Intelligent electrode slice medicine penetration physiotherapy system with skin resistance self-adaptive adjustment function

Abstract

The invention relates to an intelligent electrode slice medicine penetration physiotherapy system capable of adaptively adjusting skin resistance. The system comprises an acquisition module used for performing real-time electrical parameter acquisition and electric field response measurement on a contact interface area of an intelligent electrode slice to obtain electrical parameter distribution data and electric field response distribution data; the characteristic analysis module is used for converting the electrical parameter distribution data into a first characteristic spectrum and converting the electric field response distribution data into a second characteristic spectrum to obtain interface characteristic data; the state classification module is used for performing interface state classification operation through a machine learning model of adaptive parameter adjustment to obtain an interface state classification result; the adjusting module is used for carrying out output power adjustment and substance release control on the intelligent electrode plate to obtain a predicted transmission current; and the parameter optimization module is used for outputting working current meeting conditions. According to the invention, the energy consumption is reduced, the material transmission efficiency is improved, and the material migration depth control precision is also improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent electrode sheet control, and in particular to an intelligent electrode sheet drug-penetrating therapy system with adaptive adjustment of skin resistance. Background Art

[0002] Traditional electric field driven material transfer technology usually uses fixed parameter settings and lacks the ability to adjust the characteristics of different interfaces, resulting in low material transfer efficiency and energy waste. Although the existing intelligent electrode sheet system can realize basic material transfer functions, it generally has technical defects such as insufficient perception of changes in the electrical characteristics of the contact interface, simple feedback adjustment mechanism, and inability to dynamically optimize output parameters according to the interface state. In addition, when traditional systems deal with complex interface environments, the depth and uniformity of material migration are difficult to control, and manual intervention is often required to adjust parameters, making it difficult to achieve automated and precise control.

[0003] The electrode material transfer systems currently on the market mainly rely on preset programs to operate, lack the ability to perceive and analyze the real-time status of the contact interface, and are unable to adaptively adjust output parameters for different interface conditions. Common systems usually apply the electrode directly to the target interface and are unable to accurately identify the differences in the electrical properties of the contact interface, resulting in low material migration efficiency. Especially in low-conductivity interface environments, the material migration resistance increases, the transmission depth is limited, and the system cannot intelligently adjust the current output parameters to adapt to such changes. At the same time, the current control in the existing technology is mostly a single mode, and it is difficult to optimize the current waveform and release rate according to different interface states. The material distribution is uneven and the edge effect is obvious, which limits the promotion of the system in high-precision application scenarios. Summary of the invention

[0004] The main purpose of the present invention is to provide an intelligent electrode patch drug-penetrating therapy system with adaptive adjustment of skin resistance. The present invention realizes the directional migration and efficient utilization of substances. At the same time, with the help of interface adaptability evaluation model and high-precision electric field analysis technology, the control accuracy of substance migration depth is significantly improved, and the ability of precise substance transmission control is realized.

[0005] To achieve the above-mentioned purpose, the present invention provides a smart electrode patch drug-penetrating physiotherapy system with adaptive adjustment of skin resistance, comprising: The acquisition module is used to perform real-time electrical parameter acquisition and electric field response measurement on the contact interface area of ​​the smart electrode sheet to obtain electrical parameter distribution data and electric field response distribution data; A feature analysis module, used to convert the electrical parameter distribution data into a first feature spectrum, convert the electric field response distribution data into a second feature spectrum, and perform feature analysis to obtain interface characteristic data; A state classification module, used for inputting the interface characteristic data into a machine learning model with adaptive parameter adjustment to perform interface state classification operation and obtain an interface state classification result; A regulating module, used to determine the current output parameter and the material migration enhancement coefficient according to the interface state classification result, and to adjust the output power and control the material release of the smart electrode sheet to obtain a predicted transmission current; The parameter optimization module is used to perform deviation calculation and compensation parameter optimization on the predicted transmission current, and output a working current that meets the conditions.

[0006] Optionally, in a first implementation of the first aspect of the present invention, the acquisition module is specifically used to: Performing a microcurrent detection operation on the interface between the smart electrode sheet and the contact surface to obtain a target electrical parameter spectrum, and digitally processing the target electrical parameter spectrum to obtain initial electrical parameter data; Performing grid area statistical calculation on the initial electrical parameter data to obtain electrical parameter distribution data, and performing normalization processing and data smoothing operation on the electrical parameter distribution data to obtain interface electrical parameter distribution data; Performing real-time sampling of the contact interface region with a multi-frequency electric field response sensor to obtain real-time electric field response data, and performing interface tomography calculation on the real-time electric field response data to obtain initial electric field response sampling data; Performing spatial distribution statistical analysis on the initial electric field response sampling data to obtain electric field response statistical distribution data; Coordinate transformation and numerical integration operations are performed on the electric field response statistical distribution data to obtain electric field response correction data, and the electric field response correction data is input into an electric field distribution reconstruction algorithm to reconstruct the spatial electric field distribution to obtain electric field response distribution data.

[0007] Optionally, in a second implementation of the first aspect of the present invention, the feature analysis module is specifically used to: Normalizing and dividing the interface electrical parameter distribution data into statistical intervals to obtain electrical parameter distribution statistical intervals; According to the electrical parameter distribution statistical interval, data mapping and frequency counting are performed on the interface electrical parameter distribution data to obtain electrical parameter frequency statistical results, and a first characteristic spectrum is generated according to the electrical parameter frequency statistical results; Normalizing and dividing the electric field response distribution data into statistical intervals to obtain electric field response distribution statistical intervals; According to the electric field response distribution statistical interval, performing data mapping and frequency counting on the electric field response distribution data to obtain electric field response frequency statistical results, and generating a second characteristic spectrum according to the electric field response frequency statistical results; Performing principal component analysis on the first characteristic spectrum to extract the electrical parameter distribution characteristic vector to obtain a first characteristic vector, and performing principal component analysis on the second characteristic spectrum to extract the electric field response distribution characteristic vector to obtain a second characteristic vector; Performing feature weight calculations on the first feature vector and the second feature vector respectively, and determining a weight coefficient matrix for feature fusion through covariance matrix calculation; A weighted fusion operation is performed on the first eigenvector and the second eigenvector according to the weight coefficient matrix to obtain interface characteristic data.

[0008] Optionally, in a third implementation of the first aspect of the present invention, the state classification module is specifically used to: According to the electrical parameter characteristics and the electric field response characteristics, the interface characteristic data are separated to obtain an electrical parameter characteristic data set and an electric field response characteristic data set; Inputting the electrical parameter feature data set into the first-layer classification network in the machine learning model with adaptive parameter adjustment to perform electrical parameter classification operation, wherein the first-layer classification network adopts a three-layer convolutional neural network structure to obtain the interface electrical parameter state classification result; Performing feature enhancement processing on the interface electrical parameter state classification result, including adding a spatial attention mechanism and a channel attention mechanism, wherein the spatial attention mechanism adopts a parallel structure of maximum pooling and average pooling, and the channel attention mechanism adopts a squeeze excitation module, to obtain enhanced electrical parameter features; Performing feature fusion on the electric field response feature data set and the enhanced electrical parameter feature to obtain fused feature data; Inputting the fused feature data into the second-layer classification network in the machine learning model with adaptive parameter adjustment to perform electric field response classification operation, wherein the second-layer classification network adopts a residual network structure to obtain an electric field response state classification result; According to a preset interface conductivity evaluation standard, a comprehensive score calculation and decision fusion are performed on the interface electrical parameter state classification result and the electric field response state classification result to obtain a comprehensive score of the double-layer classification, wherein the interface conductivity evaluation standard includes an interface humidity index, a physical structure parameter and an ion distribution factor; A threshold judgment is performed on the comprehensive score of the double-layer classification. When the comprehensive score is greater than the target value, it is determined to be a high-conductivity interface state. When the comprehensive score is less than or equal to the target value, it is determined to be a low-conductivity interface state, thereby obtaining an interface state classification result.

[0009] Optionally, in a fourth implementation of the first aspect of the present invention, the adjustment module further includes: A setting unit, used for determining the interface conductive state according to the interface state classification result, setting a low-intensity current parameter for a high-conductivity interface state, and setting a high-intensity current parameter for a low-conductivity interface state, to obtain a target current parameter; A calculation unit, used to calculate the frequency of the current control system of the smart electrode sheet based on the target current parameter, wherein the first channel is in a constant current mode with an intensity of P milliamperes, and the second channel is in a pulse current mode with an intensity of Q milliamperes, to obtain current channel parameters; A dynamic analysis unit, used to perform a dynamic analysis of the electric field distribution in the contact interface region, determine the material migration enhancement coefficient by calculating the electric field enhancement effect, and obtain a migration enhancement parameter; A modulation unit, used for inputting the target current parameter into the current control system of the intelligent electrode sheet to perform current waveform modulation calculation to obtain current waveform trajectory data, and performing current output calculation according to the current waveform trajectory data and the current channel parameter to obtain modulated current data; A compensation unit, configured to perform interface compatibility analysis on the modulated current data to obtain interface reaction prediction data, and perform current waveform compensation calculation according to the migration enhancement parameter and the interface reaction prediction data to obtain transmission current data; The prediction unit is used to calculate the functional substance release rate data based on the interface characteristic data, and perform functional substance release rate modulation operation on the transmission current data to obtain a predicted transmission current.

