A method for testing coupling of dynamic load and electromagnetic interference of wiring harness

Abstract

The present invention discloses a method for testing the coupling of dynamic load and electromagnetic interference in a wiring harness, which relates to the field of wiring harness testing technology. The method comprises the following steps: S1, defining several environmental parameter groups and constructing a test platform; S2, synchronously applying dynamic current pulses and multi-axis vibration excitation; S3, applying broadband electromagnetic interference signals and monitoring changes in signal crosstalk amplitude and bit error rate; S4, dynamically configuring sensor nodes based on the wiring harness topology; S5, generating feature vectors; S6, outputting wiring harness performance indicators; S7, outputting a wiring harness failure probability prediction value; S8, obtaining prediction data; S9, triggering a high-speed data recording mode to store raw sensor data 60 seconds before the failure; and dynamically adjusting the gradient step size and loading sequence in the environmental parameter group. This application enables performance evaluation, fault prediction, and life management of wiring harnesses under complex operating conditions, thereby improving the reliability and safety of automotive electrical systems.

Description

Technical Field

[0001] The present invention relates to the technical field of wire harness testing, and in particular to a method for testing coupling of dynamic load and electromagnetic interference of a wire harness. Background Art

[0002] As a key component of the automotive electrical system, the wiring harness performs the crucial functions of power and signal transmission, and its performance is directly related to the safety and reliability of the entire vehicle. With the rapid development of the new energy vehicle industry, high-voltage wiring harnesses face a more complex operating environment. They must not only withstand physical stresses such as dynamic current pulses and mechanical vibration, but also resist electromagnetic interference from onboard electronic devices and the external environment. Therefore, accurately testing the performance of wiring harnesses under multi-physics coupling conditions has become a critical issue that the industry urgently needs to address.

[0003] Currently, the wiring harness testing technology has the following main limitations:

[0004] First, the environmental simulation is too simplistic. Traditional testing cannot simulate the complex multi-physics coupling conditions found in actual vehicle operation. For example, current load testing alone fails to account for the impact of vibration and electromagnetic interference on current transmission stability. Vibration testing, on the other hand, lacks the synergy between the electrical and electromagnetic environments, leading to significant deviations between test results and actual operating conditions. This makes it difficult to truly reflect the performance degradation patterns of wiring harnesses under combined stresses.

[0005] Second, data collection and analysis methods are outdated. Existing tests struggle to comprehensively and in real time collect multi-dimensional data such as temperature, strain, and current waveforms at key wiring harness nodes. Furthermore, traditional data processing methods primarily rely on static feature analysis, which is unable to effectively extract timing correlation features under dynamic loads and electromagnetic interference. This results in inaccurate and ineffective wiring harness performance assessments, making it difficult to accurately predict early-stage failures.

[0006] Third, fault prediction and lifespan assessment models are imperfect. Current wiring harness fault prediction lacks in-depth analysis of multi-parameter coupling relationships under complex operating conditions. Furthermore, finite element simulation models lack real-world data, resulting in inefficient parameter correction and difficulty accurately predicting wiring harness degradation trends over long-term operation. This makes it difficult to meet the design and verification requirements for high-reliability, long-life wiring harnesses for new energy vehicles.

[0007] In summary, existing wiring harness testing technology has obvious shortcomings in simulating complex working conditions, multi-dimensional data collection and analysis, and fault prediction. There is an urgent need for a testing method that can realize dynamic load and electromagnetic interference coupling testing, accurate feature extraction, and reliable life assessment to ensure the safe and stable operation of automotive electrical systems. Summary of the Invention

[0008] In view of this, the technical problem to be solved by the present invention is: to provide a wiring harness dynamic load and electromagnetic interference coupling test method, which can perform performance evaluation, fault prediction and life management of the wiring harness under complex working conditions, and improve the reliability and safety of the automotive electrical system.

[0009] In order to solve the above technical problems, the technical solution of the present invention is:

[0010] A method for testing coupling of dynamic load and electromagnetic interference of a wiring harness comprises the following steps:

[0011] S1. Define several environmental parameter groups, including dynamic current pulse gradient, multi-axis vibration frequency gradient, electromagnetic interference frequency gradient, and corrosion acceleration factor concentration gradient; construct a test platform, which includes a dynamic current generator, a multi-axis vibration table, an electromagnetic interference source, a data acquisition system, and a three-axis orthogonal electromagnetic shielding cabin. The cabin shielding effectiveness is ≥80dB, and the cabin is equipped with absorbing materials with a coverage rate of 90% or more.

[0012] S2: Dynamic current pulse loads are applied to the wiring harness based on a dynamic current pulse gradient, and multi-axis vibration excitation is applied to the wiring harness based on a multi-axis vibration frequency gradient. The dynamic current pulse and multi-axis vibration excitation are applied synchronously with a preset phase difference of 0° to 180°, simulating the transient high current and mechanical stress complex environment in actual vehicle operation.

