A battery EIS data enhancement method, device, medium and product

Abstract

The embodiments of the present application relate to the field of battery data processing technology, and disclose a battery EIS data enhancement method, device, medium and product. Test and collect original battery EIS data; train an autoencoder model to map the original battery EIS data to a low-dimensional latent space; use the encoder of the autoencoder model to convert the original battery EIS data into a latent space vector; based on the latent space vector, train a denoising diffusion probability model; use the trained denoising diffusion probability model to sample in the low-dimensional latent space, predict the sampled data, and obtain EIS latent space data; use the decoder of the autoencoder model to restore the EIS latent space data to enhanced battery EIS data. It can at least be used to solve the problem of insufficient battery EIS data collection.

Description

Technical Field

[0001] The present application relates to the field of battery data processing technology, and in particular to a battery EIS data enhancement method, device, medium and product. Background Art

[0002] Electrochemical Impedance Spectroscopy (EIS) is an analytical technique used to study electrochemical systems. It analyzes the resistance and capacitance of electrochemical processes by applying an alternating current signal to the system and measuring the response. This technique can be widely used in many fields, including batteries, corrosion research, sensors, coating evaluation, and bioelectrochemistry.

[0003] Battery EIS data is based on obtaining information by frequency scanning the response of an AC signal in an electrochemical system. In the experiment, by applying a small amplitude AC signal within a certain frequency range and then measuring the system's response (usually current and voltage), information such as resistance, capacitance, and electrochemical reaction kinetics can be obtained.

[0004] In general, electrochemical impedance spectroscopy is a powerful tool that can provide in-depth understanding and evaluation of electrochemical systems. However, since obtaining battery EIS data relies on expensive specialized equipment, the amount of data available is usually limited, which may affect the generalization ability and robustness of the EIS model used and increase the risk of overfitting. Summary of the invention

[0005] One purpose of the present application is to provide a battery EIS data enhancement method, device, medium and product, at least to solve the problem of insufficient battery EIS data collection.

[0006] To achieve the above objectives, some embodiments of the present application provide the following aspects:

[0007] In a first aspect, some embodiments of the present application provide a battery EIS data enhancement method, including: testing and collecting original battery EIS data; training an autoencoder model to map the original battery EIS data to a low-dimensional latent space; using the encoder of the autoencoder model to convert the original battery EIS data into a latent space vector; based on the latent space vector, training a denoising diffusion probability model; using the trained denoising diffusion probability model to sample in the low-dimensional latent space, predicting the sampled data to obtain EIS latent space data; using the decoder of the autoencoder model to restore the EIS latent space data to enhanced battery EIS data.

[0008] In a second aspect, some embodiments of the present application further provide an electronic device, comprising: one or more processors; and a memory storing computer program instructions, wherein the computer program instructions, when executed, cause the processor to perform the steps of the method described above.

[0009] In a third aspect, some embodiments of the present application further provide a computer-readable medium having computer program instructions stored thereon, wherein the computer program instructions can be executed by a processor to implement the method as described above.

[0010] In a fourth aspect, some embodiments of the present application further provide a computer program product, comprising a computer program / instruction, which implements the steps of the method described above when executed by a processor.

[0011] Compared with the related art, in the solution provided by the embodiment of the present application, the battery EIS data is mapped to the latent space through the autoencoder model to reduce the dimension of the EIS, and then the denoising diffusion probability model is trained on the latent space of the EIS, and the latent space data of the EIS is generated, and finally the generated EIS latent space data is restored to the normal EIS data. The denoising diffusion probability model is trained and data is generated in the latent space of the EIS, which reduces the training cost and improves the generation efficiency; the denoising diffusion probability model is used to enhance the EIS data, which increases the data volume of the EIS. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] One or more embodiments are exemplarily described by pictures in the corresponding drawings, and these exemplified descriptions do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings represent similar elements, and unless otherwise stated, the figures in the drawings do not constitute proportional limitations.

