High-Voltage Connector Fault Prediction Method and System Based on Thermal Management

Abstract

The present application relates to the technical field of high-voltage connectors, and discloses a high-voltage connector fault prediction method and system based on thermal management. The method includes: collecting temperature distribution data and electrical signal transmission characteristic data of the high-voltage connector, and establishing a thermal-electric coupling network model including temperature nodes and signal transmission nodes; separating and optimizing the transmission characteristic function to obtain a temperature-transmission characteristic mapping relationship; performing Gaussian process regression calculation on the temperature time series data to obtain temperature dynamic characteristic statistical features; inputting the temperature dynamic characteristic statistical features into a specified time-delay thermal management neural network for signal transmission delay prediction to obtain delay prediction characteristic parameters; calculating the weighted error value in the transmission characteristic space, and dynamically adjusting the signal transmission delay to obtain the compensated signal transmission time delay parameter, thereby realizing the accurate prediction of the signal transmission delay and improving the accuracy and robustness of the compensation effect.

Description

Technical Field

[0001] This application relates to the technical field of high-voltage connectors, and particularly to a method and system for predicting faults of high-voltage connectors based on thermal management. Background Art

[0002] High-voltage connectors, as key signal transmission components, are widely used in various industrial equipment. However, in the actual working environment, high-voltage connectors often bear complex thermal stresses and electromagnetic interferences, and this thermoelectric coupling effect will seriously affect the reliability and stability of signal transmission.

[0003] Traditional methods for predicting faults of high-voltage connectors mainly rely on single electrical parameter monitoring or temperature monitoring, and cannot effectively capture the comprehensive impact of the thermoelectric coupling effect on signal transmission, resulting in low accuracy and reliability of fault prediction. Especially under the working conditions of drastic temperature changes, the dynamic changes of signal transmission delay are more difficult to accurately predict and compensate. Summary of the Invention

[0004] This application provides a method and system for predicting faults of high-voltage connectors based on thermal management, thereby achieving accurate prediction of signal transmission delay and improving the accuracy and robustness of the compensation effect.

[0005] In the first aspect of this application, a method for predicting faults of high-voltage connectors based on thermal management is provided. The method for predicting faults of high-voltage connectors based on thermal management includes:

[0006] Collect temperature distribution data and electrical signal transmission characteristic data of the high-voltage connector, and establish a thermoelectric coupling network model including temperature nodes and signal transmission nodes;

[0007] According to the thermoelectric coupling network model, separate and optimize the transmission characteristic function to obtain a temperature-transmission characteristic mapping relationship;

[0008] Based on the temperature-transmission characteristic mapping relationship, perform Gaussian process regression calculation on the temperature time series data to obtain temperature dynamic characteristic statistical features;

[0009] Input the temperature dynamic characteristic statistical features into a specified time-delay thermal management neural network for signal transmission delay prediction to obtain delay prediction characteristic parameters;

[0010] Calculate the weighted error value in the transmission characteristic space according to the delay prediction characteristic parameters, and dynamically adjust the signal transmission delay to obtain the compensated signal transmission time delay parameters.

[0011] In the second aspect of this application, a system for predicting faults of high-voltage connectors based on thermal management is provided. The system for predicting faults of high-voltage connectors based on thermal management includes:

[0012] A collection module, configured to collect temperature distribution data and electrical signal transmission characteristic data of a high-voltage connector, and establish a thermal-electrical coupling network model including temperature nodes and signal transmission nodes;

[0013] A separation and optimization module, configured to separate and optimize a transmission characteristic function according to the thermal-electrical coupling network model to obtain a temperature-transmission characteristic mapping relationship;

[0014] A regression calculation module, configured to perform Gaussian process regression calculation on temperature time series data based on the temperature-transmission characteristic mapping relationship to obtain temperature dynamic characteristic statistical features;

[0015] A delay prediction module, configured to input the temperature dynamic characteristic statistical features into a specified time-delay thermal management neural network for signal transmission delay prediction to obtain delay prediction characteristic parameters;

[0016] A dynamic adjustment module, configured to calculate a weighted error value in a transmission characteristic space according to the delay prediction characteristic parameters, and dynamically adjust the signal transmission delay to obtain compensated signal transmission delay parameters.

[0017] Compared with the prior art, the present application has the following beneficial effects: By establishing a thermal-electrical coupling network model including temperature nodes and signal transmission nodes, an accurate description of the thermal-electrical coupling characteristics of the high-voltage connector is realized. Using a non-linear thermal-electrical separation network optimization method, the mapping relationship between the temperature field distribution and the signal transmission characteristics is effectively extracted, the complexity of the model is reduced, and the calculation efficiency is improved. The temperature dynamic characteristic identification method based on Gaussian process regression accurately captures the temperature change law and provides reliable temperature feature input for delay prediction. A specified time-delay thermal management neural network structure is proposed, and through multi-level feature extraction and fusion, accurate prediction of signal transmission delay is realized. A three-layer Bayesian inference algorithm is used to optimize the delay compensation strategy, significantly improving the accuracy and robustness of the compensation effect. Description of the Drawings

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0019] The structures, proportions, sizes, etc. shown in the drawings of this specification are only used to cooperate with the content disclosed in the specification for those skilled in this technology to understand and read, and are not used to limit the limiting conditions under which the present invention can be implemented. Therefore, they do not have substantial technical significance. Any modification of the structure, change in the proportional relationship, or adjustment of the size, without affecting the effects that the present invention can produce and the purposes that can be achieved, should still fall within the scope covered by the technical content disclosed in the present invention.

[0020] Figure 1 is a schematic flow chart of a high-voltage connector fault prediction method based on thermal management provided by an embodiment of the present invention;

[0021] Figure 2 is a schematic block diagram of the structure of a high-voltage connector fault prediction system based on thermal management provided by an embodiment of the present invention. Detailed implementation manners

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

[0023] The flow chart shown in the drawings is only an example illustration, and does not necessarily include all the content and operations / steps, nor does it necessarily need to be executed in the described order. For example, some operations / steps can be decomposed, combined, or partially merged. Therefore, the actual execution order may be changed according to the actual situation.

[0024] It should also be understood that the terms used in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application. As used in the specification of this application and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an", and "the" are intended to include the plural forms.

[0025] It should be further understood that the term "and / or" used in the specification of this application and the appended claims refers to any combination and all possible combinations of one or more of the related listed items, and includes these combinations. Please refer to Figure 1 , an embodiment of the high-voltage connector fault prediction method based on thermal management in the embodiments of this application includes:

[0026] Step 100, collect the temperature distribution data and electrical signal transmission characteristic data of the high-voltage connector, and establish a thermal-electrical coupling network model including temperature nodes and signal transmission nodes;

[0027] It can be understood that the execution entity of this application can be a high-voltage connector fault prediction system based on thermal management, or it can also be a terminal or a server, and specific details are not limited here. In this embodiment of the application, the server is taken as an example of the execution entity for illustration.

