A quality testing method, medium, and terminal device for a ternary cathode material

Abstract

The present invention relates to a quality testing method, medium, and terminal device for ternary cathode materials. First, the initial state of the material is understood to lay the foundation for subsequent changes. Secondly, charge-discharge data and the structural change rate of the cycle period are collected to lay the direction and process speed of subsequent changes. Then, the charge-discharge data of the next cycle period is predicted, and finally, the new predicted data is continuously iteratively predicted until the charge-discharge data after the final cycle number is obtained, so as to determine the capacity retention rate after the final preset period, and accordingly judge whether the quality of the ternary cathode material meets the standard. On the one hand, it comprehensively and systematically analyzes the various performances of the ternary cathode material, showing comprehensiveness. On the other hand, it can effectively reduce the number of experiments, reduce the manual labor intensity and the time required for quality inspection, improve the quality inspection efficiency, and increase its service life after leaving the factory and customer satisfaction.

Description

Technical Field

[0001] The present invention relates to the field of quality testing, and in particular to a quality testing method, medium and terminal equipment for a ternary positive electrode material. Background Art

[0002] Positive electrode materials, negative electrode materials, electrolytes and separators are the four main materials of power batteries, among which positive electrode materials account for 40% of the total cost and directly determine the energy density of the battery cell. Ternary positive electrode materials have gradually become the mainstream positive electrode materials in the market due to their higher energy density and lower cost. The gradual popularization of pure electric vehicles will lead to a strong market demand for high energy density ternary positive electrode materials. LiNi 0.5 Co 0.5 Mn 0.3 As a typical representative of ternary positive electrode materials for lithium-ion batteries, O2 has become a strong competitor for positive electrode materials for lithium-ion batteries due to its good safety, low cost, and high capacity. 0.5 Co 0.5 Mn 0.3 The application of O2 ternary materials in power batteries, energy storage and small high-energy-density lithium-ion batteries for electronic products requires quality testing and evaluation before leaving the factory. One of the most important performance indicators is its cycle performance, which refers to the capacity retention rate of the battery after a certain number of cycles.

[0003] In the prior art, it is usually necessary to conduct many cycles of testing, usually more than 200 times. Not only is the testing process complicated, time-consuming and costly, but the testing process itself consumes the product, greatly compromising its factory quality. How to improve its quality testing efficiency is a major difficulty in this field.

[0004] The Chinese patent with announcement number CN115338149B first conducts a small number of charge and discharge cycle tests on the battery, and then analyzes the X-ray powder diffraction spectra of the ternary layered positive electrode material before and after the cycle to obtain the change rate of lithium-nickel mixing and the thickness change of the rock salt phase before and after the cycle, and quickly judges the cycle life of the lithium battery ternary layered positive electrode material. To a certain extent, the speed of cycle life judgment has been improved. However, the structure of the ternary positive electrode material is complex, and its cycle life and quality are not determined solely by structural changes such as the lithium-nickel mixing change rate and the rock salt phase thickness change. Prediction and judgment based on only these two indicators is rather one-sided, which may cause certain false detections and missed detections.

[0005] Therefore, how to improve its quality testing methods and take into account both testing efficiency and testing accuracy is a technical problem that needs to be urgently solved in this field. Summary of the invention

[0006] To solve the above technical problems, the present invention provides a quality testing method for ternary cathode materials, which includes:

[0007] S1: Obtain initial coin cell data and initial structure data; the initial coin cell data includes any one or more of the first efficiency, charge-discharge capacities at different powers, and the first charge-discharge capacity; the initial structure data includes any one or more of the specific surface area, tap density, compression density, and component contents.

[0008] S2: Obtain charge-discharge curves for N cycle periods.

[0009] S3: Divide the N cycle periods into M stages, and obtain structure change data after each stage of cycling; N and M are integers greater than 1, and N is greater than M; the structure change data includes any one or more of particle size, morphology, distribution, surface roughness, lithium-nickel mixing data, layered structure damage, and crack conditions.