[0013] Figure 1 A schematic diagram of a battery EIS data enhancement method provided according to an embodiment of the present application;

[0014] Figure 2 A schematic diagram of a process of AE-DDPM model data processing according to an embodiment of the present application;

[0015] Figure 3 A schematic diagram of the structure of an AE-DDPM model provided according to an embodiment of the present application;

[0016] Figure 4 A schematic diagram of a process flow of another battery EIS data enhancement method provided according to an embodiment of the present application;

[0017] Figure 5 A schematic diagram of a DDPM model training process provided according to an embodiment of the present application;

[0018] Figure 6 The present invention is a schematic diagram of the structure of an electronic device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0020] The following terms are used in this article.

[0021] EIS (Electrochemical Impedance Spectroscopy): is an analytical technique used to study electrochemical systems. It analyzes the resistance and capacitance of electrochemical processes by applying an alternating current signal to the system and measuring the response. This technique can be widely used in many fields, including batteries, corrosion research, sensors, coating evaluation, and bioelectrochemistry. EIS obtains information based on frequency scanning of the response of the alternating current signal in the electrochemical system. In the experiment, by applying a small amplitude alternating current signal over a certain frequency range and then measuring the response of the system (usually current and voltage), information such as resistance, capacitance, and electrochemical reaction kinetics can be obtained. Overall, electrochemical impedance spectroscopy is a powerful tool that can provide in-depth understanding and evaluation of electrochemical systems.

[0022] DDPM (Denoising Diffusion Probabilistic Model): is a deep learning model that achieves high-quality data generation by simulating the diffusion and denoising process of data distribution. In DDPM, the diffusion process is to gradually add noise to the real data until the data becomes random and unrecognizable. This process is deterministic and can be described by a forward diffusion equation, generally a Markov chain diffusion process. The amount of noise added at each step is adjustable and usually increases with the number of steps. The denoising process is to gradually restore the noisy data to the real data. This process is probabilistic and requires training a neural network (denoising model) to predict the noise at each step and remove it from the noisy data. The denoising model learns how to reverse the diffusion process during training to reconstruct the original data. DDPM models are generally used to generate two-dimensional data such as pictures.

[0023] AE (Autoencoder): It is an unsupervised learning neural network model, whose main purpose is to learn the effective representation (latent space) of input data through encoder and decoder. The structure of the autoencoder model is usually symmetrical. The encoder is responsible for mapping the input data to a low-dimensional latent space, while the decoder is responsible for restoring the latent space data to the original data.

[0024] First embodiment

[0025] The first embodiment of the present application relates to a battery EIS data enhancement method. Figure 1 As shown, the method may include the following steps:

[0026] S101, test and collect original battery EIS data.

[0027] S102, training an autoencoder model to map the original battery EIS data to a low-dimensional latent space; using an encoder of the autoencoder model to convert the original battery EIS data into a latent space vector.

[0028] S103, training a denoising diffusion probability model based on the latent space vector;

[0029] S104, using the trained denoising diffusion probability model to sample in the low-dimensional latent space, predicting the sampled data, and obtaining EIS latent space data;

[0030] S105, using the decoder of the autoencoder model, restoring the EIS latent space data to enhanced battery EIS data.

[0031] The following is a detailed description of each of the above steps.

[0032] S101, use the electrochemical workstation to configure the frequency sweep test, test the impedance value and phase of the battery at different frequency points, and record the frequency corresponding data, mainly testing the real and imaginary data of the impedance.

[0033] S102, using the collected original battery EIS data to build an autoencoder model, including an input layer, an encoder, a latent space, a decoder and an output layer. The input layer receives the original battery EIS data, the encoder compresses the high-dimensional data into a low-dimensional latent space, and the decoder restores the low-dimensional latent space data back to high-dimensional data, using an appropriate loss function to measure the reconstruction error of the model.

[0034] Model training divides the original EIS data into a training set and a validation set. Usually, most of the data is used for training, and a small part of the data is used to verify the model performance; set training parameters, including the number of training iterations and the number of samples per batch. During the training process, monitor the performance of the model on the training set and validation set to prevent overfitting or underfitting. After the training is completed, extract the encoder part of the autoencoder model, and use the encoder to convert the original battery EIS data into a low-dimensional latent space vector. By training the autoencoder model, the original battery EIS data is mapped to a low-dimensional latent space, and a latent space vector is generated, which provides a basis for subsequent data processing and analysis.

