A connector stress-strain real-time monitoring method and system

Abstract

The application discloses a kind of connector stress strain real-time monitoring method and system, it is related to structural health monitoring technical field, including, based on real-time stress strain data and preprocessed external environment data, by wavelet multiscale decomposition into high-frequency component and low-frequency component, and dynamically weighted fusion is corrected stress strain data;Based on the corrected stress strain data, the health index of connector is continuously monitored, and the risk trend of connector is analyzed, when monitoring health index sequence exceeds dynamic safety threshold, real-time monitoring feedback is generated;According to real-time monitoring feedback and real-time stress strain data, construct health state knowledge graph, and predict the fault type and occurrence probability of connector, generate fault prediction report;Based on fault prediction report, combined with historical fault data, obtain the individualized maintenance plan of connector.The application realizes the accurate extraction of multiscale signal feature and noise suppression, effectively improves the reliability and anti-interference ability of monitoring data.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of structural health monitoring, in particular to a connector stress-strain real-time monitoring method and system. BACKGROUND

[0002] In the field of power connector reliability monitoring, real-time detection of stress-strain parameters is a key technical means for evaluating the health status of mechanical structures. Traditional monitoring methods mainly use resistance strain gauge sensors to directly measure structural deformation, and convert mechanical strain into electrical signals through a Wheatstone bridge for collection and analysis. This method is based on the linear assumption of Hooke's law, and calculates the stress distribution through the calibrated strain-voltage relationship. In industrial field applications, a standardized detection process has been formed. At the same time, optical fiber grating sensing technology has been introduced into this field in recent years, which uses the linear relationship between wavelength shift and strain value to achieve distributed measurement, providing a new technical path for structural health monitoring.

[0003] When dealing with complex working conditions, the traditional method has difficulty in effectively distinguishing between real stress changes and measurement drift caused by environmental temperature and humidity fluctuations with a single sensor system, resulting in a decrease in monitoring accuracy under dynamic load conditions. In addition, the alarm mechanism with fixed thresholds lacks predictive judgment of equipment degradation trends, making it difficult to identify gradual failure characteristics in a timely manner. In particular, in industrial scenes with significant vibration interference, the existing technology has limited ability to capture high-frequency dynamic responses, and the spatial and temporal registration accuracy between different physical quantity measurements needs to be improved, which to some extent affects the integrity of the state evaluation. SUMMARY

[0004] In view of the above existing problems, the present application is proposed.

[0005] Therefore, the present application provides a connector stress-strain real-time monitoring method to solve the problems of insufficient fusion of multi-source heterogeneous data and weak dynamic adaptability in monitoring technology.

[0006] To solve the above technical problems, the present application provides the following technical solutions:

[0007] In a first aspect, the present application provides a connector stress-strain real-time monitoring method, which comprises,

[0008] Collecting and preprocessing multi-physical quantity data and external environment data;

[0009] Extracting current and voltage signal sequences from the preprocessed multi-physical quantity data, and calculating real-time stress-strain data through an electrical model;

[0010] Based on the real-time stress-strain data and the preprocessed external environment data, decomposing into high-frequency components and low-frequency components through wavelet multi-scale decomposition, and dynamically weighting and fusing into corrected stress-strain data;

[0011] Based on the corrected stress-strain data, the health index of the connector is continuously monitored, and the risk trend of the connector is analyzed, and when the health index sequence exceeds the dynamic safety threshold, real-time monitoring feedback is generated;

[0012] According to the real-time monitoring feedback and the real-time stress-strain data, a health state knowledge graph is constructed, and the failure type and occurrence probability of the connector are predicted, and a failure prediction report is generated;

[0013] Based on the failure prediction report, combined with historical failure data, a personalized maintenance plan for the connector is obtained.

[0014] As a preferred scheme of the connector stress-strain real-time monitoring method, the multi-physical quantity data includes strain signals, optical fiber signals, current signals and voltage signals;

[0015] The external environment data includes temperature signals, humidity signals and vibration signals;

[0016] The preprocessing includes denoising processing, standardization processing, time synchronization and data alignment.

[0017] As a preferred scheme of the connector stress-strain real-time monitoring method, the current and voltage signal sequences in the preprocessed multi-physical quantity data are extracted, and the real-time stress-strain data is calculated through an electrical model, and the steps are as follows,

[0018] Separate the current signal sequence and the voltage signal sequence from the preprocessed multi-physical quantity data;

[0019] Based on Ohm's law and Hooke's law, a mathematical relationship between current, voltage and stress-strain is established, and an electrical model is generated;

[0020] The current signal sequence and the voltage signal sequence are input into the electrical model, and the initial stress-strain data is output;

[0021] Compare the preprocessed optical fiber signal and the initial stress-strain data to obtain an offset value;

[0022] The initial stress-strain data is corrected through offset compensation to generate real-time stress-strain data.

[0023] As a preferred scheme of the connector stress-strain real-time monitoring method, the real-time stress-strain data and the preprocessed external environment data are decomposed into high-frequency components and low-frequency components through wavelet multi-scale decomposition, and are dynamically weighted and fused into corrected stress-strain data, and the steps are as follows,

[0024] The real-time stress-strain data and the preprocessed external environment data are decomposed into high-frequency components and low-frequency components through wavelet multi-scale decomposition, and are dynamically weighted and fused into corrected stress-strain data, and the steps are as follows,

[0025] Identify the environmental interference according to the high-frequency component set and the low-frequency component set, and obtain the environmental interference features;

[0026] Based on the environmental interference features, the dynamic weight of each component is calculated through an exponential function, and different weight distributions are performed according to components of different frequencies;

[0027] The weighted high-frequency component and the low-frequency component are fused into the corrected stress-strain data.

[0028] As a preferred scheme of the connector stress-strain real-time monitoring method, wherein: based on the corrected stress-strain data, the health index of the connector is continuously monitored, and the risk trend of the connector is analyzed, the steps are as follows,

[0029] The corrected stress-strain data is weighted and normalized to generate a health index sequence;

[0030] The historical health index sequence is collected, and an ARIMA model is trained through a self-correlation function;

[0031] The health index sequence is input into the trained ARIMA model to predict the future short-term health index sequence and generate a risk trend slope.

