Solid-state battery safety early warning method and system and electronic equipment

Abstract

The invention provides a solid-state battery safety early warning method, a solid-state battery safety early warning system and electronic equipment, and relates to the field of solid-state battery detection. And parameter fusion and feature fusion are carried out on the target solid-state battery to obtain a fusion image corresponding to the target solid-state battery, so that a cross-modal feature complementary fusion process is realized, the problems of low detection precision and fusion parameter staticization existing in a traditional single mode are solved, the accuracy and real-time performance of dendritic crystal growth monitoring are improved, and the accuracy and real-time performance of the dendritic crystal growth monitoring are improved. And the safety early warning effect of the solid-state battery is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of solid-state battery detection, in particular to a solid-state battery safety early warning method and system and electronic equipment. BACKGROUND

[0002] Solid-state batteries have become the core direction of the next generation of energy storage devices due to their high energy density and excellent safety, but the interface short circuit problem caused by the growth of negative lithium dendrites is a key bottleneck restricting their industrialization. Therefore, dendrite growth monitoring of solid-state batteries is an important means to evaluate battery safety, but the existing technology has the following problems: 1. Single modality limitation: Optical coherence tomography (OCT) can achieve real-time in-situ observation, but the micro-nano scale resolution is insufficient; scanning electron microscopy (SEM) can provide high-resolution micro-morphology, but cannot achieve dynamic monitoring; fluorescence microscopy can mark dendrites, but lacks three-dimensional structural information, and single modality cannot fully characterize the dendrite growth characteristics; 2. Static fusion method: Traditional multi-modal fusion methods (such as wavelet transform) rely on fixed weight parameters and cannot adapt to the dynamic growth process of dendrites from initiation to penetration, resulting in distortion of the features of the fused image; 3. Lack of real-time performance: Existing systems mostly use offline image processing mode, which cannot be synchronized with the battery charging and discharging process, making it difficult to meet the online safety warning needs. SUMMARY

[0003] Therefore, the purpose of the present application is to provide a solid-state battery safety early warning method, system and electronic equipment. The method obtains multi-modal images of the negative dendrites from the obtained structural images, topographic images and labeled fluorescence images, and obtains the fusion image corresponding to the target solid-state battery after parameter fusion and feature fusion, thereby realizing the complementary fusion process of cross-modal features, solving the problems of low detection accuracy and static fusion parameters of traditional single modality, improving the accuracy and real-time performance of dendrite growth monitoring, and improving the safety early warning effect of solid-state batteries.

[0004] In a first aspect, the present application provides a solid-state battery safety early warning method, which comprises: An image acquisition step: acquiring the structural image, topographic image and labeled fluorescence image corresponding to the negative dendrites of the target solid-state battery, and determining the multi-modal image corresponding to the target solid-state battery according to the structural image, topographic image and labeled fluorescence image; A preprocessing step: obtaining the preprocessed image corresponding to the multi-modal image after performing Gaussian filter denoising, edge feature extraction and three-dimensional reconstruction processing on the multi-modal image respectively; The parameter fusion step comprises: calculating image entropy, standard deviation and structural similarity index of the preprocessed image based on the gray value of the preprocessed image, and constructing a fusion parameter corresponding to the target solid-state battery based on the image entropy, standard deviation and structural similarity index; The feature fusion step comprises: acquiring structural features and detail features corresponding to the preprocessed image, performing region energy weighted fusion calculation on the structural features by using the fusion parameter, and performing dynamic weight fusion calculation on the detail features by using the fusion parameter, to obtain a fusion image corresponding to the target solid-state battery. The real-time early warning step comprises: acquiring a dendritic crystal region in the fusion image, calculating dendritic crystal length and growth rate in the dendritic crystal region in real time, and performing safety early warning on the target solid-state battery based on the dendritic crystal length and growth rate.

[0005] Optionally, the image acquisition step comprises: acquiring a structural image by using an optical coherence tomography device corresponding to the target solid-state battery; acquiring a topographic image by using a scanning electron microscope corresponding to the target solid-state battery; acquiring a labeled fluorescence image by using a fluorescence microscope corresponding to the target solid-state battery; synchronously sampling data channels corresponding to the structural image, the topographic image and the labeled fluorescence image to obtain a multi-modal image corresponding to the target solid-state battery.

[0006] Optionally, the preprocessing step comprises: performing Gaussian filter denoising calculation on the structural image to obtain a filter image corresponding to the structural image; performing edge feature calculation on the topographic image by using a Canny operator to obtain dendritic crystal edge data of the target solid-state battery, and extracting a dendritic crystal edge region contained in the topographic image by using gradient values of the dendritic crystal edge data; acquiring a Z-axis scanning sequence corresponding to the labeled fluorescence image, and obtaining a three-dimensional structure image corresponding to the labeled fluorescence image based on maximum intensity projection results of the Z-axis scanning sequence; determining a preprocessed image corresponding to the multi-modal image based on the filter image, the dendritic crystal edge region and the three-dimensional structure image.

[0007] Optionally, the filter image is calculated by the following formula: ; wherein, is the filter image; is a Gaussian kernel function, and satisfies ; is the structural image; the dendritic crystal edge region is calculated by the following formula: ; ; wherein, is a preset high threshold value, is a preset low threshold value; is a gradient value of dendritic edge data; ; , ; is a topographic image; a three-dimensional structure image is calculated by the following formula: ; wherein, is a three-dimensional structure image; is a Z-axis scanning sequence, .

