Impedance optimization method for porous gradient anode supported solid fuel cell

Abstract

The invention relates to the technical field of solid fuel cells, and discloses a porous gradient anode supported solid fuel cell impedance optimization method which is applied to a system comprising a plurality of porous gradient anode impedance sensors and an optimization controller. The method comprises the steps that a sensor collects voltage and current data to generate an impedance state data set; the optimization controller constructs a regional impedance state matrix, extracts features through processing, performs impedance distribution prediction in combination with a potential gradient and the like, outputs spatial and temporal distribution features through an impedance optimization model, and updates a data set; and dynamically optimizing regional electrode parameters according to the distribution characteristics, including voltage adjustment, current aggregation, resistance distribution and other operations. According to the method, through multi-sensor distributed acquisition, multi-dimensional feature analysis and dynamic modeling, accurate prediction and parameter dynamic regulation and control of electrode impedance spatial and temporal distribution are realized, the performance and stability of the solid fuel cell are improved, and the method is suitable for the field of solid fuel cell management.

Description

Technical Field

[0001] The present invention relates to the technical field of solid fuel cells, and particularly to a method for optimizing the impedance of a porous gradient anode-supported solid fuel cell. Background Art

[0002] Due to the advantages of high efficiency, environmental friendliness, and strong fuel adaptability, solid fuel cells show broad application prospects in the fields of distributed power generation, transportation, etc. As an important type of SOFC, the porous gradient anode-supported solid fuel cell can effectively improve the fuel diffusion efficiency and electrode reaction activity by designing a porous gradient structure in the anode layer. However, during the actual operation process, the problem of uneven electrode impedance distribution significantly affects the performance and life of the battery.

[0003] Existing solid fuel cell management systems face many challenges in impedance optimization. On the one hand, the traditional single-point measurement method is difficult to capture the spatio-temporal distribution characteristics of electrode impedance and cannot accurately reflect the complex impedance change law inside the porous gradient anode. Due to the differences in porosity, pore size distribution, and material composition in different regions of the anode's porous gradient structure, the fuel gas diffusion path and the distribution of electrochemical reaction sites are uneven, resulting in non-uniform impedance distribution in space. Single-point measurement can only obtain the impedance information of a local area and cannot comprehensively reflect the impedance state of the entire anode. On the other hand, existing optimization algorithms are mostly based on static models and lack the ability to track the impedance evolution process in real time under dynamic operating conditions. Under different operating conditions such as load, temperature, and fuel composition, parameters such as the electrode reaction rate and gas diffusion coefficient in solid fuel cells will change dynamically, resulting in the continuous evolution of impedance characteristics over time. Traditional static models cannot adapt to this change in a timely manner and are difficult to achieve dynamic optimization and adjustment of electrode parameters. In addition, problems such as mutual interference between electrodes, transmission delay, and impedance blind spots further exacerbate the complexity of impedance optimization. In the porous gradient anode, there are mutual interactions such as electromagnetic coupling between electrodes in different regions, which will interfere with the impedance measurement results. At the same time, the signal transmission in the electrode requires a certain time, resulting in a transmission delay, which may cause a time deviation between the measured data and the actual impedance state. The existence of impedance blind spots (such as some regions are difficult to accurately obtain impedance data due to structural or measurement conditions) makes it impossible to fully grasp the impedance distribution of the entire anode and affects the formulation of optimization strategies.

[0004] In the existing technology, some studies have tried to optimize impedance management by increasing the number of sensors or improving algorithms, but there are still the following shortcomings: the deployment of sensor networks lacks systematicity and fails to fully consider the structural characteristics of porous gradient anodes, resulting in insufficient spatial coverage and accuracy of data collection; at the algorithm level, the fusion processing capabilities of multi-source data are limited, and key information such as potential intensity distribution and transmission delay characteristics cannot be effectively extracted. In addition, the intrinsic relationship between electrode structure and impedance distribution is not fully considered during the modeling process, resulting in poor accuracy and generalization of the optimization model. Therefore, how to construct a high-precision and real-time impedance optimization method based on the structural characteristics of porous gradient anodes to achieve accurate prediction and dynamic regulation of the spatiotemporal distribution of electrode impedance has become a key technical problem that needs to be solved in the current solid fuel cell field. Summary of the invention

[0005] The object of the present invention is to provide a method for optimizing impedance of a porous gradient anode-supported solid fuel cell to solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solution: a porous gradient anode supported solid fuel cell impedance optimization method, applied to a solid fuel cell management system, the system includes a plurality of impedance sensors deployed on a porous gradient anode and an optimization controller connected to the impedance sensors, two adjacent impedance sensors are separated by a set distance, the method includes: The impedance sensor collects voltage data and current data of electrodes in the region to generate an impedance state data set; The optimization controller receives real-time impedance state data of multiple impedance sensors to construct a regional impedance state matrix; Determining the distribution characteristics of the electrode impedance according to the impedance state data set and the real-time data of each impedance sensor, wherein determining the distribution characteristics of the electrode impedance includes: processing the impedance state matrix, extracting impedance characteristics in combination with the impedance state data set, and predicting the impedance distribution according to the potential gradient and electrolyte path information, outputting the spatiotemporal distribution characteristics of the electrode impedance through an impedance optimization model, and updating the impedance state data set according to the spatiotemporal distribution characteristics; According to the distribution characteristics, the regional electrode parameters are dynamically optimized.

[0007] Preferably, the determination of the distribution characteristics of the electrode impedance includes: Processing the impedance state matrix to extract potential intensity distribution, transmission delay characteristics and impedance change trends; Perform electric potential intensity modeling on the impedance state matrix according to the electric potential intensity distribution and transmission delay characteristics, divide the regional electrodes into multiple sub-regions and mark the regional identifiers, associate and match the electric potential intensity of the sub-regions with the impedance state data set, and mark the regional identifiers in the impedance state data set; Calculate the electric potential intensity gradient according to the impedance sensor position, predict the distribution of the electrode impedance according to the electric potential intensity gradient and the impedance change trend, and calculate the impedance prediction information of each sub-region; Construct an impedance optimization model, use the impedance prediction information as the input parameter of the impedance optimization model, perform spatial correlation modeling on the impedance prediction information through the impedance optimization model, and output the spatio-temporal distribution characteristics of the electrode impedance; Update the impedance state data set according to the spatio-temporal distribution characteristics, and obtain the distribution characteristics of the electrode impedance.

[0008] Preferably, the processing of the impedance state matrix includes: Normalize the impedance state matrix, intercept the impedance hot spot area in the matrix through a sliding window, filter the noise of the hot spot area, and calculate the impedance change trend through the eigen-decomposition algorithm; Calculate the spatial correlation characteristics of the impedance state matrix, calculate the interference intensity, link stability coefficient and impedance blind area index between regions according to the spatial correlation characteristics, construct a feature fusion network, and calculate the transmission delay characteristics through the feature fusion network; Extract the time-domain characteristics and frequency-domain characteristics collected by each impedance sensor, calculate the impedance feature vector of the sensor according to the phase difference between the time-domain characteristics and the frequency-domain characteristics, perform feature matching on the impedance sensors at different positions according to the impedance feature vector, and calculate the impedance change trend.

