Methods, apparatus, and non-volatile storage media for determining welding parameters

Abstract

This invention discloses a method, apparatus, and non-volatile storage medium for determining welding parameters. The method includes: acquiring material data of a battery cell to be welded, wherein the material data characterizes the structure and performance of the battery cell; inputting the material data into a pre-trained neural network model, and having the neural network model output the welding parameters of the battery cell to be welded, wherein the neural network model is obtained by training an original neural network model using training samples, including sample material data and sample welding parameters of sample battery cells. This invention solves the technical problem of low efficiency in methods for determining welding parameters used when welding the tabs of a battery cell.

Description

Technical Field

[0001] This invention relates to the field of battery manufacturing technology, and more specifically, to a method, apparatus, and non-volatile storage medium for determining welding parameters. Background Technology

[0002] With the development of next-generation information technologies such as 5G, cloud computing, and big data, and the widespread application of new devices such as electric vehicles, smart terminals, and drones, the battery industry has experienced explosive growth. The development of battery technology is driving innovation in battery cells and batteries themselves. The battery cell is the basic building block of a battery, and its energy transfer is crucial.

[0003] Currently, to meet the demands of the rapid development of new energy vehicles, the energy density of next-generation batteries needs to be further improved. The energy density and power density of next-generation batteries are far higher than those of traditional batteries, and the cell welding process has a significant impact on both energy density and power density.

[0004] In welding processes, the selection of welding parameters is directly proportional to the welding quality. Whether the welding parameters are chosen appropriately directly affects the welding quality, efficiency, and cost. However, the selection of welding parameters relies heavily on the experience of the welding operator; different operators will choose different parameters, resulting in varying welding quality. Ultrasonic welding utilizes the high-frequency vibration energy of ultrasound to weld the electrode tabs of a battery cell. However, the selection of welding parameters needs to be based on the material data of the battery cell and determined experimentally. This requires significant manpower and resources, reducing welding efficiency and increasing welding costs.

[0005] There is currently no effective solution to the above problems. Summary of the Invention

[0006] This invention provides a method, apparatus, and non-volatile storage medium for determining welding parameters, thereby addressing the technical problem of low efficiency in methods for determining welding parameters used when welding tabs to battery cells.

[0007] According to one aspect of the present invention, a method for determining welding parameters is provided, comprising: acquiring material data of a battery cell to be welded, wherein the material data characterizes the structure and performance of the battery cell to be welded; inputting the material data into a pre-trained neural network model, and outputting welding parameters of the battery cell to be welded by the neural network model, wherein the neural network model is obtained by training an original neural network model with training samples, the training samples including sample material data and sample welding parameters of sample battery cells. This embodiment achieves real-time prediction and adjustment of welding process parameters by directly inputting material data into the neural network model. This significantly reduces reliance on human experience, improves the automation level and response speed of the battery cell production line, and makes the battery cell manufacturing process more efficient and flexible.

[0008] Optionally, material data is input into a pre-trained neural network model, which outputs welding parameters for the battery cell to be welded. This includes: inputting material data into convolutional network units within the neural network model, whereby the convolutional network units extract material features from the material data, wherein the material features characterize the material properties of the battery cell to be welded; and inputting the material features into long short-term memory network units within the neural network model, whereby the long short-term memory network units output welding parameters. This optional embodiment, through a combination of convolutional neural networks and long short-term memory networks, generates a neural network model capable of outputting the optimal combination of welding parameters to meet the welding requirements of specific battery cell materials. This parameter optimization, based on autonomous learning and adjustment using deep learning algorithms, can automatically adapt to subtle differences in materials, ensuring consistency and high quality in the welding process and reducing welding defects and production delays caused by improper parameter settings.

[0009] Optionally, the neural network model is trained as follows: training samples are input into the original neural network model, and the parameters of the original neural network model are adjusted according to a predetermined loss function; the neural network model is determined based on the parameters that make the loss function meet predetermined conditions. This optional embodiment optimizes welding parameter prediction by training a neural network model, which not only improves the prediction accuracy and stability of the model, but also significantly reduces production costs and increases production efficiency, providing strong technical support for the intelligent and efficient production of the battery cell manufacturing industry.

[0010] Optionally, training samples are input into the original neural network model, and the parameters of the original neural network model are adjusted according to a pre-determined loss function. This includes: inputting sample material data into the original neural network model, which then determines the predicted welding parameters; determining the value of the loss function based on the predicted welding parameters and the sample welding parameters; and adjusting the parameters of the original neural network model using a backpropagation algorithm based on the value of the loss function. This optional embodiment, by inputting training samples into the original neural network model and adjusting the model parameters through a loss function and a backpropagation algorithm, can significantly improve the accuracy and reliability of welding parameter prediction, reduce production costs, and enhance the controllability and consistency of the welding process, thereby promoting the intelligent transformation and efficiency improvement of the battery cell manufacturing industry.

