Battery production control method and related equipment

Abstract

The invention provides a battery production control method and related equipment, and relates to the technical field of battery production. The method comprises the following steps: acquiring process data of a plurality of process parameters corresponding to a control mode; processing the process data to obtain process characteristic data; processing the process characteristic data through a target control algorithm corresponding to the control mode to obtain the contribution degree of each process parameter; and determining a target process parameter from the plurality of process parameters according to the contribution degree, and controlling the battery production process based on the target process parameter and the control mode.

Description

Technical Field

[0001] This disclosure relates to the field of battery manufacturing technology, and in particular to a battery manufacturing control method, a battery manufacturing control device, an electronic device, a computer-readable storage medium, and a computer program product. Background Technology

[0002] During battery production, battery performance is prone to abnormalities due to various factors such as raw materials, equipment, and processes. If these abnormalities are not detected and addressed promptly, they can negatively impact battery quality and performance. Abnormal battery performance may be caused by the combined effects of multiple process parameters.

[0003] In related technologies, manual analysis of process parameters is typically used to determine the root cause of battery performance anomalies. However, this method suffers from problems such as insufficient analytical accuracy, low efficiency, strong reliance on experience, low data utilization, and difficulty in handling complex production scenarios, leading to significant challenges in battery production management. Summary of the Invention

[0004] This disclosure provides a battery production control method and related equipment, which at least to some extent overcomes the problems of insufficient accuracy, low efficiency, and difficulty in production control in related technologies regarding the identification of associated process parameters.

[0005] Other features and advantages of this disclosure will become apparent from the following detailed description, or may be learned in part from practice of this disclosure.

[0006] According to one aspect of this disclosure, a battery production control method is provided, comprising: acquiring process data of multiple process parameters corresponding to a control mode; processing the process data to obtain process feature data; processing the process feature data through a target control algorithm corresponding to the control mode to obtain the contribution degree of each process parameter; determining a target process parameter from the multiple process parameters based on the contribution degree; and controlling the battery production process based on the target process parameter and the control mode.

[0007] In one embodiment of this disclosure, when the control mode includes a consistency analysis mode, the process data includes data from different production batches and / or different production stages.

[0008] In one embodiment of this disclosure, the target control algorithm is an Extreme Gradient Boosting (XGBoost) model; wherein, the step of processing the process feature data using the target control algorithm corresponding to the control mode to obtain the contribution of each process parameter includes: constructing the XGBoost model based on the process feature data using product quality indicators as variables; calculating the contribution of each process parameter based on the XGBoost model, wherein the contribution includes at least one of the following: the number of times the process parameter is used as a splitting feature in all trees of the XGBoost model, the total gain of the process parameter in all trees of the XGBoost model, and the number of samples affected by the process parameter in all trees of the XGBoost model.

[0009] In one embodiment of this disclosure, when the control mode includes an anomaly identification mode, the process data includes data of the plurality of process parameters collected during battery production.

[0010] In one embodiment of this disclosure, the target control algorithm is a decision tree model; wherein, the step of processing the process feature data using the target control algorithm corresponding to the control mode to obtain the contribution of each process parameter includes: constructing a decision tree model based on the process feature data, taking whether the battery is qualified as a variable; calculating the contribution of each process parameter based on the decision tree model, wherein the contribution of each process parameter includes at least one of the following: the process parameter used by each split node in the decision tree model and the corresponding information gain or gain ratio, the number of times each process parameter is a split node in the decision tree model, or the sum of the information gains of each process parameter as a split node in all decision tree models.

[0011] In one embodiment of this disclosure, when the control mode includes a mean offset analysis mode, the process data includes data from different time points and / or different production batches.

[0012] In one embodiment of this disclosure, the target control algorithm is a similarity measurement algorithm; wherein, the step of processing the process feature data through the target control algorithm corresponding to the control mode to obtain the contribution of each process parameter includes: calculating the similarity of the process data of each process parameter at different time points and / or different production batches through the similarity measurement algorithm, as the contribution of the process parameter.

[0013] In one embodiment of this disclosure, determining the target process parameter from multiple process parameters based on contribution includes: sorting the contribution levels and determining a preset number of process parameters that are ranked first or last as the target process parameter.

[0014] In one embodiment of this disclosure, processing the process data to obtain process feature data includes: preprocessing the process data to obtain processed process data; and associating the processed process data with corresponding battery identification information to obtain the process feature data.

[0015] In one embodiment of this disclosure, the method further includes: using a visualization tool to verify the target process parameters and obtaining verification results.

[0016] According to another aspect of this disclosure, a battery production control device is provided, comprising: a data acquisition module for acquiring process data of multiple process parameters corresponding to a control mode; a feature extraction module for processing the process data to obtain process feature data; a data processing module for processing the process feature data using a target control algorithm corresponding to the control mode to obtain the contribution degree of each process parameter; and a production control module for determining a target process parameter from the multiple process parameters based on the contribution degree, and controlling the battery production process based on the target process parameter and the control mode.

[0017] According to another aspect of this disclosure, an electronic device is also provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to perform the battery production control method described in any one of the preceding claims by executing the executable instructions.

[0018] According to another aspect of this disclosure, a computer-readable storage medium is also provided, on which a computer program is stored, which, when executed by a processor, implements the battery production control method described in any of the preceding claims.

[0019] According to another aspect of this disclosure, a computer program product is also provided, comprising a computer program that, when executed by a processor, implements the battery production control method described in any of the preceding claims.

[0020] In this embodiment, process data of multiple process parameters corresponding to a control mode are acquired; the process data are processed to obtain process feature data; the process feature data are processed using a target control algorithm corresponding to the control mode to obtain the contribution of each process parameter; a target process parameter is determined from the multiple process parameters based on the contribution; and the battery production process is controlled based on the target process parameter and the control mode. In this disclosure, on the one hand, multiple process parameters that may have a correlation are determined through the control mode, and the contribution of the process parameters is determined using a target control algorithm corresponding to the control mode. This quantifies the influence of process parameters on the control mode, enabling a comprehensive and in-depth analysis of process parameters in the battery production process, providing strong data support for monitoring, optimizing, and controlling the quality of the production process. On the other hand, based on the contribution, key process parameters with a significant impact on the control mode can be selected from multiple process parameters, thereby improving product stability, reducing product defect rates, and enabling timely implementation of appropriate corrective measures.