[0028] Specifically, the physical structure of the high-voltage connector is divided into equally spaced grids, and the complex physical structure of the connector is discretized into several standard units, each of which contains temperature monitoring points and signal monitoring points. In the process of equally spaced grid division, the finite element method is used to discretize the units to obtain a grid structure with higher consistency and computability. Temperature sampling is performed on the temperature monitoring points in the standard units. The temperature distribution information of each unit is obtained by relying on high-precision temperature sensors, while ensuring that the temporal and spatial resolution of the data meets the requirements of subsequent modeling. After collecting enough temperature data, these sampled data are processed based on the heat conduction equation to calculate the temperature gradient of each unit. The temperature gradient reflects the direction and rate of heat transfer in the unit and is an important basic parameter for describing the heat conduction behavior. Through this step, a basic data set containing the temperature distribution of all units is formed. The temperature distribution data is input into the heat conduction differential equation group for heat conduction characteristic analysis. By solving the heat conduction equation group, the heat exchange characteristics between adjacent units are described, and the heat conduction characteristic function is obtained to quantify the flow rate and intensity of heat energy between units. In this process, the influence of the thermal physical parameters of the material and the environmental conditions on heat transfer is fully considered to ensure the accuracy and physical significance of the calculation results. At the same time, for the signal monitoring points in the standard unit, the electrical signal characteristics are collected and analyzed in parallel. The amplitude, phase and delay of the signal are sampled through high-precision electrical signal measurement equipment to form a basic data set that reflects the dynamic characteristics of the signal. After the collection is completed, these data are input into the transmission line model, and the signal characteristics are calculated by solving the transmission line equation to obtain the characteristic data of the signal transmission in each unit, including key indicators such as signal attenuation, delay and distortion. The electrical signal transmission characteristic data is input into the transmission line equation group for electromagnetic field analysis to obtain the transmission characteristic function that describes the electromagnetic coupling behavior between adjacent units. This function is the core description of the transmission law of electrical signals in space, reflecting the signal interference or coupling phenomenon caused by the electromagnetic field between different units. The coupling relationship between the heat conduction characteristic function and the transmission characteristic function is modeled to form a unit-level thermal-electric coupling equation group. By constructing this equation group, the characteristics of heat transfer and electrical signal transmission are combined and integrated to describe the complex behavior of high-voltage connectors in dynamic environments. The unit-level thermal-electric coupling equation group is substituted into the energy conservation constraint condition for numerical solution. The energy conservation constraint ensures that the solution of the model can truly reflect the energy flow and conversion inside the high-voltage connector. In the process of numerical solution, the matrix calculation method is used to obtain the mapping matrix between the temperature node and the signal transmission node. Based on the mapping matrix, a thermal-electric coupling network model is constructed, which uniformly expresses the temperature distribution and signal transmission characteristics in the form of nodes and connection relationships.

[0029] Step 200: Separate and optimize the transmission characteristic function according to the thermal-electric coupling network model to obtain a temperature-transmission characteristic mapping relationship;

[0030] Specifically, a linear separation operation is performed on the heat conduction and electromagnetic field coupling relationships in the thermoelectric coupling network mathematical model. Through matrix decomposition or other numerical methods, the heat coupling relationship and the electromagnetic coupling relationship are decoupled, and the complex coupling network is split into independent heat network subsystems and electrical network subsystems. For the heat network subsystem, the temperature node data it contains is substituted into the heat conduction equation set for solution to predict the distribution characteristics of the temperature field at different nodes, and a prediction function describing the temperature field distribution is obtained. This prediction function not only contains the spatial variation information of the temperature but also can reflect its dynamic characteristics changing with time. At the same time, for the electrical network subsystem, a gain characteristic matrix and a phase response characteristic matrix are constructed based on the signal transmission parameters. These two matrices are respectively used to quantify the amplification or attenuation degree of the signal between different nodes and the phase change of the signal. Through this step, an initial transmission characteristic function is obtained. The transmission characteristic function is substituted into a non-linear optimizer for signal distortion minimization processing to obtain optimization constraint conditions. By analyzing the gain change and phase shift of the signal, the main sources of distortion are identified, and the optimization constraint conditions are set based on this. According to the optimization constraint conditions, an objective function is constructed, and boundary parameters are set in combination with the stability threshold of the system to ensure the physical meaning of the system during the optimization process and prevent the solution result from deviating from the actually achievable range. Based on the objective function and boundary parameters, an optimization iteration sequence is generated. To ensure that the optimization iteration sequence can quickly converge to the global optimal solution, the step size of the optimization algorithm is adaptively adjusted, and the convergence is dynamically judged. During the optimization process, the adaptive adjustment of the step size can adjust the search range according to the iteration convergence speed, thereby avoiding too slow convergence speed or falling into a local optimum. By monitoring the error change situation of each iteration step, it is judged whether the optimization goal of distortion minimization is achieved. When the optimization algorithm converges to the optimal solution, an optimal transmission characteristic function that satisfies distortion minimization is obtained. The correlation degree between the temperature field distribution prediction function and the optimal transmission characteristic function is calculated to reveal the influence law of temperature change on signal transmission characteristics. In the correlation degree calculation, a method based on statistical methods or physical models is used to map the dynamic changes of the temperature prediction function to the spatial and temporal distributions of the transmission characteristic function, and a temperature-transmission characteristic mapping relationship is obtained.

[0031] Step 300: Based on the temperature-transmission characteristic mapping relationship, perform Gaussian process regression calculation on the temperature time series data to obtain the statistical characteristics of the temperature dynamic characteristics;

[0032] It should be noted that a large amount of temperature change data collected during each working cycle of the high-voltage connector is screened and classified. The temperature time series data in the normal working state and the fault state are distinguished. During the screening process, based on the predefined temperature change pattern and historical operation records, abnormal or incomplete data are removed through rule matching or machine learning classification algorithms to ensure the quality and representativeness of the input data. The screened temperature time series data is preprocessed. The temperature data is denoised by the Gaussian filtering method to effectively remove the interference of random noise in the data while retaining the key trend information. The denoised data is centered and standardized to normalize the temperature data to a unified scale, eliminate the influence between data with different dimensions, and enhance the adaptability of the model to different data distributions. After completing the data preprocessing, the temperature-transmission characteristic mapping relationship is input into the normalized temperature data sequence as prior knowledge. Using this mapping relationship, the temperature change can be related to the signal transmission characteristics, constructing a high-dimensional feature space of temperature change to capture the complex non-linear correlation between temperature and transmission characteristics. In the high-dimensional feature space, the radial basis function transformation is performed on the temperature data to map the temperature time series data into the kernel space, enhancing the model's ability to capture non-linear patterns. After the transformation, the kernel function probability density matrix is obtained, which describes the distribution state of the temperature data in the feature space. To optimize the performance of the model, hyperparameter optimization is performed on the kernel function probability density matrix. By inputting it into the maximum likelihood estimation function, based on the actual situation of the data distribution, the optimal parameter set of the Gaussian process kernel function is determined. Based on the optimal parameter set, a Gaussian process model is established for the temperature change trajectory, and a multivariate Gaussian distribution function describing the dynamic characteristics of temperature is constructed. The multivariate Gaussian distribution function describes the trend and uncertainty of temperature change in the form of probability, capturing the distribution characteristics of temperature at different time points. The multivariate Gaussian distribution function is substituted into the temperature prediction model to calculate the mean and variance of the temperature change. The mean represents the main trend of the temperature change, while the variance reflects the uncertainty or fluctuation range of the temperature change. These statistical quantities together constitute the statistical characteristics of the temperature change. The coupling analysis is performed on the temperature change statistical characteristics and the temperature-transmission characteristic mapping relationship to reveal the dynamic impact of temperature change on the signal transmission characteristics, and the statistical characteristics of the temperature dynamic characteristics are obtained.

