Sodium-ion battery positive electrode material preparation monitoring method based on a digital twin system of sodium-ion battery positive electrode material preparation

Abstract

The present disclosure provides a kind of based on sodium ion battery positive material preparation monitoring method of digital twin system of sodium ion battery positive material preparation.The method includes obtaining the key process node parameter of sodium ion battery positive line;The key process node parameter of production line is weighted and fused to obtain the vacancy rate of sodium battery positive electrode preparation;The vacancy rate of sodium battery positive electrode preparation is compared with the preset vacancy rate to carry out the rate adjustment processing, to obtain the vacancy adjustment amount;According to the vacancy adjustment amount, hierarchical linkage adjustment signal is sent to the positive electrode preparation digital twin control module, to adjust the process node preparation mode of corresponding process stage.According to the degree of vacancy difference, the preparation mode of each key process stage of sodium ion battery positive line is adjusted, to carry out feedback regulation to the preparation mode of each key process stage of sodium ion battery positive line, to improve the vacancy condition on sodium ion battery positive electrode in time, effectively reduce the vacancy rate of sodium ion battery positive electrode.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of sodium-ion batteries, in particular to a sodium-ion battery positive electrode material preparation monitoring method based on a digital twin system for sodium-ion battery positive electrode material preparation. BACKGROUND

[0002] With the rapid development of new energy storage technology, sodium-ion batteries have become an important research and industrial direction after lithium-ion batteries due to their advantages of abundant resources, low cost, excellent low-temperature performance, etc. Among them, the structural stability and preparation consistency of the positive electrode material are one of the key factors affecting the performance of sodium-ion batteries.

[0003] At present, Prussian blue (PBA) materials are one of the most promising sodium-ion battery positive electrode materials, with high specific capacity and open framework structure. However, in the actual preparation process, this type of material often has the problems of high vacancy rate and difficulty in precise control, which seriously affects its electrochemical stability, resulting in phenomena such as decreased cycle life and accelerated capacity decay. The existing preparation process relies on experience to set parameters, lacks systematic modeling and quantitative analysis capabilities between key reaction conditions and material structure performance, resulting in large fluctuations between product batches, poor consistency, and low yield. These problems have become a key bottleneck restricting the large-scale and high-quality development of sodium-ion batteries. SUMMARY

[0004] The purpose of the present disclosure is to overcome the deficiencies in the prior art and provide a sodium-ion battery positive electrode material preparation monitoring method based on a digital twin system for sodium-ion battery positive electrode material preparation, which effectively reduces the vacancy rate.

[0005] The purpose of the present disclosure is achieved by the following technical solutions:

[0006] A method for monitoring the preparation of sodium-ion battery cathode materials based on a digital twin system for preparing sodium-ion battery cathode materials includes: simulating the production of sodium-ion battery cathode materials using the digital twin system, wherein the digital twin system comprises: a reactor digital module, a filter digital module, a drying oven digital module, a calcining furnace digital module, and a mixer digital module; the reactor digital module uses a nucleation-crystal growth model and CFD fluid simulation to simulate the co-precipitation stage of sodium-ion battery cathode material preparation; the filter digital module uses a porous media and pressure difference model to simulate the filtration stage of sodium-ion battery cathode material preparation; the drying oven digital module uses a heat transfer-mass transfer model to simulate the drying stage of sodium-ion battery cathode material preparation; the calcining furnace digital module uses a lattice rearrangement and densification model to simulate the calcination stage of sodium-ion battery cathode material preparation; and the mixer digital module uses a DEM particle kinetics model to simulate the mixing stage of sodium-ion battery cathode material preparation.

[0007] The method for monitoring the preparation of sodium-ion battery cathode materials includes:

[0008] Obtain key process node parameters for the production line of sodium-ion battery cathode;

[0009] The key process node parameters of the production line are weighted and fused to obtain the vacancy rate for sodium electrode preparation;

[0010] The vacancy rate of the sodium-ion cathode is adjusted by comparing it with the preset vacancy rate to obtain the vacancy adjustment amount.

[0011] Based on the vacancy adjustment, a graded linkage adjustment signal is sent to the positive electrode preparation digital twin control module to adjust the preparation mode of the corresponding process node.

[0012] In one embodiment, key process node parameters for the production line of sodium-ion battery cathode are obtained, including: obtaining the raw material flow rate of sodium-ion battery cathode; and / or, coprecipitation temperature, coprecipitation pH value, and coprecipitation stirring speed; and / or, filtration vacuum pressure; and / or, drying temperature; and / or, calcination inlet temperature, calcination mid-section temperature, and calcination outlet temperature; and / or, mixing temperature and mixing humidity.

[0013] In one embodiment, the key process node parameters of the production line are weighted and fused to obtain the vacancy rate for sodium electrode preparation, including: outlier detection of the key process node parameters of the production line to clean up outliers and missing values ​​in the key process node parameters of the production line.

[0014] In one embodiment, the key process node parameters of the production line are weighted and fused to obtain the vacancy rate for sodium electrode preparation. The method also includes: performing interpolation and normalization operations on the key process node parameters of the production line to update outliers and missing values ​​in the key process node parameters of the production line.

[0015] In one embodiment, the key process node parameters of the production line are subjected to weighted fusion processing, including: extracting spatial features from the key process node parameters of the production line to obtain process spatial features.

[0016] In one embodiment, the weighted fusion processing of the key process node parameters of the production line further includes: extracting time series features from the key process node parameters of the production line to obtain process time series features.

[0017] In one embodiment, the weighted fusion processing of the key process node parameters of the production line further includes: assigning weights and weighting the process spatial features and the process time series features to obtain a process fusion feature vector.

[0018] In one embodiment, the weighted fusion processing of the key process node parameters of the production line further includes: performing a regression operation on the process fusion feature vector to obtain the vacancy rate of sodium electrode preparation.

[0019] In one embodiment, the vacancy rate of the sodium electrode preparation is adjusted by comparing it with a preset vacancy rate to obtain a vacancy adjustment amount. This includes: calculating the adjustment between the vacancy rate of the sodium electrode preparation and the preset vacancy rate; sending a graded linkage adjustment signal to the cathode preparation digital twin control module based on the vacancy adjustment amount to adjust the preparation mode of the corresponding process node, including: detecting whether the vacancy adjustment amount is less than or equal to a first preset adjustment amount; when the vacancy adjustment amount is less than or equal to the first preset adjustment amount, sending a single-stage down-adjustment signal to the cathode preparation digital twin control module to down-adjust the reaction pH value, wherein the pH value down-adjustment ratio is 4% to 7%.