[0010] S4: Predict the charge-discharge curve for the next cycle period based on the initial coin cell data, initial structure data, charge-discharge curves for N cycle periods, and structure change data after each stage of cycling.

[0011] S5: Determine the number of cycle periods, iteratively perform step S4 to predict the charge-discharge curve for the next period of time, determine the capacity retention rate after a set number of cycle periods, and obtain the quality test result.

[0012] Further, step S4 includes: constructing and training a prediction model with the initial coin cell data, initial structure data, charge-discharge curves for N cycle periods, and structure change data after each stage of cycling as inputs and the charge-discharge curve after the next cycle period as the output, extracting relevant features, and constructing intricate connections between the inputs and outputs to obtain the prediction result.

[0013] Further, the constructed prediction model includes:

[0014] An input module, including 2 channels; the first channel is used to input the initial coin cell data, initial structure data, and structure change data after each stage of cycling; the second channel is used to input the charge-discharge curves for N cycle periods.

[0015] A feature extraction module, including: a first feature extraction unit connected to the first channel, which is used to analyze three-dimensional matrix information according to the initial coin cell data, initial structure data, and structure change data after cycling, and extract data features; a second feature extraction unit connected to the second channel, which is used to analyze the capacity retention rate, charge mid-voltage, and discharge mid-voltage according to the charge-discharge curves for N cycle periods, and extract curve features.

[0016] A prediction module, connected to the feature extraction module, is used to predict the charge-discharge curve of the next cycle period based on data features and curve features.

[0017] Further, the first feature extraction unit includes multiple convolutional layers and pooling layers;

[0018] The convolutional layer is used to implement forward propagation, extract multi-scale features of a three-dimensional matrix, with an input channel number of 3, an output channel number of 64, a convolutional kernel size of 3, a stride of 1, a padding of 1, a dilation of 1, a group number of 1, and a bias added; the pooling layer is used to return multi-scale features.

[0019] Further, the prediction module includes 2 fully connected layers and an activation function located between the 2 fully connected layers; the first fully connected layer is used to fuse data features and curve features, merge features in the feature dimension; and through the activation function, the second fully connected layer outputs the prediction result.

[0020] Further, the steps of training the prediction model include:

[0021] Obtain the initial charge-discharge data of several ternary cathode materials; initial structure data; charge-discharge curves of 50 cycle periods; structure change data after 5, 12, and 20 cycle periods;

[0022] Input the initial charge-discharge data, initial structure data, charge-discharge curves of the first 20 cycle periods, and structure change data after 5, 12, and 20 cycle periods of each ternary cathode material into the prediction model, and output the charge-discharge curve of the next cycle period;

[0023] Use the charge-discharge data of the last 30 cycle periods as the verification data set to perform regression verification on the charge-discharge curve predicted by the model, so as to modify the various parameters of the prediction model and obtain the trained prediction model.

[0024] Further, when dividing the N cycle periods into M stages, divide them in the way of increasing intervals.

[0025] Further, the initial charge-discharge data includes: first efficiency and charge-discharge capacities at different rates;

[0026] The initial structure data includes Ni, Co, Mn, impurity content, and compaction density;

[0027] The structure change data includes any one or more of: particle size, morphology, distribution, surface roughness, lithium-nickel mixing data, whether the layered structure is damaged, and whether microcracks appear.

[0028] On the other hand, the present invention also provides a computer storage medium storing executable program code; the executable program code is used to execute any of the above quality testing methods.

[0029] On the other hand, the present invention also provides a terminal device including a memory and a processor; the memory stores program code executable by the processor; the program code is used to execute any of the above quality testing methods.

