A mobile phone data line performance test and fault prediction method and system

Abstract

The application discloses a kind of mobile phone data line performance test and fault prediction method and system, belong to electronic product detection and fault prediction technical field, collect the power-on resistance, voltage stability, charging current response and data transmission rate of target data line, obtain stress response data under different bending angles, plug-in cycles and environmental temperature conditions, extract multi-dimensional stress principal component features;Fusion electrical property and stress data, establish performance degradation correlation model, realize the coupling modeling of data line internal structure damage and electrical performance degradation;Input historical use data, simulate through model, generate residual performance indicators;According to whether the set threshold value exists fault risk, if below threshold value, then output early warning information;While combining model internal characteristic map infers fault location and mode type;The method has high prediction accuracy, strong structure adaptability and good expansibility, and is suitable for quality control and intelligent diagnosis of consumer electronic cable products.

Description

Technical Field

[0001] This invention relates to the field of electronic product testing and fault prediction technology, specifically to a method and system for performance testing and fault prediction of mobile phone data cables. Background Technology

[0002] With the widespread adoption of smartphones, data cables, as an essential electronic accessory, play a crucial role in charging and data transfer. However, due to frequent bending, plugging, and pulling by users, data cables are prone to hidden faults such as broken internal wires, poor plug contact, and shielding detachment. These faults often manifest as intermittent failures in the early stages, such as intermittent charging failure, slow data transfer rates, and system prompts indicating "non-original accessory," severely impacting the user experience.

[0003] Currently, most mobile phone data cable testing on the market relies on manual visual inspection or simple resistance and voltage testing. This cannot effectively identify and predict the internal performance degradation trend of the data cable, nor can it identify potential fault risks in advance. As a result, a large number of potentially hazardous products have entered the market or reached users, increasing maintenance costs and reducing brand trust.

[0004] Therefore, there is an urgent need for a method that can comprehensively consider key physical indicators during use, combine test data from multiple scenarios, and use modeling and analysis to assess the performance status of mobile phone data cables and predict fault risks, so as to improve detection accuracy and extend their service life. Summary of the Invention

[0005] The purpose of this invention is to provide a method and system for testing the performance and predicting the faults of mobile phone data cables, so as to overcome the shortcomings in the prior art.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a method for performance testing and fault prediction of mobile phone data cables, comprising:

[0007] S100: Collect multiple sets of electrical performance data of the target mobile phone data cable under different test scenarios, including power resistance, voltage stability, charging current response and data transmission rate, and construct a set of electrical performance parameters E.

[0008] S200, Obtain stress response data set S of mobile phone data cable under different bending angles, insertion and removal times and ambient temperature conditions;

[0009] S300. Based on the electrical performance parameter set E and the stress response data set S, establish a corresponding performance degradation correlation model W to describe the relationship between changes in the internal structure of the data line and the degradation of electrical performance.

[0010] S400. Input the historical usage data of the target mobile phone data cable, and perform simulation through the W model to obtain the remaining performance index P of the data cable in the current state.

[0011] S500. According to the set performance threshold Ph, compare the index P to determine whether there is a risk of failure for the data cable. If P < Ph, output a warning message and mark it as a high risk.

[0012] S600. Based on the simulation results, output the failure location and failure mode of the data cable to achieve performance testing and failure prediction of the target mobile phone data cable.

[0013] Preferably, the S100 includes:

[0014] S101. Perform periodic electrical scans on the target mobile phone data cable in four typical usage scenarios: constant voltage charging, charging while using, data synchronization, and high-load fast charging, and obtain the transient resistance, voltage fluctuation amplitude, dynamic current response, and data throughput rate in each scenario.

[0015] S102. Construct a four-dimensional electrical performance vector based on each set of original test data, and uniformly map the electrical performance characteristics in each test scenario to the normalized parameter space to form a feature matrix Em that can be distinguished in the time series dimension.

[0016] S103. Perform feature compression and non-linear decoupling on Em through an embedded variational autoencoder to extract a low-dimensional latent electrical expression factor E.

[0017] Preferably, the S200 includes:

[0018] S201. Construct a three-dimensional coupled loading platform, and use a programmable flexible mechanism to apply combined control of different bending angles, plugging and unplugging cycles, and constant temperature / variable temperature environments to the target data cable to achieve simulation of typical stress field conditions.

[0019] S202. Synchronously deploy a strain fiber array sensor and a micro-thermocouple under each loading combination condition, and record the strain distribution, micro-crack induction points, and abnormal heat conduction paths of the outer sheath and conductor core of the data cable in real time to form a high-resolution stress response matrix Si.

[0020] S203. Use the tensor decomposition method to perform dimensionality reduction on all Si, extract the key stress principal element features, and construct a multi-dimensional stress response data set S.