[0033] Step 400: Input the statistical characteristics of the temperature dynamic characteristics into the specified time-delay thermal management neural network for signal transmission delay prediction to obtain delay prediction characteristic parameters;

[0034] Specifically, data reconstruction is performed on the statistical features of the temperature dynamic characteristics, integrating various relevant information, and fusing the temperature change rate, temperature distribution characteristics, signal integrity index, and initial delay value into a multi-dimensional input data matrix. The multi-dimensional input data matrix is input into the thermal feature extraction layer of the specified time-delay thermal management neural network. The thermal feature extraction layer is the first layer of the neural network, which extracts key temperature-related features from the input data. This layer contains three core units: the temperature dynamic encoding unit, the heat conduction feature analysis unit, and the temperature fluctuation processing unit. The temperature dynamic encoding unit encodes the temperature change rate and distribution characteristics to extract key dynamic information related to time; the heat conduction feature analysis unit focuses on modeling the spatial characteristics of the temperature distribution and capturing the laws of heat conduction behavior; the temperature fluctuation processing unit analyzes short-term and long-term temperature fluctuations to extract stability and perturbation information. After being processed by the thermal feature extraction layer, a high-dimensional thermal management feature vector is generated. Temporal feature learning is performed on the thermal management feature vector. The temporal feature learning layer contains long short-term memory units, a time attention mechanism unit, and a temporal dependence modeling unit. The long short-term memory units capture feature changes over a long time span through their gating mechanism and can effectively extract the long-term dependence relationship between temperature dynamics and signal delay; the time attention mechanism unit identifies the time points most important for delay prediction by assigning weights to different time steps, enhancing the network's sensitivity to key time information; the temporal dependence modeling unit integrates the features of the time series to establish the global correlation between each time step. After being processed by the temporal feature learning layer, a feature matrix containing temporal correlations is generated. The temporal correlation feature matrix is input into the delay prediction backbone network layer. The delay prediction backbone network layer consists of a multi-head self-attention mechanism unit, a residual connection unit, and a specified time constraint unit. The multi-head self-attention mechanism unit can perform multi-perspective correlation analysis on the input data from different feature dimensions, enhancing the network's modeling ability for complex feature relationships; the residual connection unit adds skip connections to the network structure to avoid the problem of gradient disappearance and improve the training efficiency of the model; the specified time constraint unit ensures that the prediction results conform to the time range of the system's physical characteristics by adding time constraint conditions. After being processed by the delay prediction backbone network layer, an initial delay prediction result is obtained. Temperature compensation is performed on the initial delay prediction result. The temperature compensation layer contains a temperature perturbation analysis unit, a non-linear compensation unit, and a dynamic correction unit. The temperature perturbation analysis unit analyzes the short-term fluctuations of temperature changes to identify the temperature change factors that have an important impact on delay prediction; the non-linear compensation unit corrects the complex temperature effects that cannot be captured by a simple linear model by introducing non-linear functions; the dynamic correction unit adjusts the prediction result according to real-time temperature data to improve the accuracy of delay prediction. After being processed by this layer, the compensated delay prediction value is obtained. The compensated delay prediction value is input into the multi-task learning layer to simultaneously achieve delay prediction, temperature prediction, and system stability evaluation.The multi-task learning layer completes the comprehensive analysis of transmission delay, temperature change trend, and system operating status through the delay prediction branch, temperature prediction branch, and stability evaluation branch respectively. Each branch independently optimizes its task objective while sharing the underlying feature representation to improve the overall performance of the model. Through this step, a feature set containing multi-dimensional prediction features is generated. Feature fusion processing is performed on the multi-dimensional prediction feature set. The feature fusion layer includes a cross-modal feature fusion unit, an adaptive weight allocation unit, and a global information aggregation unit. The cross-modal feature fusion unit captures the correlation information between delay, temperature, and stability by fusing the features of different branches; the adaptive weight allocation unit dynamically adjusts its weight according to the contribution of each feature to the final prediction; and the global information aggregation unit generates the final delay prediction feature parameters by integrating all feature information.

[0035] Step 500: Calculate the weighted error value in the transmission feature space based on the delay prediction feature parameters, and dynamically adjust the signal transmission delay to obtain the compensated signal transmission delay parameter.

[0036] Specifically, perform a transmission feature space mapping on the delay prediction feature parameters. The delay prediction feature parameters include delay error, temperature influence, and signal integrity features, and these pieces of information jointly describe the multiple influences suffered during the signal transmission process of the high-voltage connector. By constructing a transmission feature space, map these influence features into a unified multi-dimensional space. Within the transmission feature space, establish a weighted error calculation model for quantifying the relationship between the delay error and other key features. The weighted error calculation model assigns weights to different feature dimensions to reflect the relative importance of each feature to the transmission delay. This model can capture the main sources of the delay error and quantify the specific impacts of temperature changes and signal integrity on the transmission performance. Through this model, perform an error analysis on the transmission feature space. Calculate the weighted coefficients of each feature dimension by the least squares method to obtain the weighted error value. The least squares method ensures that the weighted error value can accurately reflect the actual error situation in the transmission feature space by minimizing the deviation between the weighted error and the real data. Perform three-layer Bayesian inference on the weighted error value and the delay prediction feature parameters. Bayesian inference incorporates uncertainty into the calculation by introducing prior knowledge to better predict the compensation strategy parameters. The first layer of the three-layer Bayesian inference constructs a preliminary parameter distribution model by analyzing the direct relationship between the weighted error value and the delay prediction feature parameters; the second layer updates the parameter distribution model to be closer to the actual situation by considering the mutual influences between different features; the third layer forms an optimized set of compensation strategy parameters from a global perspective by combining the results of multi-layer inference, which includes a dynamic adjustment scheme for the delay error and reflects the compensation priorities under the system operating state. Perform Gibbs sampling and variational inference calculations based on the set of compensation strategy parameters. Through the sampling and inference methods, optimize the probability distribution of the delay compensation amount. As a Markov chain Monte Carlo method, Gibbs sampling can generate a globally optimal parameter distribution by sampling the conditional distribution of each parameter one by one; variational inference accelerates the convergence process of parameter optimization by maximizing an approximate form of the posterior distribution. The two methods are used in combination to efficiently optimize the delay compensation amount to meet the actual requirements in the complex dynamic environment of the high-voltage connector. Through the above steps, obtain the compensated signal transmission time delay parameters. These parameters reflect the current state of signal transmission and effectively reduce the impact of delay error on the system performance through dynamic adjustment.

[0037] The weighted error value and the delay prediction feature parameters are input into the first-layer Bayesian inferencer for the calculation of distribution parameters. The inferencer uses the input error value and feature parameters to establish a probability distribution model of the delay error. This probability distribution, through the comprehensive analysis of historical data and real-time measurement data, characterizes the likelihood distribution characteristics of the delay error under different conditions, providing a preliminary statistical description for the compensation strategy. A variational inference operation is performed on the probability distribution of the delay error, and the distribution parameters are optimized by maximizing the posterior probability to obtain the initial distribution parameters for delay compensation, including the mean, variance of the delay error, and potential uncertainty factors. The initial distribution parameters for delay compensation and the temperature influence characteristics are input into the second-layer Bayesian inferencer for the calculation of the joint distribution. Through joint modeling, the interaction relationship between the delay compensation parameters and the temperature influence characteristics is captured. The influence of temperature on the delay is non-linear and has dynamic change characteristics. Through Bayesian inference, the adjustment effect of temperature change on the delay error is incorporated into the joint distribution to generate a temperature-delay probability function, which describes the likelihood distribution of delay compensation under different temperature conditions, providing a theoretical basis for the adjustment of the system in a dynamic environment. A transition probability matrix is constructed for the temperature-delay probability function. The transition probability matrix is an important tool for describing the state change of the system. By analyzing the transition law of the delay state caused by temperature change, the dynamic influence of temperature on delay compensation can be quantified. The state transition matrix and the signal integrity index are input into the third-layer Bayesian inferencer for the construction of the probability field. The Bayesian inferencer combines the state transition matrix with the signal integrity features to generate a Markov random field structure. This random field describes the interdependence between various states in the form of a graph model, enabling the system to capture the comprehensive influence of signal integrity on the delay state transition from a global perspective. Conditional probability sampling is performed on the Markov random field to obtain a sequence of state transition probabilities. Conditional probability sampling calculates the probability of the current state under the condition of fixing other states, gradually generating a series of possible state transition paths. These paths reflect the dynamic behavior of the system under different input conditions. Based on the sequence of state transition probabilities, an expectation-maximization calculation is performed to obtain the final set of compensation strategy parameters. The expectation-maximization calculation weights and sums the probabilities of the state transition paths and selects the set of strategy parameters that maximizes the expectation, ensuring that the compensation strategy is optimal within the global scope. The set of compensation strategy parameters contains the optimal compensation schemes for different temperature changes and signal states, and can dynamically adjust the delay compensation to adapt to the complex working environment of the high-voltage connector.