[0030] A quality testing method, medium and terminal device for a ternary cathode material provided by the present invention first collect initial data of coin cell and structure to understand the initial state of the material, laying a foundation for subsequent changes; secondly, collect charge-discharge data and structure change speed of the cycle period to understand the change situation of the material, laying a foundation for the subsequent change direction and process speed; then predict the charge-discharge data of the next cycle period according to the data obtained in the previous steps, and finally continuously iterate and predict the new predicted data until the preset iteration period is reached to obtain the charge-discharge data after the final cycle number, and then the capacity retention rate after the final preset period can be determined, and accordingly, it can be judged whether the quality of the ternary cathode material meets the standard. Compared with the prior art, on the one hand, it comprehensively combines the initial data of coin cell, the initial data of structure, the charge-discharge curves of N cycle periods and the structure change data after each stage of cycling, comprehensively and systematically analyzes the various performances of the ternary cathode material, and has comprehensiveness; on the other hand, it predicts the charge-discharge curve of the next cycle period through the previous data, that is, predicts its performance in the future cycle period, so as to evaluate the quality of the material, which can effectively reduce the number of experiments, reduce the manual labor intensity and the time required for quality inspection, improve the quality inspection efficiency, and at the same time can reduce the performance consumption of the product during the quality inspection process, improve its service life after leaving the factory, and improve customer satisfaction. Therefore, the quality testing method for the ternary cathode material of the present invention can meet the requirements of testing efficiency and testing accuracy, reduce the time and cost required for testing, and avoid phenomena such as missed inspection and misjudgment. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 It is a flowchart of an embodiment of the quality testing method for the ternary cathode material of the present invention;

[0032] Figure 2 It is a schematic diagram of the result of the charge-discharge curve of one cycle period;

[0033] Figure 3 It is a schematic diagram of the result of the predicted charge-discharge curve of N cycle periods. DETAILED DESCRIPTION OF THE INVENTION

[0034] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0035] It should be noted that if there are directional indications involved in the embodiments of the present invention, such as up, down, left, right, front, back..., then the directional indications are only used to explain the relative positional relationship and movement conditions between components in a specific posture. If the specific posture changes, the directional indications will also change accordingly. In addition, if there are descriptions such as "first, second", "S1, S2", "step one, step two" in the embodiments of the present invention, such descriptions are only for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the quantity of the indicated technical features or indicating the execution order of the method, etc. Those skilled in the art can understand that all those that do not violate the inventive points under the inventive concept of the invention should be included in the protection scope of the present invention.

[0036] As Figure 1 shown, the present invention provides a method for testing the quality of a ternary cathode material, including:

[0037] S1: Obtain the initial data of coin cell and the initial data of structure;

[0038] S2: Obtain the charge-discharge curves of N cycle periods;

[0039] S3: Divide the N cycle periods into M stages, and obtain the structure change data after each stage of cycling; N and M are integers, and N is greater than M;

[0040] S4: According to the initial data of coin cell, the initial data of structure, the charge-discharge curves of N cycle periods, and the structure change data after each stage of cycling, predict the charge-discharge curve of the next cycle period;

[0041] S5: Determine the number of cycle periods, iterate step S4 to predict the charge-discharge curve of the next period of time, determine the capacity retention rate after the set number of cycle periods, and obtain the quality test result.