[0035] S103, using the latent space vectors generated in step S102 as training data, these latent space vectors are low-dimensional feature representations extracted from the original battery EIS data by the autoencoder model. Construct a denoising diffusion probability model (Denoising Diffusion Probabilistic Model, DDPM), which includes a denoising process and a denoising process.

[0036] The denoising process gradually adds noise to the latent space vector over multiple time steps, gradually randomizing the data. The denoising process trains a denoising model to predict the data noise in each time step and gradually restore the noisy data. Model training includes the denoising process, which gradually adds different degrees of Gaussian noise to the training data to generate multiple noise samples, so that the latent space vector gradually changes from an ordered state to a random state; the denoising process uses the denoising model to start from random noise, gradually remove the noise, and restore it to the original latent space vector. During the training process, the performance of the denoising model can be evaluated through the validation set to ensure the denoising effect of the model under different noise levels.

[0037] S104, using the denoising diffusion probability model DDPM trained in step S103. Sampling is performed in the low-dimensional latent space, and the sampled data will be used as the input of the denoising diffusion probability model. The sampled data is processed using the trained denoising diffusion probability model, and the latent space vector is predicted at each time step, gradually approaching the original latent space vector. New EIS latent space data is obtained. These data are restored from the noise by the DDPM model and have similar distribution and characteristics to the original latent space vector.

[0038] S105, using the decoder part of the autoencoder model trained in step S102, the decoder can restore the low-dimensional latent space vector to high-dimensional EIS data. Use the EIS latent space data generated by the denoising diffusion probability model in step S104 as input data. These data are sampled from the low-dimensional latent space and obtained after denoising. Input the EIS latent space data into the decoder, and the decoder will map the low-dimensional latent space vector back to high-dimensional EIS data. The decoder restores the features in the latent space to the dimensions and structure of the original EIS data by reverse mapping layer by layer. The high-dimensional data output by the decoder is the enhanced battery EIS data, which has a distribution and characteristics similar to the original EIS data, but due to the effect of data enhancement, its sample size and diversity have been improved.

[0039] It is not difficult to find that compared with the related art, the scheme provided in the embodiment of the present application enhances the electrochemical impedance spectroscopy (EIS) data by using a denoising diffusion probability model. It is possible to generate more diverse EIS data, significantly increasing the amount of EIS data. This provides richer samples for subsequent data analysis and model training, and improves the generalization ability and prediction accuracy of the model. The DDPM model is trained and data is generated in a low-dimensional latent space, and the high-dimensional EIS data is compressed into a low-dimensional latent space through an autoencoder model, and then the DDPM is trained in the latent space, reducing the computing and storage costs. Compared with the method of directly training DDPM in a high-dimensional space, this solution significantly improves the efficiency of training and data generation, and reduces the demand for computing resources.

[0040] Second embodiment

[0041] The second embodiment of the present application relates to a battery EIS data enhancement method. The second implementation is an improvement based on the first embodiment, and the specific improvements are:

[0042] The autoencoder model AE and the denoising diffusion probability module are combined to obtain the AE-DDPM model. Figure 2 The data processing process of the AE-DDPM model is shown, where x represents the input data; the AE model encoder processes the input data x to obtain the latent space vector z; the DDPM model is trained based on the latent space vector z; the trained DDPM model processes the latent space sampling data to generate a new latent space vector z'; the AE model decoder restores the new latent space vector z' into new data x' to enhance the battery EIS data.

[0043] The AE-DDPM model structure is as follows Figure 3 As shown, it is divided into two stages. The first stage is the AE model, and the second stage is the DDPM model and EIS data restoration:

[0044] The first stage: the input part real1 to real60 represents the real part of the impedance data corresponding to high frequency to low frequency, and imaginary1 to imaginary60 represents the imaginary part of the impedance data corresponding to high frequency to low frequency; next, the input data is connected to an encoder, which maps the input data to the latent distribution Latent space; then, the latent distribution is connected to a decoder to restore the input data; after that, after the AE model training is completed, the data in the latent space and the decoder are saved for subsequent use.