[0010] Optionally, in a fifth implementation manner of the first aspect of the present invention, the prediction unit is specifically used to: Inputting the interface characteristic data into a functional substance release rate calculation module, performing calculations based on the electric field migration characteristics of the preset functional molecule characteristics, and obtaining a target functional substance release rate map; Performing a release depth calibration on the target functional substance release rate map to obtain calibrated functional substance release rate data, and inputting the transmission current data into a material migration model for electric field driven calculation to obtain target functional substance distribution data; Performing concentration gradient compensation calculation on the target functional substance distribution data according to the calibrated functional substance release rate data to obtain compensated functional substance distribution, and inputting the compensated functional substance distribution into the smart electrode sheet to perform regionalized functional substance release regulation to obtain an initial transmission current; Performing real-time feedback monitoring on the initial transmission current, calculating the current distribution uniformity and material migration depth parameters through an interface electric field diagnostic system, and obtaining transmission quality monitoring data; The calibrated functional substance release rate data is optimized and calculated according to the transmission quality monitoring data, and the optimized functional substance release rate data is obtained through iterative processing, and the optimized functional substance release rate data is input into the smart electrode sheet for secondary current modulation to obtain the predicted transmission current.

[0011] Optionally, in a sixth implementation of the first aspect of the present invention, the parameter optimization module is specifically used to: Performing target deviation analysis on the predicted transmission current, obtaining initial deviation data by calculating the difference from the ideal transmission mode, and inputting the initial deviation data into a programmable current controller adaptive compensation unit for dynamic compensation calculation to obtain compensation amount parameters; Iteratively optimize the compensation parameters according to the compensation amount parameters, and numerically calculate the compensation parameters by the least square method to obtain optimized compensation parameters; Inputting the optimized compensation parameters into a closed-loop control system, performing compensation calculation on the predicted transmission current, and obtaining compensated current data; Performing high-precision electric field analysis on the compensated current data to obtain interface electric field quality data, and inputting the interface electric field quality data into an interface electric field diagnostic system to perform electric field difference calculation, and obtaining material migration depth data by current density calculation; An interface adaptability evaluation model is established according to the interface electric field quality data and the material migration depth data. When the adaptability is lower than a preset adaptability threshold, it is determined that the current meets the output conditions, a current quality determination result is obtained, and a working current that meets the conditions is output based on the current quality determination result.

[0012] In summary, the technical solution provided by the present invention acquires the electrical parameters and electric field response data of the contact interface in real time through the acquisition module, and combines the feature analysis module to perform deep processing on the data, so that the system can accurately identify different types of interface states. Based on the double-layer feature fusion technology, the interface characteristic data acquired by the system is more comprehensive and accurate, providing a reliable basis for parameter adjustment. The state classification module adopts an innovative double-layer classification network structure, and through the combined application of a three-layer convolutional neural network and a residual network, it cooperates with the spatial attention mechanism and the channel attention mechanism to enhance the feature expression ability, and realizes high-precision interface conductivity state classification. The adjustment module intelligently sets the current parameters according to the classification results, and the high and low conductivity interfaces use different current intensities respectively, and calculates the material migration enhancement coefficient through the electric field enhancement effect, thereby reducing energy consumption and improving material transfer efficiency. The constant current and pulse current dual-channel collaborative control strategy is adopted to significantly improve the uniformity of material distribution, reduce edge effects, and improve system adaptability. The parameter optimization module constructs a complete closed-loop control system, monitors and adjusts the working current in real time, prevents unsuitable current parameters from having a negative impact on the interface, and greatly improves the long-term working stability of the system. In addition, the system accurately calculates the release rate of functional substances based on interface characteristic data, and realizes the directional migration and efficient utilization of substances through concentration gradient compensation and regional release regulation technology. At the same time, with the help of interface adaptability evaluation model and high-precision electric field analysis technology, the control accuracy of material migration depth is significantly improved, realizing precise material transfer control capabilities. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 It is a schematic diagram of an intelligent electrode patch drug-penetrating therapy system with adaptive adjustment of skin resistance in one embodiment of the present invention.

[0014] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0015] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0016] Reference Figure 1 This embodiment provides a smart electrode patch drug-penetrating therapy system with adaptive adjustment of skin resistance, including: The acquisition module 101 is used to perform real-time electrical parameter acquisition and electric field response measurement on the contact interface area of ​​the smart electrode sheet to obtain electrical parameter distribution data and electric field response distribution data; Among them, the acquisition module performs refined electrical measurements on the interface between the smart electrode sheet and the contact surface through micro-current detection operation. In this process, micro-current detection technology is used to apply a tiny AC or DC current, and by measuring the response voltage signal, the target electrical parameter map of the interface is calculated according to Ohm's law (U=IR) or the impedance model. These parameters include characteristic indicators such as resistance, capacitance, and impedance spectrum, which can reflect the conductivity, polarization characteristics, and charge transfer efficiency of the interface material. The target electrical parameter map is digitized to convert the analog signal into discrete initial electrical parameter data. The digital processing process includes sampling, quantization, and encoding steps. High-speed data acquisition cards or analog-to-digital converters are used to achieve high-precision signal sampling, and noise interference is removed through appropriate filtering algorithms to obtain a relatively pure initial data set. The initial electrical parameter data is stored in a matrix or grid form, and each grid unit corresponds to the electrical characteristics of a specific spatial position to form a preliminary electrical parameter spatial distribution map. The initial electrical parameter data is statistically calculated in the grid area. The interface area is divided into several small grids by the method of partition statistics. The statistics of the electrical parameters, such as mean, variance, maximum value, minimum value, etc., are calculated in each grid to obtain the electrical parameter distribution data. The electrical parameter distribution data is normalized and smoothed. In the normalization process, the value range of the electrical parameter is mapped to a unified standard range (for example, between 0 and 1) to avoid data bias caused by differences in numerical magnitude. The data smoothing operation reduces the random noise of the data through algorithms such as moving average, weighted filtering or Gaussian smoothing, improves the continuity and stability of the data, and obtains the interface electrical parameter distribution data. In terms of electric field response measurement, the acquisition module uses a multi-frequency electric field response sensor to sample the contact interface area in real time. The multi-frequency electric field response sensor can collect interface response data under electric field stimulation of different frequencies, and capture the response characteristics of the material at different electric field frequencies through frequency scanning technology (such as impedance spectroscopy EIS and dielectric spectroscopy DES). This method is suitable for analyzing ion transport, dielectric response and polarization phenomena in the interface. After signal conditioning and digital processing, the response data collected by the sensor is processed to obtain real-time electric field response data. These data are also organized in the form of a spatial grid, recording the electric field response at different spatial positions and different frequency conditions. Interface tomography calculation is performed on the real-time electric field response data. Interface tomography technology (such as electrical impedance tomography EIT and capacitance tomography CST) uses the spatial distribution information of multiple sensors to calculate the physical field distribution inside the interface through an inversion algorithm to generate initial electric field response sampling data, including the distribution characteristics of the electric field in space, including the electric field strength, direction, and field effect distribution. The initial electric field response sampling data is subjected to spatial distribution statistical analysis, and the data is sorted by statistical methods to obtain the electric field response statistical distribution data.By combining spatial interpolation, cluster analysis, and statistical filtering, the discrete sampling point data is converted into a continuous distribution map, and the reliability of the data is improved by removing outliers and filling missing data. The electric field response statistical distribution data is subjected to coordinate transformation and numerical integration operations. The data is transformed from the sampling coordinate system to the actual space coordinate system through coordinate transformation to achieve alignment between the data and the physical space, while the numerical integration operation is used to calculate the total response or response change rate of the electric field in a specific area. These processes make the data more consistent with the physical meaning and practical application requirements, and obtain the electric field response correction data. The electric field response correction data is input into the electric field distribution reconstruction algorithm to reconstruct the spatial electric field distribution. By solving the physical model of the electric field distribution (such as Poisson's equation and electric field intensity distribution equation), the discrete correction data is reconstructed into spatially continuous electric field response distribution data.

[0017] The feature analysis module 102 is used to convert the electrical parameter distribution data into a first feature spectrum, convert the electric field response distribution data into a second feature spectrum, and perform feature analysis to obtain interface characteristic data; Specifically, the feature analysis module normalizes the interface electrical parameter distribution data to eliminate the imbalance problem caused by different dimensions or numerical ranges in the data. The normalization process uses methods such as linear normalization to map the electrical parameter data to a unified numerical range (such as between 0 and 1), so that the data maintains numerical consistency and comparability in the subsequent statistical and feature extraction process. The normalized electrical parameter data is divided into statistical intervals. The statistical interval division method is based on equal interval segmentation or quantile segmentation, and the data space is divided into several continuous intervals. Each interval corresponds to a specific statistical range to form an electrical parameter distribution statistical interval. According to the electrical parameter distribution statistical interval, the normalized electrical parameter distribution data is subjected to data mapping and frequency counting operations. In the data mapping process, each data point is mapped to the corresponding statistical interval according to its numerical value. By counting the data frequency in each interval, the electrical parameter frequency statistical results are obtained. This result is expressed in the form of a histogram, a frequency distribution table or a heat map, reflecting the spatial distribution characteristics and statistical characteristics of different electrical parameters in the interface. According to the frequency statistics, the first feature map is generated, and the frequency distribution information is converted into a high-dimensional data expression in the feature space through a specific image processing algorithm (such as grayscale conversion, color mapping, feature enhancement), so that the system uses these maps as inputs to the feature extraction algorithm. The electric field response distribution data is normalized to normalize the data to a unified numerical range. After the normalization is completed, the electric field response distribution data is divided into statistical intervals to generate electric field response distribution statistical intervals, and the same segmentation standard is used to ensure the comparability of feature data during feature fusion and the consistency of calculation. According to the electric field response distribution statistical interval, data mapping and frequency counting operations are performed on the normalized electric field response distribution data, and the electric field response data points are mapped to their respective statistical intervals. By counting the response frequency of each interval, the electric field response frequency statistical results are generated, and the second feature map is constructed based on these results. The first characteristic map and the second characteristic map are subjected to principal component analysis respectively. Principal component analysis is a dimensionality reduction technique. By calculating the covariance matrix of the characteristic map, the main characteristic components in the map data are extracted, thereby projecting the high-dimensional data into a low-dimensional space while maximizing the variance preservation of the data. After the principal component analysis is performed on the first characteristic map, the electrical parameter distribution feature vector is obtained, which contains the main information in the first characteristic map, such as the main change trend and distribution characteristics of the electrical parameters in different statistical intervals. Similarly, the second characteristic map is subjected to principal component analysis to extract the electric field response distribution feature vector, which reflects the main change mode and response characteristics of the electric field response in the interface space. The feature analysis module calculates the feature weights of the first feature vector and the second feature vector respectively, and determines the weight coefficient matrix of the feature fusion through the covariance matrix operation.In this process, the covariance matrix reflects the linear relationship and correlation between the two eigenvectors in different dimensions. By calculating the eigenvalues ​​and eigenvectors of the covariance matrix, the distribution strategy of the feature weights is obtained. The first eigenvector and the second eigenvector are weighted fused according to the weight coefficient matrix. The weighted linear combination method is used to linearly weight the two eigenvectors according to the weight coefficient matrix to obtain the fused interface characteristic data.