[0042] In this embodiment, a method for testing the quality of the ternary cathode material of the present invention is provided. First, in step S1, the initial data of coin cell and structure are collected to understand the initial state of the material, laying the foundation for subsequent changes. Secondly, in steps S2 - S3, the charge-discharge data and the structural change rate of the cycle period are collected to understand the change of the material, laying the direction and process speed of subsequent changes. Then, in step S4, based on the data obtained in the above steps, the charge-discharge data of the next cycle period is predicted. Finally, in step S5, the new predicted data is continuously iterated in step S4 until the preset iteration period is reached, and the charge-discharge data after the final cycle number is obtained, and then the capacity retention rate after the final preset period can be determined, and accordingly, it can be judged whether the quality of the ternary cathode material meets the standard. Compared with the prior art, on the one hand, it comprehensively combines the initial data of coin cell, the initial data of structure, the charge-discharge curves of N cycle periods and the structural change data after each stage of cycling, and comprehensively and systematically analyzes the various performances of the ternary cathode material, avoiding one-sidedness and being comprehensive. On the other hand, through the previous data, it predicts the charge-discharge curve of the next cycle period, that is, predicts its performance in future cycle periods, so as to evaluate the quality of the material, which can effectively reduce the number of experiments. For example, in the prior art, if it is necessary to understand the capacity retention rate after 1000 cycles, 1000 cycles need to be carried out to understand its final charge-discharge curve, which not only takes time but also cannot be done for each product, otherwise the service life after the product leaves the factory will be greatly reduced. By using the method of the present invention, only the charge-discharge curves and structural changes of the first dozens of times need to be tested to make predictions of the charge-discharge curves for an infinite number of subsequent times, and the final capacity retention rate can be obtained. Therefore, the present invention can reduce the labor intensity of manual work and the time required for quality inspection, improve the quality inspection efficiency, and at the same time can reduce the performance consumption of the product during the quality inspection process, improve its service life after leaving the factory, and improve customer satisfaction. The method for testing the quality of the ternary cathode material of the present invention can meet the requirements of testing efficiency and testing accuracy, and on the basis of reducing the time and cost required for testing, avoid phenomena such as missed inspection and misjudgment.

[0043] S1: Obtain the initial data of coin cell and the initial data of structure;

[0044] Specifically, "coin cell" refers to a coin-type full cell, which is a form of battery test used in the laboratory and is mainly composed of a positive electrode case, a negative electrode case, electrode sheets, a separator, gaskets, spring sheets and electrolyte; it is used to evaluate the electrochemical performance of battery materials, such as capacity, cycle life, etc.

[0045] As shown in Table 1, the initial data of coin cell, optionally but not limited to, include: the first efficiency, that is, the ratio of the discharge capacity to the theoretical capacity of the battery in the first charge-discharge cycle; the charge-discharge capacities at different rates, such as 0.2C; 0.5C; 1C; the first charge-discharge capacity, etc.

[0046] Table 1: Schematic Table of Initial Data of Coin Cell Discharge for Ternary Cathode Materials

[0047]

[0048] Initial structural data can be obtained by techniques such as X-ray diffraction (XRD) and scanning electron microscopy (SEM) to obtain initial structural information such as the crystal structure and morphology of the material. Optional but not limited to including: specific surface area, tapped density, compression density, content of each component, such as any one or more of moisture, residual alkali, Li content, Ni / Co / Mn content, impurities, etc., as shown in Tables 2 and 3.

[0049] Table 2: Schematic Table of Initial Structural Data of Ternary Cathode Materials

[0050]

[0051] Table 3: Schematic Table of Initial Structural Data of Ternary Cathode Materials

[0052]

[0053] S2: Obtain charge-discharge curves for N cycle periods;

[0054] Specifically, it can be selected to conduct charge-discharge cycle tests for a period of time under the condition of 25 degrees, and record the coin cell discharge cycle data after each cycle period, that is, the charge-discharge curves. By way of example, taking 20 charge-discharge cycles as an example, record its charge-discharge curves for each cycle period, that is: the charge-discharge curve with specific capacity on the horizontal axis and voltage on the vertical axis, as shown in the example Figure 2 as shown

[0055] S3: Divide N cycle periods into M stages and obtain the structural change data after each stage of cycling;