[0008] Optionally, the parameter fusion step comprises: determining a first fusion weight, a second fusion weight and a third fusion weight corresponding to the structure image, the topographic image and the labeled fluorescence image respectively; constructing a three-dimensional nectar source vector using the first fusion weight, the second fusion weight and the third fusion weight; determining a search step length based on a maximum iteration number of a scout bee corresponding to the artificial bee colony model, determining a new nectar source corresponding to the three-dimensional nectar source vector using the step length, and updating the nectar source corresponding to the artificial bee colony model according to the new nectar source; obtaining a gray value of the preprocessed image, calculating an image entropy, a standard deviation and a structural similarity index of the preprocessed image using the gray value; determining an adaptive function corresponding to the preprocessed image according to the image entropy, the standard deviation and the structural similarity index; determining a selection probability of the nectar source under the adaptive function based on a roulette strategy of an onlooker bee and a nectar source updating strategy of a scout bee corresponding to the artificial bee colony model; determining an optimized fusion parameter corresponding to the adaptive function through the selection probability, and constructing a fusion parameter corresponding to the target solid-state battery using the optimized fusion parameter.

[0009] Optionally, the adaptive function is calculated by the following formula: ; wherein, is an adaptive function; is a three-dimensional nectar source vector; is an image entropy; is a standard deviation; is a structural similarity index; , , are weight values corresponding to the image entropy, the standard deviation and the structural similarity index respectively; ; is a probability distribution of the gray value ; ; is a fusion image corresponding to the pre-processed image calculated by using the gray value is a mean value of the fusion image ; wherein and are a mean value of a reference image corresponding to the pre-processed image and a mean value of the fusion image respectively, is a covariance, , , is a gray level.

[0010] Optionally, the feature fusion step comprises: performing non-subsampled shearlet transform decomposition on the pre-processed image to obtain a low-frequency component and a high-frequency component of the pre-processed image corresponding to the pre-processed image; determining a structural feature of the pre-processed image by using the low-frequency component and determining a detailed feature of the pre-processed image by using the high-frequency component; performing zone energy weighted fusion calculation on the structural feature by using a fusion parameter to obtain a low-frequency fusion coefficient of the pre-processed image; wherein, ; is a zone energy weight, ; is a zone energy, ; is a modal index; performing zone energy weighted fusion calculation on the structural feature by using a fusion parameter to obtain a high-frequency fusion coefficient of the pre-processed image; wherein, ; is an optimal weight value corresponding to the fusion parameter; obtaining an inverse transform operator used in non-subsampled shearlet transform decomposition, and performing inverse transform processing on the low-frequency fusion coefficient and the high-frequency fusion coefficient by using the inverse transform operator to obtain a fusion image corresponding to the target solid-state battery; wherein, the fusion image is calculated by using the following formula; ; is the inverse transform operator.

[0011] Optionally, the real-time early warning step comprises: determining a dendrite region contained in the fusion image based on a structural image, a morphology image and a labeled fluorescence image corresponding to the negative dendrite. The dendrite length and growth rate in the dendrite region are calculated in real time based on the endpoints of the dendrite skeleton within the dendrite region; where the dendrite length... ; and The starting and ending points of the dendritic framework; growth rate ; Let be the length of the t-th monitoring session. For monitoring intervals; The system obtains preset warning threshold conditions, determines the warning level corresponding to the target solid-state battery based on the correspondence between dendrite length and growth rate and the warning threshold conditions, and uses the warning level to provide safety warnings for the target solid-state battery.

[0012] In a second aspect, the present invention provides a solid-state battery safety early warning system, the system comprising: Image acquisition unit: used to acquire structural images, morphological images and labeled fluorescence images corresponding to the negative electrode dendrites of the target solid-state battery, and to determine the multimodal image corresponding to the target solid-state battery based on the structural images, morphological images and labeled fluorescence images; Preprocessing unit: used to perform Gaussian filtering for noise reduction, edge feature extraction and 3D reconstruction on the multimodal image to obtain the preprocessed image corresponding to the multimodal image; Parameter fusion unit: used to calculate the image entropy, standard deviation and structural similarity index of the preprocessed image based on the gray value of the preprocessed image, and to construct the fusion parameters corresponding to the target solid-state battery based on the image entropy, standard deviation and structural similarity index; Feature fusion unit: used to obtain structural features and detail features corresponding to the preprocessed image, perform regional energy weighted fusion calculation on the structural features using fusion parameters, and perform dynamic weighted fusion calculation on the detail features using fusion parameters to obtain the fused image corresponding to the target solid-state battery; Real-time early warning unit: used to acquire dendritic regions contained in the fused image, calculate dendrite length and growth rate in the dendrite region in real time, and provide safety warnings for the target solid-state battery based on dendrite length and growth rate.

[0013] Thirdly, embodiments of the present invention also provide an electronic device, including a processor and a memory, wherein the memory stores computer-executable instructions that can be executed by the processor, and the processor executes the computer-executable instructions to implement the steps of the solid-state battery safety warning method provided in the first aspect.

[0014] Fourthly, embodiments of the present invention also provide a storage medium storing computer-executable instructions, which, when invoked and executed by a processor, cause the processor to implement the steps of the solid-state battery safety warning method provided in the first aspect.