[0009] Preferably, the electric potential intensity modeling of the impedance state matrix includes: Extract the electric potential intensity sampling points in each frame of data according to the electric potential intensity distribution, perform association mapping on the sampling points and the transmission delay characteristics to generate an electric potential intensity map, spatially align the electric potential intensity maps collected by multiple sensors, and calculate the electric potential intensity distribution of the region; Set an interference threshold value, locate the interference source according to the electric potential intensity values of multiple frames of impedance state matrices, calculate the interference intensity difference. If the interference intensity difference is greater than or equal to the interference threshold value, it indicates that there is an impedance blind area in this region. Perform propagation model constraint compensation on the current region, perform iterative correction on the electric potential intensity distribution of the current region according to the path loss model corresponding to the current region, and calculate the intensity compensation value of the blind area electric potential according to the correction result; Perform potential intensity modeling on the impedance state matrix according to the described potential intensity distribution, and perform time delay annotation on the potential model of the region through the transmission delay characteristics.

[0010] Preferably, the calculation of the potential intensity gradient according to the impedance sensor position includes: Extract the potential intensity change points according to multiple groups of impedance coverage data, map the change points to a unified electrode coordinate system according to the deployment positions of the sensors, and fit the change points through a spatial interpolation algorithm to generate a potential field model of the region; Perform equally spaced sampling along the transmission path of the potential field model, calculate the voltage attenuation rate, interference fluctuation index, and potential change slope of the path according to the sampling results, and calculate the potential change parameters according to the voltage attenuation rate, interference fluctuation index, and potential change slope; According to the deployment parameters and acquisition accuracy of the impedance sensors, project the distribution characteristics of impedance changes in each frame of data onto the potential field model, partition according to the number of sensors along the transmission direction of the potential field model, analyze the change rules of impedance changes within the partitions, and calculate the impedance distribution characteristics according to the change rules; Calculate the potential intensity gradient according to the potential change parameters and the impedance distribution characteristics. The calculation process of the potential intensity gradient includes: based on the electrode position range from the first impedance sensor to the last impedance sensor, select spatial coordinate points in the sensor deployment direction, accumulate and calculate the product of the potential field strength characteristic weight value and the impedance distribution characteristic weight value within the spatial resolution range, and superimpose the influence value of the sensor acquisition frequency on the potential intensity change rate.

[0011] Preferably, the calculation of the impedance prediction information for each sub-region includes: Taking the main transmission path of the potential field model as the reference line, taking the peak position of the impedance change in each frame of data as the reference point, calculating the impedance offset, and drawing the impedance distribution curve according to the electrode coordinates; Correct the change rate and direction in the impedance change trend according to the potential intensity gradient; Starting from the nearest impedance distribution point, continue to draw the distribution curve according to the corrected results of the change rate and direction to generate the impedance distribution points in the next time period until the distribution points cover the entire target region to generate the impedance prediction information.

[0012] Preferably, the construction of the impedance optimization model includes: The input layer is used to organize the impedance prediction information into spatial distribution data and perform normalization processing; The feature fusion layer is used to extract the regional association features of the impedance by processing the spatial distribution data and construct the dependence relationship between electrode units; The parameter optimization layer is used to integrate the correlation relationship of the electrode impedance on the spatial unit and generate an electrode parameter optimization strategy.

[0013] Preferably, the obtaining of the distribution characteristics of the electrode impedance includes: According to the spatio-temporal distribution characteristics of the electrode impedance output by the impedance optimization model, the identification of the sub-region is corresponded to the spatio-temporal distribution characteristics; Reorganize the regional data in the impedance state dataset according to the spatio-temporal characteristics to generate a regional distribution map sorted by impedance intensity; According to the reorganized regional distribution map, output the optimized distribution characteristics of the electrode impedance.

[0014] Preferably, the dynamic optimization of the regional electrode parameters includes: One-to-one map the regional identification to the regions of the distribution characteristics of the electrode impedance; According to the spatio-temporal distribution characteristics of the electrode impedance, control the execution actions of the electrode parameters, including voltage adjustment, current aggregation and resistance distribution operations; According to the spatial distribution of the electrode impedance and the preset parameter optimization strategy, dynamically allocate the electrode parameters to the corresponding electrode regions.

[0015] Preferably, the control of the execution actions of the electrode parameters includes: When the electrode impedance reaches the preset intensity threshold in the target region, trigger the voltage boost command for the adjacent electrodes; Dynamically combine the available circuit resources according to the current aggregation strategy to generate a resistance distribution vector; Adjust the electrode parameters of the transmission nodes in the target region based on the resistance distribution vector.

[0016] Compared with the prior art, the beneficial effects of the present invention are: By deploying multiple impedance sensors on the porous gradient anode, the voltage data and current data of the electrodes in the region are collected at set distance intervals to generate an impedance state dataset. This distributed sensor network coverage mode can comprehensively capture the impedance information of different regions of the electrode compared with the traditional single-point measurement, effectively solve the problem of local measurement deviation caused by uneven impedance distribution under the porous gradient structure, greatly improve the spatial resolution and integrity of data collection, and lay a solid data foundation for the subsequent accurate analysis of impedance distribution characteristics.

[0017] The optimization controller receives the real-time impedance state data of multiple impedance sensors and constructs a regional impedance state matrix. Through operations such as normalization processing, noise filtering, and eigen-decomposition of the matrix, key information such as the distribution of potential intensity, transmission delay characteristics, and impedance change trends is extracted. Among them, the calculation of spatial correlation characteristics and the construction of a feature fusion network can deeply analyze the interference intensity between regions, the link stability coefficient, and the impedance blind area index, effectively overcoming the influence of complex factors such as mutual interference between electrodes, transmission delay, and impedance blind area on impedance analysis, and ensuring the accuracy and reliability of the extracted features.

[0018] In the process of determining the electrode impedance distribution characteristics, the regional electrodes are divided into multiple sub-regions and labeled and associated through potential intensity modeling. Combining the calculation of potential intensity gradient and the generation of impedance prediction information, the dynamic prediction of the spatio-temporal distribution of electrode impedance is realized. Based on the spatial correlation modeling of the impedance optimization model, the dependence relationship between electrode units can be accurately captured, and the distribution characteristics reflecting the spatio-temporal evolution law of electrode impedance are output, providing a scientific basis for the dynamic optimization of electrode parameters. This complete process from data acquisition, feature extraction to modeling prediction forms a closed-loop analysis system for impedance distribution characteristics, significantly improving the cognitive depth and prediction accuracy of the impedance distribution of porous gradient anodes.