[0045] The second stage: use the data in the latent space as the training data set to train the DDPM model; then, use the DDPM model to generate new data in the latent space; finally, use the Decoder to restore the new data in the latent space to EIS data, that is, the newly generated EIS data.

[0046] It is not difficult to find that in the embodiment of the present application, by combining the autoencoder model (AE) with the denoising diffusion probability model (DDPM) to form the AE-DDPM model, efficient enhancement of battery EIS data is achieved. Compared with the prior art, this embodiment significantly increases the quantity and diversity of EIS data, reduces training costs, improves data generation efficiency, and generates high-quality data through the denoising process. In addition, the modular design of the AE-DDPM model makes it highly flexible and scalable, which can better support battery performance analysis and prediction, and has broad application prospects.

[0047] Third embodiment

[0048] The third embodiment of the present application relates to a battery EIS data enhancement method. The third implementation is an improvement based on the first embodiment, and the specific improvements are:

[0049] The frequency is configured to perform a scanning test, and the original battery EIS data is collected at different frequency points; the original battery EIS data includes the real part data and the imaginary part data of the impedance corresponding to each frequency point.

[0050] Training the autoencoder model includes: based on the original battery EIS data, using the mean square error as a loss function for training until the autoencoder model converges.

[0051] Training the denoising diffusion probability model includes: based on the latent space vector, gradually adding noise until the data is completely randomized to obtain noise data; based on the noise data, training the denoising model; predicting the noise at any time step through the denoising model, and recovering the latent space vector from the noise data.

[0052] The autoencoder model is constructed and trained based on the keras neural network platform; the denoising diffusion probability model is trained based on the keras neural network platform and using the U-Net architecture.

[0053] Configuring the frequency for scanning test includes: configuring the frequency range to HZ to HZ.

[0054] The enhanced battery EIS data and the original battery EIS data are similarly calculated, and corresponding thresholds are set to perform data screening.

[0055] like Figure 4 As shown, test and collect battery EIS data: Use the electrochemical workstation to configure the frequency sweep test, test the impedance value and phase of the battery at different frequency points, and record the frequency response data, mainly the real and imaginary data of the impedance. Further, the EIS configuration frequency range is HZ to HZ, this embodiment selects 60 frequency values ​​as samples.

[0056] Training AE model: AE model is built and trained based on keras platform. The AE model structure includes 2 layers of fully connected layers between input data and encoder (latent space). The number of neurons in the input data is 120, and the number of neurons in the 2 layers of fully connected layers is 60 and 20 respectively, that is, the dimension of the latent space vector is 20. The connection layer between the latent space and the decoder is 2 layers of fully connected layers, and the number of neurons is 60 and 120 respectively. The loss function of the AE model is mean square error.

[0057] Calculate the latent space data of EIS: Take the EIS data as input data and use the encoder of the AE model to generate a latent space vector with a dimension of 20.

[0058] Training the DDPM model: The latent space vector of EIS is used as the input data of the DDPM model to train the DDPM model. The U-Net framework is used to train the DDPM model.

[0059] Generate new data in the EIS latent space: Take the data in the EIS latent space vector as input data, use the DDPM model to make predictions, and generate new EIS latent vector data.

[0060] Restore EIS latent space data to normal EIS data: Use the Decoder to restore the new data generated by the EIS latent space to normal EIS data, that is, generate new EIS data.

[0061] It is not difficult to find that in the embodiments of the present application, the scanning test is performed by accurately configuring the frequency to ensure the comprehensiveness and accuracy of data collection; the mean square error is used as the loss function to train the autoencoder model to improve the convergence and stability of the model; the denoising diffusion probability model (DDPM) is trained by the method of gradual denoising and denoising to generate high-quality enhanced data; the model is built and trained based on the Keras platform and using the U-Net architecture, which significantly improves the efficiency of training and data generation.