[0015] The method provided by the embodiment of the present application, the system and the electronic equipment for solid-state battery safety warning, in the process of safety warning of the negative dendrite of the target solid-state battery, first acquires the structure image, the morphology image and the labeled fluorescence image corresponding to the negative dendrite of the target solid-state battery, and determines the multi-modal image corresponding to the target solid-state battery according to the structure image, the morphology image and the labeled fluorescence image; then, after the multi-modal image is respectively subjected to Gaussian filter denoising, edge feature extraction and three-dimensional reconstruction processing, the pre-processing image corresponding to the multi-modal image is obtained; subsequently, the image entropy, the standard deviation and the structural similarity index of the pre-processing image are calculated based on the gray value of the pre-processing image, and the fusion parameter corresponding to the target solid-state battery is constructed based on the image entropy, the standard deviation and the structural similarity index; then, the structure feature and the detail feature corresponding to the pre-processing image are acquired, the structure feature is subjected to regional energy weighted fusion calculation by using the fusion parameter, and the detail feature is subjected to dynamic weight fusion calculation by using the fusion parameter, so as to obtain the fusion image corresponding to the target solid-state battery; finally, the dendrite region contained in the fusion image is acquired, the dendrite length and the growth rate in the dendrite region are calculated in real time, and the target solid-state battery is subjected to safety warning based on the dendrite length and the growth rate. The multi-modal image of the negative dendrite is obtained by the structure image, the morphology image and the labeled fluorescence image acquired by the method, and the fusion image corresponding to the target solid-state battery is obtained after parameter fusion and feature fusion, so as to realize the cross-modal complementary fusion process, solve the problems of low detection accuracy and static fusion parameter of the traditional single mode, improve the accuracy and real-time performance of the dendrite growth monitoring, and improve the safety warning effect of the solid-state battery.

[0016] Other features and advantages of the present application will be set forth in the descriptions below, and in part will be apparent from the description, or can be learned by practice of the present application. The purposes and other advantages of the present application will be realized and attained by the structures particularly pointed out in the description, the claims and the drawings.

[0017] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the following preferred embodiments are specifically described below, and the accompanying drawings are described in detail as follows. BRIEF DESCRIPTION OF DRAWINGS

[0018] In order to more clearly illustrate the specific embodiments of the present application or the technical solutions in the prior art, the following will briefly introduce the drawings needed to be used in the specific embodiments or the prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and those skilled in the art can also obtain other drawings according to these drawings without creating any creative labor.

[0019] Figure 1 The flowchart of the solid-state battery safety warning method provided by the embodiment of the present application; Figure 2 A flow chart of the image acquisition step S101 of the solid-state battery safety early warning method provided by the embodiment of the present application is shown in the figure. Figure 3 A flow chart of the preprocessing step S102 of the solid-state battery safety early warning method provided by the embodiment of the present application is shown in the figure. Figure 4 A flow chart of the parameter fusion step S103 of the solid-state battery safety early warning method provided by the embodiment of the present application is shown in the figure. Figure 5 A flow chart of the feature fusion step S104 of the solid-state battery safety early warning method provided by the embodiment of the present application is shown in the figure. Figure 6 A flow chart of the real-time early warning step S105 of the solid-state battery safety early warning method provided by the embodiment of the present application is shown in the figure. Figure 7 A structural schematic diagram of the solid-state battery safety early warning system provided by the embodiment of the present application is shown in the figure. Figure 8 A structural schematic diagram of the electronic device provided by the embodiment of the present application is shown in the figure.

[0020] Icon: 710-image acquisition unit; 720-preprocessing unit; 730-parameter fusion unit; 740-feature fusion unit; 750-real-time early warning unit; 101-processor; 102-memory; 103-bus; 104-communication interface. DETAILED DESCRIPTION

[0021] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions of the present application will be described below in connection with the embodiments. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0022] To make the embodiments of the present application clearer, first, a solid-state battery safety early warning method disclosed by the embodiments of the present application will be described in detail. Figure 1 As shown in the figure, the method comprises: Image acquisition step S101: acquiring the structure image, the morphology image, and the labeled fluorescence image corresponding to the negative electrode dendrite of the target solid-state battery, and determining the multi-modal image corresponding to the target solid-state battery according to the structure image, the morphology image, and the labeled fluorescence image.

[0023] This step collects three types of key images of the target solid-state battery negative electrode dendrite: structure images (reflecting the macroscopic spatial distribution of dendrites), morphology images (presenting the microscopic morphological details of dendrites), and labeled fluorescence images (realizing specific recognition of dendrites), and then integrates them into a multi-modal image that can comprehensively characterize the state of the dendrites through image registration technology (ensuring that the spatial positions of the three types of images correspond).

[0024] The preprocessing step S102: After Gaussian filter denoising, edge feature extraction and three-dimensional reconstruction processing are performed on the multi-modal images respectively, the preprocessed images corresponding to the multi-modal images are obtained.

[0025] This step is a preprocessing step. For the multi-modal images obtained in S101, three key processes are performed: Gaussian filter denoising (to eliminate electronic noise, background fluorescence and other interference during the acquisition process), edge feature extraction (to highlight the boundary profile of dendrites and negative electrode / electrolyte), and three-dimensional reconstruction (to convert two-dimensional images into three-dimensional models of dendrites). Finally, preprocessed images with low noise, clear features and spatial information are obtained.

[0026] The parameter fusion step S103: based on the gray value of the preprocessed image, the image entropy, standard deviation and structural similarity index of the preprocessed image are calculated, and the fusion parameters corresponding to the target solid-state battery are constructed based on the image entropy, standard deviation and structural similarity index.

[0027] This step calculates three types of quantitative indicators based on the pixel gray value of the preprocessed image: image entropy (reflecting the richness of image information, with higher entropy values in dendrite regions), standard deviation (reflecting the gray level dispersion, with higher standard deviation values when the difference between dendrites and background is greater), and structural similarity index (SSIM) (verifying the structural consistency of different modal images, excluding impurity interference). Then, through dynamic weighting algorithm, the three types of indicators are integrated to construct the fusion parameters that can quantify the "existence, reliability and complexity" of dendrites.