[0018] A state classification module 103 is used to input the interface characteristic data into the machine learning model with adaptive parameter adjustment to perform interface state classification operation and obtain an interface state classification result; It should be noted that, according to the electrical parameter characteristics and the electric field response characteristics, the input interface characteristic data is subjected to data separation processing to obtain the electrical parameter characteristic data set and the electric field response characteristic data set. Through the feature decoupling algorithm, the multidimensional feature data is segmented according to specific feature channels or feature types, so that the electrical parameters and the electric field response characteristics constitute independent data sets respectively. The electrical parameter characteristic data set is input into the first-layer classification network in the machine learning model with adaptive parameter adjustment for electrical parameter classification operation. The first-layer classification network adopts a three-layer convolutional neural network structure, which realizes the layer-by-layer extraction and high-dimensional feature expression of the electrical parameter characteristic data through the combination of convolution operation, activation function and pooling layer. In the first layer of convolution, the network extracts local features in the data through a small-sized convolution kernel (such as 3×3 or 5×5), and through the channel expansion and feature enhancement technology in the feature map, the spatial distribution characteristics of the electrical parameters are expressed in a more fine-grained manner. The second layer of convolution further aggregates features in a larger range, and combines pooling operations (such as maximum pooling or average pooling) to reduce the dimension of the feature data, reducing the computational complexity while retaining key information. The third convolution layer is combined with the fully connected layer to achieve a high-level expression of features. The interface electrical parameter state classification results are output through the Softmax activation function or other classification activation functions, including the classification probability distribution of electrical parameter features under different interface states, revealing the possibility that the interface is in a high conductivity, low conductivity or intermediate state. The interface electrical parameter state classification results are subjected to feature enhancement processing. The feature enhancement process includes the introduction of spatial attention mechanism and channel attention mechanism to achieve the focus on key features and the suppression of redundant features. In the spatial attention mechanism, a parallel structure of maximum pooling and average pooling is adopted. By performing these two pooling operations simultaneously on the spatial dimension of the feature map, the significant areas in the feature map are expressed with higher weights. This dual-channel pooling process ensures the comprehensiveness of feature extraction and enhances the sensitivity to local high response areas. At the same time, in the channel attention mechanism, a squeeze excitation module is adopted. This module obtains the global feature response of each channel through the global average pooling operation, and then realizes the correlation modeling between channels through the fully connected layer. The weight coefficient of each channel is generated through the Sigmoid activation function to achieve weighted enhancement of useful channels and suppression of useless channels in the feature map. After these enhancement operations, the enhanced electrical parameter features are obtained. The enhanced electrical parameter features are fused with the electric field response feature data set to obtain fused feature data. In the feature fusion process, multimodal fusion technology is used to seamlessly connect the electrical parameters and electric field response features in the feature space through feature splicing, feature weighting or feature crossover to form a higher-dimensional and higher-information feature representation. The fused feature data is input into the second-layer classification network in the machine learning model with adaptive parameter adjustment for electric field response classification operations. The classification network adopts a residual network structure.The residual network effectively solves the common gradient vanishing and gradient exploding problems in deep learning networks by introducing jump connections, so that the model can still maintain good training effects when the depth increases. The residual module in the residual network realizes the identity mapping of features by directly adding the input features to the output features, avoiding the information loss in the process of feature transmission between layers. This design enables the network to improve the stability and accuracy of the classification operation while maintaining the model depth, and obtain the classification results of the electric field response state. After completing the double-layer classification, according to the preset interface conductivity evaluation standard, the interface electrical parameter state classification results and the electric field response state classification results are comprehensively scored and fused. This evaluation standard includes key evaluation dimensions such as interface humidity index, physical structure parameters and ion distribution factors. Through the multi-dimensional weighted scoring method, the two classification results are integrated into a unified score value. In the comprehensive scoring calculation process, according to the weight coefficient of each evaluation index, the weighted average, decision tree or fuzzy logic method is used to integrate the multi-faceted information of the interface state into a numerical conductivity evaluation score. The higher the score, the better the interface conductivity. The comprehensive score of the double-layer classification is judged by threshold. When the comprehensive score is greater than the target value, the current interface state is judged to be a high conductivity state, which means that the interface is wet, the ion concentration is high, and the physical structure is conducive to current conduction. When the comprehensive score is less than or equal to the target value, it is judged to be a low conductivity interface state, which indicates that the interface is dry, the ion concentration is low, or the interface structure has obstacles to current transmission.

[0019] The adjustment module 104 is used to determine the current output parameter and the material migration enhancement coefficient according to the interface state classification result, and to adjust the output power and control the material release of the smart electrode sheet to obtain the predicted transmission current; Specifically, the setting unit in the adjustment module determines the conductive state of the current interface based on the interface state classification result. After the system obtains the comprehensive score of the interface electrical parameters and the electric field response through the state classification module, the setting unit compares the comprehensive score with the preset interface conductivity evaluation standard. When the comprehensive score is greater than the target value, it is judged as a high conductivity interface state, and when the comprehensive score is less than or equal to the target value, it is judged as a low conductivity interface state. Based on this judgment result, the setting unit adopts different current parameter setting strategies. For the high conductivity interface state, a low-intensity current parameter is selected to avoid excessive stimulation of the interface or unnecessary energy consumption caused by excessive current; and for the low conductivity interface state, a high-intensity current parameter is set to increase the current intensity to improve the interface material transmission efficiency and obtain the target current parameter. The calculation unit calculates the frequency of the current control system of the intelligent electrode sheet based on the target current parameter, and realizes the refined control of the current output by selecting the mode of the current channel and adjusting the frequency. The current control system of the system is designed as a dual-channel mode, in which the first channel works in a constant current mode with an output intensity of P mA. This mode is suitable for maintaining a stable current flow and is suitable for use when the electrode sheet is in good contact with the interface and has high conductivity to maintain a stable material release rate. The second channel adopts a pulse current mode with an output intensity of Q mA. This mode generates dynamic changes in the electric field intensity by periodically applying pulse current, thereby enhancing the electric field response effect of the interface, especially in the low conductivity interface state. By adjusting the frequency, pulse width and duty cycle of the pulse, effective stimulation of interface ion migration and material transport is achieved. The calculation unit dynamically adjusts the current output parameters of the two channels by analyzing the target current parameters to obtain the current channel parameters. The dynamic analysis unit dynamically analyzes the electric field distribution in the contact interface area, collects the electric field distribution data of the interface area in real time through the electric field sensor installed on the smart electrode sheet, and calculates the material migration enhancement coefficient using the electric field enhancement effect. The electric field enhancement effect is based on the local enhancement of the electric field in the interface inhomogeneous area. For example, at the interface microstructure such as capillaries, micropores or sharp edges, the electric field strength will be significantly improved, thereby accelerating the directional migration of ions and the release of functional substances. The dynamic analysis unit calculates the material migration enhancement coefficient under different electric field distribution conditions through numerical simulation and finite element analysis methods to obtain the migration enhancement parameters. The target current parameters are input into the current control system of the intelligent electrode sheet for current waveform modulation calculation. The modulation unit generates specific current waveform trajectory data through current control algorithms (such as pulse width modulation PWM, frequency modulation FM or amplitude modulation AM). These data include the amplitude change of the current, as well as the phase, frequency and periodic characteristics of the waveform.After generating the current waveform trajectory data, the modulation unit performs the current output operation according to the calculated current channel parameters (P and Q values), maintains the basic electric field environment through the constant current of the first channel, and generates a dynamic electric field effect in combination with the pulse current of the second channel to obtain the modulated current data. The compensation unit performs interface compatibility analysis on the modulated current data, predicts the interface reaction behavior by analyzing the electrical response characteristics and chemical reaction characteristics of the interface, and obtains the interface reaction prediction data. In the process of interface compatibility analysis, the electrochemical characteristics of the interface material, the electrode polarization effect, and the ion concentration change trend are comprehensively considered, and the reaction process of the interface under a specific current waveform is predicted by electrochemical impedance spectroscopy (EIS) or surface potential scanning technology, including ion exchange, material degradation or electrochemical deposition. After obtaining the interface reaction prediction data, the compensation unit combines the migration enhancement parameters and fine-tunes the current waveform through the waveform compensation algorithm to calculate the transmission current data. This data not only ensures the stability of the current output at the physical level, but also optimizes the material transmission efficiency by dynamically adjusting the waveform characteristics (such as fine-tuning of the pulse frequency and duty cycle). The prediction unit calculates the release rate of the functional substance based on the interface characteristic data, and establishes a prediction model for the release rate of the functional substance through comprehensive analysis of the electric field distribution, electrical parameters and interface state. This model is implemented through a machine learning regression model or a mass transfer equation based on a physical model (such as the Nernst-Planck equation). After obtaining the functional substance release rate data, the prediction unit performs a functional substance release rate modulation operation on the transmission current data, and adjusts the current output parameters by calculating the nonlinear relationship between the current and the substance release rate (such as the ion concentration gradient, the change in the diffusion coefficient under the electric field drive), and finally obtains the predicted transmission current.

