and rollback mechanisms, effectively preventing production interruptions or equipment failures caused by improper software updates. Additionally, log recording and auditing functions allow for rapid identification and tracing of fault causes, improving problem-solving efficiency.

[0147] In actual battery production, the control parameters and results of the battery production process need to be collected by sensors, and the amount of data is often very large. At the same time, there may be differences between the control parameters and results of the battery production process of different industrial control computers. The following describes how to transmit data in order to enable the control parameters and results of the battery production process to be transmitted to the edge device in a timely and complete manner.

[0148] In some embodiments, the industrial control computer may include equipment (e.g., a PLC) for performing battery production processes and the aforementioned sensors. For example, the sensor may be a camera, which can take pictures to obtain images of the PLC during the production process, as actual battery production result data.

[0149] In this embodiment, the industrial control computer can preprocess the actual battery production process control parameters and actual battery production result data of the process, and then upload the preprocessed actual battery production process control parameters and actual battery production result data to the edge device.

[0150] For example, actual battery production process control parameters and actual battery production result data can be categorized into unstructured data (e.g., images) and structured data (e.g., process parameters) based on data type. Unstructured data refers to data without a predefined data model or structure, exhibiting diverse forms and being difficult to process directly. Structured data, on the other hand, is organized according to a predefined data model. The storage methods for structured and unstructured data differ.

[0151] For example, compression strategies can be used to compress unstructured data, while feature extraction and format adjustment can be used to process structured data.

[0152] In particular, regarding the compression strategy, since the actual battery production process control parameters and actual battery production results data exhibit high-dimensionality, high-frequency collection, and strong correlation, a deep learning-based compression model can be used to automatically identify and extract key features from the data (such as the width and thickness of the coated film, and the portion of the wound negative electrode sheet that extends beyond the positive electrode sheet in the length and width directions) to address the uniqueness of the actual battery production process control parameters and actual battery production results data. At the same time, redundant information that has little impact on the production process is filtered out, thus achieving data processing. This intelligent compression method not only improves compression efficiency but also ensures the fidelity of the data during the compression process, avoiding the negative impact of information loss on production decisions.

[0153] Furthermore, since the actual battery production process control parameters and data formats of actual battery production results may differ between different industrial control computers (for example, different industrial control computers from different suppliers may have inconsistent formats for process parameters), the data format can be optimized using the aforementioned format adjustment strategies (e.g., unifying the data formats of actual battery production process control parameters and actual battery production results in key processes such as coating, die-cutting, and winding) to reduce unnecessary redundant information. This simplifies the data structure, optimizes the data encoding method, and further reduces the complexity of data transmission and storage.

[0154] In this embodiment, the aforementioned data preprocessing improves data processing efficiency and speed while reducing data transmission and storage overhead, thus lowering overall operating costs. Furthermore, the optimized data format and structure enhance the performance of the data processing system and reduce computational resource consumption. Moreover, the high-fidelity data obtained through the above data processing strategies supports more accurate and reliable production decisions.

[0155] In some embodiments, as mentioned above, the actual battery production process control parameters and actual battery production result data exhibit characteristics of high-dimensionality, high-frequency acquisition, and strong correlation during the battery production process. This results in a large amount of data for the actual battery production process control parameters and actual battery production result data. Therefore, it is necessary to use efficient network communication methods to transmit these actual battery production process control parameters and actual battery production result data.

[0156] For example, actual battery production process control parameters and actual battery production result data can be transmitted to edge devices via a pre-configured network communication method. This network communication method includes at least one of 5G wireless communication, 6G wireless communication, and fiber optic communication.

[0157] In this embodiment, precise control of each process in battery production, such as coating, winding, and electrolyte injection, is required. The high-speed transmission capabilities of 5G and 6G wireless communication ensure that the actual battery production process control parameters and actual battery production results data collected by sensors on the production line can be uploaded in real time to edge devices deployed at the base for rapid analysis and processing. This allows for real-time adjustment of battery production process control parameters in case of production anomalies, ensuring quality control at each stage.

[0158] Furthermore, in some embodiments, when the industrial control computer transmits these actual battery production process control parameters and actual battery production result data to the edge device, the industrial control computer can determine the upload order of each actual battery production process control parameter and actual battery production result data. According to the upload order, the industrial control computer uploads the actual battery production process control parameters, actual battery production result data, and sequence identifiers to the edge device in sequence. When the edge device receives these data, it determines the receiving order of the actual battery production process control parameters and actual battery production result data, and determines whether there is an abnormality in the data transmission of the actual battery production process control parameters and actual battery production result data according to the receiving order and sequence identifier. If there is an abnormality, it outputs a data transmission abnormality prompt message.

[0159] For example, when an industrial control computer transmits three data sets S1, S2, and S3 sequentially, it adds a transmission sequence number ① to data S1, a transmission sequence number ② to data S2, and a transmission sequence number ③ to data S3. If the edge device extracts the transmission sequence number ①, transmission sequence number ②, and transmission sequence number ③ from the sequentially received data, then the data transmission is successful. However, if the edge device extracts the transmission sequence number ① from the first received data set and directly extracts the transmission sequence number ③ from the second received data set, then there is a problem with the data transmission, and a data transmission error message is output to inform the industrial control computer that the data transmission needs to be re-performed.