[0028] The feature fusion step S104: obtains the structure features and detail features corresponding to the preprocessed images, performs regional energy weighted fusion calculation on the structure features using the fusion parameters, and performs dynamic weight fusion calculation on the detail features using the fusion parameters, to obtain the fusion image corresponding to the target solid-state battery.

[0029] This step first extracts two types of core features from the preprocessed images: structure features (macroscopic distribution of dendrites, main stem growth direction, etc.) and detail features (dendrite tip curvature, branch density, etc.). Then, based on the fusion parameters of S103, regional energy weighted fusion is performed on the structure features (to highlight high-risk areas such as dendrite dense areas), and dynamic weight fusion is performed on the detail features (to adjust the weight according to the feature reliability to avoid errors). Finally, the two types of optimized features are integrated to obtain a fusion image that takes into account both macroscopic structure and microscopic details.

[0030] Real-time early warning step S105: Obtain the dendrite region contained in the fusion image, calculate the dendrite length and growth rate in the dendrite region in real time, and perform safety warning on the target solid-state battery based on the dendrite length and growth rate.

[0031] This step first identifies and locates the dendrite region in the fusion image through a correlation segmentation algorithm (automatic recognition), and then calculates two core risk parameters in real time: dendrite length (straight-line distance from the negative electrode to the farthest end of the dendrite, to determine whether it is close to the thickness of the electrolyte) and dendrite growth rate (calculated by the length difference at different time points, to determine whether the growth is accelerated); then compare the two parameters with the preset safety threshold, and trigger the corresponding safety warning according to the risk level (low / medium / high) of the target solid-state battery.

[0032] Optionally, as shown in Figure 2 , the image acquisition step S101 includes: Step S201: Collecting a structure image using an optical coherence tomography device corresponding to the target solid-state battery.

[0033] First, an optical coherence tomography device (OCT) adapted to the target solid-state battery is used to scan the negative electrode region inside the battery, generating a structure image that reflects the macroscopic spatial state of the dendrite. The OCT device has the advantages of non-invasiveness, high resolution (micron level), and fast imaging. It can penetrate the electrolyte and the shell without disassembling the battery, clearly presenting the growth path of the dendrite from the negative electrode (such as whether it extends along the electrolyte gap or approaches the positive electrode), providing a basis for subsequent judgment of the macroscopic growth trend of the dendrite. For example, it can directly observe whether the dendrite has approached the middle layer of the electrolyte and preliminarily assess the short-circuit risk.

[0034] Step S202: Collecting a topography image using a scanning electron microscope corresponding to the target solid-state battery.

[0035] With the help of a scanning electron microscope (SEM) corresponding to the target solid-state battery, the dendrite on the negative electrode surface and shallow region is microscopically scanned to capture a topography image that reflects the microstructure of the dendrite. The core advantage of SEM is high magnification (up to hundreds of thousands of times) and nanometer-level resolution, which can clearly present the micro details of the dendrite: such as the diameter of the dendrite trunk, the number and distribution of branches, and the sharpness of the tip (the sharper the tip, the easier it is to break through the interface barrier of the solid-state electrolyte). These micro-topographic features are directly related to the growth activity of the dendrite and are the key basis for subsequent judgment of whether the dendrite is growing at an accelerated rate.

[0036] Step S203: Collecting a labeled fluorescence image using a fluorescence microscope corresponding to the target solid-state battery.

[0037] The step first injects a fluorescent probe (such as a fluorescent molecule containing a lithium-affinity functional group) that specifically binds to lithium dendrites into the interior of the target solid-state battery, and then uses a fluorescence microscope to observe the negative electrode region and collect a labeled fluorescence image that only the dendrite region emits a fluorescence signal. The fluorescence microscope can effectively exclude the interference of impurities (such as electrolyte decomposition products and electrode powder) in the battery through specific fluorescence recognition. Only lithium dendrites combined with the fluorescent probe will emit light, and other regions will have no fluorescence signal, which can accurately locate the real dendrite region and avoid the warning error caused by mistaking impurities for dendrites in the subsequent process.

[0038] Step S204: After synchronously sampling the data channels corresponding to the structural image, the topographic image, and the labeled fluorescence image, a multi-modal image corresponding to the target solid-state battery is obtained.

[0039] The structural image collected in S201, the topographic image collected in S202, and the labeled fluorescence image collected in S203 are respectively subjected to time and space synchronous sampling of the corresponding device data channels (such as the optical signal channel of OCT, the electronic signal channel of SEM, and the fluorescence signal channel of the fluorescence microscope), so as to ensure that the pixel positions and collection time of the three types of images correspond one by one, and finally a multi-modal image is obtained by integration. In actual scenarios, the multi-channel synchronous sampling process can be realized by using a 16-bit AD conversion chip to achieve time alignment, and the sampling interval is ≤10 ms.

[0040] Optionally, the preprocessing step S102 includes the following steps as shown in the following table: Figure 3 Step S301: After Gaussian filter denoising calculation of the structural image, a filter image corresponding to the structural image is obtained.

[0041] First, the structural image is subjected to Gaussian filter denoising. For the OCT original image (MxN is the size of the image), a two-dimensional Gaussian filter is used to suppress noise.

[0042] The filter image is calculated by the following formula: ; Wherein, is the filter image; is a Gaussian kernel function, , and satisfies ; is the structural image.