[0062] Fourth embodiment

[0063] The fourth embodiment of the present application relates to a battery EIS data enhancement method. The fourth embodiment is an improvement based on the first embodiment, and the specific improvements are:

[0064] Testing and collecting battery electrochemical impedance spectrum data requires professional impedance spectrum testing instruments, and needs to cover a certain frequency range. The frequency range can be set from 10-2HZ to 105HZ. Multiple frequency values ​​are selected at certain intervals in the middle of the frequency range. The frequency values ​​are generally selected from 5 to 60. This embodiment selects 60 as a sample. When collecting data, it is necessary to record the real and imaginary data of the impedance corresponding to each frequency, as well as the target value to be predicted, which is the corresponding battery capacity data.

[0065] Construct and train the AE model. AE is an unsupervised learning neural network model. Its main purpose is to learn the effective representation (encoding) of input data through an encoder and a decoder. The structure of the autoencoder model is usually symmetrical. The encoder is responsible for compressing the input data into a low-dimensional code, while the decoder is responsible for restoring the low-dimensional code to the original data. When the AE model is trained in this embodiment, the model iteration number is 500 and the sample batch is 10.

[0066] The role of the encoder is to map the input data x to a low-dimensional latent space representation z. This latent space usually has a lower dimension than the input data, so the encoder can be seen as a dimensionality reduction tool. The encoder usually consists of a series of linear layers and non-linear activation functions, which provide the learning ability of the model.

[0067] Latent Space z is the representation of input data in low-dimensional space. In the autoencoder model, the latent space z tries to retain the key information of the input data x while removing unnecessary noise. In this way, the latent space can be used for data compression, feature extraction or as input to other machine learning models.

[0068] Decoder: The role of the decoder is to map the latent space z back to the space of the original input data, trying to reconstruct data x' as close as possible to the original input x. The structure of the decoder is usually similar to that of the encoder, but it is a mirror image of the encoder.

[0069] Loss function,The loss function of the autoencoder model is used to measure the difference between the reconstructed data x' and the original data x. Since EIS is a continuous value, the loss function here is the mean square error (MSE). The goal of the model is to minimize this loss function so that the reconstructed data is as close to the original data as possible.

[0070] Generate EIS latent space vector data, use the EIS data as input data of the AE model encoder to generate the corresponding latent space vector.

[0071] Train the DDPM model, generate good EIS latent space vector data, and train the DDPM model. You can use the U-Net architecture to train the DDPM model on the Keras platform. The training process of the DDPM model includes two stages, such as Figure 5 As shown:

[0072] Noise adding stage: Get real samples from the data set and gradually add noise within a certain time step until the data is completely randomized. The noise adding process formula is as follows:

[0073]

[0074] in, Indicates that at each step forward, Adding Gaussian noise to the data yields ; is the data state at time step t; is the data state at time step t-1; is the noise ratio at time step t, usually a positive number less than 1; It means the mean and the variance is Normal distribution of; is the identity matrix.

[0075] After T steps, It will be a state close to pure noise.

[0076] Denoising stage: Train the denoising model to predict the noise at any time step and recover the original data from the noisy data. The denoising process formula is as follows:

[0077]

[0078] Indicates that at each step in the backward direction, Remove the Gaussian noise data to get ;

[0079] is the mean of the denoising model predictions, which is about and a function of time step t;

[0080] is the variance of the denoising model prediction, which is also about and a function of time step t;

[0081] N(·| , ) indicates that the mean is and the variance is The normal distribution of .

[0082] During training, the denoising model learns to predict the accurate mean and variance by minimizing the reconstruction error, so that As close to the original data as possible. During the generation process, the denoising model Start, forecast step by step Until it recovers .

[0083] Generate new data in the EIS latent space,After the DDPM model is trained, sampling is performed in the EIS latent space, and then the sampled data is predicted using the DDPM model to obtain the newly generated EIS latent space data after denoising.

[0084] Restoring EIS data,Through the above steps, the newly generated EIS latent space data has been obtained.,Use the decoder in the AE model to restore the above data to obtain normal EIS data.

[0085] The effect was tested on a public data set, and the impedance data was enhanced. The input data has a total of 120 features, with feature numbers from 1 to 120. The first 60 features are the real part of the impedance data corresponding to the frequency from high to low, and the last 60 features are the imaginary part of the impedance data corresponding to the frequency from high to low.