[0056] Specifically, taking the above-mentioned 20 cycles as an example, they can be divided into 4 stages on average. After 5, 10, 15 and 20 cycles respectively, high-resolution surface morphology images of the battery material are obtained by scanning electron microscopy, and the structural change data are observed and obtained, which may include but are not limited to: particle size, morphology, distribution, surface roughness, lithium-nickel mixing data, layered structure damage, the appearance of microcracks or cracks, etc. Examples: 1. Particle size, initial state: the average particle size is 5 μm, and the distribution is uniform; after 10 cycles: the particle size increases to 8 μm, and some particles agglomerate; more preferably, the agglomeration ratio can also be statistically analyzed; 2. Morphology, initial state: the particle surface is smooth and has a regular polyhedral shape; after cycling: corrosion, depressions or holes appear on the particle surface, and the morphology becomes irregular; 3. Distribution, initial state: the particles are evenly distributed in the electrode without obvious agglomeration; after cycling: the particle distribution is uneven, and local agglomeration or voids appear; 4. Surface roughness, initial state: the surface roughness (Ra) is 50 nm; after cycling: the surface roughness increases to 200 nm, and the surface becomes rough; 5. Lithium-nickel mixing data, initial state: the lithium-nickel mixing degree is low, and the proportion of nickel ions in the lithium layer is 2%; after cycling: the lithium-nickel mixing degree increases, and the proportion of nickel ions in the lithium layer increases to 10%; 6. Destruction of layered structure, initial state: the material has a complete layered structure, and the (003) peak is obvious in the XRD spectrum; after cycling: the layered structure is partially destroyed, the (003) peak intensity weakens, and a spinel phase or a rock salt phase appears; 7. The appearance of microcracks or cracks, initial state: the particles are intact and have no cracks; after cycling: microcracks appear inside and on the surface of the particles, and the crack width is 100 nm, etc.

[0057] More preferably, since the structural change characteristics of the ternary positive electrode material are more obvious in the early stage and the subsequent changes are smaller, it is possible to divide the N cycles into M stages in an increasing interval. For example, taking the above 20 cycles as an example, it is divided into 3 stages, and the structural change data are observed and obtained after 5, 12, and 20 cycles, that is, the structural change data are obtained at intervals of 5, 7, and 8 times, respectively.

[0058] It is worth noting that the number of cycles, specific intervals, etc., can be set arbitrarily by those skilled in the art. The present invention is subsequently described using historical cycle = 20 times and predicted cycle = 50 times as an example, but is not limited thereto. In the actual detection process, the charge and discharge curves after hundreds or even thousands of cycles can be predicted.

[0059] S4: Predict the charge-discharge curve of the next cycle based on the initial data of the coin cell, the initial structure data, the charge-discharge curves of N cycle periods, and the structural change data after each stage of cycling.

[0060] Specifically, in step S4, it is optional but not limited to using machine learning, statistics, etc. to make predictions based on historical data. Preferably, a neural network model can be used to construct and train a prediction model with the initial data of the coin cell, the initial structure data, the charge-discharge curves of N cycle periods, and the structural change data after each stage of cycling as the input and the charge-discharge curve after the next cycle as the output, extract relevant features, and establish intricate connections between the input and output to obtain the prediction result. More specifically, step S4 may optionally include two steps: model construction and training.

[0061] S41: Model construction, which can use any model of the neural network.

[0062] Preferably, the prediction model includes:

[0063] A: Input module, including 2 channels;

[0064] A1: The first channel is used to input the initial data of the coin cell, the initial structure data, and the structural change data after each stage of cycling. These data can be organized into a three-dimensional matrix containing the initial state of the material and the structural change data after cycling.

[0065] A2: The second channel is used to input the charge-discharge curves of N cycle periods. These data can be organized into time series data to record the performance changes of the battery during cycling.

[0066] B: Feature extraction module, including:

[0067] B1: The first feature extraction unit, connected to the first channel, is used to analyze the three-dimensional matrix information according to the initial data of the coin cell, the initial structure data, and the structural change data after cycling, and extract data features.

[0068] Specifically, considering that the initial data of the coin cell, the initial structure data, and the structural change data after cycling are all local features, the first feature extraction unit may optionally use a convolutional neural network (CNN) to utilize its powerful local feature extraction ability to extract features from the initial data and the structural change data. It can be designed based on PyTorch as an example, including multiple convolutional layers and pooling layers; for example, the convolutional layer is used to implement forward propagation and extract multi-size features of the three-dimensional matrix; taking one convolutional layer as an example, the number of input channels can be 3, the number of output channels can be 64, the kernel size can be 3, the stride can be 1, the padding can be 1, the dilation can be 1, the number of groups can be 1, and a bias can be added; the pooling layer is used to return multi-size features.