[0160] For example, Figure 4 This is a schematic diagram of the data transmission process provided in an embodiment of this application, such as... Figure 4 As shown, at the message production end (e.g., industrial control computer), a transmission sequence number is added for each message sent (equivalent to actual battery production process control parameters and actual battery production result data). At the message consumption end (e.g., edge device), the transmission sequence number is extracted for each message received, and then all transmission sequence numbers are summarized to verify the integrity of data transmission.

[0161] For example, Figure 5 A schematic diagram of a data transmission process provided for another embodiment of this application, as shown below. Figure 5As shown, during the process of the message producer 51 (equivalent to an industrial control computer) transmitting the actual battery production process control parameters and actual battery production result data, only one piece of data can be transmitted at a time, and it can be determined whether a confirmation message is received (for example, whether the message middleware 52 has returned a confirmation message). If a confirmation message is returned, the message middleware 52 continues to send the message to the message consumer 53 (equivalent to an edge device). If the edge device also returns a confirmation message, the message producer 51 continues to transmit the next piece of data, and so on, until all data has been transmitted.

[0162] After introducing the battery production system described above, the steps performed by the battery production system will be described in detail below through some methodological embodiments. It should be noted that the cloud server and edge devices in the battery production system can be integrated together, or they can be implemented independently and collaboratively to achieve this solution.

[0163] Figure 6 This is a schematic flowchart of a battery production method provided in an embodiment of this application. This method can be applied to the aforementioned battery production system. Figure 6 As shown, the method may include the following steps:

[0164] Step S610: Obtain the actual battery production process control parameters and actual battery production result data for different battery production processes;

[0165] Step S620: Obtain reference battery production process control parameters for different battery production processes under different production conditions;

[0166] Step S630: Based on the reference battery production process control parameters and the actual battery production result data, adjust the actual battery production process control parameters to obtain the adjusted actual battery control process parameters;

[0167] Step S640: Control battery production according to the adjusted actual battery control process parameters.

[0168] In this embodiment, referring to the description of the battery production system, the battery production process may include at least one of stirring, coating, cold pressing, die cutting, and winding. Actual battery production result data may include at least one of the following: raw material state, process parameters, and industrial control computer state. Actual battery production process control parameters may refer to the parameters required to control the industrial control computer; for example, their values ​​may refer to the aforementioned process parameters. For example, taking the stirring process as an example, process parameters may refer to the stirring time and stirring speed during the stirring process. In addition, actual battery production process control parameters may also include equipment parameters.

[0169] In this embodiment, as mentioned above, the cloud server in the battery production system can be remotely deployed at the headquarters. By communicating with edge devices in various production bases, it can aggregate the actual battery production process control parameters and actual battery production result data of the industrial control computers in each process of each production base.

[0170] The cloud server can analyze the actual battery production process control parameters and actual battery production result data to determine reference battery production process control parameters that can maximize the production efficiency of the industrial control computers. For example, by analyzing the actual battery production process control parameters and actual battery production result data of all industrial control computers in the entire battery production process, the cloud server can provide a reference stirring time and a reference stirring speed. When industrial control computer A operates at the reference stirring time and reference stirring speed, the efficiency of the stirring process and other processes on the entire production line can be maximized.

[0171] In this embodiment of the application, by aggregating the actual battery control process parameters and actual battery production result data in different battery production processes, it is beneficial to promptly identify problems that occur in the production process and adjust the actual battery control process parameters in the process in a timely manner to prevent the decline in the product yield and to ensure that the battery production result data can meet the production target requirements as much as possible, thereby improving battery production efficiency.

[0172] In other embodiments, Figure 7 A schematic flowchart of a battery manufacturing method provided in another embodiment of this application is shown below. Figure 7 As shown, the method may include the following steps:

[0173] Step S710: Obtain the reference battery production process control parameters for the target process and the actual battery production result data of the upstream process of the target process;

[0174] Step S720: Based on the actual battery production results data of the upstream process, adjust the reference battery production process control parameters of the target process to obtain the adjusted reference battery production process control parameters.

[0175] Step S730: Based on the adjusted reference battery production process control parameters and the actual battery production result data of the target process, adjust the actual battery production process parameters of the target process to obtain the adjusted actual battery production process control parameters of the target process.

[0176] In this embodiment, taking the winding process as the target process as an example, the industrial control computer can accurately calculate the optimal matching scheme of the anode and cathode film rolls through edge computing algorithms, and seamlessly transmit the relevant battery control process parameters in the optimal matching scheme to the industrial control computer in the subsequent process (such as the winding process). The industrial control computer in the winding process executes the winding process according to the relevant battery control process parameters in the optimal matching scheme, which can significantly improve the yield of bare cells.