[0032] As a preferred scheme of the connector stress-strain real-time monitoring method, wherein: when the health index sequence is monitored to exceed the dynamic safety threshold, a real-time monitoring feedback is generated, and the steps are as follows,

[0033] The health index sequence is calculated by rolling statistics, and is dynamically adjusted in combination with the risk trend slope to generate a dynamic safety threshold;

[0034] When the health index sequence exceeds the dynamic safety threshold, the abnormal index value, the abnormal timestamp, the correlation parameter and the abnormal level are recorded to generate a real-time monitoring feedback.

[0035] As a preferred scheme of the connector stress-strain real-time monitoring method, wherein: according to the real-time monitoring feedback and the real-time stress-strain data, a health state knowledge graph is constructed, and the steps are as follows,

[0036] The timestamps of the real-time monitoring feedback and the real-time stress-strain data are aligned, and the abnormal features and the time sequence features are extracted respectively to integrate into a multi-dimensional feature vector sequence;

[0037] Based on the multi-dimensional feature vector sequence, in combination with the historical health index sequence, the health state nodes of the connector and the conversion relationship edges between the health states in the health state knowledge graph are defined in the health state knowledge graph to form a health state knowledge graph framework;

[0038] The multi-dimensional feature vector sequence is mapped into a health state knowledge graph framework, the multi-dimensional feature vector sequence is grouped and associated with a state node through a clustering algorithm, a health state knowledge graph is constructed, and an embedded vector sequence is generated.

[0039] As a preferred scheme of the connector stress-strain real-time monitoring method, the step of predicting the failure type and occurrence probability of the connector and generating a failure prediction report is as follows,

[0040] According to historical failure data, the multilayer perceptron is parameter-adjusted through a loss function, and a trained multilayer perceptron is generated;

[0041] The embedded vector sequence is input into the trained multilayer perceptron, and a failure type probability distribution and an occurrence probability value are output;

[0042] The failure type probability distribution and the occurrence probability value are formatted, and a failure prediction report is obtained.

[0043] As a preferred scheme of the connector stress-strain real-time monitoring method, the step of predicting the failure type and occurrence probability of the connector and generating a failure prediction report is as follows,

[0044] Respectively extract maintenance features and failure features in the failure prediction report and the historical failure data to generate a multi-dimensional maintenance feature vector;

[0045] Based on the multi-dimensional maintenance feature vector, a K-nearest neighbor algorithm is used to retrieve a maintenance plan of a similar failure case in the historical failure data to generate a maintenance plan candidate set of the connector;

[0046] The maintenance plan candidate set of the connector is multi-objectively optimized through a genetic algorithm to generate a personalized maintenance plan of the connector.

[0047] In a second aspect, the application provides a connector stress-strain real-time monitoring system, comprising,

[0048] A data acquisition module is configured to acquire and preprocess multi-physical quantity data and external environment data;

[0049] A real-time calculation module is configured to extract current and voltage signal sequences from the preprocessed multi-physical quantity data and calculate real-time stress-strain data through an electrical model;

[0050] A dynamic weighting module is configured to decompose real-time stress-strain data and preprocessed external environment data into high-frequency components and low-frequency components through wavelet multi-scale decomposition, and dynamically weight and fuse the high-frequency components and the low-frequency components into corrected stress-strain data;

[0051] a risk monitoring module, configured to continuously monitor the health index of the connector based on the corrected stress-strain data, and analyze the risk trend of the connector, and generate real-time monitoring feedback when the health index sequence exceeds the dynamic safety threshold;

[0052] a fault prediction module, configured to construct a health state knowledge graph according to the real-time monitoring feedback and the real-time stress-strain data, and predict the fault type and occurrence probability of the connector, and generate a fault prediction report;

[0053] a fault maintenance module, configured to obtain a personalized maintenance plan of the connector based on the fault prediction report and historical fault data.

[0054] The present application has the beneficial effects that: through the wavelet multi-scale decomposition step, the real-time stress-strain data and the preprocessed external environment data are decomposed into high-frequency components and low-frequency components, accurate extraction of multi-scale signal features and noise suppression are realized, and the reliability and anti-interference ability of the monitoring data are effectively improved. At the same time, through the health state knowledge graph construction step, the real-time monitoring feedback and the stress-strain data are mapped into a structured knowledge network, deep semantic analysis of the health state and early warning of the fault are realized. BRIEF DESCRIPTION OF DRAWINGS

[0055] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0056] Fig. 1 The flowchart of the connector stress-strain real-time monitoring method.

[0057] Fig. 2 The schematic diagram of the connector stress-strain real-time monitoring system.

[0058] Fig. 3 The flowchart of data acquisition and preprocessing.

[0059] Fig. 4 The flowchart of health monitoring and maintenance plan generation. DETAILED DESCRIPTION

[0060] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the specific embodiments of the present application will be described in detail below with reference to the drawings of the specification.

[0061] In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application. However, it will be appreciated that the present application can be practiced in a variety of ways beyond the specifics set forth herein, and that the present application can be practiced in other embodiments that depart from these specific details, and that similar alternatives can be used. The present application is therefore not limited to the details below, which are presented by way of example only.

[0062] Second, the "one embodiment" or "an embodiment" as referred to herein means a specific implementation that can include features, structures or characteristics that are not included in all embodiments of the present application. The "in one embodiment" appearing in various places in the specification does not mean the same embodiment, nor does it mean an independent or alternative embodiment that is mutually exclusive with other embodiments.

[0063] Reference Figs. 1-4 For one embodiment of the present application, the embodiment provides a connector stress-strain real-time monitoring method, comprising the following steps:

[0064] S1, collect multi-physical quantity data and external environment data and pre-process;

[0065] The multi-physical quantity data includes strain signals, optical fiber signals, current signals and voltage signals;

[0066] Further, the strain signals and optical fiber signals of the connector are collected by the resistance strain gauge sensor and the optical fiber Bragg grating sensor (the sampling frequency is usually 1000 Hz); the current signals and voltage signals of the connector are collected by the Hall current sensor and the voltage dividing circuit sensor (the sampling frequency is usually 2000 Hz).

[0067] The external environment data includes temperature signals, humidity signals and vibration signals;

[0068] Further, the temperature signals and humidity signals of the external environment are collected by the thermocouple temperature sensor and the capacitive humidity sensor (the sampling frequency is usually 100 Hz); the vibration signals of the external environment are collected by the piezoelectric vibration sensor (the sampling frequency is usually 5000 Hz).