[0020] In one embodiment, after detecting whether the vacancy adjustment amount is less than or equal to a first preset adjustment amount, the method further includes: when the vacancy adjustment amount is greater than the first preset adjustment amount, detecting whether the vacancy adjustment amount is less than or equal to a second preset adjustment amount; when the vacancy adjustment amount is less than or equal to the second preset adjustment amount, sending a two-stage down-adjustment signal to the positive electrode preparation digital twin control module to down-adjust the reaction pH value and the raw material feeding rate, wherein the pH value is down-adjusted by 7% and the raw material feeding rate is down-adjusted by 20%.

[0021] Compared with the prior art, this disclosure has at least the following advantages:

[0022] After collecting parameters of key process nodes in the production line, it is easy to determine the production status of each key process stage of the sodium-ion battery cathode production line. Then, by weighted fusion processing of the parameters of key process nodes in the production line, the vacancy rate of sodium-ion battery cathode material during the preparation process is predicted. Then, the vacancy rate of the prepared sodium-ion battery cathode is compared with the standard vacancy rate to determine the degree of difference in vacancy rate on the sodium-ion battery cathode. Finally, based on the degree of vacancy difference, the preparation mode of each key process stage of the sodium-ion battery cathode production line is adjusted to provide feedback adjustment for the preparation method of each key process stage of the sodium-ion battery cathode production line, so as to improve the vacancy situation on the sodium-ion battery cathode in a timely manner and effectively reduce the vacancy rate of the sodium-ion battery cathode. Attached Figure Description

[0023] To more clearly illustrate the technical solutions of the embodiments of this disclosure, the accompanying drawings used in the embodiments will be briefly described below. It should be understood that the following drawings only show some embodiments of this disclosure and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a flowchart of a method for monitoring the preparation of sodium-ion battery cathode materials based on a digital twin system for preparing sodium-ion battery cathode materials, as described in one embodiment.

[0025] Figure 2 This is a schematic diagram of a CNN-LSTM model based on dynamic weighted fusion. Detailed Implementation

[0026] To facilitate understanding of this disclosure, a more complete description will be given below with reference to the accompanying drawings, which illustrate preferred embodiments of the present disclosure. However, this disclosure can be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the disclosure.

[0027] It should be noted that when an element is referred to as being "fixed to" another element, it can be directly attached to the other element or there may be an intervening element. When an element is referred to as being "connected to" another element, it can be directly connected to the other element or there may be an intervening element. The terms "vertical," "horizontal," "left," "right," and similar expressions used herein are for illustrative purposes only and do not represent the only possible implementation.

[0028] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of this disclosure. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0029] This disclosure relates to a method for monitoring the preparation of sodium-ion battery cathode materials based on a digital twin system for preparing sodium-ion battery cathode materials. In one embodiment, the method includes acquiring key process node parameters of the sodium-ion battery cathode production line; performing weighted fusion processing on the key process node parameters to obtain the vacancy rate of the sodium-ion battery cathode preparation; performing vacancy rate adjustment processing on the vacancy rate of the sodium-ion battery cathode preparation and a preset vacancy rate to obtain a vacancy adjustment amount; and sending a graded linkage adjustment signal to the cathode preparation digital twin control module according to the vacancy adjustment amount to adjust the preparation mode of the process node at the corresponding process stage. After collecting parameters of key process nodes in the production line, it is easy to determine the production status of each key process stage of the sodium-ion battery cathode production line. Then, by weighted fusion processing of the parameters of key process nodes in the production line, the vacancy rate of sodium-ion battery cathode material during the preparation process is predicted. Then, the vacancy rate of the prepared sodium-ion battery cathode is compared with the standard vacancy rate to determine the degree of difference in vacancy rate on the sodium-ion battery cathode. Finally, based on the degree of vacancy difference, the preparation mode of each key process stage of the sodium-ion battery cathode production line is adjusted to provide feedback adjustment for the preparation method of each key process stage of the sodium-ion battery cathode production line, so as to improve the vacancy situation on the sodium-ion battery cathode in a timely manner and effectively reduce the vacancy rate of the sodium-ion battery cathode.

[0030] Please see Figure 1This is a flowchart of a monitoring method for sodium-ion battery cathode material preparation based on a digital twin system for sodium-ion battery cathode material preparation, according to an embodiment of this disclosure. The monitoring method includes some or all of the following steps. The digital twin system for sodium-ion battery cathode material preparation includes: a reactor digital module, a filter digital module, a drying oven digital module, a calcining furnace digital module, and a mixer digital module. The reactor digital module uses a nucleation-crystal growth model and CFD fluid simulation to simulate the co-precipitation stage of sodium-ion battery cathode material preparation. The filter digital module uses a porous media and pressure difference model to simulate the filtration stage of sodium-ion battery cathode material preparation. The drying oven digital module uses a heat transfer-mass transfer model to simulate the drying stage of sodium-ion battery cathode material preparation. The calcining furnace digital module uses a lattice rearrangement and densification model to simulate the calcination stage of sodium-ion battery cathode material preparation. The mixer digital module uses a DEM particle kinetics model to simulate the mixing stage of sodium-ion battery cathode material preparation.

[0031] The method for monitoring the preparation of sodium-ion battery cathode materials includes the following specific steps:

[0032] S100: Obtain key process node parameters for the production line of sodium-ion battery cathode.

[0033] In this embodiment, the key process node parameters of the production line refer to the preparation data corresponding to the key process stages on the sodium-ion battery cathode material preparation production line. In other words, the key process node parameters are the process indicators of the key process stages on the sodium-ion battery cathode production line, and thus correspond to the production status of the key process stages on the sodium-ion battery cathode production line. By collecting these key process node parameters, it is convenient to monitor the preparation status of the key process stages during the preparation of the sodium-ion battery cathode, thereby facilitating the determination of the real-time status of the sodium-ion battery cathode material during the preparation process.