[0011] Optionally, a backpropagation algorithm is employed to adjust the parameters of the original neural network model based on the value of the loss function, including: determining the gradient of the loss function; and an adaptive moment estimation algorithm is employed to adjust the parameters of the original neural network model based on the gradient of the loss function. This optional embodiment uses backpropagation and adaptive moment estimation algorithms to adjust the neural network model parameters, which can significantly improve the training efficiency and prediction accuracy of the model, reduce the risk of overfitting, and accelerate model convergence, providing the battery cell manufacturing industry with a more intelligent, efficient, and reliable welding parameter prediction solution.

[0012] Optionally, the material data includes at least one of the following: the number of tab layers, foil thickness, and weld depth, wherein the number of tab layers refers to the number of metal foil layers included in the tab of the battery cell to be welded, the foil thickness refers to the thickness of the metal foil forming the tab of the battery cell to be welded, and the weld depth refers to the depth of the weld lines to be formed on the tab of the battery cell to be welded. This optional embodiment uses the number of tab layers, foil thickness, and weld depth as material data to provide specific structural and performance information of the battery cell tabs. By learning the correlation between these data and welding parameters, the neural network model can accurately output welding parameters that match the battery cell material characteristics. This means that tabs with different numbers of layers, thicknesses, and weld depth requirements can obtain customized welding parameters, ensuring consistency in welding quality and battery cell performance.

[0013] According to another aspect of the present invention, a device for determining welding parameters is also provided, comprising: an acquisition module for acquiring material data of a battery cell to be welded, wherein the material data characterizes the structure and performance of the battery cell to be welded; and a determination module for inputting the material data into a pre-trained neural network model, wherein the neural network model is obtained by training an original neural network model with training samples, the training samples including sample material data and sample welding parameters of sample battery cells.

[0014] According to another aspect of the present invention, a non-volatile storage medium is also provided, the non-volatile storage medium including a stored program, wherein, when the program is running, the device where the non-volatile storage medium is located is controlled to execute any of the above-described methods for determining welding parameters.

[0015] According to another aspect of the present invention, a computer device is also provided, the computer device including a processor, the processor being configured to run a program, wherein the program, when running, executes any of the above-described methods for determining welding parameters.

[0016] According to another aspect of the present invention, a computer program product is also provided, including a computer program that, when executed by a processor, implements the method for determining any of the welding parameters described above.

[0017] In this embodiment of the invention, material data of the battery cell to be welded is obtained, wherein the material data characterizes the structure and performance of the battery cell to be welded; the material data is input into a pre-trained neural network model, and the neural network model outputs the welding parameters of the battery cell to be welded. The neural network model is obtained by training the original neural network model with training samples, including sample material data and sample welding parameters of sample battery cells. This achieves the goal of accurately predicting the optimal welding parameters based on the material data of the battery cell, greatly improving the efficiency and quality of the welding process, and thus solving the technical problem of low efficiency in the method of determining the welding parameters used for welding the tabs of the battery cell. Attached Figure Description

[0018] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0019] Figure 1 A hardware block diagram of a computer terminal for implementing a method for determining welding parameters is shown.

[0020] Figure 2 This is a flowchart illustrating a method for determining welding parameters according to an embodiment of the present invention.

[0021] Figure 3 This is a schematic diagram of the structure of a neural network model provided in an optional embodiment of the present invention;

[0022] Figure 4 This is a schematic diagram of the welding parameter prediction process provided by an optional embodiment of the present invention;

[0023] Figure 5 This is a structural block diagram of a welding parameter determination device provided according to an embodiment of the present invention. Detailed Implementation

[0024] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0025] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0026] According to an embodiment of the present invention, a method embodiment for determining welding parameters is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0027] The method embodiment provided in Embodiment 1 of this application can be executed on a mobile terminal, computer terminal, or similar computing device. Figure 1 A hardware block diagram of a computer terminal for implementing a method for determining welding parameters is shown. Figure 1 As shown, the computer terminal 10 may include one or more processors (shown as 102a, 102b, ..., 102n in the figure) (the processor may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of a BUS bus), a network interface, a power supply, and / or a camera. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, computer terminal 10 may also include... Figure 1The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0028] It should be noted that the aforementioned one or more processors and / or other data processing circuits are generally referred to herein as "data processing circuits". These data processing circuits may be implemented wholly or partially as software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuits may be a single, independent processing module, or may be wholly or partially integrated into any other element in the computer terminal 10. As involved in the embodiments of this application, the data processing circuits serve as processor control (e.g., selection of a variable resistor termination path connected to an interface).