[0021] Preferably, the S300 includes:

[0022] S301. The constructed set of electrical performance parameters E and the extracted set of stress response data S are time-stamp aligned and feature synchronized. High-dimensional correlation extraction of stress and electrical features is achieved through a multi-channel residual fusion network.

[0023] S302. Introduce a structural embedding tensor to construct a latent variable map of the internal structural changes of the data line, and embed it as a model structural constraint into the performance degradation correlation model W.

[0024] S303. A time-series prediction module based on LSTM-GRU hybrid units is used to dynamically train the model W, enabling it to simulate the nonlinear degradation process of electrical performance parameters over time or cycle number under different stress paths.

[0025] Preferably, S400 includes:

[0026] S401. Collect historical usage data of the target mobile phone data cable, including cumulative number of plugging and unplugging, typical bending trajectory, total charging time, ambient temperature distribution and usage scenario labels, and construct a usage behavior vector sequence Ut;

[0027] S402. Input the behavior vector Ut into the trained performance degradation correlation model W, use the model’s time recursion capability to calculate the electrical performance evolution path within the prediction window, and output the simulated state curve Pt.

[0028] S403. Based on the dynamic change rate of resistance, current and speed parameters in the simulation results, construct a weighted fusion index function, aggregate and reduce Pt, and generate the data line residual performance index Po in the current state.

[0029] This invention also provides a mobile phone data cable performance testing and fault prediction system, comprising:

[0030] The data acquisition module collects multiple sets of electrical performance data of the target mobile phone data cable under different test scenarios, including current resistance, voltage stability, charging current response and data transmission rate, and constructs a set of electrical performance parameters E.

[0031] The stress analysis module acquires a set of stress response data S of the mobile phone data cable under different bending angles, insertion and removal cycles, and ambient temperature conditions.

[0032] The performance degradation modeling module establishes a corresponding performance degradation correlation model W based on the electrical performance parameter set E and the stress response data set S, which is used to describe the relationship between changes in the internal structure of the data line and the degradation of electrical performance.

[0033] The indicator generation module inputs the historical usage data of the target mobile phone data cable, performs simulation through the W model, and obtains the remaining performance indicator P of the data cable in the current state.

[0034] The risk warning module compares the index P with the set performance threshold Ph to determine whether there is a risk of failure in the data cable. If P < Ph, it outputs a warning message and marks it as a high risk.

[0035] The pattern recognition module outputs the failure location and failure mode of the data cable based on the simulation results, realizing the performance test and failure prediction of the data cable of the target mobile phone.

[0036] In the above technical solution, the technical effects and advantages provided by the present invention are as follows:

[0037] 1. By integrating multi-scene electrical performance acquisition, three-dimensional coupled stress loading, high-dimensional feature extraction, and structural prior modeling, the present invention establishes a performance degradation correlation model W for mobile phone data cables, realizing a complete mapping path from physical response to electrical performance evolution. Compared with traditional methods based on single indicators or manual detection, the present invention can comprehensively capture the multi-dimensional degradation characteristics of data cables during actual use, and has stronger robustness, predictability, and engineering applicability.

[0038] 2. The present invention combines time-recursive simulation and weighted fusion evaluation mechanism to construct a quantifiable remaining performance index P, and further cooperates with threshold judgment and deep recognition network to achieve intelligent fault warning and pattern positioning, significantly improving the accuracy and automation level of fault diagnosis. This method is not only applicable to the quality control and operation and maintenance of consumer electronic products, but also has technical generality and expansion potential for promoting to other flexible cable structures. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments recorded in the present invention, and those of ordinary skill in the art can also obtain other drawings based on these drawings.

[0040] Figure 1 It is the method mind map of the present invention.

[0041] Figure 2 It is the system module mind map of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0042] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Apparently, the described embodiments are some, but not all, of the embodiments of the present invention. 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.

[0043] Example 1. Refer to Figure 1 As shown, a method for testing the performance and predicting faults of a mobile phone data cable in this embodiment includes:

[0044] S100. Collect multiple groups of electrical performance data of the target mobile phone data cable under different test scenarios, including power-on resistance, voltage stability, charging current response, and data transmission rate, and construct an electrical performance parameter set E;

[0045] S200. Obtain a stress response data set S of the mobile phone data cable under different bending angles, insertion and extraction times, and environmental temperature usage conditions;

[0046] S300. According to the electrical performance parameter set E and the stress response data set S, establish a corresponding performance degradation correlation model W to describe the relationship between the internal structure change and the electrical performance decline of the data cable;

[0047] S400. Input the historical usage data of the target mobile phone data cable, and perform simulation through the W model to obtain the remaining performance index P of the data cable in the current state;

[0048] S500. According to the set performance threshold Ph, compare the index P to determine whether there is a fault risk for the data cable. If P < Ph, output a warning message and mark it as a high risk;

[0049] S600. Based on the simulation results, output the fault location and fault mode of the data cable to achieve performance testing and fault prediction of the target mobile phone data cable.