[0069] B2: The second feature extraction unit, connected to the second channel, is used to analyze the capacity retention rate, charge mid-voltage, and discharge mid-voltage according to the charge-discharge curves of N cycle periods, and extract curve features;

[0070] Specifically, considering that the charge-discharge curves of N cycle periods are charge-discharge cycle data within a period of time and have time series characteristics. The second feature extraction unit preferably uses a recurrent neural network RNN and its variants, such as long short-term memory network LSTM and gated recurrent unit GRU. Preferably, the construction of the second feature extraction unit includes:

[0071] First, the input data of the second channel needs to be preprocessed into a shape suitable for LSTM input:

[0072] # Assume input_data2 is the input data of the second channel, with the shape (batch_size, sequence_length, input_size)

[0073] # input_size is the number of features at each time step

[0074] features = FeatureExtractionUnit2(input_size=10, hidden_size=64) # Adjust input_size and hidden_size according to the actual number of features

[0075] extracted_features = features(input_data2)

[0076] Then, based on LSTM, construct the second feature extraction unit:

[0077] import torch

[0078] import torch.nn as nn

[0079] class FeatureExtractionUnit2(nn.Module):

[0080] def __init__(self, input_size, hidden_size, num_layers=1):

[0081] super(FeatureExtractionUnit2, self).__init__()

[0082] self.lstm = nn.LSTM(input_size, hidden_size, num_layers,batch_first=True)

[0083] def forward(self, x):

[0084] # The shape of x is (batch_size, sequence_length, input_size)

[0085] # Initialize the hidden state and cell state

[0086] h0 = torch.zeros(self.lstm.num_layers, x.size(0), self.lstm.hidden_size).to(x.device)

[0087] c0 = torch.zeros(self.lstm.num_layers, x.size(0), self.lstm.hidden_size).to(x.device)

[0088] # Forward propagate through the LSTM

[0089] out, _ = self.lstm(x, (h0, c0))

[0090] # Optionally return the output of the last time step or all outputs

[0091] return out[:, -1, :] # Return the output of the last time step

[0092] C: The prediction module, connected to the feature extraction module, is used to predict the charge and discharge curve of the next cycle based on the data features and curve features;

[0093] Specifically, the prediction module includes 2 fully connected layers and an activation function located between the 2 fully connected layers; The first fully connected layer is used to fuse the data features and curve features, merge the features in the feature dimension; And through the activation function, the second fully connected layer outputs the prediction result. Specifically:

[0094] import torch

[0095] import torch.nn as nn

[0096] class PredictionUnit(nn.Module):

[0097] def __init__(self, feature_dim1, feature_dim2, output_dim):

[0098] super(PredictionUnit, self).__init__()

[0099] # Assume feature_dim1 and feature_dim2 are the feature dimensions output by two feature extraction modules respectively

[0100] # output_dim is the dimension of the prediction result. The prediction is the charge-discharge curve, which is the number of points on the curve

[0101] self.fc1 = nn.Linear(feature_dim1 + feature_dim2, 128) # The first fully connected layer

[0102] self.relu = nn.ReLU()

[0103] self.fc2 = nn.Linear(128, output_dim) # The final output layer

[0104] def forward(self, x1, x2):

[0105] # x1 and x2 are the outputs of two feature extraction modules

[0106] combined_features = torch.cat((x1, x2), dim=1) # Combine features along the feature dimension

[0107] x = self.fc1(combined_features) # Pass through the first fully connected layer

[0108] x = self.relu(x) # Activation function

[0109] x = self.fc2(x) # Pass through the second fully connected layer and output the prediction result

[0110] return x

[0111] S42: Training stage:

[0112] Obtain the initial data of the coin cell discharge, the initial structural data, the charge-discharge curves of 50 cycle periods, and the structural change data after 5, 12, and 20 cycle periods for several ternary cathode materials;