[0043] Step S302: The Canny operator is used to calculate the edge features of the topographic image, to obtain the dendrite edge data of the target solid-state battery, and the gradient value of the dendrite edge data is used to extract the dendrite edge region contained in the topographic image.

[0044] ​Edge features are extracted from the topography images acquired by SEM, and the Canny operator is used to process the topography images corresponding to the SEM. Extract the dendrite edges, and then calculate the gradient using the Sobel operator: , ; The asterisk (*) indicates convolution calculation and gradient magnitude. and direction The calculation formula is: , ; The edge preservation condition is: or Furthermore, the domain contains high threshold edges. For the preset high threshold, This is the preset low threshold.

[0045] Step S303: Obtain the Z-axis scanning sequence corresponding to the labeled fluorescence image, and obtain the three-dimensional structure image corresponding to the labeled fluorescence image based on the maximum intensity projection result of the Z-axis scanning sequence.

[0046] This step involves three-dimensional reconstruction of the fluorescence image, based on the Z-axis scanning sequence of the fluorescence microscope. Three-dimensional structural images are generated using maximum intensity projection (MIP): , where Z is the number of scan layers along the Z-axis.

[0047] Step S304: Determine the preprocessed image corresponding to the multimodal image based on the filtered image, dendrite edge region, and three-dimensional structure image.

[0048] Optionally, the parameter fusion step S103 can determine the fusion parameters based on the Artificial Bee Colony (ABC) algorithm, such as... Figure 4 As shown, it includes: Step S401: Determine the first fusion weight, second fusion weight, and third fusion weight corresponding to the structural image, morphological image, and labeled fluorescence image, respectively.

[0049] This step corresponds to the honey source encoding and initialization process. The first fusion weight, second fusion weight, and third fusion weight corresponding to the structural image, morphological image, and labeled fluorescence image are respectively... , , .

[0050] Step S402: Construct a three-dimensional honey source vector using the first fusion weight, the second fusion weight, and the third fusion weight.

[0051] Specifically, the high-frequency fusion weights of OCT, SEM, and fluorescence modalities are encoded into a three-dimensional honey source vector. , meet and (m is the modal index). The population size is initialized to 50, and the formula for generating the honey source randomly is: ; where rand(0,1) is a uniform random number in the interval (0,1), and the superscript (0) indicates the initial iteration.

[0052] Step S403: Determine the search step size based on the maximum number of iterations of the artificial bee colony model corresponding to the employed bee, determine the new honey source corresponding to the three-dimensional honey source vector using the step size, and update the honey source corresponding to the artificial bee colony model according to the new honey source.

[0053] This step is the field search process of the employed bee, and the employed bee generates a new honey source through field search , and the calculation formula is: ; where is the weight dimension, k≠i is a randomly selected other honey source, and the search step size is dynamically attenuated with the iteration number t: ; wherein is the maximum number of iterations.

[0054] Step S404: Obtain the gray value of the preprocessed image, and calculate the image entropy, standard deviation, and structural similarity index of the preprocessed image using the gray value.

[0055] Specifically, is the image entropy; is the standard deviation; is the structural similarity index; ; is the probability distribution of the gray value ; ; is the fusion image corresponding to the preprocessed image calculated using the gray value; is the mean of the fusion image; ; wherein and are the mean of the reference image corresponding to the preprocessed image and the mean of the fusion image, respectively, is the covariance, , , is the gray level.

[0056] Step S405: Determine the fitness function corresponding to the preprocessed image according to the image entropy, standard deviation, and structural similarity index.

[0057] The fitness function is calculated by the following formula: ; wherein, is the fitness function; is the three-dimensional nectar source vector; , , are the weight values corresponding to the image entropy, standard deviation and structural similarity index respectively; Step S406: Based on the roulette strategy of the observation bee corresponding to the artificial bee colony model and the nectar source updating strategy of the scout bee, the selection probability of the nectar source under the fitness function is determined.

[0058] This step is the observation bee selection and scout bee updating process. The observation bee selects the nectar source according to the roulette strategy, and the selection probability is For the nectar source that is not optimized for 20 consecutive iterations, global random reset is adopted: wherein is a standard normal random number, which avoids the algorithm from falling into local optimum.

[0059] Step S407: The optimization fusion parameter corresponding to the fitness function is determined through the selection probability, and the optimization fusion parameter is used to construct the fusion parameter corresponding to the target solid-state battery.

[0060] The above process is the fusion parameter optimization based on the artificial bee colony (ABC) algorithm. The multi-scale transform domain fusion weight is encoded as a nectar source. Through the scout bee field search, the observation bee roulette selection and the scout bee global updating strategy, the fusion parameter is optimized by taking the image entropy, the standard deviation and the structural similarity index as the fitness function.

[0061] Optionally, the feature fusion step S104, as shown in Figure 5 , includes: Step S501: The preprocessed image is decomposed by non-subsampled shearlet transform to obtain low-frequency components and high-frequency components .

[0062] The preprocessed image is decomposed by non-subsampled shearlet transform (NSCT). Each modality image after preprocessing is decomposed by 4-layer NSCT to obtain low-frequency components and high-frequency components (l=1,…4 is the decomposition layer number), and the decomposition process satisfies: wherein is the NSCT inverse transform operator.

[0063] Step S502: The structural features corresponding to the preprocessed image are determined by using the low-frequency components, and the detail features corresponding to the preprocessed image are determined by using the high-frequency components.