[0050] In a method for testing the performance and predicting faults of a mobile phone data cable proposed by the present invention, step S100 is the acquisition and preprocessing stage of electrical performance data, which is a key basic link for subsequent performance degradation modeling and fault prediction. This step realizes a high-fidelity data modeling of the operating state of the mobile phone data cable by constructing an electrical performance test framework with multiple working conditions and multiple indicators, and cooperating with a high-dimensional feature expression and compression mechanism. This step mainly includes three sub-steps, S101 to S103, specifically as follows:

[0051] S101: First, to comprehensively characterize the electrical performance of the target mobile phone data cable under real-world usage conditions, periodic electrical scans are proposed under four typical operating scenarios:

[0052] (1) Constant voltage charging scenario, that is, using a regulated power supply to perform a standard charging process on the data cable;

[0053] (2) Charging and using scenario, simulating the common usage state of users operating the mobile phone while charging;

[0054] (3) Data synchronization scenario, that is, the process of data transmission via USB connection to PC or other devices;

[0055] (4) Fast charging high load scenario, that is, using a fast charging power supply that supports PD / QC protocol to quickly charge the mobile phone.

[0056] In each scenario, a precision electrical parameter testing module is used to perform periodic electrical scans on the data cable. It is recommended that each scan cycle be set between 100ms and 500ms to balance data accuracy and response efficiency. During the scan, the following key performance indicators are collected:

[0057] Transient resistance: reflects the dynamic impedance change of the data line conductor during the energization process;

[0058] Voltage fluctuation amplitude: measures end-to-end voltage stability and reflects contact quality;

[0059] Dynamic current response: Records the transient current characteristics under varying charging loads;

[0060] Data throughput rate: Reflects the data transfer capability of the USB channel.

[0061] The above indicators constitute the original electrical performance test dataset, covering electrical response information across multiple dimensions and time points.

[0062] S102: To achieve a unified expression of electrical parameters across different scenarios, a method for constructing a four-dimensional electrical performance vector is proposed. Specifically, for each set of raw electrical performance data collected in each scenario, a vector representation is uniformly adopted, in the following form: ;in, Indicates transient resistance. Indicates the voltage fluctuation range. Indicates dynamic current response, This represents the data throughput rate. Vectors obtained from all scenarios are labeled for each scenario, and a normalization mapping function is used to uniformly scale all metrics to the [0,1] range, eliminating the interference of metric dimension differences on subsequent model training.

[0063] Furthermore, the normalized electrical performance vectors collected in each scenario are arranged in chronological order to form a feature matrix Em with time-series resolution capability, the structure of which is shown below:

[0064] Where m is the total number of scenes (4 in this embodiment), and n is the number of time points in each scene. Let n be the four-dimensional electrical performance vector at time n.

[0065] S103: Considering the problems of high dimensionality, high redundancy, and strong correlation in the original feature matrix Em, traditional feature extraction methods (such as PCA or ordinary autoencoders) struggle to achieve effective compression while preserving nonlinear relationships. Therefore, this invention introduces an embedded variational autoencoder (E-VAE) structure to perform feature compression and nonlinear decoupling on the feature matrix.

[0066] The E-VAE architecture consists of an encoder, a latent space, and a decoder, and has the following characteristics:

[0067] The encoder employs a multi-layer convolutional network, which can automatically extract the spatiotemporal coupling features from the electrical performance vectors at each time step;

[0068] The latent space is approximated using a Gaussian distribution to generate statistically meaningful latent representation vectors;

[0069] The decoder is used to reconstruct the original features to verify the integrity of the compressed information. The training objective is to maximize the reconstruction accuracy and minimize the KL divergence.

[0070] The final output is a set of low-dimensional latent electrical expression factors E. These expression factors preserve the dominant trend of electrical performance changes across scenarios, significantly reduce the complexity of model training, and enhance the ability to identify subtle performance degradation features.

[0071] The complete electrical performance acquisition and expression mechanism constructed through S100 not only achieves systematic modeling of the multi-dimensional electrical performance of mobile phone data cables under typical usage scenarios, but also integrates advanced algorithms such as normalized mapping, high-dimensional feature matrix construction, and variational compression at the model structure level. This effectively enhances the sensitivity and generalization ability of the subsequent performance degradation model to early anomalies. Compared with existing schemes that use single-index detection or static testing, this scheme has significant practicality, advancement, and scalability.