[0034] S200: The key process node parameters of the production line are weighted and fused to obtain the vacancy rate for sodium electrode preparation.

[0035] In this embodiment, the key process node parameters of the production line are the preparation data corresponding to the key process stages on the sodium-ion battery cathode material preparation production line. That is, the key process node parameters are the process indicators of the key process stages on the sodium-ion battery cathode production line, and they correspond to the production status of the key process stages on the sodium-ion battery cathode production line. By collecting these key process node parameters, it is convenient to monitor the preparation status of the key process stages during the preparation of the sodium-ion battery cathode, thereby facilitating the determination of the real-time status of the sodium-ion battery cathode material during the preparation process. After the weighted fusion processing, the process production status of each key process stage corresponding to the key process node parameters is integrated, making it easier to predict the vacancy situation during the formation of the sodium-ion battery cathode.

[0036] S300: The vacancy rate of the sodium electrode preparation is adjusted by comparing it with the preset vacancy rate to obtain the vacancy adjustment amount.

[0037] In this embodiment, the vacancy rate of the sodium-ion battery cathode is obtained through the key process node parameters of the production line. These key process node parameters are the preparation data corresponding to key process stages on the sodium-ion battery cathode material preparation production line; that is, they are the process indicators of key process stages on the sodium-ion battery cathode production line, and thus correspond to the production status of key process stages on the sodium-ion battery cathode production line. By collecting these key process node parameters, it is convenient to monitor the preparation status of key process stages during the preparation of the sodium-ion battery cathode, thereby facilitating the determination of the real-time status of the sodium-ion battery cathode material during the preparation process. After the weighted fusion processing, the process production status of each key process stage corresponding to the key process node parameters is integrated, making it easier to predict the vacancy situation during the formation of the sodium-ion battery cathode. The preset vacancy rate is the standard vacancy rate after the sodium-ion battery cathode is prepared, that is, the preset vacancy rate is the safe vacancy distribution of the sodium-ion battery cathode. By adjusting the vacancy rate of the prepared sodium-ion battery cathode with the preset vacancy rate, it is easy to determine the vacancy difference of the sodium-ion battery cathode during the preparation process, thereby making it easier to predict the degree of vacancy in the sodium-ion battery cathode.

[0038] S400: Based on the vacancy adjustment amount, a graded linkage adjustment signal is sent to the positive electrode preparation digital twin control module to adjust the preparation mode of the corresponding process node.

[0039] In this embodiment, the vacancy adjustment is based on the vacancy rate of the sodium-ion battery cathode preparation and the preset vacancy rate. The vacancy rate of the sodium-ion battery cathode preparation is obtained through the key process node parameters of the production line. The key process node parameters are the preparation data corresponding to the key process stages on the sodium-ion battery cathode material preparation production line. That is, the key process node parameters are the process indicators of the key process stages of the sodium-ion battery cathode production line, and the key process node parameters correspond to the production status of the key process stages on the sodium-ion battery cathode production line. By collecting the key process node parameters, it is convenient to monitor the preparation status of the key process stages in the preparation of the sodium-ion battery cathode, thereby facilitating the determination of the real-time status of the sodium-ion battery cathode material during the preparation process. After the weighted fusion processing, the process production status of each key process stage corresponding to the key process node parameters is integrated, which facilitates the prediction of the vacancy situation during the formation of the sodium-ion battery cathode. The preset vacancy rate is the standard vacancy rate after the sodium-ion battery cathode is prepared, i.e., the safe vacancy distribution of the sodium-ion battery cathode. By adjusting the vacancy rate between the prepared sodium-ion battery cathode and the preset vacancy rate, it is easy to determine the vacancy difference during the preparation process of the sodium-ion battery cathode, thereby facilitating the prediction of the degree of vacancy in the sodium-ion battery cathode. After obtaining the vacancy adjustment value, the vacancy situation of the prepared sodium-ion battery cathode is determined. At this time, by sending a graded linkage adjustment signal to the cathode preparation digital twin control module, feedback adjustment is made on each key process stage of the sodium-ion battery cathode to reduce the vacancy situation of the sodium-ion battery cathode and effectively reduce the preparation vacancy rate of the sodium-ion battery cathode.

[0040] In the above embodiments, after collecting the key process node parameters of the production line, it is convenient to determine the production status of each key process stage of the sodium-ion battery cathode production line. Then, through weighted fusion processing of the key process node parameters of the production line, the vacancy rate of the sodium-ion battery cathode material during the preparation process is predicted. Then, the vacancy rate of the prepared sodium-ion battery cathode is compared with the standard vacancy rate to determine the degree of difference in the vacancy rate on the sodium-ion battery cathode. Finally, based on the degree of vacancy difference, the preparation mode of each key process stage of the sodium-ion battery cathode production line is adjusted to provide feedback adjustment for the preparation method of each key process stage of the sodium-ion battery cathode production line, so as to improve the vacancy situation on the sodium-ion battery cathode in a timely manner and effectively reduce the vacancy rate of the sodium-ion battery cathode.

[0041] In one embodiment, key process node parameters for the sodium-ion battery cathode production line are obtained, including: obtaining the raw material flow rate of the sodium-ion battery cathode; and / or, co-precipitation temperature, co-precipitation pH value, and co-precipitation stirring speed; and / or, filtration vacuum pressure; and / or, drying temperature; and / or, calcination inlet temperature, calcination mid-stage temperature, and calcination outlet temperature; and / or, mixing temperature and mixing humidity. In this embodiment, the key process node parameters are the preparation data corresponding to the key process stages on the sodium-ion battery cathode material preparation production line, that is, the key process node parameters are the process indicators of the key process stages on the sodium-ion battery cathode production line, and the key process node parameters correspond to the production status of the key process stages on the sodium-ion battery cathode production line. By collecting the key process node parameters, it is convenient to monitor the preparation status of the key process stages in the preparation of the sodium-ion battery cathode, thereby facilitating the determination of the real-time status of the sodium-ion battery cathode material during the preparation process. The key process parameters of the production line include the raw material flow rate of the sodium-ion battery cathode, which is the feed rate at the reactor inlet.