[0021] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0022] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure. It is obvious that the drawings described below are merely some embodiments of this disclosure, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0023] Figure 1 This diagram illustrates the structure of an energy storage system provided in an embodiment of the present disclosure.

[0024] Figure 2 A flowchart of a battery production control method provided in an embodiment of this disclosure is shown.

[0025] Figure 3 A flowchart of a contribution determination method provided by an embodiment of this disclosure is shown.

[0026] Figure 4 A flowchart of another contribution determination method provided by an embodiment of this disclosure is shown.

[0027] Figure 5 This diagram illustrates another battery production control method provided in an embodiment of the present disclosure.

[0028] Figure 6 A flowchart of another battery production control method provided in an embodiment of this disclosure is shown.

[0029] Figure 7This diagram illustrates the structure of a battery production control device according to an embodiment of the present disclosure.

[0030] Figure 8 This diagram illustrates a structural block diagram of an electronic device provided in an embodiment of the present disclosure. Detailed Implementation

[0031] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, they are provided so that this disclosure will be more comprehensive and complete, and will fully convey the concept of the exemplary embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0032] Furthermore, the accompanying drawings are merely illustrative of this disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0033] Because the energy we need is highly time- and space-dependent, in order to utilize energy rationally and improve energy efficiency, it is necessary to store one form of energy in the same way or by converting it into another, and then release it in a specific energy form for future applications. Currently, the main way to generate green electricity is to develop green energy sources such as photovoltaics and wind power to replace fossil fuels.

[0034] Currently, the generation of green electricity generally relies on solar, wind, and hydropower. However, wind and solar power are generally characterized by strong intermittency and large fluctuations, which can cause grid instability, insufficient power during peak demand periods, and excessive power during off-peak periods. Unstable voltage can also damage the power grid. Therefore, insufficient electricity demand or insufficient grid capacity may lead to the problem of "wind and solar curtailment." Solving these problems requires energy storage. This involves converting electrical energy into other forms of energy through physical or chemical means and storing it. When needed, this energy can be converted back into electrical energy and released. Simply put, energy storage is like a large "power bank," storing electrical energy when solar and wind power are abundant and releasing the stored electricity when needed.

[0035] Taking electrochemical energy storage as an example, this solution provides an energy storage device for use in energy storage systems. The energy storage device is equipped with a set of chemical batteries, which mainly use the chemical elements in the batteries as energy storage media. The charging and discharging process is accompanied by the chemical reaction or change of the energy storage media. Simply put, the electrical energy generated by wind and solar energy is stored in the chemical batteries. When the use of external electrical energy reaches its peak, the stored electricity is released for use, or transferred to places with a shortage of electricity for use.

[0036] Current energy storage applications are quite widespread, including generation-side energy storage, grid-side energy storage, and consumption-side energy storage. The corresponding types of energy storage devices include:

[0037] (1) Large-scale energy storage power stations applied to wind power and photovoltaic power stations can assist renewable energy power generation in meeting grid connection requirements and improve the utilization rate of renewable energy. As a high-quality active / reactive power regulation power source on the power supply side, energy storage power stations can achieve load matching of power in time and space, enhance the absorption capacity of renewable energy, reduce instantaneous power changes, reduce the impact on the power grid, improve the absorption of new energy power generation, and are of great significance in power grid system backup, alleviating peak load power supply pressure and peak regulation and frequency regulation.

[0038] (2) Energy storage containers applied on the grid side mainly function as peak shaving, frequency regulation and grid congestion relief. In terms of peak shaving, they can achieve peak shaving and valley filling of electricity load, that is, charging the energy storage battery when the electricity load is low and releasing the stored electricity during the peak electricity load period, thereby achieving a balance between power production and consumption.

[0039] (3) Small energy storage cabinets applied to the electricity consumption side mainly function as self-consumption of electricity, peak-valley price arbitrage, capacity cost management, and improvement of power supply reliability. Depending on the application scenario, electricity consumption side energy storage can be divided into industrial and commercial energy storage cabinets, household energy storage devices, energy storage charging piles, etc., which are generally used in conjunction with distributed photovoltaics. Industrial and commercial users can use energy storage for peak-valley price arbitrage and capacity cost management. In the electricity market implementing peak-valley pricing, by charging the energy storage system when the electricity price is low and discharging the energy storage system when the electricity price is high, peak-valley price arbitrage can be achieved, reducing electricity costs. In addition, industrial enterprises subject to two-part tariffs can use energy storage systems to store energy during off-peak hours and discharge during peak loads, thereby reducing peak power and the maximum demand declared, achieving the goal of reducing capacity charges. Household photovoltaics with energy storage can improve the level of self-consumption of electricity. Due to high electricity prices and poor power supply stability, the demand for household photovoltaic installations is driven. Given that photovoltaic power generation occurs during the day, while user load is generally higher at night, configuring energy storage can better utilize photovoltaic power, improve self-consumption levels, and reduce electricity costs. Furthermore, energy storage is needed in areas such as communication base stations and data centers for backup power.

[0040] In some embodiments, see Figure 1 , Figure 1 This is a schematic diagram of the structure of an energy storage system 400 according to an embodiment of this application. Figure 1 And this application Figure 1 The embodiments are illustrated using a shared energy storage scenario on the generation / distribution side as an example. The energy storage device in this application is not limited to the energy storage scenario on the generation / distribution side.

[0041] This application provides an energy storage system 100, which includes: a high-voltage cable 110, a first power conversion device 120, a second power conversion device 130, and the energy storage device provided in this application. In some embodiments of the power generation scenario, the second power conversion device 130 can be a wind power conversion device. Since the electricity generated by wind power conversion is volatile, random, and intermittent, the unstable electricity output by the wind power conversion device can be stored in the energy storage device through grid connection. The energy storage device is connected to the high-voltage cable 110 and outputs smooth electricity to the power consumption side of the distribution network, realizing peak shaving and frequency regulation, and stable grid operation; or, wind power conversion... The power conversion device is always connected to the high-voltage cable 110. Under normal power generation conditions, the power output of the wind power conversion device is supplied to the power consumption side of the distribution network through the high-voltage cable. When the current power load is low and the wind power conversion device generates excess power, the excess power is first stored in the energy storage device to reduce the curtailment rate of wind and solar power and improve the problem of new energy power generation consumption. When the power load is high, the power grid issues an instruction to transmit the power stored in the energy storage device together with the high-voltage cable 110 in grid-connected mode to supply power to the power consumption side. This provides the power grid with various services such as peak shaving, frequency regulation, and backup, giving full play to the peak shaving role of the power grid, promoting peak shaving and valley filling, and alleviating the power supply pressure of the power grid.