[0019] According to the impedance distribution characteristics, the regional electrode parameters are dynamically optimized. By mapping the regional label to the impedance distribution characteristics, the spatial precise positioning of electrode parameter adjustment is realized. Controlling the electrode parameters to perform operations such as voltage adjustment, current aggregation, and resistance distribution can adjust the working parameters in real time according to the impedance state of different regions. For example, when the impedance of the target region electrode reaches the preset intensity threshold, a voltage increase instruction for adjacent electrodes is triggered, and a resistance distribution vector is generated by dynamically combining available circuit resources and the transmission node parameters are adjusted, realizing the rapid response and local regulation of the impedance abnormal region. This dynamic optimization strategy based on spatio-temporal distribution characteristics breaks the limitations of traditional static parameter adjustment, enables the dynamic matching of the electrode working state and the impedance distribution, and effectively improves the overall performance and operation stability of the solid oxide fuel cell.

[0020] By real-time updating the impedance state data set, a closed-loop optimization mechanism of "data acquisition - modeling analysis - parameter optimization - data feedback" is formed. This mechanism can continuously track the dynamic evolution process of electrode impedance, continuously optimize the model parameters and adjust the electrode working state, so that the system is always in the optimal operation state, significantly extending the service life of the solid oxide fuel cell, reducing the maintenance cost, and providing a strong guarantee for its long-term stable operation in practical applications. Brief Description of the Drawings

[0021] Figure 1 It is the working principle diagram of the impedance optimization method for the porous gradient anode-supported solid oxide fuel cell described in the present invention; Figure 2 Working schematic diagram for determining the electrode impedance distribution characteristics; Figure 3 Working schematic diagram for calculating the electric potential intensity gradient. Specific implementation manners

[0022] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0023] Please refer to Figures 1 - 3 , the impedance optimization method for a porous gradient anode-supported solid fuel cell involved in the present invention is applied to a solid fuel cell management system. The system includes a plurality of impedance sensors deployed on the porous gradient anode and an optimization controller connected to the impedance sensors, and the distance between two adjacent impedance sensors is a set distance. The specific implementation scheme is as follows: Step 1: Through a plurality of impedance sensors deployed on the porous gradient anode, the voltage data and current data of the electrodes in each region are collected in real time. Each impedance sensor periodically samples the electrical parameters of the electrode at its location according to a preset sampling frequency. After timestamping the collected voltage data and current data, they are encapsulated according to a preset data format to generate an impedance status data set containing information such as the location of each sensor, sampling time, voltage value, and current value. This data set serves as the basic data for subsequent analysis and processing and is used to reflect the impedance status of the electrode at different times and locations.

[0024] Step 2: The optimization controller receives the real-time impedance status data sent by a plurality of impedance sensors through a communication link. According to the deployment locations and numbers of the impedance sensors, the received data is arranged in the order of spatial positions to construct a regional impedance status matrix. The rows and columns of this matrix respectively correspond to the spatial coordinate directions of the electrode regions, and each element in the matrix represents the impedance status data collected by the sensor at the corresponding position, thereby visually presenting the spatial distribution of the electrode impedance in the form of a matrix and providing a structured data basis for subsequent analysis of the impedance distribution characteristics.

[0025] Step 3: Process the impedance status matrix, extract impedance characteristics in combination with the impedance status data set, and predict the impedance distribution based on the electric potential gradient and electrolyte path information. The spatio-temporal distribution characteristics of the electrode impedance are output through an impedance optimization model, and the impedance status data set is updated according to the spatio-temporal distribution characteristics. The specific process is as follows: Process the impedance state matrix to extract the electric potential intensity distribution, transmission delay characteristics, and impedance change trend; perform electric potential intensity modeling on the impedance state matrix according to the electric potential intensity distribution and transmission delay characteristics, divide the regional electrodes into multiple sub-regions and mark the region identifiers, and associate and match the electric potential intensity of the sub-regions with the impedance state data set to mark the region identifiers in the impedance state data set; calculate the electric potential intensity gradient according to the impedance sensor position, predict the distribution of electrode impedance according to the electric potential intensity gradient and impedance change trend, and calculate the impedance prediction information of each sub-region; construct an impedance optimization model, use the impedance prediction information as input parameters, perform spatial correlation modeling on the impedance prediction information through the impedance optimization model, and output the spatio-temporal distribution characteristics of electrode impedance; update the impedance state data set according to the spatio-temporal distribution characteristics to obtain the distribution characteristics of electrode impedance.

[0026] Step 4: Dynamically adjust the regional electrode parameters according to the electrode impedance distribution characteristics determined in Step 3. Specifically, associate the distribution characteristics of the electrode impedance with the physical position of the electrode region, analyze the reasons for impedance anomalies in different regions, and generate corresponding parameter adjustment instructions through an optimization controller for the impedance conditions of each region to dynamically optimize parameters such as the voltage, current, and resistance of the electrode, so as to reduce the non-uniformity of the electrode impedance and improve the overall performance and stability of the solid oxide fuel cell.

[0027] The present invention will be further described below in conjunction with Embodiments 1 to 5:

[0028] Embodiment 1: In this embodiment, the process of determining the electrode impedance distribution characteristics needs to carry out detailed operations from links such as impedance state matrix processing, electric potential intensity modeling, and related feature extraction. When first processing the impedance state matrix, it is necessary to first perform a standardization processing step, that is, convert the voltage and current data with different dimensions in the matrix into numerical values with a unified dimension through a data normalization algorithm, so that the data at each position is comparable. For example, the min-max normalization method can be used to map the value of each data point to the interval [0,1] to eliminate the influence of sensor acquisition accuracy differences and different physical quantity units on subsequent analysis.

[0029] After completing the standardization, intercept the impedance hot spot area in the matrix through the sliding window technique. The size and step length of the sliding window can be set according to the sensor deployment density and electrode region characteristics. For example, set the window to cover an area of 5×5 sensor positions, with a step length of 1 sensor spacing, scan the matrix row by row and column by column, and identify the hot spot areas where the impedance values are significantly higher or lower than the surrounding areas. For these hot spot areas, use median filtering or Gaussian filtering algorithms to filter out noise and remove abnormal data points caused by factors such as electromagnetic interference and sensor transient failures, and retain the effective data reflecting the true impedance state.

[0030] The filtered matrix data is processed using eigenvalue decomposition algorithms (such as principal component analysis PCA) to calculate the impedance change trend. Through eigenvalue decomposition, the high-dimensional impedance state data is mapped to a low-dimensional feature space, the main eigenvectors are extracted, and the variation law over time is analyzed to determine the rising, falling, or fluctuating trend of impedance in the overall region. For example, by observing the change curve of the principal component scores over time, the rate and periodic characteristics of impedance change are judged.

[0031] When calculating the spatial correlation characteristics of the impedance state matrix, spatial autocorrelation analysis methods (such as Moran's index) can be used to measure the correlation between sensor data at different positions. According to the calculation results, the interference intensity between regions is determined, that is, the degree to which the impedance changes in adjacent regions affect each other; the link stability coefficient is calculated to evaluate the reliability of the data transmission link between sensors; the impedance blind area index is calculated to identify regions where data may be missing or the impedance is abnormally stable. When constructing a feature fusion network, a fully connected neural network structure can be adopted, taking parameters such as interference intensity, link stability coefficient, and impedance blind area index as inputs, and through the non-linear transformation of multiple layers of neurons, the transmission delay feature is output, that is, the time delay value of the signal transmission between different regions.

