Servo tension-based sterile barrier sealing strength detection method and system

Abstract

The invention belongs to the technical field of sealing detection, and particularly relates to a sterile barrier sealing strength detection method and system based on servo tension, and the method comprises the following steps: cutting a sterile sealing sample to form an initial detection sample; and applying constant displacement constraint, and constructing a constant mechanical test reference data set. After temperature control is stable, servo force values and dielectric parameters are synchronously collected, homologous time sequence data are obtained, and a mechanical-dielectric original time sequence data set is formed through integration. And extracting stress relaxation data to calculate a relaxation modulus, fitting to construct a mechanical-dielectric correlation model, and deducing the long-term creep failure life through a short-time test. And finally, combining the service life and the interface state, calculating a sealing strength equivalent value through model mapping, and forming a whole-process data closed loop. According to the invention, through fusion of servo tension and dielectric homologous detection, short-time cross-scale extrapolation and block chain evidence storage, precise characterization of sealing strength, full-period lossless pre-judgment and compliance traceable closed loop are realized, and the detection precision and efficiency are improved.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of sealing detection and analysis, in particular to a sterile barrier sealing strength detection method and system based on servo tension. BACKGROUND

[0002] The traditional sterile barrier sealing strength detection method has obvious shortcomings, and is mostly in a destructive single-point detection mode, only instantaneous breaking strength values can be obtained, the long-term degradation trend and service life of the sealing strength cannot be predicted, and the sample is scrapped after detection, so that subsequent integrity verification cannot be connected. The detection dimension is single, only macro mechanical properties are concerned, the micro degradation state of the sealing interface is ignored, and early failure precursors such as interface debonding and gap initiation are difficult to capture, and the detection precision is low. In addition, the traditional method has no systematic data calibration and storage mechanism, the data is fragmented and cannot be traced, is easy to be disturbed by assembly and environment, and cannot realize synchronous collection of mechanical and dielectric parameters, so it is difficult to fully reflect the real state of the sealing strength, and cannot meet the detection requirements of high precision, full cycle and compliance traceability of sterile medical devices. SUMMARY

[0003] In order to make up for the shortcomings of the prior art, the sterile barrier sealing strength detection method based on servo tension is provided. The application is mainly used to solve the problems of traditional detection destruction, inability to predict service life and untraceable data.

[0004] The sterile barrier sealing strength detection method based on servo tension provided by the application comprises the following steps: S1: cutting a sterile sealing sample, adhering a flexible interdigital electrode to the sealing interface of the sample and connecting the sample to an impedance analyzer to form an initial detection sample.

[0005] S2: applying a constant displacement constraint to the initial detection sample, activating the force value collection state, fusing the sample geometric characteristics and circuit reference parameters to construct a constant mechanical test reference data set.

[0006] S3: According to the constant mechanical test reference data set, set the parameters of the impedance analyzer, start the temperature control module to stabilize the temperature, trigger synchronous collection, match the servo real-time force value with the dielectric parameter, and obtain the homologous time sequence detection data.

[0007] S4: According to the homologous time sequence detection data, continuously collect the stress decay change and dielectric constant, loss factor and impedance modulus evolution information in the collection period until the dielectric parameter tends to be stable, and form a mechanical-dielectric original time sequence data set.

[0008] S5: Extracting stress relaxation data from the mechanical-dielectric original time sequence data set to calculate the relaxation modulus, fitting the relaxation modulus with the dielectric loss factor characteristic peak, constructing a mechanical-dielectric correlation model and substituting a preset creep failure threshold, and deducing the long-term creep failure life of the sealing element through short-time test data.

[0009] S6: According to the interface bonding state inversed from the long-term creep failure life and the dielectric parameter, the measured equivalent value of the sterile barrier sealing strength is calculated through a mechanical-dielectric correlation model mapping to form a full-process data closed loop.

[0010] According to the sterile barrier sealing strength detection method based on servo tension provided by the application, in step S2, the specific steps of constructing the constant mechanical test reference data set are: S21: The assembly surface of the initial detection sample is precisely fitted with a rigid constraint tool, the tool stroke is calibrated through a displacement sensor, the sample is locked with full-degree-of-freedom constant displacement constraint, and sample positioning reference data is output.

[0011] S22: The sample positioning reference data is imported into a force value collection device, a piezoelectric force sensor and a signal conditioning circuit are activated, initial force value time series signals in the constraint state are collected according to a preset sampling frequency, and original force values are output.

[0012] S23: Three-dimensional visual scanning is used to obtain the inner and outer contours, wall thickness and sealing surface roughness of the sample, the spatial matching of feature points and force value sampling points is completed according to the original force value collection data stream, and a geometry-force value correlation feature matrix is output.

[0013] S24: The geometry-force value correlation feature matrix is drift-corrected and outlier-removed according to the circuit reference parameters, the mechanical response law under the constraint boundary is fitted through finite element simulation, and the constant mechanical test reference data set is generated.

[0014] According to the sterile barrier sealing strength detection method based on servo tension provided by the application, in step S24, the specific steps of generating the constant mechanical test reference data set are: According to the geometry-force value correlation feature matrix, the circuit reference parameters corresponding to the initial detection sample are retrieved, the drift data in the matrix is accurately corrected, the outliers generated in the collection process are removed, and a corrected geometry-force value correlation feature matrix is obtained.

[0015] According to the corrected geometry-force value correlation feature matrix, a finite element simulation model suitable for the constant displacement constraint scene is built, the constraint boundary conditions are input, the mechanical response law of the sample under the constraint state is fitted through simulation iteration, and a mechanical response simulation data set is formed.

[0016] The corrected geometry-force value correlation feature matrix and the mechanical response simulation data are data-regularized, dimension-unified and precision-calibrated to generate the constant mechanical test reference data set.

[0017] According to the sterile barrier sealing strength detection method based on servo tension provided by the application, in step S3, the specific steps of obtaining the homologous time sequence detection data are: S31: Based on the sampling frequency, measurement point coordinates and calibration coefficient of the constant mechanical test reference data set, a mechanical parameter-dielectric instrument configuration linkage mapping model is constructed, and the excitation voltage, test frequency band and sampling point number are dynamically iteratively optimized by an adaptive algorithm, and an instrument configuration parameter set is output.

[0018] S32: The instrument configuration parameter set is input into the impedance analyzer and open circuit short circuit load calibration is performed, PID temperature control and predictive compensation algorithm is used to stabilize to the target detection temperature, and a constant temperature environment state identifier is output.

[0019] S33: The temperature stability check code in the constant temperature environment state identifier is analyzed, a double-channel trigger signal with timing pre-synchronization is triggered, a servo system is driven to realize adaptive loading according to the constraint law of the mechanical reference data set, a servo real-time force value time sequence stream is output.

[0020] S34: The servo real-time force value time sequence stream and the dielectric parameter time sequence stream are accurately aligned according to a unified timestamp using a homologous anchoring algorithm, time sequence mismatch and signal distortion data are automatically identified and removed in combination with correlation analysis, and a homologous time sequence detection data set is generated.

[0021] According to the sterile barrier sealing strength detection method based on servo tension provided by the application, in step S34, the specific steps of accurate timestamp alignment are as follows: The homologous clock anchor points of the force value time sequence stream and the dielectric parameter time sequence stream are extracted, the three times spline interpolation resampling of the two non-equidistant data is performed, and the unified sampling frequency and timestamp axis are obtained. The remaining time sequence offset is corrected by cross-correlation function peak positioning, the accurate digital alignment of the two signals in time domain is completed, and the aligned two-way time sequence matrix is generated.

