High-speed connector detection method, device and equipment based on data analysis

Abstract

The invention discloses a high-speed connector detection method, device and equipment based on data analysis. The method comprises the following steps: constructing a multi-physics field coupling analysis model according to geometric parameters of a high-speed connector; determining characteristic parameters influencing the performance of the high-speed connector according to the multi-physics field coupling analysis model, and generating a standard characteristic library corresponding to the characteristic parameters and the performance indexes; acquiring real-time detection data of the high-speed connector; and identifying potential defects of the high-speed connector according to the standard feature library and the real-time detection data. Through the implementation of the scheme of the invention, the real-time detection data is compared with the standard feature library, and the theoretical basis provided by the performance abnormity and the multi-physics field model can be found in time, so that the defect identification is more accurate.

Description

Technical Field

[0001] The present application relates to the field of data processing, and in particular to a high-speed connector detection method, device, and equipment based on data analysis. Background Art

[0002] With the rapid development of electronic information technology, high-speed connectors, as key components for signal transmission between electronic devices, have a direct impact on the stability of the entire system due to their reliability and performance. Modern communications, computers, aerospace, and other fields have placed increasingly higher demands on the rate, bandwidth, and integrity of signal transmission, which poses a huge challenge to the design and manufacture of high-speed connectors. Traditional high-speed connector detection methods mainly rely on manual experience and single physical field analysis, making it difficult to comprehensively evaluate the performance characteristics of connectors in complex working environments. In actual applications, high-speed connectors are often simultaneously subjected to the coupling effects of multiple physical fields such as mechanical stress, electromagnetic fields, and temperature fields. These factors influence and restrict each other, resulting in a very complex mechanism for connector performance degradation and the formation of potential defects. In addition, existing detection methods lack a systematic and standardized characteristic parameter evaluation system, and are unable to accurately identify and predict potential failures of connectors. Summary of the Invention

[0003] The present application provides a high-speed connector detection method, device and equipment based on data analysis, which is used to solve the problem in related technologies that potential faults of connectors cannot be accurately identified and predicted.

[0004] A first aspect of the present application provides a high-speed connector detection method based on data analysis, the high-speed connector detection method based on data analysis comprising: Construct a multi-physics coupling analysis model based on the geometric parameters of the high-speed connector; Determining characteristic parameters that affect the performance of the high-speed connector according to the multi-physics field coupling analysis model, and generating a standard characteristic library corresponding to the characteristic parameters and performance indicators; Acquiring real-time detection data of the high-speed connector; Potential defects of the high-speed connector are identified based on the standard feature library and the real-time detection data.

[0005] Optionally, in a first implementation of the first aspect of the present application, before the step of constructing a multi-physics field coupling analysis model according to the geometric parameters of the high-speed connector, the method further includes: Acquiring geometric data of the high-speed connector by performing three-dimensional laser scanning on the high-speed connector; determining a parameterized geometric model according to the geometric data; A digital twin model is constructed according to the geometric parameters corresponding to the parameterized geometric model.

[0006] Optionally, in a second implementation of the first aspect of the present application, the step of determining characteristic parameters affecting the performance of the high-speed connector according to the multi-physics field coupling analysis model and generating a standard feature library corresponding to the characteristic parameters and performance indicators includes: Obtaining mechanical parameters, electrical parameters, and thermal parameters from the digital twin model respectively; constructing a mechanical model according to the mechanical parameters; constructing an electrical model according to the electrical parameters; constructing a thermal model according to the thermal parameters; Determining performance parameters of the high-speed connector by coupling data of the mechanical model, the electrical model, and the thermal model; Identifying characteristic parameters of the performance parameters that affect the high-speed connector through parameter sensitivity analysis; Determining a mapping relationship between the characteristic parameters and the performance indicators; A standard feature library is generated according to the mapping relationship.

[0007] Optionally, in a third implementation of the first aspect of the present application, the step of obtaining real-time detection data of the high-speed connector includes: determining contact pressure measurement data of the high-speed connector according to the force-sensitive sensor array; determining hotspot distribution data of the high-speed connector according to a temperature sensor array; Determining deformation data at a contact interface of the high-speed connector according to a micro-displacement sensor; The contact pressure measurement data, the hot spot distribution data, and the deformation variable data are preprocessed to generate physical parameter data.

[0008] Optionally, in a fourth implementation of the first aspect of the present application, the method further includes: determining electric field distribution data of the high-speed connector according to an electric field probe array; determining magnetic field distribution data of the high-speed connector according to a magnetic field probe array; The electric field distribution data and the magnetic field distribution data are fused by a multi-dimensional data fusion algorithm to form electromagnetic field data.