[0020] The prediction unit inputs the interface characteristic data into the functional substance release rate calculation module, and the interface characteristic data includes electrical parameters, spatial electric field distribution, and interface state classification results. The functional substance release rate calculation module performs calculations based on the electric field migration characteristics of the preset functional molecular characteristics. Through modeling calculation methods (such as the Nernst-Planck equation and the diffusion model driven by the electric field), the migration behavior of the functional molecules under the action of the electric field is simulated, and the target functional substance release rate map is obtained by combining the electric field strength, charge density, and electrode interface characteristics. The release rate distribution of the functional substance at different spatial positions is displayed, and the dynamic change trend of the substance release under specific electric field conditions is reflected. The release depth of the target functional substance release rate map is calibrated, and the calculated release rate is more consistent with the depth distribution characteristics of the actual substance migration process by adjusting the spatial depth of the data in the map. The calibration method adopts multi-level spatial transformation technology, including spatial reconstruction based on depth sensors, depth correction based on electric field intensity gradients, and dynamic calibration based on molecular diffusion models. This process adjusts the spatial distribution parameters of the release rate by comparing the actual measured material distribution data with the release rate map in the calculation model, so that the calibrated functional material release rate data truly reflects the actual migration and release state of the functional molecules under the electric field drive. At the same time, the prediction unit inputs the transmission current data into the material migration model for electric field driven calculation. The material migration model converts the current data into the specific distribution form of the material in space through the electric field-ion exchange coupling model, the electric field driven fluid mechanics model and other methods to obtain the target functional material distribution data. These data represent the concentration and migration direction of the functional molecules at different positions in three-dimensional space coordinates. In the concentration gradient compensation calculation, the prediction unit adjusts the target functional material distribution data according to the calibrated functional material release rate data. The concentration gradient compensation mainly calculates the concentration gradient change of the functional molecules in space and balances the local concentration areas in the distribution data that are too high or too low. The gradient compensation algorithm (such as the compensation model based on Fick's diffusion law and the ion balance model based on electric field guidance) is adopted to achieve uniform material distribution by dynamically adjusting the electric field strength and material release rate, and obtain the compensated functional material distribution. The compensated functional substance distribution data is input into the smart electrode sheet, which realizes regionalized functional substance release regulation through current modulation and field intensity control according to the material demand in different regions. This regulation method uses multi-channel current control technology on the electrode sheet to apply electric fields of different intensities or frequencies in different spatial regions, thereby accurately controlling the release concentration and migration direction of functional molecules in the target area and obtaining the initial transmission current.The prediction unit performs real-time feedback monitoring of the initial transmission current. The feedback monitoring is achieved through the interface electric field diagnostic system. The system collects current distribution data and electric field response data in real time through the sensor array, and obtains transmission quality monitoring data by calculating the current distribution uniformity and material migration depth parameters. In the current distribution uniformity analysis, by calculating the current density distribution of the current in different areas, it is determined whether there is excessive current concentration or current blank areas, thereby evaluating the stability of the current output. The material migration depth parameter is calculated through the coupling relationship between the electric field distribution and the change in material concentration, reflecting the actual penetration depth of the functional molecules under the guidance of the electric field. These monitoring data provide real-time feedback information for the system, enabling the system to quickly identify problems in the material transmission process, such as insufficient migration depth, too fast or too slow release rate, etc. The calibrated functional substance release rate data is optimized and calculated according to the transmission quality monitoring data. The optimization process is realized through iterative processing methods. The gradient descent algorithm, genetic algorithm or dynamic optimization algorithm based on reinforcement learning are used to adjust the functional substance release rate for multiple rounds. In each iteration, the error between the predicted substance release rate and the actual transmission effect is calculated. The parameters in the release rate calculation model are adjusted through the error back propagation mechanism to obtain the optimized functional substance release rate data. The optimized functional substance release rate data is input into the intelligent electrode sheet for secondary current modulation. By adjusting the current waveform, frequency and intensity again, the predicted transmission current is finely controlled, so that the predicted transmission current outputted in the end better matches the actual needs of the interface, and the safety and stability of the current output are effectively controlled while ensuring the substance release efficiency.

[0021] The parameter optimization module 105 is used to perform deviation calculation and compensation parameter optimization on the predicted transmission current, and output a working current that meets the conditions.

[0022] Among them, the parameter optimization module performs target deviation analysis on the predicted transmission current and evaluates the difference between the predicted current and the ideal transmission mode. The difference is not only a simple deviation in current intensity, but also includes the inconsistency of current waveform, frequency response, phase difference and spatial current distribution. The system compares the predicted transmission current with the preset ideal current model and uses the difference calculation method to obtain the initial deviation data, quantify the degree of deviation between the current output and the target mode, and reveal the systematic errors in the current control process (such as current fluctuations caused by changes in interface impedance). The initial deviation data is input into the adaptive compensation unit of the programmable current controller. The compensation unit calculates the compensation parameters required in real time through dynamic compensation calculation methods (such as adaptive filters, PID control algorithms or dynamic error compensation models). After obtaining the compensation parameters, the parameter optimization module continues to iteratively optimize the compensation parameters. The iterative optimization process numerically calculates the compensation parameters through the least squares method. The least squares method is an optimization method based on the principle of error minimization. By constructing an objective function, the sum of squares of the error between the actual output and the expected output is minimized to obtain the optimal compensation parameters. In each round of iteration, the system will recalculate the error function and adjust the value of the compensation parameter so that the error gradually converges to the minimum value. This iterative calculation method can not only improve the accuracy of the compensation parameters, but also further accelerate the convergence process through adaptive algorithms (such as gradient descent method and Newton iteration method) to obtain the final optimized compensation parameters. The optimized compensation parameters are input into the closed-loop control system to perform compensation operations on the predicted transmission current. The core of the closed-loop control system lies in real-time feedback and dynamic adjustment. By real-time monitoring of current output data, the current current state is compared with the ideal current model, and the control signal is adjusted according to the feedback data to achieve refined compensation of the current. The compensation operation process is based on classical control theory (such as proportional-integral-differential PID control and model predictive control MPC). The system adjusts the output of the control signal according to the optimized compensation parameters to achieve synchronous compensation operations on the current amplitude, frequency and waveform to obtain compensated current data. High-precision electric field analysis is performed on the compensated current data to evaluate the quality of the electric field generated by the compensated current in the interface area. The electric field distribution data of the interface area is collected by high-precision electric field sensors, and the interface electric field quality data is calculated using numerical analysis methods (such as finite element analysis FEM, electric field distribution simulation technology). The interface electric field quality data is input into the interface electric field diagnostic system for electric field difference calculation. By comparing the current electric field distribution with the ideal electric field model, the electric field difference is calculated to evaluate the impact of current output on the interface material transmission effect. At the same time, through the current density calculation model, the material migration depth data is derived using the current distribution data. These data are combined with the electric field strength and material concentration distribution characteristics to calculate the actual penetration depth of functional molecules under the action of the electric field.The parameter optimization module establishes an interface adaptability evaluation model based on the interface electric field quality data and material migration depth data. The model is based on multi-dimensional adaptability evaluation criteria, including the uniformity of electric field distribution, the stability of current density, and the rationality of material migration depth. The interface fitness value is calculated through multi-factor analysis methods (such as fuzzy logic analysis and weighted scoring method). When the fitness is lower than the preset adaptation threshold, it is determined that the current output meets the actual needs of material transmission and the current quality determination result is output. Based on the current quality determination result, the parameter optimization module outputs the working current that meets the conditions.

[0023] Optionally, the acquisition module 101 is specifically used for: Performing a microcurrent detection operation on the interface between the smart electrode sheet and the contact surface to obtain a target electrical parameter spectrum, and digitally processing the target electrical parameter spectrum to obtain initial electrical parameter data; Performing grid area statistical calculation on the initial electrical parameter data to obtain electrical parameter distribution data, and performing normalization processing and data smoothing operation on the electrical parameter distribution data to obtain interface electrical parameter distribution data; Performing real-time sampling of the contact interface region with a multi-frequency electric field response sensor to obtain real-time electric field response data, and performing interface tomography calculation on the real-time electric field response data to obtain initial electric field response sampling data; Performing spatial distribution statistical analysis on the initial electric field response sampling data to obtain electric field response statistical distribution data; Coordinate transformation and numerical integration operations are performed on the electric field response statistical distribution data to obtain electric field response correction data, and the electric field response correction data is input into the electric field distribution reconstruction algorithm to reconstruct the spatial electric field distribution to obtain electric field response distribution data.