[0113] Input the initial coin cell data, initial structure data, charge-discharge curves for the first 20 cycle periods, and structure change data after 5, 12, and 20 cycle periods of each ternary cathode material into the prediction model constructed in step S41 to output the charge-discharge curve for the next cycle period. Use the charge-discharge data for the subsequent 30 cycle periods as the validation dataset to perform regression validation on the charge-discharge curve predicted by the model, so as to modify the various parameters of the prediction model and obtain the trained prediction model. When conducting specific detections in the future, the initial coin cell data, initial structure data, charge-discharge curves for N cycle periods, and structure change data after each stage of cycling of the current ternary cathode material can be collected, so as to predict and output the charge-discharge curve for the next cycle period through the trained prediction model, as shown in Figure 3 Tables 4 and 5.

[0114] Table 4 Charge-discharge data for several cycle periods 1

[0115]

[0116] Table 5 Charge-discharge data for several cycle periods 2

[0117]

[0118] S5: Determine the number of cycle periods, iteratively perform step S4 to predict the charge-discharge curve for the next period of time, and determine the capacity retention rate after the set number of cycle periods to obtain the quality test result. Specifically, through the predicted charge-discharge curve, obtain the discharge specific capacity, calculate its ratio to the initial value, and determine the capacity retention rate after the set number of cycle periods, as shown in Table 6.

[0119] Table 6: Prediction results of capacity retention rate

[0120]

[0121] Specifically, the number of cycle periods can be determined according to actual quality requirements, such as the specific field to which the ternary cathode material applies. For general factory requirements, the number of cycle periods can be set to 200 times; for high-standard industries, the number of cycle periods can be determined to be several hundred or even thousands of times. Iteratively perform step S4 until after the set number of cycle periods, and calculate the final capacity retention rate. If the predicted capacity retention rate is higher than a certain threshold, such as 80%, it is considered that the material has good cycle stability and qualified quality. If the predicted capacity retention rate is lower than the threshold, it is considered that the material does not have good cycle stability and unqualified quality. It can be eliminated, or the trial use requirements can be reduced. It can also be further modified or optimized according to the quality inspection pass rate of batch products, etc., to improve its cycle stability and electrochemical performance.

[0122] On the other hand, the present invention also provides a computer storage medium storing executable program code; the executable program code is used to execute any of the above quality testing methods.

[0123] On the other hand, the present invention also provides a terminal device including a memory and a processor; the memory stores program code executable by the processor; the program code is used to execute any of the above quality testing methods.

[0124] Exemplarily, the program code can be split into one or more modules / units, and the one or more modules / units are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units can be a series of computer program instruction segments capable of performing specific functions, and these instruction segments are used to describe the execution process of the program code in the terminal device.

[0125] The terminal device can be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The terminal device may include, but is not limited to, a processor and a memory. Those skilled in the art can understand that the terminal device may further include input / output devices, network access devices, a bus, etc.

[0126] The processor may be a Central Processing Unit (CPU), or may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0127] The memory may be an internal storage unit of the terminal device, such as a hard disk or memory. The memory may also be an external storage device of the terminal device, such as a plug-in hard disk, a SmartMedia Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. equipped on the terminal device. Further, the memory may also include both the internal storage unit and the external storage device of the terminal device. The memory is used to store the program code and other programs and data required by the terminal device. The memory may also be used to temporarily store data that has been output or will be output.

[0128] The above computer storage medium and terminal device are created based on the above quality testing method, and their technical functions and beneficial effects will not be elaborated here. The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.

[0129] The above embodiments only represent several implementation manners of the present invention, and the description thereof is relatively specific and detailed, but it should not be understood as a limitation to the scope of the invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the present invention patent shall be subject to the appended claims.