[0022] According to the aligned two-way time sequence matrix, the Pearson correlation coefficient r is calculated window by window, the mismatch threshold is set, the signal amplitude distortion and jump point is detected, the abnormal point binary mask matrix is generated, the time sequence matrix is removed according to the mask, and the cleaned two-way time sequence matrix is output.

[0023] The cleaned two-way time sequence matrix is normalized and quantized, digital meta information is added to the matrix, the matrix data structure with fused meta information is organized in CSV format, and the homologous time sequence detection data set with digital checksum is generated.

[0024] According to the sterile barrier sealing strength detection method based on servo tension provided by the application, in step S4, the specific steps of forming the mechanical-dielectric original time sequence data set are as follows: S41: The force value and time sequence dielectric data are collected using an adaptive sliding window iterative algorithm according to the homologous time sequence detection data, the trend entropy and fluctuation threshold of the dielectric constant, loss factor and impedance modulus value are calculated in real time, the steady state is dynamically determined, and the continuous acquisition time sequence segment is output.

[0025] S42: According to the continuous acquisition time sequence segment and the trend fitting parameter, a periodic adaptive segmentation algorithm is used to divide the acquisition period, a time sequence alignment verification model is used to accurately map the stress decay sequence and the dielectric parameter sequence in each period, the decay rate and the dielectric evolution gradient feature are extracted, and a mechanical-dielectric correlation time sequence subset is generated.

[0026] S43: According to the mechanical-dielectric correlation time sequence subset, an anomaly detection algorithm is used to perform adaptive weighted interpolation repair on the missing points, the whole period multi-dimensional feature data is integrated, the time sequence consistency verification is completed, and the mechanical-dielectric original time sequence data set is output.

[0027] According to the sterile barrier sealing strength detection method based on servo tension provided by the application, in step S5, the specific steps of deducing the long-term creep failure life of the sealing element are: S51: Extract the force value and time sequence of the stress relaxation stage from the mechanical-dielectric original time sequence data set, use a variable order exponential decay model to fit the relaxation modulus evolution, and output a dynamic relaxation modulus sequence.

[0028] S52: According to the dynamic relaxation modulus sequence, a multi-scale wavelet transform is used to extract the time-frequency domain feature peak value of the dielectric loss factor, a nonlinear mapping of the relaxation modulus and the dielectric loss peak value is constructed through an attention mechanism weighting, and a mechanical-dielectric correlation model is output.

[0029] S53: The mechanical-dielectric correlation model is substituted into the preset creep failure threshold, combined with the long-time life data of similar materials transferred by the transfer learning framework, the short-time test data is extrapolated in a cross-scale manner, and a long-term creep failure life prediction result of the sealing element is output.

[0030] According to the sterile barrier sealing strength detection method based on servo tension provided by the application, in step S52, the specific steps of outputting the mechanical-dielectric correlation model are: Extract the dielectric loss factor time sequence in the dynamic relaxation modulus sequence, use a multi-scale wavelet transform to do time-frequency domain decomposition on the dielectric loss factor, get the wavelet coefficient matrix under different scales, and locate the local extreme points under each scale as the time-frequency domain feature peak value.

[0031] According to the time-frequency domain feature peak value and the dynamic relaxation modulus sequence, the time sequence is aligned, the contribution weight of each feature peak value to the relaxation modulus is calculated through the attention mechanism, the weighted feature-modulus correlation pair is generated, and the initial nonlinear mapping relationship is constructed.

[0032] The weighted feature-modulus correlation pair is input into a deep neural network, the fitting error of the correlation pair is used as a loss function to iteratively optimize the network parameters, and after convergence, a mechanical-dielectric correlation model with dynamic weight distribution capability is output.

[0033] According to the sterile barrier seal strength detection method based on servo tension provided by the application, in step S6, the specific steps for forming a full-process data closed loop are: S61: based on the interface bonding defect distribution inversed from the long-term creep failure life confidence interval and the dielectric time-frequency domain feature, a multi-dimensional strength mapping feature tensor is constructed, a creep constitutive correction factor is embedded for tensor normalization processing, and a normalized strength mapping feature tensor is obtained.

[0034] S62: the normalized strength mapping feature tensor is input into a mechanics-dielectric correlation model, an equivalent value of the sterile barrier seal strength is solved through adaptive weight reasoning, and a strength quantification atlas with error traceability is generated.

[0035] S63: according to the strength quantification atlas, the full-process original data, model parameters and verification results are connected in series to establish a block chain type evidence link to complete data verification, and a full-process closed data chain is formed.

[0036] The application also provides a sterile barrier seal strength detection system based on servo tension, comprising: A sample preparation module is used to cut a sterile seal sample, adhere a flexible interdigital electrode to the seal interface of the sample, and connect the sample to an impedance analyzer to form an initial detection sample.

[0037] A reference construction module is used to apply a constant displacement constraint to the initial detection sample, activate a force value collection state, and fuse sample geometric features and circuit reference parameters to construct a constant mechanical test reference data set.

[0038] A synchronous acquisition module is used to set parameters in the impedance analyzer according to the constant mechanical test reference data set, start a temperature control module to stabilize the temperature, trigger synchronous acquisition, match the servo real-time force value with the dielectric parameters, and obtain homologous time sequence detection data.

[0039] A data set generation module is used to continuously collect stress decay changes and dielectric constant, loss factor and impedance modulus evolution information within the collection period until the dielectric parameters tend to be stable, and form a mechanics-dielectric original time sequence data set.

[0040] A life deduction module is used to extract stress relaxation data from the mechanics-dielectric original time sequence data set to calculate the relaxation modulus, fit the relaxation modulus with the dielectric loss factor characteristic peak, construct a mechanics-dielectric correlation model and substitute a preset creep failure threshold, and deduce the long-term creep failure life of the seal through short-time test data.

[0041] A strength closed loop module is used to calculate the measured equivalent value of the sterile barrier seal strength through the mechanics-dielectric correlation model based on the interface bonding state inversed from the long-term creep failure life and the dielectric parameters, and form a full-process data closed loop.

[0042] The application provides a sterile barrier sealing strength detection method based on servo tension, which combines servo tension and dielectric homologous detection, short-time cross-scale extrapolation and block chain storage, realizes accurate characterization of sealing strength, full-cycle non-destructive prediction and compliance traceable closed loop, and improves detection accuracy and efficiency.

[0043] The application has the following advantages: 1. The application combines servo tension displacement closed-loop constraint technology and flexible interdigital electrode dielectric detection technology, synchronously collects macro mechanical signals and micro dielectric parameters of the sealed sample, combines homologous clock anchoring, time sequence accurate alignment and multi-dimensional data calibration, constructs a constant mechanical test reference and homologous time sequence detection system, and effectively eliminates system errors caused by assembly deflection, circuit interference and environmental fluctuations. Compared with the traditional single mechanical or dielectric detection mode, the fusion mode can simultaneously capture stress relaxation, modulus attenuation and sealing interface dielectric characteristic evolution, accurately invert the interface bonding defect distribution and bonding force degradation law, provide comprehensive and reliable multi-dimensional data source for sterile barrier sealing strength equivalent calculation, significantly improve the resolution, accuracy and data traceability of sealing strength detection, and solve the technical pain point that the traditional detection cannot accurately capture the subtle degradation of the interface.