[0042] In some embodiments on the distribution network side, the first power conversion device 120 can be a photovoltaic power conversion device. The energy storage device is connected to the high-voltage cable 110 and installed downstream of the high-voltage cable 110 between the user load and the user load. The power output by the photovoltaic power conversion device is stored in the energy storage device, which can respond in time to act as a backup power source when the power grid / distribution network fails. Alternatively, it can provide power supply support to alleviate line congestion when the high-voltage cable 110 transmission line is blocked, and to delay the economic pressure caused by the expansion of the power grid / distribution capacity when the power grid is planned to be expanded.

[0043] Optionally, the first power conversion device may include, but is not limited to, a wind power conversion device, and the second power conversion device may include, but is not limited to, a photovoltaic power conversion device. The first power conversion device 120 and the second power conversion device 130 can convert at least one of solar energy, light energy, wind energy, thermal energy, tidal energy, biomass energy, and mechanical energy into electrical energy.

[0044] Optionally, energy storage devices may include, but are not limited to, energy storage power stations, hydropower / thermal / wind power generation systems, solar power generation systems, mobile power systems, smart home systems, or temporary power supply systems, and are also used in data centers, military equipment, aerospace, charging piles, electric vehicles, and many other fields.

[0045] Optionally, the energy storage device may include, but is not limited to, a single battery cell, or a battery module, battery pack, battery cluster, power bank, energy storage cabinet / container, or other battery integrated system composed of single batteries. The actual application form of the energy storage device provided in this application embodiment may be, but is not limited to, the listed products, and may also be other application forms. This application embodiment does not strictly limit the application form of the energy storage device. This application embodiment only uses a multi-cell battery as an example for illustration.

[0046] Optionally, when the energy storage device is a single battery, the energy storage device can be, but is not limited to, at least one of cylindrical, prismatic, prismatic, or other shaped batteries.

[0047] Optionally, the battery cell can be a rechargeable battery, which refers to a battery cell that can be recharged after discharge to activate the active materials and continue to be used. The battery cell can be a lithium-ion battery, sodium-ion battery, sodium-lithium-ion battery, lithium metal battery, sodium metal battery, lithium-sulfur battery, magnesium-ion battery, nickel-metal hydride battery, nickel-cadmium battery, lead-acid battery, etc., and this application does not specifically limit it.

[0048] In the battery production process, the target process parameters are closely related to the preceding process parameters. When the target process parameters are abnormal, analyzing the relationship between the target process parameters and the preceding process parameters can identify the key factors affecting battery quality. By controlling the related parameters, the abnormality rate of the target process parameters can be reduced, thereby improving battery quality.

[0049] In related technologies, graphs can be used to compare the data of associated process parameters with those of the target process parameters. For example, based on experience, production process data of batteries can be obtained, and a scatter plot can be created on the generated process data using graphing tools. The degree of fit between the target process parameters and the preceding process parameters can be observed. By comparing the trends of the two, the correlation between the target process parameters and the preceding process parameters can be determined. By observing the correlation of the graphs, the most influential correlation factor can be identified, which is then identified as the main reason for the anomaly of the target process parameters.

[0050] However, the above method has the following drawbacks:

[0051] (1) Data analysis is not comprehensive and accurate enough. Manual analysis usually relies on experience and is difficult to fully cover complex production data. It may not be able to capture all key variables and their interactions, resulting in inaccurate data analysis results. Analytical bias may lead to untimely or inappropriate process adjustments, affecting product quality and reducing consistency.

[0052] (2) Inefficient. The above methods are time-consuming. Manual analysis requires a lot of time for data collection, organization and processing. Especially in large-scale production, battery manufacturing has high requirements for the real-time performance of process parameters. Manual analysis consumes a lot of human resources, and low efficiency may become a production bottleneck, making it difficult to meet the needs of high-efficiency production.

[0053] (3) Limitations of experience. Manual analysis relies heavily on the experience of the personnel. Different personnel may have different judgments on the same issue, leading to inconsistent analysis results.

[0054] (4) Inability to fully utilize data potential. A large amount of data is generated during the battery manufacturing process. The data utilization rate of manual analysis is low, a lot of potentially valuable information is wasted, and there is a lack of in-depth mining. Manual analysis makes it difficult to discover hidden patterns or abnormal patterns in the data. The above information is crucial for optimizing the process and preventing failures.

[0055] Therefore, the above methods suffer from problems such as insufficient analytical accuracy, low efficiency, strong reliance on experience, low data utilization, and difficulty in dealing with complex production scenarios. These problems not only affect the production efficiency of battery manufacturing but also reduce product quality and corporate competitiveness.

[0056] To address at least some of the aforementioned technical problems, the battery production control method provided in this disclosure includes: acquiring process data of multiple process parameters corresponding to a control mode; processing the process data to obtain process feature data; processing the process feature data using a target control algorithm corresponding to the control mode to obtain the contribution degree of each process parameter; determining a target process parameter from the multiple process parameters based on the contribution degree; and controlling the battery production process based on the target process parameter and the control mode. In this disclosure, on the one hand, multiple potentially related process parameters are determined through the control mode, and the contribution degree of the process parameters is determined using a target control algorithm corresponding to the control mode. This quantifies the influence of process parameters on the control mode, enabling comprehensive and in-depth analysis of process parameters in the battery production process, providing strong data support for monitoring, optimizing, and controlling the quality of the production process. On the other hand, based on the contribution degree, key process parameters with a significant impact on the control mode can be selected from multiple process parameters, thereby improving product stability, reducing product defect rates, and enabling timely implementation of appropriate corrective measures.

[0057] Under the above system architecture, this disclosure provides a battery production control method, which can be executed by any electronic device with computing capabilities. For example, a processor, such as a programmable logic controller (PLC) or a microcontroller, is acceptable, as long as it can perform the corresponding functions.