[0029] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the welding parameter determination method in this embodiment of the invention. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory 104, thereby realizing the welding parameter determination method of the aforementioned application. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor, and these remote memories can be connected to the computer terminal 10 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0030] The display may be, for example, a touchscreen liquid crystal display (LCD) that allows the user to interact with the user interface of the computer terminal 10.

[0031] The tabs of a battery cell are metal pieces or wires that connect the positive and negative electrode materials in batteries such as lithium batteries. Tabs are typically located at both ends of the battery and are used to connect the positive and negative terminals, thus connecting the battery to an external circuit. The design and connection method of the tabs have a significant impact on the battery's performance and safety. To connect the positive and negative terminals of the battery to form a complete circuit, the tabs of the battery cell need to be soldered.

[0032] Ultrasonic welding of the electrode tabs is a critical step in the battery cell manufacturing process, and the quality of the welding affects the cell's performance, safety, and production costs. Good welding quality ensures stable cell performance, improves the vibration and impact resistance of the weld joint, and enhances the cell's safety. Conversely, poor welding quality may lead to cell malfunctions during use, reducing product safety and increasing the cost of subsequent repairs or recalls.

[0033] The setting of ultrasonic welding parameters is crucial to the welding of electrode tabs. These parameters determine the heating, pressing, and vibration of the material during welding, thus affecting welding quality and efficiency. Increasing the energy parameter accelerates material softening and flow during welding, improving weld strength; however, excessive energy can lead to overheating of the welding area, requiring careful energy control. Appropriate pressure parameters ensure a tight fit between the welded surfaces, improving weld strength, while excessively high or low pressure can negatively impact welding quality and efficiency. Amplitude parameters affect the vibration intensity and frequency of the welding area; appropriate amplitude improves weld strength and sealing, but excessively high or low amplitude can result in poor welding performance. Therefore, the selection of ultrasonic welding parameters must be based on a comprehensive consideration of factors such as the welding material, shape, and process requirements, and appropriate adjustments and control are necessary to ensure a stable and efficient welding process and achieve good weld quality.

[0034] Traditional ultrasonic welding parameter selection requires finding optimal values ​​through multiple welding experiments. Its drawback is that these experiments are time-consuming and resource-intensive. Furthermore, traditional methods typically only find the optimal parameters among preset values; manual parameter setting has limitations and cannot guarantee that the preset parameters include the optimal ones.

[0035] To address the above problems, this invention provides a method for determining welding parameters. Figure 2 This is a flowchart illustrating a method for determining welding parameters according to an embodiment of the present invention, as shown below. Figure 2 As shown, the method includes the following steps:

[0036] Step S202: Obtain material data of the battery cell to be welded, wherein the material data characterizes the structure and performance of the battery cell to be welded.

[0037] In this step, the battery cell to be welded is the one whose welding parameters need to be determined. The material data can be data that characterizes the properties of the electrode material of the battery cell, reflecting the actual situation of the electrode material, so as to determine more suitable welding parameters.

[0038] As an optional embodiment, the material data includes at least one of the following: number of tab layers, foil thickness, and solder depth, wherein the number of tab layers is the number of metal foil layers included in the tab of the battery cell to be welded, the foil thickness is the thickness of the metal foil constituting the tab of the battery cell to be welded, and the solder depth is the depth of the solder lines to be formed on the tab of the battery cell to be welded.

[0039] Optionally, material data may include the number of tab layers, foil thickness, and weld depth; correspondingly, welding parameters may include welding energy, pressure, and amplitude. By adjusting the energy, pressure, and amplitude of the welding machine, it can be ensured that the tabs of battery cells with different numbers of tab layers and foil thicknesses can achieve the ideal weld depth, thereby guaranteeing the strength of the weld and the performance of the battery cell.

[0040] The number of tab layers refers to the number of layers in the battery cell's tabs (usually the conductive material of the positive or negative electrode). In battery cell manufacturing, tabs are typically made of multiple layers of thin metal foil stacked together to increase the conductive area and mechanical strength. The more tab layers there are, the greater the welding energy required to ensure all layers are fully fused. Increasing the number of layers also leads to an increase in tab thickness, thus requiring greater pressure to ensure a strong weld. Increasing the number of layers may affect vibration transmission, so amplitude adjustments may be necessary to ensure optimal welding results.