[0044] 2. The application extracts stress relaxation information from the mechanical-dielectric original time sequence data, combines variable order exponential fitting, multi-scale wavelet transform and attention mechanism, constructs a high-precision mechanical-dielectric correlation model, introduces a transfer learning framework to transfer long-time life data of similar materials, realizes cross-scale extrapolation of short-time test data to long-term creep failure life. This method does not need to carry out long-time aging test, greatly shortens the detection cycle and reduces the detection cost, and adopts non-destructive detection mode throughout, so that the tested sample can be connected to subsequent sterile barrier integrity verification. At the same time, through the coupling mapping of relaxation modulus and dielectric characteristics, the real-time residual value of sealing strength can be deduced reversely, the strength degradation rate can be quantified, the transformation from instantaneous strength detection to full-life cycle strength trend prediction can be realized, and the short board that the traditional destructive detection can only obtain single-point instantaneous strength and cannot predict long-term reliability is effectively made up.

[0045] 3.The application realizes the deep linkage and accurate matching of mechanical, dielectric and strength data by taking the sealing strength quantification atlas as the core anchor point, connecting the whole process data of sample preparation, benchmark construction, synchronous acquisition, model deduction and strength calculation, embedding the creep constitutive correction and adaptive weight reasoning technology.Meanwhile, the blockchain node hash encryption technology is used to build an unalterable evidence link to complete the consistency and integrity verification of the whole process data, forming a complete closed loop of detection-modeling-deduction-verification-evidence storage.The closed loop system not only solves the problem of fragmented and untraceable traditional detection data, but also realizes the whole process checkable strength calculation process through the error traceability atlas, and the preserved undamaged sample can further connect the sterile barrier integrity verification, realize the linkage verification of sealing strength and barrier performance, and fully meet the compliance requirements of sterile medical device quality control, providing standardized and quantifiable technical support for product quality supervision and fault traceability. BRIEF DESCRIPTION OF DRAWINGS

[0046] The application will be further described below according to the drawings.

[0047] Fig. 1 is a step diagram of a sterile barrier sealing strength detection method based on servo tension provided by an embodiment of the application; Fig. 2 is a flowchart of a sterile barrier sealing strength detection method based on servo tension provided by an embodiment of the application; Fig. 3 is a module diagram of a sterile barrier sealing strength detection system based on servo tension provided by an embodiment of the application. DETAILED DESCRIPTION

[0048] In order to make the technical means, creative features, purposes and effects realized by the application easy to understand, the application will be further described below according to the specific embodiments.

[0049] As shown in Figs. 1 to 3 , the sterile barrier sealing strength detection method based on servo tension provided by the embodiment of the application, the method comprises: S1: cutting a sterile sealing sample and adhering a flexible interdigital electrode at the sealing interface, connecting the electrode lead to an impedance analyzer, completing insulation check to ensure stable test circuit and forming an initial test sample.

[0050] Cut the sterile sealing sample, remove the impurities and excess corners on the surface of the sample, and form a sterile sealing basic sample.

[0051] Adhere the flexible interdigital electrode on the complete sealing interface of the sterile sealing basic sample, arrange the electrode lead after adhesion, and form a pretreated sample.

[0052] The electrode lead of the pretreated sample is connected to the impedance analyzer to avoid poor contact affecting the stability of the test. After the lead is connected, the sample to be insulated is obtained for inspection.

[0053] The sample to be insulated for inspection is connected to the impedance analyzer for insulation detection to check for circuit short circuit, poor contact and other hidden dangers. The lead connection state is adjusted in time until the detection is qualified to ensure the stability of the test circuit and form the initial test sample for subsequent test.

[0054] S2: The initial test sample is clamped to the servo tension machine insulation tool, the servo tension machine is switched to displacement closed loop control mode, the preloaded displacement is set and the displacement value is locked, the force value collection channel is opened and standby, and the constant constraint mechanical test reference condition is constructed according to the initial state of the circuit.

[0055] S21: The assembly surface of the initial test sample is precisely fitted with the rigid constraint tool, the tool stroke is calibrated by the displacement sensor, the constant displacement constraint locking of the sample is completed, and the sample positioning reference data is output.

[0056] The positioning reference surface of the initial test sample assembly surface and the rigid constraint tool is aligned edge by edge, and the gap is detected with a feeler gauge , if > (the allowable gap threshold), the posture correction is performed through the three-axis fine adjustment mechanism, the correction amount is , and the assembly deflection and gap error are eliminated.

[0057] The displacement sensor closed loop calibration tool three-axis feed stroke is started, the displacement feedback value of each level of feed is collected, the feed displacement feedback xi, yi, zi is collected, the stroke cumulative deviation is calculated and compensated.

[0058] The calculation formula of the stroke cumulative deviation is: In the formula, is the displacement average, is the set displacement.

[0059] The stroke cumulative deviation compensation amount calculation formula is represented as: In the formula, is the total sum of the cumulative deviation of multiple strokes, which refers to the algebraic cumulative value of the stroke cumulative deviation ΔX generated in each level of feed action from the start of the tool to the current time. is the jth stroke cumulative deviation, which refers to the difference between the displacement average at the jth sampling time and the set displacement of the corresponding level, and m is the cumulative feed number.

[0060] According to the calibrated precise displacement parameter driving the tool locking mechanism, the displacement freedom of the six degrees of freedom of the sample is locked, and the sample positioning reference data containing three-dimensional coordinates, constraint stiffness and stroke compensation value is output .

[0061] S22: The sample positioning reference data is imported into the force value acquisition device, the piezoelectric force sensor and the signal conditioning circuit are activated, the initial force value time series signal under the constraint state is collected according to the preset sampling frequency, and the original force value is output.

[0062] The sample positioning reference data is imported into the main control unit of the force value acquisition device, the one-to-one mapping configuration of the tool coordinates and the sensor acquisition channel is completed, and the matching accuracy of the coordinate mapping is verified. The piezoelectric force sensor and the signal conditioning circuit are powered, zero point clearing, gain calibration and noise floor test are performed, and it is ensured that the circuit is in a stable acquisition state.

[0063] The zero point clearing formula is represented as: In the formula, is the no-load voltage, n is the number of sampling points, is the zero point clearing compensation voltage, k is the sample sequence number, representing the kth no-load voltage sampling.

[0064] According to the preset high-frequency sampling frequency, continuous acquisition is triggered, the sampling time stamp and the corresponding constraint coordinates are synchronously marked, the continuous force value time series signal under the constraint state is stored, and the original force value data set associated with the time stamp and the coordinates is output.

[0065] S23: The three-dimensional visual scanning is adopted to obtain the inner and outer contours, wall thickness and sealing surface roughness of the sample, the spatial matching of the feature points and the force value sampling points is completed according to the original force value acquisition data stream, and the geometric-force value correlation feature matrix is output.

[0066] The focal length, scanning accuracy and field of view range of the three-dimensional visual scanning equipment are debugged, non-contact scanning is performed on the whole domain of the sample, the inner and outer contour coordinates, wall thickness distribution value and sealing surface microscopic roughness parameters are extracted through point cloud reconstruction. The time stamp and sampling coordinate sequence of the original force value data set are analyzed, the geometric feature points and the force value sampling points are matched according to the spatial coordinate consistency principle, and the invalid data with unmatched coordinates are removed. The one-to-one corresponding geometric feature parameters and force value data are integrated according to the unified dimension, and the geometric-force value correlation feature matrix containing spatial coordinates, geometric parameters and force value signals is constructed.