[0177] In this embodiment, by obtaining actual battery production result data from upstream processes, it is beneficial to promptly identify problems that arise during the production process and provide actual battery production process parameter adjustment strategies for the next target process, thereby preventing a decrease in the yield of products in the next target process and improving battery production efficiency.

[0178] In other embodiments, the battery production system described above can also detect whether there are any abnormalities in the actual battery production process control parameters and / or actual battery production result data of each battery production step; and if there are abnormalities, output abnormality prompt information, and / or determine the cause of the abnormality.

[0179] This system allows setting threshold values ​​for production process parameters. When the actual battery production results for a particular battery production step exceed these threshold values, an anomaly can be identified for that step. To facilitate on-site troubleshooting, the anomaly alert can include both the abnormal battery production step and the abnormal actual battery production results.

[0180] Furthermore, during battery production control, a situation may arise where the actual battery production process control parameters are improperly adjusted. For example, changes in the characteristics of the materials may cause the actual battery production process control parameters to become incompatible with the changed material properties. To address this, a control parameter adjustment range can be set. If the actual battery production process control parameter deviates from this range, it is considered an anomaly. Similarly, to facilitate on-site troubleshooting, anomaly alerts can include the abnormal battery production process and the abnormal actual battery production process control parameters.

[0181] In this embodiment of the application, by performing anomaly monitoring, anomaly alarms can be issued in a timely manner, notifying on-site staff to investigate the problem promptly and avoiding situations such as large-scale work stoppages.

[0182] Furthermore, the following steps can be used to detect abnormalities in the battery manufacturing process:

[0183] Step (1): Obtain the first actual battery production result data of the battery production process at the first moment and the second actual battery production result data of the battery production process at the second moment;

[0184] Step (2) Determine the amount of fluctuation between the first actual battery production result data and the second actual battery production result data;

[0185] Step (3) Based on the fluctuation amount, determine whether there are any abnormalities in the actual battery production process control parameters and / or actual battery production result data of the battery production process.

[0186] In this embodiment, the edge device mentioned above can collect real-time data on the actual battery production results of each battery production process at any given moment. Simultaneously, the edge device can extract a key parameter from this data. For example, in the stirring process, the key parameter could include stirring speed and stirring time. This allows the acquisition of the stirring speed and stirring time at each moment in the stirring process. By comparing the changes in stirring speed and stirring time at each moment, it can be determined whether there are any abnormalities in the stirring process.

[0187] Specifically, a fluctuation threshold can be set. When the difference between the stirring speed and / or stirring time at the previous moment and the stirring speed and / or stirring time at the next moment exceeds the fluctuation threshold, it is determined that there is an abnormality in the stirring process.

[0188] In this embodiment of the application, by collecting and comparing actual battery production result data at two different times, when fluctuations are found in the actual battery production result data through comparison, an anomaly in the battery production process can be quickly identified, improving the timeliness of anomaly detection, so as to facilitate rapid problem handling and ensure battery production quality and efficiency.

[0189] In other embodiments, in order to ensure that faults can be detected and resolved in a timely manner when they occur, the production system can prioritize acquiring the associated data related to the fault after detecting a fault in the first process; and determine the cause of the fault in the first process based on the associated data.

[0190] In this embodiment, taking the stirring process mentioned above as the first process as an example, after comparing the stirring speed and / or stirring time at two different times and determining that there is an abnormality in the stirring process, the relevant data related to stirring, such as stirring speed, stirring time and the characteristics of the stirred material, can be extracted from the actual battery production result data at these two times and / or the actual production result data at more historical times, thereby analyzing the cause of the failure in the first process.

[0191] For example, it can detect whether the characteristics of the material being stirred fluctuate. If fluctuations occur, the cause of the malfunction can be determined to be an abnormality in the material.

[0192] In this embodiment, since the computing resources of the battery production system are limited, after a faulty process is detected, it is necessary to increase the priority of the faulty process and allocate computing resources to deal with the cause of the faulty process first.

[0193] In this embodiment of the application, by prioritizing the acquisition of associated data related to the fault and determining the cause of the fault, a fault solution can be provided, which can quickly resolve the problem in a timely manner, prevent the problem from escalating and causing large-scale downtime, and improve production efficiency.

[0194] In other embodiments, a production process control parameter determination model can be deployed on the cloud server of the battery production system. This model is trained using actual battery production results data under different production conditions as input and production process control parameters under those conditions as output.

[0195] In this embodiment, after training the production process control parameter determination model, the reference battery production process control parameters for the second process under different production conditions can be obtained by using the production process control parameter determination model, the actual battery production process control parameters of the second process, and the actual battery production result data.

[0196] The second process can be any process on the battery production line. Taking the stirring process as the second process as an example, we can obtain the actual battery production process control parameters and actual battery production result data for the stirring process at each moment, such as the stirring speed and stirring completion time of the stirring process at the first historical moment, and the stirring speed and stirring completion time of the stirring process at the second historical moment.

[0197] In order to improve production efficiency, the mixing completion time can be used as the input of the production process control parameter determination model. The generated process control parameters are trained based on this input and a prediction result is input. This prediction result should be as close as possible to the mixing speed.