[0041] Foil thickness refers to the thickness of the metal foil that makes up the tab. Foil thickness directly affects the mechanical strength and electrical conductivity of the tab. The thicker the foil, the greater the welding energy required to penetrate the thicker metal layer and achieve good fusion. Increased thickness can lead to uneven pressure distribution in the welding area, thus requiring greater pressure to ensure uniform welding. Increased foil thickness may also affect vibration transmission, necessitating amplitude adjustment to ensure optimal welding results.

[0042] Weld depth refers to the depth of the weld mark formed on the electrode lug after welding. Weld depth is an important indicator of weld quality, and a certain standard is typically required to ensure weld strength. Higher weld depth requirements necessitate greater welding energy to ensure the weld reaches the desired standard. Higher weld depth requirements also require greater welding pressure to ensure complete fusion of the metal in the weld area. Furthermore, higher weld depth requirements may necessitate adjustments to the welding amplitude to ensure sufficient fusion of the metal and proper weld mark formation during the welding process.

[0043] This optional embodiment uses material data such as the number of tab layers, foil thickness, and solder depth to provide specific structural and performance information of the battery cell tabs. By learning the correlation between these data and welding parameters, the neural network model can accurately output welding parameters that match the battery cell material characteristics. This means that tabs with different layer numbers, thicknesses, and solder depth requirements can obtain customized welding parameters, ensuring consistency in welding quality and battery cell performance.

[0044] Step S204: Input the material data into the pre-trained neural network model, and output the welding parameters of the battery cell to be welded by the neural network model. The neural network model is obtained by training the original neural network model with training samples, which include sample material data and sample welding parameters of the sample battery cell.

[0045] In this step, material data can be directly input into a pre-trained neural network model to automatically acquire welding parameters, enabling real-time prediction and adjustment of welding process parameters. The neural network model can be trained using a large number of training samples, including sample material data from numerous sample battery cells and optimal sample welding parameters determined during the welding of these cells. Using a neural network model to predict welding parameters significantly reduces reliance on human experience, improves the automation level and response speed of the battery cell production line, and makes the battery cell manufacturing process more efficient and flexible.

[0046] As an optional embodiment, the material data is input into a pre-trained neural network model, and the neural network model outputs welding parameters for the battery cell to be welded. This includes: inputting the material data into the convolutional network units included in the neural network model, and having the convolutional network units extract material features from the material data, wherein the material features characterize the material properties of the battery cell to be welded; inputting the material features into the long short-term memory network units included in the neural network model, and having the long short-term memory network units output welding parameters.

[0047] Optionally, the neural network model provided in this optional embodiment can be a Convolutional-Long Short-Term Memory (CNN-LSTM) network model, that is, the neural network model is composed of a convolutional neural network and a long short-term memory network. Specifically, the model takes the number of tab layers, foil thickness, and solder depth of the battery cell as input data. First, it extracts the spatial features of the input data through a convolutional neural network (CNN). The convolutional and pooling layers of the CNN can identify and extract these important local features, which reflect the geometric characteristics of the battery cell tab material. Then, the extracted spatial features can be input into a long short-term memory (LSTM) network for processing. LSTM networks are good at processing sequential data and can capture temporal dependencies and sequence information, further modeling the dynamic changes of these features in the time dimension. In this way, the model can more comprehensively analyze and understand the input data, thereby more accurately predicting the parameters required for welding, including energy, pressure, and amplitude.

[0048] This optional embodiment utilizes a neural network model derived from a combination of convolutional neural networks and long short-term memory networks. This model outputs the optimal combination of welding parameters to meet the welding requirements of specific battery cell materials. This parameter optimization, based on autonomous learning and adjustment using deep learning algorithms, automatically adapts to subtle differences in materials, ensuring consistency and high quality in the welding process and reducing welding defects and production delays caused by improper parameter settings.

[0049] As an optional embodiment, the neural network model is trained in the following manner: training samples are input into the original neural network model, and the parameters of the original neural network model are adjusted according to a predetermined loss function; the neural network model is determined according to the parameters that make the loss function meet predetermined conditions.

[0050] Optionally, during model training, the internal parameters of the model can be adjusted according to the loss function, enabling the model to learn knowledge from the training samples. This optional embodiment uses mean squared error (MSE) as the loss function to measure the difference between the model's predicted values ​​and the actual values. MSE is a loss function commonly used in regression problems, suitable for situations where the model needs to predict continuous numerical values ​​rather than classification labels. Specifically, MSE calculates the average of the squares of the differences between the predicted and actual values, thus quantifying the magnitude of the prediction error and helping to optimize the model to minimize prediction error and improve prediction accuracy.

[0051]

[0052] Where n is the number of samples, y i Let be the predicted value for the i-th sample. This represents the actual value of the i-th sample.