[0069] The pre-processing includes denoising processing, standardization processing, time synchronization and data alignment;

[0070] Further, in a fixed-size sliding window (e.g., 5 sampling points), for each time point of the multi-physical quantity data and the external environment data, the average value of adjacent data points in the window is calculated, and the average value of adjacent data points is taken instead of the current point to eliminate random high-frequency noise; the multi-physical quantity data and the external environment data are subjected to Z-score standardization processing, and the steps are as follows: the arithmetic mean and the standard deviation of each signal are calculated, each data point is subtracted by the mean value and divided by the standard deviation, and the standardized multi-physical quantity data and the external environment data are generated; taking the time axis with the highest sampling frequency (e.g., 5000 Hz of the vibration signal) as the reference, a unified time point sequence is generated, and linear interpolation is used to interpolate the data points with lower sampling frequency to the unified time point sequence; it is verified whether each time point contains data of all signals, and linear interpolation is used to fill in the missing values, abnormal values exceeding the standard deviation range are detected, and sliding window median filtering (window size of 5 points) is used for smoothing processing.

[0071] It should be noted that the standard deviation range is set according to the confidence interval of the normal distribution, for example, when the multi-physical quantity data and the external environment data follow an approximate normal distribution, about 99.7% of the data should fall within ±3 standard deviations of the mean value.

[0072] S2, extract the current and voltage signal sequences from the pre-processed multi-physical quantity data, and calculate real-time stress and strain data through an electrical model;

[0073] Separate the current signal sequence and the voltage signal sequence from the pre-processed multi-physical quantity data;

[0074] Further, according to the multi-physical quantity signal labels (such as "current" and "voltage"), the current signal sequence and the voltage signal sequence are extracted, and the current signal sequence and the voltage signal sequence are detected point by point on a unified time axis to determine whether there are missing values and sampling intervals exceeding the set threshold, and linear interpolation is used to fill in the missing values.

[0075] Based on Ohm's law and Hooke's law, a mathematical relationship between current, voltage and stress and strain is established to generate an electrical model;

[0076] Further, based on the relationship between the resistance of the conductor, voltage and current described by Ohm's law, the relationship between stress and strain described by Hooke's law and the relationship between the rate of resistance change and strain described by the piezoresistive effect, the mathematical relationship between current, voltage and stress-strain is established to generate an electrical model; the current signal sequence, voltage signal sequence and fiber signal strain value are aligned point by point on a unified time axis, the strain value in the fiber signal is taken as a supervised reference input, compared with the initial stress-strain data calculated by the electrical model, an error loss function with the mean square error of the two as the target is constructed, and the strain sensitivity coefficient and material elastic modulus correction coefficient in the electrical model are iteratively updated by using the gradient descent algorithm, and the training is stopped when the error change is less than a preset convergence threshold, and the calibrated electrical model is output.

[0077] It should be noted that the convergence threshold is set according to the convergence speed of the error change in the electrical model training and the signal noise level, and the exemplary value range is usually set to 1x10 -4 to 1x10 -6 .

[0078] The current signal sequence and the voltage signal sequence are input into the electrical model to output initial stress-strain data.

[0079] Further, the real-time resistance value at each time point in the current signal sequence and the voltage signal sequence is calculated by the Ohm's law expression, and the strain value and the stress value are calculated by the strain value calculation expression and the stress value calculation expression, and the strain values and stress values of all time points are integrated to generate the initial stress-strain data.

[0080] The strain value calculation expression is:

[0081] ;

[0082] wherein, is the strain value at time point ; is the time point; is the index of the time point; is the strain sensitivity coefficient (the value range depends on the material type and structure, for example, the constantan alloy of the metal strain gauge is usually 2.0-2.2, and the silicon of the semiconductor is usually 100-170); is the real-time resistance value at time point ; is the initial resistance value.

[0083] It should be noted that the strain sensitivity coefficient is obtained by applying a known strain (e.g. 0~1000με) to the connector material under controlled loading conditions while recording the resistance change rate, calculating the ratio of strain to resistance change rate, and fitting the curve slope.

[0084] The stress value calculation expression is:

[0085] ;

[0086] Wherein, is the stress value at the time point ; is the material elastic modulus (the value range depends on the material type, for example, steel is usually 190-210 GPa).

[0087] It should be noted that the material elastic modulus is obtained by experimental calibration, that is, the theoretical elastic modulus is obtained based on the material type, the stress is measured by applying a known strain in the experiment, and the theoretical value is corrected by linear fitting the slope of the stress-strain relationship curve to obtain the actual elastic modulus of the material under the current temperature and humidity and load environment.

[0088] By comparing the pre-processed optical fiber signal and the initial stress-strain data, the offset value is obtained;

[0089] Further, on the unified time axis, the pre-processed optical fiber signal sequence and the initial stress-strain data sequence are correspondingly matched to ensure that the sampling times of the two signals are completely consistent; the time sequence change amount of the center wavelength is extracted from the pre-processed optical fiber signal, and the optical fiber signal strain value is obtained through the optical fiber strain calculation formula; the difference between the optical fiber signal strain value and the initial stress-strain data is calculated to obtain the offset value.

[0090] The initial stress-strain data is corrected by offset compensation to generate real-time stress-strain data;

[0091] Further, the initial strain value in the initial stress-strain data at each time point and the offset value at the corresponding time point are read, the initial strain value and the offset value are added to obtain the corrected strain value; the corrected strain value is re-input into the stress value calculation expression to output the corrected stress value; the corrected strain value and the stress value at all time points are obtained and integrated into real-time stress-strain data.

[0092] S3, based on the real-time stress-strain data and the pre-processed external environment data, through wavelet multi-scale decomposition into high-frequency components and low-frequency components, and dynamically weighted fusion into corrected stress-strain data;

[0093] The real-time stress-strain data and the pre-processed external environment data are wavelet multi-scale decomposed to generate a high-frequency component set and a low-frequency component set;

[0094] Further, the real-time stress-strain data and the pre-processed external environment data are taken as input signals, db4 wavelet is selected as the mother wavelet function according to the principle of continuous wavelet transform, the characteristics of the input signals at different scales and times are localized and decomposed, and the change characteristics at different time scales are extracted; the number of decomposition layers is set according to the sampling frequency of the input signal, the signal is expanded in time and frequency dimensions at the same time, the decomposed input signal is obtained (for example, three layers of decomposition are set for the vibration signal with a sampling frequency of 5000 Hz), and the real-time stress-strain data and the pre-processed external environment data are point-by-point convolution operated by the wavelet function, the high-frequency detail component and the low-frequency approximation component are separated out, the high-frequency detail component corresponds to the short-time rapid change characteristics in the decomposed input signal, and the low-frequency approximation component corresponds to the slow change long-term trend in the decomposed input signal; the wavelet decomposition is completed on the real-time stress-strain data and the pre-processed external environment data respectively, the high-frequency detail components and the low-frequency approximation components of the stress-strain signal, the temperature signal, the humidity signal and the vibration signal corresponding to the real-time stress-strain data at different scales are obtained, and the high-frequency component set and the low-frequency component set are integrated.

