Coating weight loss ratio prediction method, electronic equipment and storage medium

Abstract

The embodiment of the invention discloses a coating weight loss ratio prediction method, electronic equipment and a storage medium. Production control data collected in the coating process of the battery pole piece and quality detection data generated by a manufacturing execution system corresponding to the battery pole piece are obtained, and the quality detection data comprise a first coating weight loss ratio obtained through pre-detection; determining the detection time corresponding to the first coating weight loss ratio, the delay duration between the detection time and the production time of the battery pole piece, and the production duration of the battery pole piece; determining a target time window based on the detection time, the delay duration and the production duration; based on the target time window, performing data alignment on the production control data and the quality detection data to obtain aligned coating data; and predicting a second coating weight loss ratio of the battery pole piece based on the aligned coating data. Therefore, the coating weight loss ratio of the battery pole piece can be accurately and efficiently predicted, and the prediction efficiency of the coating weight loss ratio of the battery pole piece is improved.

Description

Technical Field

[0001] This application relates to the field of battery technology, specifically to a method for predicting coating weight loss rate, electronic devices, and storage media. Background Technology

[0002] The quality control of the electrode coating process in batteries directly affects the consistency and safety of the finished batteries.

[0003] However, existing production lines generally suffer from the problem of inaccurate alignment between quality inspection data from Manufacturing Execution System (MES) and production control data collected from Internet of Things (IoT) devices. This is especially true in cases where there is no barcode association or the data sample is small. The inability to accurately align quality inspection data with production control data makes it impossible for existing coating weight loss prediction methods to accurately and efficiently predict the coating weight loss rate of battery electrodes. Summary of the Invention

[0004] This application provides a coating weight loss prediction method, electronic device, and storage medium, which can accurately align quality inspection data and production control data, thereby enabling accurate and efficient prediction of the coating weight loss rate of battery electrodes based on the aligned quality inspection data and production control data, further improving the prediction efficiency of the coating weight loss rate of battery electrodes.

[0005] This application provides a method for predicting coating weight loss rate, including: Acquire production control data collected during the coating process of the battery electrode, and quality inspection data generated by the manufacturing execution system corresponding to the battery electrode, wherein the quality inspection data includes the first coating weight loss rate obtained in advance; Determine the detection time corresponding to the first coating weight loss rate, the delay between the detection time and the production time of the battery electrode, and the production time of the battery electrode; The target time window is determined based on the detection time, the delay duration, and the production duration; Based on the target time window, the production control data and the quality inspection data are aligned to obtain aligned coating data; The second coating weight loss rate of the battery electrode is predicted based on the aligned coating data.

[0006] In one embodiment, determining the target time window based on the detection time, the delay duration, and the production duration includes: The starting point of the window is determined based on the detection time, the delay duration, and the production duration; Based on the detection time, determine the end point of the window; The target time window is determined based on the window start point and the window end point.

[0007] Thus, by dynamically determining the target time window for data alignment based on the detection time, delay duration, and electrode production time corresponding to the quality inspection data, accurate data alignment of production control data and quality inspection data can be achieved based on the dynamically determined time window.

[0008] In one embodiment, the step of aligning the production control data and the quality inspection data based on the target time window to obtain aligned coating data includes: Based on the target time window, target production control data that matches the quality inspection data is found in the production control data to obtain aligned coating data.

[0009] Thus, by aligning production control data and quality inspection data based on a dynamic target time window, the accuracy of aligning production control data and quality inspection data can be improved, further enhancing the prediction efficiency of battery electrode coating weight loss rate.

[0010] In one embodiment, the step of searching for target production control data that matches the quality inspection data in the production control data based on the target time window to obtain aligned coating data includes: Calculate multiple statistical indicators corresponding to the production control data to obtain the statistical characteristics of the production control data; Based on the target time window and the time information corresponding to the production control data, a target data statistical feature that matches the quality inspection data is found in the data statistical features; Based on the quality inspection data and the statistical characteristics of the target data, the aligned coating data is obtained.

[0011] Thus, by performing feature statistics and aggregation on the original production control data, and then aligning the aggregated data statistical features with the corresponding quality inspection data, the accuracy of data alignment can be improved, further enhancing the prediction efficiency of battery electrode coating weight loss rate.

[0012] In one embodiment, predicting the second coating weight loss rate of the battery electrode based on the aligned coating data includes: Based on the aligned coating data, the second coating weight loss rate of the battery electrode is predicted using a target prediction model.

[0013] Therefore, by using a target prediction model to predict the coating weight loss rate of battery electrodes, the accuracy of predicting the coating weight loss rate of battery electrodes can be improved.

[0014] In one embodiment, before predicting the second coating weight loss rate of the battery electrode using a target prediction model based on the aligned coating data, the method further includes: At least one evaluation index is calculated using multiple candidate prediction models to obtain the index calculation results corresponding to the evaluation index. Based on the calculation results of the aforementioned indicators, the target prediction model is selected from the prediction models.

[0015] Thus, by calculating multiple evaluation indicators and selecting the optimal target prediction model from multiple prediction models, the prediction efficiency of coating weight loss rate of battery electrode can be further improved by using the target prediction model to predict the coating weight loss rate.

[0016] In one embodiment, the step of selecting a target prediction model from the prediction models based on the index calculation results includes: The calculation results of the aforementioned indicators are standardized to obtain an initial evaluation score; The initial evaluation score is fused based on the preset weights corresponding to the evaluation indicators to obtain the target evaluation score corresponding to the prediction model. Based on the target evaluation score, a target prediction model is selected from the prediction models.

[0017] In this way, the target evaluation score of each prediction model is determined by calculating multiple evaluation indicators. Based on the target evaluation score, the optimal target prediction model is selected from multiple prediction models. Based on the target prediction model, the coating weight loss rate is predicted, thereby further improving the prediction efficiency of battery electrode coating weight loss rate.

[0018] In one embodiment, after predicting the second coating weight loss rate of the battery electrode using a target prediction model based on the aligned coating data, the method further includes: Determine the model stability index corresponding to the target prediction model; If the model stability index meets the preset stability conditions, the detection frequency of the first coating weight loss rate is reduced. If the model stability index does not meet the preset stability condition, determine the model prediction accuracy of the target prediction model; If the prediction accuracy of the target prediction model decreases, the detection frequency of the first coating weight loss rate will be increased.

[0019] Thus, by adjusting the detection frequency of quality inspection data according to the model stability index corresponding to the target prediction model, the prediction efficiency of battery electrode coating weight loss rate can be further improved.

[0020] In one embodiment, the method further includes: If the second coating weight loss rate of the battery electrode is greater than the preset weight loss rate threshold, an alarm operation is executed.

[0021] Thus, by issuing an alarm in a timely manner when the second coating weight loss rate of the battery electrode is detected to be greater than the preset weight loss rate threshold, the abnormal feedback chain can be shortened, and the prediction efficiency of the coating weight loss rate of the battery electrode can be further improved.