[0009] Optionally, in a fifth implementation of the first aspect of the present application, the real-time detection data includes the physical parameter data and the electromagnetic field data, and the step of identifying potential defects of the high-speed connector based on the standard feature library and the real-time detection data includes: Generate defect training samples of a deep learning model based on the standard feature library and the real-time detection data; Training the deep learning model according to the defect training samples; Perform feature extraction on the physical parameter data and the electromagnetic field data respectively according to the multi-stream convolutional neural network of the trained deep learning model to determine the spatial features of the physical parameter data and the electromagnetic field data; Determine the time series characteristics of the physical parameter data and the electromagnetic field data according to the long short-term memory network of the deep learning model after the training is completed; Generate a multidimensional feature vector by splicing the spatial features and the temporal features; Potential defects of the high-speed connector are identified according to the multi-dimensional feature vector.

[0010] Optionally, in a sixth implementation of the first aspect of the present application, the method further includes: Obtaining historical operating data of the high-speed connector; Establishing a performance degradation model of the high-speed connector based on the historical operation data and the real-time detection data; The remaining service life of the high-speed connector is predicted according to the performance degradation model.

[0011] A second aspect of the present application provides a high-speed connector detection device based on data analysis, the high-speed connector detection device based on data analysis comprising: A building module for building a multi-physics coupling analysis model based on geometric parameters of the high-speed connector; A generating module, configured to determine characteristic parameters affecting the performance of the high-speed connector according to the multi-physics field coupling analysis model, and to generate a standard characteristic library corresponding to the characteristic parameters and performance indicators; An acquisition module, configured to acquire real-time detection data of the high-speed connector; An identification module is used to identify potential defects of the high-speed connector according to the standard feature library and the real-time detection data.

[0012] A third aspect of an embodiment of the present application provides an electronic device, comprising a memory and a processor, wherein the processor is configured to execute a computer program stored on the memory. When the processor executes the computer program, the processor implements the steps of the high-speed connector detection method based on data analysis provided in the first aspect of the embodiment of the present application.

[0013] A fourth aspect of an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the high-speed connector detection method based on data analysis provided in the first aspect of the embodiment of the present application are implemented.

[0014] In summary, according to the data analysis-based high-speed connector detection method, device, and equipment provided by the present application, a multi-physics coupling analysis model is constructed based on the geometric parameters of the high-speed connector; characteristic parameters affecting the performance of the high-speed connector are determined based on the multi-physics coupling analysis model, and a standard feature library corresponding to the characteristic parameters and performance indicators is generated; real-time detection data of the high-speed connector is obtained; and potential defects of the high-speed connector are identified based on the standard feature library and the real-time detection data. Through the implementation of the present application, by comparing the real-time detection data with the standard feature library, performance anomalies can be discovered in a timely manner. The theoretical foundation provided by the multi-physics model makes defect identification more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 A schematic diagram of a flow chart of a high-speed connector detection method based on data analysis provided in an embodiment of the present application; Figure 2 A schematic diagram of a program module of a high-speed connector detection device based on data analysis provided in an embodiment of the present application; Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0016] In order to make the purpose, features, and advantages of the invention of this application more obvious and easy to understand, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are only part of the embodiments of this application, not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without making creative efforts shall fall within the scope of protection of this application.

[0017] In order to solve the problem in related art that potential faults of connectors cannot be accurately identified and predicted, the embodiment of the present application provides a high-speed connector detection method based on data analysis, such as Figure 1 This is a flow chart of a high-speed connector detection method based on data analysis provided in this embodiment. The high-speed connector detection method based on data analysis includes the following steps: Step 110: Construct a multi-physics field coupling analysis model according to the geometric parameters of the high-speed connector.

[0018] Specifically, in this embodiment, a high-precision three-dimensional scanner is used to scan the high-speed connector to obtain its precise geometric parameters, including the diameter and length of the male end pin, the thickness and elastic modulus of the female end spring, etc. The scan data is imported into computer-aided design (CAD) software to establish a geometric model of the connector, wherein the multi-physics field coupling analysis model includes a mechanical model, an electrical model, a thermal model, and an electromagnetic field model.

[0019] In an optional implementation of this embodiment, before the step of constructing a multi-physics field coupling analysis model based on the geometric parameters of the high-speed connector, it also includes: obtaining the geometric data of the high-speed connector by performing three-dimensional laser scanning on the high-speed connector; determining a parameterized geometric model based on the geometric data; and constructing a digital twin model based on the geometric parameters corresponding to the parameterized geometric model.