[0095] It should be noted that scale is the core variable in wavelet multiscale, which is used to control the stretching ratio of wavelet basis function in time and frequency, and the scale is inversely proportional to the sampling frequency, which is usually determined by the sampling frequency of the input signal and the number of decomposition layers.

[0096] According to the high-frequency component set and the low-frequency component set, the environmental interference is identified, and the environmental interference characteristics are obtained.

[0097] Further, for the temperature signal component, the humidity signal component and the vibration signal component in the high-frequency component set, the average energy change of each high-frequency component in the time sequence is calculated by the frequency energy analysis method, and the high-frequency interference characteristics are identified, for example, when the average energy change of the high-frequency component of the vibration signal increases to twice the original value in a short time, it is determined as transient mechanical impact interference; for the temperature signal component, the humidity signal component and the vibration signal component in the low-frequency component set, the average change rate and the fluctuation amplitude of the low-frequency component in the time sequence are calculated, when the signal has a persistent offset and a long-term cumulative trend, it is identified as a low-frequency trend interference characteristic, for example, when the mean value of the temperature signal component is monotonously increasing in a fixed time window (for example, 30 seconds) and the fluctuation amplitude is small, it is identified as temperature drift interference; the high-frequency interference characteristics and the low-frequency interference characteristics are time-weighted to generate environmental interference characteristics (the time weighting coefficients are determined according to the influence degree of each signal component on the stress-strain change, for example, the vibration signal has a large weight, and the humidity signal has a medium weight).

[0098] It should be pointed out that the frequency energy analysis method is a signal energy distribution evaluation method based on Fourier energy spectrum, which is used to calculate the energy proportion of signals in different frequency ranges, to identify the change trend of high frequency and low frequency components in energy distribution by comparing the energy proportion change of different time periods (for example, when the increase is more than 50% compared with the reference value, it is determined that there is transient mechanical impact or high frequency vibration interference), and to measure the energy intensity by performing spectrum transformation on high frequency components and low frequency components respectively, and calculating the integral value of each signal power per unit time; the high frequency interference characteristics include high frequency energy mutation characteristics, short time amplitude sudden increase characteristics and transient fluctuation characteristics; the low frequency interference characteristics include low frequency energy accumulation characteristics, smooth trend offset characteristics and long-term drift characteristics.

[0099] Based on the environmental interference characteristics, the dynamic weight of each component is calculated by an exponential function, and different weight distribution is performed according to different frequency components;

[0100] Further, a nonlinear mapping relationship between environmental interference intensity and dynamic weight is established by an exponential function, the environmental interference intensity of each signal component at each time point is input into the exponential function, and the corresponding dynamic weight initial value is output; in the high frequency component set, the change of dynamic weight initial value shows an amplification effect on short-time fluctuation and transient energy mutation, so that the weight rapidly increases when vibration impact or humidity rapidly changes; in the low frequency component set, the change of dynamic weight initial value shows a smoothing effect on long-term slowly varying trend, so that the weight slowly adjusts when temperature drift or humidity accumulates, and the stability of stress and strain estimation is maintained; when assigning weights to different frequency components, the influence proportion of the same source signal at different frequency levels is adjusted by the frequency band weighting coefficient, so that the component with high energy proportion is assigned a larger weight, and the component with low energy proportion is assigned a smaller weight, to generate a dynamic weight sequence corresponding to the high frequency component set and the low frequency component set point by point on the time axis;

[0101] It should be pointed out that the frequency band weighting coefficient is a proportional factor for measuring the influence degree of different frequency components on stress and strain, the weight parameter is set according to the energy proportion and stress and strain influence degree of each signal component, and the frequency band weighting coefficient is obtained after the energy proportion is normalized,

[0102] The weighted high frequency component and low frequency component are fused into corrected stress and strain data;

[0103] Further, the dynamic weight sequence is aligned with the corresponding energy amplitudes in the high-frequency component set and the low-frequency component set point by point in time, and the same scale is weighted and calculated, and the energy amplitude of each time point is nonlinearly weighted by the dynamic weight sequence to obtain the comprehensive interference influence of the external environment on the real-time stress-strain data, calculate the environmental interference contribution, and decompose the environmental interference contribution into high-frequency environmental correction terms and low-frequency environmental correction terms in different scales through the wavelet reconstruction function; subtract the high-frequency environmental correction term from the high-frequency stress-strain signal, and subtract the low-frequency environmental correction term from the low-frequency stress-strain signal to obtain the high-frequency fusion component and the low-frequency fusion component after the environmental interference is suppressed; and the high-frequency fusion component and the low-frequency fusion component of each scale are superimposed along the time axis through the wavelet reconstruction function to generate the corrected stress-strain data.

[0104] It should be noted that the energy amplitude refers to the local energy intensity obtained by the modulus square of the wavelet coefficient after the real-time stress-strain data and the preprocessed external environment data are decomposed through continuous wavelet transform; the wavelet reconstruction function is a function of recombining the components of each scale obtained by wavelet decomposition into a time domain signal, and the inverse wavelet transform is performed on each scale of high-frequency detail component and low-frequency approximation component to recover the overall structure of the signal in time sequence.

[0105] S4, based on the corrected stress-strain data, continuously monitor the health indicators of the connector, and analyze the risk trend of the connector, and generate real-time monitoring feedback when the health indicator sequence exceeds the dynamic safety threshold;

[0106] The corrected stress-strain data is weighted and normalized to generate a health indicator sequence;

[0107] Further, the continuous wavelet transform is performed on the corrected stress-strain data, the modulus square of the wavelet coefficient is read, and the energy amplitude sequence is generated point by point; the energy amplitude sequence is multiplied point by point with the corrected stress-strain data as a weighting factor to generate a weighted stress sequence and a weighted strain sequence; the mean and standard deviation of the weighted stress sequence and the weighted strain sequence are calculated based on a sliding statistical window, and Z-score normalization is performed to obtain a normalized weighted stress sequence and a normalized weighted strain sequence; the normalized weighted stress sequence and the normalized weighted strain sequence are fused and weighted to generate a health indicator sequence.