[0022] Accordingly, embodiments of this application also provide a coating weight loss prediction device, comprising: The acquisition unit is used to acquire production control data collected during the coating process of the battery electrode, as well as quality inspection data generated by the manufacturing execution system corresponding to the battery electrode. The quality inspection data includes the first coating weight loss rate obtained in advance. The first determining unit is used to determine the detection time corresponding to the first coating weight loss rate, the delay time between the detection time and the production time of the battery electrode, and the production time of the battery electrode. The second determining unit is used to determine a target time window based on the detection time, the delay duration, and the production duration; An alignment unit is used to align the production control data and the quality inspection data based on the target time window to obtain aligned coating data. A prediction unit is used to predict the second coating weight loss rate of the battery electrode based on the aligned coating data.

[0023] Furthermore, embodiments of this application also provide an electronic device, including a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor performs the steps of any of the coating weight loss prediction methods provided in embodiments of this application.

[0024] Furthermore, embodiments of this application also provide a computer-readable storage medium including a computer program, which, when run on an electronic device, causes the electronic device to perform the steps of any of the coating weight loss prediction methods provided in embodiments of this application.

[0025] Furthermore, embodiments of this application also provide a computer program product, including a computer program stored in a computer-readable storage medium; when a processor of an electronic device reads the computer program from the computer-readable storage medium, the processor executes the computer program, causing the electronic device to perform the steps of any of the coating weight loss prediction methods provided in embodiments of this application.

[0026] This application embodiment acquires production control data collected during the coating process of battery electrodes, and quality inspection data generated by the manufacturing execution system corresponding to the battery electrodes. The quality inspection data includes a first coating weight loss rate obtained through pre-detection; determining the detection time corresponding to the first coating weight loss rate, the delay between the detection time and the production time of the battery electrodes, and the production time of the battery electrodes; determining a target time window based on the detection time, delay, and production time; aligning the production control data and quality inspection data based on the target time window to obtain aligned coating data; and predicting a second coating weight loss rate of the battery electrodes based on the aligned coating data. Thus, by determining the target time window based on the detection time, delay, and production time of the battery electrodes obtained through pre-detection of the first coating weight loss rate, the quality inspection data and production control data can be accurately aligned based on the dynamic target time window. Furthermore, based on the aligned quality inspection data and production control data, accurate and efficient prediction of the coating weight loss rate of battery electrodes can be achieved even without barcode association or with small data samples, further improving the prediction efficiency of the coating weight loss rate of battery electrodes. Attached Figure Description

[0027] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0028] Figure 1 This is a schematic diagram of an implementation scenario for a coating weight loss prediction method provided in the embodiments of this application; Figure 2 This is a flowchart illustrating a coating weight loss prediction method provided in an embodiment of this application. Figure 3a This is a schematic diagram of the delay distribution of a coating weight loss prediction method provided in the embodiments of this application; Figure 3b This is a schematic diagram of model screening for a coating weight loss rate prediction method provided in the embodiments of this application; Figure 3cThis is a schematic diagram of the specific process of a coating weight loss prediction method provided in the embodiments of this application; Figure 3d This is another specific flowchart illustrating a coating weight loss prediction method provided in the embodiments of this application; Figure 3e This is a schematic diagram of the system architecture of a coating weight loss prediction method provided in the embodiments of this application; Figure 4 This is a schematic diagram of the coating weight loss prediction device provided in the embodiments of this application; Figure 5 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0029] 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, and 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.

[0030] Furthermore, in the description of the embodiments of this application, the terms "first," "second," etc., are used only for distinguishing descriptions and should not be construed as indicating or implying relative importance. Therefore, a feature specified as "first" or "second" may explicitly or implicitly include one or more features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0031] This application provides a method, apparatus, electronic device, and storage medium for predicting coating weight loss rate. The coating weight loss rate prediction apparatus can be integrated into an electronic device, which can be a server, a terminal, or other similar device.

[0032] The server can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery network (CDN) acceleration services, and big data and artificial intelligence platforms. The terminal can include, but is not limited to, mobile phones, computers, smart voice interaction devices, smart home appliances, vehicle terminals, and aircraft. The terminal and server can be directly or indirectly connected via wired or wireless communication, which is not limited herein.

[0033] Please see Figure 1Taking the integration of coating weight loss prediction devices into electronic devices as an example, Figure 1 This is a schematic diagram illustrating an implementation scenario of the coating weight loss prediction method provided in this application. The electronic device can be a server or a terminal. It can acquire production control data collected during the coating process of the battery electrode, as well as quality inspection data generated by the manufacturing execution system corresponding to the battery electrode. The quality inspection data includes a pre-detected first coating weight loss rate; determining the detection time corresponding to the first coating weight loss rate, the delay between the detection time and the production time of the battery electrode, and the production time of the battery electrode; determining a target time window based on the detection time, the delay time, and the production time; aligning the production control data and the quality inspection data based on the target time window to obtain aligned coating data; and predicting a second coating weight loss rate of the battery electrode based on the aligned coating data.

[0034] It should be noted that, Figure 1 The schematic diagram illustrating the implementation environment of the coating weight loss prediction method is merely an example. The implementation environment of the coating weight loss prediction method described in this application is intended to more clearly illustrate the technical solutions of this application and does not constitute a limitation on the technical solutions provided in this application. Those skilled in the art will recognize that, with the evolution of data processing and the emergence of new business scenarios, the technical solutions provided in this application are equally applicable to similar technical problems.

[0035] The solutions provided in this application are specifically illustrated through the following embodiments. It should be noted that the order of description of the following embodiments is not intended to limit the preferred order of the embodiments.

[0036] This embodiment will be described from the perspective of a coating weight loss prediction device, which can be integrated into an electronic device, such as a server or a terminal, and this application does not impose any restrictions on it.

[0037] Please see Figure 2 , Figure 2 This is a flowchart illustrating the coating weight loss prediction method provided in this application embodiment. The coating weight loss prediction method includes: In step 101, production control data collected during the coating process of the battery electrode and quality inspection data generated by the manufacturing execution system corresponding to the battery electrode are obtained.

[0038] The quality inspection data may include the first coating weight loss rate obtained in advance.

[0039] The battery electrode can be a battery electrode, and the battery can be a lithium-ion battery or other type of battery. The production control data can be production process parameters collected by equipment sensors during the coating process of the battery electrode; this can be simply referred to as Internet of Things (IoT) data. It can include process parameters, equipment status parameters, and environmental parameters during the coating process. For example, process parameters may include real-time data such as oven temperature, coating speed, and slurry pressure; equipment status parameters may include motor current, vibration frequency, and valve opening; and environmental parameters may include data on workshop temperature, humidity, and cleanliness. The Manufacturing Execution System (MES) serves as a shop floor-level management information system, bridging the upper-level planning and management system and the lower-level industrial control system. The quality inspection data, often simply referred to as MES data, primarily originates from shop floor management information. This data can include production order information such as work order numbers, product specifications, and planned output; resource status information, such as equipment status (running, downtime, faulty); personnel information; material consumption; quality inspection results, such as weight loss rate, defect codes, and inspection time measured manually or with quality inspection equipment during the coating process; and performance indicators, such as Overall Equipment Effectiveness (OEE), output rate, and pass rate. The first coating weight loss rate can be obtained by manually or with quality inspection equipment inspecting the battery electrode sheets. For example, after the production of a single electrode roll is completed, a portion of the electrode sheets can be sampled to obtain the first coating weight loss rate.