[0042] In another embodiment, the key process node parameters of the production line include at least one of the following: co-precipitation temperature, co-precipitation pH value, and co-precipitation stirring speed for the sodium-ion battery cathode. The co-precipitation temperature is the temperature inside the reactor during the co-precipitation process, the co-precipitation pH value is the pH value inside the reactor during the co-precipitation process, and the co-precipitation stirring speed is the stirring rate of the reactor during the co-precipitation process. The reactor digital module uses a nucleation-crystal growth model and CFD fluid simulation to simulate the co-precipitation stage of sodium-ion battery cathode material preparation. The nucleation rate of the nucleation model satisfies the following formula: Where J is the nucleation rate and A is the frequency factor. The critical energy for nucleation changes only; R is the gas constant, and T is the temperature.

[0043] The crystal growth model satisfies the following formula: Where V is the crystal growth rate, K is the growth constant, C is the solute concentration in the solution, and C0 is the saturation concentration of the solute in the solution.

[0044] CFD fluid simulation satisfies the following formula: ,in, ρ is the fluid density, v is the fluid velocity, p is the pressure, μ is the dynamic viscosity of the fluid, and f is the external force.

[0045] In another embodiment, the key process node parameters of the production line include the filtration vacuum pressure of the sodium-ion battery cathode. This filtration vacuum pressure is the vacuum pressure during the filtration stage of sodium-ion battery cathode preparation. The filter digital module uses a porous media and pressure difference model to simulate the filtration stage of sodium-ion battery cathode material preparation. Porous media flow is used to describe the flow behavior of fluid through a porous medium (such as filter paper or a membrane). The fluid flow in the porous medium satisfies the following formula: Where Q is the flow rate, k is the permeability of the medium, and A is the cross-sectional area. is the pressure difference, μ is the fluid viscosity, and L is the flow path length.

[0046] In another embodiment, the key process node parameters of the production line include the drying temperature of the sodium-ion battery cathode. The drying temperature is the temperature during the drying stage of sodium-ion battery cathode preparation. The drying chamber digital module uses a heat transfer-mass transfer model to simulate the drying stage of sodium-ion battery cathode material preparation. The heat conduction satisfies the following formula: Where q is the heat flux density and k is the thermal conductivity. It is the temperature gradient. The mass transfer model satisfies the following formula: Where J is the diffusion flux of the substance, and D is the diffusion coefficient. It is a concentration gradient.

[0047] In another embodiment, the key process node parameters of the production line include the calcination inlet temperature, calcination mid-stage temperature, and calcination outlet temperature of the sodium-ion battery cathode. The calcination inlet temperature is the temperature at the inlet of the calcination stage in the preparation of the sodium-ion battery cathode, the calcination mid-stage temperature is the temperature at the middle of the calcination stage in the preparation of the sodium-ion battery cathode, and the calcination outlet temperature is the temperature at the outlet of the calcination stage in the preparation of the sodium-ion battery cathode. The calcination furnace digital module uses a lattice rearrangement and densification model to simulate the calcination stage of sodium-ion battery cathode material preparation. The lattice rearrangement and densification process involves structural changes and density increases in the material. The lattice rearrangement and densification model satisfies the following formula: Where k is the reaction rate constant, A is the frequency factor, and E is the frequency factor. a R is the activation energy, R is the gas constant, and T is the temperature.

[0048] In another embodiment, the key process node parameters of the production line include the mixing temperature and mixing humidity of the sodium-ion battery cathode. The mixing temperature is the temperature of the mixing stage in the preparation of the sodium-ion battery cathode, and the mixing humidity is the humidity of the mixing stage in the preparation of the sodium-ion battery cathode. The mixer digital module uses the DEM particle dynamics model to simulate the mixing stage of the preparation of sodium-ion battery cathode materials to describe the collision, friction and flow behavior between particles. The DEM particle dynamics model uses the Discrete Element Method (DEM), a common method for simulating particle systems, especially for simulating particle interactions and flow processes. The DEM particle dynamics model satisfies the following formula: F=ma, where F is the interparticle force; m is the mass of the particle; and a is the acceleration.

[0049] In one embodiment, a weighted fusion process is performed on the key process node parameters of the production line to obtain the vacancy rate for sodium-ion battery cathode preparation. This includes outlier detection of the key process node parameters to remove outliers and missing values. In this embodiment, the key process node parameters are the preparation data corresponding to key process stages on the sodium-ion battery cathode material preparation production line. Specifically, the key process node parameters are the process indicators of key process stages on the sodium-ion battery cathode production line, and thus correspond to the production status of key process stages on the sodium-ion battery cathode production line. Collecting these key process node parameters facilitates monitoring the preparation status of key process stages during sodium-ion battery cathode preparation, thereby facilitating the determination of the real-time status of the sodium-ion battery cathode material during preparation. After the weighted fusion process, the production status of each key process stage corresponding to the key process node parameters is integrated, making it easier to predict the vacancy situation during the formation of the sodium-ion battery cathode. Before converting the key process node parameters of the production line into vacancy rates, the data of these parameters needs to be cleaned. Specifically, by detecting outliers in the key process node parameters, it is easier to identify abnormal / missing data, thereby facilitating the identification of abnormal process stages in the preparation of sodium-ion battery cathode materials. The method based on historical mean and standard deviation is used to detect outliers / missing values, and its detection model satisfies the following formula: Where μ is the historical mean; The historical standard deviation; The sensor data at the current moment; if ( If the threshold is used, it is considered an outlier or a missing value.

[0050] Further, the weighted fusion processing of the key process node parameters of the production line to obtain the vacancy rate in sodium-ion battery cathode preparation also includes: performing interpolation and normalization operations on the key process node parameters of the production line to update outliers and missing values ​​in the key process node parameters. In this embodiment, the key process node parameters of the production line are the preparation data corresponding to the key process stages on the sodium-ion battery cathode material preparation production line, that is, the key process node parameters of the production line are the process indicators of the key process stages of the sodium-ion battery cathode production line, and that is, the key process node parameters of the production line correspond to the production status of the key process stages on the sodium-ion battery cathode production line. By collecting the key process node parameters of the production line, it is convenient to monitor the preparation status of the key process stages in the preparation of sodium-ion battery cathode, thereby facilitating the determination of the real-time status of the sodium-ion battery cathode material during the preparation process. After the weighted fusion processing of the key process node parameters of the production line, the process production status of each key process stage corresponding to the key process node parameters of the production line is integrated, which facilitates the prediction of the vacancy situation during the preparation and molding of sodium-ion battery cathode. After identifying outliers and missing values, appropriate processing is required to ensure the data of the key process node parameters of the production line is normal. Specifically, linear interpolation is performed on both outliers and missing values, and the linear interpolation satisfies the following formula: , where x t-1 x represents the data point at the previous time step. t+1 This represents the data point at the next time step.