Claims

1. A quality testing method for a ternary cathode material, characterized in that Including: S1: Obtain the initial data of coin cell charge-discharge and the initial data of the structure; The initial data of coin cell charge-discharge includes any one or more of the first efficiency, charge-discharge capacities at different powers, and the first charge-discharge capacity; the initial data of the structure includes any one or more of the specific surface area, tap density, compression density, and the content of each component; S2: Obtain the charge-discharge curves of N cycle periods; S3: Divide the N cycle periods into M stages, and obtain the structure change data after each stage of cycling; N and M are integers greater than 1, and N is greater than M; the structure change data includes any one or more of the particle size, morphology, distribution, surface roughness, lithium-nickel mixing data, layered structure damage, and crack condition; S4: Predict the charge-discharge curve of the next cycle period based on the initial data of coin cell charge-discharge, the initial data of the structure, the charge-discharge curves of N cycle periods, and the structure change data after each stage of cycling; including: constructing and training a prediction model with the initial data of coin cell charge-discharge, the initial data of the structure, the charge-discharge curves of N cycle periods, and the structure change data after each stage of cycling as inputs, and the charge-discharge curve after the next cycle period as the output; the constructed prediction model includes: An input module, including 2 channels; the first channel is used to input the initial data of coin cell charge-discharge, the initial data of the structure, and the structure change data after each stage of cycling; the second channel is used to input the charge-discharge curves of N cycle periods; A feature extraction module, including: a first feature extraction unit, connected to the first channel, for analyzing the three-dimensional matrix information according to the initial data of coin cell charge-discharge, the initial data of the structure, and the structure change data after cycling, and extracting data features; a second feature extraction unit, connected to the second channel, for analyzing the capacity retention rate, charging mid-voltage, and discharging mid-voltage according to the charge-discharge curves of N cycle periods, and extracting curve features; A prediction module, connected to the feature extraction module, for predicting the charge-discharge curve of the next cycle period according to the data features and the curve features; S5: Determine the number of cycle periods, iteratively perform step S4, predict the charge-discharge curve of the next period of time, determine the capacity retention rate after a set number of cycle periods, and obtain the quality test result.

2. The quality testing method according to claim 1, characterized in that The first feature extraction unit includes multiple convolutional layers and pooling layers; The convolutional layer is used to implement forward propagation, extract multi-size features of the three-dimensional matrix, with the number of input channels being 3, the number of output channels being 64, the convolutional kernel size being 3, the stride being 1, the padding being 1, the dilation being 1, the number of groups being 1, and adding a bias; the pooling layer is used to return the multi-size features.

3. The quality testing method according to claim 2, characterized in that The prediction module includes 2 fully connected layers and an activation function located between the 2 fully connected layers; the first fully connected layer is used to fuse the data features and the curve features and merge the features in the feature dimension; And through the activation function, the second fully connected layer outputs the prediction result.

4. The quality testing method according to claim 1, characterized in that, The steps for training the prediction model include: Obtain the initial data of coin cell charge-discharge, the initial data of the structure, the charge-discharge curves of 50 cycle periods, and the structure change data after 5, 12, and 20 cycle periods for several ternary cathode materials; Input the initial coin cell data, initial structure data, charge-discharge curves for the first 20 cycle periods, and structure change data after 5, 12, and 20 cycle periods of each ternary cathode material into the prediction model to output the charge-discharge curve for the next cycle period. Use the charge-discharge data for the subsequent 30 cycle periods as the validation dataset to perform regression validation on the charge-discharge curve predicted by the model, so as to modify the various parameters of the prediction model and obtain the trained prediction model.

5. The quality testing method according to claim 1, characterized in that, When dividing the N cycle periods into M stages, divide them in a way that the intervals increase.

6. The quality testing method according to any one of claims 1-5, characterized in that The initial coin cell data includes: the first efficiency and charge-discharge capacities at different rates. The initial structure data includes Ni, Co, Mn, impurity content, and tap density. The structure change data includes any one or more of: particle size, morphology, distribution, surface roughness, lithium-nickel mixing data, whether the layered structure is damaged, and whether microcracks appear.

7. A computer storage medium, characterized in that, Stores executable program code; the executable program code is used to execute the quality testing method described in any one of claims 1-6.

8. A terminal device, characterized in that, Includes a memory and a processor; the memory stores program code executable by the processor; the program code is used to execute the quality testing method described in any one of claims 1-6.

Images