[0072] In the mobile phone data cable performance testing and fault prediction method proposed in this invention, step S200 is mainly used to construct the mechanical stress response mechanism of the data cable under real-world usage conditions. By introducing multi-field coupling loading, advanced sensing technology, and multi-dimensional data extraction methods, the system obtains key stress information affecting the lifespan and performance stability of the data cable, and provides accurate structural response data support for subsequent degradation models. This step includes three sub-steps, S201 to S203, as follows:

[0073] S201: To effectively simulate the complex mechanical loads and environmental influences experienced by mobile phone data cables during actual use, this invention proposes the construction of a three-dimensional coupled loading platform. This platform consists of the following modules:

[0074] Programmable flexible loading mechanism: Employing a multi-axis servo actuator combined with a flexible robotic arm system, it achieves continuous multi-angle loading control of the target data line in the horizontal, vertical, and spatial bending directions. The bending angle range is designed to be 0°~180°, with a control accuracy better than ±1°.

[0075] Insertion and removal cycle drive unit: Through the electronically controlled propulsion module and the standard USB interface socket, it simulates the frequent insertion and removal actions of actual users. The insertion and removal frequency can be set between 0.5Hz and 2Hz, and it supports more than 10,000 cycles.

[0076] Environmental temperature control module: It adopts thermoelectric cooling chip and PID temperature control system to realize constant temperature (±0.5℃ control accuracy) and variable temperature (rise / fall rate controlled within 2℃ / min) environment simulation. The temperature range is set to −20℃ to +60℃, covering the daily use environment.

[0077] The aforementioned 3D loading platform uses a central controller to orchestrate load paths, supporting the application of loads in a predetermined sequence and time step, thus enabling the construction of typical stress field conditions with high repeatability and controllability. This platform can simulate stress-induced degradation processes such as material fatigue, conductor breakage, and sheath damage in data cables caused by frequent bending, excessive insertion and removal, and extreme temperature variations.

[0078] S202: To accurately capture the mechanical response of the data line under various loading combinations, this invention simultaneously deploys a multimodal sensing system during the loading process, specifically including:

[0079] Fiber Optic Strain Array Sensor: A miniature fiber optic grating (FBG) array is uniformly distributed on the outer layer of the data line, with a sensing point arranged at 5mm intervals, for real-time measurement of local strain field distribution. FBG sensors have the advantages of high sensitivity, resistance to electromagnetic interference, and the ability to achieve long-distance synchronous acquisition, making them suitable for monitoring flexible structures.

[0080] Miniature thermocouple probe: A T-type thermocouple is installed at the junction of the data cable core and the sheath to monitor key thermal response characteristics of the conductor material under different ambient temperatures, such as the heat conduction path and local abnormal temperature rise areas.

[0081] The aforementioned sensing system, through a synchronous acquisition unit and clock synchronization protocol, ensures complete alignment of strain and temperature signals at every load moment. Under each loading condition, the system acquires and forms a high-resolution stress response matrix Si with spatial, temporal, and multi-physical quantity coupling properties, the structure of which can be expressed as: ; where ε(x,y,t) represents the strain response of each sensing node at a certain moment, and T(x,y,t) represents the corresponding temperature distribution.

[0082] This matrix can effectively reflect the local damage evolution trend, potential microcrack initiation points, and abnormal thermal diffusion paths of the internal structure of materials under composite stress fields, providing a rich source of information for constructing damage sensing mechanisms and degradation prediction models.

[0083] S203: Given the large amount of data, high dimensionality, and information redundancy in the original stress response matrix Si, directly using it for modeling would lead to decreased computational efficiency and potentially introduce overfitting risks. Therefore, this invention proposes a tensor decomposition method to reduce the dimensionality of all Si data.

[0084] Specifically, the Higher-Order Singular Value Decomposition (HOSVD) algorithm is used to extract principal components from the three-dimensional tensor Si, compressing the multidimensional stress response information into several representative tensor principal component vectors to form a representative stress principal feature space.

[0085] After HOSVD processing, a set of low-dimensional key stress principal element features Si′ was obtained, which contains the stress field distribution information that has the greatest impact on the data line structure performance under this working condition. The Si′ features under all loading combinations were integrated to form a multi-dimensional stress response dataset S. ;

[0086] Where z is the number of loading condition combinations, and each Si′ corresponds to the principal stress feature under a loading combination scenario.

[0087] Through the implementation of S200 above, this invention can accurately simulate typical stress loading conditions during the use of mobile phone data cables under non-destructive conditions, and collect stress response data at the microstructural level through a multimodal sensing mechanism. Combined with high-dimensional tensor dimensionality reduction technology, a compact set of expression features S that can be used for modeling and analysis is ultimately formed. Compared with traditional single-field loading or purely empirical modeling methods, this method has stronger structural adaptability, anomaly sensitivity, and modeling versatility, and is a key foundation for achieving accurate performance degradation modeling and fault prediction.