[0024] In this embodiment, a weak AC or DC current is applied between the smart electrode sheet and the contact interface through a high-precision micro-current detector. Assume that the applied micro-current is The microcurrent detector measures the response voltage , using Ohm's law The resistance at the interface is calculated At the same time, the impedance of the interface under different frequency currents is measured by AC impedance spectroscopy technology. ,in is the frequency, and the calculation formula is: ;in, and Respectively at frequency After these measurement data are analyzed in the time domain and frequency domain, a target electrical parameter map is constructed. The map is in the form of spatial coordinates. and frequency As a dimension, the electrical characteristics of the interface area at different positions and frequencies are displayed. The target electrical parameter map is digitized. The continuous electrical signal is discretized into a digital signal through an analog-to-digital converter. Assuming the sampling frequency is The discretized data is expressed as , where i, j represent spatial coordinates, k=1,2,...,N are the numbers of sampling points, and N represents the total number of samples. These discrete initial electrical parameter data are constructed into a multidimensional array, which represents the electrical response of the interface area at different spatial positions and different frequencies. The initial electrical parameter data are statistically calculated in the grid area, and the entire interface area is divided into grids of equal size. Assume that the size of the grid is , by calculating the average value, variance and extreme value of the electrical parameters in each grid, the distribution data of the electrical parameters is obtained. The statistical calculation process is implemented by the following formula: ; in, Indicates The average value of the electrical parameters in the grid, is the number of data points in the grid, Represents the first These distribution data are normalized to map the parameter values ​​to a standard range (such as [0,1]). The normalization formula is: ; in, and are the minimum and maximum values ​​of the electrical parameters in all grids respectively. In order to eliminate the noise and spikes in the data, the electrical parameter distribution data is smoothed. For example, the moving average smoothing formula is:

[0025] in, In order to smooth the window size, the data in adjacent grids are weighted averaged to achieve data smoothing and obtain the interface electrical parameter distribution data. At the same time, the multi-frequency electric field response sensor is used to sample the contact interface area in real time, and the sensor is used to generate the electric field at different frequencies. The electric field response measured under , obtain real-time electric field response data. Input these data into the interface tomography calculation module, and reconstruct the electric field distribution inside the interface using the inversion algorithm based on the boundary electric field data obtained by the multi-channel sensor through electrical impedance tomography or capacitance tomography technology to obtain the initial electric field response sampling data. Based on the initial electric field response sampling data, perform spatial distribution statistical analysis to calculate the statistical characteristics of the electric field response in different regions, including mean, variance, frequency response characteristics, etc. Spatial distribution statistical analysis uses cluster analysis or spatial interpolation methods. For example, the average value of the electric field strength in a certain area is calculated:

[0026] in, Indicates area The average electric field strength inside is the area of ​​the region, is the electric field at position The intensity at the point. These statistical analysis results are constructed into the electric field response statistical distribution data. Coordinate transformation and numerical integration operations are performed on the electric field response statistical distribution data. The data is transformed from the sampling coordinate system to the actual space coordinate system through coordinate transformation, such as through polar coordinate transformation. , , realizing spatial remapping of data. In numerical integration operations, the total response or field effect of the electric field in a specific area is calculated, for example, the electric field flux is calculated by surface integral: ; in, represents the electric field flux, is the integration area, is a small area element. Through these calculations, the electric field response correction data are obtained, and these data are input into the electric field distribution reconstruction algorithm. The electric field distribution reconstruction algorithm (such as finite element method FEM, boundary element method BEM) is used to reconstruct the spatial electric field distribution of the electric field response correction data. The reconstruction algorithm is based on the Poisson equation: ; in, represents the conductivity distribution in the interface region, is the electric potential distribution, is the charge density. By solving this equation, the spatial electric field response distribution data of the entire interface area is obtained. These data are presented in the form of a three-dimensional spatial map, showing the changes in the intensity and direction of the electric field at different locations.

[0027] Optionally, the feature analysis module 102 is specifically used for: Normalizing and dividing the interface electrical parameter distribution data into statistical intervals to obtain the electrical parameter distribution statistical intervals; According to the electrical parameter distribution statistical interval, data mapping and frequency counting are performed on the interface electrical parameter distribution data to obtain electrical parameter frequency statistical results, and a first characteristic spectrum is generated according to the electrical parameter frequency statistical results; Normalizing and dividing the electric field response distribution data into statistical intervals to obtain the electric field response distribution statistical intervals; According to the electric field response distribution statistical interval, data mapping and frequency counting are performed on the electric field response distribution data to obtain the electric field response frequency statistical result, and a second characteristic spectrum is generated according to the electric field response frequency statistical result; Performing principal component analysis on the first characteristic spectrum to extract the electrical parameter distribution characteristic vector to obtain the first characteristic vector, and performing principal component analysis on the second characteristic spectrum to extract the electric field response distribution characteristic vector to obtain the second characteristic vector; The feature weights of the first eigenvector and the second eigenvector are calculated respectively, and the weight coefficient matrix of feature fusion is determined by covariance matrix operation; A weighted fusion operation is performed on the first eigenvector and the second eigenvector according to the weight coefficient matrix to obtain interface characteristic data.

[0028] In this embodiment, the interface electrical parameter distribution data is normalized to eliminate the differences in data due to different physical dimensions and numerical ranges. Assume that the interface electrical parameter distribution data is ,in Represents the position coordinates of the data in two-dimensional space, through the normalization formula:

[0029] in, is the normalized electrical parameter data, and are the minimum and maximum values ​​of the electrical parameter data, respectively. The normalization process compresses the original data into the standard range of [0,1] to ensure the numerical stability of subsequent statistical analysis. In order to analyze the distribution characteristics of the data, the normalized data is divided into statistical intervals. Assume that the data is divided into There are statistical intervals, and the width of each interval is:

[0030] in, is the step length of the statistical interval. Map to the corresponding statistical interval, count the frequency of data in each interval, and get the frequency statistical results of electrical parameters. Frequency statistical results The calculation formula is:

[0031] in, Indicates The frequency of a statistical interval, is the indicator function, when Fall into When the interval , otherwise 0. This frequency counting process presents the distribution characteristics of the electrical parameter data in the form of a histogram, and generates the first characteristic spectrum by visualizing the frequency statistical results. A similar processing method is applied to the electric field response distribution data , normalized, the normalization formula is:

[0032] in, and are the minimum and maximum values ​​in the electric field response data, is the normalized electric field response data. After normalization, the data is also divided into statistical intervals to obtain the electric field response distribution statistical intervals, and the electric field response frequency statistical results are calculated by the frequency counting method. The calculation method of the electric field response frequency statistical results is similar to the electrical parameter frequency statistical results. By counting the frequency of data in different intervals, the distribution characteristics of the electric field response data are converted into a discrete frequency distribution form, and the second characteristic spectrum is generated accordingly. The main eigenvectors in the first characteristic spectrum and the second characteristic spectrum are extracted by the principal component analysis method. The principal component analysis is performed through the characteristic covariance matrix Extract the main change direction of the data. Assume that the data matrix of the first feature map is , the size is ,express samples and features, then the covariance matrix The calculation formula is:

[0033] in, is the transpose of the matrix. By performing eigenvalue decomposition on the covariance matrix, we get the eigenvalue and the corresponding eigenvector The eigenvector represents the projection of the data on a specific dimension, and the eigenvalue reflects the variance of the data on that dimension. Select the eigenvectors with the largest eigenvalues. As the first eigenvector, For the second feature map, the same method is used to calculate the covariance matrix And extract the eigenvector to get the second eigenvector In order to achieve feature fusion, the feature weights of the first eigenvector and the second eigenvector are calculated respectively, and the weight coefficient matrix The covariance matrix via the eigenvectors The calculation results are:

[0034] Calculate the weight coefficient matrix by singular value decomposition or maximum correlation analysis , which represents the similarity and correlation of two eigenvectors in each dimension. The first eigenvector and the second eigenvector are weighted fused according to the weight coefficient matrix. The calculation formula of weighted fusion is:

[0035] in, is the interface characteristic data after fusion, is the unit matrix, and through weighted fusion, effective integration of data of different feature dimensions is achieved.

[0036] Optionally, the state classification module 103 is specifically used for: According to the electrical parameter characteristics and the electric field response characteristics, the interface characteristic data are separated to obtain an electrical parameter characteristic data set and an electric field response characteristic data set; The electrical parameter feature data set is input into the first-layer classification network in the machine learning model with adaptive parameter adjustment to perform electrical parameter classification operations. The first-layer classification network adopts a three-layer convolutional neural network structure to obtain the interface electrical parameter state classification results; The interface electrical parameter state classification results are enhanced by adding a spatial attention mechanism and a channel attention mechanism. The spatial attention mechanism uses a parallel structure of maximum pooling and average pooling, and the channel attention mechanism uses a squeeze excitation module to obtain enhanced electrical parameter features. Performing feature fusion on the electric field response feature data set and the enhanced electrical parameter features to obtain fused feature data; The fused feature data is input into the second-layer classification network of the machine learning model with adaptive parameter adjustment to perform electric field response classification operation. The second-layer classification network adopts a residual network structure to obtain the classification result of the electric field response state. According to the preset interface conductivity evaluation criteria, the interface electrical parameter state classification results and the electric field response state classification results are comprehensively scored and fused to obtain a comprehensive score of the double-layer classification. The interface conductivity evaluation criteria include interface humidity index, physical structure parameters and ion distribution factor. A threshold judgment is performed on the comprehensive score of the double-layer classification. When the comprehensive score is greater than the target value, it is judged as a high-conductivity interface state. When the comprehensive score is less than or equal to the target value, it is judged as a low-conductivity interface state, and the interface state classification result is obtained.