[0067] S24: According to the calibration of the circuit reference parameters, the drift correction and outlier removal are performed on the geometric-force value correlation feature matrix, the mechanical response law under the constraint boundary is fitted through finite element simulation, and the constant mechanical test reference data set is generated.

[0068] According to the geometric-force value correlation characteristic matrix, the circuit reference parameters corresponding to the initial test sample are retrieved, the drift data in the matrix is accurately corrected, the abnormal values generated in the collection process are eliminated, and a corrected geometric-force value correlation characteristic matrix is obtained.

[0069] According to the corrected geometric-force value correlation characteristic matrix, a finite element simulation model of an adaptive constant displacement constraint scene is built, the constraint boundary conditions are input, the mechanical response law of the sample under the constraint state is fitted through simulation iteration, and a mechanical response simulation data set is formed.

[0070] The corrected geometric-force value correlation characteristic matrix and the mechanical response simulation data are subjected to data regularization, dimension unification and precision calibration, and a constant mechanical test reference data set is generated.

[0071] S3: According to the mechanical test reference conditions, the test frequency band and low-voltage alternating current test voltage suitable for the polymer sealing material are set on the impedance analyzer, the temperature control module is started to stabilize the test environment temperature, the servo tension machine and the impedance analyzer are triggered for synchronous collection, the force value output by the servo tension machine and the dielectric parameters collected by the impedance analyzer are collected on the time axis, and macro mechanical and micro dielectric homochronous detection data are obtained.

[0072] S31: Based on the sampling frequency, measurement point coordinates and calibration coefficients of the constant mechanical test reference data set, a mechanical parameter-dielectric instrument configuration linkage mapping model is constructed, and the excitation voltage, test frequency band and sampling point number are dynamically iteratively optimized through an adaptive algorithm, and an instrument configuration parameter set is output.

[0073] The mechanical test reference data set is subjected to time domain sampling frequency Fourier spectrum analysis, and the main frequency component and aliasing threshold are extracted. The measurement point Cartesian coordinates are converted into a spatial normalized digital coordinate vector (the range is mapped to [0, 1]). The calibration coefficients are least square error fitted to generate a calibration coefficient error covariance matrix, and a standardized digital feature library is constructed after eliminating the wild value coefficients.

[0074] The linkage mapping model is numerically modeled with mechanical parameters (stress, strain, loading rate) as input dimensions and dielectric instrument configuration (excitation voltage, test frequency band, sampling point number) as output dimensions, a multi-input multi-output (MIMO) nonlinear digital mapping model is constructed, tensor decomposition is used to reduce dimension redundancy, a mechanical-dielectric coupling transfer function matrix is solved, and initial numerical calibration of the model is completed.

[0075] Adaptive iterative optimization digital operation sets fitness function as dielectric signal signal-to-noise ratio SNR+mechanical response matching degree RMSE, through adaptive particle swarm algorithm iteration, each round generates parameter candidate set, substitutes into mapping model to do forward numerical calculation, calculates fitness value, updates particle velocity and position, convergence judgment. When the fitness change rate is less than 1e-6, terminate iteration, output quantized instrument configuration digital parameter set (including voltage quantization step, frequency band discrete point column, sampling point number integer value).

[0076] S32: The instrument configuration parameter set is recorded into the impedance analyzer and open-circuit short-circuit load calibration is performed, PID temperature control and predictive compensation algorithm is used to stabilize to the target detection temperature, and the constant temperature environment state identifier is output.

[0077] The configuration parameter set is encoded into instrument bus digital instruction frame, and open-circuit parasitic impedance, short-circuit reference impedance and standard load impedance frequency domain data are sequentially collected. Through vector network analysis S parameter solution, the complex impedance compensation factor of the clamp cable is calculated, and the frequency domain full segment calibration compensation digital matrix is generated, and the original dielectric test channel is subjected to complex frequency domain digital compensation to eliminate system parasitic error.

[0078] PID discrete digital temperature control operation samples the analog signal of the temperature sensor by ADC, quantizes it into a digital temperature value, and calculates the discrete deviation e(k) from the target temperature. The digital control quantity is calculated according to the digital PID formula. The digital PID formula is represented as: In the formula, is the digital control quantity at the kth sampling time, k is the sampling time sequence number, and represents the kth sampling (k=0, 1, 2,...), is the proportional coefficient, which is used to adjust the response speed of the deviation. The larger the proportional coefficient, the faster the response, but too large may lead to system oscillation. is the deviation value at the kth sampling time, is the integral coefficient, which is used to eliminate the steady-state error of the system. T is the sampling period, is the derivative coefficient, which is used to suppress the dynamic overshoot of the system, predict the future trend through the change rate of the deviation, and apply damping action in advance, is the deviation value at the k-1th sampling time, which is used to calculate the change rate of the deviation. is the change rate of the deviation, which represents the change amount of the deviation per unit time. is the cumulative sum of the deviation from the 0th to the kth sampling.

[0079] The control quantity is quantized into PWM duty cycle digital code and output to the temperature control actuator to form a closed-loop discrete regulation sequence.

[0080] The predictive compensation and constant temperature state digital coding use an exponential smoothing time series prediction model to extrapolate the temperature deviation at the next moment, and make a feedforward compensation correction to the lag error of the PID output. The variance and peak value of the temperature digital sequence are calculated in real time. When the fluctuation is less than or equal to the set digital threshold, a constant temperature state identifier is generated, which includes the temperature mean value, variance check code, and stable duration binary digital coding, serving as a subsequent trigger enable signal.

[0081] S33: Analyzing the temperature stability check code in the constant temperature environment state identifier, triggering a double-channel trigger signal with time sequence pre-synchronization, driving the servo system to realize adaptive loading according to the constraint law of the mechanical reference data set, synchronously activating the force value collection noise reduction module, and outputting the servo real-time force value time series stream.

[0082] The check code of the constant temperature state identifier is subjected to CRC digital check, and the trigger module is unlocked after the check is passed. Taking the system homologous digital clock as the reference, clock frequency division and phase synchronization are performed to generate a double-channel digital trigger pulse sequence with the same frequency and phase, one of which drives the servo controller and the other triggers the dielectric collection card, ensuring that the two-way trigger time series deviation is less than or equal to one clock period.

[0083] The servo adaptive loading digital solution analyzes the loading law of the mechanical reference data set and converts it into a discrete force displacement time series digital table. The servo controller performs closed-loop digital control: real-time collection of feedback force values, calculation of deviation from the target time series table, output of driving digital quantity through PID / fuzzy control algorithm → conversion to motor driving pulse. The loading rate digital parameters are dynamically corrected during the loading process to adapt to the changes in material mechanics response.

[0084] Force value signal digital noise reduction and time series stream packaging: After the force value collection signal is quantized by ADC, the IIR digital low-pass filter cutoff frequency is matched with the loading bandwidth, the least squares detrend item is used to eliminate zero drift, and the 3σ criterion is used for abnormal value detection and interpolation replacement. A high-precision digital timestamp is added to each valid force value data, and it is packaged into a continuous servo real-time force value digital time series stream.

[0085] S34: Using the homologous anchoring algorithm to accurately align the servo real-time force value time series stream with the dielectric parameter time series stream according to the unified timestamp, automatically identifying and removing time series mismatch and signal distortion data through correlation analysis, and generating a homologous time series detection data set.

[0086] Extracting the homologous clock anchor points of the force value time series stream and the dielectric parameter time series stream, performing cubic spline interpolation resampling on the two-way non-equidistant data, and unifying the sampling frequency and timestamp axis. The remaining time series offset is corrected by peak positioning of the cross-correlation function, the two-way signal time domain is accurately aligned, and the aligned two-way time series matrix is output.