[0013] S3. Apply a broadband electromagnetic interference signal to a wiring harness on a test platform. The wiring harness includes a high-voltage wiring harness and an adjacent low-voltage signal wiring harness. Use a bit error rate monitoring device to monitor the signal crosstalk amplitude and bit error rate changes between the high-voltage wiring harness and the low-voltage signal wiring harness in real time.

[0014] S4, collecting temperature, strain, and high-frequency current waveform data of several designated sensor nodes in the harness in real time through a distributed fiber grating sensor network, where the sensor nodes are dynamically configured according to the harness topology;

[0015] S5. Extract features from the dynamic data collected at several sensor nodes to generate feature vectors, where the feature vectors include the temperature gradient change rate, the dynamic current harmonic distortion rate, and the vibration spectrum energy distribution;

[0016] S6. Input the feature vector into the wiring harness parameter performance analysis model. The wiring harness parameter performance analysis model is deployed on the edge computing device. The temporal-spatial feature extraction is performed through a double-layer bidirectional gated recurrent unit to obtain the target high-dimensional feature vector. The parameter performance regression analysis is performed through the classification regression layer to output the wiring harness performance index.

[0017] S7. Input the feature vector into the wiring harness fault prediction network. The wiring harness fault prediction network is deployed on the edge computing device. The hidden features are extracted through the bidirectional long short-term memory layer. After fusion through the fully connected layer, the wiring harness fault probability prediction value is output.

[0018] S8. Correct the electrical-thermal-mechanical coupling parameters of the wiring harness based on the digital twin simulation model, and predict the remaining service life and fault threshold of the wiring harness by combining the measured data of S3 and S4 to obtain predicted data;

[0019] S9: When the predicted value of the wiring harness failure probability exceeds the threshold or the failure threshold predicted by S8 is exceeded, the high-speed data recording mode is triggered to store the raw sensor data 60 seconds before the failure; the prediction result of S8 is fed back to S1 to dynamically adjust the gradient step size and loading sequence in the environmental parameter group.

[0020] Preferably, in S2, the loading range of the dynamic current pulse load is 200A to 500A, the pulse duration is 1ms to 10ms, the frequency is 1Hz to 100Hz, and the time deviation between the rising edge of the dynamic current pulse and the vibration peak moment is ≤1ms;

[0021] The multi-axis vibration excitation includes vibration frequency gradients in the X-axis, Y-axis, and Z-axis directions. The vibration frequency ranges of the X-axis, Y-axis, and Z-axis are all 10Hz to 500Hz, and the acceleration amplitude is 0.5g to 20g.

[0022] Preferably, in S3, the injection frequency band of the broadband electromagnetic interference signal is 1 MHz to 6 GHz, the interference intensity is 10 V / m to 100 V / m, and the superposition mode includes radiation interference and conduction interference;

[0023] Radiated interference includes the electromagnetic field formed around the wiring harness through electromagnetic radiators, and conducted interference includes conduction through direct connection of the wiring harness through a coupler. The power ratio of radiated interference to conducted interference is 3:1 to 1:3.

[0024] Preferably, in S4, the arrangement density of the distributed fiber Bragg grating sensor network is one sensor node every 10 cm to 20 cm, the spatial resolution is ±2 mm, the temperature measurement accuracy is ±0.5 ° C, the strain measurement accuracy is ±1 με, the sampling frequency is 10 Hz to 10 kHz, the fiber Bragg grating sensor is shielded by a metal braid layer with a shielding effectiveness of ≥60 dB, and data transmission adopts a wavelength division multiplexing method;

[0025] The sensor nodes and the bit error rate monitoring equipment in S3 are synchronized through the PTP precise time protocol, and the clock deviation is ≤50μs.

[0026] Preferably, in S5, the temperature gradient change rate is calculated as follows: dT / dt=(T(t+Δt)-T(t)) / Δt, where T(t) is the temperature at the current moment, T(t+Δt) is the temperature at the next moment, Δt is the sampling interval, and the sampling interval is 0.1 seconds to 10 seconds. The temperature gradient change rate is used to evaluate the thermal stability and failure risk of the wiring harness, and the threshold range is 0.1°C / s to 5°C / s;

[0027] When the temperature gradient change rate dT / dt>5°C / s, the dynamic current load is cut off, the multi-axis vibration excitation is stopped and the electromagnetic interference source is turned off.

[0028] Preferably, in S5, feature extraction includes performing fast Fourier transform analysis on the dynamic current waveform, extracting the total harmonic distortion rate and the energy proportion of the high-frequency component, performing time series analysis on the temperature data, calculating the temperature gradient change rate and the temperature fluctuation standard deviation, performing wavelet transform analysis on the vibration data, and extracting the vibration spectrum energy distribution.