[0037] In this embodiment, the interface characteristic data is separated according to the electrical parameter characteristics and the electric field response characteristics to obtain an electrical parameter characteristic data set and an electric field response characteristic data set. Assume that the interface characteristic data matrix is ,in Represents the coordinates of the data in the spatial dimension. Each element in the data matrix Electrical parameter characteristics and electric field response characteristics The data separation process is expressed as:

[0038] in and are the mask matrices for feature separation, and the electrical parameter part of the data set is extracted through matrix dot product operation. , extract the part belonging to the electric field response as , these separated data constitute the electrical parameter feature data set and the electric field response feature data set respectively. After completing the data separation, the electrical parameter feature data set is input into the first-layer classification network in the machine learning model with adaptive parameter adjustment for electrical parameter classification operation. The classification network adopts a three-layer convolutional neural network structure, and realizes deep learning of electrical parameter data through multi-level convolution and feature extraction. In the convolutional network, the first-layer convolution operation is performed through a small-sized convolution kernel (e.g. Extract local spatial features, assuming that the input feature map is , the convolution kernel is The convolution operation calculation formula is:

[0039] in Represents the first layer feature map obtained after convolution. Through the first layer of convolution, the edge features and local electrical characteristics in the electrical parameter data are extracted. In the second layer of convolution, a larger receptive field (e.g. The convolution kernel of ) aggregates features in a wider range, and further reduces the dimension of the feature map through pooling operations (such as maximum pooling and average pooling), retaining key information while reducing computational complexity. The third convolution layer is combined with the fully connected layer, and nonlinear activation functions (such as ReLU activation function) are used for feature enhancement, and the interface electrical parameter state classification results are output, which are expressed as ,in is the classification result of electrical parameter status, and are the weight and bias parameters of the convolutional layer, respectively. is the activation function. After obtaining the classification results, the interface electrical parameter state classification results are subjected to feature enhancement. The enhancement process includes adding a spatial attention mechanism and a channel attention mechanism. In the spatial attention mechanism, a parallel structure of maximum pooling and average pooling is adopted. Through the maximum pooling operation and average pooling operation At the same time, the important areas in the feature map are calculated, and the calculation formula is ,in is the enhanced feature map, is the Sigmoid activation function, which is used to compress the feature value into the range of (0,1). In the channel attention mechanism, the squeeze excitation module (SE module) is used to obtain the global feature response of each channel through global average pooling, and then the correlation modeling between channels is realized through the fully connected layer to obtain the enhanced electrical parameter characteristics. The enhanced electrical parameter characteristics are compared with the electric field response characteristic dataset Perform feature fusion. The feature fusion process adopts the weighted fusion method, through the weight coefficient matrix Calculate fusion feature data :

[0040] in, The feature fusion weight matrix is ​​used to dynamically adjust the fusion ratio of the two features through the optimal weighting method (such as linear weighting or covariance-based weighting algorithm) to ensure that the fused feature data fully expresses the comprehensive characteristics of electrical parameters and electric field response. The second-layer classification network input into the machine learning model with adaptive parameter adjustment performs electric field response classification operations. The second-layer classification network adopts a residual network structure. The residual network effectively solves the common gradient vanishing problem in deep learning networks by introducing jump connections, ensuring that the model can still maintain good classification performance when the depth increases. The residual module in the residual network is calculated by formula Calculate, where represents the output of the residual module, is the convolution kernel weight in the residual module, It is a convolution operation. By adding the input features directly to the output features, the feature identity mapping is realized. By stacking multiple layers of residual modules, the classification result of the electric field response state is obtained. In order to evaluate the interface conductivity, the electrical parameter state classification results are classified according to the preset interface conductivity evaluation standard. And the electric field response state classification results Comprehensive scoring calculation and decision fusion are performed. The interface conductivity evaluation criteria include interface humidity index , physical structure parameters and ion distribution factor , the comprehensive score calculation formula is:

[0041] in, For the comprehensive rating, is the weight coefficient of each evaluation index, and the comprehensive score calculation is realized through the weighted average method. The system makes a threshold judgment on the comprehensive score of the double-layer classification. Greater than target value When , it is judged as a high conductivity interface state, otherwise it is judged as a low conductivity interface state, and the interface state classification result is obtained. :

[0042] Optionally, the adjustment module 104 further includes: A setting unit, used for determining the interface conductive state according to the interface state classification result, setting a low-intensity current parameter for the high-conductivity interface state, and setting a high-intensity current parameter for the low-conductivity interface state, to obtain a target current parameter; A calculation unit, used to calculate the frequency of the current control system of the intelligent electrode sheet based on the target current parameter, wherein the first channel is in a constant current mode with an intensity of P milliamperes, and the second channel is in a pulse current mode with an intensity of Q milliamperes, to obtain the current channel parameter; A dynamic analysis unit is used to dynamically analyze the electric field distribution in the contact interface area, determine the material migration enhancement coefficient through electric field enhancement effect calculation, and obtain the migration enhancement parameter; The modulation unit is used to input the target current parameters into the current control system of the intelligent electrode sheet to perform current waveform modulation calculation to obtain current waveform trajectory data, and perform current output calculation according to the current waveform trajectory data and current channel parameters to obtain modulated current data; A compensation unit is used to perform interface compatibility analysis on the modulated current data to obtain interface reaction prediction data, and to perform current waveform compensation calculation based on the migration enhancement parameter and the interface reaction prediction data to obtain transmission current data; The prediction unit is used to calculate the functional substance release rate data based on the interface characteristic data, and perform functional substance release rate modulation operation on the transmission current data to obtain the predicted transmission current.

[0043] In this embodiment, the setting unit determines the conductive state of the interface according to the interface state classification result. When the classification model of the system outputs that the interface state is high conductivity, a low-intensity current parameter is selected to avoid excessive electrolysis of the interface or ion imbalance caused by excessive current. Assume that the low-intensity current parameter is set to mA; when the interface state is low conductivity, the system sets the high intensity current parameter mA, in order to enhance the electric field strength through higher current output, improve material migration efficiency and ion flux, and thus obtain the target current parameters , the calculation method of this parameter is expressed as:

[0044] After obtaining the target current parameters, the calculation unit is entered to perform specific current control system frequency calculation. The current control system of the smart electrode sheet is designed as a dual-channel mode. The first channel is a constant current mode, and the current intensity is set to mA is mainly used to maintain the basic electric field environment to ensure the formation of a stable current path between the electrode sheet and the contact interface. It is suitable for use when the interface conductivity is good to maintain the uniformity and stability of the material release. The second channel is the pulse current mode, and the current intensity is set to Milliamperes, by applying high-frequency or low-frequency pulse current, a periodically changing electric field effect is generated, and the pulse current is used to enhance the ion migration rate and the release rate of functional substances in the interface state with low ion concentration or poor conductivity. The calculation formula of the current channel parameter is:

[0045] in, is the output current of the current channel, Represents the timing function of the pulse current (such as a square wave or a triangle wave function), by adjusting and The proportion and The dynamic analysis unit dynamically analyzes the electric field distribution in the contact interface area. By collecting the electric field data of the interface area in real time, the material migration enhancement coefficient is calculated using the electric field enhancement effect. This coefficient reflects the enhancement multiple of the material migration speed relative to the standard state under the current electric field distribution conditions. Assuming the electric field strength is , in a certain area The electric field enhancement effect inside is expressed by the formula:

[0046] in, is the migration enhancement factor, is the reference electric field strength, For Region The area of ​​​​the ... The target current parameters are input into the current control system of the intelligent electrode sheet for current waveform modulation calculation. The modulation unit generates specific current waveform trajectory data through the current control algorithm (such as pulse width modulation PWM, frequency modulation FM or amplitude modulation AM). These data include the amplitude change of the current, as well as the phase, frequency and period characteristics of the waveform. The calculation formula of the waveform trajectory data is expressed as:

[0047] in, For time The current waveform at the moment, is the modulation frequency, is the phase shift. In this way, a complex current waveform is generated to achieve refined control of the electric field distribution. After obtaining the current waveform trajectory data, combined with the current channel parameters, the modulated current data is obtained through current output calculation to achieve dynamic current control of the smart electrode sheet. On this basis, the compensation unit performs interface compatibility analysis on the modulated current data, predicts the interface reaction behavior by analyzing the electrochemical properties of the interface material, the electrode polarization effect, and the ion concentration change trend, and obtains the interface reaction prediction data. The system combines the migration enhancement parameters and uses the waveform compensation algorithm to fine-tune the current waveform to achieve dynamic compensation of the current waveform. The compensation calculation formula is:

[0048] in, is the current data after compensation, The interface reaction prediction data is obtained by comparing the predicted interface response with the current current waveform and dynamically adjusting the output current to obtain the transmission current data. , so that the current output better adapts to the actual material transmission needs. The prediction unit calculates the release rate of the functional substance based on the interface characteristic data, and establishes a prediction model for the release rate of the functional substance by analyzing the electric field distribution, electrical parameters and interface state. Assuming that the release rate of the functional substance is , the prediction model is expressed as:

[0049] in, is the material release coefficient, is the material concentration distribution function in the interface area. The system calculates the functional material release rate data through this model, and performs functional material release rate modulation calculation on the transmission current data. By calculating the nonlinear relationship between current and material release rate, the current output parameters are adjusted to finally obtain the predicted transmission current. .

[0050] Optionally, the prediction unit is specifically used for: The interface characteristic data is input into the functional substance release rate calculation module, and the electric field migration characteristics of the preset functional molecule characteristics are calculated to obtain the target functional substance release rate spectrum; The release depth of the target functional substance release rate map is calibrated to obtain the calibrated functional substance release rate data, and the transmission current data is input into the material migration model for electric field driven calculation to obtain the target functional substance distribution data; Perform concentration gradient compensation calculation on the target functional substance distribution data according to the calibrated functional substance release rate data to obtain the compensated functional substance distribution, and input the compensated functional substance distribution into the smart electrode sheet to perform regionalized functional substance release regulation to obtain the initial transmission current; The initial transmission current is monitored in real time, and the current distribution uniformity and material migration depth parameters are calculated through the interface electric field diagnostic system to obtain transmission quality monitoring data; The calibrated functional substance release rate data is optimized and calculated according to the transmission quality monitoring data, and the optimized functional substance release rate data is obtained through iterative processing. The optimized functional substance release rate data is input into the smart electrode sheet for secondary current modulation to obtain the predicted transmission current.