[0087] The Pearson correlation coefficient r is calculated window-by-window for the aligned dual-channel timing matrix, with r < 0.9 set as the mismatch threshold. Simultaneously, signal amplitude distortion and abrupt changes in the matrix are detected, generating an outlier binary mask matrix. Row / column removal operations are performed on the dual-channel timing matrix according to the mask, retaining valid data segments. Short missing match points are repaired using linear interpolation, and the cleaned and normalized dual-channel timing matrix is ​​output.

[0088] The cleaned and standardized dual-channel time series matrix is ​​normalized and quantized, and digital metadata (configuration parameter ID, temperature check code, measurement point coordinate encoding, and time stamp precision) is added to the matrix. The matrix data structure of the fused metadata is organized in CSV format to generate a homogeneous time series detection dataset with digital checksums, and the final standardized homogeneous time series detection dataset (CSV format) is output.

[0089] S4: Based on the same source time-series detection data, the dielectric parameters are continuously collected until they tend to stabilize. The stress attenuation changes and the evolution information of dielectric constant, loss factor and impedance modulus within the collection period are used to form the mechanical-dielectric original time-series dataset.

[0090] S41: Based on the same source time-series detection data, the adaptive sliding window iterative algorithm is used to collect force value and time-series dielectric data, calculate the trend entropy and fluctuation threshold of dielectric constant, loss factor, and impedance modulus in real time, dynamically determine the steady state, and output continuously acquired time-series segments.

[0091] Using the unified timestamps, force value time series, and dielectric parameter time series of the same-source time series detection dataset as inputs, the basic width W0 and iteration step size S0 of the sliding window are first initialized, and an adaptive window scale adjustment mechanism is constructed: the first-order difference amplitude of the dielectric parameter in the time domain is calculated in real time; when the difference exceeds the threshold, the window shrinks to 0.5W0 to improve transient capture accuracy; when the difference is below the threshold, the window expands to 1.5W0 to enhance the statistical robustness of the stationary segment. Force value digital sequences and dielectric constant, loss factor, and impedance modulus digital sequences are collected iteratively window by window. Information trend entropy is calculated for the three types of dielectric parameters within a single window: the parameter sequences are first normalized to a probability distribution, and then... Solve for the entropy value, where H is the information trend entropy. This represents the probability value corresponding to the i-th state in the time series after normalization. Let be the probability value for the i-th state. The natural logarithm is used to quantify the information content of the probability distribution; the smaller the entropy value, the more regular the parameter trend. Simultaneously, based on the dynamic quantiles of the data within the window, the upper and lower limits of fluctuation are iteratively updated, and the parameter fluctuation residual is calculated after removing instantaneous impulse interference. A dual convergence criterion is set: the entropy of the dielectric parameter trend is less than the threshold H for three consecutive iteration windows. thand the fluctuation residuals of the three types of parameters fall into the dynamic threshold interval, it is determined that the dielectric parameters enter a stationary state, the data stream is truncated, and a continuous acquisition time sequence segment carrying the window number, the trend entropy sequence, the fluctuation threshold sequence, and the time stamp is output.

[0092] S42: According to the continuous acquisition time sequence segment and the trend fitting parameter, a periodic adaptive segmentation algorithm is used to divide the acquisition period, and through a time sequence alignment verification model, the stress decay sequence and the dielectric parameter sequence in each period are accurately mapped, the decay rate and the dielectric evolution gradient feature are extracted, and a mechanical-dielectric correlation time sequence subset is generated.

[0093] With the continuous acquisition time sequence segment and the embedded trend entropy and fluctuation fitting parameter as input, a periodic adaptive segmentation algorithm coupled with extreme points is used: first, the inflection points of the stress sequence in the time sequence segment are solved by second-order difference, and combined with the dielectric evolution gradient mutation points, the long time sequence is divided into independent acquisition periods such as the initial loading segment, the steady-state decay segment, and the stable maintenance segment, and the segmentation boundary is calibrated by the stress inflection point and the dielectric mutation point. A time sequence alignment verification model is constructed, and the time domain synchronicity of the stress decay sequence and the three types of dielectric parameter sequences is verified by the cross-correlation function, and after correcting the period boundary deviation, point-by-point accurate mapping is realized. The stress sequence in each period is linearly fitted to solve the stress decay rate, and the dielectric constant, loss factor, and impedance modulus sequence is slidingly differentiated to solve the dielectric evolution gradient, and the period number, decay rate, dielectric gradient, and original time sequence data are bound one by one to generate a multi-dimensional feature-labeled mechanical-dielectric correlation time sequence subset.

[0094] S43: According to the mechanical-dielectric correlation time sequence subset, an anomaly detection algorithm is used to perform adaptive weighted interpolation repair on missing points, integrate multi-dimensional feature data in the whole period, and complete time sequence consistency verification, and output the mechanical-dielectric original time sequence data set.

[0095] With the mechanical-dielectric correlation time sequence subset as input, a multi-dimensional fusion anomaly detection algorithm is used: synchronous detection of time sequence missing points, stress-dielectric correlation mismatch points, and parameter amplitude jump points, and by setting the correlation coefficient threshold and the gradient distortion threshold, all abnormal data points are marked. Adaptive weighted interpolation repair is performed on the missing points, and the weight calculation formula is: In the formula, is the stress-dielectric correlation coefficient of adjacent points, is the time sequence distance. , To normalize the weight coefficient, the missing value fitting and filling are completed by weighted sum. After repair, three-layer time sequence consistency verification is carried out: verifying the strict incremental nature of the time stamp, the continuity of the characteristic value of each cycle, the coupling of stress and dielectric parameter evolution trend, and re-iterating segmentation and repair for the cycle section that does not meet the verification. After passing the verification, the original time sequence data, derived feature data, cycle label, verification result and metadata information are integrated to output the structured and traceable mechanical-dielectric original time sequence dataset.

[0096] S5: According to the mechanical-dielectric original time sequence dataset, the stress relaxation data is extracted to calculate the relaxation modulus, which is cross-fitted with the dielectric loss factor characteristic peak value, the mechanical-dielectric correlation model is constructed and substituted into the preset creep failure threshold, and the long-term creep failure life of the sealing element is deduced through short-time test data.

[0097] S51: From the mechanical-dielectric original time sequence dataset, the force value and time sequence of the stress relaxation stage are extracted, and the variable order exponential decay model is used to fit the relaxation modulus evolution, and the dynamic relaxation modulus sequence is output.

[0098] From the mechanical-dielectric original time sequence dataset, the complete data segment of the stress relaxation stage is screened out through the stress first-order difference threshold. The force value, time and strain digital sequence of this stage are extracted, the strain digital sequence is normalized according to the gauge length size of the sealing element, the influence of gauge length difference is eliminated, the relaxation calculation basis array is constructed, and the data sampling frequency and effective data point number are recorded.

[0099] The normalized force value and strain digital array are used as input, and the relaxation modulus calculation formula is expressed as , wherein is the relaxation modulus, is the real-time force value in the stress relaxation stage, is the initial cross-sectional area of the sealing element, is the normalized real-time strain, and the initial relaxation modulus sequence is calculated. The 1 to 4 order exponential decay function is used for step-by-step iterative fitting, and the exponential decay function formula is expressed as: , wherein y is the target variable obtained by fitting, is the amplitude coefficient of the i-th order exponential component, is the relaxation time of the i-th order exponential component, and t is the time variable.