[0198] Furthermore, in some embodiments, in order to improve the training effect of the production process control parameter determination model, the training data can be enriched by the actual production process control parameters and actual battery production results data of the stirring process on each production line in each battery production base, thereby improving the prediction accuracy of the production process control parameter determination model.

[0199] Once the production process control parameter determination model is trained using the actual production process control parameters and actual battery production result data of the mixing process on each production line in each battery production base, it can be used to predict the reference battery production process control parameters.

[0200] In this embodiment, by aggregating actual battery production process control parameters and actual battery production result data from different processes as training data, a production process control parameter determination model is trained. This allows for continuous optimization and adjustment of the actual battery production process control parameters, improving the accuracy of parameter adjustments. Furthermore, by utilizing actual production process control parameters and actual battery production result data from the same process on each production line in each production base, the training data is enriched, enhancing the training effect of the production process control parameter determination model and enabling it to predict more accurate reference battery production process control parameters.

[0201] For example, Figure 8 This is a schematic diagram of the data architecture of the battery production system provided in the embodiments of this application, such as... Figure 8 As shown, the overall process includes six steps: 1. Data production; 2. Transmission and processing; 3. Data storage; 4. Analysis and application; 5. Presentation and use; 6. Consumption scenarios.

[0202] In the data storage process, the actual battery production process control parameters and actual battery production result data in different battery production steps can be preprocessed; the preprocessed actual battery production process control parameters and actual battery production result data are then encrypted and stored in the database.

[0203] By encrypting and storing the actual battery production process control parameters and actual battery production results data in the database, data leakage is prevented on the one hand, and other devices with access permissions can be made to perform subsequent analysis and application, presentation and use and consumption scenarios through interface calls.

[0204] Furthermore, in some embodiments, the data preprocessing process can be implemented through the following steps:

[0205] Step 1: When the actual battery production process control parameters and actual battery production result data are unstructured data, compress the actual battery production process control parameters and actual battery production result data.

[0206] Step 2: Given that the actual battery production process control parameters and actual battery production result data are structured data, extract multiple key data from the actual battery production process control parameters and actual battery production result data, and adjust the data format of each key data to the target format.

[0207] In this embodiment, regarding the compression strategy, since the actual battery production process control parameters and actual battery production result data exhibit high-dimensionality, high-frequency acquisition, and strong correlation characteristics during battery production, a deep learning-based compression model can be used to automatically identify and extract key features from the data (such as the width and thickness of the coated film, and the portion of the wound negative electrode sheet that extends beyond the positive electrode sheet in the length and width directions). At the same time, redundant information that has little impact on the production process is filtered out, thus achieving data processing. This intelligent compression method not only improves compression efficiency but also ensures the fidelity of the data during the compression process, avoiding the negative impact of information loss on production decisions.

[0208] Furthermore, since the actual battery production process control parameters and data formats of actual battery production results may differ between different industrial control computers (for example, different industrial control computers from different suppliers may have inconsistent formats for process parameters), the data format can be optimized using the aforementioned format adjustment strategies (e.g., unifying the data formats of actual battery production process control parameters and actual battery production results in key processes such as coating, die-cutting, and winding) to reduce unnecessary redundant information. This simplifies the data structure, optimizes the data encoding method, and further reduces the complexity of data transmission and storage.

[0209] In this embodiment, data preprocessing followed by encrypted storage in the database prevents the leakage of core process parameters during actual battery production. This also facilitates subsequent process analysis, enabling targeted process optimization based on the analysis results and improving production efficiency. Furthermore, optimizing the data format improves the performance of the data processing system and reduces computational resource consumption. Moreover, compressing unstructured data yields high-fidelity data, supporting more accurate and reliable production decisions.

[0210] Further, please refer to the above. Figure 8 After analyzing the data, the results can be presented, such as obtaining the actual battery production process parameters and actual battery production results data of the third process in different battery production processes at each moment; and obtaining the data change trend of the third process based on the actual battery production process parameters and actual battery production results data of the third process at each moment. Here, the third process can be any process in different battery production processes.

[0211] The data trend can be a trend chart of control parameters in the actual battery production process, an analysis report, or a trend chart of actual battery production results.

[0212] In addition, please continue to refer to the above. Figure 8In terms of presentation and use, in addition to edge devices generating process dashboards, parameter trend charts, diagnostic results, analysis reports, and alarm records based on actual battery production process parameters and actual battery production result data, the center (i.e., the cloud server deployed at headquarters) can also realize line dashboards, closed-loop dashboards, anomaly records, build application lists and production reports, and present evaluation results.

[0213] In this embodiment of the application, by analyzing the actual battery production process parameters and actual battery production result data of the third process at each moment, a data change trend is formed, which can more intuitively grasp the changes in the process and facilitate problem investigation and process optimization.