[0051] After handling outliers and missing values, the key process node parameters of the production line are complete and normal. At this point, all input data are Min-Max normalized to [0, 1] for each channel to satisfy the following formula: In this way, through linear interpolation and normalization, outliers in the key process node parameters of the production line are replaced and missing values ​​are supplemented.

[0052] In one embodiment, the key process node parameters of the production line are subjected to weighted fusion processing, including: extracting spatial features from the key process node parameters to obtain process spatial features. In this embodiment, the key process node parameters are the preparation data corresponding to the key process stages on the sodium-ion battery cathode material preparation production line, that is, the key process node parameters are the process indicators of the key process stages of the sodium-ion battery cathode production line, and the key process node parameters correspond to the production status of the key process stages on the sodium-ion battery cathode production line. By collecting the key process node parameters, it is convenient to monitor the preparation status of key process stages in the preparation of sodium-ion battery cathode, thereby facilitating the determination of the real-time status of the sodium-ion battery cathode material during the preparation process. After the weighted fusion processing, the process production status of each key process stage corresponding to the key process node parameters is integrated, which facilitates the prediction of the vacancy situation during the formation of the sodium-ion battery cathode. The key process node parameters of the production line undergo spatial feature extraction to facilitate the extraction of spatial features from these parameters. Specifically, spatial feature extraction of the key process node parameters is performed using a CNN layer to satisfy the following formula: , where x t It is the value of the input signal at time t; w k The k-th weight of the convolution kernel; z t is the output signal after the convolution operation, and its value at time t; b is the bias fixed term.

[0053] Furthermore, the weighted fusion processing of the key process node parameters of the production line also includes: extracting time-series features from the key process node parameters to obtain process time-series features. The key process node parameters are the preparation data corresponding to key process stages on the sodium-ion battery cathode material preparation production line; that is, the key process node parameters are the process indicators of key process stages on the sodium-ion battery cathode production line, and thus correspond to the production status of key process stages on the sodium-ion battery cathode production line. By collecting the key process node parameters, it is convenient to monitor the preparation status of key process stages during the preparation of the sodium-ion battery cathode, thereby facilitating the determination of the real-time status of the sodium-ion battery cathode material during the preparation process. After the weighted fusion processing, the process production status of each key process stage corresponding to the key process node parameters is integrated, facilitating the prediction of vacancy situations during the formation of the sodium-ion battery cathode. The key process node parameters of the production line are the preparation data corresponding to the key process stages on the sodium-ion battery cathode material preparation production line. In other words, the key process node parameters are the process indicators of the key process stages on the sodium-ion battery cathode production line, and they correspond to the production status of the key process stages on the sodium-ion battery cathode production line. By collecting these key process node parameters, it is convenient to monitor the preparation status of key process stages during the preparation of the sodium-ion battery cathode, thereby facilitating the determination of the real-time status of the sodium-ion battery cathode material during the preparation process. After the weighted fusion processing, the process production status of each key process stage corresponding to the key process node parameters is integrated, facilitating the prediction of vacancy situations during the formation of the sodium-ion battery cathode. The key process node parameters undergo time series feature extraction to capture the long-term dependencies of the key process node parameters in the time series. Specifically, time series feature extraction of the key process node parameters is performed using an LSTM layer to satisfy the following formula:

[0054]

[0055]

[0056]

[0057]

[0058]

[0059]

[0060] Among them, it f t o t These are the input gate, forget gate, and output gate, respectively; c t In cellular state; h t is the hidden state; W and b are the weight matrix and bias, respectively.

[0061] Furthermore, the weighted fusion processing of the key process node parameters of the production line also includes: weighting and fusion of the process spatial features and the process time series features to obtain a process fusion feature vector. In this embodiment, the key process node parameters of the production line are the preparation data corresponding to the key process stages on the sodium-ion battery cathode material preparation production line, that is, the key process node parameters of the production line are the process indicators of the key process stages of the sodium-ion battery cathode production line, and that is, the key process node parameters of the production line correspond to the production status of the key process stages on the sodium-ion battery cathode production line. By collecting the key process node parameters of the production line, it is convenient to monitor the preparation status of the key process stages in the preparation of sodium-ion battery cathode, thereby facilitating the determination of the real-time status of the sodium-ion battery cathode material during the preparation process. After the weighted fusion processing, the process production status of each key process stage corresponding to the key process node parameters of the production line is integrated, which facilitates the prediction of the vacancy situation during the preparation and molding of the sodium-ion battery cathode. The key process node parameters of the production line undergo spatial feature extraction to facilitate the extraction of spatial features. Specifically, spatial feature extraction is performed on the key process node parameters using a CNN layer. Simultaneously, the key process node parameters also undergo time-series feature extraction to capture the long-term dependencies of the key process node parameters over time. Specifically, time-series feature extraction is performed on the key process node parameters using an LSTM layer. See Appendix for details. Figure 2 At this point, both the process spatial features and the process time series features are feature extractions of key process node parameters of the production line in both space and time series. Then, the aforementioned dynamic features are weighted, that is, they are weighted according to the relevance of the input features. Specifically, the weight of each feature is calculated, and its influence in the model is dynamically adjusted according to the weight. The dynamic feature weighting used is a self-attention model, satisfying the following formula:

[0062] Where Q is the query vector, K is the key vector, V is the value vector, and d k Let be the dimension of the key vector, and softmax be the activation function. By calculating the similarity between the query vector (Q) and the key vector (K), the attention weight of each value vector (V) is obtained, thus dynamically weighting the features.