[0040] In the battery electrode coating process, coating weight loss rate is a key quality indicator. It is typically measured and recorded in the MES system after coating via offline weighing, while the IoT platform continuously collects various process parameters during the coating machine's operation. Since the quality of the coated product (coating weight loss rate) is determined by process parameters (such as oven temperature and coating speed) at specific time points during production, a reliable predictive model can only be trained by precisely mapping each quality inspection result (MES data) to the original process data (IoT data) used to produce the product. This allows for the identification of key parameters affecting quality and accurate prediction of the battery electrode coating weight loss rate. Furthermore, the quality inspection completion time (T_test) recorded in the MES system usually lags behind the actual production end time (due to time required for cooling, handling, and measurement). Therefore, directly searching IoT data using T_test will incorrectly correlate with subsequent batch production data, introducing noisy data and reducing data alignment quality. Furthermore, in industrial scenarios, quality inspection data is typically far less than production control data. For example, a weight loss rate test result might only occur every few hours, while production control data is generated every second. Therefore, precise time window alignment ensures that limited quality data is paired with correct, high-quality production control data, maximizing the utilization of each sample and improving the model's generalization ability with small sample sizes. Thus, to establish a correlation model between quality inspection data and production control data and achieve accurate coating weight loss rate prediction, it is essential to trace MES data from the MES system back to IoT data.

[0041] In step 102, the detection time corresponding to the first coating weight loss rate, the delay between the detection time and the production time of the battery electrode, and the production time of the battery electrode are determined.

[0042] The detection time (T_test) can be the detection time for the first coating weight loss rate, or the time when the first coating weight loss rate detection is completed and entered into the MES system. For example, it can be the MES inspection sheet time (manual measurement completion time). The production time can be the time when the battery electrode production ends. The delay duration (T_delay) can be the time difference between the detection time and the production time, which can be determined through historical data analysis. For example, the empirical delay between the end of production and the completion of manual measurement can be one hour. The production duration (T_prod) can be the net manufacturing time of the battery electrode on the production line. For example, it can be the statistical average of the production time of a single electrode roll obtained from the MES work order, such as 1 hour for producing 1 roll of battery electrode.

[0043] For example, please refer to Figure 3a , Figure 3aThis is a schematic diagram of the delay distribution of a coating weight loss prediction method provided in this application embodiment. The horizontal axis represents the delay time interval, which is used to indicate the delay between the test and production time of the test sample. For example, [9, 29] can represent a delay time between 9 minutes and 29 minutes, and [29, 49] can represent a delay time between 29 minutes and 49 minutes. The vertical axis can represent the number of test samples, which is used to indicate the probability that the delay time of the test sample falls within each delay time interval. For example, the number of test samples with a delay time in the interval [9, 29] is 13, the number of test samples with a delay time in the interval [29, 49] is 22, and the number of test samples with a delay time in the interval [49, 69] is 35. Approximately 70% or more of the test samples have a delay time exceeding one hour.

[0044] In step 103, a target time window is determined based on the detection time, delay duration, and production duration.

[0045] The target time window can be a time window used for data alignment of production control data and quality inspection data.

[0046] There are several ways to determine the target time window based on detection time, delay duration, and production duration. For example, the window start point can be determined based on detection time, delay duration, and production duration, the window end point can be determined based on detection time, and the target time window can be determined based on the window start point and the window end point.

[0047] The starting point of this window can be the starting point of the time window corresponding to the quality inspection data at the current time, and the ending point of this window can be the ending point of the time window corresponding to the quality inspection data at the current time. A first coating weight loss rate can correspond to a target time window.

[0048] There are several ways to determine the starting point of the window based on the detection time, delay duration, and production duration. For example, you can input the detection time, subtract the fixed delay duration, and then subtract the production duration to obtain the starting point of the target time window corresponding to the quality inspection data.

[0049] For example, the window start point T_start = T_test T_delay T_prod, window end T_end=T_test If T_delay, then the target time window = [T_start, T_end].

[0050] The delay duration T_delay originates from the "coating-cooling-transfer-testing" process and has a stable statistical distribution. The production duration T_prod determines the material occupation time of a single roll of electrode sheet on the production line and serves as the physical basis for aligning MES data with IoT data. The window start point is determined by calculating T_test - T_delay - T_prod, and T_test is calculated as follows: Using T_delay to determine the end point of the window can strictly cover the complete physical process corresponding to the electrode, avoiding the problem of the coating weight loss prediction accuracy being reduced due to the window covering process data of other rolls or mixing in other irrelevant data.

[0051] Therefore, based on the target time window provided in the embodiments of this application, the constraint window determined by the physical logic based on the movement path of the electrode material can be used to perform time slicing and alignment of the quality inspection data and IoT data that match the first coating weight loss rate in time. Thus, based on the dynamic target time window that matches the time of each first coating weight loss rate, accurate and efficient data alignment of production control data and quality inspection data can be achieved.

[0052] In step 104, based on the target time window, the production control data and quality inspection data are aligned to obtain aligned coating data.

[0053] The aligned coating data may include production control data and quality inspection data aligned based on a target time window.

[0054] There are several ways to align production control data and quality inspection data based on the target time window to obtain aligned coating data. For example, based on the target time window, the target production control data that matches the quality inspection data can be found in the production control data to obtain aligned coating data.

[0055] The target production control data can be production control data that is time-aligned with the quality inspection data.

[0056] There are several ways to find the aligned coating data by searching for the target production control data that matches the quality inspection data in the production control data based on the target time window. For example, multiple data statistical indicators corresponding to the production control data can be calculated to obtain the data statistical features corresponding to the production control data; the target data statistical features that match the quality inspection data can be found in the data statistical features based on the target time window and the time information corresponding to the production control data; and the aligned coating data can be obtained based on the quality inspection data and the target data statistical features.

[0057] The statistical indicators can be metrics used to describe the data distribution characteristics of production control data, such as maximum, minimum, variance, mean, 25th percentile, and 75th percentile. The statistical features can be the results of calculating multiple statistical indicators from the production control data, such as the calculated maximum, minimum, and variance. The time information corresponding to the production control data can be the time when the production control data was generated, stored, or collected. The target statistical feature can be a statistical feature that matches the time of the quality inspection data.