[0214] Figure 9 This is a schematic diagram of the security architecture of a battery production system provided in an embodiment of this application, such as... Figure 9 As shown, this security architecture is divided into five parts: 1. Application password / login control, mainly used for scenarios involving application use or updates. 2. Application access control, mainly including file management, data verification, anti-replay mechanism, session management, sensitive information, anti-brute force, system permissions, access control, exception handling, keyword filtering, and data transmission. 3. Application integration control / application log management and application security monitoring. 4. External security control, mainly including host firewall, host intrusion protection, data backup and recovery, security separation of architecture, network intrusion prevention, and web application protection. 5. Relevant materials, mainly including data security level confirmation emails and PIA assessment reports.

[0215] For example, taking application updates as an example, in some embodiments, users can remotely initiate application update requests to update applications on devices in various production bases. This could involve updating applications integrated into edge devices or updating applications on PLC devices. In this case, the battery production system first determines whether the application update request carries authentication information. If the authentication information matches preset authentication information, the system obtains an encrypted application software update package based on the application update request; then, it distributes the encrypted application software update package to the battery production process control equipment on each production line in each production base. The encrypted application software update package is used by the battery production process control equipment to decrypt it according to a preset encryption algorithm before updating the application software to control battery production.

[0216] The authentication information can be the application password. This means that users need to verify their identity using the application password when updating the application to prevent malicious activity.

[0217] In some embodiments, when distributing encrypted application software update packages, a highly secure remote encrypted operation and maintenance channel can be established. This channel employs advanced encryption algorithms and authentication mechanisms to ensure absolute confidentiality and integrity during data transmission. Through this encrypted channel, it is possible to penetrate complex network environments and securely and efficiently access and control PLC devices. This not only enables remote deployment and configuration of PLCs but also allows for real-time updates and upgrades of PLC software without affecting production operations.

[0218] In this embodiment, by distributing encrypted application software update packages to the battery production process control equipment on each production line in each production base, maintenance personnel can remotely access and control the industrial control computers, eliminating the need for on-site personnel to travel, thus reducing maintenance costs and improving efficiency. Furthermore, remote data transmission allows for real-time updates and upgrades to the software in the industrial control computers, enhancing the flexibility and responsiveness of the production system.

[0219] Further, please refer to the above. Figure 9 In some embodiments, application log management can be implemented in the security architecture. For example, the application software version information before and after each application software update is obtained by the battery production process control equipment. Then, application logs are generated based on the version information before and after the update.

[0220] In this embodiment, the application log management module enables intelligent version management and rollback mechanisms. For example, during PLC software updates, the update scope can be precisely controlled, effectively preventing production interruptions or equipment failures caused by improper updates. Furthermore, the application log management module of this battery production system can be configured with log recording and auditing functions, enabling real-time tracking and recording of every remote access and operation, providing detailed data support for subsequent troubleshooting and accountability.

[0221] In this embodiment of the application, by recording the version information when the application software is updated, it is easier to conduct subsequent troubleshooting and rollback operations, thereby improving the stability of the application software during the update process.

[0222] Further, please refer to the above. Figure 9 In some embodiments, as mentioned above, application access control includes file management and access control functions. For example, after a target object (e.g., a user) initiates a data access request, the application access control module in the battery production system responds to the request by further determining whether the target object's access permissions match preset permissions. If the target object's access permissions match preset permissions, the module sends the encrypted actual battery production process control parameters and actual battery production result data stored in the database to the target object.

[0223] In this embodiment, access permissions can be configured. By configuring access permissions, the actual battery production process control parameters and actual battery production result data can be restricted to flow only between a limited number of authorized devices, thus preventing data leakage.

[0224] When the application access control module interacts with the target object, it can instruct the target object to upload its own access permission credentials. If the target object's access permission credentials do not match the preset permissions or the target object does not upload access permission credentials, it will not be able to access the encrypted actual battery production process control parameters and actual battery production result data, thereby ensuring data security.

[0225] For example, the preset permissions can be a whitelist. If the identifier of the target object (e.g., device number) is in the whitelist, then the target object has the permission to access the encrypted actual battery production process control parameters and actual battery production result data.

[0226] In this embodiment of the application, by setting access permissions, it is possible to prevent other unauthorized users from accessing the actual battery production process control parameters and actual battery production result data in the database, thereby improving data security and preventing the leakage of process production data.

[0227] Further, please refer to the above. Figure 9 In some embodiments, the application access control module also includes a data verification function. This data verification function can be used to verify the integrity of the actual battery production process control parameters and the actual battery production result data. This is to account for the possibility of data loss during the data acquisition process in the production process. Specifically, during the data verification process, the identification information of each actual battery production process control parameter and the actual battery production result data in the battery production process can be obtained; then, based on the identification information, it is verified whether there is any data missing in the battery production process; and if data is missing, a data anomaly prompt message is output. The battery production process includes at least one actual battery production process control parameter and at least one actual battery production result data.

[0228] For example, the identification information could refer to the generation time of each data point. For instance, the control parameters of the actual battery production process are generated first, so their identification information could be sequence number ①. The identification information of the actual battery production result data is generated later, so its identification information could be sequence number ②. If it is found that only data with sequence number ② has been obtained, it indicates that data is missing.