[0063] After assigning weights to the process spatial features and process time series features, a weighted fusion of features is required. Specifically, the process spatial feature z and the process time series feature h are weighted and fused after the weights are calculated using a self-attention model. The weighted fusion model satisfies the following formula: Where z comes from the spatial features of the CNN layer, h comes from the temporal features of the LSTM layer, α1 and α2 are dynamic weights generated by the attention mechanism, and f fused This is the integrated feature representation after fusion, which will be used in subsequent prediction layers.

[0064] Furthermore, the weighted fusion processing of the key process node parameters of the production line also includes: performing a regression operation on the process fusion feature vector to obtain the vacancy rate in the preparation of the sodium-ion battery cathode. In this embodiment, the key process node parameters of the production line are the preparation data corresponding to the key process stages on the material preparation production line of the sodium-ion battery cathode, that is, the key process node parameters of the production line are the process indicators of the key process stages of the sodium-ion battery cathode production line, and the key process node parameters of the production line correspond to the production status of the key process stages on the sodium-ion battery cathode production line. By collecting the key process node parameters of the production line, it is convenient to monitor the preparation status of the key process stages in the preparation of the sodium-ion battery cathode, thereby facilitating the determination of the real-time status of the sodium-ion battery cathode material during the preparation process. After the weighted fusion processing of the key process node parameters of the production line, the process production status of each key process stage corresponding to the key process node parameters of the production line is integrated, which facilitates the prediction of the vacancy situation during the preparation and molding of the sodium-ion battery cathode. The key process node parameters of the production line undergo spatial feature extraction to facilitate the extraction of spatial features. Specifically, spatial feature extraction is performed on the key process node parameters through a CNN layer. Simultaneously, the key process node parameters also undergo time-series feature extraction to capture the long-term dependencies of the key process node parameters in the time series. Specifically, time-series feature extraction is performed on the key process node parameters through an LSTM layer. After weight allocation and weighted fusion, the fused feature formed by the process spatial features and process time-series features serves as the comprehensive transformation feature of the key process node parameters. That is, the process fused feature vector is represented as the comprehensive feature. This fused feature vector is input into a regression network for prediction. Specifically, the fused feature vector is input into the regression network through a regression layer to predict the cathode vacancy rate after the preparation of sodium-ion battery cathode materials. This facilitates subsequent feedback adjustment of process parameters for each key process stage of sodium-ion battery cathode preparation. The regression operation satisfies the following formula: ,in, The vacancy rate was prepared for the predicted sodium-ion cathode.

[0065] In one embodiment, the vacancy rate of the sodium electrode preparation is adjusted by comparing it with a preset vacancy rate to obtain a vacancy adjustment amount. This includes: calculating the adjustment between the vacancy rate of the sodium electrode preparation and the preset vacancy rate; sending a graded linkage adjustment signal to the cathode preparation digital twin control module based on the vacancy adjustment amount to adjust the preparation mode of the corresponding process node, including: detecting whether the vacancy adjustment amount is less than or equal to a first preset adjustment amount; when the vacancy adjustment amount is less than or equal to the first preset adjustment amount, sending a single-stage down-adjustment signal to the cathode preparation digital twin control module to down-adjust the reaction pH value, wherein the pH value down-adjustment ratio is 4% to 7%. In this embodiment, the vacancy rate of the sodium-ion battery cathode is obtained through the key process node parameters of the production line. These key process node parameters are the preparation data corresponding to key process stages on the sodium-ion battery cathode material preparation production line; that is, they are the process indicators of key process stages on the sodium-ion battery cathode production line, and thus correspond to the production status of key process stages on the sodium-ion battery cathode production line. By collecting these key process node parameters, it is convenient to monitor the preparation status of key process stages during the preparation of the sodium-ion battery cathode, thereby facilitating the determination of the real-time status of the sodium-ion battery cathode material during the preparation process. After the weighted fusion processing, the process production status of each key process stage corresponding to the key process node parameters is integrated, making it easier to predict the vacancy situation during the formation of the sodium-ion battery cathode. The preset vacancy rate is the standard vacancy rate after the sodium-ion battery cathode is prepared, i.e., the safe vacancy distribution of the sodium-ion battery cathode. By adjusting the vacancy rate between the prepared sodium-ion battery cathode and the preset vacancy rate, it is easy to determine the vacancy differences in the sodium-ion battery cathode during the preparation process, thereby facilitating the prediction of the degree of vacancy in the sodium-ion battery cathode. By calculating the adjustment between the prepared sodium-ion battery cathode vacancy rate and the preset vacancy rate, for example, by calculating the least squares difference between the prepared sodium-ion battery cathode vacancy rate and the preset vacancy rate, the finished product vacancy situation corresponding to the simulated preparation of the sodium-ion battery cathode can be determined. The vacancy adjustment amount being less than or equal to the first preset adjustment amount indicates that the predicted vacancy rate of the sodium-ion battery cathode after preparation is lower than the first-order vacancy rate. At this time, the vacancy situation of the sodium-ion battery cathode is mainly due to the density of the precipitation structure. By sending a single-level down-adjustment signal to the cathode preparation digital twin control module, the reaction pH value in the co-precipitation stage is adjusted in a single item. Specifically, the current pH value is lowered by 4% to 7%. 7% helps to reduce the excessively fast reaction rate of hydrogen ion concentration, improve the density of the precipitation structure, and thus reduce the vacancy rate of the sodium-ion battery cathode.

[0066] In another embodiment, detecting whether the vacancy adjustment amount is less than or equal to a first preset adjustment amount further includes:

[0067] Check whether the adjusted vacancy amount is less than or equal to the safe vacancy adjustment;

[0068] When the vacancy adjustment amount is less than or equal to the safe vacancy adjustment amount, the process parameters of each current process stage are maintained.

[0069] When the vacancy adjustment amount is greater than the safe vacancy adjustment amount, the step is to detect whether the vacancy adjustment amount is less than or equal to the first preset adjustment amount.

[0070] Among them, the vacancy rate between the safe vacancy adjustment and the first preset adjustment amount is (5%, 7%).