[0020] Specifically, in this embodiment, the digital modeling process for a high-speed connector first requires a high-precision 3D laser scanner to perform a full-scale scan of the connector. This laser scanner typically utilizes blue-light structured light technology, achieving scanning accuracies on the order of 0.01 mm. During the scanning process, the connector is mounted on a precision rotary table, and multi-angle and multi-directional scanning is performed to ensure the integrity and accuracy of the captured data. During the scanning process, structured light emitted by the laser scanner strikes the connector surface, forming a stripe pattern. This pattern is captured by a high-resolution camera, and the 3D surface contour of the object is reconstructed using triangulation principles. Subsequently, the acquired raw scan data is processed using specialized point cloud processing software, including noise removal, data alignment, and mesh reconstruction. During this stage, particular attention is paid to the data integrity of key connector features, such as the contact areas of the pins and reeds. Reverse engineering software is used to convert the processed point cloud data into an editable 3D solid model. This process requires precise surface fitting to ensure the model's geometric accuracy. Next, a parametric geometric model is constructed based on the acquired geometric data. This process requires identifying key dimensional parameters of the connector, such as the diameter and length of the pins and the thickness and bend angle of the reeds. Using parametric modeling software (such as CATIA or NX), these key dimensions are set as variable parameters to create a parameter-driven geometric model. This parametric model is highly adjustable, facilitating design optimization and variant design. Finally, a digital twin model is constructed based on the parametric geometric model. The digital twin model not only contains geometric information but also integrates multidimensional information such as physical properties, material attributes, and assembly relationships. By associating sensor data from the physical connector with the digital model, real-time mapping and interaction between the physical and digital worlds is achieved. The digital twin model can reflect the connector's operating status in real time, predict performance trends, and provide support for product optimization and maintenance decisions.

[0021] Step 120: Determine characteristic parameters that affect the performance of the high-speed connector based on the multi-physics field coupling analysis model, and generate a standard characteristic library corresponding to the characteristic parameters and performance indicators.

[0022] Specifically, in this embodiment, based on the coupling analysis results, the stress distribution and stress concentration points in the key areas are determined. Characteristic parameters such as the maximum stress value, stress distribution pattern, and stress concentration coefficient are recorded. The current density distribution characteristics are determined, and characteristic parameters such as the maximum current density, current density change in the key areas, and current density gradient are recorded. Based on the thermal analysis results, the temperature distribution characteristics are determined, and characteristic parameters such as the maximum temperature rise, temperature change in the key areas, and thermal stress are recorded. Based on the actual use requirements of the connector, performance indicators such as contact resistance, mechanical strength, and high-temperature resistance are determined. Through experiments and simulations, the corresponding relationship between characteristic parameters and performance indicators is established. For example, maximum stress and mechanical strength, maximum current density and contact resistance, maximum temperature rise and high-temperature resistance, etc. The multi-physics field coupling analysis results and experimental data are collected, and the corresponding relationship between characteristic parameters and performance indicators is sorted. A standard feature library is established, and the corresponding relationship between characteristic parameters and performance indicators is entered into the database to form a complete standard feature library. This feature library will serve as a benchmark for subsequent real-time detection and defect identification.

[0023] In an optional implementation of this embodiment, the steps of determining characteristic parameters affecting the performance of the high-speed connector based on the multi-physics field coupling analysis model and generating a standard feature library corresponding to the characteristic parameters and performance indicators include: Mechanical parameters, electrical parameters and thermal parameters are obtained from the digital twin model respectively; a mechanical model is constructed based on the mechanical parameters; an electrical model is constructed based on the electrical parameters; a thermal model is constructed based on the thermal parameters; the performance parameters of the high-speed connector are determined by coupling the data of the mechanical model, the electrical model and the thermal model; characteristic parameters that affect the high-speed connector in the performance parameters are identified through parameter sensitivity analysis; the mapping relationship between the characteristic parameters and the performance indicators is determined; and a standard feature library is generated based on the mapping relationship.

[0024] Specifically, in this embodiment, during the multi-physics field analysis of the high-speed connector, it is first necessary to extract relevant physical parameters from the digital twin model. By analyzing the digital twin model, mechanical parameters (such as elastic modulus, Poisson's ratio, yield strength, etc.), electrical parameters (such as conductivity, dielectric constant, etc.) and thermal parameters (such as thermal conductivity, specific heat capacity, etc.) can be obtained. In the parameter extraction process, it is necessary to pay attention to the interdependence between the parameters, such as the influence of temperature on the elastic modulus of the material, the influence of stress on conductivity, etc. A mechanical model is constructed based on the obtained mechanical parameters, and this process is mainly implemented by the finite element method. In the mechanical model, it is necessary to consider the stress conditions of the connector under actual working conditions, including plugging and unplugging force, contact pressure, vibration load, etc. At the same time, an electrical model is constructed based on electrical parameters, focusing on characteristics such as current distribution, contact resistance, and parasitic parameters. In addition, a thermal model is constructed using thermal parameters to analyze temperature field distribution, thermal stress effects, etc. After establishing each physical field model, a coupling analysis is performed using a multi-physics field coupling solver. During the coupling process, complex interactions occur between various physical fields. For example, Joule heating generated by current flow affects the temperature field distribution, and this temperature field change in turn induces thermal stress, which in turn changes contact pressure and resistance. Through iterative solving, a stable coupling solution is ultimately obtained, determining the comprehensive performance parameters of the connector. Parameter sensitivity analysis can identify characteristic parameters that significantly influence connector performance. This process is accomplished by varying input parameters and observing the changes in the output response. By calculating sensitivity coefficients, the importance of different parameters can be quantified. After determining the key characteristic parameters, a mapping relationship is established between these parameters and performance indicators, ultimately generating a standard feature library.