[0032] When extracting the time-domain features and frequency-domain features of the data collected by each impedance sensor, the time-domain features can include the mean voltage, current variance, rise time, etc., and the frequency-domain features can obtain the amplitudes and phases of each frequency component through fast Fourier transform (FFT). According to the phase difference between the time-domain features and the frequency-domain features, the impedance feature vector of the sensor is calculated, and this vector contains the amplitude and phase information of the impedance at the position where the sensor is located. By matching the impedance feature vectors of sensors at different positions through algorithms such as cosine similarity, the consistency of the impedance change trend is analyzed, for example, to judge whether the impedance changes between adjacent sensors are synchronized or there is a phase difference.

[0033] When modeling the electric potential intensity of the impedance state matrix, first, according to the electric potential intensity distribution, the electric potential intensity sampling points are extracted from each frame of data. The selection of sampling points can be based on the sensor position or evenly distributed in the electrode area through interpolation methods. The sampling points are associated and mapped with the transmission delay feature, that is, for each sampling point, its electric potential intensity value and the corresponding signal transmission delay time are recorded to generate an electric potential intensity map. Through spatial transformation algorithms (such as translation, rotation, scaling), the electric potential intensity maps collected by multiple sensors are spatially aligned so that the maps of different sensors coincide in a unified electrode coordinate system, thereby accurately calculating the electric potential intensity distribution of the region, for example, determining the positions and ranges of high-electric-potential regions and low-electric-potential regions.

[0034] Set an interference threshold value (such as twice the average interference intensity statistically based on historical data), and analyze the potential intensity values of multiple-frame impedance state matrices. By comparing the potential intensity differences between adjacent frames or adjacent regions, locate the possible positions of interference sources. Calculate the interference intensity difference. If the difference is greater than or equal to the interference threshold value, it indicates that there may be an impedance blind area in this region, that is, a region where impedance data cannot be accurately obtained due to interference. At this time, perform propagation model constraint compensation on the current region. According to the path loss model corresponding to this region (such as free space propagation model, log-distance attenuation model), iteratively correct the potential intensity distribution. For example, assume the path loss model is (where is the reference distance loss, is the path loss exponent, is the distance, is the Gaussian noise). By iteratively adjusting the model parameters, make the corrected potential intensity value match the actual measured value, and then calculate the intensity compensation value of the potential in the blind area to correct the potential data deviation caused by the blind area.

[0035] Finally, based on the corrected potential intensity distribution, perform potential intensity modeling on the impedance state matrix, and mark the corresponding potential intensity value at each element position in the matrix. At the same time, perform time delay annotation on the potential model of the region through the transmission delay feature, that is, record the time delay information of the potential change in each region in the potential intensity map or matrix, such as the time difference between the potential change in a certain region and the reference point, so as to consider the influence of time factors when analyzing the impedance distribution later.

[0036] During the process of processing the impedance state matrix, it is necessary to ensure that the data processing logic of each link is coherent. For example, normalization processing provides a unified data basis for subsequent feature extraction and modeling, noise filtering avoids the interference of abnormal data on the analysis results, and feature decomposition and spatial correlation analysis reveal the laws of impedance changes from different dimensions. The potential intensity modeling link realizes the accurate characterization of the potential distribution in the electrode region through sampling point selection, map alignment, and interference compensation, providing a reliable basis for subsequent calculation of potential intensity gradient and impedance prediction.

[0037] Example 2: In this embodiment, calculating the potential intensity gradient is a key step in determining the impedance distribution characteristics of the electrode, which needs to be achieved through a series of operations such as data processing, model construction, and parameter calculation starting from multiple groups of impedance coverage data. First, preprocess multiple groups of impedance coverage data to identify and extract potential intensity change points. These change points are the positions where the potential intensity in the electrode region changes significantly, and can be determined by comparing the potential differences between adjacent data points. For example, set a potential change threshold. When the potential difference between two adjacent points exceeds this threshold, mark the position between these two points as a potential intensity change point.

[0038] According to the deployment positions of the sensors, map the extracted potential intensity change points to a unified electrode coordinate system. This coordinate system takes a certain fixed point of the electrode as the origin, defines clear axis directions and unit lengths, so that the change points at different positions have a unified coordinate representation. Through this mapping, the scattered change points can be integrated into a complete spatial framework, facilitating subsequent analysis and processing.

[0039] After completing the coordinate mapping of the change points, use a spatial interpolation algorithm to fit these points to generate a potential field model. The spatial interpolation algorithm can choose methods such as polynomial interpolation or spline interpolation. According to the known positions of the change points and potential intensity values, estimate the potential intensity at any position within the entire electrode region. For example, polynomial interpolation fits a polynomial function so that its function values at the known change points are equal to the actual potential intensity values, thereby obtaining the potential distribution of the entire region. The generated potential field model represents the potential distribution within the electrode region in the form of a continuous function.

[0040] Perform equally spaced sampling along the transmission path of the potential field model to obtain data such as voltage values, interference values, and potential values at each sampling point on the path. The size of the sampling interval can be set according to the length and accuracy requirements of the transmission path to ensure that the potential change characteristics on the path can be fully captured. For each sampling point, record its position coordinates in the electrode coordinate system and the corresponding voltage, interference, and potential values to form a set of sampling data.

[0041] According to the sampling results, calculate the voltage attenuation rate, interference fluctuation index, and potential change slope of the path. The voltage attenuation rate reflects the change of voltage with distance on the transmission path and is calculated by comparing the voltage value differences between adjacent sampling points and combining the distance information. The interference fluctuation index measures the fluctuation degree of the interference signal on the path and can be determined by calculating statistical quantities such as the standard deviation or variance of the interference values. The potential change slope represents the rate of change of potential with distance and is obtained by performing a difference calculation on the potential values of adjacent sampling points. Combining these three parameters, calculate the potential change parameter, which is used to describe the overall change characteristics of the potential on the transmission path and provides an important basis for subsequent analysis of the potential distribution.

[0042] According to the deployment parameters and acquisition accuracy of the impedance sensors, project the distribution characteristics of impedance changes in each frame of data onto the potential field model. The deployment parameters of the sensors include the spacing between sensors, position coordinates, etc., and the acquisition accuracy determines the resolution and accuracy of the data. By spatially aligning the distribution characteristics of impedance changes with the potential field model, the relationship between impedance changes and potential distribution can be analyzed. For example, observe the corresponding relationship between high-impedance regions and potential distribution to determine whether there is a situation where regions with large potential gradients correspond to high-impedance regions.

[0043] According to the number of sensors, the electrode region is divided into multiple partitions along the transmission direction of the electric potential field model. The size of each partition can be adjusted according to the distribution density of the sensors and the characteristics of the electrode region to ensure that the impedance changes within each partition have a certain similarity and regularity. Analyze the law of impedance change within each partition, such as statistically analyzing the distribution range of impedance values, determining its maximum, minimum, and average values; observing the trend of impedance change over time to judge whether it is rising, falling, or fluctuating, etc.