[0071] Further, the method detects whether the vacancy adjustment amount is less than or equal to a first preset adjustment amount, and then further includes: when the vacancy adjustment amount is greater than the first preset adjustment amount, detecting whether the vacancy adjustment amount is less than or equal to a second preset adjustment amount; when the vacancy adjustment amount is less than or equal to the second preset adjustment amount, sending a two-stage down-adjustment signal to the positive electrode preparation digital twin control module to down-adjust the reaction pH value and the raw material feeding rate, wherein the pH value is down-adjusted by 7% and the raw material feeding rate is down-adjusted by 20%. In this embodiment, the second preset adjustment value is a secondary standard value for detecting the vacancy rate of the sodium-ion battery cathode material. If the vacancy adjustment value is less than or equal to the second preset adjustment value, it indicates that the predicted vacancy rate of the sodium-ion battery cathode after preparation is lower than the secondary vacancy rate. This means the vacancy rate difference of the sodium-ion battery cathode is between the first and second preset adjustment values, or between primary and secondary vacancy levels. At this point, a dual-level down-adjustment signal is sent to the cathode preparation digital twin control module for dual-stage adjustment. Specifically, the reaction pH value and the raw material feeding rate are lowered. That is, when the pH is lowered by 7%, the raw material feeding rate is simultaneously lowered by 20%, which slows down the nucleation rate, optimizes the crystal structure integrity, and further reduces the vacancy rate of the sodium-ion battery cathode. The vacancy rates corresponding to the first and second preset adjustment values ​​are (7%, 9%).

[0072] Furthermore, the process includes detecting whether the vacancy adjustment amount is less than or equal to a second preset adjustment amount, followed by:

[0073] When the vacancy adjustment amount is greater than the second preset adjustment amount, it is detected whether the vacancy adjustment amount is less than or equal to the third preset adjustment amount;

[0074] When the vacancy adjustment amount is less than or equal to the third preset adjustment amount, a three-level joint down-adjustment signal is sent to the positive electrode preparation digital twin control module to down-adjust the reaction pH value and the raw material feeding rate, while extending the dropping and stirring time. The pH value is down-adjusted by 7%, the raw material feeding rate is down-adjusted by 30%, and the dropping and stirring time is extended by 15%.

[0075] In this embodiment, the third preset adjustment value is a tertiary standard value for detecting the vacancy rate of the sodium-ion battery cathode material. If the vacancy adjustment value is less than or equal to the third preset adjustment value, it indicates that the predicted vacancy rate of the sodium-ion battery cathode after preparation is lower than the tertiary vacancy rate. This means the degree of vacancy rate difference in the sodium-ion battery cathode is between the second and third preset adjustment values, or between the second and third vacancy levels. At this point, a three-level joint downward adjustment signal is sent to the cathode preparation digital twin control module for triple adjustment. Specifically, the reaction pH value and the raw material feeding rate are lowered, while the dropping and stirring time is extended. That is, with a 7% decrease in pH and a 30% decrease in the raw material feeding rate, the dropping and stirring time is extended by 15%, effectively optimizing the crystal structure integrity and further reducing the vacancy rate of the sodium-ion battery cathode. The vacancy rates corresponding to the second and third preset adjustment values ​​are (9%, 11%).

[0076] In another embodiment, when the vacancy adjustment amount exceeds a third preset adjustment amount, a four-level joint alarm signal is sent to the cathode preparation digital twin control module to adjust the reaction pH value, raw material feeding rate, and dropping and stirring time to the maximum extent, while simultaneously issuing a stop-feed warning. At this time, the predicted vacancy rate of the sodium-ion battery cathode after preparation exceeds the safe vacancy rate, and it is in a defective product state with an excessive vacancy rate. The reaction pH value is reduced by 55%, the raw material feeding rate is reduced by 45%, and the dropping and stirring time is extended by 35% to reduce the vacancy rate as much as possible, while issuing an abnormality warning.

[0077] In another embodiment, to improve the stability and robustness of the vacancy rate prediction model, a graded linkage adjustment signal is sent to the positive electrode fabrication digital twin control module based on the vacancy adjustment amount to adjust the fabrication mode of the corresponding process node. This is followed by the following steps:

[0078] To obtain the total vacancy loss at the positive electrode of a sodium-ion battery;

[0079] Detect whether the total loss of the empty space is greater than or equal to the preset loss amount;

[0080] When the total loss of the vacancy is greater than or equal to the preset loss, a model penalty optimization signal is sent to the positive electrode preparation digital twin control module to optimize the model at each stage.

[0081] In this embodiment, the total vacancy loss refers to the degree of vacancy rate loss in the sodium-ion battery cathode material after the completion of the preparation process. As a measure of regression error for the vacancy rate, it facilitates determining the impact of each process stage model on the vacancy rate, thereby facilitating the assessment of the stability of each model's vacancy rate prediction. If the total vacancy loss is greater than or equal to a preset loss, it indicates that the vacancy rate loss on the sodium-ion battery cathode is too large, meaning the stability of the models for each process stage of the sodium-ion battery cathode is poor. In this case, a model penalty optimization signal is sent to the cathode preparation digital twin control module to optimize the models at each stage, making the vacancy rate predictions of the sodium-ion battery cathode more accurate.

[0082] In another embodiment, the total loss of vacancy spaces satisfies the following formula:

[0083] .

[0084] Wherein, Huber loss function L Huber When the error is small, the squared error form is used to ensure good model fitting accuracy; when the error is large, it automatically switches to the absolute error form to reduce the interference of extreme batches or measurement outliers on the model training process. The Huber loss function satisfies the following formula:

[0085]

[0086] Where y is the standard vacancy rate and δ is the vacancy rate error threshold.

[0087] To ensure that the predicted vacancy rate stays within a controllable range, the system sets an ideal vacancy rate interval [l, u] = [0.05, 0.07]. When the predicted result exceeds this interval, an additional penalty function is introduced to enhance the model's sensitivity to process deviations, as detailed below:

[0088]

[0089] in, This is the interval offset penalty term.

[0090] Since pH, feed flow rate, and stirring speed represent the acidity / alkalinity of the reaction environment, the reaction rate, and the homogeneity of material mixing, respectively, they directly affect the structural stability and crystal defect formation during the coprecipitation reaction. Therefore, pH, feed flow rate, and stirring speed are selected as process deviation penalty parameters to achieve effective response and dynamic optimization to abnormal operating conditions. The process deviation penalty function satisfies the following formula:

[0091]

[0092] Where pH1 is the pH value inside the reactor, F1 is the feed flow rate, and R1 is the stirring speed inside the reactor. , , γ1, γ2, and γ3 are the empirically optimal values, and are hyperparameters for adjusting the intensity of the penalty.