[0108] It should be noted that the wavelet coefficient is a set of numerical values obtained by convoluting the mother wavelet function at different scales and different time positions with the multi-physical quantity signal, which is used to quantify the energy size of the multi-physical quantity signal.

[0109] The historical health indicator sequence is collected, and an ARIMA model is trained through an autocorrelation function;

[0110] Further, the health index data of multiple time periods in the time window is continuously collected to generate a historical health index sequence, the historical health index sequence is subjected to difference and stationary processing, the degradation of the device performance and the load of the environmental operation are eliminated by calculating the change amount between adjacent time points, and a stationary health index sequence is obtained; the stationary health index sequence is input into an autocorrelation function and a partial autocorrelation function, the correlation coefficients and the partial correlation coefficients under different lag orders are calculated, a lag order correlation distribution is output, the order parameters of the ARIMA model are set according to the lag order correlation distribution, the autoregressive order (for example, p = 1, the difference order d = 1, and the moving average order q = 1) is set, and the ARIMA model order parameters are generated; the stationary health index sequence and the ARIMA model order parameters are input into the ARIMA model for training, and the steps are as follows: the autoregressive coefficients, the moving average coefficients and the constant term are calculated by the maximum likelihood estimation method, the residual error is calculated, and the white noise test is performed; when the autocorrelation coefficients of the residual error sequence are close to zero at all lag orders, the training is completed, and the trained ARIMA model is output.

[0111] It should be noted that the maximum likelihood estimation method is a parameter estimation method, specifically, the maximum likelihood estimation method measures the possibility of observing the current data under different parameter values by constructing a likelihood function, and finds the parameter value that maximizes the possibility of the current data by using an optimization algorithm; the autocorrelation function is used to measure the linear correlation degree of the time sequence under different lag orders, to judge the periodicity and trend continuity of the data; the partial autocorrelation function is used to exclude the influence of the intermediate lag term and calculate the direct correlation degree of the time delay step.

[0112] The health index sequence is input into the trained ARIMA model to predict the future short-term health index sequence, and a risk trend slope is generated;

[0113] Further, the health index sequence is input into the trained ARIMA model, a short-term predicted health index sequence difference domain is iteratively generated in a one-step rolling manner, the short-term predicted health index sequence difference domain is subjected to inverse difference reconstruction, is accumulated in time sequence and is aligned with the benchmark, and a short-term predicted health index sequence is generated; the short-term predicted health index sequence and the corresponding time index are subjected to least square linear fitting in the prediction interval, and the slope of the fitted straight line is taken as the risk trend slope, which is used to quantify the rising or falling speed of the health index sequence in the short term.

[0114] The health index sequence is subjected to rolling statistical calculation, and a dynamic safety threshold is generated by combining the risk trend slope.

[0115] Furthermore, based on the health indicator sequence, within a fixed-length sliding window (e.g., a window length of 60 sampling points), the rolling mean and rolling standard deviation corresponding to each time point are continuously calculated to generate a rolling statistics sequence; a nonlinear mapping relationship of the threshold gain coefficient is established according to the sign of the risk trend slope, mapping the risk trend slope to the threshold gain coefficient;

[0116] The expression for the threshold gain coefficient is:

[0117] ;

[0118] in, The threshold gain coefficient at time point t; This is the adjustment coefficient; The slope of the risk trend at time point t;

[0119] Using the threshold gain coefficient sequence as weights, the rolling standard deviation is multiplied by the corresponding threshold gain coefficient at each time point to form a dynamic standard deviation sequence; when the risk trend slope is positive (health indicators rise), the threshold gain coefficient is greater than 1, and the rolling standard deviation is amplified; when the risk trend slope is negative (health indicators fall), the threshold gain coefficient is less than 1, and the rolling standard deviation is compressed.

[0120] Align the rolling mean and dynamic standard deviation point by point over time, perform a linear combination operation to generate a dynamic safety threshold. The typical range for the dynamic safety threshold is 0.6 to 1.2. When the risk trend slope is positive, the dynamic safety threshold shifts upward to expand the safety range and avoid false alarms; when the risk trend slope is negative, the dynamic safety threshold shifts downward to narrow the safety range and enhance monitoring. The expression for the dynamic safety threshold is set as follows:

[0121] ;

[0122] in, For time points Dynamic security threshold; This is the rolling average; To ensure safety, the coefficient is relaxed. For dynamic standard deviation;

[0123] It should be noted that the adjustment coefficient is set based on the sensitivity of the trend change of the health indicator sequence and the time response requirements, and the exemplary value range is usually between 0.05 and 0.3; the safety relaxation coefficient is set based on the statistical distribution characteristics and risk tolerance of the historical health indicator sequence, and is set by statistically analyzing the historical data of health indicators during the training phase, and the exemplary value range is usually between 1.2 and 2.5.

[0124] When the health index sequence exceeds the dynamic safety threshold, record the abnormal index value, abnormal timestamp, correlation parameter and abnormal level, and generate real-time monitoring feedback;

[0125] Further, at the same time point, compare the health index sequence with the dynamic safety threshold point by point, and mark the position where the health index sequence is greater than the dynamic safety threshold to form an out-of-boundary mark sequence. The value corresponding to the marked time point in the out-of-boundary mark sequence is taken as the abnormal index value, and the time index corresponding to the time point is taken as the abnormal timestamp. At the same time, the stress value and strain value of the corresponding time point are extracted from the corrected stress-strain data, and the rolling mean and dynamic standard deviation of the corresponding time point are extracted from the rolling mean and dynamic standard deviation. The scalar values of the corresponding time points are extracted from the risk trend slope, temperature signal, humidity signal and vibration signal, and are integrated into correlation parameters, including rolling mean, dynamic standard deviation, risk trend slope, stress value, strain value, temperature parameter, humidity parameter and vibration parameter. The difference between the health index sequence and the dynamic safety threshold at the same time point sequence is calculated, and the strength score, weighted strength score and abnormal timestamp are combined to obtain the comprehensive abnormal score. When the comprehensive abnormal score is greater than the high abnormal threshold, it is marked as high-level abnormality. When the comprehensive abnormal score is between the medium abnormal threshold and the high abnormal threshold, it is marked as medium-level abnormality. When the comprehensive abnormal score is less than the medium abnormal threshold, it is marked as low-level abnormality, and an abnormal level sequence is generated. The abnormal index value, abnormal timestamp, correlation parameter and abnormal level are integrated into real-time monitoring feedback.