[0088] In the mobile phone data cable performance testing and fault prediction method proposed in this invention, step S300 is used to construct a performance degradation correlation model W, which is the core bridge connecting the nonlinear relationship between electrical performance parameters and structural stress response. By integrating high-dimensional feature alignment, multimodal data fusion, structural knowledge embedding, and time-series prediction mechanisms, the modeling and prediction of the time evolution law of the electrical performance of the data cable under complex stress paths are realized. This step includes three sub-steps, S301 to S303, as follows:

[0089] S301: Since the electrical performance parameter set E and the stress response data set S originate from different subsystems, and there are inconsistencies in sampling frequency, time dimension, and structural dimension, directly inputting them into the modeling module will lead to problems such as information coupling failure and training non-convergence. Therefore, it is necessary to first complete the timestamp alignment and feature synchronization processing of the two types of data.

[0090] In this embodiment, a time series registration algorithm based on a sliding window is used to resample and interpolate the original data of E and S, unify the time axis dimension, and construct a joint input sequence with frame-to-frame correspondence: Xt=[et∥st] where et represents the electrical performance feature vector in the t-th frame, st is the corresponding stress principal element feature vector, and ∥ represents the vector concatenation operation.

[0091] To extract high-dimensional correlation features, this invention constructs a multi-channel residual fusion network, whose structural features are as follows:

[0092] Dual-input branch structure: Independent convolution channels are constructed for the electrical performance vector and the stress vector respectively to extract local features of each data class;

[0093] Feature cross residual blocks: Introducing cross-modal interaction paths through residual connections, enabling the fusion of information between different feature dimensions and avoiding gradient vanishing;

[0094] Multi-scale convergence module: Integrates multi-granularity information extracted by different convolutional kernels to improve the model's sensitivity to temporal pattern changes.

[0095] The final output is a unified correlation feature tensor Ft∈Rk, which serves as the input for subsequent structural graph embedding and temporal modeling.

[0096] S302: Considering the typical structural damage evolution path of data cables during degradation, such as core wire fatigue fracture extending outwards from the center and sheath aging often starting at bending stress concentration points, data-driven models alone easily overlook these prior laws. To enhance the physical rationality and structural explanatory power of the model, this invention introduces a structural embedding tensor as a constraint mechanism.

[0097] The construction method is as follows:

[0098] Based on the spatial distribution of stress response in S200, response significance indicators at different locations inside the data line are extracted, and a spatial node set V={v1,v2,...,vm} is constructed; m is the total number of nodes.

[0099] Construct an adjacency matrix A of stress propagation paths and material coupling relationships between nodes, and then construct a spatial graph using graph convolution methods;

[0100] The structural nodes and their adjacency relationships are encoded into tensor form SET and fused with the feature tensor Ft, which serves as the input model W for structural prior constraints.

[0101] The structural embedding tensor-guided model prioritizes feature changes in key structural regions when learning degradation trends, giving the W model stronger physical interpretability and predictive rationality.

[0102] S303: Performance degradation is a complex evolutionary process characterized by nonlinearity, temporality, and path dependence. To accurately simulate the dynamic decay of electrical performance over the usage period, this invention proposes using a time-series prediction module based on an LSTM-GRU hybrid unit to train the W model.

[0103] This hybrid unit structure has the following advantages:

[0104] LSTM (Long Short-Term Memory) networks excel at modeling long-term dependencies and are well-suited for capturing the degradation trends of devices over hundreds of cycles.

[0105] GRU (Gated Cyclic Unit) has high computational efficiency and fewer parameters, making it more suitable for handling abrupt changes within short cycles.

[0106] By cascading LSTM and GRU structures, the model can achieve both global trend modeling and local anomaly detection capabilities.

[0107] The training input is a fusion feature tensor {F1, F2, ..., FT} of time series data, and the output is the predicted electrical performance index {e1, e2, ..., eT} at the corresponding time step. The model loss function is jointly optimized using weighted mean squared error and structural consistency loss. Where Dstruct represents the difference measure function between the predicted features and the structural prior, which can be cosine similarity distance or KL divergence; Mean squared error (MSE) measures the deviation between the model's predicted values ​​and the true values, and is the primary supervised objective during training. α and β represent weight coefficients (positive real numbers) used to adjust the relative importance of the two parts of the loss function: α controls the model's focus on prediction accuracy; β controls the model's learning intensity regarding structural consistency. A typical setting is α=1.0, β=0.2: prioritizing prediction accuracy, with structure as an auxiliary factor; dynamic optimization through cross-validation is also possible.