[0058] Figure 2 This invention discloses a flowchart of a battery production control method according to an embodiment of the present invention, as shown below. Figure 2 As shown, the battery production control method provided in this embodiment includes the following steps:

[0059] S202. Obtain process data for multiple process parameters corresponding to the control mode.

[0060] The control modes described above can be determined based on different analysis objectives or content, and can also be referred to as control types, analysis types, analysis modes, etc. Analysis objectives or content can include predicting battery performance, optimizing production processes, etc.

[0061] The control modes can include consistency analysis mode, anomaly identification mode, and mean deviation analysis mode. Among them, the consistency analysis mode is used to evaluate whether the batteries of different production batches and / or different production stages maintain stable consistency in key process parameters; the anomaly identification mode is used to identify outliers or abnormal points in process data, which may indicate potential quality problems in abnormal time periods during battery production; the mean deviation analysis mode is used to detect whether there is a significant mean deviation of key process parameters between different time points and / or different production batches, which may indicate drift or change in the battery production process.

[0062] The multiple process parameters corresponding to the control mode refer to the key process parameters under the corresponding control mode. The battery production process may include the wafer fabrication process, assembly process, formation process, etc., and the multiple process parameters may include process parameters in different production processes.

[0063] For example, when the control mode is a consistency analysis mode or anomaly identification mode, the multiple process parameters corresponding to the control mode may include process parameters such as the raw material mixing ratio, mixing time, stirring time, and coating thickness in the positive electrode and negative electrode mixing processes. They may also include process parameters such as coating thickness, rolling density, and cutting accuracy in the positive electrode and negative electrode coating processes. Furthermore, they may include process parameters such as formation conditions and formation capacity in the formation process, in order to determine the process parameters that have a greater impact on battery performance.

[0064] When the control mode is the mean offset analysis mode, the multiple process parameters corresponding to the control mode can include any one or more of the above process parameters.

[0065] Process data refers to the data generated during battery production based on the process parameters under the corresponding control mode. It should be noted that detailed process data can be collected from the upstream Manufacturing Execution System (MES) during battery production. The process data in the MES can be stored in the form of data tables or datasets. By retrieving process data corresponding to the process parameters of the control mode, the comprehensiveness and accuracy of the data can be ensured, while also reducing the data volume and improving analysis efficiency.

[0066] It should be noted that the process parameters corresponding to the control mode can be pre-configured in the system, or the process parameters of interest can be manually selected from the system. This disclosure does not impose any specific limitations on this.

[0067] S204. Process the process data to obtain process characteristic data.

[0068] In one embodiment, the above-mentioned S204 process the process data to obtain process feature data, including: preprocessing the process data to obtain processed process data; and associating the processed process data with the corresponding battery identification information to obtain process feature data.

[0069] In one embodiment, the process data can be preprocessed, and the preprocessed process data can be associated with the battery's unique identifier to obtain process feature data. Preprocessing may include, but is not limited to, data cleaning processes such as data simplification, integrity processing, uniqueness processing, accuracy processing, and uniformity processing.

[0070] The purpose of data cleaning is to improve the quality and reliability of datasets, and to ensure the accuracy and effectiveness of data analysis.

[0071] Data simplification mainly involves removing information irrelevant to process parameters, avoiding redundant data interference, and simplifying the data processing flow.

[0072] Integrity processing, also known as missing value imputation, is used to fill in missing values ​​in process data to ensure data integrity. There are no specific restrictions on the methods used to imput missing values.

[0073] Uniqueness processing is used to remove duplicate data records and prevent bias in analysis results.

[0074] Accuracy processing is used to identify and handle outliers caused by measurement bias, data entry errors, or other factors.

[0075] Standardization processing is used to standardize or normalize process data, bringing process data with different dimensions to the same scale for easier comparison and analysis. Standardization is the ratio of the difference between a feature and its mean to its standard deviation, and the StandardScaler class in the preprocessing library can be used to standardize the data.

[0076] The aforementioned identification information can be the battery's barcode. By integrating the cleaned process data and binding the process data with the battery's identification information, process feature data is obtained, ensuring the accuracy and effectiveness of subsequent data analysis.

[0077] S206. The process characteristic data is processed by the target control algorithm corresponding to the control mode to obtain the contribution of each process parameter.

[0078] In one embodiment, a corresponding target control algorithm can be matched according to the control mode. The target control algorithm can be a machine learning model or statistical algorithm corresponding to the control mode.

[0079] Contribution degree can quantify the extent to which process parameters influence the analytical objective or content. For example, a higher contribution degree indicates a greater influence of the process parameters on battery performance, while a lower contribution degree indicates a smaller influence.

[0080] It should be noted that the target control algorithm corresponding to the control mode can be pre-configured in the system. Once the control mode is selected, the corresponding target control algorithm is determined.

[0081] S208. Determine the target process parameter from multiple process parameters based on the contribution, and control the battery production process based on the target process parameter and the control mode.

[0082] In one embodiment, at least one target process parameter can be determined from multiple process parameters based on the magnitude of its contribution.

[0083] It should be noted that the target process parameters obtained may differ due to factors such as battery production equipment and the precision of process control.

[0084] In this embodiment, process data of multiple process parameters corresponding to a control mode are acquired; the process data are processed to obtain process feature data; the process feature data are processed using a target control algorithm corresponding to the control mode to obtain the contribution of each process parameter; a target process parameter is determined from the multiple process parameters based on the contribution; and the battery production process is controlled based on the target process parameter and the control mode. In this disclosure, on the one hand, multiple process parameters that may have a correlation are determined through the control mode, and the contribution of the process parameters is determined using a target control algorithm corresponding to the control mode. This quantifies the influence of process parameters on the control mode, enabling a comprehensive and in-depth analysis of process parameters in the battery production process, providing strong data support for monitoring, optimizing, and controlling the quality of the production process. On the other hand, based on the contribution, key process parameters with a significant impact on the control mode can be selected from multiple process parameters, thereby improving product stability, reducing product defect rates, and enabling timely implementation of appropriate corrective measures.

[0085] In one embodiment, when the control mode includes a consistency analysis mode, the process data includes data from different production batches and / or different production stages.

[0086] A production batch refers to a collection of identical batteries produced according to a certain quantity, time, or specific conditions during the battery manufacturing process. This disclosure can be applied to the consistency analysis of process data between different production batches, where the required process data includes data from different production batches; it can also be applied to the consistency analysis of process data at different production stages within the same production batch, where the required process data includes data from different production stages within the same production batch.