[0064] Step S503: Perform zone energy weighted fusion calculation on the structural features through the fusion parameters to obtain the low-frequency fusion coefficients corresponding to the preprocessed images ; This step is a low-frequency component fusion process, which fuses the low-frequency components using a zone energy weighted rule. The low-frequency fusion coefficient of a position (x, y) is : ; Where the zone energy weight , the zone energy .

[0065] Step S504: Perform zone energy weighted fusion calculation on the structural features through the fusion parameters to obtain the high-frequency fusion coefficients corresponding to the preprocessed images ; This step is a high-frequency component fusion process, which fuses the high-frequency components based on the ABC optimized weights. The high-frequency fusion coefficient is , where is the optimal weight obtained by the ABC algorithm optimization.

[0066] Step S505: Obtain the inverse transform operator used in the non-subsampled shearlet transform decomposition, and perform inverse transform processing on the low-frequency fusion coefficients and the high-frequency fusion coefficients using the inverse transform operator to obtain the fusion image corresponding to the target solid-state battery. The fusion image is calculated by the following formula: ; is the inverse transform operator.

[0067] Optionally, the real-time early warning step S105, as shown in Figure 6 , includes: Step S601: Determine the dendrite region contained in the fusion image based on the structural image, the topographic image, and the labeled fluorescence image corresponding to the negative dendrite. Step S602: Real-time calculate the dendrite length and growth rate in the dendrite region according to the end points of the dendrite skeleton in the dendrite region. Step S603: Obtain a preset early warning threshold condition, determine the early warning level of the target solid-state battery based on the corresponding relationship between the dendrite length and the growth rate and the early warning threshold condition, and use the early warning level to perform safety early warning on the target solid-state battery.

[0068] Specifically, the above process includes a dendrite feature extraction step and an early warning preparation judgment step. In the dendrite feature extraction process, the dendrite length : and are the starting point and the ending point of the dendrite skeleton; the growth rate . is the t-th monitoring length, is the monitoring interval.

[0069] In the early warning threshold judgment process, the corresponding early warning threshold conditions can be set in advance. Specifically, the first early warning is and cycle; the second early warning is and the tip curvature (curvature The third early warning is to detect that the dendrite penetrates the electrolyte interface (judged by OCT depth information).

[0070] Through the above solid-state battery safety early warning method, the method synchronously collects negative dendrite multi-modal images of the solid-state battery through optical coherence tomography, scanning electron microscopy and fluorescence microscopy, dynamically optimizes multi-scale transform domain fusion parameters using an improved artificial bee colony algorithm, realizes cross-modal complementary fusion, combines a real-time monitoring module to complete dendrite growth dynamic tracking and early warning, thereby solving the problems of low detection accuracy and static fusion parameters of traditional single modal, improving the accuracy and real-time of dendrite growth monitoring, and improving the solid-state battery safety early warning effect.

[0071] Corresponding to the above solid-state battery safety early warning method embodiment, the embodiment of the present application also provides a solid-state battery safety early warning system, as shown in Figure 7 The system comprises: An image acquisition unit 710 is configured to acquire structural images, topographic images and labeled fluorescence images corresponding to negative dendrites of a target solid-state battery, and determine multi-modal images corresponding to the target solid-state battery according to the structural images, topographic images and labeled fluorescence images. A preprocessing unit 720 is configured to obtain preprocessed images corresponding to the multi-modal images by performing Gaussian filter denoising, edge feature extraction and three-dimensional reconstruction processing on the multi-modal images, respectively. A parameter fusion unit 730 is configured to calculate image entropy, standard deviation and structural similarity index of the preprocessed images based on the gray values of the preprocessed images, and construct fusion parameters corresponding to the target solid-state battery based on the image entropy, standard deviation and structural similarity index. A feature fusion unit 740 is configured to obtain structural features and detail features corresponding to the preprocessed images, perform region energy weighted fusion calculation on the structural features using the fusion parameters, and perform dynamic weight fusion calculation on the detail features using the fusion parameters, to obtain a fusion image corresponding to the target solid-state battery. A real-time early warning unit 750 is configured to obtain a dendrite region contained in the fusion image, calculate dendrite length and growth rate in the dendrite region in real time, and perform safety early warning on the target solid-state battery based on the dendrite length and growth rate.

[0072] Through the above-mentioned solid-state battery safety warning system, the multi-modal image of the negative electrode dendrite is obtained through the structural image, the topographic image and the labeled fluorescent image obtained by collection, and the fusion image corresponding to the target solid-state battery is obtained after parameter fusion and feature fusion, so as to realize the cross-modal complementary fusion process, solve the problems of low detection accuracy and static fusion parameters existing in the traditional single mode, improve the accuracy and real-time performance of dendrite growth monitoring, and improve the solid-state battery safety warning effect.

[0073] The solid-state battery safety warning system provided by the embodiment of the present application has the same implementation principle and technical effects as the foregoing solid-state battery safety warning method embodiment. For brevity of description, the part of the system embodiment not mentioned can be referred to the corresponding content in the foregoing solid-state battery safety warning method embodiment.

[0074] The embodiment further provides an electronic device, and a structure diagram of the electronic device is shown in Figure 8 The device includes a processor 101 and a memory 102; wherein the memory 102 is used to store one or more computer instructions, and the one or more computer instructions are executed by the processor to realize the steps of the foregoing solid-state battery safety warning method.

[0075] Figure 8 The electronic device shown in the figure further includes a bus 103 and a communication interface 104, and the processor 101, the communication interface 104 and the memory 102 are connected through the bus 103.