[0038] In the embodiments of the present application, by establishing a thermal-electrical coupling network model including temperature nodes and signal transmission nodes, an accurate description of the thermal-electrical coupling characteristics of high-voltage connectors is achieved. The non-linear thermal-electrical separation network optimization method is adopted to effectively extract the mapping relationship between the temperature field distribution and signal transmission characteristics, reduce the complexity of the model, and improve the calculation efficiency. The temperature dynamic characteristic identification method based on Gaussian process regression accurately captures the temperature change law and provides reliable temperature characteristic input for delay prediction. A thermal management neural network structure with a specified time delay is proposed, and through multi-level feature extraction and fusion, accurate prediction of signal transmission delay is achieved. The three-layer Bayesian inference algorithm is used to optimize the delay compensation strategy, significantly improving the accuracy and robustness of the compensation effect.

[0039] In a specific embodiment, the process of executing step 100 may specifically include the following steps:

[0040] Perform equally spaced grid division on the physical structure of the high-voltage connector to obtain a number of standard units containing temperature monitoring points and signal monitoring points;

[0041] Perform temperature sampling on the temperature monitoring points in the standard units, and calculate the temperature gradient based on the heat conduction equation for the sampled data to obtain the temperature distribution data of each standard unit;

[0042] Input the temperature distribution data into the heat conduction differential equations for heat conduction characteristic analysis to obtain the heat conduction characteristic function describing the heat exchange between adjacent units;

[0043] Perform signal amplitude, phase, and time delay sampling on the signal monitoring points in the standard units, and calculate the signal characteristics based on the transmission line equation for the sampled data to obtain the electrical signal transmission characteristic data of each standard unit;

[0044] Input the electrical signal transmission characteristic data into the transmission line equations for electromagnetic field analysis to obtain the transmission characteristic function describing the electromagnetic coupling between adjacent units, and establish a coupling relationship model for the heat conduction characteristic function and the transmission characteristic function to obtain the unit-level thermal-electrical coupling equations;

[0045] Substitute the unit-level thermal-electrical coupling equations into the energy conservation constraint conditions for numerical solution to obtain the mapping matrix between the temperature nodes and signal transmission nodes, and construct a thermal-electrical coupling network model based on the mapping matrix.

[0046] Specifically, equally spaced grid division is performed on the physical structure of the high-voltage connector by the finite element analysis method. Assume the length of the connector is 、width is 、height is , divide it into a three-dimensional grid of , each grid is called a standard unit, and the size is , where , , . In each unit, temperature monitoring points and signal monitoring points are arranged. The temperature monitoring points are used to collect thermal characteristic data, and the signal monitoring points are used to obtain the electrical signal transmission characteristics. Temperature sampling is performed on the temperature monitoring points in the standard unit to obtain the temperature distribution data during the operation of the high-voltage connector. Suppose in a certain unit , the collected temperature is , representing the temperature value at time . Based on the heat conduction equation, the temperature gradient of each unit is calculated. The basic form of the heat conduction equation is:

[0047] ;

[0048] where, is the material density, is the specific heat capacity, is the thermal conductivity, is the temperature, is the heat source term per unit volume. By performing numerical calculations on the sampled data in space and time, the temperature gradient is obtained, thereby describing the distribution and change of heat in the unit. The calculated temperature gradient is input into the heat conduction differential equations for heat conduction characteristic analysis to quantify the heat exchange between adjacent units. For two adjacent units and , the heat exchange is represented by the heat conduction characteristic function , and its expression is:

[0049] ;

[0050] where, is the temperature difference between the two units, is the distance between the centers of the two units, is the heat conduction area, is the thermal conductivity. By performing similar calculations on all units, the heat conduction characteristic function matrix of the entire system is obtained, describing the heat transfer relationship between each unit and its neighboring units. At the same time, signal amplitude, phase, and time delay sampling are performed on the signal monitoring points in the standard unit. Suppose in unit , the sampled signal amplitude is , the phase is , and the time delay is . Based on the transmission line equation, the signal characteristics within the unit are calculated. The form of the transmission line equation is:

[0051] ;

[0052] wherein, is the voltage, is the current, is the inductance per unit length, is the capacitance per unit length. By solving these equations, the characteristic data of the signal in the unit is obtained, such as the propagation speed, reflection coefficient, and attenuation rate. The signal transmission characteristic data is input into the transmission line equations for electromagnetic field analysis to calculate the electromagnetic coupling characteristics between adjacent units. For two adjacent units and , the electromagnetic coupling is represented by the transmission characteristic function , and its form is:

[0053] ;

[0054] wherein, is the voltage difference, is the signal propagation time, is the characteristic impedance. By calculating the transmission characteristic function matrix of the entire system, the electromagnetic coupling relationship between all units is described. After obtaining the heat conduction characteristic function matrix and the transmission characteristic function matrix , they are coupled and modeled to form the unit-level thermal-electrical coupling equations. The form of the coupling equations is:

[0055] ;

[0056] wherein, is the coupling matrix, is the coupling coefficient, which is used to balance the influence of thermal effects and electromagnetic effects. Substitute the unit-level thermal-electrical coupling equations into the energy conservation constraint conditions for numerical solution to ensure that the system satisfies heat and energy conservation. The energy conservation constraint conditions are expressed as:

[0057] ;

[0058] By solving this set of equations, the mapping matrix between the temperature nodes and the signal transmission nodes is obtained. Each column of this matrix represents the coupling relationship between the temperature of a certain node and the signal characteristics. Based on the mapping matrix , a thermal-electrical coupling network model is constructed. This model takes the temperature nodes and the signal transmission nodes as basic units, and describes the thermal-electrical characteristics of the entire high-voltage connector through the mapping relationship.

[0059] In a specific embodiment, the process of executing step 200 may specifically include the following steps:

[0060] Perform a linear separation operation on the coupling relationship between heat conduction and electromagnetic fields in the mathematical model of the thermoelectric coupling network to obtain a heat network subsystem and an electrical network subsystem;

[0061] Substitute the temperature node data in the heat network subsystem into the heat conduction equations for solution to obtain a prediction function describing the temperature field distribution, and construct a gain characteristic matrix and a phase response characteristic matrix for the signal transmission parameters in the electrical network subsystem to obtain a transmission characteristic function;

[0062] Substitute the transmission characteristic function into a non-linear optimizer for signal distortion minimization to obtain optimization constraint conditions, construct an objective function for the optimization constraint conditions, and set boundary parameters based on the system stability threshold to obtain an optimization iteration sequence;

[0063] Perform step-size adaptive adjustment and convergence judgment on the optimization iteration sequence to obtain an optimal transmission characteristic function that satisfies distortion minimization, and calculate the correlation degree between the temperature field distribution prediction function and the optimal transmission characteristic function to obtain a temperature-transmission characteristic mapping relationship.