[0087] In this embodiment of the disclosure, by reasonably screening process data and conducting consistency analysis, the key process parameters affecting the consistency of battery performance during battery production are determined, thereby improving the yield rate of battery production.

[0088] Figure 3 A flowchart illustrating a contribution determination method provided by an embodiment of this disclosure is shown. Figure 3 As shown, in one embodiment, the target control algorithm is the Extreme Gradient Boosting (XGBoost) model; S206 above processes the process feature data using the target control algorithm corresponding to the control mode to obtain the contribution of each process parameter, including:

[0089] S302. Using product quality indicators as variables, construct an XGBoost model based on process characteristic data;

[0090] S304. Based on the XGBoost model, calculate the contribution of each process parameter, wherein the contribution includes at least one of the following: the number of times the process parameter is used as a splitting feature in all trees of the XGBoost model, the total gain of the process parameter in all trees of the XGBoost model, and the number of samples affected by the process parameter in all trees of the XGBoost model.

[0091] In S302, XGBoost is a model that uses Gradient Boosting Decision Tree (GBDT) as a base learner. It optimizes the model by continuously adding new decision trees to fit the residuals of previous models. The decision trees in the XGBoost model use a level-wise growth method, attempting to split off all leaf nodes in each iteration.

[0092] The extreme gradient boosting model uses a regression tree as each base classifier, and the training method employs a forward stepwise algorithm to optimize each base classifier.

[0093] When building the XGBoost model, product quality indicators can include battery yield, key performance indicators, etc.

[0094] In S304, the XGBoost model built based on process feature data can use feature importance to measure the contribution of each process parameter to the prediction accuracy of the XGBoost model.

[0095] The feature importance index of the XGBoost model can be determined by methods such as the weighting method, gain method, and coverage method. The calculated feature importance is used as the contribution of each process parameter. The weighting method determines the number of times the process parameter is used as a splitting feature in all trees of the XGBoost model, denoted as the weight value; the gain method determines the total gain of the process parameter in all trees of the XGBoost model, denoted as the total gain; and the coverage method determines the number of samples affected by the process parameter in all trees of the XGBoost model, denoted as the coverage.

[0096] The greater the total gain of a process parameter, the higher its impact on battery production consistency; conversely, the smaller the total gain, the lower its impact. Therefore, the contribution of process parameters can be calculated using the gain method, serving as the basis for selecting target process parameters. This allows us to identify process parameters with a high impact on battery production consistency and improve the accuracy of battery production control.

[0097] Coverage, also known as Cover, is the number of samples covered by a leaf node under a process parameter when splitting a decision tree, divided by the number of times that process parameter is used for splitting. The closer the split is to the root, the greater the coverage. The greater the coverage, the greater the contribution, and the higher the degree of influence of the process parameter on the consistency of battery production.

[0098] In this embodiment of the disclosure, the XGBoost model can identify key process parameters that affect consistency analysis and quantify the fluctuations of key process parameters in different production batches or different production stages. This helps to monitor the stability of the battery production process, detect potential quality fluctuation risks in a timely manner, and improve the stability of battery quality.

[0099] In one embodiment, when the control mode includes an anomaly detection mode, the process data includes data on multiple process parameters collected during battery production.

[0100] Anomaly identification patterns are used to identify key process parameters that lead to product defects or non-conformities. Process data can be collected from multiple process parameters during battery production, and these parameters can vary, allowing target control algorithms to distinguish between acceptable and unacceptable products.

[0101] Process data can also be obtained from different production periods to determine when a product changes from qualified to unqualified, thereby allowing for the handling of unqualified products.

[0102] In this embodiment of the disclosure, by reasonably screening process data for anomaly identification, the key process parameters that cause battery defects during battery production can be determined. For example, in battery production, identifying parameters whose abnormal fluctuations may lead to battery short circuits or insufficient capacity can reduce the defect rate of battery production.

[0103] Figure 4 A flowchart illustrating another contribution determination method provided by an embodiment of this disclosure is shown. Figure 4 As shown, in one embodiment, the target control algorithm is a decision tree model; S206 above processes the process characteristic data through the target control algorithm corresponding to the control mode to obtain the contribution of each process parameter, including:

[0104] S402. Using battery qualification as a variable, construct a decision tree model based on process characteristic data;

[0105] S404. Based on the decision tree model, calculate the contribution of each process parameter. The contribution of the process parameter includes at least one of the following: the process parameter used by each split node in the decision tree model and the corresponding information gain or gain ratio; the number of times each process parameter is a split node in the decision tree model; or the sum of the information gains of each process parameter as a split node in all decision tree models.

[0106] Decision tree model is a rule-based nonparametric model with good interpretability and robustness. The decision tree model can construct a tree structure based on data characteristics and divide process data into different categories through the branches of the tree structure, thereby identifying outlier data points that are significantly different from other process data.

[0107] Decision tree models can clearly show the decision path of process data and identify the process parameters that contribute the most to the classification of outlier data.

[0108] In S402, the variable in the decision tree model is whether the product is qualified, or normal / abnormal.

[0109] Initialize the root node and select the globally optimal process feature data as the basis for root node judgment; segment the process feature data of the root node to form child nodes, and then repeat the segmentation of the process feature data of the child nodes. When the child node cannot be further segmented, a leaf node is formed, and the category (qualified or unqualified) of the leaf node is determined, thus completing the construction of the decision tree model.

[0110] In S404, the contribution of process parameters can be the process parameters used by each split node in the decision tree model and the corresponding information gain or gain ratio. Information gain measures the degree to which process parameters improve data purity, and gain ratio characterizes the intrinsic information of feature splitting. A split node refers to a node with child nodes or leaf nodes.

[0111] The contribution of process parameters can be represented by the number of times each process parameter acts as a splitting node in the decision tree model, also known as the characteristic frequency. The larger the value of this frequency, the greater the influence of the process parameter on product non-conformity.

[0112] The contribution of a process parameter can be represented by the sum of the information gains of each process parameter as a splitting node in all decision tree models. The larger the sum of information gains, the greater the influence of that process parameter on product nonconformity.

[0113] In this embodiment of the disclosure, anomaly identification can be performed using a decision tree model. This model identifies key process parameters that lead to product defects and quantifies the contribution of these key process parameters in different production batches and / or different production periods. This allows for timely detection of anomalies in the production process, enabling corresponding intervention and correction measures to improve the yield rate of battery production and reduce product defects.