[0025] Step 130: Acquire real-time detection data of the high-speed connector.

[0026] Specifically, in this embodiment, appropriate sensors, such as force sensors, temperature sensors, and current density sensors, are selected based on characteristic parameters. These sensors are placed in key areas of the connector, such as stress concentration points, areas of varying current density, and areas of elevated temperature, to ensure real-time monitoring of important parameters. The acquired real-time detection data is cleaned to remove noise and outliers, ensuring data accuracy.

[0027] In an optional implementation of this embodiment, the step of obtaining real-time detection data of the high-speed connector includes: determining the contact pressure measurement data of the high-speed connector based on the force-sensitive sensor array; determining the hotspot distribution data of the high-speed connector based on the temperature sensor array; determining the deformation variable data at the contact interface of the high-speed connector based on the micro-displacement sensor; and pre-processing the contact pressure measurement data, hotspot distribution data, and deformation variable data to generate physical parameter data.

[0028] Specifically, in this embodiment, a force sensor array is used to measure the pressure distribution at the contact interface of a high-speed connector. Force sensors convert physical pressure into electrical signals. The sensor array can acquire pressure data at multiple points, forming a complete pressure distribution map. For example, when a connector is inserted into its corresponding slot, the force sensor array can detect the pressure value at each contact point, thereby determining the uniformity and firmness of the contact. This data can be transmitted to the central processing unit (CPU) via a data acquisition system for analysis. While acquiring contact pressure data, a temperature sensor array is used to monitor the heat distribution generated by the high-speed connector during operation. High-speed connectors, operating under high-frequency and high-current conditions, are prone to heat generation, leading to elevated temperatures. The temperature sensor array can monitor the temperature of various parts of the connector in real time and generate a hotspot distribution map. For example, if the temperature at a particular contact point is significantly higher than that at other areas, this may indicate poor contact or excessive resistance at that contact point. This temperature data is also transmitted to the CPU via the data acquisition system for analysis. Micro-displacement sensors are used to measure deformation data at the contact interface of high-speed connectors. Micro-displacement sensors can detect tiny displacement changes and reflect the deformation of the connector during the contact process. For example, during the connector insertion process, certain contact points may deform, affecting the contact quality. The micro-displacement sensor array can accurately measure these deformation variables and provide detailed deformation data.

[0029] After acquiring contact pressure measurement data, hotspot distribution data, and deformation data, these data require preprocessing. Data preprocessing includes steps such as noise filtering, data calibration, and data fusion. First, noise filtering aims to remove random noise and interference signals from sensor data, thereby improving data accuracy. For example, digital filtering techniques such as mean filtering and Kalman filtering can be used to smooth sensor data. Second, data calibration ensures consistency and comparability between sensor data. For example, experimental calibration can be used to determine the sensor's response curve and sensitivity, and to calibrate the measurement data. Finally, data fusion combines data from different sensors to generate more comprehensive and reliable physical parameter data. For example, multi-sensor data fusion techniques such as weighted averaging and Bayesian estimation can be used to combine contact pressure data, hotspot distribution data, and deformation data to generate a complete physical parameter model.

[0030] Understandably, in practical applications, a high-speed connector may simultaneously experience uneven contact pressure, localized overheating, and deformation when transmitting high-frequency signals. Comprehensive and accurate diagnosis of these issues is difficult if relying solely on a single type of sensor. However, the combined use of force sensor arrays, temperature sensor arrays, and micro-displacement sensors allows comprehensive monitoring of the connector's operating status and acquisition of detailed physical parameter data. For example, a force sensor array can reveal significantly lower pressure at certain contact points than in other areas, suggesting the possibility of poor contact. A temperature sensor array can detect abnormally elevated temperatures in certain areas, suggesting localized overheating. Micro-displacement sensors can monitor connector deformation during insertion, indicating potential mechanical stress issues. Data preprocessing and fusion can generate a comprehensive physical parameter model, providing an important basis for fault diagnosis and performance optimization.

[0031] In an optional implementation of this embodiment, the electric field distribution data of the high-speed connector is determined based on the electric field probe array; the magnetic field distribution data of the high-speed connector is determined based on the magnetic field probe array; the electric field distribution data and the magnetic field distribution data are fused through a multi-dimensional data fusion algorithm to form electromagnetic field data.

[0032] Specifically, in this embodiment, an electric field probe array is used to measure the electric field distribution around a high-speed connector. The electric field probe can convert the electric field strength into an electrical signal through the capacitive effect, thereby achieving accurate measurement of the electric field distribution. Similar to the electric field probe array, a magnetic field probe array is used to measure the magnetic field distribution around a high-speed connector. The magnetic field probe can convert the magnetic field strength into an electrical signal through the inductive effect, thereby achieving accurate measurement of the magnetic field distribution. After data preprocessing is completed, a variety of data fusion algorithms can be used to fuse the electric and magnetic field data. For example, a weighted average method can be used to perform a weighted sum based on the weights of the electric and magnetic field data to obtain fused electromagnetic field data. Alternatively, a Bayesian estimation method can be used to fuse and update data by establishing a probabilistic model for the electric and magnetic field data. In addition, a deep learning algorithm can be used to automatically fuse and predict electric and magnetic field data by training a neural network model. Through the data fusion algorithm, the electric and magnetic field data can be combined to obtain more complete and accurate electromagnetic field distribution data.