[0053] Additionally, R can be set. 2 As a convergence criterion for the model, mean squared error is used to measure the difference between the model's predicted values ​​and the actual values, while R0 is used for convergence. 2 This assesses the model's ability to explain the data variance. In regression tasks, R... 2 Used as a metric to measure the goodness of fit of a model, its value ranges from 0 to 1, with values ​​closer to 1 indicating a better fit. R is introduced. 2 As a convergence criterion for the model, it can not only monitor the degree of fit of the model during the training process, but also help evaluate the model's predictive ability on the data, thereby further optimizing the model and ensuring that it has higher prediction accuracy and stability in practical applications.

[0054]

[0055] Among them, SS res This represents the sum of squared residuals, which is the sum of the squared differences between the model's predicted values ​​and the actual observed values. SS... tot The total sum of squares represents the sum of squares of the differences between the actual observed values ​​and the mean of the actual observed values.

[0056] This optional embodiment optimizes welding parameter prediction by training a neural network model, which not only improves the model's prediction accuracy and stability, but also significantly reduces production costs and increases production efficiency, providing strong technical support for intelligent and efficient production in the battery cell manufacturing industry.

[0057] As an optional embodiment, training samples are input into the original neural network model, and the parameters of the original neural network model are adjusted according to a predetermined loss function. This includes: inputting sample material data into the original neural network model, and the original neural network model determining the predicted welding parameters; the original neural network model determining the value of the loss function based on the predicted welding parameters and the sample welding parameters; and using a backpropagation algorithm to adjust the parameters of the original neural network model based on the value of the loss function.

[0058] Optionally, in this optional embodiment, the specific steps of training the original neural network model to predict welding parameters are as follows: First, training sample material data containing information such as the number of tab layers, foil thickness, and weld depth are input into the original neural network model. This data forms the basis for model training, used to learn the mapping relationship between different material properties and welding parameters. Then, based on the input material data, the original neural network model performs calculations using its internal parameters and outputs predicted welding parameters, such as energy, pressure, and amplitude. At this point, the model attempts to predict the optimal welding parameters for a given material property based on its current knowledge. The predicted welding parameters output by the model can then be compared with the actual welding parameters in the training samples, and the difference between the predicted value and the true value can be quantified using a loss function (e.g., mean squared error, MSE). The smaller the value of the loss function, the closer the model's prediction is to the actual value, and the better the model's performance.

[0059] Next, the backpropagation (BP) algorithm is used to adjust the model's parameters. The BP algorithm calculates the gradient of the loss function with respect to the model parameters, propagating the error backward from the output layer to the input layer, updating the model's weights and biases to minimize the loss function. This process is iterative; after each training sample passes through the model, the parameters are adjusted based on the calculated gradient, gradually optimizing the model's performance.

[0060] The above steps constitute a training loop, which the model repeats until the loss function reaches the preset convergence criterion or the training iterations are completed. This ensures that the model can continuously learn from the data and constantly improve the accuracy of predicting welding parameters.

[0061] This optional embodiment inputs training samples into the original neural network model and adjusts the model parameters through a loss function and backpropagation algorithm, which can significantly improve the accuracy and reliability of welding parameter prediction, reduce production costs, and enhance the controllability and consistency of the welding process, thereby promoting the intelligent transformation and efficiency improvement of the battery cell manufacturing industry.

[0062] As an optional embodiment, the backpropagation algorithm is used to adjust the parameters of the original neural network model based on the value of the loss function, including: determining the gradient of the loss function value; and using an adaptive moment estimation algorithm to adjust the parameters of the original neural network model based on the gradient of the loss function value.

[0063] Optionally, to address potential issues such as exponential parameter growth, overfitting, and slow training speed during model training, the following training methods can be employed to prevent these problems while improving model performance and training efficiency. For example, the Adaptive Moment Estimation Algorithm (Adam) can be used as the optimizer during the backpropagation algorithm training process. Adam combines the advantages of momentum optimization and adaptive learning rate, effectively updating network parameters and accelerating model convergence. The core principle of Adam is to consider both the first moment (mean) and second moment (variance) estimates of the gradient at each parameter update. Specifically, Adam uses an exponentially weighted moving average to estimate the first and second moments of the gradient and corrects for biases in these estimates.

[0064] Additionally, batch normalization (BN) can be used to process features, making their mean 0 and variance 1. This aims to accelerate neural network training and enhance the model's robustness and generalization ability. The main purpose of BN is to address the internal covariate shift problem in deep neural network training. This shift refers to the variation in the distribution of input data at each layer, making network learning more difficult. BN improves network stability by normalizing features in each batch of data, eliminating variations in the input data distribution.