[0126] It should be noted that the high abnormal threshold and the medium abnormal threshold are based on the historical health index sequence to calculate the historical comprehensive abnormal score in the corresponding time period, and are set according to the confidence level of the distribution of the historical comprehensive abnormal score (for example, the medium threshold corresponds to the 95th percentile position of the score distribution, and the high threshold corresponds to the 99th percentile position of the score distribution). The medium threshold is exemplarily taken in the range of 1.5-2.0, and the high threshold is exemplarily taken in the range of 2.5-3.0.

[0127] S5, according to the real-time monitoring feedback and the real-time stress-strain data, constructing a health state knowledge graph, and predicting the fault type and occurrence probability of the connector, generating a fault prediction report;

[0128] Align the timestamps of the real-time monitoring feedback and the real-time stress-strain data, and extract abnormal features and time series features respectively, and integrate them into a multi-dimensional feature vector sequence;

[0129] Further, read the abnormal timestamp in the real-time monitoring feedback and the time index in the real-time stress-strain data, align the time points through inner connection, extract the abnormal indicator value, correlation parameter and abnormal level in the real-time monitoring feedback, and combine to generate an abnormal feature sequence; read the stress value and strain value from the real-time stress-strain data point by point, and obtain the first-order difference, sliding mean and sliding standard deviation of the stress value and strain value in a fixed sliding window (for example, the sliding window length is 60 sampling points), to generate a time sequence feature sequence; cascade the abnormal feature sequence and the time sequence feature sequence point by point into a single vector under the same timestamp, and stack in time sequence to form a multi-dimensional feature vector sequence.

[0130] Based on the multi-dimensional feature vector sequence and in combination with the historical health indicator sequence, define the health state node of the connector and the transformation relationship edge between the health states in the health state knowledge graph, to form a health state knowledge graph framework.

[0131] Further, based on the multi-dimensional feature vector sequence and in combination with the historical health indicator sequence, determine the health state at each time point of the multi-dimensional feature vector sequence, the steps are as follows: when the abnormal level sequence is high-level abnormality and the stress value reaches the material elastic safety limit threshold, mark it as “overload”; when the abnormal level sequence is medium-level abnormality, mark it as “warning”; when the abnormal level sequence is low-level abnormality and the value of the health indicator sequence does not continuously exceed the dynamic safety threshold (for example, 3 times of not continuously exceeding the dynamic safety threshold), mark it as “normal”; when the abnormal level sequence reaches the material elastic safety limit threshold multiple times (for example, 3 times or more) within a time window and is accompanied by slow accumulation of strain value, mark it as “fatigue evolution”, to generate a health state label sequence; group and aggregate the multi-dimensional feature vector sequence according to the health state label sequence, calculate the center vector and distribution range of each health state in the feature space, and form a health state node set described by the state name, center vector and statistical boundary; perform adjacent time point transition statistics on the health state label sequence, obtain the transition times and transition probability from any health state to another health state, and record the average residence time and transition trigger condition, to generate a health state transformation relationship edge set; uniformly index the health state node set and the health state transformation relationship edge set according to the node identification and time sequence, and assemble into a health state knowledge graph framework containing the health state node attribute (center vector and statistical boundary) and the transformation relationship edge attribute (transition probability, average residence time and trigger condition) between the health states.

[0132] It should be noted that the material elastic safety limit threshold is usually set to 60% to 85% of the material elastic safety limit, which is the maximum safe stress value that the connector material can withstand in the elastic stage, and is set based on the material mechanical property parameters and in combination with the environmental correction coefficient.

[0133] Map the multi-dimensional feature vector sequence into the health state knowledge graph framework, group and associate the state nodes by clustering algorithm, construct the health state knowledge graph, and generate the embedding vector sequence;

[0134] Further, the number of health state node sets is read as the number of clusters, and K-Means is used to cluster the multi-dimensional feature vector sequence to generate a cluster label sequence and a cluster center set; the cluster center set and the center vector in the health state node set are calculated one by one to find the center vector of the health state node with the smallest Euclidean distance for each cluster center, and the corresponding mapping relationship is established, and finally the mapping relationship of "cluster center→health state node" is formed, and the mapping relationship is applied to the cluster label sequence to generate a state association sequence; read the state association sequence at adjacent time points, accumulate the occurrence times of each pair of adjacent states, and update the transition probability and average stay time in the health state transition relationship edge set, and generate a health state knowledge graph; perform Node2Vec random walk on the health state knowledge graph to obtain the vector representation of each health state node, and arrange the health state node vectors corresponding to each time point in the state association sequence in time sequence to generate an embedding vector sequence.

[0135] According to the historical fault data, the parameters of the multi-layer perceptron are adjusted by the loss function to generate a trained multi-layer perceptron;

[0136] Further, the embedding vector sequence and the historical fault data are aligned point by point to construct a training sample set and a validation sample set with embedding vectors as features and fault types and occurrence labels in historical fault data as supervised labels, establish a full connection structure of the input layer, the hidden layer and the output layer of the multi-layer perceptron, use cross-entropy loss function as the optimization objective, and use Adam optimization algorithm to perform forward calculation of cross-entropy loss function value in small batch iteration and reverse propagation according to the gradient of the loss function to update the weights and biases of the multi-layer perceptron; weight decay is used to suppress overfitting, and the cycle is repeated according to the number of rounds until the validation sample set loss function no longer decreases to trigger stop, and the trained multi-layer perceptron is generated.

[0137] It should be noted that the historical fault data is derived from the historical monitoring records and maintenance records of the connector during long-term operation, and the historical fault data includes time index, fault type, occurrence label, operating environment parameter, historical repair and maintenance information, and stress-strain reference value.