[0100] After each order fitting, the Akaike information criterion and the root mean square error are calculated, and the optimal fitting order is selected as the double screening standard that AIC is minimum and RMSE is less than 50 MPa. The model parameters under the optimal order are solved, the material instantaneous elastic deformation interference is eliminated by iterative correction, and the continuous fitting curve that fits the measured data is obtained.

[0101] The precise value of the relaxation modulus E(t) is calculated step by step based on the optimal order exponential decay model, and the relaxation rate is calculated by a first-order difference algorithm to quantify the decay trend of the modulus over time. The relaxation modulus sequence obtained by calculation is subjected to 3σ criterion outlier detection and linear interpolation repair to generate a dynamic relaxation modulus sequence containing timestamps, relaxation modulus values, fitting residuals, and relaxation rates, and is saved in a structured array format.

[0102] S52: According to the dynamic relaxation modulus sequence, the time-frequency domain feature peak value of the dielectric loss factor is extracted by using multi-scale wavelet transform, and a nonlinear mapping of the relaxation modulus and the dielectric loss peak value is constructed by using an attention mechanism to output a mechanical-dielectric correlation model.

[0103] The dielectric loss factor digital time sequence corresponding to the time stamp of the dynamic relaxation modulus sequence is extracted synchronously to ensure that the time axes of the two are completely aligned. Daubechies wavelet is selected to perform 4-layer multi-scale wavelet decomposition on the dielectric loss factor time sequence to obtain high-frequency detail coefficient matrices and low-frequency approximation coefficient matrices at each scale. The soft threshold function is used to denoise each scale coefficient matrix to generate a three-dimensional digital matrix of wavelet coefficients after denoising. The local extreme value detection algorithm is used to locate the local maximum value points of each scale coefficient matrix after denoising, and the amplitude, timestamp, corresponding scale, and frequency interval of each extreme value point are extracted as time-frequency domain feature peaks. The time-frequency domain feature peaks are time-sequentially aligned with the dynamic relaxation modulus sequence, the contribution weight of each feature peak to the relaxation modulus is calculated by using an attention mechanism, a feature-modulus correlation pair with weight is generated, and an initial nonlinear mapping relationship is constructed.

[0104] The feature-modulus correlation pair with weight is input into a deep neural network, the mean square error between the predicted value and the measured dynamic relaxation modulus value is used as the loss function, the Adam optimizer is used to iteratively optimize the network parameters, the iteration is stopped when the loss function converges to below 1e-6, and a mechanical-dielectric correlation model with dynamic weight distribution capability is output, the model includes a feature weight matrix, a nonlinear mapping function, and an error correction coefficient.

[0105] S53: The mechanical-dielectric correlation model is substituted into the preset creep failure threshold, combined with the transfer learning framework to transfer long-time life data of similar materials, realizes the cross-scale extrapolation of short-time test data, and outputs the long-term creep failure life prediction result of the sealing element.

[0106] Load the long-term creep failure data set of the same type of sealing material, and perform domain distribution difference analysis on the current short-term test data set. Calculate the feature distribution distance of the two types of data sets. Through domain adversarial network (DAN) training, minimize the feature distribution difference between the source domain and the target domain, and realize domain adaptation. Migrate the weight of the long-term life prediction model trained in the source domain to the mechanical-dielectric correlation model. By fine-tuning the model's fully connected layer parameters, the migration ability of the long-term failure features in the source domain is preserved, and a migration-enhanced mechanical-dielectric correlation model adapted to the current seal is obtained, improving the model's extrapolation reliability.

[0107] Substitute the preset seal creep failure modulus threshold into the migration-enhanced mechanical-dielectric correlation model, and perform reverse solving to obtain the critical peak value of the dielectric loss factor under the corresponding failure state. Label the frequency scale and characteristic weight corresponding to the critical peak value. Use the power-law time scale expansion function to complete the cross-scale extrapolation calculation from short-term test data to long-term creep failure life, and simultaneously calculate the error coefficient in the extrapolation process to correct the extrapolation result.

[0108] Use K-S test to verify the distribution rationality of the cross-scale extrapolation result, calculate the goodness-of-fit R 2 , confidence interval, and eliminate abnormal extrapolation values outside the confidence interval. Combine the source domain migration weight and the short-term data fitting error of the target domain to label the failure risk level of the prediction result. Generate a structured long-term creep failure life prediction result for the seal, including the time when the seal strength decreases to the failure threshold, the confidence interval, the goodness-of-fit, the failure risk level, the critical dielectric loss peak, and the error coefficient, to ensure the accuracy and traceability of the prediction result.

[0109] The essence of the sterile barrier seal strength is the seal interface bonding force and the material's resistance to creep deformation. The stress relaxation and modulus decay captured by your process are the direct mechanical roots of the seal strength degradation over time: The continuous decline in relaxation modulus leads to the loss of seal interface bonding stiffness, which in turn leads to the decay of seal compression force, resulting in a simultaneous decrease in seal strength.

[0110] The dielectric loss factor peak and the time-frequency domain feature mutation lead to seal interface debonding and gap initiation, which are the precursors of seal strength failure.

[0111] S6: According to the long-term creep failure life result and the seal interface bonding state reflected by the dielectric parameters, determine the creep failure risk level, and retain the samples after the whole-process non-destructive testing to link the subsequent sterile barrier integrity verification, forming a closed-loop of whole-process data.

[0112] S61: Based on the interface bonding defect distribution inversed from the long-term creep failure life confidence interval and the dielectric time-frequency domain characteristics, a multi-dimensional strength mapping feature tensor is constructed, a creep constitutive correction factor is embedded for tensor normalization processing, and a normalized strength mapping feature tensor is obtained. Extract the upper and lower confidence limits, mean life of long-term creep failure life, and the interface defect area, distribution uniformity, and debonding probability inversed from the dielectric time-frequency domain characteristics, and assemble a four-dimensional basic feature array to complete the feature tensor initialization. Introduce the material temperature-creep coupling constitutive correction factor to correct the feature deviation under different working conditions, multiply the correction factor and the basic feature tensor dimension by dimension to generate the original strength mapping feature tensor with working condition adaptation. The maximum and minimum normalization algorithm is used to scale the corrected tensor to the [0, 1] interval to eliminate the dimension difference, and the normalized strength mapping feature tensor with uniform dimension and regular distribution is output.

[0113] S62: Input the normalized strength mapping feature tensor into the mechanics-dielectric correlation model, solve the sterile barrier sealing strength equivalent value through adaptive weight reasoning, and generate a strength quantification atlas with error tracing. The normalized strength mapping feature tensor is input into the pre-trained mechanics-dielectric correlation model, and the forward propagation is completed through multi-layer nonlinear mapping to output the initial sterile barrier sealing strength equivalent prediction value. According to the contribution of each feature dimension to the strength, the adaptive reasoning weight is dynamically allocated to correct the model prediction deviation and obtain the high-precision sterile barrier sealing strength equivalent value. Using the correlation strength equivalent value, the contribution weight of each dimension feature, the reasoning error, and the tracing node information, a strength quantification atlas with error tracing is generated, including a numerical cloud chart, an error curve, and a tracing path.