[0108] In the mobile phone data cable performance testing and fault prediction method proposed in this invention, step S400 aims to simulate and predict the current performance status of the target data cable based on real user behavior data and using a trained performance degradation correlation model W, generating a quantitative indicator reflecting its health level. This step, based on the W model, outputs a determinable remaining performance indicator Po through time recursion and parameter aggregation mechanisms, providing data support for subsequent risk warning. This step includes three sub-steps, S401 to S403, as follows:

[0109] S401: Considering that the performance degradation of data cables is closely related to their actual usage, static testing alone is insufficient to accurately assess their lifespan. Therefore, this invention designs a mechanism for collecting behavioral data and constructing vectors. The collected historical behavioral data includes, but is not limited to, the following key dimensions:

[0110] Cumulative insertion and removal cycles: The connection cycle is recorded through an embedded interface counting module, reflecting the fatigue level of the contact end;

[0111] Typical bending trajectory: The bending angle and frequency during daily use are recorded using an embedded IMU (Inertial Measurement Unit), and the deformation pattern is extracted;

[0112] Total charging time and cycle distribution: Daily charging time and charging behavior patterns are statistically analyzed through the port power supply current monitoring module;

[0113] Ambient temperature distribution: Combined with environmental sensors to record changes in external air temperature, the impact of thermal cycling on performance is evaluated;

[0114] Usage scenario tags: Usage background classification variables are constructed based on historical charging environments (such as fast charging, in-vehicle charging, and charging while using).

[0115] The above raw behavioral data is uniformly encoded and time-series processed to construct a multi-dimensional time-series vector set, denoted as: ; This indicates that the data line uses a state vector at time step t, where s is the number of behavioral dimensions used.

[0116] To adapt to the model input format, Normalization and window sliding are performed to form a historical behavior sequence within the time window. T represents the window length, which serves as the basis for the input data of model W.

[0117] S402: Use the constructed behavior vector sequence as described above. The input is fed into the pre-trained performance degradation correlation model W, which utilizes its time recursion and state transition capabilities to simulate the performance state within a short future window.

[0118] The model W incorporates an LSTM-GRU hybrid prediction unit (see S303) to recursively generate predicted values ​​of key electrical performance of the data line from the present to several future time points, under the constraint of the structural prior tensor SET. This forms the simulated state curve Pt, specifically in the following form: ;in: This represents the predicted transient resistance; This represents the predicted dynamic current response; This represents the predicted data throughput rate. The entire simulation path can be viewed as the trajectory of the electrical performance evolution of the target data line over a future period under current usage trends.

[0119] To ensure the stability and physical consistency of the simulation output, model W also introduces an internal regularization mechanism and a historical trajectory alignment module during the recursive process, ensuring that the output results fluctuate reasonably within the boundary conditions and avoiding prediction offset or oscillation.

[0120] S403: After obtaining the simulated state curve Pt, in order to more intuitively reflect the current health status and potential fault risk of the data line, this invention proposes to construct a weighted fusion performance evaluation function, which compresses and reduces multiple predicted electrical performance parameters to a single numerical index: the residual performance index Po.

[0121] The construction method is as follows:

[0122] right Perform first-order difference operation and weighted average fusion of the calculation results to obtain the residual performance index Po: the final generated Po value ranges from [0,1], where close to 1 indicates good performance and close to 0 indicates significant performance degradation.

[0123] In the mobile phone data cable performance testing and fault prediction method proposed in this invention, steps S500 and S600 respectively complete the intelligent judgment of the performance status of the target data cable and the fault identification and location function, which are the key technical links to realize the transformation from prediction results to practical output.

[0124] By combining the performance threshold judgment logic with the multi-source information fusion inference model, not only can it accurately determine whether the target data line is currently on the verge of potential failure, but it can also further output the specific fault location and possible fault mode types, providing direct technical support for product warning, quality traceability, and structural improvement. The following details the specific implementations of S500 and S600:

[0125] S500: After obtaining the remaining performance index P of the current data line (generated by S403), compare and judge whether this index is in the failure critical state according to the preset performance safety threshold Ph, so as to trigger the risk warning mechanism.

[0126] In this embodiment, the performance threshold Ph is set according to a large amount of experimental data and engineering tolerance requirements, and its definition is as follows:

[0127] Ph ∈ (0, 1), and its value reflects the lower allowable level of electrical performance degradation. Below this value, faults such as intermittent charging, data transmission failure, or thermal failure may occur.

[0128] The warning logic of the system is as follows:

[0129] If the current remaining performance index P ≥ Ph, the system considers that the data line is in the normal working range, and the status is marked as "safe";

[0130] If P < Ph, the system identifies that there is a potential failure risk, the status is marked as "high risk", and automatically outputs a warning message W, the content of which includes:

[0131] Data line identification information;

[0132] The current predicted remaining performance value P;

[0133] The triggered risk level;

[0134] Suggested handling measures (such as reminding to replace, using with temporary load limit, detecting at the detection station, etc.).

[0135] In addition, to improve the practicability of the system, the warning message W can be synchronously uploaded to the upper-level system or the mobile APP through the local interface (such as screen prompt or LED indicator) or the wireless communication module (such as Bluetooth, WiFi), facilitating users or maintenance personnel to grasp the running status of the data line in real time.