[0051] In this embodiment, the interface characteristic data are input into the functional substance release rate calculation module. These interface characteristic data include electrical parameter distribution , Electric field response characteristics And the interface status classification results ,in Represents the spatial coordinates. By calculating these data with the electric field migration characteristics of the preset functional molecule characteristics, the release rate spectrum of the target functional substance is obtained. The release rate of the functional substance is calculated using the migration model of the functional molecule under the action of the electric field (such as the Nernst-Planck equation). Assuming that the concentration of the functional molecule is , the electric field strength is , the mobility is , then the target functional substance release rate The calculation formula is:

[0052] in, Represented in space coordinates The negative sign indicates the migration direction of the substance from the high concentration area to the low concentration area. Through this formula, the interface characteristic data is combined with the migration characteristics of the functional substance to generate the target functional substance release rate map, which shows the release rate changes in different areas in the form of two-dimensional spatial distribution. The release depth calibration is performed on the target functional substance release rate map to ensure that the release rate data accurately reflects the penetration effect of the functional substance at different depths. The calibration process is performed by adjusting the electric field strength. and the material diffusion coefficient Calculate the actual penetration depth of the material inside the interface , the calibration formula is:

[0053] in, is the diffusion coefficient, is the electric field strength. Through this calibration, the calibrated functional substance release rate data is obtained. At the same time, the current data will be transmitted Input the material migration model to perform electric field driven calculation to obtain the target functional material distribution data. The material migration model is based on the electric field induced ion migration theory and is calculated through the relationship between current and material concentration change. Assuming the current density is , the charge number is , the Faraday constant is , then the target functional substance distribution data The calculation formula is:

[0054] in, is the initial concentration, ( is the electrode area), this formula directly links the current data with the change in substance concentration, allowing the system to calculate the substance distribution in different areas in real time. The concentration gradient compensation calculation is performed on the target functional substance distribution data based on the calibrated functional substance release rate data to eliminate the uneven transmission caused by local excessive or low concentration. The concentration gradient compensation is calculated by and diffusion coefficient Compensation calculation is performed, and the distribution of functional substances after compensation The calculation formula is:

[0055] in, is the spatial gradient of the substance concentration, and the negative sign indicates that the concentration difference is balanced through the diffusion process, making the distribution of the substance in space more uniform. The compensated functional substance distribution data is input into the smart electrode sheet, and the release of substances in different spatial regions is finely controlled through regionalized functional substance release regulation to obtain the initial transmission current. Real-time feedback monitoring of the initial transmission current and calculation of the current distribution uniformity through the interface electric field diagnostic system and material migration depth parameters , the calculation formula for transmission quality monitoring data is:

[0056] in, For the monitoring area, Indicates in the area The uniformity of the internal current distribution, The actual depth of material migration is evaluated in real time through these monitoring data. The matching degree between the current output and the material transmission effect is optimized and calculated based on the transmission quality monitoring data. The key parameters in the release rate model are continuously adjusted through iterative processing methods (such as gradient descent method or adaptive learning algorithm). The optimized functional material release rate data The calculation formula is:

[0057] in, and is the adjustment coefficient, and The target current uniformity and target migration depth are respectively used. The release rate is automatically adjusted by the difference between the feedback data and the target value to achieve dynamic optimization of the material transfer process. The optimized functional material release rate data is input into the smart electrode sheet for secondary current modulation. The predicted transmission current is achieved by adjusting the current waveform, frequency and intensity again. The calculation formula for predicting the transmission current is:

[0058] in, is the modulation coefficient. Through this calculation, the system dynamically adjusts the current output to cope with different changes in interface states while maintaining a stable material release rate, thereby achieving adaptive regulation and efficient management of the material transfer process, ensuring that the intelligent electrode system can maintain optimal working performance in various complex environments and achieve high-precision material transfer and release effects.

[0059] Optionally, the parameter optimization module 105 is specifically used for: Perform target deviation analysis on the predicted transmission current, obtain initial deviation data by calculating the difference from the ideal transmission mode, and input the initial deviation data into the adaptive compensation unit of the programmable current controller for dynamic compensation calculation to obtain compensation amount parameters; Iteratively optimize the compensation parameters according to the compensation amount parameters, perform numerical calculations on the compensation parameters by the least square method, and obtain optimized compensation parameters; The optimized compensation parameters are input into the closed-loop control system, and the predicted transmission current is compensated to obtain the compensated current data; Perform high-precision electric field analysis on the compensated current data to obtain interface electric field quality data, and input the interface electric field quality data into the interface electric field diagnostic system for electric field difference calculation, and obtain material migration depth data through current density calculation; An interface adaptability evaluation model is established based on the interface electric field quality data and the material migration depth data. When the adaptability is lower than the preset adaptability threshold, it is determined that the current meets the output conditions, and a current quality determination result is obtained. Based on the current quality determination result, a working current that meets the conditions is output.

[0060] In this embodiment, the predicted transmission current Target deviation analysis is performed by calculating the deviation from the ideal transmission mode. The difference between the initial deviation data By calculating the error between the predicted current and the ideal current, the difference is calculated using the mean square error method. The specific formula is:

[0061] in, is the total number of sampling points, For the The sampling time, and are the predicted current and ideal current values ​​at that moment respectively. Through this formula, the deviation between the current output and the target value is quantified, and the initial deviation data is Input into the adaptive compensation unit of the programmable current controller for dynamic compensation calculation to obtain the compensation parameter The adaptive compensation unit uses a dynamic compensation algorithm (such as proportional-integral-differential PID control or adaptive filtering algorithm) based on the initial deviation data. Adjust the current output in real time, and the calculation formula of the compensation parameter is:

[0062] in, , and They are proportional, integral and differential control coefficients respectively. By adjusting these coefficients, fast response and output stability are balanced to achieve fine compensation of current deviation. The compensation parameters are iteratively optimized and the least squares method is used to numerically calculate the compensation parameters to obtain the optimized compensation parameters. The least squares method constructs the error objective function , minimize the sum of squared errors to achieve the best estimation of compensation parameters. The objective function is defined as:

[0063] By the objective function Perform minimization and use the gradient descent method or Newton method to calculate the optimal value of the compensation parameter to obtain the optimized compensation parameter. , the optimization formula is:

[0064] in, is the learning rate. After multiple iterations, the system converges to the minimum error point and achieves accurate optimization of the compensation parameters. The optimized compensation parameters are input into the closed-loop control system, and the predicted transmission current is compensated to obtain the compensated current data. The closed-loop control system adjusts the signal through real-time feedback to keep the current output close to the ideal current value. The calculation formula for the compensation operation is:

[0065] Through this calculation, the system can dynamically correct the error in the predicted transmission current during the current output process, so that the compensated current data better meets the target requirements of current control. Perform high-precision electric field analysis on the compensated current data to obtain the interface electric field quality data The electric field distribution data under the compensation current is collected by the electric field sensor, and the electric field intensity and distribution characteristics of the interface area are reconstructed using numerical analysis methods (such as finite element analysis FEM). The calculation formula of the electric field quality data is:

[0066] in, is the conductivity distribution function of the interface area. Through this calculation, the electric field intensity distribution at different spatial positions is obtained. At the same time, the interface electric field quality data is input into the interface electric field diagnosis system for electric field difference calculation. Compare and calculate the electric field difference :

[0067] The uniformity of current density distribution and material migration depth parameters are analyzed by electric field difference. Through Faraday's law and current density The calculation formula is:

[0068] in, is the current density, is the electrode surface area, is the charge number, is the Faraday constant, is the current action time, and this formula quantifies the actual migration depth of functional substances under the action of current. An interface adaptability evaluation model is established based on the electric field quality data and material migration depth data. The model calculates the interface adaptability through a multi-factor weighted scoring method. , the calculation formula is:

[0069] in, , and The weight coefficients for fitness evaluation are adjusted to balance the effects of electric field quality, migration depth, and electric field difference on fitness. Below the preset adaptation threshold When the system determines that the current meets the output conditions, the output current quality judgment result :

[0070] Output the working current that meets the conditions based on the current quality judgment result When it is determined that the conditions are met, the system directly outputs the compensated current data as the final working current. Otherwise, the system adjusts the compensation parameters through the feedback mechanism, and re-iterates the calculation and compensation operation until the current output reaches the preset quality standard, thereby realizing closed-loop optimization and precise control of the current output process, ensuring that the smart electrode sheet always maintains efficient and stable material transmission capabilities under different interface states, and provides ideal current output effects.

[0071] In the embodiment of the present application, the electrical parameters and electric field response data of the contact interface are acquired in real time by the acquisition module 101, and the data is deeply processed in combination with the feature analysis module 102, so that the system can accurately identify different types of interface states. Based on the double-layer feature fusion technology, the interface characteristic data acquired by the system is more comprehensive and accurate, providing a reliable basis for parameter adjustment. The state classification module 103 adopts an innovative double-layer classification network structure, and through the combined application of a three-layer convolutional neural network and a residual network, the spatial attention mechanism and the channel attention mechanism are used to enhance the feature expression ability, thereby achieving high-precision interface conductivity state classification. The adjustment module 104 intelligently sets the current parameters according to the classification results, and the high and low conductivity interfaces use different current intensities respectively, and calculates the material migration enhancement coefficient through the electric field enhancement effect, thereby reducing energy consumption and improving material transfer efficiency. The constant current and pulse current dual-channel collaborative control strategy is adopted to significantly improve the uniformity of material distribution, reduce edge effects, and improve system adaptability. The parameter optimization module 105 constructs a complete closed-loop control system, monitors and adjusts the working current in real time, prevents unsuitable current parameters from having a negative impact on the interface, and greatly improves the long-term working stability of the system. In addition, the system accurately calculates the release rate of functional substances based on interface characteristic data, and realizes the directional migration and efficient utilization of substances through concentration gradient compensation and regional release regulation technology. At the same time, with the help of interface adaptability evaluation model and high-precision electric field analysis technology, the control accuracy of material migration depth is significantly improved, realizing precise material transfer control capabilities.