[0086] Table 1 Battery EIS data set sample (partial)

[0087]

[0088] Where f1 to f120 represent the EIS frequency characteristics.

[0089] Based on the AE model, the EIS data is mapped to the latent space, and the obtained latent space data is as follows:

[0090] Table 2 Battery EIS latent space data sample (partial)

[0091]

[0092] Train the DDPM model based on the EIS latent space data and generate new EIS latent space data. The example is as follows:

[0093] Table 3. Examples of EIS latent space data generated by DDPM model (partial)

[0094]

[0095] The EIS potential data generated by the DDPM model is restored to obtain the newly generated EIS data, as shown below:

[0096] Table 4 Newly generated EIS data sample

[0097]

[0098] In addition, the newly generated EIS data can be further filtered by calculating the cosine similarity or Euclidean distance between the newly generated EIS data and the original EIS data and setting a corresponding threshold.

[0099] It is not difficult to find that in the embodiment of the present application, by accurately configuring the frequency for data collection, optimizing the training of the autoencoder model (AE), and combining the denoising diffusion probability model (DDPM) for data generation, the accuracy and comprehensiveness of data collection are significantly improved, and the training process and efficiency of the model are optimized. The enhanced data finally generated has higher quality and diversity, and can better support the analysis and prediction of battery performance.

[0100] The step division of the above methods is only for the purpose of clear description. When implemented, they can be combined into one step or some steps can be split and decomposed into multiple steps. As long as they include the same logical relationship, they are all within the scope of protection of this patent; adding insignificant modifications to the algorithm or process or introducing insignificant designs without changing the core design of the algorithm and process are all within the scope of protection of this patent.

[0101] In addition, some embodiments of the present application also provide an electronic device. The electronic device may be a digital computer in various forms, such as a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe computer, etc. The electronic device may also be a mobile device in various forms, such as a personal digital processing, a cellular phone, a smart phone, a wearable device, and other similar computing devices.

[0102] The electronic device includes: one or more processors; and a memory storing computer program instructions, wherein when the computer program instructions are executed, the processor executes the steps of the method provided in any one or more of the above embodiments. Figure 6 An exemplary structural diagram of the electronic device is disclosed. Figure 6 As shown, the electronic device includes: one or more processors 1101, a memory 1102, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. The various components are connected to each other using different buses and can be installed on a common motherboard or installed in other ways as needed. The processor can process instructions executed in the electronic device, including instructions stored in or on the memory to display graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In some other embodiments, if necessary, multiple processors and / or multiple buses can be used with multiple memories and multiple memories. Similarly, multiple electronic devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Among them, the components shown in this article, their connections and relationships, and their functions are only examples, and are not intended to limit the implementation of the present application described and / or required herein.

[0103] The electronic device may further include: an input device 1103 and an output device 1104. The processor 1101, the memory 1102, the input device 1103 and the output device 1104 may be connected via a bus or other means. Figure 6 The example of connecting through bus is taken in the following.

[0104] The input device 1103 can receive input digital or character information, and generate key signal input related to the user settings and function control of the electronic device, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator rod, one or more mouse buttons, a trackball, a joystick and other input devices. The output device 1104 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The display device may include, but is not limited to, a liquid crystal display (LCD), a light emitting diode (LED) display and a plasma display. In some embodiments, the display device may be a touch screen.

[0105] To provide interaction with a user, the electronic device may be a computer. The computer has: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball), through which the user can provide input to the computer. Other types of devices may also be used to provide interaction with a user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0106] In the embodiments of the present application, a computer program / instruction is stored on a computer-readable medium, and when the computer program / instruction is executed by a processor, the steps of the method provided by any one or more of the above embodiments are implemented. The computer-readable medium may be included in the electronic device described in the above embodiments; or it may exist independently without being assembled into the device. The above computer-readable medium carries one or more computer-readable instructions.

[0107] The memory 1102 can be used as a non-transient computer-readable storage medium, which can be used to store non-transient software programs, non-transient computer executable programs and modules. The processor 1101 executes various functional applications and data processing of the server by running the non-transient software programs, instructions and modules stored in the memory 1102, so as to implement the program instructions / modules corresponding to the method provided by any one or more embodiments in the embodiments of the present application.