[0138] The embedding vector sequence is input into the trained multi-layer perceptron to output the fault type probability distribution and the occurrence probability value;

[0139] Further, the embedded vector sequence is sequentially inputted into the trained multi-layer perception at the same time point sequence, forward calculation is performed and normalized probability transformation is performed at the output layer to obtain a fault type probability distribution corresponding to each time point, the category corresponding to the maximum probability is read at each point on the fault type probability distribution as the fault type, and the corresponding probability value is read as the fault occurrence probability value.

[0140] The fault type probability distribution and the occurrence probability value are formatted, and a fault prediction report is obtained.

[0141] Further, the fault type probability distribution and the occurrence probability value are sequentially and uniformly formatted at each point, the fault type probability distribution at each time point is converted to a percentage form and the fault type corresponding to the maximum probability is extracted, and the occurrence probability value at the corresponding time point is recorded together to form a fault prediction report.

[0142] S6, based on the fault prediction report, combined with historical fault data, a personalized maintenance plan for the connector is obtained;

[0143] The maintenance features and fault features in the fault prediction report and the historical fault data are extracted respectively, and a multi-dimensional maintenance feature vector is generated;

[0144] Further, the maintenance and maintenance information (including maintenance action, maintenance time, downtime, component replacement record and cost) in the fault prediction report and the historical fault data are matched according to the time index, the fault features (fault type, occurrence probability value and fault type probability distribution) are numerically valued, the maintenance features (maintenance action, maintenance time, downtime, component replacement record and cost) are encoded and standardized, all features are sequentially concatenated at the same time point to generate a multi-dimensional maintenance feature vector.

[0145] Based on the multi-dimensional maintenance feature vector, the K nearest neighbor algorithm is used to retrieve the maintenance plan of the similar fault case in the historical fault data to generate a maintenance plan candidate set for the connector;

[0146] Further, the K nearest neighbor algorithm is used to calculate the Euclidean distance between the multi-dimensional maintenance feature vector and the historical multi-dimensional maintenance feature vector library in the feature space, and the nearest neighbor samples with the smallest distance (for example, the number of nearest neighbors is 5) are selected under the standardized measurement, the maintenance action, maintenance time, downtime, component replacement record and cost record corresponding to the nearest neighbor samples are extracted as the maintenance plan of the similar fault case, and the maintenance plan of the similar fault case is integrated in ascending order of time index and distance to output the maintenance plan candidate set for the connector.

[0147] It should be noted that the historical multi-dimensional maintenance feature vector library is generated by uniformly encoding and standardizing the fault features and maintenance features contained in the historical fault data.

[0148] The candidate set of maintenance plans for the connector is multi-objectively optimized by a genetic algorithm to generate a personalized maintenance plan for the connector.

[0149] Further, the entries of the candidate set of maintenance plans for each connector are encoded as chromosomes, the maintenance actions, maintenance time length, downtime length, component replacement records and cost records are taken as gene contents, a multi-objective fitness function containing cost minimization, downtime length minimization and risk reduction amplitude maximization is established, and is synthesized into a single fitness score in a weighted manner; the chromosome population is constantly updated by selection, crossover and mutation operations to evolve iteratively in the population, constraint checking is performed on each generation population to ensure that the maintenance time length does not exceed the available maintenance window, the iteration is terminated when the fitness improvement of consecutive generations is less than a preset fitness threshold or the generation upper limit is reached, the chromosome with the highest fitness is output and decoded into a maintenance action list, execution order, predicted maintenance time length, predicted downtime length and predicted cost, and a personalized maintenance plan for the connector is generated.

[0150] It should be noted that the available maintenance window refers to the time period during which the connector is allowed to perform maintenance operations in the running cycle, which is set based on the running plan; the fitness threshold is set based on the normalized scale of the multi-objective function and the actual optimization sensitivity, and the exemplary value range is usually 1x10 -4 ~ 1x10 -2 ; the generation upper limit is determined according to the dimension of the multi-dimensional maintenance feature vector and the population size experience, and the exemplary value range is usually 100-300 generations.

[0151] The embodiment also provides a connector stress-strain real-time monitoring system, comprising:

[0152] A data acquisition module is configured to acquire and pre-process multi-physical quantity data and external environment data;

[0153] A real-time calculation module is configured to extract current and voltage signal sequences from the pre-processed multi-physical quantity data, and calculate real-time stress-strain data through an electrical model;

[0154] A dynamic weighting module is configured to decompose the real-time stress-strain data and the pre-processed external environment data into high-frequency components and low-frequency components through wavelet multi-scale decomposition, and dynamically weight and fuse the high-frequency components and the low-frequency components into corrected stress-strain data;

[0155] A risk monitoring module is configured to continuously monitor health indicators of the connector based on the corrected stress-strain data, and analyze risk trends of the connector, and generate real-time monitoring feedback when the health indicator sequence exceeds a dynamic safety threshold;

[0156] A fault prediction module is configured to construct a health state knowledge graph based on real-time monitoring feedback and real-time stress-strain data, and to predict the fault type and occurrence probability of the connector, and to generate a fault prediction report;

[0157] A fault maintenance module is configured to obtain a personalized maintenance plan for the connector based on the fault prediction report and historical fault data.

[0158] To sum up, the present application has the following advantages: through the wavelet multi-scale decomposition step, the real-time stress-strain data and the pre-processed external environment data are decomposed into high-frequency components and low-frequency components, the accurate extraction of multi-scale signal features and noise suppression are realized, and the reliability and anti-interference ability of the monitoring data are effectively improved. At the same time, through the health state knowledge graph construction step, the real-time monitoring feedback and the stress-strain data are mapped into a structured knowledge network, the deep semantic analysis of the health state and the early warning of the fault are realized.

[0159] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and are not limiting. Although the present application has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solutions of the present application can be modified or replaced equivalently without departing from the spirit and scope of the technical solutions of the present application, and they should be covered in the scope of the claims of the present application.