[0076] The memory 102 can include a high-speed random access memory (RAM), and can also include a non-volatile memory, for example, at least one disk memory. The bus 103 can be an ISA bus, a PCI bus or an EISA bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, Figure 8 only one bidirectional arrow is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0077] The communication interface 104 is used to connect with at least one user terminal and other network units through a network interface, and send the encapsulated IPv4 packet or IPv4 packet to the user terminal through the network interface.

[0078] The processor 101 can be an integrated circuit chip with processing capability. In implementation process, each step of the above method can be completed by integrated logic circuit of hardware in the processor 101 or by instructions in the form of software. The processor 101 described above can be a general processor, including a central processing unit (CPU), a network processor (NP), etc.; can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component. Each method, step and logic block diagram disclosed in the embodiments of the present disclosure can be implemented or executed. The general processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in combination with the embodiments of the present disclosure can be directly embodied as a hardware code processor to execute, or be executed by a combination of hardware and software modules in the code processor. The software module can be located in a random access memory, a flash memory, a read only memory, a programmable read only memory or an electrically erasable programmable memory, a register, or other mature storage medium in the art. The storage medium is located in the storage 102, and the processor 101 reads the information in the storage 102 and combines the hardware to complete the steps of the method of the above embodiments.

[0079] The embodiments of the present application also provide a storage medium, which stores a computer program. When the computer program is run by a processor, the steps of the solid-state battery safety warning method in the above embodiments are executed.

[0080] In several embodiments provided in the present application, it should be understood that the disclosed system, device, equipment and method can be implemented by other ways. The system embodiments described above are only schematic, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some communication interface, device or unit, and can be electrical, mechanical or other forms.

[0081] The units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, i.e. may be located in one place, or may be distributed on multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0082] In addition, each functional unit in each embodiment of the application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit.

[0083] If the functions are realized in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer readable storage medium executable by a processor. Based on this understanding, the technical solutions of the application or the part of the prior art that essentially contributes or the part of the technical solutions can be embodied in the form of a software product, which is stored in a storage medium and includes instructions for making a computer device (which can be a personal computer, an electronic device, or a network device, etc.) execute all or part of the steps of the method described in each embodiment of the application. The foregoing storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disk and various program code storage media.

[0084] Finally, it should be noted that: the above-described embodiments are only specific embodiments of the application, which are used to illustrate the technical solutions of the application, but not to limit it, the protection scope of the application is not limited to this, although the application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art within the technical range disclosed by the application can still modify or easily think of changes to the technical solutions recorded in the foregoing embodiments, or make equivalent replacement to part of the technical features; and these modifications, changes or replacements do not make the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the application, and all should be covered in the protection scope of the application. Therefore, the protection scope of the application should be subject to the protection scope of the claims.

Claims

1. A solid-state battery safety early warning method, characterized by, The method comprises: An image acquisition step: acquiring a structure image, a morphology image and a labeled fluorescence image corresponding to a negative electrode dendrite of a target solid-state battery, and determining a multi-modal image corresponding to the target solid-state battery according to the structure image, the morphology image and the labeled fluorescence image; A preprocessing step: after respectively performing Gaussian filter denoising, edge feature extraction and three-dimensional reconstruction processing on the multi-modal image, a preprocessed image corresponding to the multi-modal image is obtained; A parameter fusion step: calculating the image entropy, standard deviation and structural similarity index of the preprocessed image based on the gray value of the preprocessed image, and constructing a fusion parameter corresponding to the target solid-state battery based on the image entropy, the standard deviation and the structural similarity index; A feature fusion step: obtaining structure features and detail features corresponding to the preprocessed image, performing regional energy weighted fusion calculation on the structure features by using the fusion parameter, and performing dynamic weight fusion calculation on the detail features by using the fusion parameter, to obtain a fusion image corresponding to the target solid-state battery; A real-time early warning step: acquiring a dendrite region contained in the fusion image, calculating the dendrite length and growth rate in the dendrite region in real time, and performing safety warning on the target solid-state battery based on the dendrite length and the growth rate.

2. The solid-state battery safety warning method of claim 1, wherein, The image acquisition step comprises: acquiring the structure image by using an optical coherence tomography device corresponding to the target solid-state battery; acquiring the morphology image by using a scanning electron microscope corresponding to the target solid-state battery; acquiring the labeled fluorescence image by using a fluorescence microscope corresponding to the target solid-state battery; after synchronously sampling data channels corresponding to the structure image, the morphology image and the labeled fluorescence image, obtaining the multi-modal image corresponding to the target solid-state battery.

3. The solid-state battery safety warning method of claim 1, wherein, The preprocessing step comprises: after Gaussian filter denoising calculation is performed on the structure image, a filter image corresponding to the structure image is obtained; edge feature calculation is performed on the morphology image by using a Canny operator, to obtain dendrite edge data of the target solid-state battery, and a dendrite edge region contained in the morphology image is extracted by using gradient values of the dendrite edge data; a Z-axis scanning sequence corresponding to the labeled fluorescence image is obtained, and a three-dimensional structure image corresponding to the labeled fluorescence image is obtained based on maximum intensity projection results of the Z-axis scanning sequence; the preprocessed image corresponding to the multi-modal image is determined based on the filter image, the dendrite edge region and the three-dimensional structure image.

4. The solid-state battery safety warning method of claim 3, wherein, The filter image is calculated by the following formula: ； wherein is the filtered image; is a Gaussian kernel function, and satisfies ; is the structure image; The dendrite edge region is calculated by the following formula: ； ； wherein, is a pre-set high threshold value, is a pre-set low threshold value; is the gradient value of the dendrite edge data; ; , ; is the topographic image; The three-dimensional structure image is calculated by the following formula: ； wherein is the three-dimensional structure image; is the Z-axis scan sequence, .