[0065] As a specific embodiment, this invention proposes a CNN-LSTM model for predicting ultrasonic welding parameters of battery cell tabs, which significantly improves welding quality and production efficiency. Through real-time data processing and prediction optimization, it realizes the automation and precise control of the welding process, resulting in significant technological progress and economic benefits for battery manufacturing and related industries.

[0066] The CNN-LSTM model, trained on different datasets, can predict parameters across various scenarios. This model combines the feature extraction capabilities of Convolutional Neural Networks (CNNs) with the time-series analysis capabilities of Long Short-Term Memory Networks (LSTMs), effectively handling the complex data generated during battery cell manufacturing. By training on datasets from different scenarios, the model can learn the relationships between various manufacturing parameters, thereby predicting the optimal parameter combinations, optimizing the manufacturing process, and improving battery cell quality and performance. Whether it's welding, coating, winding, or drying, the CNN-LSTM model can analyze input data to predict the optimal parameters, ensuring the stability and consistency of the manufacturing process and ultimately improving the overall performance of the battery cell.

[0067] Figure 3 This is a schematic diagram of the structure of a neural network model provided by an optional embodiment of the present invention, such as... Figure 3 As shown, the CNN-LSTM model combines a Convolutional Neural Network (CNN) and a Long Short-Term Memory (LSTM) network to acquire prediction data. First, the data undergoes preprocessing and normalization to improve the computational speed and efficiency of the CNN network. The preprocessed data is then fed into the CNN network for feature extraction and analysis. Maxpool1D is a one-dimensional max pooling operation used to reduce the size of the input data and extract the most salient features. It achieves pooling by taking the maximum value at each sliding window of the input data. Flattening is the operation of converting a multi-dimensional array into a one-dimensional array, typically used to flatten the output of a convolutional or pooling layer into the input of a fully connected layer. The flattening operation preserves the order of the input data but rearranges it into a one-dimensional array. Flattening is usually performed between the convolutional and fully connected layers of a neural network. The extracted features are then input into the LSTM network, which outputs the prediction results.

[0068] Figure 4 This is a schematic diagram of the welding parameter prediction process provided by an optional embodiment of the present invention, such as... Figure 4 As shown, when predicting welding parameters, input data is first acquired, then fed into the welding parameter prediction model, which outputs the prediction results. The welding parameter prediction model is obtained by training a CNN-LSTM model with preprocessed sample data.

[0069] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that the present invention is not limited to the described order of actions, because according to the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to the present invention.

[0070] Through the above description of the embodiments, those skilled in the art can clearly understand that the method for determining welding parameters according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platform. Of course, it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0071] According to embodiments of the present invention, a welding parameter determination apparatus for implementing the above-described welding parameter determination method is also provided. Figure 5 This is a structural block diagram of a welding parameter determination device provided according to an embodiment of the present invention, such as... Figure 5 As shown, the device for determining welding parameters includes an acquisition module 52 and a determination module 54. The device for determining welding parameters will be described below.

[0072] The acquisition module 52 is used to acquire the material data of the battery cell to be welded, wherein the material data characterizes the structure and performance of the battery cell to be welded.

[0073] The determination module 54, connected to the acquisition module 52, is used to input material data into a pre-trained neural network model, and the neural network model outputs the welding parameters of the battery cell to be welded. The neural network model is obtained by training the original neural network model with training samples, which include sample material data and sample welding parameters of the sample battery cell.

[0074] It should be noted that the acquisition module 52 and the determination module 54 mentioned above correspond to steps S202 to S204 in the embodiments. Multiple modules implement the same instances and application scenarios as their corresponding steps, but are not limited to the content disclosed in the above embodiments. It should also be noted that the above modules, as part of the device, can run on the computer terminal 10 provided in the embodiments.

[0075] Embodiments of the present invention may provide a computer device. Optionally, in this embodiment, the computer device may be located in at least one of a plurality of network devices in a computer network. The computer device includes a memory and a processor.

[0076] The memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the welding parameter determination method and apparatus in this embodiment of the invention. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, thereby realizing the aforementioned welding parameter determination method. The memory may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include memory remotely located relative to the processor, and these remote memories can be connected to a computer terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0077] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: acquire the material data of the battery cell to be welded, wherein the material data characterizes the structure and performance of the battery cell to be welded; input the material data into a pre-trained neural network model, and output the welding parameters of the battery cell to be welded by the neural network model, wherein the neural network model is obtained by training the original neural network model through training samples, and the training samples include sample material data and sample welding parameters of sample battery cells.

[0078] Optionally, the processor may also execute program code for the following steps: inputting material data into a pre-trained neural network model and outputting welding parameters of the battery cell to be welded by the neural network model, including: inputting material data into convolutional network units included in the neural network model and extracting material features from the material data by the convolutional network units, wherein the material features characterize the material properties of the battery cell to be welded; inputting the material features into long short-term memory network units included in the neural network model and outputting welding parameters by the long short-term memory network units.