[0229] In other embodiments, the data verification function can be integrated into the edge device. During the process of the edge device collecting data from the industrial control computer, the industrial control computer can configure transmission sequence numbers for each actual battery production process control parameter and actual battery production result data according to the transmission order of each actual battery production process control parameter and actual battery production result data. When the edge device receives these actual battery production process control parameters and actual battery production result data, it reads the transmission sequence numbers in sequence. If one of the transmission sequence numbers is found to be missing, it can be determined that the data transmission is incomplete and there is a data loss.

[0230] In this embodiment of the application, by using identification information to detect data, data loss can be prevented and data integrity can be ensured.

[0231] Figure 10 This is a schematic flowchart of a battery production method provided in an embodiment of this application. This method can be applied to edge devices, i.e., using edge devices as the execution entity. For example... Figure 10 As shown, the method may include the following steps:

[0232] Step S1010: Obtain the actual battery production process control parameters and actual battery production result data for different processes from the industrial control computer;

[0233] Step S1020: Obtain reference battery production process control parameters for different processes under different production conditions from the cloud server;

[0234] Step S1030: Based on the reference battery production process control parameters and the actual battery production result data, adjust the actual battery production process control parameters to obtain the adjusted actual battery control process parameters.

[0235] Step S1040: Send the adjusted actual battery control process parameters to the corresponding industrial control computer so that the industrial control computer can produce the battery according to the adjusted actual battery control process parameters.

[0236] In this embodiment of the application, during the battery production process, the actual battery production process control parameters and actual battery production result data of each industrial control computer in different processes are aggregated by edge devices. This helps to promptly identify problems that occur during the production process and provides the industrial control computers in the process with adjusted actual battery control process parameters to prevent a decrease in the yield of high-quality products and improve battery production efficiency.

[0237] Figure 11 This is a schematic flowchart illustrating a battery production method according to another embodiment of this application. This method can be applied to an industrial control computer, i.e., using an industrial control computer as the execution entity. For example... Figure 11 As shown, the method may include the following steps:

[0238] Step S1110: Preprocess the actual battery production process control parameters and actual battery production result data of the corresponding process.

[0239] Step S1120: Upload the pre-processed actual battery production process control parameters and actual battery production result data to the edge device;

[0240] Step S1130: Obtain the adjusted actual battery control process parameters from the edge device;

[0241] Step S1140: Produce the battery according to the adjusted actual battery control process parameters.

[0242] In this embodiment, the industrial control computer preprocesses the actual battery production process control parameters and actual battery production result data to be transmitted, reducing data transmission and storage overhead. Then, the data is transmitted to the edge device via a preset network communication method. This ensures that the actual battery production process control parameters and actual battery production result data collected by sensors on the production line can be uploaded to the edge device deployed at the production base in real time for rapid analysis and processing. This allows the edge device to adjust the battery production process control parameters of the industrial control computer in real time when production anomalies occur, ensuring quality control at each stage.

[0243] In some embodiments, when transmitting the actual battery production process control parameters and actual battery production result data after the above-described transmission processing to the edge device, a sequence identifier can also be configured for each actual battery production process control parameter and actual battery production result data.

[0244] The sequence identifier is used by edge devices to verify the integrity of the received data.

[0245] In other embodiments, when transmitting the processed actual battery production process control parameters and actual battery production result data to the edge device, the priority of each actual battery production process control parameter and actual battery production result data can be determined first; then, through a preset network communication method, the actual battery production process control parameters and actual battery production result data are transmitted to the edge device in descending order of priority.

[0246] In this embodiment of the application, prioritizing the transmission of high-priority data related to faults can help the entire system quickly diagnose and resolve fault problems, thereby improving battery production efficiency.

[0247] Figure 12 This is a schematic flowchart illustrating a battery production method according to another embodiment of this application. This method can be applied to a cloud server, i.e., the cloud server serves as the execution entity. For example... Figure 12 As shown, the method may include the following steps:

[0248] Step S1210: Obtain actual battery production process control parameters and actual battery production result data for different processes under different production conditions from the edge device;

[0249] Step S1220: Based on the trained production process control parameters, determine the model, the actual battery production process results of different processes under different production conditions, and determine the reference battery production process control parameters for different processes under different production conditions.

[0250] Step S1230: Send reference battery production process control parameters for different processes under different production conditions to the edge devices.

[0251] In this embodiment of the application, by acquiring the actual battery production process control parameters and actual battery production result data of different processes under different production conditions, and by analyzing and mining them, reasonable reference battery production process control parameters can be provided to the industrial control computer, ensuring continuous optimization and efficiency improvement of the production process.

[0252] For a detailed description of the method steps in the above embodiments, please refer to the section on the battery production system above, which will not be repeated here.

[0253] Figure 13 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 13 As shown, the electronic device 1300 may include a processor 1301 and a memory 1302 storing computer program instructions.