[0108] The memory 1102 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the electronic device, etc. In addition, the memory 1102 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory 1102 may optionally include a memory remotely arranged relative to the processor 1101, and these remote memories may be connected to the electronic device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0109] It should be noted that the computer-readable medium described in this application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this application, a computer-readable medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device.

[0110] Computer readable media include permanent and non-permanent, removable and non-removable media, and can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, modules of programs or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disk (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device.

[0111] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0112] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware or any combination thereof. For example, an application specific integrated circuit (ASIC), a general-purpose computer or any other similar hardware device may be used to implement the embodiments. In some embodiments, the software program of the present application may be executed by a processor to implement the above steps or functions. Similarly, the software program of the present application (including related data structures) may be stored in a computer-readable recording medium, such as a RAM memory, a magnetic or optical drive or a floppy disk and the like. In addition, some steps or functions of the present application may be implemented by hardware, for example, as a circuit that cooperates with a processor to perform various steps or functions.

[0113] The computer program product provided in the embodiment of the present application includes one or more computer programs / instructions, and when the computer program / instructions are executed by the processor, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website site, a computer, a server, or a data center to another website site, a computer, a server, or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or a data center that includes one or more available media integrations. The available medium may be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state disk (SSD)), etc.

[0114] The flow chart or block diagram in the accompanying drawings shows the possible architecture, function and operation of the equipment, method and computer program product according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated system for hardware that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0115] The scope of the present application is defined by the appended claims rather than the above description, and it is intended that all changes that fall within the meaning and scope of the equivalent elements of the claims are included in the present application. Any figure mark in the claims should not be regarded as limiting the claims involved. In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in the device claim may also be implemented by one unit or device through software or hardware. The words "first", "second", etc. are only used to distinguish the description, and do not indicate any particular order, nor can they be understood as indicating or implying relative importance.

[0116] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily mention changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims, and the above embodiments should be regarded as exemplary and non-restrictive.

Claims

1. A battery EIS data enhancement method, characterized in that: The method comprises: Test and collect raw battery EIS data; Training an autoencoder model to map the original battery EIS data to a low-dimensional latent space; the training of the autoencoder model includes training based on the original battery EIS data using a mean square error as a loss function until the autoencoder model converges; Using the encoder of the autoencoder model, converting the raw battery EIS data into a latent space vector; Based on the latent space vector, a denoising diffusion probability model is trained; the denoising diffusion probability model training includes gradually adding noise based on the latent space vector until the data is completely randomized to obtain noise data; based on the noise data, a denoising model is trained; the noise at any time step is predicted by the denoising model, and the latent space vector is recovered from the noise data; Using the trained denoising diffusion probability model to sample in the low-dimensional latent space, predicting the sampled data, and obtaining EIS latent space data; Using the decoder of the autoencoder model, the EIS latent space data is restored to enhanced battery EIS data.

2. The method according to claim 1, characterized in that The testing and collecting of original battery EIS data include: The frequency is configured to perform a scanning test, and the original battery EIS data is collected at different frequency points; the original battery EIS data includes the real part data and the imaginary part data of the impedance corresponding to each frequency point.

3. The method according to claim 1, characterized in that The method comprises: Building and training the autoencoding model based on the keras neural network platform; The denoising diffusion probability model is trained based on the keras neural network platform and using the U-Net architecture.

4. The method according to claim 2, characterized in that: The configuration frequency for scanning test includes: configuring the frequency range to be to .

5. The method according to any one of claims 1 to 4, characterized in that: The method further comprises: The enhanced battery EIS data and the original battery EIS data are similarly calculated, and corresponding thresholds are set to perform data screening.

6. An electronic device, characterized in that: The electronic device comprises: one or more processors; and A memory storing computer program instructions, which, when executed, cause the processor to perform the steps of the method as claimed in any one of claims 1 to 5.

7. A computer readable medium having a computer program / instruction stored thereon, characterized in that: When the computer program / instructions are executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

8. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images