[0114] In one embodiment, when the control mode includes a mean offset analysis mode, the process data includes data from different time points and / or different production batches.

[0115] Mean deviation analysis aims to identify changes in the distribution of process parameters across different production batches or at different points in time, thereby uncovering potential mean deviation problems.

[0116] In one embodiment, the target control algorithm is a similarity measurement algorithm; wherein, S206 above processes the process feature data through the target control algorithm corresponding to the control mode to obtain the contribution of each process parameter, including: calculating the similarity of the process data of each process parameter at different time points and / or different production batches through the similarity measurement algorithm, as the contribution of the process parameter.

[0117] The similarity measurement algorithm mentioned above can be a cosine similarity algorithm. That is, cosine similarity can be used to measure the similarity of the distribution of process parameters at different production batches or different time points.

[0118] Treating the values ​​of each process parameter across different production batches or time points as vectors, we calculate the cosine similarity between these vectors to measure their directional similarity. A cosine similarity value closer to 1 indicates greater similarity between the two vectors, while a value closer to -1 indicates less similarity.

[0119] It should be noted that, in addition to using cosine similarity to determine the contribution, Euclidean distance, Manhattan distance, and other methods can also be used, and this disclosure does not make specific limitations on this.

[0120] In this embodiment of the disclosure, a similarity measurement algorithm is used to measure the similarity of process parameters at different time points or in different production batches, thereby performing mean offset analysis to identify key process parameters that cause fluctuations in product quality, improve the yield rate of battery production, and reduce product defects.

[0121] Figure 5 This diagram illustrates another battery production control method provided by an embodiment of the present disclosure. Figure 2 Based on the example, S208 is refined to S2082 to limit the case where the target process parameters are determined based on contribution. For example... Figure 5 As shown, in one embodiment, the method includes steps S202-S206 and S2082. Step S208 involves determining the target process parameter from multiple process parameters based on contribution, including:

[0122] S2082. Sort the contribution levels and determine the preset number of process parameters that are ranked first or last as the target process parameters.

[0123] It should be noted that the specific implementation of S202 to S202 in this embodiment is similar to the specific implementation of S202 to S206 in the previous embodiment, and will not be repeated here.

[0124] The target process parameters are those that contribute significantly to the product's performance, i.e., the key process parameters.

[0125] In one embodiment, the contribution can be sorted in descending order to determine a preset number of process parameters that are ranked first as target process parameters.

[0126] In one embodiment, the contribution can be sorted in ascending order to determine a preset number of process parameters that are ranked last as target process parameters.

[0127] The preset quantity can be pre-configured in the system, and the preset quantity is less than the number of process parameters. The value of the preset quantity can be determined according to actual needs, and there is no specific limitation on it. For example, the preset quantity can be 3, 5, etc.

[0128] For example, when the control mode is consistency analysis mode, multiple process parameters are sorted in descending order according to their contribution to obtain a contribution ranking based on consistency analysis. This is suitable for analyzing the situations where process parameters have the greatest impact on the consistency and stability of product quality. The process parameters with higher rankings indicate that they have a greater impact on product quality in different production batches or different production stages, and fluctuations may lead to product quality instability. The process parameters with higher rankings are taken as target process parameters, which are key parameters that need to be monitored and controlled.

[0129] For example, when the control mode is anomaly identification mode, multiple process parameters are sorted in descending order based on characteristic frequency or total information gain to obtain a contribution ranking based on anomaly analysis. This is suitable for identifying key factors leading to product defects. For instance, in battery production, abnormal fluctuations in process parameters may cause short circuits or insufficient capacity in the battery. The process parameters ranked higher indicate that the abnormal values ​​of these parameters are most likely to lead to the product being classified as an anomaly (e.g., a non-conforming product). These top-ranked process parameters are taken as target process parameters, which are key parameters that need to be focused on and optimized to reduce the product defect rate.

[0130] For example, when the control mode is mean shift analysis mode, multiple process parameters are sorted in descending order based on the magnitude of similarity changes to obtain a contribution ranking based on mean shift analysis. This is suitable for analyzing significant distribution changes of process parameters across different production batches or time points. For instance, in battery production, the distribution of process parameters varies significantly across different production batches, leading to fluctuations in product quality. The process parameters ranked higher indicate that their distribution varies considerably across different production batches or time points, potentially representing a key factor causing product quality fluctuations. These top-ranked process parameters should be used as target process parameters, requiring further investigation to determine if a mean shift issue exists and to implement appropriate corrective measures.

[0131] In one embodiment, process parameters whose contribution is greater than a preset contribution threshold can also be determined as target process parameters. The preset contribution threshold can be determined according to actual needs, and this disclosure does not specifically limit it.

[0132] In this embodiment of the disclosure, selecting target process parameters based on their contribution ranking can significantly improve the stability and consistency of the battery production process, enhance the efficiency of process development and improvement, reduce the risk of quality fluctuations during battery production, and lower production costs.

[0133] In one embodiment, the battery production control method of this disclosure further includes: using a visualization tool to verify the target process parameters and obtain the verification result.

[0134] Visualization tools may include at least one of box plots, two-value time series plots, and two-value scatter plots.

[0135] Box plot analysis can be used to create box plots for each high-contribution process parameter to observe the distribution of process data, including the median, quartiles, and outliers. By comparing box plots of different process parameters, it is possible to preliminarily determine whether there are significant differences or similarities between them. Pay attention to any outliers and analyze their impact on the overall process data distribution and correlation.

[0136] Two-value time series analysis can plot two-value time series diagrams for process parameters that change over time. It compares the control mode with the process parameters that contribute significantly to the process over time, observes the changing trends of the two time series curves, and determines whether there is synchronicity or lag between them. This allows for a preliminary assessment of the correlation between the two, analysis of periodic, seasonal or sudden changes in the two-sub-time series diagrams, and determination of the impact of the changes on the analysis target.

[0137] Two-valued scatter plot analysis can generate a scatter plot showing the relationship between the analytical target and each highly contributing process parameter. This visually displays the distribution of scatter points, allowing analysis of the shape and direction of the scatter plot to determine if a linear, non-linear, or other complex relationship exists between the two variables. The correlation coefficient of the scatter plot is calculated and labeled to quantify the degree of correlation between the two variables. Outliers in the two-valued scatter plot are analyzed to explore their impact on the overall correlation and to consider whether further processing is necessary.