[0044] Based on the law of impedance change within the partition, calculate the impedance distribution characteristics. These characteristics include statistical quantities such as the average value, variance, maximum value, and minimum value of the impedance, as well as characteristic parameters such as skewness and kurtosis of the impedance distribution. Through the analysis of these characteristics, the distribution of impedance within the electrode region can be comprehensively understood, providing data support for the subsequent calculation of the electric potential intensity gradient.

[0045] When calculating the electric potential intensity gradient, based on the electrode position range from the first impedance sensor to the last impedance sensor, select multiple spatial coordinate points in the sensor deployment direction. The selection of these coordinate points should cover the entire electrode region and be as evenly distributed as possible to ensure that the spatial variation of the electric potential intensity can be accurately reflected.

[0046] For each selected spatial coordinate point, cumulatively calculate the product of the weight value of the electric potential field strength characteristics and the weight value of the impedance distribution characteristics within the spatial resolution range where the point is located. The spatial resolution range can be set according to the calculation accuracy requirements and actual situations, such as a small area centered on this point. The weight value of the electric potential field strength characteristics reflects the influence degree of the electric potential field strength around this point on the overall gradient, and the weight value of the impedance distribution characteristics represents the contribution of the impedance distribution around this point to the gradient. The specific calculation of these two weight values can be determined based on the analysis results of the electric potential field model and impedance distribution characteristics, combined with the actual application scenario.

[0047] At the same time, consider the influence value of the sensor acquisition frequency on the change rate of the electric potential intensity. The higher the sensor acquisition frequency, the denser the acquired data, and the faster changes in the electric potential intensity can be more accurately captured; conversely, when the acquisition frequency is lower, some details of the rapid changes may be missed. Therefore, when calculating the electric potential intensity gradient, the influence value of the sensor acquisition frequency on the change rate of the electric potential intensity needs to be superimposed on the previous calculation results. By comprehensively considering factors such as the electric potential field strength characteristics, impedance distribution characteristics, and sensor acquisition frequency, the electric potential intensity gradient that accurately reflects the spatial change rate of the electric potential intensity is finally obtained.

[0048] Throughout the calculation process, every step of data processing is closely linked, and the result of the previous step provides the basis for the calculation of the next step. For example, the construction of the electric potential field model depends on the extraction and interpolation fitting of the electric potential intensity change points, and the calculation of the impedance distribution characteristics is based on the electric potential field model and the partition analysis. The deployment parameters and acquisition accuracy of the sensors also play an important constraint role throughout the process, affecting the quality of the data and the accuracy of the calculation results.

[0049] Embodiment 3: In this embodiment, calculating the impedance prediction information of each sub-region requires combining multiple aspects of information such as the electric potential field model, the electric potential intensity gradient, and the impedance change trend, and is achieved through steps such as baseline setting, trend correction, and curve drawing. First, use the main transmission path of the electric potential field model as the baseline. This main path is usually the main direction of electric potential transmission within the electrode region and can be determined by analyzing the distribution law of the electric potential intensity in the electric potential field model. For example, select the direction with the most significant change in electric potential intensity or the longest transmission path as the main path. In each frame of data, identify the peak positions of impedance changes, that is, the positions where the impedance value reaches the local maximum or minimum, and use them as reference points. Calculate the impedance offset of the reference point relative to the baseline. This offset is determined by the difference between the horizontal coordinate of the reference point in the electrode coordinate system and the baseline coordinate, and is used to measure the deviation degree of the impedance distribution relative to the main transmission path. For example, if the baseline is the x-axis, the horizontal coordinate of the reference point is x1, and the baseline coordinate is x0, then the impedance offset is |x1 - x0|.

[0050] According to the coordinate order of the electrode coordinate system, correspond the impedance values and position information of each reference point, and draw the impedance distribution curve. When drawing, use the horizontal coordinate to represent the spatial position of the electrode region, and the vertical coordinate to represent the impedance value. Connect the points with a smooth curve to visually display the spatial distribution pattern of the impedance, such as whether there are single peaks, multiple peaks, or uniform distribution and other characteristics.

[0051] According to the calculated electric potential intensity gradient, correct the change rate and direction in the impedance change trend. The electric potential intensity gradient reflects the change rate and direction of the electric potential in space. When the electric potential intensity gradient in a certain region is large, it indicates that the electric potential in this region changes violently, which may have a significant impact on the transmission of ions or electrons, and thus lead to an acceleration of the impedance change rate or a change in direction. For example, in a region where the electric potential intensity gradient is positive (the electric potential increases with the increase of the spatial position), if the original impedance change trend is upward, the change rate may increase due to the driving effect of the electric potential; if the trend is downward, the downward rate may slow down due to the hindering effect of the electric potential. When correcting, multiply the electric potential intensity gradient value by a preset correction coefficient to obtain the adjustment amount for the change rate and direction, and then superimpose the adjustment amount onto the original change trend parameters to form the corrected change rate and direction parameters.

[0052] Starting from the nearest impedance distribution point, that is, selecting the impedance distribution point at the current moment or the most recent sampling as the starting point, and gradually predicting the impedance distribution points in the next time period according to the corrected change rate and direction. During prediction, according to the preset time interval (such as ), or spatial interval (such as ), calculate the impedance value and position of the next point. For example, if the impedance value of the current point is , the position is , the corrected change rate is (in units of or ), and the direction is positive (indicating that the impedance increases with the increase of time or space), then the impedance value of the next point is: (or ), and the position is: (or the time is ).

[0053] When drawing the distribution curve, it is necessary to ensure that the changes between adjacent points conform to the corrected trend, and avoid sudden changes or unreasonable fluctuations. Through point-by-point prediction and drawing, the distribution curve gradually covers the entire target area until all sub-areas are included. The generated impedance prediction information includes the predicted impedance values and the corresponding relationships of spatial positions in each sub-area in the future time period, and is stored in the form of a data table or graph for subsequent input into the impedance optimization model for processing.

[0054] In the whole calculation process, the accurate selection of the reference line is the key, and its rationality directly affects the calculation of the impedance offset and the shape of the distribution curve. The correction effect of the electric potential intensity gradient needs to be based on the theoretical analysis of the electrode physical characteristics and the transmission mechanism to ensure that the correction logic conforms to the actual physical laws. The setting of the time interval or spatial interval during the prediction process needs to comprehensively consider the sensor acquisition frequency and the electrode reaction speed to avoid the prediction result being distorted due to too large an interval or increasing the calculation complexity due to too small an interval. In addition, when drawing the impedance distribution curve, a suitable smoothing algorithm, such as the moving average method or the spline smoothing method, should be used to eliminate the curve fluctuations caused by data noise and make the prediction result more credible.