[0058] Optionally, there are several ways to align production control data and quality inspection data based on the target time window to obtain aligned coating data. For example, based on the target time window and the time information corresponding to the production control data and quality inspection data, the production control data and quality inspection data that match each target time window can be found in the production control data and quality inspection data; the production control data and quality inspection data that match each target time window can be aligned to obtain aligned coating data.

[0059] In step 105, the second coating weight loss rate of the battery electrode is predicted based on the aligned coating data.

[0060] The second coating weight loss rate can be the coating weight loss rate predicted for the battery electrode based on the aligned coating data. The coating weight loss rate can refer to the proportion of mass loss caused by solvent evaporation or component decomposition after the wet film is dried or baked in the coating process.

[0061] There are several ways to predict the second coating weight loss rate of the battery electrode based on the aligned coating data. For example, the second coating weight loss rate of the battery electrode can be predicted by a target prediction model based on the aligned coating data.

[0062] The target prediction model can be a model used to predict the coating weight loss rate of battery electrodes. For example, it can be a Gradient Boosting Regression (GBR) model, a Random Forest (RF) model, an Extreme Gradient Boosting (XGBoost) model, a Light Gradient Boosting Machine (LightGBM) model, etc.

[0063] Optionally, at least one evaluation index can be calculated using multiple candidate prediction models to obtain the index calculation results corresponding to the evaluation index; the target prediction model can be selected from the prediction models based on the index calculation results.

[0064] The prediction model can be a pre-trained model used to predict the coating weight loss rate of battery electrodes. The evaluation metric can be a regression indicator to assess the quality of the model, such as the coefficient of determination (R²), mean square error (MSE), root mean square error (RMSE), and mean absolute error (MAE). The calculation result of this metric can be the result of calculating at least one evaluation metric using the prediction model.

[0065] There are several ways to select the target prediction model from the prediction model based on the indicator calculation results. For example, the indicator calculation results can be standardized to obtain an initial evaluation score; the initial evaluation score can be fused based on the preset weights corresponding to the evaluation indicators to obtain the target evaluation score corresponding to the prediction model; and the target prediction model can be selected from the prediction model based on the target evaluation score.

[0066] The target evaluation score can be used to measure the reliability of the prediction model.

[0067] Optionally, the specific weight values ​​of the preset weights can be determined based on the process sensitivity analysis of the battery electrode, for example, based on factors such as coating speed and oven temperature. Thus, by filtering the prediction models through preset weights, the most accurate and suitable target prediction model can be non-linearly selected in the battery electrode coating process scenario, improving the accuracy of coating weight loss rate prediction.

[0068] For example, please refer to Figure 3b , Figure 3bThis is a schematic diagram of model selection for a coating weight loss prediction method provided in the embodiments of this application. The prediction model may include GBR model, RF, XGBoost model, and LightGBM model. These four prediction models can be trained, and multiple evaluation metrics can be calculated using these models, including the coefficient of determination (R²), mean squared error (MSE), root mean squared error (RMSE), and mean absolute error (MAE). Then, the calculation results of each metric can be standardized, for example, by normalizing the results to obtain the initial evaluation scores of the prediction models under each evaluation metric. Next, the initial evaluation scores under each evaluation metric can be weighted and summed according to the preset weights corresponding to each metric to obtain the target evaluation score. For example, the preset weight for R² can be 0.5, the preset weight for MSE can be -0.15, the preset weight for RMSE can be -0.15, and the preset weight for MAE can be -0.2, etc. Specific weight values ​​can be set according to actual conditions. In this way, the target evaluation scores of each prediction model can be obtained, and the prediction model with the highest target evaluation score is determined as the optimal prediction model, i.e., the target prediction model.

[0069] Optionally, if the second coating weight loss rate of the battery electrode exceeds a preset weight loss rate threshold, an alarm operation is performed.

[0070] For example, please refer to Figure 3c , Figure 3c This is a schematic diagram of a coating weight loss prediction method provided in this application embodiment. The prediction module uses a target prediction model to obtain the prediction result of the second coating weight loss of the battery electrode. Specifically, the prediction module can run every 2 hours, outputting the predicted value and confidence interval of the second coating weight loss, and checking whether it meets the alarm conditions to execute an alarm operation. For example, if the predicted value of the second coating weight loss exceeds the process standard, the confidence interval of the predicted value is greater than 500 ppm (Parts Per Million), or the system used to implement the coating weight loss prediction method provided in this application embodiment is malfunctioning, a process alarm or system alarm can be triggered. This alarm can be pushed to relevant responsible persons, such as field engineers, production supervisors, and technical directors, through various channels such as instant messaging applications, for alarm processing. This allows for timely optimization and adjustment of the battery electrode coating process, and the alarm status can be updated based on the feedback processing results.

[0071] In one embodiment, the model stability index corresponding to the target prediction model can be determined; if the model stability index meets the preset stability conditions, the detection frequency of the first coating weight loss rate is reduced; if the model stability index does not meet the preset stability conditions, the model prediction accuracy of the target prediction model is determined; if the model prediction accuracy of the target prediction model decreases, the detection frequency of the first coating weight loss rate is increased.

[0072] The model stability index measures the stability of the target prediction model. The preset stability condition sets predefined criteria for judging the stability of the target prediction model. For example, a smaller model stability index indicates higher stability, so the preset stability condition could be an index below a preset threshold. Conversely, a larger model stability index indicates higher stability, so the preset stability condition could be an index above a preset threshold. Specific conditions can be set according to actual conditions. The preset index threshold is a pre-defined critical value for the model stability index, used to determine if the stability of the target prediction model meets requirements. The detection frequency measures the number of times the first coating weight loss rate is measured. For example, it can be the frequency at which the first coating weight loss rate is measured manually or using quality control equipment during the coating process. Higher frequencies result in higher resource and time costs. The model prediction accuracy refers to the accuracy with which the target prediction model predicts the second coating weight loss rate.

[0073] While the first coating weight loss rate obtained through manual inspection or quality control equipment is often quite accurate, relying solely on this rate to determine the coating weight loss rate of the battery electrode would consume significant resources, time, and manpower, resulting in low efficiency. Therefore, this embodiment combines the first coating weight loss rate obtained through manual inspection with a target prediction model to accurately predict the coating weight loss rate of the battery electrode. Furthermore, this embodiment dynamically adjusts the detection frequency of the first coating weight loss rate based on the performance and prediction accuracy of the target prediction model, thereby reducing the detection cost while maintaining the prediction accuracy. Additionally, this embodiment can use the detected first coating weight loss rate to retrain the target prediction model, thereby improving the accuracy of the target prediction model in predicting the coating weight loss rate. Therefore, the embodiments of this application can achieve accurate alignment of quality inspection data and production control data in the absence of barcode association or small data samples, and can train a target prediction model with high accuracy, thereby further improving the prediction efficiency of coating weight loss rate of battery electrodes.

[0074] There are several ways to determine the model stability index corresponding to the target prediction model. For example, the confidence interval of the predicted values ​​of the second coating weight loss rate continuously output by the target prediction model can be calculated as the model stability index corresponding to the target prediction model.