[0136] S600: After determining that there is a fault risk, further implement the S600 step to analyze the spatial distribution characteristics and mode types of the fault, that is, to realize the structural fault location and classification of the target data line.

[0137] The key technology in this step is to combine the intermediate variables predicted by model W (such as stress feature mapping, thermal response distribution, and electrical parameter mutation points) with the structural prior information SET to construct a localization mechanism based on rule reasoning and deep feature fusion.

[0138] Specifically, it includes the following sub-processes:

[0139] S601: Combining the stress response data collected in S200 with the structural embedding tensor SET in S302, a multidimensional position mapping function is constructed: L=floc(SET,∇Pt); representing the gradient rate of change of electrical parameters along time or structural nodes, reflecting the region of accelerated local performance degradation. The function floc can be implemented in the following way:

[0140] Local rate of change analysis is performed on the resistance and current response curves to identify "abrupt change points";

[0141] By linking the time node corresponding to the mutation point with the location of the stress sensor, the location of the fault in the physical space can be deduced.

[0142] Output the location coordinates L, or use the structural section number (such as "connector A to cable section B").

[0143] This method allows for accurate marking of locations such as "fatigue fracture in the middle of the conductor," "local damage to the sheath," or "abnormal contact of the plug."

[0144] S602: Based on the differences in characteristic patterns corresponding to different fault manifestations, a fault mode determination mechanism is proposed. The system performs pattern recognition based on the multi-parameter evolution path output by model W and the SET graph. Common fault modes include, but are not limited to:

[0145] Resistance-type faults (such as partial wire breakage): manifested as a sudden increase in Rt and a decrease in It;

[0146] Poor contact type faults (such as loose plugs): manifested as increased voltage fluctuations and intermittent decreases in data rate;

[0147] Thermal degradation faults (such as insulation deterioration due to overheating): manifested as long-term abnormal thermal response and slow parameter drift;

[0148] Frequent bending fatigue failure: manifested as continuous oscillation of electrical parameters corresponding to stress concentration points.

[0149] In this embodiment, a lightweight fault classification network based on the attention mechanism (Fault Attention Network, FAN-Net) is adopted to compare the known fault template library with the current predicted features and complete the rapid matching output of multiple fault modes. The output result form is: M = Mode(Pt, SET) → "poor contact" / "fracture trend" / ...; The coordinated implementation of S500 and S600 enables the present invention to not only have the performance prediction ability, but also have practical decision-making value and engineering adaptability. Different from the existing methods that only provide numerical detection or rough failure judgment, the method described in the present invention can achieve the following innovative effects:

[0150] Convert the numerical prediction result into a clear "high risk" / "safe" state for quick response; achieve physical-level positioning through high-resolution stress mapping and model-embedded structural knowledge; combine deep learning with the prior rule library to accurately discriminate different degradation mechanisms; can be linked with the backend maintenance platform or terminal device to support prompting, recall or restriction strategies.

[0151] In summary, S500 and S600 are the key steps for the present invention to transition from a data-driven model to intelligent decision-making and application deployment, significantly improving the engineering feasibility and technological advancement of the present invention.

[0152] Embodiment 2, please refer to Figure 2 As shown, a mobile phone data cable performance testing and fault prediction system described in this embodiment includes:

[0153] A data acquisition module that acquires multiple groups of electrical performance data of the target mobile phone data cable in different test scenarios, including the on-resistance, voltage stability, charging current response, and data transmission rate, and constructs an electrical performance parameter set E;

[0154] A stress analysis module that obtains a stress response data set S of the mobile phone data cable under different bending angles, plugging and unplugging times, and environmental temperature usage conditions;

[0155] A performance degradation modeling module that establishes a corresponding performance degradation correlation model W according to the electrical performance parameter set E and the stress response data set S to describe the relationship between the internal structure change and the electrical performance decline of the data cable;

[0156] An index generation module that inputs the historical usage data of the target mobile phone data cable and performs simulation through the W model to obtain the remaining performance index P of the data cable in the current state;

[0157] A risk warning module that compares the index P with a set performance threshold Ph to determine whether there is a fault risk for the data cable. If P < Ph, it outputs a warning message and marks it as high risk;

[0158] The pattern recognition module outputs the fault location and fault mode of the data cable based on the simulation results, thereby realizing performance testing and fault prediction of the target mobile phone data cable.

[0159] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.