[0033] Step 140: Identify potential defects of the high-speed connector based on the standard feature library and real-time detection data.

[0034] Specifically, in this embodiment, key characteristic parameters, such as stress, temperature, and current density, are extracted from real-time detection data. These extracted characteristic parameters are then compared with data in a standard feature library to determine whether any deviations exist. It should be noted that during this comparison process, machine learning algorithms (such as support vector machines, random forests, and neural networks) are employed for defect identification. The model is trained using data from the standard feature library as the training set and real-time detection data as the test set. The specific location and type of the defect are determined based on the detection data generated by the machine learning algorithm.

[0035] In an optional implementation of this embodiment, the step of identifying potential defects of high-speed connectors based on a real standard feature library and real-time detection data includes: generating defect training samples of a deep learning model based on the standard feature library and real-time detection data; training the deep learning model based on the defect training samples; performing feature extraction on physical parameter data and electromagnetic field data based on the multi-stream convolutional neural network of the trained deep learning model to determine the spatial features of the physical parameter data and the electromagnetic field data; determining the temporal features of the physical parameter data and the electromagnetic field data based on the long short-term memory network of the trained deep learning model; generating a multidimensional feature vector by splicing the spatial features and the temporal features; and identifying potential defects in the high-speed connector based on the multidimensional feature vector.

[0036] Specifically, in this embodiment, representative historical data and its corresponding characteristic parameters are extracted from a standard feature library. These data include various known physical parameters and electromagnetic field data under normal and fault conditions. Real-time detection data, including physical parameters and electromagnetic field data under the current state collected by the sensor array and electromagnetic probe, is also acquired simultaneously and compared with the data in the standard feature library to determine whether it contains anomalies or potential defects. When generating defect training samples, the standard feature library is first matched with the real-time detection data to screen out data samples with typical fault characteristics. Specifically, by comparing the real-time detection data with the characteristic parameters of the normal state in the standard feature library, abnormal data points can be identified. For example, if the contact pressure of a connector in the real-time detection data is significantly lower than the normal range and the electric and magnetic field strengths also show abnormal fluctuations, it can be preliminarily determined that the connector may have a potential contact defect. These abnormal data points, along with their corresponding annotation information, constitute the defect training samples. A deep learning model is trained based on the generated defect training samples. First, a multi-stream convolutional neural network (CNN) structure is designed to process the physical parameter data and electromagnetic field data separately. The convolutional layer of a CNN performs convolution operations on the input data using a sliding window approach to extract the spatial features of the data. For physical parameter data such as contact pressure, temperature, and deformation, CNN can extract spatial distribution characteristics of the data, such as pressure concentrations or temperature hotspots in certain areas. For electromagnetic field data, CNN can identify the distribution patterns and changing patterns of electric and magnetic fields, such as abnormal electric field strength or magnetic field leakage in certain areas. During model training, the weights of the convolutional layer are continuously adjusted using the backpropagation algorithm to minimize prediction error. The features extracted by the convolutional layer are downsampled by the pooling layer to reduce the data dimension while retaining important features. Finally, the features are mapped to the output space through a fully connected layer to obtain the classification results. Using a large number of defect training samples, the CNN gradually learns the spatial features of various fault conditions, enabling accurate classification of physical parameter and electromagnetic field data. In addition to spatial features, physical parameter and electromagnetic field data also have temporal characteristics. In the trained deep learning model, a long short-term memory network (LSTM) is used to capture the temporal characteristics of the data. LSTM, through its unique gating mechanism, can effectively process time series data and capture long-term data dependencies. For example, in the case of contact pressure data for a connector, LSTM can identify the pressure's temporal trend and determine whether it is stable or gradually deteriorating. For electromagnetic field data, LSTM can identify periodic or sudden changes in electric and magnetic field strength, thereby identifying potential faults such as electromagnetic interference or short circuits. By combining spatial and temporal features, a multidimensional feature vector can be generated.Specifically, the spatial features extracted by the CNN and the temporal features extracted by the LSTM are concatenated to form a high-dimensional feature vector. This feature vector contains comprehensive information about both the physical parameter data and the electromagnetic field data. During the feature vector concatenation process, a weighted averaging method or an attention mechanism can be used to assign different weights to different features to highlight the importance of key features. Ultimately, potential defects in high-speed connectors are identified based on the multidimensional feature vector. By analyzing the concatenated feature vector, the type and severity of the connector fault can be accurately identified. For example, if certain spatial and temporal features in the feature vector significantly deviate from the normal range, it can be determined that the connector may have faults such as poor contact, overheating, or electromagnetic interference.