[0055] Example 4: In this example, constructing the impedance optimization model is the core link to realize the analysis of the spatio-temporal distribution characteristics of the electrode impedance and parameter optimization, and it needs to be elaborated in detail from aspects such as the model architecture design, the implementation of each layer's functions, and the data processing flow. This model is divided into an input layer, a feature fusion layer, and a parameter optimization layer, and a complete optimization logic chain is formed through data transfer and algorithm processing between each layer.

[0056] The primary task of the input layer is to organize the calculated impedance prediction information into spatial distribution data. The impedance prediction information contains the impedance values and corresponding spatial coordinates of each sub-region in the future period. The input layer needs to arrange these discrete point data in the order of the spatial coordinates of the electrode area to form a data set with a clear spatial position index. For example, the data is stored in the form of a two-dimensional matrix, where the rows and columns of the matrix correspond to the horizontal and vertical coordinates of the electrode area, respectively, and the matrix elements are the impedance prediction values of the corresponding positions, so that the data presents a spatial distribution structure consistent with the physical layout of the electrode.

[0057] The input layer normalizes the spatial distribution data. Since the impedance values of different sub-regions may have dimension differences or numerical range differences, standardization can eliminate the impact of these differences on model training. In specific operations, the normalization method can be used to map each impedance value to a specific interval (such as [0,1] or [-1,1]). The mapping is usually achieved by calculating the maximum, minimum, mean, and standard deviation of the data and using a linear transformation formula. For example, for a certain impedance value Z, the formula Calculate the normalized value ,in and are the maximum and minimum values in the batch of data respectively. The standardized spatial distribution data is taken as the output of the input layer and passed to the feature fusion layer.

[0058] The core function of the feature fusion layer is to process spatially distributed data through algorithms, extract regional correlation features of impedance, and construct dependencies between electrode units. This layer can use a variety of neural network structures or signal processing algorithms, such as convolutional neural networks (CNNs), graph neural networks (GNNs), or self-attention mechanisms (Self-Attention). Taking convolutional neural networks as an example, by designing convolution kernels of different sizes, convolution operations are performed on spatially distributed data to capture local regional correlation features at different scales. For example, a 3×3 convolution kernel can extract direct associations between adjacent sub-regions, while a 5×5 convolution kernel can capture indirect effects over a larger range.

[0059] In the feature extraction process, the standardized spatial distribution data is first used as the input of the convolution layer, and the characteristic response value of each position is calculated through the sliding window operation of the convolution kernel. The characteristic response value reflects the impedance distribution characteristics of the position and its neighborhood. The nonlinear transformation is introduced through the activation function (such as ReLU) to enhance the model's ability to express complex associated features. After alternating processing of multiple convolutional layers and pooling layers, features from low-level to high-level are gradually extracted, such as the impedance value features of a single sub-region, the gradient features of adjacent regions, and the long-range dependency features across regions.

[0060] In addition to convolutional neural networks, graph neural networks are also an effective feature fusion method. Each electrode sub-region is regarded as a node in the graph structure, the node attribute is the impedance prediction value of this region, and the edges between nodes represent the spatial adjacency relationship or dependence strength between sub-regions. Through graph convolutional operation (GCN) or graph attention operation (GAT), nodes can aggregate the feature information of neighboring nodes, thereby capturing the mutual influence between regions. For example, the graph attention mechanism can dynamically adjust the contribution degree of different neighboring nodes to the feature update of the current node by calculating the attention weights between nodes, and then construct a more flexible electrode unit dependence relationship model.

[0061] The output of the feature fusion layer is a high-dimensional feature vector containing region-associated features. These feature vectors not only retain the impedance information of each sub-region but also encode the spatial dependence relationships between sub-regions, such as the synchrony of impedance changes in adjacent regions and the coupling effect of distant regions. These features provide in-depth spatial association information for the parameter optimization layer, enabling the model to analyze the impedance distribution problem from a global perspective.

[0062] The main function of the parameter optimization layer is to integrate the association relationships of electrode impedance on spatial units and generate an electrode parameter optimization strategy. This layer is usually composed of models such as fully connected neural networks or decision trees. It receives the high-dimensional feature vectors output by the feature fusion layer and performs feature mapping through multiple layers of non-linear transformations. First, the fully connected layer compresses the high-dimensional feature vectors to a lower dimension and extracts the most critical feature components for parameter optimization. For example, by setting multiple fully connected layers, the feature dimension is gradually reduced from several hundred dimensions to dozens of dimensions. At the same time, through the learning of the weight matrix, the features related to parameter optimization are strengthened, and redundant information is suppressed.

[0063] When integrating spatial association relationships, the parameter optimization layer needs to consider the physical constraints and optimization objectives of electrode parameter adjustment. Physical constraints include voltage adjustment range, current-carrying capacity, resistance adjustable accuracy, etc. The optimization objective is usually to minimize the overall impedance, balance the impedance distribution, or improve the fuel cell output power. For example, if the optimization objective is to minimize the overall impedance, the model can measure the difference between the predicted impedance and the target impedance through a loss function (such as mean squared error), and update the model parameters through the backpropagation algorithm, so that the generated optimization strategy can effectively reduce the impedance value.

[0064] When generating the electrode parameter optimization strategy, the parameter optimization layer will output the parameter adjustment values corresponding to each sub-region, such as voltage adjustment amount, current aggregation coefficient, resistance distribution ratio, etc. These adjustment values need to correspond one-to-one with the spatial positions of the sub-regions to ensure that the optimization controller can accurately send parameter instructions to the target region. For example, for a high-impedance sub-region, the model may generate a strategy to increase the voltage of adjacent regions and reduce the resistance of this region to reduce its impedance value through potential gradient adjustment and current path optimization.

[0065] During the model training process, historical impedance data and the corresponding parameter adjustment effects need to be used as training samples. Through continuous iterative training, the model can learn the optimal parameter adjustment strategies under different impedance distribution patterns. During the training process, attention should be paid to avoiding overfitting, and methods such as regularization techniques (such as L2 regularization), dropout layers, or cross-validation can be used to improve the generalization ability of the model.

[0066] The construction process of the entire impedance optimization model needs to be closely combined with the physical characteristics of the electrodes and the operating mechanism of the fuel cell. For example, the regional correlation features extracted by the feature fusion layer need to conform to the physical laws of ion transport, and the strategies generated by the parameter optimization layer need to meet the electrical performance constraints of the electrode materials. The input and output design of the model should form a closed loop with the front-end data acquisition and the back-end actuators to ensure the smooth connection of the entire process from impedance data acquisition, feature analysis to parameter optimization.

[0067] Through data standardization in the input layer, extraction of spatial correlation features in the feature fusion layer, and generation of strategies in the parameter optimization layer, the impedance optimization model can efficiently process complex impedance distribution data and output an optimization scheme with physical significance and practical operability.