[0064] Specifically, the mathematical model of the thermoelectric coupling network is obtained through physical modeling and includes the relationship between heat conduction and electromagnetic field interaction. Its basic form is expressed as the following coupling equations:

[0065] ;

[0066] Among them, represents the coupling matrix, represents the heat network characteristic matrix, represents the electrical network characteristic matrix, is the thermoelectric coupling coefficient, indicating the degree of influence of heat conduction on signal characteristics. The goal of the linear separation operation is to separate and solve these two subsystems independently. By means of matrix decomposition methods such as eigenvalue decomposition or singular value decomposition, the coupling matrix is disassembled into a heat network subsystem and an electrical network subsystem, thus obtaining:

[0067] ;

[0068] Among them, and respectively describe the behaviors when heat conduction and electrical signal characteristics exist independently. For the heat network subsystem, substitute its temperature node data into the heat conduction equations for solution. The basic form of the heat conduction equations is:

[0069] ;

[0070] Among them, is the density, is the specific heat capacity, is the thermal conductivity, is the temperature, is the heat source term per unit volume. Assuming that the temperature node data varies with time By using the finite difference method or the finite element method, this partial differential equation is numerically solved to obtain a prediction function describing the temperature field distribution, where represents the spatial coordinates. At the same time, a gain characteristic matrix and a phase response characteristic matrix are constructed for the signal transmission parameters of the electrical network subsystem. The gain characteristic matrix describes the amplification or attenuation of the signal between nodes and node , and its basic form is:

[0071] ;

[0072] where, and represent the voltages of nodes and node respectively. The phase response characteristic matrix represents the phase change of the signal during transmission and is defined as:

[0073] ;

[0074] By combining the gain characteristic matrix and the phase response characteristic matrix, a transmission characteristic function is constructed, where represents the signal frequency. The transmission characteristic function is substituted into the non - linear optimizer for signal distortion minimization. The main sources of distortion include amplitude distortion and phase distortion, and the goal is to minimize the following objective function:

[0075] ;

[0076] where, and are the measured values respectively, and are the calculated values respectively. By setting optimization constraints (such as system stability thresholds) and boundary parameters (such as signal power ranges), an optimization iteration sequence is constructed. During the optimization iteration process, through a step - size adaptive adjustment method (such as the Adam optimization algorithm), the update step - size is adjusted according to the current gradient change, thereby accelerating convergence. At the same time, through a convergence judgment condition (such as the change of the objective function is less than a preset threshold), it is ensured that the iteration result reaches the optimal solution. The optimization process obtains an optimal transmission characteristic function that satisfies distortion minimization. The temperature field distribution prediction function and the optimal transmission characteristic function Perform correlation calculation to establish the temperature-transmission characteristic mapping relationship. This process is achieved by calculating the correlation coefficient matrix between the two:

[0077] ;

[0078] Among them, represents the covariance of temperature nodes and , and respectively represent the standard deviations of temperature nodes and . The correlation coefficient matrix describes the coupling strength between temperature changes and signal characteristics, thus forming a complete temperature-transmission characteristic mapping relationship.

[0079] In a specific embodiment, the process of executing step 300 may specifically include the following steps:

[0080] Screen and classify the temperature change data collected by the high-voltage connector in each working cycle to obtain temperature time series data including normal working conditions and fault conditions;

[0081] Perform Gaussian filtering denoising and centralization normalization processing on the temperature time series data to obtain a normalized temperature data sequence, and input the temperature-transmission characteristic mapping relationship as prior knowledge into the normalized temperature data sequence to obtain a high-dimensional feature space of temperature changes;

[0082] Perform radial basis function transformation and eigen-decomposition on the temperature data in the high-dimensional feature space to obtain a kernel function probability density matrix, and input the kernel function probability density matrix into the maximum likelihood estimation function for hyperparameter optimization to obtain the optimal parameter set of the Gaussian process kernel function;

[0083] Based on the optimal parameter set, perform Gaussian process modeling on the temperature change trajectory to obtain a multivariate Gaussian distribution function describing the dynamic characteristics of temperature, and substitute the multivariate Gaussian distribution function into the temperature prediction model for mean and variance calculation to obtain temperature change statistics;

[0084] Perform coupling analysis on the temperature change statistics and the temperature-transmission characteristic mapping relationship to obtain the statistical characteristics of the temperature dynamic characteristics.

[0085] Specifically, screen and classify the temperature change data collected by the high-voltage connector in multiple working cycles. Assume that the collected temperature time series data is , where represents the temperature value of the th monitoring point at time , is the total number of monitoring points. By analyzing the stability and trend of the data, it is divided into normal working state and fault state. Under the normal working state, the temperature data shows relatively stable with a small fluctuation range, while the fault state is usually accompanied by drastic abnormal temperature changes. Using rule definition or supervised learning methods, the data is labeled as and , representing the time series under normal and fault states respectively. Gaussian filtering is performed on the filtered temperature time series data to eliminate the random noise existing in the acquisition process. The process of Gaussian filtering is achieved through convolution operation, and the filtered data represents the smoothed temperature time series. After filtering, the data is centered and standardized to obtain the normalized temperature data sequence . The standardization formula is:

[0086] ;

[0087] where and represent the mean and standard deviation of the sequence respectively. The roles of centering and standardization are to eliminate the differences in temperature ranges and scales of different monitoring points, making the data more suitable for subsequent modeling and analysis. On this basis, the temperature-transmission feature mapping relationship is input into the normalized temperature data sequence as prior knowledge to construct a high-dimensional feature space. The temperature-transmission feature mapping relationship describes the influence of temperature change on the signal characteristics , and its expression form is:

[0088] ;

[0089] where represents the mapping function. By embedding this relationship into the normalized temperature sequence, a high-dimensional feature space containing temperature change features and signal influence features is generated. Radial basis function transformation and feature decomposition are performed on the temperature data in the high-dimensional feature space. The mathematical form of the radial basis function is:

[0090] ;

[0091] where represents the feature vectors of two data points, is the scale parameter of the kernel function. Through the radial basis function transformation, the original features are mapped into a higher-dimensional feature space to capture the non-linear relationship. Feature decomposition is performed to extract the main features, generating the kernel function probability density matrix , whose element represents the data points and Similarity. The kernel function probability density matrix is input into the maximum likelihood estimation function for hyperparameter optimization to determine the optimal parameter set of the Gaussian process kernel function. The goal of maximum likelihood estimation is to maximize the following log-likelihood function:

[0092] ;

[0093] where, is the temperature data vector, is the position vector in the feature space, is the hyperparameter of the kernel function, is the kernel function matrix, is the number of data points. By optimizing , the optimal kernel function parameter set describing the temperature change characteristics is obtained. Based on the optimal parameter set, Gaussian process modeling is performed on the temperature change trajectory. The multivariate Gaussian distribution function generated by Gaussian process modeling is:

[0094] ;

[0095] where, is the mean function of temperature, is the kernel matrix. By calculating the mean and variance of this distribution function, the statistics and of temperature change are obtained, representing the expectation and uncertainty of temperature respectively. The coupling analysis is performed on the temperature change statistics and the temperature-transmission characteristic mapping relationship. By calculating the correlation index between the two, such as the Pearson correlation coefficient, the dynamic influence of temperature change on signal characteristics is quantitatively described, and the statistical characteristics

[0096] of temperature dynamics are obtained. In a specific embodiment, the process of executing step 400 may specifically include the following steps:

[0097] Perform data reconstruction on the statistical characteristics of temperature dynamics to obtain a multi-dimensional input data matrix including the temperature change rate, temperature distribution characteristics, signal integrity index, and initial delay value;

[0098] Input the multi-dimensional input data matrix into the thermal feature extraction layer of the specified time-delay thermal management neural network. The thermal feature extraction layer includes a temperature dynamics encoding unit, a heat conduction feature analysis unit, and a temperature fluctuation processing unit to obtain a thermal management feature vector;

[0099] Perform processing on the thermal management feature vector by the temporal feature learning layer. The temporal feature learning layer includes a long short-term memory unit, a time attention mechanism unit, and a temporal dependence modeling unit to obtain a temporal correlation feature matrix;

[0100] Input the time-series correlation feature matrix into the delay prediction backbone network layer, which includes a multi-head self-attention mechanism unit, a residual connection unit, and a specified time constraint unit, to obtain an initial delay prediction result;

[0101] Process the initial delay prediction result through a temperature compensation layer, which includes a temperature perturbation analysis unit, a non-linear compensation unit, and a dynamic correction unit, to obtain a compensated delay prediction value;

[0102] Input the compensated delay prediction value into the multi-task learning layer, which includes a delay prediction branch, a temperature prediction branch, and a stability evaluation branch, to obtain a multi-dimensional prediction feature set;

[0103] Process the multi-dimensional prediction feature set through a feature fusion layer, which includes a cross-modal feature fusion unit, an adaptive weight allocation unit, and a global information aggregation unit, to obtain delay prediction feature parameters.