[0114] S63: According to the strength quantification atlas, the original data, model parameters and verification results of the whole process are connected to establish a block chain storage link for data verification, and a closed data chain of the whole process is formed. Taking the strength quantification atlas as the core anchor point, according to the sample information, the reference data set, the homologous time series data and the correlation model parameters, a whole-process integrated data set is formed. The integrated data set is encrypted by node hashing, and chain storage blocks are generated according to the detection time sequence to ensure that each piece of data cannot be tampered with and can be traced back, and the block chain storage link is built. The storage data is checked for consistency and integrity, abnormal nodes are corrected, and a compliant closed data chain of the whole process is output to realize a closed loop of detection-modeling-reasoning-verification-storage.

[0115] As shown in Fig. 3 The present application also provides a sterile barrier sealing strength detection system based on servo tension, which comprises: A sample preparation module is used to cut the sterile sealing sample, adhere a flexible interdigital electrode to the sealing interface and connect an impedance analyzer to form an initial detection sample.

[0116] A reference modeling module is configured to apply a constant displacement constraint to the initial test sample, activate a force value collection state, fuse the sample geometric features and the circuit reference parameters to construct a constant mechanical test reference dataset.

[0117] A synchronous collection module is configured to set parameters on the impedance analyzer according to the constant mechanical test reference dataset, start the temperature control module to stabilize the temperature, trigger synchronous collection, match the servo real-time force value with the dielectric parameters, and obtain the homochronous time sequence detection data.

[0118] A dataset generation module is configured to continuously collect the stress decay change and the dielectric constant, loss factor and impedance modulus evolution information in the collection period according to the homochronous time sequence detection data, and form a mechanical-dielectric original time sequence dataset.

[0119] A life deduction module is configured to extract stress relaxation data from the mechanical-dielectric original time sequence dataset to calculate the relaxation modulus, fit the relaxation modulus with the dielectric loss factor characteristic peak value, construct a mechanical-dielectric correlation model and substitute the preset creep failure threshold value, and deduce the long-term creep failure life of the seal through short-time test data.

[0120] A strength closed loop module is configured to map and calculate the measured equivalent value of the sterile barrier seal strength according to the long-term creep failure life and the interface bonding state inverted from the dielectric parameters through the mechanical-dielectric correlation model, and form a full-process data closed loop.

[0121] In summary, the present embodiment provides a sterile barrier seal strength detection method and system based on servo tension, which deeply fuses the servo tension displacement closed loop constraint technology and the flexible interdigital electrode dielectric detection technology, synchronously collects the macro mechanical signal and the micro dielectric parameter of the seal sample, combines the homochronous clock anchoring, time sequence accurate alignment and multi-dimensional data calibration, constructs a constant mechanical test reference and homochronous time sequence detection system, and effectively eliminates the system error caused by assembly deviation, circuit interference and environmental fluctuation. Compared with the traditional single mechanical or dielectric detection mode, the fusion mode can simultaneously capture the stress relaxation, modulus decay and seal interface dielectric characteristic evolution, accurately invert the interface bonding defect distribution and bonding force degradation law, provide a comprehensive and reliable multi-dimensional data source for sterile barrier seal strength equivalent calculation, significantly improve the resolution, accuracy and data traceability of the seal strength detection, and solve the technical pain point that the traditional detection cannot accurately capture the subtle interface degradation.

[0122] Those skilled in the art can clearly understand the implementation of the various embodiments by means of software and necessary general hardware platforms through the description of the above embodiments, and of course, the embodiments can also be implemented by hardware. Based on such understanding, the above technical solutions, essentially or in other words, the part of the prior art that makes a contribution, can be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, and the like, and includes a number of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods of the various embodiments or some parts of the embodiments.

[0123] Finally, it should be noted that: the above examples are only used to illustrate the technical solutions of the present application, and not to limit it. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for some technical features. And these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the various embodiments of the present application.

Claims

1. A method for detecting the sealing strength of a sterile barrier based on servo-tension force, characterized in that, include: S1: Cut the sterile sealed sample, attach the flexible interdigital electrode to its sealing interface and connect it to the impedance analyzer to form the initial test sample; S2: Apply a constant displacement constraint to the initial test sample, activate the force value acquisition state, and construct a constant mechanical test benchmark dataset by fusing the sample's geometric features and circuit reference parameters. S3: Based on the constant mechanical test benchmark dataset, set parameters in the impedance analyzer, start the temperature control module to stabilize the temperature, trigger synchronous acquisition, match the real-time servo force value with the dielectric parameter, and obtain the same source time sequence detection data; S4: Based on the same source time series detection data, the dielectric parameters are continuously collected until they tend to stabilize. The stress attenuation changes and the evolution information of dielectric constant, loss factor and impedance modulus within the collection period are used to form the mechanical-dielectric original time series dataset. S5: Extract stress relaxation data from the mechanical-dielectric original time series dataset to calculate the relaxation modulus, fit the relaxation modulus with the characteristic peak value of the dielectric loss factor, construct a mechanical-dielectric correlation model and substitute it with the preset creep failure threshold, and extrapolate the long-term creep failure life of the seal through short-time test data. S6: Based on the interface bonding state obtained from the long-term creep failure lifetime and dielectric parameter inversion, the measured equivalent value of the sterile barrier sealing strength is calculated through the mechanical-dielectric correlation model mapping, forming a closed loop of data for the entire process.

2. The method for detecting the sealing strength of a sterile barrier based on servo tension according to claim 1, characterized in that: In step S2, the specific steps for constructing the constant mechanics test benchmark dataset are as follows: S21: Precisely fit the assembly surface of the initial test specimen with the rigid constraint fixture, calibrate the fixture stroke through the displacement sensor, complete the constant displacement constraint locking of the specimen with full degrees of freedom, and output the specimen positioning reference data; S22: Import the sample positioning reference data into the force acquisition device, activate the piezoelectric force sensor and signal conditioning circuit, acquire the initial force value timing signal under the constraint state according to the preset sampling frequency, and output the original force value; S23: Use three-dimensional visual scanning to obtain the inner and outer contours, wall thickness, and sealing surface roughness of the sample. Based on the original force value acquisition data stream, complete the spatial matching of feature points and force value sampling points, and output the geometric-force value correlation feature matrix. S24: Based on the circuit reference parameters, the geometry-force correlation feature matrix is ​​corrected for drift and outliers are removed. The mechanical response law under the constraint boundary is fitted by finite element simulation to generate a constant mechanical test reference dataset.

3. The method for detecting the sealing strength of a sterile barrier based on servo-tension according to claim 2, characterized in that: In step S24, the specific steps for generating the constant mechanics test benchmark dataset are as follows: Based on the geometric-force correlation feature matrix, the circuit reference parameters corresponding to the initial test sample are retrieved, the drift data in the matrix is ​​accurately corrected, and the abnormal values ​​generated during the acquisition process are removed to obtain the corrected geometric-force correlation feature matrix. Based on the modified geometry-force value correlation feature matrix, a finite element simulation model adapted to the constant displacement constraint scenario is built. The constraint boundary conditions are input, and the mechanical response law of the specimen under the constraint state is fitted through simulation iteration to form a mechanical response simulation dataset. The modified geometry-force correlation feature matrix and mechanical response simulation data are subjected to data normalization, dimensional unification and accuracy calibration to generate a constant mechanics test benchmark dataset.