[0072] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, device, article or system including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, device, article or system. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the existence of other identical elements in the process, device, article or system including the element.

[0073] The above description is only a preferred embodiment of the present invention, and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. An intelligent electrode patch drug-penetrating physiotherapy system with adaptive adjustment of skin resistance, characterized in that: include: The acquisition module is used to perform real-time electrical parameter acquisition and electric field response measurement on the contact interface area of ​​the smart electrode sheet to obtain electrical parameter distribution data and electric field response distribution data; A feature analysis module, used to convert the electrical parameter distribution data into a first feature spectrum, convert the electric field response distribution data into a second feature spectrum, and perform feature analysis to obtain interface characteristic data; A state classification module, used for inputting the interface characteristic data into a machine learning model with adaptive parameter adjustment to perform interface state classification operation and obtain an interface state classification result; A regulating module, used to determine the current output parameter and the material migration enhancement coefficient according to the interface state classification result, and to adjust the output power and control the material release of the smart electrode sheet to obtain a predicted transmission current; The parameter optimization module is used to perform deviation calculation and compensation parameter optimization on the predicted transmission current, and output a working current that meets the conditions.

2. The intelligent electrode patch drug-penetrating physiotherapy system with adaptive skin resistance adjustment according to claim 1 is characterized in that: The acquisition module is specifically used for: Performing a microcurrent detection operation on the interface between the smart electrode sheet and the contact surface to obtain a target electrical parameter spectrum, and digitally processing the target electrical parameter spectrum to obtain initial electrical parameter data; Performing grid area statistical calculation on the initial electrical parameter data to obtain electrical parameter distribution data, and performing normalization processing and data smoothing operation on the electrical parameter distribution data to obtain interface electrical parameter distribution data; Performing real-time sampling of the contact interface region with a multi-frequency electric field response sensor to obtain real-time electric field response data, and performing interface tomography calculation on the real-time electric field response data to obtain initial electric field response sampling data; Performing spatial distribution statistical analysis on the initial electric field response sampling data to obtain electric field response statistical distribution data; Coordinate transformation and numerical integration operations are performed on the electric field response statistical distribution data to obtain electric field response correction data, and the electric field response correction data is input into an electric field distribution reconstruction algorithm to reconstruct the spatial electric field distribution to obtain electric field response distribution data.

3. The skin resistance adaptively adjusted intelligent electrode patch drug-permeable physiotherapy system according to claim 2 is characterized in that: The feature analysis module is specifically used for: Normalizing and dividing the interface electrical parameter distribution data into statistical intervals to obtain electrical parameter distribution statistical intervals; According to the electrical parameter distribution statistical interval, data mapping and frequency counting are performed on the interface electrical parameter distribution data to obtain electrical parameter frequency statistical results, and a first characteristic spectrum is generated according to the electrical parameter frequency statistical results; Normalizing and dividing the electric field response distribution data into statistical intervals to obtain electric field response distribution statistical intervals; According to the electric field response distribution statistical interval, performing data mapping and frequency counting on the electric field response distribution data to obtain electric field response frequency statistical results, and generating a second characteristic spectrum according to the electric field response frequency statistical results; Performing principal component analysis on the first characteristic spectrum to extract the electrical parameter distribution characteristic vector to obtain a first characteristic vector, and performing principal component analysis on the second characteristic spectrum to extract the electric field response distribution characteristic vector to obtain a second characteristic vector; Performing feature weight calculations on the first feature vector and the second feature vector respectively, and determining a weight coefficient matrix for feature fusion through covariance matrix calculation; A weighted fusion operation is performed on the first eigenvector and the second eigenvector according to the weight coefficient matrix to obtain interface characteristic data.

4. The skin resistance adaptively adjusted intelligent electrode patch drug-permeable physiotherapy system according to claim 1, characterized in that: The state classification module is specifically used for: According to the electrical parameter characteristics and the electric field response characteristics, the interface characteristic data are separated to obtain an electrical parameter characteristic data set and an electric field response characteristic data set; Inputting the electrical parameter feature data set into the first-layer classification network in the machine learning model with adaptive parameter adjustment to perform electrical parameter classification operation, wherein the first-layer classification network adopts a three-layer convolutional neural network structure to obtain the interface electrical parameter state classification result; Performing feature enhancement processing on the interface electrical parameter state classification result, including adding a spatial attention mechanism and a channel attention mechanism, wherein the spatial attention mechanism adopts a parallel structure of maximum pooling and average pooling, and the channel attention mechanism adopts a squeeze excitation module, to obtain enhanced electrical parameter features; Performing feature fusion on the electric field response feature data set and the enhanced electrical parameter feature to obtain fused feature data; Inputting the fused feature data into the second-layer classification network in the machine learning model with adaptive parameter adjustment to perform electric field response classification operation, wherein the second-layer classification network adopts a residual network structure to obtain an electric field response state classification result; According to a preset interface conductivity evaluation standard, a comprehensive score calculation and decision fusion are performed on the interface electrical parameter state classification result and the electric field response state classification result to obtain a comprehensive score of the double-layer classification, wherein the interface conductivity evaluation standard includes an interface humidity index, a physical structure parameter and an ion distribution factor; A threshold judgment is performed on the comprehensive score of the double-layer classification. When the comprehensive score is greater than the target value, it is determined to be a high-conductivity interface state. When the comprehensive score is less than or equal to the target value, it is determined to be a low-conductivity interface state, thereby obtaining an interface state classification result.

5. The skin resistance adaptively adjusted intelligent electrode patch drug-permeable physiotherapy system according to claim 1, characterized in that: The adjustment module also includes: A setting unit, used for determining the interface conductive state according to the interface state classification result, setting a low-intensity current parameter for a high-conductivity interface state, and setting a high-intensity current parameter for a low-conductivity interface state, to obtain a target current parameter; A calculation unit, used to calculate the frequency of the current control system of the smart electrode sheet based on the target current parameter, wherein the first channel is in a constant current mode with an intensity of P milliamperes, and the second channel is in a pulse current mode with an intensity of Q milliamperes, to obtain current channel parameters; A dynamic analysis unit, used to perform a dynamic analysis of the electric field distribution in the contact interface region, determine the material migration enhancement coefficient by calculating the electric field enhancement effect, and obtain a migration enhancement parameter; A modulation unit, used for inputting the target current parameter into the current control system of the intelligent electrode sheet to perform current waveform modulation calculation to obtain current waveform trajectory data, and performing current output calculation according to the current waveform trajectory data and the current channel parameter to obtain modulated current data; A compensation unit, configured to perform interface compatibility analysis on the modulated current data to obtain interface reaction prediction data, and perform current waveform compensation calculation according to the migration enhancement parameter and the interface reaction prediction data to obtain transmission current data; The prediction unit is used to calculate the functional substance release rate data based on the interface characteristic data, and perform functional substance release rate modulation operation on the transmission current data to obtain a predicted transmission current.

6. The skin resistance adaptively adjusted intelligent electrode patch drug-permeable physiotherapy system according to claim 5, characterized in that: The prediction unit is specifically used for: The interface characteristic data is input into a functional substance release rate calculation module, and the electric field migration characteristics of the preset functional molecule characteristics are calculated to obtain a target functional substance release rate spectrum; Performing a release depth calibration on the target functional substance release rate map to obtain calibrated functional substance release rate data, and inputting the transmission current data into a material migration model for electric field driven calculation to obtain target functional substance distribution data; Performing concentration gradient compensation calculation on the target functional substance distribution data according to the calibrated functional substance release rate data to obtain compensated functional substance distribution, and inputting the compensated functional substance distribution into the smart electrode sheet to perform regionalized functional substance release regulation to obtain an initial transmission current; Performing real-time feedback monitoring on the initial transmission current, calculating the current distribution uniformity and material migration depth parameters through an interface electric field diagnostic system, and obtaining transmission quality monitoring data; The calibrated functional substance release rate data is optimized and calculated according to the transmission quality monitoring data, and the optimized functional substance release rate data is obtained through iterative processing, and the optimized functional substance release rate data is input into the smart electrode sheet for secondary current modulation to obtain the predicted transmission current.

7. The intelligent electrode patch drug-penetrating physiotherapy system with adaptive skin resistance adjustment according to claim 1 is characterized in that: The parameter optimization module is specifically used for: Performing target deviation analysis on the predicted transmission current, obtaining initial deviation data by calculating the difference from the ideal transmission mode, and inputting the initial deviation data into a programmable current controller adaptive compensation unit for dynamic compensation calculation to obtain compensation amount parameters; Iteratively optimize the compensation parameters according to the compensation amount parameters, and numerically calculate the compensation parameters by the least square method to obtain optimized compensation parameters; Inputting the optimized compensation parameters into a closed-loop control system, performing compensation calculation on the predicted transmission current, and obtaining compensated current data; Performing high-precision electric field analysis on the compensated current data to obtain interface electric field quality data, and inputting the interface electric field quality data into an interface electric field diagnostic system to perform electric field difference calculation, and obtaining material migration depth data by current density calculation; An interface adaptability evaluation model is established according to the interface electric field quality data and the material migration depth data. When the adaptability is lower than a preset adaptability threshold, it is determined that the current meets the output conditions, a current quality determination result is obtained, and a working current that meets the conditions is output based on the current quality determination result.

Images