[0075] A narrower confidence interval indicates that the statistical estimate of the predicted values ​​by the target prediction model is more concentrated on the overall parameter, thus indicating higher accuracy. In other words, a smaller model stability index represents higher stability of the target prediction model. Conversely, a wider confidence interval indicates that the statistical estimate of the predicted values ​​by the target prediction model is more dispersed on the overall parameter, thus indicating lower accuracy. In other words, a larger model stability index represents lower stability of the target prediction model.

[0076] In one embodiment, a bootstrap algorithm can be used to calculate the confidence interval of the predicted value to quantify the uncertainty and stability of the target prediction model. For example, based on a trained target prediction model and an original training dataset, n (e.g., 100) bootstrap iterations can be performed. The original training dataset may include the detected first coating weight loss rate and the corresponding aligned coating data samples. In each bootstrap iteration, a new dataset can be generated by random sampling with replacement, and a base learner can be trained. This base learner is used to predict the new input coating data to obtain a new predicted value. The 100 predicted values ​​obtained from all 100 iterations are counted and sorted from largest to smallest. The 2.5th and 97.5th percentiles of the sorted sequence are taken as the lower bound (L) and upper bound (U) of the 95% confidence interval, respectively, thus obtaining the confidence interval Width=UL.

[0077] Therefore, the model stability index determined based on the confidence interval can describe the instability of model prediction caused by fluctuations in equipment operating conditions. Thus, the resource scheduling strategy for the detection frequency of coating weight loss rate can be dynamically adjusted based on the model stability index to ensure the accuracy of coating weight loss rate prediction.

[0078] Optionally, there are several other ways to determine the model stability index corresponding to the target prediction model. For example, the prediction result of the second coating weight loss rate output by the target prediction model can be input into a pre-trained stability prediction model, thereby predicting the model stability index corresponding to the target prediction model through the stability prediction model. Here, the stability prediction model can be a trained deep learning model used to predict the model stability index of the target prediction model.

[0079] Optionally, there are several other ways to determine the model stability index corresponding to the target prediction model. For example, the model stability index corresponding to the target prediction model can be determined based on the first coating weight loss rate. For example, the difference between the second coating weight loss rate predicted by the target prediction model based on the aligned coating data and the first coating weight loss rate corresponding to the aligned coating data can be calculated. If the weight loss rate difference is greater than a preset difference, the model stability index can be considered not to meet the preset stability condition. Alternatively, if a preset number of consecutive weight loss rate differences are all greater than the preset difference, the model stability index can be considered not to meet the preset stability condition. Otherwise, the model stability index can be considered to meet the preset stability condition.

[0080] In one embodiment, when the model stability index of the target prediction model does not meet the preset stability condition and / or the model prediction accuracy is poor, the target prediction model can be retrained using data samples composed of the first coating weight loss rate, thereby obtaining a target prediction model with higher prediction accuracy.

[0081] For example, please refer to Figure 3d , Figure 3d This is another specific flowchart illustrating a coating weight loss prediction method provided in this application embodiment. When predicting the second coating weight loss of the battery electrode using a target prediction model, the stability of the target prediction model can be evaluated. Based on the model stability index of the target prediction model, the manual inspection plan for the first coating weight loss can be dynamically adjusted. When the model stability index is lower than a specified threshold, for example, if the confidence interval corresponding to the predicted value of the second coating weight loss of the target prediction model is less than or equal to 500 ppm for a continuous month, the measurement frequency can be reduced, that is, the detection frequency of the first coating weight loss can be reduced. For example, it can be set to once per shift, or the detection frequency of the first coating weight loss can be reduced from 12 times / day to 2 times / day to reduce labor costs, thereby improving the prediction efficiency of coating weight loss. If the confidence interval corresponding to the predicted value of the second coating weight loss rate by the target prediction model is not less than or equal to 500 ppm for a continuous month, the prediction accuracy of the target prediction model can be determined. When the model accuracy decreases, the measurement frequency can be increased, i.e., the detection frequency of the first coating weight loss rate can be increased. For example, the detection frequency of the first coating weight loss rate can be set to once every two hours, i.e., once every 2 hours, to improve the accuracy of the coating weight loss rate determined for the battery electrode. When the model accuracy does not decrease, the current detection frequency can be maintained. For example, the first coating weight loss rate can be detected once every 2 hours. Then, the instruction to adjust the detection frequency can be issued to the production execution system to perform manual measurement of the first coating weight loss rate based on the adjusted detection frequency, and the target prediction model can be adjusted according to the model accuracy of the target prediction model.

[0082] In one embodiment, the quality control of the lithium-ion battery electrode coating process directly affects the consistency and safety of the finished battery. Existing production lines commonly suffer from problems such as inaccurate alignment between MES data and IoT data, insufficient effective sample size, and high frequency of manual inspections, leading to insufficient accuracy in the prediction model and the inability to monitor in real time. To address this, this application provides a coating weight loss rate prediction method. Through feature aggregation, dynamic time window alignment, multi-model weighted selection, and dual-mode alarms, it achieves real-time prediction and closed-loop control of the coating process quality, while simultaneously reducing the frequency of manual inspections, improving prediction accuracy, and shortening feedback latency. Specifically, the dynamic time window alignment mechanism provided in this application ensures that IoT data accurately covers the electrode rolls recorded by the MES even without barcode association, achieving accurate alignment between MES data and IoT data. It also enables high-precision modeling of the prediction model under small sample conditions, with a prediction error of less than ±500 ppm. Furthermore, adjusting the frequency of manual inspections based on the model prediction results can significantly reduce labor costs. In addition, the model is automatically retrained and the version is rolled back using the continuous daily error threshold as the trigger condition, which drives process adjustment and quality feedback in real time, further improving the prediction accuracy of coating weight loss rate.

[0083] In one specific embodiment, please refer to Figure 3e , Figure 3eThis is a schematic diagram of the system architecture of a coating weight loss rate prediction method provided in the embodiments of this application. The system may include an IoT data acquisition module, a feature aggregation module, a data interface module, a data calling module, a dynamic time window alignment module, a multi-model weighted selection module, a prediction execution module, a resource configuration module, and a prediction alarm module. Production control data is collected through the IoT data acquisition module and stored in a time-series database. In the time-series database layer, six major statistical features—maximum, minimum, variance, average, 25th percentile, and 75th percentile—are calculated in real time. This database aggregation reduces bandwidth and external computational overhead. Then, the data is transmitted to the prediction engine every 15 minutes via the API (Application Programming Interface) gateway of the data interface module, and quality inspection data is obtained through the data call module. A dynamic time window alignment module dynamically determines the target time window by combining inspection time, fixed delay, and production duration, achieving precise alignment between MES data and IoT data. Then, through the model self-consistent engine provided in this embodiment, a multi-model weighted selection module can be used to select the best model based on gradient boosting regression, random forest, XGBoost, LightGBM, and other models with weighted scoring. Retraining is automatically triggered if predictions exceed the target for five consecutive days. Finally, the prediction execution module uses the selected target prediction model to predict the coating weight loss rate of the battery electrode sheets. Furthermore, the system can run predictions every 2 hours and execute dual-mode alarms based on the prediction results through the prediction alarm module. For example, alarms can be issued through instant messaging applications such as WeChat for Enterprise, and the alarm events can be fed back to the resource configuration module. The resource configuration module determines the adjusted detection frequency and feeds it back to the production execution system for execution. For example, the frequency of manual inspection can be reduced from 12 times / day to 2 times / day. It can also feed back to the model self-consistent engine to optimize and adjust the prediction model so that the absolute error of prediction is ≤500ppm and the monthly pass rate reaches 96%. This can significantly improve production efficiency and quality control level, and further improve the prediction efficiency of coating weight loss rate of battery electrodes.