4. The method for detecting the sealing strength of a sterile barrier based on servo-tension according to claim 1, characterized in that: In step S3, the specific steps for obtaining the same-source time series detection data are as follows: S31: Based on the sampling frequency, measurement point coordinates and calibration coefficients of the constant mechanical test benchmark dataset, construct a linkage mapping model of mechanical parameters-dielectric instrument configuration, and dynamically iterate and optimize the excitation voltage, test frequency band and number of sampling points through an adaptive algorithm to output the instrument configuration parameter set; S32: Input the instrument configuration parameter set into the impedance analyzer and perform open-circuit and short-circuit load calibration. Use PID temperature control and predictive compensation algorithm to stabilize to the target detection temperature and output constant temperature environment status indicator. S33: Parse the temperature stability check code in the constant temperature environment status mark, trigger the dual trigger signal with timing pre-synchronization, drive the servo system to achieve adaptive loading according to the constraint law of the mechanical benchmark dataset, synchronously activate the force value acquisition and noise reduction module, and output the servo real-time force value timing stream; S34: The same source anchoring algorithm is used to accurately align the servo real-time force value timing stream and the dielectric parameter timing stream with a unified timestamp. Combined with correlation analysis, timing mismatch and signal distortion data are automatically identified and removed to generate a same source timing detection dataset.

5. The method for detecting the sealing strength of a sterile barrier based on servo-tension according to claim 4, characterized in that: In step S34, the specific steps for precise timestamp alignment are as follows: Extract the common clock anchor points of the force value timing stream and dielectric parameter timing stream, perform cubic spline interpolation resampling on the two non-equal interval data, and unify the sampling frequency and timestamp axis; correct the remaining timing offset by the peak location of the cross-correlation function, complete the precise digital alignment of the two signals in the time domain, and generate the aligned dual-channel timing matrix; Based on the aligned dual-channel timing matrix, the Pearson correlation coefficient r is calculated window by window, a mismatch threshold is set, signal amplitude distortion and jump points are detected, an anomaly binary mask matrix is ​​generated, the timing matrix is ​​removed according to the mask, and the cleaned dual-channel timing matrix is ​​output. The cleaned dual-channel time series matrix is ​​normalized and quantized to add digital metadata to the matrix. The matrix data structure of the fused metadata is organized in CSV format to generate a homogeneous time series detection dataset with digital checksum.

6. The method for detecting the sealing strength of a sterile barrier based on servo-tension according to claim 1, characterized in that: In step S4, the specific steps for forming the mechanical-dielectric raw time series dataset are as follows: S41: Based on the same source time-series detection data, use an adaptive sliding window iterative algorithm to collect force values ​​and time-series dielectric data, calculate the trend entropy and fluctuation threshold of dielectric constant, loss factor, and impedance modulus in real time, dynamically determine the stable state, and output continuously collected time-series segments. S42: Based on the continuously acquired time series segments and trend fitting parameters, the acquisition period is divided using a periodic adaptive segmentation algorithm. Through the time series alignment verification model, the stress decay sequence and dielectric parameter sequence in each period are accurately mapped, and the decay rate and dielectric evolution gradient features are extracted to generate a mechanical-dielectric correlated time series subset. S43: Based on the aforementioned mechanical-dielectric correlated time series subset, an anomaly detection algorithm is used to perform adaptive weighted interpolation repair on missing points, integrate full-cycle multi-dimensional feature data and complete time series consistency verification, and output the original mechanical-dielectric time series dataset.

7. The method for detecting the sealing strength of a sterile barrier based on servo-tension according to claim 1, characterized in that: In step S5, the specific steps for estimating the long-term creep failure life of the seal are as follows: S51: Extract the force values ​​and time series of the stress relaxation stage from the mechanical-dielectric raw time series dataset, fit the evolution of the relaxation modulus using a variable-order exponential decay model, and output the dynamic relaxation modulus sequence. S52: Based on the dynamic relaxation modulus sequence, multi-scale wavelet transform is used to extract the time-frequency domain characteristic peak of the dielectric loss factor. The nonlinear mapping between the relaxation modulus and the dielectric loss peak is constructed by weighting through an attention mechanism, and the mechanical-dielectric correlation model is output. S53: Substitute the mechanical-dielectric correlation model into the preset creep failure threshold, combine the transfer learning framework to transfer long-term life data of similar materials, realize cross-scale extrapolation of short-term test data, and output the prediction result of long-term creep failure life of the seal.

8. The method for detecting the sealing strength of a sterile barrier based on servo tension according to claim 7, characterized in that: In step S52, the specific steps for outputting the mechanical-dielectric correlation model are as follows: The time series of dielectric loss factor is extracted from the dynamic relaxation modulus sequence. Multi-scale wavelet transform is used to decompose the dielectric loss factor in the time and frequency domain to obtain the wavelet coefficient matrix at different scales. The local extrema at each scale are located as the characteristic peaks in the time and frequency domain. Based on the time-frequency domain feature peaks and the dynamic relaxation modulus sequence, time-series alignment is performed, and the contribution weight of each feature peak to the relaxation modulus is calculated through an attention mechanism to generate weighted feature-modulus association pairs and construct an initial nonlinear mapping relationship. The weighted feature-modulus correlation pairs are input into a deep neural network, and the network parameters are iteratively optimized using the fitting error of the correlation pairs as the loss function. After convergence, a mechanical-dielectric correlation model with dynamic weight allocation capability is output.

9. The method for detecting the sealing strength of a sterile barrier based on servo tensile force according to claim 1, characterized in that: In step S6, the specific steps to form a closed loop of data throughout the entire process are as follows: S61: Based on the interface-combined defect distribution derived from the long-term creep failure lifetime confidence interval and dielectric time-frequency domain characteristics, a multi-dimensional intensity mapping feature tensor is constructed, and a creep constitutive correction factor is embedded for tensor normalization to obtain the normalized intensity mapping feature tensor. S62: Input the normalized intensity mapping feature tensor into the mechanical-dielectric correlation model, solve the equivalent value of the sterile barrier sealing strength through adaptive weight inference, and generate an intensity quantization spectrum with error traceability; S63: Based on the intensity quantization spectrum, connect the original data, model parameters and verification results of the entire process, establish a blockchain-style evidence storage link to complete data verification and form a closed data chain for the entire process.

10. A servo-tension-based sterile barrier seal strength testing system, which employs the servo-tension-based sterile barrier seal strength testing method as described in any one of claims 1 to 9, characterized in that, The detection system includes: The sample preparation module is used to cut sterile sealed samples, attach flexible interdigitated electrodes to their sealing interface and connect them to an impedance analyzer to form an initial test sample. The benchmark construction module is used to apply a constant displacement constraint to the initial test sample, activate the force value acquisition state, and integrate the sample geometric features and circuit benchmark parameters to construct a constant mechanical test benchmark dataset. The synchronous acquisition module is used to set parameters in the impedance analyzer according to the constant mechanical test benchmark dataset, start the temperature control module to stabilize the temperature, trigger synchronous acquisition, match the real-time servo force value with the dielectric parameter, and obtain the same source time sequence detection data. The dataset generation module is used to continuously collect the same source time-series detection data until the dielectric parameters tend to stabilize, and to generate the stress decay changes and the evolution information of dielectric constant, loss factor and impedance modulus within the collection period to form a mechanical-dielectric original time-series dataset. The life prediction module is used to extract stress relaxation data from the mechanical-dielectric original time series dataset, calculate the relaxation modulus, fit the relaxation modulus with the characteristic peak value of the dielectric loss factor, construct a mechanical-dielectric correlation model and substitute it with a preset creep failure threshold, and predict the long-term creep failure life of the seal through short-term test data. The strength closed-loop module is used to calculate the measured equivalent value of the sterile barrier sealing strength based on the interface bonding state derived from the long-term creep failure life and dielectric parameters, through a mechanical-dielectric correlation model mapping, thus forming a closed-loop data system for the entire process.

Images