[0254] Specifically, the processor 1301 may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0255] Memory 1302 may include mass storage for data or instructions. For example, and not as a limitation, memory 1302 may include a hard disk drive (HDD), a floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or a Universal Serial Bus (USB) drive, or a combination of two or more of these.

[0256] Where appropriate, memory 1302 may include removable or non-removable (or fixed) media. Where appropriate, memory 1302 may be internal or external to the integrated gateway disaster recovery device. In a particular embodiment, memory 1302 is a non-volatile solid-state memory.

[0257] Memory 1302 may include read-only memory (ROM), random access memory (RAM), disk storage media device, optical storage media device, flash memory device, electrical, optical, or other physical / tangible memory storage device. Therefore, typically, memory 1302 includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it can perform the operations described in any of the methods described in the above embodiments. Processor 1301 implements any of the methods in the above embodiments by reading and executing computer program instructions stored in memory 1302.

[0258] In one example, electronic device 1300 may further include communication interface 1303 and bus 1304. For example, Figure 13 As shown, the processor 1301, memory 1302, and communication interface 1303 are connected through bus 1304 and complete communication with each other.

[0259] The communication interface 1303 is mainly used to realize communication between various modules, devices, units and / or equipment in the embodiments of this application.

[0260] Bus 1304 includes hardware, software, or both, that couples components of an online data traffic metering device together. For example, and not limitingly, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Microchannel 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 (VLB) bus, or other suitable buses, or combinations of two or more of these. Where appropriate, bus 1304 may include one or more buses. Although specific buses are described and illustrated in embodiments of this application, any suitable bus or interconnect is contemplated herein.

[0261] The electronic device can be the aforementioned edge device, the aforementioned cloud server, or the aforementioned industrial control computer.

[0262] Furthermore, in conjunction with the methods in the above embodiments, this application embodiment can provide a computer storage medium for implementation. This computer storage medium stores computer program instructions; when these computer program instructions are executed by a processor, they implement any of the methods in the above embodiments.

[0263] This application also provides a computer program product, including a computer program, which, when executed, implements any of the methods described in the above embodiments.

[0264] It should be understood that the specific examples in this document are only intended to help those skilled in the art better understand the embodiments of this application, and are not intended to limit the scope of the embodiments of this application.

[0265] It should also be understood that, in the various embodiments of this application, the sequence number of each process does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0266] It should also be understood that the various implementation methods described in this specification can be implemented individually or in combination, and the embodiments of this application are not limited in this respect.

[0267] Although this application has been described with reference to preferred embodiments, various modifications can be made thereto and components can be replaced with equivalents without departing from the scope of this application. In particular, the technical features mentioned in the various embodiments can be combined in any manner, provided there is no structural conflict. This application is not limited to the specific embodiments disclosed herein, but includes all technical solutions falling within the scope of the claims.

Claims

1. A battery manufacturing method, characterized in that, include: Obtain actual battery production process control parameters and actual battery production result data for different battery production processes; Obtain reference battery production process control parameters for the different battery production processes under different production conditions; Based on the reference battery production process control parameters and the actual battery production result data, the actual battery production process control parameters are adjusted to obtain the adjusted actual battery control process parameters. Battery production is controlled based on the adjusted actual battery control process parameters.

2. The method according to claim 1, characterized in that, The step of adjusting the actual battery production process control parameters based on the reference battery production process control parameters and the actual battery production result data to obtain adjusted actual battery control process parameters includes: Obtain reference battery production process control parameters for the target process and actual battery production result data for the upstream processes of the target process; Based on the actual battery production results data of the upstream process, the reference battery production process control parameters of the target process are adjusted to obtain the adjusted reference battery production process control parameters. Based on the adjusted reference battery production process control parameters and the actual battery production result data of the target process, the actual battery production process parameters of the target process are adjusted to obtain the adjusted actual battery production process control parameters of the target process.

3. The method according to claim 1, characterized in that, Also includes: Check for any abnormalities in the actual battery production process control parameters and / or actual battery production result data for each battery production step; In the event of an anomaly, output an anomaly message and / or determine the cause of the anomaly.

4. The method according to claim 3, characterized in that, The detection of whether there are any abnormalities in the actual battery production process control parameters and / or actual battery production result data of each battery production step includes: Obtain the first actual battery production result data of the battery production process at the first moment and the second actual battery production result data of the battery production process at the second moment; Determine the amount of fluctuation between the first actual battery production result data and the second actual battery production result data; Based on the fluctuation amount, determine whether there are any abnormalities in the actual battery production process control parameters and / or actual battery production result data of the battery production process.

5. The method according to claim 1, characterized in that, Also includes: In the event of a failure in the first process, priority is given to acquiring the associated data related to the failure; the first process can be any of the different battery production processes. Based on the associated data, the cause of the failure in the first process is determined.

6. The method according to claim 1, characterized in that, The acquisition of reference battery production process control parameters for different battery production processes under different production conditions includes: Based on the production process control parameter determination model, the actual battery production process control parameters of the second process, and the actual battery production result data, reference battery production process control parameters for the second process under different production conditions are obtained. The second process can be any one of the different battery production processes. The production process control parameter determination model is trained using the actual battery production result data of the battery production process under different production conditions as input and the production process control parameters of the battery production process under different production conditions as output.