[0084] As described above, this embodiment of the application acquires production control data collected during the coating process of the battery electrode, and quality inspection data generated by the manufacturing execution system corresponding to the battery electrode. The quality inspection data includes a first coating weight loss rate obtained through pre-detection; determining the detection time corresponding to the first coating weight loss rate, the delay between the detection time and the production time of the battery electrode, and the production time of the battery electrode; determining a target time window based on the detection time, delay, and production time; aligning the production control data and quality inspection data based on the target time window to obtain aligned coating data; and predicting a second coating weight loss rate of the battery electrode based on the aligned coating data. Thus, by determining the target time window based on the detection time, delay, and production time of the battery electrode obtained through pre-detection of the first coating weight loss rate, the quality inspection data and production control data can be accurately aligned based on the dynamic target time window. Furthermore, based on the aligned quality inspection data and production control data, the coating weight loss rate of the battery electrode can be accurately and efficiently predicted, further improving the prediction efficiency of the coating weight loss rate of the battery electrode.

[0085] To better implement the above methods, embodiments of the present invention also provide a coating weight loss prediction device, which can be integrated into an electronic device, such as a terminal or a server.

[0086] For example, such as Figure 4 The diagram shown is a schematic representation of the coating weight loss prediction device provided in this application embodiment. The coating weight loss prediction device may include an acquisition unit 201, a first determination unit 202, a second determination unit 203, an alignment unit 204, and a prediction unit 205, as follows: The acquisition unit 201 is used to acquire production control data collected in the coating process of the battery electrode, and quality inspection data generated by the manufacturing execution system corresponding to the battery electrode. The quality inspection data includes the first coating weight loss rate obtained in advance. The first determining unit 202 is used to determine the detection time corresponding to the first coating weight loss rate, the delay time between the detection time and the production time of the battery electrode, and the production time of the battery electrode. The second determining unit 203 is used to determine a target time window based on the detection time, the delay duration, and the production duration; Alignment unit 204 is used to align the production control data and the quality inspection data based on the target time window to obtain aligned coating data; The prediction unit 205 is used to predict the second coating weight loss rate of the battery electrode based on the aligned coating data.

[0087] In one embodiment, the second determining unit 203 is configured to: The starting point of the window is determined based on the detection time, the delay duration, and the production duration; Based on the detection time, determine the end point of the window; The target time window is determined based on the window start point and the window end point.

[0088] In one embodiment, the alignment unit 204 is used for: Based on the target time window, target production control data that matches the quality inspection data is found in the production control data to obtain aligned coating data.

[0089] In one embodiment, the above-mentioned method of searching for target production control data that matches the quality inspection data in the production control data based on the target time window to obtain aligned coating data is specifically used for: Calculate multiple statistical indicators corresponding to the production control data to obtain the statistical characteristics of the production control data; Based on the target time window and the time information corresponding to the production control data, a target data statistical feature that matches the quality inspection data is found in the data statistical features; Based on the quality inspection data and the statistical characteristics of the target data, the aligned coating data is obtained.

[0090] In one embodiment, the prediction unit 205 is configured to: Based on the aligned coating data, the second coating weight loss rate of the battery electrode is predicted using a target prediction model.

[0091] In one embodiment, the coating weight loss prediction device is further used for: At least one evaluation index is calculated using multiple candidate prediction models to obtain the index calculation results corresponding to the evaluation index. Based on the calculation results of the aforementioned indicators, the target prediction model is selected from the prediction models.

[0092] In one embodiment, the above-mentioned selection of a target prediction model from the prediction model based on the index calculation results is specifically used for: The calculation results of the aforementioned indicators are standardized to obtain an initial evaluation score; The initial evaluation score is fused based on the preset weights corresponding to the evaluation indicators to obtain the target evaluation score corresponding to the prediction model. Based on the target evaluation score, a target prediction model is selected from the prediction models.

[0093] In one embodiment, the coating weight loss prediction device is further used for: Determine the model stability index corresponding to the target prediction model; If the model stability index meets the preset stability conditions, the detection frequency of the first coating weight loss rate is reduced. If the model stability index does not meet the preset stability condition, determine the model prediction accuracy of the target prediction model; If the prediction accuracy of the target prediction model decreases, the detection frequency of the first coating weight loss rate will be increased.

[0094] In one embodiment, the coating weight loss prediction device is further used for: If the second coating weight loss rate of the battery electrode is greater than the preset weight loss rate threshold, an alarm operation is executed.

[0095] As can be seen from the above, in this embodiment of the application, the acquisition unit 201 acquires production control data collected in the coating process of the battery electrode, and quality inspection data generated by the manufacturing execution system corresponding to the battery electrode. The quality inspection data includes the first coating weight loss rate obtained in advance. The first determination unit 202 determines the detection time corresponding to the first coating weight loss rate, the delay time between the detection time and the production time of the battery electrode, and the production time of the battery electrode. The second determination unit 203 determines the target time window based on the detection time, the delay time, and the production time. The alignment unit 204 aligns the production control data and the quality inspection data based on the target time window to obtain aligned coating data. The prediction unit 205 predicts the second coating weight loss rate of the battery electrode based on the aligned coating data. Therefore, by determining the target time window based on the detection time, delay time, and production time of the battery electrode corresponding to the first coating weight loss rate obtained in advance, the quality inspection data and production control data can be accurately aligned based on the dynamic target time window. Furthermore, based on the aligned quality inspection data and production control data, the coating weight loss rate of the battery electrode can be accurately and efficiently predicted, thereby further improving the prediction efficiency of the coating weight loss rate of the battery electrode.

[0096] Accordingly, this application also provides an electronic device, which can be a terminal.