[0079] Optionally, the processor may also execute program code that performs the following steps: the neural network model is trained by inputting training samples into the original neural network model, adjusting the parameters of the original neural network model according to a predetermined loss function; and determining the neural network model based on the parameters that make the loss function meet predetermined conditions.

[0080] Optionally, the processor may also execute program code that performs the following steps: inputting training samples into the original neural network model, and adjusting the parameters of the original neural network model according to a predetermined loss function, including: inputting sample material data into the original neural network model, and determining the predicted welding parameters by the original neural network model; determining the value of the loss function by the original neural network model based on the predicted welding parameters and the sample welding parameters; and adjusting the parameters of the original neural network model based on the value of the loss function using a backpropagation algorithm.

[0081] Optionally, the processor may also execute program code that performs the following steps: using the backpropagation algorithm to adjust the parameters of the original neural network model based on the value of the loss function, including: determining the gradient of the loss function; and using the adaptive moment estimation algorithm to adjust the parameters of the original neural network model based on the gradient of the loss function.

[0082] Optionally, the processor may also execute program code for the following steps: the material data includes at least one of the following: number of tab layers, foil thickness, and solder depth, wherein the number of tab layers is the number of metal foil layers included in the tab of the battery cell to be welded, the foil thickness is the thickness of the metal foil constituting the tab of the battery cell to be welded, and the solder depth is the depth of the solder lines to be formed on the tab of the battery cell to be welded.

[0083] This invention provides a method for determining welding parameters. By acquiring material data of the battery cell to be welded, where the material data characterizes the structure and performance of the battery cell, and inputting the material data into a pre-trained neural network model, the neural network model outputs the welding parameters of the battery cell to be welded. The neural network model is obtained by training an original neural network model using training samples, including sample material data and sample welding parameters of sample battery cells. This achieves the goal of accurately predicting the optimal welding parameters based on the battery cell's material data, greatly improving the efficiency and quality of the welding process, and thus solving the technical problem of low efficiency in methods for determining welding parameters used when welding the tabs of battery cells.

[0084] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing the hardware related to the terminal device. The program can be stored in a non-volatile storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk, etc.

[0085] Embodiments of the present invention also provide a non-volatile storage medium. Optionally, in this embodiment, the aforementioned non-volatile storage medium can be used to store the program code executed by the method for determining welding parameters provided in the above embodiments.

[0086] Optionally, in this embodiment, the non-volatile storage medium may be located in any computer terminal in a group of computer terminals in a computer network, or in any mobile terminal in a group of mobile terminals.

[0087] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for performing the following steps: acquiring material data of the battery cell to be welded, wherein the material data characterizes the structure and performance of the battery cell to be welded; inputting the material data into a pre-trained neural network model, and outputting welding parameters of the battery cell to be welded by the neural network model, wherein the neural network model is obtained by training the original neural network model through training samples, and the training samples include sample material data and sample welding parameters of sample battery cells.

[0088] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for performing the following steps: inputting material data into a pre-trained neural network model, and outputting welding parameters of the battery cell to be welded by the neural network model, including: inputting material data into convolutional network units included in the neural network model, and extracting material features from the material data by the convolutional network units, wherein the material features characterize the material properties of the battery cell to be welded; inputting the material features into long short-term memory network units included in the neural network model, and outputting welding parameters by the long short-term memory network units.

[0089] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for performing the following steps: the neural network model is trained in the following manner: training samples are input into the original neural network model, and the parameters of the original neural network model are adjusted according to a predetermined loss function; the neural network model is determined according to the parameters that make the loss function meet predetermined conditions.

[0090] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for performing the following steps: inputting training samples into the original neural network model, and adjusting the parameters of the original neural network model according to a predetermined loss function, including: inputting sample material data into the original neural network model, and determining the predicted welding parameters by the original neural network model; determining the value of the loss function by the original neural network model based on the predicted welding parameters and the sample welding parameters; and adjusting the parameters of the original neural network model according to the value of the loss function using a backpropagation algorithm.

[0091] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for performing the following steps: using the backpropagation algorithm to adjust the parameters of the original neural network model according to the value of the loss function, including: determining the gradient of the value of the loss function; using the adaptive moment estimation algorithm to adjust the parameters of the original neural network model according to the gradient of the value of the loss function.