[0093] The embodiments described above are merely illustrative of several implementations of this disclosure, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this disclosure, and these all fall within the protection scope of this disclosure. Therefore, the protection scope of this patent should be determined by the appended claims.

Claims

1. A sodium-ion battery cathode material preparation monitoring method based on a digital twin system of a sodium-ion battery cathode material preparation, characterized in that, The application relates to a sodium-ion battery positive electrode material preparation digital twin system and a sodium-ion battery positive electrode material preparation monitoring method. The sodium-ion battery positive electrode material preparation digital twin system comprises: A reaction kettle digital module which simulates a co-precipitation stage of sodium-ion battery positive electrode material preparation by adopting a nucleation-crystal growth model and a CFD fluid simulation; A filter digital module which simulates a filtering stage of sodium-ion battery positive electrode material preparation by adopting a porous medium and differential pressure model; A drying box digital module which simulates a drying stage of sodium-ion battery positive electrode material preparation by adopting a heat and mass transfer model; A calcining furnace digital module which simulates a calcining stage of sodium-ion battery positive electrode material preparation by adopting a crystal lattice rearrangement and densification model; A mixer digital module which simulates a mixing stage of sodium-ion battery positive electrode material preparation by adopting a DEM particle dynamics model. The sodium-ion battery positive electrode material preparation monitoring method comprises the following steps: Obtaining key process node parameters of a sodium-ion battery positive electrode production line; Performing weighted fusion processing on the key process node parameters to obtain a sodium-ion battery positive electrode preparation vacancy rate; Performing a vacancy adjustment on the sodium-ion battery positive electrode preparation vacancy rate and a preset vacancy rate to obtain a vacancy adjustment amount; Sending a hierarchical linkage adjustment signal to a positive electrode preparation digital twin control module according to the vacancy adjustment amount to adjust a process node preparation mode of a corresponding process stage. 2.The sodium-ion battery cathode material preparation monitoring method based on a digital twin system of a sodium-ion battery cathode material preparation system according to claim 1, wherein Obtaining key process node parameters of a sodium-ion battery positive electrode production line comprises the following steps: Obtaining raw material flow of the sodium-ion battery positive electrode; and / or, co-precipitation temperature, co-precipitation PH value, co-precipitation stirring speed; and / or, filtration vacuum pressure; and / or, drying temperature; and / or, calcining inlet temperature, calcining middle temperature and calcining outlet temperature; and / or, mixing temperature and mixing humidity. 3.The sodium-ion battery cathode material preparation monitoring method based on a digital twin system of a sodium-ion battery cathode material preparation system according to claim 1, wherein, Performing weighted fusion processing on the key process node parameters to obtain a sodium-ion battery positive electrode preparation vacancy rate comprises the following steps: Performing abnormal value detection on the key process node parameters to clean abnormal values and missing values in the key process node parameters. 4.The sodium-ion battery cathode material preparation monitoring method based on a digital twin system of a sodium-ion battery cathode material preparation system according to claim 3, wherein Performing weighted fusion processing on the key process node parameters to obtain a sodium-ion battery positive electrode preparation vacancy rate further comprises the following steps: Performing interpolation normalization operation on the key process node parameters to update abnormal values and missing values in the key process node parameters. 5.The sodium-ion battery cathode material preparation monitoring method based on a digital twin system of a sodium-ion battery cathode material preparation system according to claim 1, wherein, Performing weighted fusion processing on the key process node parameters comprises the following steps: Performing spatial feature extraction on the key process node parameters to obtain process spatial features.

6. The sodium-ion battery cathode material preparation monitoring method based on the digital twin system of the sodium-ion battery cathode material preparation system according to claim 5, wherein Performing weighted fusion processing on the key process node parameters further comprises the following steps: Performing time sequence feature extraction on the key process node parameters to obtain process time sequence features.

7. The sodium-ion battery cathode material preparation monitoring method based on the digital twin system of the sodium-ion battery cathode material preparation system according to claim 6, wherein Performing weighted fusion processing on the key process node parameters further comprises the following steps: Performing weight distribution and weighted fusion on the process spatial features and the process time sequence features to obtain a process fusion feature vector. 8.The sodium-ion battery cathode material preparation monitoring method based on a digital twin system of a sodium-ion battery cathode material preparation system according to claim 7, wherein, Performing weighted fusion processing on the key process node parameters further comprises the following steps: The regression operation is performed on the process fusion feature vector to obtain a vacancy rate of the sodium battery positive electrode preparation. 9.The sodium-ion battery cathode material preparation monitoring method based on a digital twin system of a sodium-ion battery cathode material preparation system according to claim 1, wherein, The vacancy rate of the sodium battery positive electrode preparation is subjected to a void adjustment process with a preset vacancy rate to obtain a void adjustment amount, including: Obtaining the adjustment of the vacancy rate of the sodium battery positive electrode preparation and the preset vacancy rate; According to the void adjustment amount, a hierarchical linkage adjustment signal is sent to the positive electrode preparation digital twin control module to adjust the process node preparation mode of the corresponding process stage, including: Detecting whether the void adjustment amount is less than or equal to a first preset adjustment amount; When the void adjustment amount is less than or equal to the first preset adjustment amount, a single-stage down-regulation signal is sent to the positive electrode preparation digital twin control module to down-regulate the reaction PH value, wherein the PH value down-regulation ratio is 4% to 7%. 10.The sodium-ion battery cathode material preparation monitoring method based on a digital twin system of a sodium-ion battery cathode material preparation system according to claim 9, wherein, Detecting whether the void adjustment amount is less than or equal to a first preset adjustment amount, and then including: When the void adjustment amount is greater than the first preset adjustment amount, it is detected whether the void adjustment amount is less than or equal to a second preset adjustment amount; When the void adjustment amount is less than or equal to the second preset adjustment amount, a two-stage down-regulation signal is sent to the positive electrode preparation digital twin control module to down-regulate the reaction PH value and the raw material feeding rate, wherein the PH value down-regulation ratio is 7%, and the raw material feeding rate down-regulation ratio is 20%.

Images