[0097] like Figure 5 As shown, Figure 5This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device 300 includes a processor 301 with one or more processing cores, a memory 302 with one or more computer-readable storage media, and a computer program stored in the memory 302 and executable on the processor. The processor 301 and the memory 302 are electrically connected. Those skilled in the art will understand that the electronic device structure shown in the figure does not constitute a limitation on the electronic device, and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0098] The processor 301 is the control center of the electronic device 300. It connects various parts of the electronic device 300 through various interfaces and lines. By running or loading software programs and / or units stored in the memory 302, and calling data stored in the memory 302, it executes various functions of the electronic device 300 and processes data. The processor 301 may be a CPU, GPU, network processor (NP), etc., and can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application.

[0099] In this embodiment, the processor 301 in the electronic device 300 loads the instructions corresponding to the processes of one or more applications into the memory 302 according to the following steps, and the processor 301 runs the applications stored in the memory 302 to realize various functions, such as: Acquire production control data collected during the coating process of the battery electrode, as well as quality inspection data generated by the manufacturing execution system corresponding to the battery electrode. The quality inspection data includes the first coating weight loss rate obtained in advance. Determine the detection time corresponding to the first coating weight loss rate, the delay between the detection time and the production time of the battery electrode, and the production time of the battery electrode. The target time window is determined based on the detection time, delay duration, and production duration; Based on the target time window, production control data and quality inspection data are aligned to obtain aligned coating data. Predict the second coating weight loss rate of the battery electrode based on the aligned coating data.

[0100] This solution acquires production control data gathered during the coating process of battery electrodes, as well as quality inspection data generated by the corresponding manufacturing execution system (MES) for the battery electrodes. The quality inspection data includes a pre-detected first coating weight loss rate; it determines the detection time corresponding to the first coating weight loss rate, the delay between the detection time and the battery electrode's production time, and the battery electrode's production time; based on the detection time, delay, and production time, it determines a target time window; based on the target time window, it aligns the production control data and quality inspection data to obtain aligned coating data; and based on the aligned coating data, it predicts a second coating weight loss rate for the battery electrodes. Thus, by determining the target time window based on the pre-detected first coating weight loss rate, the detection time, delay, and the battery electrode's production time, a dynamic target time window can accurately align the quality inspection data and production control data. This, in turn, allows for accurate and efficient prediction of the battery electrode's coating weight loss rate, further improving the prediction efficiency.

[0101] Furthermore, the various functions implemented by running the application stored in memory 302 can also be found in the description of the foregoing embodiments, and will not be repeated here.

[0102] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0103] Optional, such as Figure 5 As shown, the electronic device 300 also includes: a touch display screen 303, a radio frequency circuit 304, an audio circuit 305, an input unit 306, and a power supply 307. The processor 301 is electrically connected to the touch display screen 303, the radio frequency circuit 304, the audio circuit 305, the input unit 306, and the power supply 307. Those skilled in the art will understand that... Figure 5 The electronic device structure shown does not constitute a limitation on the electronic device and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0104] The touch display screen 303 can be used to display a graphical user interface (GUI) and receive operation commands generated by the user interacting with the GUI. The touch display screen 303 may include a display panel and a touch panel. The display panel can be used to display information input by the user or information provided to the user, as well as various graphical user interfaces of the electronic device. These graphical user interfaces can be composed of graphics, text, icons, video, and any combination thereof. Optionally, the display panel can be configured using a liquid crystal display (LCD), organic light-emitting diode (OLED), or other similar technologies. The touch panel can be used to collect touch operations performed by the user on or near it (such as operations performed by the user using a finger, stylus, or any suitable object or accessory on or near the touch panel), generate corresponding operation commands, and execute the corresponding program according to the operation commands. Optionally, the touch panel may include two parts: a touch detection device and a touch controller. The touch detection device detects the user's touch location and the signal generated by the touch operation, transmitting the signal to the touch controller. The touch controller receives touch information from the touch detection device, converts it into touch point coordinates, and sends it to the processor 301. It can also receive and execute commands from the processor 301. The touch panel can cover the display panel. When the touch panel detects a touch operation on or near it, it transmits the information to the processor 301 to determine the type of touch event. Subsequently, the processor 301 provides corresponding visual output on the display panel based on the type of touch event. In this embodiment, the touch panel and the display panel can be integrated into the touch display screen 303 to achieve input and output functions. However, in some embodiments, the touch panel and the touch display screen 303 can be implemented as two independent components to achieve input and output functions. That is, the touch display screen 303 can also be used as part of the input unit 306 to achieve input functions.

[0105] The radio frequency circuit 304 can be used to transmit and receive radio frequency signals to establish wireless communication with network devices or other electronic devices, and to transmit and receive signals with network devices or other electronic devices.

[0106] Audio circuitry 305 can be used to provide an audio interface between a user and an electronic device via a speaker and a microphone. Audio circuitry 305 converts received audio data into electrical signals, transmits them to the speaker, and the speaker converts them into sound signals for output. Conversely, the microphone converts collected sound signals into electrical signals, which are then received by audio circuitry 305, converted back into audio data, and then processed by processor 301 before being transmitted via radio frequency circuitry 304 to, for example, another electronic device, or output to memory 302 for further processing. Audio circuitry 305 may also include an earphone jack to facilitate communication between peripheral headphones and electronic devices.

[0107] The input unit 306 can be used to receive input target video and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

[0108] Power supply 307 is used to supply power to various components of electronic device 300. Optionally, power supply 307 can be logically connected to processor 301 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. Power supply 307 may also include one or more DC or AC power supplies, recharging systems, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0109] although Figure 5 As not shown in the diagram, the electronic device 300 may also include a camera, sensor, wireless fidelity module, Bluetooth module, etc., which will not be described in detail here.

[0110] In the above embodiments, the descriptions of each embodiment have their own emphasis. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments. It should be noted that the electronic device provided in this application embodiment and the coating weight loss prediction method in the above embodiments belong to the same concept. The specific implementation process is detailed in the above method embodiments and will not be repeated here.

[0111] As can be seen from the above, the electronic device provided in this application embodiment can acquire production control data collected during the coating process of the battery electrode, and quality inspection data generated by the manufacturing execution system corresponding to the battery electrode. The quality inspection data includes a first coating weight loss rate obtained through pre-detection; determining the detection time corresponding to the first coating weight loss rate, the delay time between the detection time and the production time of the battery electrode, and the production time of the battery electrode; determining a target time window based on the detection time, delay time, and production time; aligning the production control data and quality inspection data based on the target time window to obtain aligned coating data; and predicting a second coating weight loss rate of the battery electrode based on the aligned coating data. Thus, by determining the target time window based on the detection time, delay time, and production time of the battery electrode obtained through pre-detection of the first coating weight loss rate, the quality inspection data and production control data can be accurately aligned based on the dynamic target time window. Furthermore, based on the aligned quality inspection data and production control data, the coating weight loss rate of the battery electrode can be accurately and efficiently predicted, further improving the prediction efficiency of the coating weight loss rate of the battery electrode.

[0112] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be performed by instructions, or by instructions controlling related hardware. These instructions can be stored in a computer-readable storage medium and loaded and executed by a processor.