7. The method according to claim 6, characterized in that, The process of determining the model based on production process control parameters, the actual battery production process control parameters of the second process, and the actual battery production result data, and obtaining reference battery production process control parameters for the second process under different production conditions, includes: Summarize the actual production process control parameters and actual battery production results data for the second process on each production line in each production base; Based on the production process control parameters, the model is determined, along with the actual production process control parameters and actual battery production result data for the second process on each production line in each production base. Reference battery production process control parameters for the second process under different production conditions are then obtained.

8. The method according to claim 1, characterized in that, Also includes: In response to an application update request, determine whether the application update request carries authentication information; If the authentication information matches the preset authentication information, the encrypted application software update package is obtained according to the application update request. The encrypted application software update package is sent to the battery production process control equipment on each production line in each production base. The encrypted application software update package is used by the battery production process control equipment to update the application software to control battery production after being decrypted according to a preset encryption algorithm.

9. The method according to claim 8, characterized in that, Also includes: The battery production process control equipment obtains the application software version information before and after each application software update. Application logs are generated based on the version information before and after the update.

10. The method according to claim 1, characterized in that, After obtaining the actual battery production process control parameters and actual battery production result data in different battery production processes, the method further includes: Preprocessing is performed on the actual battery production process control parameters and actual battery production result data in the different battery production processes. The pre-processed actual battery production process control parameters and actual battery production results data are encrypted and stored in the database.

11. The method according to claim 10, characterized in that, The preprocessing of the actual battery production process control parameters and actual battery production result data in the different battery production processes includes: When the actual battery production process control parameters and actual battery production result data are unstructured data, the actual battery production process control parameters and actual battery production result data are compressed. When the actual battery production process control parameters and actual battery production result data are structured data, multiple key data are extracted from the actual battery production process control parameters and actual battery production result data, and the data format of each key data is adjusted to the target format.

12. The method according to claim 1, characterized in that, Also includes: Obtain the actual battery production process parameters and actual battery production result data of the third process in the different battery production processes at each time step; the third process is any one of the different battery production processes. Based on the actual battery production process parameters and actual battery production result data at each moment of the third process, the data change trend of the third process is obtained.

13. The method according to claim 1, characterized in that, Also includes: In response to a data access request from a target object, determine whether the access permissions of the target object match preset permissions; If the access permissions of the target object match the preset permissions, the encrypted actual battery production process control parameters and actual battery production result data stored in the database are sent to the target object.

14. The method according to claim 1, characterized in that, After obtaining the actual battery production process control parameters and actual battery production result data for different battery production processes, the method further includes: Acquire the identification information of each actual battery production process control parameter and actual battery production result data in the battery production process, wherein the battery production process includes at least one actual battery production process control parameter and at least one actual battery production result data. Based on the identification information, verify whether there are any missing data in the battery production process; If data is missing, output a data anomaly message.

15. A battery production system, characterized in that, It includes a cloud server and at least one edge device that is communicatively connected to the cloud server, with each edge device connected to an industrial control computer located at different battery production processes on the battery production line. The edge device is used to obtain actual battery production process control parameters and actual battery production result data for different battery production processes from the industrial control computer. The edge device is further configured to obtain reference battery production process control parameters for different battery production processes under different production conditions from the cloud server; adjust the actual battery production process control parameters according to the reference battery production process control parameters and the actual battery production result data to obtain adjusted actual battery control process parameters; and send the adjusted actual battery control process parameters to the corresponding industrial control computer so that the industrial control computer produces batteries according to the adjusted actual battery control process parameters. The cloud server is used to send reference battery production process control parameters for different battery production processes under different production conditions to the edge device.

16. The system according to claim 15, characterized in that, The edge device is further configured to adjust the reference battery production process control parameters of the target process based on the actual battery production result data of the upstream process of the target process; and to adjust the actual battery production process parameters of the target process based on the adjusted reference battery production process control parameters and the actual battery production result data of the target process, thereby obtaining the adjusted actual battery production process control parameters of the target process.

17. The system according to claim 15, characterized in that, The cloud server integrates a production process control parameter determination model; The cloud server is also used to determine the model based on the trained production process control parameters, the actual battery production process results of the target process uploaded by each edge device, and output the reference battery production process control parameters of the target process under different production conditions. The production process control parameter determination model is trained using actual battery production result data samples of different battery production processes under different production conditions as input and battery production process control parameter labels as output.

18. The system according to claim 15, characterized in that, The edge device is specifically used for: Obtain the actual battery production process parameters and actual battery production result data of the target process at each moment; Based on the actual battery production process parameters and actual battery production result data of the target process at each moment, the data change trend of the target process is obtained.

19. The system according to claim 15, characterized in that, The cloud server is specifically used for: The actual production process control parameters and actual battery production results data of each battery production process on each production line in each production base are summarized to generate battery production process analysis results.

Images