5. The solid-state battery safety warning method of claim 1, wherein, The parameter fusion step comprises: determining a first fusion weight, a second fusion weight and a third fusion weight corresponding to the structure image, the morphology image and the labeled fluorescence image, respectively; constructing a three-dimensional honey source vector by using the first fusion weight, the second fusion weight and the third fusion weight; The search step is determined according to the maximum iteration number of the employed bee in the artificial bee colony model, the new nectar source corresponding to the three-dimensional nectar source vector is determined by using the step, and the nectar source corresponding to the artificial bee colony model is updated according to the new nectar source; The gray value of the preprocessed image is obtained, and the image entropy, standard deviation and structural similarity index of the preprocessed image are calculated by using the gray value; The fitness function corresponding to the preprocessed image is determined according to the image entropy, the standard deviation and the structural similarity index; The selection probability of the nectar source under the fitness function is determined based on the roulette strategy of the observer bee and the nectar source updating strategy of the scout bee in the artificial bee colony model; The optimization fusion parameter corresponding to the fitness function is determined by the selection probability, and the fusion parameter corresponding to the target solid-state battery is constructed by using the optimization fusion parameter.

6. The solid-state battery safety warning method of claim 5, wherein, The fitness function is calculated by the following formula: ； wherein, is the adaptation function; is the three-dimensional nectar source vector; is the image entropy; is the standard deviation; is the structural similarity index; , , are weight values corresponding to the image entropy, the standard deviation and the structural similarity index, respectively. ; is a probability distribution of gray values ; ; a fusion image corresponding to the pre-processed image calculated using the gray values; is a mean value of the fusion image; ； wherein and are the mean of the corresponding reference image and the mean of the fused image respectively for the pre-processed image, is the covariance, , , is the gray level.

7. The solid-state battery safety warning method of claim 1, wherein, The feature fusion step includes: performing non-subsampled shearlet transform decomposition on the preprocessed image to obtain a low-frequency component and a high-frequency component corresponding to the preprocessed image and high-frequency components ; The structural features corresponding to the preprocessed image are determined by using the low-frequency component, and the detail features corresponding to the preprocessed image are determined by using the high-frequency component; The structure features are subjected to zone energy weighted fusion calculation through the fusion parameters, to obtain low-frequency fusion coefficients corresponding to the preprocessed image ; wherein, ; is a zone energy weight, ; is a zone energy, ; is a modal index; The structural features are subjected to region energy weighted fusion calculation through the fusion parameters, to obtain high-frequency fusion coefficients corresponding to the preprocessed image ; wherein ; is an optimal weight value corresponding to the fusion parameter An inverse transform operator used in a non-subsampled shearlet transform decomposition is obtained, and the low-frequency fusion coefficients and the high-frequency fusion coefficients are inversely transformed using the inverse transform operator to obtain a fusion image corresponding to the target solid-state battery; wherein the fusion image is calculated by the following formula; is the inverse transform operator.​ 8. The solid-state battery safety warning method of claim 1, wherein, The real-time early warning step includes: The dendrite area contained in the fusion image is determined based on the structural image, the morphology image and the labeled fluorescence image corresponding to the negative dendrite of the target solid-state battery; calculating the dendrite length and growth rate in the dendrite region in real time according to the end points of the dendrite skeleton in the dendrite region; wherein the dendrite length ; and is the starting end point and the ending end point of the dendrite skeleton; the growth rate ; is the length of the tth monitoring, is the monitoring interval; A preset early warning threshold condition is obtained, the early warning level corresponding to the target solid-state battery is determined based on the corresponding relationship between the dendrite length and the growth rate and the early warning threshold condition, and the safety of the target solid-state battery is warned by using the early warning level.

9. A solid-state battery safety warning system, characterized by, The system includes: An image acquisition unit is configured to acquire a structural image, a morphology image and a labeled fluorescence image corresponding to a negative dendrite of a target solid-state battery, and determine a multi-modal image corresponding to the target solid-state battery according to the structural image, the morphology image and the labeled fluorescence image; A preprocessing unit is configured to obtain a preprocessed image corresponding to the multi-modal image by performing Gaussian filter denoising, edge feature extraction and three-dimensional reconstruction processing on the multi-modal image, respectively; A parameter fusion unit is configured to calculate an image entropy, a standard deviation and a structural similarity index of the preprocessed image based on a gray value of the preprocessed image, and construct a fusion parameter corresponding to the target solid-state battery based on the image entropy, the standard deviation and the structural similarity index; A feature fusion unit is configured to obtain structural features and detail features corresponding to the preprocessed image, perform region energy weighted fusion calculation on the structural features by using the fusion parameter, and perform dynamic weight fusion calculation on the detail features by using the fusion parameter, to obtain a fusion image corresponding to the target solid-state battery; A real-time early warning unit is configured to obtain a dendrite area contained in the fusion image, calculate a dendrite length and a growth rate in the dendrite area in real time, and perform safety warning on the target solid-state battery based on the dendrite length and the growth rate.

10. An electronic device, comprising: A computer program product comprising a processor and a memory storing computer executable instructions executable by the processor to implement the steps of the solid state battery safety warning method of any one of claims 1 to 8. A computer program product comprising a processor and a memory storing computer executable instructions executable by the processor to implement the steps of the solid state battery safety warning method of any one of claims 1 to 8.

Images