[0068] Example 5: In this embodiment, the dynamic optimization of regional electrode parameters needs to be achieved through links such as regional identification mapping, execution action control, and parameter allocation. Each step closely focuses on the spatio-temporal distribution characteristics of electrode impedance to ensure the pertinence and effectiveness of the optimization strategy. First, perform regional mapping of regional identification and electrode impedance distribution characteristics. After determining the spatio-temporal distribution characteristics of electrode impedance, each sub-region has been assigned a unique regional identification (such as a number or a coordinate interval) through the electric potential intensity modeling process. At this time, establish a one-to-one mapping relationship between these regional identifications and the corresponding impedance distribution characteristics (such as impedance value range, change trend, spatial position) to form a regional-impedance feature comparison table. For example, the sub-region numbered A1 corresponds to a high-impedance region, whose impedance value is higher than the preset threshold and shows an upward trend, and is located in the left-edge region of the electrode; the sub-region numbered B3 corresponds to a low-impedance region, whose impedance value is stable within the normal range and is located in the central region of the electrode. This comparison table serves as the basic data for subsequent parameter adjustment, enabling the optimization controller to quickly locate the regions that need to be adjusted.

[0069] According to the spatio-temporal distribution characteristics of electrode impedance, control the execution actions of electrode parameters, including voltage adjustment, current aggregation, and resistance distribution operations. When it is monitored that the electrode impedance of a certain target area reaches a preset intensity threshold (such as higher than the upper limit value of the normal operating range), a voltage boost instruction for adjacent electrodes is triggered. Specifically, by looking up the area-impedance characteristic comparison table, determine the location of the target area and the adjacent area identifier, and send a voltage boost signal to the electrodes in the adjacent area. By increasing the electric potential of the adjacent area, a potential gradient difference is formed to guide the flow of ions or electrons towards the target area, thereby reducing the impedance of the target area. For example, if the target area is the A1 area at the left edge, and its adjacent right area is A2, the voltage of the A2 area can be increased by 5% to form a potential gradient from A2 to A1 to promote charge transfer.

[0070] The current aggregation operation needs to dynamically combine available circuit resources according to a preset current aggregation strategy. The circuit resources include current channels, power supply modules, and load units in each sub-area, etc. By analyzing the impedance states of each sub-area, determine which current channels in which areas can be activated or closed to achieve reasonable current distribution. For example, for the low-impedance B3 central area, because of its high charge transfer efficiency, more current channels can be activated to converge more current; for the high-impedance A1 area, temporarily reduce its current load to avoid energy loss. When generating the resistance distribution vector, a corresponding resistance adjustment value needs to be assigned to each sub-area. This vector is stored in the form of a matrix or a list, and each element corresponds to the resistance adjustment direction (increase or decrease) and amplitude (such as percentage) of a sub-area. For example, the resistance adjustment value of the A1 area in the resistance distribution vector is -10%, indicating that the resistance of this area needs to be reduced by 10% to reduce the impedance; the resistance adjustment value of the B3 area is 0%, indicating to maintain the current resistance state.

[0071] Based on the resistance distribution vector, adjust the electrode parameters of the transmission nodes in the target area. The transmission node is a key position responsible for current transmission within the electrode area, and each node corresponds to one or more sub-areas. Send the resistance adjustment instruction to the actuator (such as a variable resistor) of the target transmission node through a communication link, and the actuator adjusts the resistance value of the node according to the instruction, thereby changing the current transmission characteristics of this area. The adjustment process needs to follow the order of low-priority areas first and then high-priority areas to avoid system fluctuations caused by simultaneously adjusting multiple key areas.

[0072] According to the spatial distribution of electrode impedance and the preset parameter optimization strategy, the electrode parameters are dynamically allocated to the corresponding electrode area. The parameter optimization strategy predefines the adjustment rules for different impedance distribution scenarios. For example, when a local high impedance area appears, the voltage and resistance of the area and its adjacent areas are adjusted first; when the overall impedance distribution is uniform but high, a global current aggregation strategy is adopted. According to the spatial distribution pattern of the current impedance, the corresponding optimization strategy is matched to generate a specific parameter allocation plan. For example, if a strip-shaped high impedance area is detected on the right side of the electrode, the "local area voltage-resistance coordinated adjustment strategy" is matched to adjust the voltage and resistance of the strip area and its upper and lower adjacent areas in a coordinated manner. The voltage increase is 3%-5%, and the resistance reduction is 8%-12%. The specific values are determined according to the degree of regional impedance deviation.

[0073] When dynamically allocating electrode parameters, the timing and coordination of parameter adjustments need to be considered. For example, voltage adjustment and resistance adjustment need to be performed in sequence. Usually, the voltage is adjusted first to establish the potential gradient, and then the resistance is adjusted to optimize the current path to avoid charge transfer disorder caused by simultaneous adjustments. For cross-region parameter adjustments (such as simultaneous adjustments of multiple adjacent regions), synchronization signals are required to ensure that the execution actions of each region are consistent in time to prevent new impedance imbalances caused by differences in adjustment timing.

[0074] The entire dynamic optimization process requires real-time monitoring of the impedance feedback data after the electrode parameters are adjusted. The impedance sensor collects the voltage and current data of each area in real time, calculates the adjusted impedance value, and compares it with the optimization target. If the adjusted impedance value does not achieve the expected effect (such as still higher than the threshold or the distribution is still uneven), the secondary optimization process is triggered to re-analyze the impedance distribution characteristics, adjust the optimization strategy and parameter allocation plan until the optimization target is met.

[0075] During the implementation process, the physical properties of the electrodes and the safe operation specifications of the fuel cell must be strictly followed. For example, the voltage adjustment range must not exceed the tolerance limit of the electrode material, and the resistance adjustment range must be within the adjustable range of the actuator. At the same time, it is necessary to avoid frequent parameter adjustments that lead to fatigue loss of the electrode components, and set a reasonable adjustment interval (such as waiting for 5-10 minutes after each adjustment, and then monitoring and adjusting the next time after the system is stable).

[0076] It should be noted that in this text, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device.

[0077] Although the embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for optimizing the impedance of a porous gradient anode-supported solid oxide fuel cell, which is applied to a solid oxide fuel cell management system. The system includes a plurality of impedance sensors deployed on the porous gradient anode and an optimization controller connected to the impedance sensors. The distance between two adjacent impedance sensors is a set distance. The method is characterized in that, The method includes: Collecting voltage data and current data of electrodes within the area through the impedance sensor to generate an impedance state data set; Receiving real-time impedance state data of multiple impedance sensors through the optimization controller to construct a regional impedance state matrix; Determining the distribution characteristics of the electrode impedance according to the impedance state data set and the real-time data of each impedance sensor. Wherein, determining the distribution characteristics of the electrode impedance includes: processing the impedance state matrix, extracting impedance characteristics in combination with the impedance state data set, predicting the impedance distribution according to the electric potential gradient and electrolyte path information, outputting the spatio-temporal distribution characteristics of the electrode impedance through the impedance optimization model, and updating the impedance state data set according to the spatio-temporal distribution characteristics; Dynamically optimizing the regional electrode parameters according to the distribution characteristics.