[0092] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for performing the following steps: the material data includes at least one of the following: the number of tab layers, the foil thickness, and the solder depth, wherein the number of tab layers is the number of metal foil layers included in the tab of the battery cell to be soldered, the foil thickness is the thickness of the metal foil constituting the tab of the battery cell to be soldered, and the solder depth is the depth of the solder lines to be formed on the tab of the battery cell to be soldered.

[0093] Embodiments of the present invention also provide a computer program product, including a computer program that, when executed by a processor, implements the steps of the welding parameter determination method in various embodiments of the present application.

[0094] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0095] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0096] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0097] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0098] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0099] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a non-volatile storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0100] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for determining welding parameters, characterized in that, include: Obtain material data of the battery cell to be welded, wherein the material data characterizes the structure and performance of the battery cell to be welded; The material data is input into a pre-trained neural network model, which outputs the welding parameters of the battery cell to be welded. The neural network model is obtained as follows: training samples are input into an original neural network model, which adjusts its parameters according to a predetermined loss function; the neural network model is determined based on parameters that make the loss function meet predetermined conditions. The training samples include sample material data and sample welding parameters of the sample battery cell. The neural network model is a convolutional long short-term memory network model. The step of inputting the material data into a pre-trained neural network model and having the neural network model output the welding parameters of the battery cell to be welded includes: taking the number of tab layers, foil thickness, and weld depth of the battery cell to be welded as input data, and extracting the spatial features of the input data through a convolutional neural network. The number of tab layers refers to the number of metal foil layers included in the tabs of the battery cell to be welded; the foil thickness refers to the thickness of the metal foil forming the tabs of the battery cell to be welded; and the weld depth refers to the depth of the weld lines to be formed on the tabs of the battery cell to be welded. The convolutional layers and pooling layers of the convolutional neural network are used to identify and extract the spatial features, which reflect the geometric characteristics of the battery cell tab material. The extracted spatial features are then input into a long short-term memory network for processing to capture temporal dependencies and sequence information, and the dynamic changes of the spatial features in the time dimension are modeled to obtain the welding parameters.

2. The method according to claim 1, characterized in that, The step of inputting the training samples into the original neural network model, and adjusting the parameters of the original neural network model according to a predetermined loss function, includes: The sample material data is input into the original neural network model, and the original neural network model determines the predicted welding parameters. The original neural network model determines the value of the loss function based on the predicted welding parameters and the sample welding parameters; The parameters of the original neural network model are adjusted based on the value of the loss function using the backpropagation algorithm.

3. The method according to claim 2, characterized in that, The backpropagation algorithm is used to adjust the parameters of the original neural network model based on the value of the loss function, including: Determine the gradient of the value of the loss function; An adaptive moment estimation algorithm is used to adjust the parameters of the original neural network model based on the gradient of the loss function.

4. A device for determining welding parameters, characterized in that, include: An acquisition module is used to acquire material data of the battery cell to be welded, wherein the material data characterizes the structure and performance of the battery cell to be welded; A determination module is used to input the material data into a pre-trained neural network model, and the neural network model outputs the welding parameters of the battery cell to be welded. The neural network model is obtained based on the following method: inputting training samples into an original neural network model, and adjusting the parameters of the original neural network model according to a pre-determined loss function; determining the neural network model based on parameters that make the loss function meet predetermined conditions. The training samples include sample material data and sample welding parameters of sample battery cells, and the neural network model is a convolutional long short-term memory network model. The determining module is further configured to take the number of tab layers, foil thickness, and weld depth of the battery cell to be welded as input data, and extract the spatial features of the input data through a convolutional neural network. The number of tab layers refers to the number of metal foil layers included in the tab of the battery cell to be welded; the foil thickness refers to the thickness of the metal foil constituting the tab of the battery cell to be welded; and the weld depth refers to the depth of the weld lines to be formed on the tab of the battery cell to be welded. The convolutional layers and pooling layers of the convolutional neural network are used to identify and extract the spatial features, which reflect the geometric characteristics of the battery cell tab material. The extracted spatial features are then input into a long short-term memory network for processing to capture temporal dependencies and sequence information, and the dynamic changes of the spatial features in the time dimension are modeled to obtain the welding parameters.

5. A non-volatile storage medium, characterized in that, The non-volatile storage medium includes a stored program, wherein, when the program is executed, the device containing the non-volatile storage medium is controlled to perform the method for determining welding parameters according to any one of claims 1 to 3.

6. A computer device, characterized in that, include: Memory and processor The memory stores computer programs; The processor is configured to execute a computer program stored in the memory, wherein when the computer program is executed, the processor performs the method for determining welding parameters according to any one of claims 1 to 3.

7. A computer program product comprising computer instructions, characterized in that, The computer instructions are executed by the processor to determine the welding parameters according to any one of claims 1 to 3.

Images