[0104] Specifically, perform data reconstruction on the statistical features of temperature dynamic characteristics and convert them into a multi-dimensional input data matrix suitable for neural network processing. Assume that the statistical features of temperature dynamic characteristics include the temperature change rate (describing the rate of change of temperature over time), the temperature distribution feature (describing the temperature distribution in space), the signal integrity index (measuring the quality of signal transmission, such as bit error rate or signal strength), and the initial delay value (representing the initial time delay of the signal under the current conditions). These features are combined to form a multi-dimensional input data matrix where:

[0105] ;

[0106] where is the number of sampling points, and each row of the matrix represents the multi-dimensional features of a sampling point. Input the constructed multi-dimensional input data matrix into the thermal feature extraction layer of the specified time delay thermal management neural network. In the thermal feature extraction layer, the temperature dynamic encoding unit encodes the input features and to generate feature vectors of temperature changes in time and space; the heat conduction feature analysis unit converts the temperature distribution feature into features that can reflect the heat flow behavior through simulating the heat conduction process; the temperature fluctuation processing unit analyzes the temperature change rate and the fluctuation amplitude to extract short-term temperature fluctuation characteristics. Assume that the thermal management feature vector is , which is generated from the output of the extraction layer:

[0107] ;

[0108] wherein represents the non - linear mapping function of the thermal feature extraction layer. The thermal management feature vector is input into the temporal feature learning layer. This layer includes long short - term memory units (LSTM), a temporal attention mechanism unit, and a temporal dependence modeling unit, which are used to learn the temporal relationship between temperature dynamic characteristics and signal delay. The LSTM remembers important features within a long time span through a gating mechanism and generates a time - series output , and its formula is:

[0109] ;

[0110] where and are the weight matrix and bias of the LSTM, and © represents element - wise multiplication. The temporal attention mechanism unit assigns weights to different time steps to strengthen the information at key time points. The temporal dependence modeling unit generates a temporal correlation feature matrix by constructing a global time dependence relationship . The temporal correlation feature matrix is input into the delay prediction backbone network layer, which includes a multi - head self - attention mechanism unit, a residual connection unit, and a specified time constraint unit. The multi - head self - attention mechanism is calculated by the following formula:

[0111] ;

[0112] where are the query, key, and value matrices, is the dimension of the key. The residual connection unit prevents gradient vanishing by adding skip connections and enhances the stability of training, while the specified time constraint unit ensures that the prediction result meets the system physical constraints. The output of the delay prediction backbone network is the initial delay prediction result, which is input into the temperature compensation layer for processing. The temperature compensation layer includes a temperature perturbation analysis unit (analyzing the short - term impact of temperature on delay), a non - linear compensation unit (introducing a non - linear function to correct the deviation), and a dynamic correction unit (updating the prediction result according to real - time temperature data). After processing by this layer, the compensated delay prediction value . Take The input multi-task learning layer includes a delay prediction branch, a temperature prediction branch, and a stability evaluation branch. The delay prediction branch generates the final delay prediction result. The temperature prediction branch is used to predict the future temperature change trend, while the stability evaluation branch evaluates the operating state of the system. The output of the multi-task learning layer is a multi-dimensional prediction feature set. The multi-dimensional prediction feature set is processed by a feature fusion layer, which includes a cross-modal feature fusion unit (integrating features of different modalities), an adaptive weight allocation unit (dynamically adjusting the feature importance weights), and a global information aggregation unit (extracting global features). The output after fusion is the delay prediction feature parameter, which is used for the dynamic adjustment and fault prediction of the high-voltage connector.

[0113] In a specific embodiment, the process of executing step 500 may specifically include the following steps:

[0114] Perform a transmission feature space mapping on the delay prediction feature parameter, and construct a weighted error calculation model for the delay error, temperature influence, and signal integrity feature;

[0115] Based on the weighted error calculation model, perform an error analysis on the transmission feature space, calculate the weighted coefficients of each feature dimension by the least squares method, and obtain the weighted error value in the transmission feature space;

[0116] Perform three-layer Bayesian inference on the weighted error value and the delay prediction feature parameter to obtain a compensation strategy parameter set;

[0117] Based on the compensation strategy parameter set, perform Gibbs sampling and variational inference calculations to optimize the probability distribution of the delay compensation amount, and obtain the compensated signal transmission delay parameter.

[0118] Specifically, perform a transmission feature space mapping on the delay prediction feature parameter. Assume that the delay prediction feature parameter includes the delay error , temperature influence , and signal integrity feature . These parameters jointly describe the characteristic changes of signal transmission. By defining a mapping function , transform the above parameters into a position vector in the transmission feature space, and its form is:

[0119] ;

[0120] where is a point in the feature space for subsequent calculation and analysis. After obtaining the transmission feature space representation, construct a weighted error calculation model to quantify the error value. Assume that the error function is expressed as:

[0121] ;

[0122] where Represents the total error value, is the weighting coefficient for the corresponding feature dimension. These weighting coefficients are calculated by the least squares method to minimize the deviation between the error model and the actual data. The least squares objective function is:

[0123] ;

[0124] where is the number of samples, is the th actual error value of the sample. The above objective function is differentiated and the derivative is set to zero to solve for the weighting coefficients:

[0125] ;

[0126] where , is the input feature matrix, is the error vector. Based on the calculated weighted error values and combined with the delay prediction feature parameters, three-layer Bayesian inference is performed to determine the compensation strategy parameter set. In the first layer of Bayesian inference, a probability distribution model of the delay error is constructed using the weighted error values. Assuming that the delay error follows a normal distribution, its probability density function is:

[0127] ;

[0128] where and are the mean and variance of the distribution. By maximizing the posterior probability, and are optimized to obtain the initial distribution parameters for delay compensation. In the second layer of Bayesian inference, the initial distribution parameters for delay compensation are jointly modeled with the temperature influence features to construct a temperature-delay joint probability distribution:

[0129] ;

[0130] By introducing the transition probability matrix , the dynamic influence of different temperature states on delay compensation is characterized:

[0131] ;

[0132] where represents the probability of transitioning from temperature state to state . In the third layer of Bayesian inference, combined with the signal integrity feature , a Markov random field is constructed to describe the dependence relationship between global features. The joint probability distribution of the random field is expressed as:

[0133] ;

[0134] wherein and are the edge potential function and the node potential function respectively. Through conditional probability sampling, a state transition sequence of the delay compensation strategy is generated. Using the compensation strategy parameter set, Gibbs sampling and variational inference calculations are performed on the delay compensation amount, so as to optimize the probability distribution of the compensation amount. Gibbs sampling gradually updates the conditional distribution of each parameter through the following iterative formula:

[0135] ;

[0136] Variational inference optimizes the distribution parameters by maximizing the variational lower bound :

[0137] ;

[0138] wherein is the approximate distribution. By combining Gibbs sampling and variational inference, the compensated signal transmission delay parameters are obtained.