[0037] It should be noted that in this embodiment, a multi-stream convolutional neural network (CNN) and a long short-term memory network (LSTM) are combined to extract spatial features and temporal features from physical parameter data and electromagnetic field data, and generate a multi-dimensional feature vector: , Among them, V is a multidimensional feature vector, is the activation function, represents the weighted sum of the spatial feature vectors extracted by CNN, M is the number of physical parameter data, is the weight coefficient of the i-th physical parameter data, The i-th physical parameter data The spatial feature vector extracted by CNN, represents the weighted sum of the time series feature vectors extracted by LSTM, N is the number of electromagnetic field data, is the weight coefficient of the j-th electromagnetic field data, is the jth electromagnetic field data Combined with the previous hidden state The time series feature vector extracted by LSTM, It is a feature concatenation operation that combines the spatial feature vector and the temporal feature vector into a multi-dimensional feature vector.

[0038] It should be noted that the formula of the trained classification model can be expressed as: , in, is the final classification result, is the activation function used to transform the input vector into a probability distribution, is the weight matrix of the output layer, is the bias vector of the output layer, is an element-level multiplication operation, used to introduce the attention mechanism. is the attention vector, which represents the importance weight of each feature. This formula integrates the spatial and temporal features of physical parameter data and electromagnetic field data, and generates a multidimensional feature vector after weighting through the attention mechanism. The layer outputs classification results, which are used to identify potential defects in high-speed connectors.

[0039] In an optional implementation of this embodiment, historical operating data of the high-speed connector is obtained; a performance degradation model of the high-speed connector is established based on the historical operating data and real-time detection data; and the remaining service life of the high-speed connector is predicted based on the performance degradation model.

[0040] Specifically, in this embodiment, historical operating data is acquired through a multi-type sensor array installed on the high-speed connector. These sensors include force sensors, temperature sensors, electric field probes, and magnetic field probes. This allows the connector's operating parameters under different operating and environmental conditions to be obtained, including multi-dimensional historical data such as contact pressure, temperature distribution, electric field strength, and magnetic field strength. This data is then combined with operational maintenance data, such as connector maintenance records, fault records, and replacement records, to establish a complete historical database. Based on the historical operating data, real-time detection data is correlated and analyzed with the historical operating data, and a performance degradation model for the high-speed connector is established using a deep learning algorithm. Based on the established performance degradation model, the remaining useful life of the connector can be predicted by inputting real-time detection data. The prediction process first normalizes the real-time data to align it with the scale of the historical data. The processed data is then input into the trained performance degradation model. The model compares the current performance parameters with historical degradation trends and, combined with the Weibull distribution model, calculates the reliability function of the high-speed connector and predicts its remaining useful life.

[0041] Optionally, the calculation formula of the performance degradation model of this embodiment is expressed as: , in, is the performance degradation index vector at time t, is a nonlinear mapping function, K is the number of feature extractors, and a feature extractor is an algorithm or model used to extract useful feature information from raw data. It is mainly used to extract key features that can reflect the performance status of the connector from complex data collected by sensors. is the weight coefficient of the kth feature extractor, is the k-th deep feature extractor based on the improved LSTM network, is the historical data matrix at time t, is the real-time data matrix at time t, is the tensor product operator used for feature fusion, λ is the attenuation coefficient, is the time-varying stress function, is the adaptive weight function, It is understood that the historical data matrix and the real-time data matrix are prepared in the data preparation stage, including but not limited to pressure, temperature, electromagnetic field strength, etc. Feature extraction is to extract useful features from historical data and real-time data through a deep learning model (such as an improved LSTM network). According to the importance of the feature, a weight is assigned to each feature extractor. The time-varying stress function in the stress function calculation stage is This describes the stress changes experienced by a device during operation, which affect its degradation rate. The environmental impact analysis phase comprehensively considers the impact of environmental factors (such as temperature, humidity, and dust) on device degradation using an adaptive weighting function and environmental factor impact vectors. Ultimately, all extracted features and weights are nonlinearly mapped, and the final performance degradation index is calculated by combining the stress attenuation factor and environmental impact.

[0042] According to the data analysis-based high-speed connector inspection method provided by this application, a multi-physics coupling analysis model is constructed based on the geometric parameters of the high-speed connector. The multi-physics coupling analysis model is used to determine characteristic parameters that affect the high-speed connector's performance, and a standard feature library is generated that corresponds to the characteristic parameters and performance indicators. Real-time inspection data for the high-speed connector is obtained, and potential defects in the high-speed connector are identified based on the standard feature library and the real-time inspection data. By implementing this application, real-time inspection data is compared with the standard feature library, enabling timely detection of performance anomalies. The theoretical foundation provided by the multi-physics model makes defect identification more accurate.