Claims

1. A connector stress-strain real-time monitoring method, characterized by: The application relates to a method for monitoring the health of a connector, and belongs to the field of connector health monitoring. Collecting and preprocessing multi-physical quantity data and external environment data; Extracting current and voltage signal sequences from the preprocessed multi-physical quantity data, calculating real-time stress and strain data through an electrical model, and the specific steps are as follows, Separating the current signal sequence and the voltage signal sequence from the preprocessed multi-physical quantity data; The multi-physical quantity data comprises strain signals, fiber signals, current signals and voltage signals; The fiber signal is an optical signal collected by a fiber Bragg grating sensor and represents the strain change of the connector through the time sequence change of the central wavelength; Based on Ohm's law and Hooke's law, a mathematical relationship between current, voltage and stress and strain is established to generate an electrical model; Inputting the current signal sequence and the voltage signal sequence into the electrical model to output initial stress and strain data; Comparing the preprocessed fiber signal with the initial stress and strain data to obtain an offset value, and the specific steps are as follows, On a unified time axis, the preprocessed fiber signal sequence is correspondingly matched with the initial stress and strain data sequence to ensure that the sampling times of the two signals are completely consistent; Extracting the time sequence change of the central wavelength from the preprocessed fiber signal, and obtaining the fiber signal strain value through a fiber strain calculation formula; Calculating the difference between the fiber signal strain value and the initial stress and strain data to obtain the offset value; Correcting the initial stress and strain data through offset compensation to generate real-time stress and strain data; Based on the real-time stress and strain data and the preprocessed external environment data, the data are decomposed into high-frequency components and low-frequency components through wavelet multi-scale decomposition, and are dynamically weighted and fused into corrected stress and strain data; Based on the corrected stress and strain data, the health index of the connector is continuously monitored, and the risk trend of the connector is analyzed, and when the health index sequence exceeds the dynamic safety threshold, real-time monitoring feedback is generated, and the steps are as follows, Weighted normalization is performed on the corrected stress and strain data to generate a health index sequence; Collecting a historical health index sequence and training an ARIMA model through a self-correlation function; Inputting the health index sequence into the trained ARIMA model to predict the future short-term health index sequence and generate a risk trend slope; According to the real-time monitoring feedback and the real-time stress and strain data, a health state knowledge graph is constructed, and the failure type and occurrence probability of the connector are predicted to generate a failure prediction report; Based on the failure prediction report, a personalized maintenance plan for the connector is obtained in combination with historical failure data.

2. The connector strain real-time monitoring method of claim 1, wherein: The external environment data comprises temperature signals, humidity signals and vibration signals; The preprocessing comprises denoising, standardization, time synchronization and data alignment.

3. The connector strain real-time monitoring method of claim 1, wherein: Based on the real-time stress and strain data and the preprocessed external environment data, the data are decomposed into high-frequency components and low-frequency components through wavelet multi-scale decomposition, and are dynamically weighted and fused into corrected stress and strain data, and the steps are as follows, Wavelet multi-scale decomposition is performed on the real-time stress and strain data and the preprocessed external environment data to generate a high-frequency component set and a low-frequency component set; According to the high-frequency component set and the low-frequency component set, environmental interference is identified, and environmental interference characteristics are obtained; Based on the environmental interference characteristics, the dynamic weights of the components are calculated through an exponential function, and different weight distributions are performed on the components with different frequencies. The weighted high-frequency component and the low-frequency component are fused into the corrected stress-strain data.

4. The connector strain real-time monitoring method of claim 3, wherein: When the health index sequence is monitored to exceed the dynamic safety threshold, real-time monitoring feedback is generated, and the steps are as follows, The health index sequence is calculated by rolling statistics, and the dynamic safety threshold is adjusted dynamically in combination with the risk trend slope. When the health index sequence exceeds the dynamic safety threshold, the abnormal index value, the abnormal timestamp, the associated parameter and the abnormal level are recorded, and the real-time monitoring feedback is generated.

5. The connector strain real-time monitoring method of claim 4, wherein: The health state knowledge graph is constructed according to the real-time monitoring feedback and the real-time stress-strain data, and the steps are as follows, The timestamps of the real-time monitoring feedback and the real-time stress-strain data are aligned, and the abnormal features and the time sequence features are extracted respectively, and are integrated into a multi-dimensional feature vector sequence; Based on the multi-dimensional feature vector sequence, the health state nodes of the connector and the conversion relationship edges between the health states in the health state knowledge graph are defined in the health state knowledge graph in combination with the historical health index sequence, and a health state knowledge graph framework is formed; The multi-dimensional feature vector sequence is mapped into the health state knowledge graph framework, the multi-dimensional feature vector sequence is grouped and associated with the state nodes by a clustering algorithm, the health state knowledge graph is constructed, and an embedding vector sequence is generated.

6. The connector strain real-time monitoring method of claim 5, wherein: The fault type and the occurrence probability of the connector are predicted, and a fault prediction report is generated, and the steps are as follows, According to the historical fault data, the multilayer perceptron is adjusted by a loss function, and a trained multilayer perceptron is generated; The embedding vector sequence is input into the trained multilayer perceptron, and a fault type probability distribution and an occurrence probability value are output; The fault type probability distribution and the occurrence probability value are formatted, and a fault prediction report is obtained.

7. The connector strain real-time monitoring method of claim 6, wherein: Based on the fault prediction report, the individual maintenance plan of the connector is obtained in combination with the historical fault data, and the steps are as follows, Maintenance features and fault features in the fault prediction report and the historical fault data are extracted respectively, and a multi-dimensional maintenance feature vector is generated; Based on the multi-dimensional maintenance feature vector, a maintenance plan candidate set of the connector is generated by using a K-nearest neighbor algorithm to retrieve a similar fault case maintenance plan of the historical fault data; The maintenance plan candidate set of the connector is optimized by a genetic algorithm, and an individual maintenance plan of the connector is generated.

8. A connector stress-strain real-time monitoring system based on the connector stress-strain real-time monitoring method according to any one of claims 1 to 7, characterized in that: It comprises, a data acquisition module for acquiring multi-physical quantity data and external environment data and pre-processing; a real-time calculation module for extracting current and voltage signal sequences from the pre-processed multi-physical quantity data, and calculating real-time stress-strain data through an electrical model; a dynamic weighting module for decomposing the real-time stress-strain data and the pre-processed external environment data into high-frequency components and low-frequency components through wavelet multi-scale decomposition, and dynamically weighting and fusing them into corrected stress-strain data; a risk monitoring module for continuously monitoring the health index of the connector based on the corrected stress-strain data, and analyzing the risk trend of the connector, and generating real-time monitoring feedback when the health index sequence exceeds the dynamic safety threshold; a fault prediction module for constructing a health state knowledge graph according to the real-time monitoring feedback and the real-time stress-strain data, and predicting the fault type and the occurrence probability of the connector, and generating a fault prediction report; A fault maintenance module is configured to obtain a personalized maintenance plan for the connector based on the fault prediction report in combination with historical fault data.

Images