[0139] In a specific embodiment, the process of performing three-layer Bayesian inference on the weighted error value and the delay prediction feature parameters to obtain the compensation strategy parameter set may specifically include the following steps:

[0140] Input the weighted error value and the delay prediction feature parameters into the first-layer Bayesian inference engine for distribution parameter calculation to obtain the delay error probability distribution, and perform variational inference operation on the delay error probability distribution to obtain the initial distribution parameters of the delay compensation;

[0141] Input the initial distribution parameters of the delay compensation and the temperature influence feature into the second-layer Bayesian inference engine for joint distribution calculation to obtain the temperature-delay probability function, and construct a transition probability matrix for the temperature-delay probability function to obtain the state transition matrix;

[0142] Input the state transition matrix and the signal integrity index into the third-layer Bayesian inference engine for probability field construction to obtain the Markov random field structure, and perform conditional probability sampling on the Markov random field structure to obtain the state transition probability sequence;

[0143] Based on the state transition probability sequence, maximum expectation calculation is performed to obtain the compensation strategy parameter set.

[0144] Specifically, the weighted error value and the delay prediction feature parameters (including the delay error , the temperature influence feature and the signal integrity index )Input the first-layer Bayesian inferencer to calculate the distribution parameters. Assume that the delay error follows a normal distribution, and its probability density function is expressed as:

[0145] ;

[0146] where and are the distribution parameters to be inferred, representing the mean and variance of the delay error respectively. By maximizing the posterior probability , the initial estimate of the delay error probability distribution is obtained. In the calculation of the posterior probability, prior assumptions of the normal distribution are added, such as and Inv-Gamma , and the posterior form is:

[0147] ;

[0148] Based on the initially calculated delay error probability distribution, optimize the distribution parameters through variational inference. The goal of variational inference is to maximize the variational lower bound (ELBO):

[0149] ;

[0150] where is the approximate distribution, and the initial distribution parameters for delay compensation are obtained by optimizing the parameters of . Input the initial distribution parameters for delay compensation and the temperature influence characteristics into the second-layer Bayesian inferencer to perform the calculation of the joint distribution. The joint distribution function represents the relationship between delay compensation and temperature characteristics, and is decomposed into the product of conditional probability and marginal probability:

[0151] ;

[0152] To characterize the dynamic behavior of the system under different temperature states, construct the temperature-delay transition probability matrix , where each element represents the probability of transitioning from temperature state to state , and is defined as:

[0153] ;

[0154] Estimate the transition probability by analyzing the state change patterns in historical data. In the third-layer Bayesian inference, combine the state transition matrix with the signal integrity index to construct a Markov random field (MRF). The joint probability distribution form of the MRF is:

[0155] ;

[0156] Among them, is the potential function between nodes, is the potential function of the node itself. Through conditional probability sampling, a state transition probability sequence is generated, and its recurrence form is:

[0157] ;

[0158] Based on the state transition probability sequence, the maximum expectation algorithm (EM) is used to calculate the final compensation strategy parameter set. The E-step of the EM algorithm updates the objective function by calculating the expected value under the current parameters:

[0159] ;

[0160] The M-step updates the parameters by maximizing the function:

[0161] ;

[0162] After iterative optimization, the optimized compensation strategy parameter set is finally obtained.

[0163] The above describes the high-voltage connector fault prediction method based on thermal management in the embodiments of the present application. Next, the high-voltage connector fault prediction system 10 based on thermal management in the embodiments of the present application will be described. Please refer to Figure 2 , an embodiment of the high-voltage connector fault prediction system 10 based on thermal management in the embodiments of the present application includes:

[0164] An acquisition module 11, configured to acquire temperature distribution data and electrical signal transmission characteristic data of the high-voltage connector, and establish a thermal-electrical coupling network model including temperature nodes and signal transmission nodes;

[0165] A separation and optimization module 12, configured to separate and optimize the transmission characteristic function according to the thermal-electrical coupling network model to obtain a temperature-transmission characteristic mapping relationship;

[0166] A regression calculation module 13, configured to perform Gaussian process regression calculation on the temperature time series data based on the temperature-transmission characteristic mapping relationship to obtain temperature dynamic characteristic statistical features;

[0167] A delay prediction module 14, configured to input the temperature dynamic characteristic statistical features into a specified time-delay thermal management neural network for signal transmission delay prediction to obtain delay prediction characteristic parameters;

[0168] The dynamic adjustment module 15 is used to calculate the weighted error value in the transmission feature space according to the delay prediction feature parameters, and dynamically adjust the signal transmission delay to obtain the compensated signal transmission delay parameter.

[0169] Through the collaborative cooperation of the above-mentioned various components, by establishing a thermal-electrical coupling network model including temperature nodes and signal transmission nodes, an accurate description of the thermal-electrical coupling characteristics of the high-voltage connector is achieved. Using the non-linear thermal-electrical separation network optimization method, the mapping relationship between the temperature field distribution and the signal transmission characteristics is effectively extracted, reducing the complexity of the model and improving the calculation efficiency. The temperature dynamic characteristic identification method based on Gaussian process regression accurately captures the temperature change law, providing reliable temperature feature input for delay prediction. A thermal management neural network structure with a specified time delay is proposed, and through multi-level feature extraction and fusion, an accurate prediction of the signal transmission delay is achieved. The three-layer Bayesian inference algorithm is used to optimize the delay compensation strategy, significantly improving the accuracy and robustness of the compensation effect.

[0170] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the above-described systems, systems, and units can refer to the corresponding processes in the foregoing method embodiments and will not be described herein again.

[0171] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing an electronic device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0172] The above is the case. The above embodiments are only used to illustrate the technical solutions of this application and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments or perform equivalent replacements for some of the technical features. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the various embodiments of this application.

Claims

1. A high voltage connector fault prediction method based on thermal management, characterized in that: The method comprises: Collect temperature distribution data and electrical signal transmission characteristic data of high-voltage connectors, and establish a thermal-electric coupling network model including temperature nodes and signal transmission nodes; According to the thermal-electric coupling network model, the transmission characteristic function is separated and optimized to obtain a temperature-transmission characteristic mapping relationship; Based on the temperature-transmission characteristic mapping relationship, Gaussian process regression calculation is performed on the temperature time series data to obtain the statistical characteristics of the temperature dynamic characteristics; Inputting the temperature dynamic characteristic statistical features into a specified time delay thermal management neural network to predict signal transmission delay, and obtaining delay prediction characteristic parameters; The weighted error value in the transmission feature space is calculated according to the delay prediction characteristic parameter, and the signal transmission delay is dynamically adjusted to obtain the compensated signal transmission delay parameter.

2. The high voltage connector fault prediction method based on thermal management according to claim 1, characterized in that: The method collects temperature distribution data and electrical signal transmission characteristic data of the high-voltage connector and establishes a thermal-electric coupling network model including temperature nodes and signal transmission nodes, including: The physical structure of the high-voltage connector is divided into equally spaced grids to obtain several standard units including temperature monitoring points and signal monitoring points; Performing temperature sampling on the temperature monitoring points in the standard unit, and calculating the temperature gradient of the sampled data based on the heat conduction equation to obtain the temperature distribution data of each standard unit; Inputting the temperature distribution data into a heat conduction differential equation group to perform heat conduction characteristic analysis to obtain a heat conduction characteristic function describing heat exchange between adjacent units; Sampling the signal amplitude, phase and delay of the signal monitoring points in the standard unit, and calculating the signal characteristics of the sampled data based on the transmission line equation to obtain the electrical signal transmission characteristic data of each standard unit; Inputting the electrical signal transmission characteristic data into the transmission line equation group to perform electromagnetic field analysis, obtaining a transmission characteristic function describing electromagnetic coupling between adjacent units, and modeling the coupling relationship between the heat conduction characteristic function and the transmission characteristic function to obtain a unit-level thermal-electric coupling equation group; The unit-level thermal-electric coupling equations are substituted into the energy conservation constraint conditions for numerical solution to obtain a mapping matrix between temperature nodes and signal transmission nodes, and a thermal-electric coupling network model is constructed based on the mapping matrix.