[0043] Figure 2 The present invention provides a high-speed connector detection device based on data analysis, which can be used to implement the high-speed connector detection method based on data analysis in the above-mentioned embodiment. Figure 2 As shown, the high-speed connector detection device based on data analysis mainly includes: A construction module 10 is used to construct a multi-physics field coupling analysis model according to geometric parameters of the high-speed connector; A generation module 20 is used to determine characteristic parameters that affect the performance of the high-speed connector based on the multi-physics field coupling analysis model, and to generate a standard feature library corresponding to the characteristic parameters and performance indicators; An acquisition module 30 is used to acquire real-time detection data of the high-speed connector; The identification module 40 is used to identify potential defects of the high-speed connector based on the standard feature library and real-time detection data.

[0044] In an optional implementation of this embodiment, the high-speed connector detection device further includes a determination module. The acquisition module is configured to acquire geometric data of the high-speed connector by performing a three-dimensional laser scan on the high-speed connector. The determination module is configured to determine a parameterized geometric model based on the geometric data. The construction module is configured to construct a digital twin model based on geometric parameters corresponding to the parameterized geometric model.

[0045] In an optional implementation of this embodiment, the generation module is specifically used to: obtain mechanical parameters, electrical parameters and thermal parameters from the digital twin model respectively; construct a mechanical model based on the mechanical parameters; construct an electrical model based on the electrical parameters; construct a thermal model based on the thermal parameters; determine the performance parameters of the high-speed connector by coupling the data of the mechanical model, the electrical model and the thermal model; identify the characteristic parameters that affect the high-speed connector in the performance parameters through parameter sensitivity analysis; determine the mapping relationship between the characteristic parameters and the performance indicators; and generate a standard feature library based on the mapping relationship.

[0046] In an optional implementation of this embodiment, the acquisition module is specifically used to: determine the contact pressure measurement data of the high-speed connector based on the force-sensitive sensor array; determine the hotspot distribution data of the high-speed connector based on the temperature sensor array; determine the deformation variable data at the contact interface of the high-speed connector based on the micro-displacement sensor; pre-process the contact pressure measurement data, hotspot distribution data and deformation variable data to generate physical parameter data.

[0047] In an optional implementation of this embodiment, the determination module is also used to: determine the electric field distribution data of the high-speed connector based on the electric field probe array; determine the magnetic field distribution data of the high-speed connector based on the magnetic field probe array; and fuse the electric field distribution data and the magnetic field distribution data through a multi-dimensional data fusion algorithm to form electromagnetic field data.

[0048] In an optional implementation of this embodiment, the identification module is specifically used to: generate defect training samples of a deep learning model based on a standard feature library and real-time detection data; train the deep learning model based on the defect training samples; extract features of physical parameter data and electromagnetic field data based on the multi-stream convolutional neural network of the trained deep learning model to determine the spatial features of the physical parameter data and the electromagnetic field data; determine the temporal features of the physical parameter data and the electromagnetic field data based on the long short-term memory network of the trained deep learning model; generate a multidimensional feature vector by splicing the spatial features and the temporal features; and identify potential defects in the high-speed connector based on the multidimensional feature vector.

[0049] In an optional implementation of this embodiment, the high-speed connector detection device further includes a prediction module. The acquisition module is further configured to obtain historical operating data of the high-speed connector. The construction module is further configured to establish a performance degradation model for the high-speed connector based on the historical operating data and real-time detection data. The prediction module is configured to predict the remaining useful life of the high-speed connector based on the performance degradation model.

[0050] According to the data analysis-based high-speed connector inspection device provided by the present application, a multi-physics coupling analysis model is constructed based on the geometric parameters of the high-speed connector. The multi-physics coupling analysis model is used to determine characteristic parameters that affect the performance of the high-speed connector and generate a standard feature library corresponding to the characteristic parameters and performance indicators. Real-time inspection data of the high-speed connector is obtained. Potential defects of the high-speed connector are identified based on the standard feature library and the real-time inspection data. By implementing the present application, real-time inspection data is compared with the standard feature library, enabling timely detection of performance anomalies. The theoretical foundation provided by the multi-physics model makes defect identification more accurate.

[0051] According to the application plan Figure 3 An electronic device provided in an embodiment of the present application can be used to implement the high-speed connector detection method based on data analysis in the aforementioned embodiment, mainly comprising: Memory 301, processor 302, and computer program 303 stored in memory 301 and executable on processor 302. Memory 301 and processor 302 are connected via communication. When processor 302 executes computer program 303, the high-speed connector detection method based on data analysis described in the aforementioned embodiment is implemented. The number of processors can be one or more.

[0052] The memory 301 can be a high-speed random access memory (RAM) memory or a non-volatile memory such as a disk drive. The memory 301 is used to store executable program code. The processor 302 is coupled to the memory 301 .

[0053] Furthermore, the embodiment of the present application also provides a computer-readable storage medium, which can be provided in the electronic device in the above embodiments. The computer-readable storage medium can be the above Figure 3 Memory in the illustrated embodiment.