[0138] The verification result can include verification pass or verification fail. Target process parameters that pass the verification are identified as critical process parameters. Target process parameters that fail the verification can no longer be controlled as critical process parameters in the battery production process.

[0139] In this embodiment of the disclosure, by verifying the target process parameters, the effectiveness of battery production control can be improved, and data support can be provided for the closed-loop management of process parameters; visualization tools can enhance the intuitiveness and readability of the test results.

[0140] This disclosure utilizes consistency analysis, anomaly analysis, and mean deviation analysis to monitor and optimize production processes in real time, thereby improving production efficiency and product quality. Through precise data insights and machine learning algorithms, it achieves anomaly detection, root cause analysis, mean deviation monitoring, and trend prediction, providing manufacturing enterprises with a scientific basis to drive continuous improvement and help them achieve intelligent manufacturing.

[0141] Based on the same inventive concept, this disclosure also provides a battery production control device, as described in the following embodiments. Since the principle by which this device solves the problem is similar to that of the method embodiments described above, the implementation of this device embodiment can refer to the implementation of the method embodiments described above, and repeated details will not be repeated.

[0142] Figure 7 This diagram illustrates a battery production control device according to an embodiment of the present disclosure, such as... Figure 7 As shown, in one embodiment, the device includes a data acquisition module 710, a feature extraction module 720, a data processing module 730, and a production control module 740.

[0143] Among them, the data acquisition module 710 is used as a data acquisition module to acquire process data of multiple process parameters corresponding to the control mode;

[0144] The feature extraction module 720 is used to process process data to obtain process feature data;

[0145] The data processing module 730 is used to process the process characteristic data through the target control algorithm corresponding to the control mode to obtain the contribution of each process parameter;

[0146] The production control module 740 is used to determine the target process parameters from multiple process parameters based on the contribution, and to control the battery production process based on the target process parameters and the control mode.

[0147] It should be noted that when the control mode includes the consistency analysis mode, the process data includes data from different production batches and / or different production stages.

[0148] In one embodiment, the target control algorithm is the Extreme Gradient Boosting (XGBoost) model; the data processing module 730 is used to construct an XGBoost model based on process feature data, using product quality indicators as variables; and to calculate the contribution of each process parameter based on the XGBoost model, wherein the contribution includes at least one of the following: the number of times the process parameter is used as a splitting feature in all trees of the XGBoost model, the total gain of the process parameter in all trees of the XGBoost model, and the number of samples affected by the process parameter in all trees of the XGBoost model.

[0149] It should be noted that when the control mode includes an anomaly identification mode, the process data includes data from multiple process parameters collected during battery production.

[0150] In one embodiment, the target control algorithm is a decision tree model; the data processing module 730 is used to construct a decision tree model based on process characteristic data, taking whether the battery is qualified as a variable; and to calculate the contribution of each process parameter based on the decision tree model. The contribution of the process parameter includes at least one of the following: the process parameter used by each split node in the decision tree model and the corresponding information gain or gain ratio; the number of times each process parameter is a split node in the decision tree model; or the sum of the information gains of each process parameter as a split node in all decision tree models.

[0151] It should be noted that when the control mode includes mean offset analysis mode, the process data includes data from different time points and / or different production batches.

[0152] In one embodiment, the target control algorithm is a similarity measurement algorithm; the data processing module 730 is used to calculate the similarity of process data of each process parameter at different time points and / or different production batches through the similarity measurement algorithm, as the contribution of the process parameter.

[0153] In one embodiment, the production control module 740 is used to sort the contribution levels and determine a preset number of process parameters that are ranked first or last as target process parameters.

[0154] In one embodiment, the feature extraction module 710 is used to preprocess the process data to obtain processed process data; and associate the processed process data with the corresponding battery identification information to obtain process feature data.

[0155] In one embodiment, the apparatus further includes a verification module (not shown in the figures), which is used to verify the target process parameters using a visualization tool to obtain verification results.

[0156] In this embodiment, process data of multiple process parameters corresponding to a control mode are acquired; the process data are processed to obtain process feature data; the process feature data are processed using a target control algorithm corresponding to the control mode to obtain the contribution of each process parameter; a target process parameter is determined from the multiple process parameters based on the contribution; and the battery production process is controlled based on the target process parameter and the control mode. In this disclosure, on the one hand, multiple process parameters that may have a correlation are determined through the control mode, and the contribution of the process parameters is determined using a target control algorithm corresponding to the control mode. This quantifies the influence of process parameters on the control mode, enabling a comprehensive and in-depth analysis of process parameters in the battery production process, providing strong data support for monitoring, optimizing, and controlling the quality of the production process. On the other hand, based on the contribution, key process parameters with a significant impact on the control mode can be selected from multiple process parameters, thereby improving product stability, reducing product defect rates, and enabling timely implementation of appropriate corrective measures.

[0157] Those skilled in the art will understand that various aspects of this disclosure can be implemented as a system, method, or program product. Therefore, various aspects of this disclosure can be specifically implemented in the following forms: a completely hardware implementation, a completely software implementation (including firmware, microcode, etc.), or a combination of hardware and software aspects, collectively referred to herein as a "circuit," "module," or "system."

[0158] The following reference Figure 8 To describe an electronic device 800 according to such an embodiment of the present disclosure. Figure 8 The electronic device 800 shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments disclosed herein.

[0159] In one embodiment, the electronic device 800 includes a processor and a memory for storing executable instructions of the processor, wherein the processor is configured to perform the battery production control method described above by executing the executable instructions.

[0160] like Figure 8 As shown, the electronic device 800 is manifested in the form of a general-purpose computing device. The components of the electronic device 800 may include, but are not limited to: at least one processing unit 810, at least one storage unit 820, and a bus 830 connecting different system components (including storage unit 820 and processing unit 810).

[0161] The storage unit stores program code that can be executed by the processing unit 810, causing the processing unit 810 to perform the steps described in the "Exemplary Methods" section of this specification according to various exemplary embodiments of this disclosure. For example, the processing unit 810 can perform the following steps of the above method embodiments: acquiring process data of multiple process parameters corresponding to a control mode; processing the process data to obtain process feature data; processing the process feature data using a target control algorithm corresponding to the control mode to obtain the contribution of each process parameter; determining a target process parameter from the multiple process parameters based on the contribution; and controlling the battery production process based on the target process parameter and the control mode.