Claims

1. A method for performance testing and fault prediction of mobile phone data cables, characterized in that: Including: S100. Collect multiple groups of electrical performance data of the target mobile phone data cable under different test scenarios, including power-on resistance, voltage stability, charging current response, and data transmission rate, and construct an electrical performance parameter set E; S200. Obtain a stress response data set S of the mobile phone data cable under different bending angles, plugging and unplugging times, and environmental temperature usage conditions; The S200 includes: S201. Construct a three-dimensional coupled loading platform, and use a programmable flexible mechanism to apply combined control of different bending angles, plugging and unplugging cycles, and constant temperature / variable temperature environments to the target data cable to achieve simulation of typical stress field conditions; S202. Synchronously deploy a strain fiber array sensor and a micro-thermocouple under each loading combination condition, and record in real time the strain distribution, micro-crack induction points, and abnormal heat conduction paths of the outer sheath and conductor core wire of the data cable to form a high-resolution stress response matrix Si; S203. Use the tensor decomposition method to perform dimensionality reduction processing on all Sis, extract key stress principal element features, and construct a multi-dimensional stress response data set S; S300. According to the electrical performance parameter set E and the stress response data set S, establish a corresponding performance degradation correlation model W to describe the relationship between the internal structure change and the electrical performance decline of the data cable; The S300 includes: S301. Align the time stamps and synchronize the features of the constructed electrical performance parameter set E and the extracted stress response data set S, and use a multi-channel residual fusion network to achieve high-dimensional correlation extraction of stress and electrical characteristics; S302. Introduce a structure embedding tensor to construct an implicit variable map of the internal structure change of the data cable, and embed it into the performance degradation correlation model W as a model structure constraint condition; S303. Use a time series prediction module based on a hybrid unit of LSTM-GRU to dynamically train the model W so that it can simulate the non-linear degradation process of electrical performance parameters over time or the number of cycles under the drive of different stress paths; S400. Input the historical usage data of the target mobile phone data cable, and perform simulation through the W model to obtain the remaining performance index P of the data cable in the current state; The S400 includes: S401. Collect the historical usage data of the target mobile phone data cable, including the cumulative number of plugging and unplugging times, typical bending trajectories, total charging duration, environmental temperature distribution, and usage scenario labels, and construct a usage behavior vector sequence Ut; S402. Input the behavior vector Ut into the trained performance degradation correlation model W, and use the model's time recursion capability to calculate the electrical performance evolution path within the prediction window, outputting the simulated state curve Pt, specifically in the form of: ;in: This represents the predicted transient resistance; This represents the predicted dynamic current response; This indicates the predicted data throughput rate; S403. Based on the dynamic change rates of resistance, current, and speed parameters in the simulation results, a weighted fusion index function is constructed to aggregate and reduce Pt, generating the data line residual performance index P in the current state. Specifically, this includes: Perform first-order difference operations and then perform weighted average fusion of the calculation results to obtain the data line residual performance index P; S500. According to the set performance threshold Ph, compare the index P to determine whether there is a fault risk for the data cable. If P < Ph, output a warning message and mark it as a high risk; S600. Based on the simulation results, output the fault location and fault mode of the data cable to achieve performance testing and fault prediction of the target mobile phone data cable.

2. The method for performance testing and fault prediction of a mobile phone data cable according to claim 1, characterized in that: The S100 includes: S101. Perform periodic electrical scans on the target mobile phone data cable under four typical usage scenarios of constant voltage charging, charging while using, data synchronization, and fast charging with high load, and obtain the transient resistance, voltage fluctuation amplitude, dynamic current response, and data throughput rate under each scenario; S102. Construct a four-dimensional electrical performance vector based on each set of original test data, and uniformly map the electrical performance characteristics in each test scenario into a normalized parameter space to form a feature matrix Em that can be distinguished in the time series dimension; S103. Perform feature compression and non-linear decoupling on Em through an embedded variational autoencoder to extract a low-dimensional latent electrical expression factor E.

3. A mobile phone data cable performance testing and fault prediction system, used to implement the mobile phone data cable performance testing and fault prediction method according to any one of claims 1-2, characterized in that: It includes: A data acquisition module that acquires multiple sets of electrical performance data of the target mobile phone data cable under different test scenarios, including the on-resistance, voltage stability, charging current response, and data transmission rate, and constructs an electrical performance parameter set E; A stress analysis module that obtains a stress response data set S of the mobile phone data cable under different bending angles, insertion and extraction times, and environmental temperature usage conditions; A performance degradation modeling module that establishes a corresponding performance degradation correlation model W according to the electrical performance parameter set E and the stress response data set S, and is used to describe the relationship between the internal structure change of the data cable and the electrical performance decline; An index generation module that inputs the historical usage data of the target mobile phone data cable, and performs simulation through the W model to obtain the remaining performance index P of the data cable in the current state; A risk warning module that compares the index P with a set performance threshold Ph to judge whether there is a fault risk in the data cable. If P < Ph, an early warning message is output and marked as a high risk; A pattern recognition module that outputs the fault location and fault mode of the data cable according to the simulation results, and realizes the performance test and fault prediction of the target mobile phone data cable.

Images