[0054] The computer-readable storage medium stores a computer program that, when executed by a processor, implements the high-speed connector detection method based on data analysis described in the aforementioned embodiment. Furthermore, the computer-readable storage medium may be any medium capable of storing program code, such as a USB flash drive, a removable hard drive, a read-only memory (ROM), RAM, a magnetic disk, or an optical disk.

[0055] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0056] 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 the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program code.

[0057] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A high-speed connector detection method based on data analysis, characterized in that: include: Construct a multi-physics coupling analysis model based on the geometric parameters of the high-speed connector; Determine characteristic parameters that affect the performance of the high-speed connector according to the multi-physics field coupling analysis model, and generate a standard characteristic library corresponding to the characteristic parameters and performance indicators; Acquiring real-time detection data of the high-speed connector; Potential defects of the high-speed connector are identified based on the standard feature library and the real-time detection data.

2. The high-speed connector detection method based on data analysis according to claim 1, characterized in that: Before the step of constructing a multi-physics field coupling analysis model according to the geometric parameters of the high-speed connector, the method further includes: Acquiring geometric data of the high-speed connector by performing three-dimensional laser scanning on the high-speed connector; determining a parameterized geometric model according to the geometric data; A digital twin model is constructed according to the geometric parameters corresponding to the parameterized geometric model.

3. The high-speed connector detection method based on data analysis according to claim 2, characterized in that: The step of determining the characteristic parameters affecting the performance of the high-speed connector according to the multi-physics field coupling analysis model and generating a standard characteristic library corresponding to the characteristic parameters and performance indicators includes: Obtaining mechanical parameters, electrical parameters and thermal parameters from the digital twin model respectively; Constructing a mechanical model according to the mechanical parameters; constructing an electrical model according to the electrical parameters; Constructing a thermal model according to the thermal parameters; Determining performance parameters of the high-speed connector by coupling data of the mechanical model, the electrical model, and the thermal model; Identifying characteristic parameters of the performance parameters that affect the high-speed connector through parameter sensitivity analysis; Determining a mapping relationship between the characteristic parameters and the performance indicators; A standard feature library is generated according to the mapping relationship.

4. The high-speed connector detection method based on data analysis according to claim 1, characterized in that: The step of obtaining real-time detection data of the high-speed connector includes: Determining contact pressure measurement data of the high-speed connector according to the force-sensitive sensor array; Determine hot spot distribution data of the high-speed connector according to the temperature sensor array; Determining deformation data at a contact interface of the high-speed connector according to a micro-displacement sensor; The contact pressure measurement data, the hot spot distribution data and the deformation amount data are preprocessed to generate physical parameter data.

5. The high-speed connector detection method based on data analysis according to claim 4, characterized in that: The method further comprises: Determining electric field distribution data of the high-speed connector according to an electric field probe array; Determining magnetic field distribution data of the high-speed connector according to a magnetic field probe array; The electric field distribution data and the magnetic field distribution data are fused by a multi-dimensional data fusion algorithm to form electromagnetic field data.

6. The high-speed connector detection method based on data analysis according to claim 5, characterized in that: The real-time detection data includes the physical parameter data and the electromagnetic field data, and the step of identifying potential defects of the high-speed connector according to the standard feature library and the real-time detection data includes: Generate defect training samples of a deep learning model according to the standard feature library and the real-time detection data; Training the deep learning model according to the defect training samples; Perform feature extraction on the physical parameter data and the electromagnetic field data respectively according to the multi-stream convolutional neural network of the trained deep learning model to determine the spatial features of the physical parameter data and the electromagnetic field data; Determine the time series characteristics of the physical parameter data and the electromagnetic field data according to the long short-term memory network of the deep learning model after the training is completed; Generate a multi-dimensional feature vector by splicing the spatial feature and the temporal feature; Potential defects of the high-speed connector are identified according to the multi-dimensional feature vector.

7. The high-speed connector detection method based on data analysis according to claim 5, characterized in that: The method further comprises: Acquiring historical operation data of the high-speed connector; Establishing a performance degradation model of the high-speed connector according to the historical operation data and the real-time detection data; The remaining service life of the high-speed connector is predicted according to the performance degradation model.

8. A high-speed connector detection device based on data analysis, characterized in that: The high-speed connector detection device based on data analysis includes: A building module for building a multi-physics coupling analysis model according to geometric parameters of the high-speed connector; A generating module, used to determine characteristic parameters affecting the performance of the high-speed connector according to the multi-physics field coupling analysis model, and generate a standard characteristic library corresponding to the characteristic parameters and performance indicators; An acquisition module, used for acquiring real-time detection data of the high-speed connector; An identification module is used to identify potential defects of the high-speed connector according to the standard feature library and the real-time detection data.

9. An electronic device, characterized in that: The device comprises a memory and a processor, wherein: The processor is used to execute the computer program stored in the memory; When the processor executes the computer program, the steps of the high-speed connector detection method based on data analysis described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the high-speed connector detection method based on data analysis described in any one of claims 1 to 7 are implemented.

Images