[0162] Storage unit 820 may include a readable medium in the form of a volatile storage unit, such as random access memory (RAM) 8201 and / or cache memory 8202, and may further include a read-only memory (ROM) 8203.

[0163] The storage unit 820 may also include a program / utility 8204 having a set (at least one) of program modules 8205, including but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment.

[0164] Bus 830 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.

[0165] Electronic device 800 can also communicate with one or more external devices 840 (e.g., keyboard, pointing device, Bluetooth device, etc.), and with one or more devices that enable a user to interact with the electronic device 800, and / or with any device that enables the electronic device 800 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interface 850. Furthermore, electronic device 800 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 860. Figure 8 As shown, network adapter 860 communicates with other modules of electronic device 800 via bus 830. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with electronic device 800, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0166] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, terminal device, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0167] In particular, according to embodiments of the present disclosure, the processes described above with reference to the flowcharts can be implemented as a computer program product, which includes a computer program that, when executed by a processor, implements the steps described in the "Exemplary Methods" section above according to various exemplary embodiments of the present disclosure.

[0168] In exemplary embodiments of this disclosure, a computer-readable storage medium is also provided, having a computer program stored thereon that, when executed by a processor, implements the steps of the various exemplary embodiments of this disclosure described in the "Exemplary Methods" section above. This computer-readable storage medium may be a readable signal medium or a readable storage medium.

[0169] In some possible implementations, various aspects of this disclosure can also be implemented as a program product comprising a computer program that, when executed by a processor, implements the battery production control method of any of the above embodiments. In one possible embodiment, the program product includes program code that, when the program product is run on a terminal device, causes the terminal device to perform the steps of the various exemplary embodiments of this disclosure described in the "Exemplary Methods" section above.

[0170] More specific examples of computer-readable storage media in this disclosure may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0171] In this disclosure, a computer-readable storage medium may include a data signal propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium, capable of transmitting, propagating, or transmitting a program for use by or in connection with an instruction execution system, apparatus, or device.

[0172] Optionally, the program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0173] In practical implementation, program code for performing the operations of this disclosure can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0174] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to embodiments of this disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0175] Furthermore, although the steps of the method in this disclosure are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in that specific order, or that all the steps shown must be performed to achieve the desired result. Additional or alternative steps may be omitted, multiple steps may be combined into one step, and / or a step may be broken down into multiple steps.

[0176] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, mobile terminal, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0177] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the appended claims.

Claims

1. A battery production control method, characterized in that, include: Acquire process data for multiple process parameters corresponding to the control mode; The process data is processed to obtain process feature data; The process feature data is processed by the target control algorithm corresponding to the control mode to obtain the contribution of each process parameter. The target process parameter is determined from multiple process parameters based on the contribution, and the battery production process is controlled based on the target process parameter and the control mode.

2. The method according to claim 1, characterized in that, When the control mode includes a consistency analysis mode, the process data includes data from different production batches and / or different production stages.

3. The method according to claim 2, characterized in that, The target control algorithm is the Extreme Gradient Boosting (XGBoost) model. The step of processing the process feature data using a target control algorithm corresponding to the control mode to obtain the contribution of each process parameter includes: Using product quality indicators as variables, the XGBoost model is constructed based on the process characteristic data. Based on the XGBoost model, the contribution of each process parameter is calculated, wherein the contribution includes at least one of the following: the number of times the process parameter is used as a splitting feature in all trees of the XGBoost model, the total gain of the process parameter in all trees of the XGBoost model, and the number of samples affected by the process parameter in all trees of the XGBoost model.

4. The method according to claim 1, characterized in that, When the control mode includes an anomaly identification mode, the process data includes data of the multiple process parameters collected during battery production.

5. The method according to claim 4, characterized in that, The target control algorithm is a decision tree model; The step of processing the process feature data using a target control algorithm corresponding to the control mode to obtain the contribution of each process parameter includes: Using battery qualification as a variable, a decision tree model is constructed based on the process characteristic data. Based on the decision tree model, the contribution of each process parameter is calculated. The contribution of the process parameter includes at least one of the following: the process parameter used by each split node in the decision tree model and the corresponding information gain or gain ratio; the number of times each process parameter is a split node in the decision tree model; or the sum of the information gains of each process parameter as a split node in all decision tree models.

6. The method according to claim 1, characterized in that, When the control mode includes a mean offset analysis mode, the process data includes data from different time points and / or different production batches.

7. The method according to claim 6, characterized in that, The target control algorithm is a similarity measurement algorithm; The step of processing the process feature data using a target control algorithm corresponding to the control mode to obtain the contribution of each process parameter includes: The similarity of process data for each process parameter at different time points and / or different production batches is calculated using a similarity measurement algorithm, and this similarity is used as the contribution of the process parameter.

8. The method according to any one of claims 1-7, characterized in that, The process of determining the target process parameter from multiple process parameters based on contribution includes: The contribution levels are sorted, and a preset number of process parameters that are ranked first or last are determined as the target process parameters.

9. The method according to claim 1, characterized in that, The process data processing to obtain process feature data includes: The process data is preprocessed to obtain processed process data; The processed process data is associated with the corresponding battery identification information to obtain the process feature data.

10. The method according to claim 1, characterized in that, The method further includes: The target process parameters were verified using a visualization tool, and the verification results were obtained.

11. A battery production control device, characterized in that, include: The data acquisition module is used to acquire process data for multiple process parameters corresponding to the control mode; The feature extraction module is used to process the process data to obtain process feature data; The data processing module is used to process the process feature data through a target control algorithm corresponding to the control mode to obtain the contribution of each process parameter. The production control module is used to determine the target process parameters from multiple process parameters based on the contribution, and to control the battery production process based on the target process parameters and the control mode.

12. An electronic device, characterized in that, include: processor; as well as Memory for storing the executable instructions of the processor; The processor is configured to execute the battery production control method according to any one of claims 1 to 10 by executing the executable instructions.

13. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the battery production control method according to any one of claims 1 to 10.

14. A computer program product, characterized in that, It includes a computer program, which, when executed by a processor, implements the battery production control method according to any one of claims 1 to 10.

Images