[0113] Therefore, embodiments of this application provide a computer-readable storage medium, including a computer program, which, when run on an electronic device, causes the electronic device to perform any of the coating weight loss prediction methods provided in embodiments of this application. For example, the computer program can perform the steps of the following coating weight loss prediction method: Acquire production control data collected during the coating process of the battery electrode, as well as quality inspection data generated by the manufacturing execution system corresponding to the battery electrode. The quality inspection data includes the first coating weight loss rate obtained in advance. Determine the detection time corresponding to the first coating weight loss rate, the delay between the detection time and the production time of the battery electrode, and the production time of the battery electrode. The target time window is determined based on the detection time, delay duration, and production duration; Based on the target time window, production control data and quality inspection data are aligned to obtain aligned coating data. Predict the second coating weight loss rate of the battery electrode based on the aligned coating data.

[0114] This solution acquires production control data gathered during the coating process of battery electrodes, as well as quality inspection data generated by the corresponding manufacturing execution system (MES) for the battery electrodes. The quality inspection data includes a pre-detected first coating weight loss rate; it determines the detection time corresponding to the first coating weight loss rate, the delay between the detection time and the battery electrode's production time, and the battery electrode's production time; based on the detection time, delay, and production time, it determines a target time window; based on the target time window, it aligns the production control data and quality inspection data to obtain aligned coating data; and based on the aligned coating data, it predicts a second coating weight loss rate for the battery electrodes. Thus, by determining the target time window based on the pre-detected first coating weight loss rate, the detection time, delay, and the battery electrode's production time, a dynamic target time window can accurately align the quality inspection data and production control data. This, in turn, allows for accurate and efficient prediction of the battery electrode's coating weight loss rate, further improving the prediction efficiency.

[0115] Furthermore, the detailed steps of the above method can be found in the description of the foregoing embodiments, and will not be repeated here.

[0116] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0117] The computer-readable storage medium may include: read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0118] Since the computer program stored in the computer-readable storage medium can execute any of the coating weight loss prediction methods provided in the embodiments of this application, the beneficial effects that any of the coating weight loss prediction methods provided in the embodiments of this application can achieve can be realized, as detailed in the preceding embodiments, and will not be repeated here.

[0119] According to one aspect of this application, a computer program product is also provided, comprising a computer program stored in a computer-readable storage medium; when a processor of an electronic device reads the computer program from the computer-readable storage medium, the processor executes the computer program, causing the electronic device to perform the methods provided in various optional implementations of the above embodiments.

[0120] In the above embodiments of the coating weight loss prediction device, computer-readable storage medium, electronic device, and computer program product, the descriptions of each embodiment have different focuses. Parts not described in detail in a particular embodiment can be referred to in the relevant descriptions of other embodiments. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process and beneficial effects of the coating weight loss prediction device, computer-readable storage medium, computer program product, electronic device, and their corresponding units described above can be referred to the description of the coating weight loss prediction method in the above embodiments, and will not be repeated here.

[0121] The foregoing has provided a detailed description of a coating weight loss prediction method, apparatus, electronic device, computer-readable storage medium, and computer program product provided in the embodiments of this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for predicting coating weight loss rate, characterized in that, include: Acquire production control data collected during the coating process of the battery electrode, and quality inspection data generated by the manufacturing execution system corresponding to the battery electrode, wherein the quality inspection data includes the first coating weight loss rate obtained in advance; Determine the detection time corresponding to the first coating weight loss rate, the delay between the detection time and the production time of the battery electrode, and the production time of the battery electrode; The target time window is determined based on the detection time, the delay duration, and the production duration; Based on the target time window, the production control data and the quality inspection data are aligned to obtain aligned coating data; The second coating weight loss rate of the battery electrode is predicted based on the aligned coating data.

2. The coating weight loss prediction method as described in claim 1, characterized in that, The step of determining the target time window based on the detection time, the delay duration, and the production duration includes: The starting point of the window is determined based on the detection time, the delay duration, and the production duration; Based on the detection time, determine the end point of the window; The target time window is determined based on the window start point and the window end point.

3. The coating weight loss prediction method as described in claim 1, characterized in that, The step of aligning the production control data and the quality inspection data based on the target time window to obtain aligned coating data includes: Based on the target time window, target production control data that matches the quality inspection data is found in the production control data to obtain aligned coating data.

4. The coating weight loss prediction method as described in claim 3, characterized in that, The step of finding target production control data that matches the quality inspection data in the production control data based on the target time window to obtain aligned coating data includes: Calculate multiple statistical indicators corresponding to the production control data to obtain the statistical characteristics of the production control data; Based on the target time window and the time information corresponding to the production control data, a target data statistical feature that matches the quality inspection data is found in the data statistical features; Based on the quality inspection data and the statistical characteristics of the target data, the aligned coating data is obtained.

5. The coating weight loss prediction method according to any one of claims 1 to 4, characterized in that, The prediction of the second coating weight loss rate of the battery electrode based on the aligned coating data includes: Based on the aligned coating data, the second coating weight loss rate of the battery electrode is predicted using a target prediction model.

6. The coating weight loss prediction method as described in claim 5, characterized in that, Before predicting the second coating weight loss rate of the battery electrode using a target prediction model based on the aligned coating data, the method further includes: At least one evaluation index is calculated using multiple candidate prediction models to obtain the index calculation results corresponding to the evaluation index. Based on the calculation results of the aforementioned indicators, the target prediction model is selected from the prediction models.

7. The coating weight loss prediction method as described in claim 6, characterized in that, The step of selecting the target prediction model from the prediction models based on the calculation results of the indicators includes: The calculation results of the aforementioned indicators are standardized to obtain an initial evaluation score; The initial evaluation score is fused based on the preset weights corresponding to the evaluation indicators to obtain the target evaluation score corresponding to the prediction model. Based on the target evaluation score, a target prediction model is selected from the prediction models.

8. The coating weight loss prediction method as described in claim 5, characterized in that, After predicting the second coating weight loss rate of the battery electrode using a target prediction model based on the aligned coating data, the method further includes: Determine the model stability index corresponding to the target prediction model; If the model stability index meets the preset stability conditions, the detection frequency of the first coating weight loss rate is reduced. If the model stability index does not meet the preset stability condition, determine the model prediction accuracy of the target prediction model; If the prediction accuracy of the target prediction model decreases, the detection frequency of the first coating weight loss rate will be increased.

9. The coating weight loss prediction method according to any one of claims 1 to 8, characterized in that, The method further includes: If the second coating weight loss rate of the battery electrode is greater than the preset weight loss rate threshold, an alarm operation is executed.

10. An electronic device, characterized in that, It includes a processor and a memory, wherein the memory stores a computer program that, when executed by the processor, causes the processor to perform the steps of the coating weight loss prediction method according to any one of claims 1-9.

11. A computer-readable storage medium, characterized in that, Includes a computer program, which, when run on an electronic device, causes the electronic device to perform the steps of the coating weight loss prediction method according to any one of claims 1-9.

Images