2. The impedance optimization method of a porous gradient anode-supported solid fuel cell according to claim 1, wherein The determination of the distribution characteristics of the electrode impedance includes: Processing the impedance state matrix to extract the electric potential intensity distribution, transmission delay characteristics, and impedance change trend; Performing electric potential intensity modeling on the impedance state matrix according to the electric potential intensity distribution and transmission delay characteristics, dividing the regional electrodes into multiple sub-regions and marking region identifiers, associating and matching the electric potential intensity of the sub-regions with the impedance state data set, and marking the region identifiers in the impedance state data set; Calculating the electric potential intensity gradient according to the impedance sensor position, predicting the distribution of the electrode impedance according to the electric potential intensity gradient and the impedance change trend, and calculating the impedance prediction information of each sub-region; Constructing an impedance optimization model, using the impedance prediction information as the input parameter of the impedance optimization model, performing spatial correlation modeling on the impedance prediction information through the impedance optimization model, and outputting the spatio-temporal distribution characteristics of the electrode impedance; Updating the impedance state data set according to the spatio-temporal distribution characteristics to obtain the distribution characteristics of the electrode impedance.

3. The impedance optimization method of a porous gradient anode-supported solid fuel cell according to claim 2, wherein The processing of the impedance state matrix includes: Normalizing the impedance state matrix, intercepting the impedance hot spot area in the matrix through a sliding window, filtering the noise of the hot spot area, and calculating the impedance change trend through the eigen-decomposition algorithm; Calculating the spatial correlation characteristics of the impedance state matrix, calculating the interference intensity, link stability coefficient, and impedance blind area index between regions according to the spatial correlation characteristics, constructing a feature fusion network, and calculating the transmission delay characteristics through the feature fusion network; Extracting the time-domain characteristics and frequency-domain characteristics collected by each impedance sensor, calculating the impedance feature vector of the sensor according to the phase difference between the time-domain characteristics and the frequency-domain characteristics, performing feature matching on the impedance sensors at different positions according to the impedance feature vector, and calculating the impedance change trend.

4. The impedance optimization method of a porous gradient anode-supported solid fuel cell according to claim 3, characterized in that The electric potential intensity modeling of the impedance state matrix includes: Extracting the electric potential intensity sampling points in each frame of data according to the electric potential intensity distribution, performing correlation mapping according to the sampling points and the transmission delay characteristics to generate an electric potential intensity map, spatially aligning the electric potential intensity maps collected by multiple sensors, and calculating the electric potential intensity distribution of the region. Set the interference threshold value, locate the interference source according to the potential intensity value of the multi-frame impedance state matrix, calculate the interference intensity difference. If the interference intensity difference is greater than or equal to the interference threshold value, it indicates the existence of an impedance blind area in this area. Perform propagation model constraint compensation on the current area, and perform iterative correction on the potential intensity distribution of the current area according to the path loss model corresponding to the current area. Calculate the intensity compensation value of the blind area potential according to the correction result; Perform potential intensity modeling on the impedance state matrix according to the potential intensity distribution, and perform time delay annotation on the potential model of the area through the transmission delay characteristics.

5. The impedance optimization method of a porous gradient anode-supported solid oxide fuel cell according to claim 4, characterized in that, The calculation of the potential intensity gradient according to the impedance sensor position includes: Extract the potential intensity change points according to multiple groups of impedance coverage data, map the change points to a unified electrode coordinate system according to the deployment positions of the sensors, and fit the change points through a spatial interpolation algorithm to generate the potential field model of the area; Perform equally spaced sampling along the transmission path of the potential field model, calculate the voltage attenuation rate, interference fluctuation index and potential change slope of the path according to the sampling results, and calculate the potential change parameters according to the voltage attenuation rate, interference fluctuation index and potential change slope; According to the deployment parameters and acquisition accuracy of the impedance sensors, project the distribution characteristics of impedance changes in each frame of data onto the potential field model, partition according to the number of sensors along the transmission direction of the potential field model, analyze the change rules of impedance changes within the partitions, and calculate the impedance distribution characteristics according to the change rules; Calculate the potential intensity gradient according to the potential change parameters and the impedance distribution characteristics. The calculation process of the potential intensity gradient includes: based on the electrode position range from the first impedance sensor to the last impedance sensor, select spatial coordinate points in the sensor deployment direction, cumulatively calculate the product of the potential field strength characteristic weight value and the impedance distribution characteristic weight value within the spatial resolution range, and superimpose the influence value of the sensor acquisition frequency on the potential intensity change rate.

6. A method for optimizing the impedance of a porous gradient anode-supported solid oxide fuel cell according to claim 5, characterized in that, The calculation of the impedance prediction information for each sub-region includes: Taking the main transmission path of the potential field model as the reference line, taking the peak position of the impedance change in each frame of data as the reference point, calculate the impedance offset, and draw the impedance distribution curve according to the electrode coordinates; According to the potential intensity gradient, correct the change rate and direction in the impedance change trend; Starting from the nearest impedance distribution point, continue to draw the distribution curve according to the correction results of the change rate and direction to generate the impedance distribution points in the next time period until the distribution points cover the entire target area to generate the impedance prediction information.

7. The impedance optimization method of a porous gradient anode-supported solid fuel cell according to claim 2, wherein The construction of the impedance optimization model includes: The input layer is used to organize the impedance prediction information into spatial distribution data and perform standardization processing; The feature fusion layer is used to extract the regional correlation features of the impedance by processing the spatial distribution data and construct the dependence relationship between electrode units; The parameter optimization layer is used to integrate the correlation relationship of the electrode impedance on the spatial unit to generate the electrode parameter optimization strategy.

8. The impedance optimization method of a porous gradient anode-supported solid fuel cell according to claim 2, characterized in that The acquisition of the distribution characteristics of the electrode impedance includes: According to the spatio-temporal distribution characteristics of the electrode impedance output by the impedance optimization model, correspond the identifiers of the sub-regions to the spatio-temporal distribution characteristics; Recombine the regional data in the impedance state dataset according to spatio-temporal characteristics to generate a regional distribution map sorted by impedance intensity; Output the optimized electrode impedance distribution characteristics according to the recombined regional distribution map.

9. The impedance optimization method for a porous gradient anode-supported solid oxide fuel cell according to claim 1, wherein The dynamic optimization of the regional electrode parameters includes: One-to-one map the region identifiers to the regions of the distribution characteristics of the electrode impedance; Control the execution actions of the electrode parameters according to the spatio-temporal distribution characteristics of the electrode impedance, including voltage adjustment, current aggregation and resistance allocation operations; Dynamically allocate the electrode parameters to the corresponding electrode regions according to the spatial distribution of the electrode impedance and the preset parameter optimization strategy.

10. The impedance optimization method for a porous gradient anode-supported solid fuel cell according to claim 9, wherein The control of the execution actions of the electrode parameters includes: When the electrode impedance reaches the preset intensity threshold in the target region, trigger the voltage increase instruction for the adjacent electrodes; Dynamically combine the available circuit resources according to the current aggregation strategy to generate a resistance allocation vector; Adjust the electrode parameters of the target region transmission node based on the resistance allocation vector.

Images