3. The high voltage connector fault prediction method based on thermal management according to claim 2, characterized in that: The separation and optimization of the transmission characteristic function according to the thermal-electric coupling network model to obtain a temperature-transmission characteristic mapping relationship includes: Performing linear separation operation on the heat conduction and electromagnetic field coupling relationship of the thermal-electric coupling network model to obtain a thermal network subsystem and an electrical network subsystem; Substituting the temperature node data in the thermal network subsystem into the heat conduction equation group for solving, obtaining a prediction function describing the temperature field distribution, and constructing a gain characteristic matrix and a phase response characteristic matrix for the signal transmission parameters in the electrical network subsystem to obtain a transmission characteristic function; Substituting the transmission characteristic function into a nonlinear optimizer to perform signal distortion minimization processing to obtain optimization constraints, constructing an objective function for the optimization constraints, and setting boundary parameters based on a system stability threshold to obtain an optimization iteration sequence; The step size of the optimization iteration sequence is adaptively adjusted and the convergence is judged to obtain the optimal transmission characteristic function that satisfies the distortion minimization, and the prediction function describing the temperature field distribution and the optimal transmission characteristic function are correlated to obtain the temperature-transmission characteristic mapping relationship.

4. The high-voltage connector fault prediction method based on thermal management according to claim 3, characterized in that: Based on the temperature-transmission characteristic mapping relationship, Gaussian process regression calculation is performed on the temperature time series data to obtain the statistical characteristics of the temperature dynamic characteristics, including: The temperature change data collected by the high-voltage connector in each working cycle is screened and classified to obtain the temperature time series data including the normal working state and the fault state; Performing Gaussian filtering denoising and centralization standardization processing on the temperature time series data to obtain a normalized temperature data sequence, and inputting the temperature-transmission feature mapping relationship as prior knowledge into the normalized temperature data sequence to obtain a high-dimensional feature space of temperature change; Performing radial basis function transformation and eigendecomposition on the temperature data in the high-dimensional feature space to obtain a kernel function probability density matrix, and inputting the kernel function probability density matrix into a maximum likelihood estimation function to perform hyperparameter optimization to obtain an optimal parameter set of a Gaussian process kernel function; Based on the optimal parameter set, Gaussian process modeling is performed on the temperature change trajectory to obtain a multivariate Gaussian distribution function that describes the dynamic characteristics of temperature, and the multivariate Gaussian distribution function is substituted into the temperature prediction model to calculate the mean and variance to obtain the temperature change statistics; A coupling analysis is performed on the temperature change statistics and the temperature-transmission characteristic mapping relationship to obtain a statistical feature of the temperature dynamic characteristic.

5. The high voltage connector fault prediction method based on thermal management according to claim 4, characterized in that: The step of inputting the temperature dynamic characteristic statistical features into the specified time delay thermal management neural network to predict the signal transmission delay and obtain the delay prediction characteristic parameters includes: Reconstructing the statistical characteristics of the temperature dynamic characteristics to obtain a multi-dimensional input data matrix including temperature change rate, temperature distribution characteristics, signal integrity indicators and initial delay values; Inputting the multidimensional input data matrix into a thermal feature extraction layer of a thermal management neural network with a predetermined time delay, wherein the thermal feature extraction layer includes a temperature dynamic encoding unit, a heat conduction feature analysis unit, and a temperature fluctuation processing unit to obtain a thermal management feature vector; Performing a time series feature learning layer processing on the thermal management feature vector, wherein the time series feature learning layer includes a long short-term memory unit, a time attention mechanism unit, and a time series dependency modeling unit to obtain a time series correlation feature matrix; Inputting the time series correlation feature matrix into a delay prediction backbone network layer, wherein the delay prediction backbone network layer includes a multi-head self-attention mechanism unit, a residual connection unit, and a prescribed time constraint unit, to obtain an initial delay prediction result; Performing temperature compensation layer processing on the initial delay prediction result, the temperature compensation layer comprising a temperature disturbance analysis unit, a nonlinear compensation unit and a dynamic correction unit, to obtain a compensated delay prediction value; Inputting the compensated delay prediction value into a multi-task learning layer, wherein the multi-task learning layer includes a delay prediction branch, a temperature prediction branch, and a stability evaluation branch, to obtain a multi-dimensional prediction feature set; The multi-dimensional prediction feature set is subjected to feature fusion layer processing, wherein the feature fusion layer comprises a cross-modal feature fusion unit, an adaptive weight allocation unit and a global information aggregation unit, so as to obtain delay prediction feature parameters.

6. The high voltage connector fault prediction method based on thermal management according to claim 5, characterized in that: The step of calculating the weighted error value in the transmission feature space according to the delay prediction characteristic parameter and dynamically adjusting the signal transmission delay to obtain the compensated signal transmission delay parameter includes: Performing transmission feature space mapping on the delay prediction feature parameters, and constructing a weighted error calculation model based on delay error, temperature influence and signal integrity features; Based on the weighted error calculation model, error analysis is performed on the transmission feature space, and the weighted coefficients of each feature dimension are calculated by the least square method to obtain the weighted error value in the transmission feature space; Performing three-layer Bayesian inference on the weighted error value and the delay prediction characteristic parameter to obtain a compensation strategy parameter set; Based on the compensation strategy parameter set, Gibbs sampling and variational inference calculations are performed, and probability distribution optimization is performed on the delay compensation amount to obtain the compensated signal transmission delay parameters.

7. The high voltage connector fault prediction method based on thermal management according to claim 6, characterized in that: The three-layer Bayesian inference is performed on the weighted error value and the delay prediction characteristic parameter to obtain a compensation strategy parameter set, including: Inputting the weighted error value and the delay prediction feature parameter into the first layer Bayesian inference device to calculate the distribution parameters to obtain the delay error probability distribution, and performing variational inference operation on the delay error probability distribution to obtain the initial distribution parameters of the delay compensation; Inputting the initial distribution parameters of the delay compensation and the temperature influence characteristics into the second-layer Bayesian inference machine to perform joint distribution calculation to obtain a temperature-delay probability function, and constructing a transition probability matrix for the temperature-delay probability function to obtain a state transfer matrix; Inputting the state transfer matrix and the signal integrity index into the third-layer Bayesian inference device to construct a probability field to obtain a Markov random field structure, and performing conditional probability sampling on the Markov random field structure to obtain a state transfer probability sequence; A maximum expectation calculation is performed based on the state transition probability sequence to obtain a compensation strategy parameter set.

8. A high voltage connector fault prediction system based on thermal management, characterized in that: Used to execute the high-voltage connector fault prediction method based on thermal management according to any one of claims 1 to 7, the high-voltage connector fault prediction system based on thermal management comprises: An acquisition module is used to acquire temperature distribution data and electrical signal transmission characteristic data of the high-voltage connector, and to establish a thermal-electric coupling network model including temperature nodes and signal transmission nodes; A separation optimization module, used to separate and optimize the transmission characteristic function according to the thermal-electric coupling network model to obtain a temperature-transmission characteristic mapping relationship; A regression calculation module, used to perform Gaussian process regression calculation on the temperature time series data based on the temperature-transmission characteristic mapping relationship to obtain statistical characteristics of temperature dynamic characteristics; A delay prediction module, used for inputting the statistical characteristics of the temperature dynamic characteristics into a predetermined time delay thermal management neural network to predict the signal transmission delay and obtain delay prediction characteristic parameters; The dynamic adjustment module is used to calculate the weighted error value in the transmission feature space according to the delay prediction characteristic parameter, and dynamically adjust the signal transmission delay to obtain the compensated signal transmission delay parameter.

Images