[0029] Preferably, in S6, the double-layer bidirectional gated recurrent unit includes a first-layer bidirectional recurrent neural network and a second-layer gated recurrent unit, the hidden layer dimension of the first-layer bidirectional recurrent neural network is 64, and the hidden layer dimension of the second-layer gated recurrent unit is 32. The time series features are weightedly fused through the attention mechanism, and the target high-dimensional feature vector with a dimension of 128 is generated after dimensionality reduction.

[0030] Preferably, in S7, the bidirectional long short-term memory layer includes an attention mechanism module, the hidden layer dimensions of the forward LSTM and the backward LSTM are both 64, the attention mechanism module calculates the dot product of the query vector and the time series feature to generate the attention weight, and inputs the weighted feature into the fully connected layer. The fully connected layer includes 3 hidden layers, and the number of neurons is 128, 64, and 32 respectively.

[0031] Preferably, in S8, the digital twin simulation model is constructed based on finite element analysis, including an electric-thermal coupling sub-model, a thermal-mechanical coupling sub-model and an aging prediction sub-model. The model parameters are corrected by a Bayesian optimization algorithm to predict the remaining service life of the wiring harness at time nodes of 1000 hours, 5000 hours and 10,000 hours.

[0032] Preferably, in S8, the fault threshold is determined based on: when the harness resistance change rate exceeds 50% or the signal error rate exceeds 10 -4 When , a fault warning signal is triggered; the resistance change rate calculation formula is: (ΔR) / R0=((Rt-R0)) / R0×100%, where R0 is the initial reference resistance, Rt is the real-time working resistance, and ΔR is the absolute change in resistance;

[0033] The digital twin simulation model uses a Bayesian optimization algorithm to correct parameters, with a convergence condition of less than 5% root mean square error between measured and simulated data. The model accuracy is recalibrated every 24 hours, and the aging prediction sub-model is reconstructed when the error is greater than 5% for three consecutive calibrations.

[0034] The resistance change rate is calculated by comparing the current resistance value with the initial resistance value, and the signal bit error rate is determined by measuring the ratio of the number of bit errors per unit time to the total number of transmitted bits using a bit error meter.

[0035] The aging prediction sub-model introduces hydrogen sulfide concentration as a corrosion acceleration factor with a concentration gradient of 10ppm to 1000ppm. The concentration gradient is dynamically adjusted according to the type of wire harness sheath material: rubber materials use 10ppm to 500ppm, and silicone materials use 200ppm to 1000ppm.

[0036] After adopting the above technical solution, the beneficial effects of the present invention are:

[0037] 1. The present invention can significantly improve the authenticity of composite environment simulation. Among them, the precise synchronous loading (S2) of dynamic current pulses and multi-axis vibrations is achieved through 0°~180° phase difference control, which fundamentally solves the inherent defects of electromechanical stress timing separation in traditional tests. This design significantly improves the reproducibility of extreme working conditions such as sudden acceleration and braking by simulating the composite environment of transient high current and mechanical stress in actual vehicle operation. The adjustable phase difference mechanism can accurately match the electromechanical coupling characteristics of different vehicle models. The strict alignment of the rising edge of the dynamic current pulse and the vibration peak effectively suppresses the contact resistance fluctuations and terminal micro-wear caused by mechanical vibration, providing a real physical environment basis for the performance degradation research of wiring harnesses under composite stress.

[0038] 2. The present invention can break through the synergy of multi-physical field monitoring. Among them, the collaborative architecture (S1+S4) of the three-axis orthogonal electromagnetic shielding cabin (shielding effectiveness ≥80dB) and the distributed fiber grating sensor network constructs a multi-physical field synchronous monitoring system in an electromagnetically pure environment. The high coverage of the absorbing material in the shielding cabin combined with the metal braided layer shielding design of the optical fiber sensor can still ensure the acquisition accuracy of temperature, strain, and current waveform data under strong electromagnetic interference conditions. The clock synchronization between the sensor node and the bit error rate monitoring equipment is achieved through the PTP precise time protocol, which solves the pain point of data time and space inaccuracy in traditional step-by-step testing, and provides a highly consistent data foundation for crosstalk analysis of high-voltage and low-voltage signal harnesses and research on electro-thermal-mechanical coupling effects.

[0039] 3. Fault prediction reliability has been substantially enhanced. A dual-path parallel processing architecture (S6+S7) employing a GRU performance analysis model and an LSTM fault prediction model fully leverages the time series model's ability to deeply analyze dynamic feature vectors. The GRU network extracts the spatiotemporal evolution of wiring harness performance indicators through a two-layer, bidirectional structure, while the LSTM network focuses on identifying long-term dependencies in fault characteristics. The complementary fusion of the two models significantly improves the ability to detect hidden faults such as microcracks in the insulation layer and fatigue fractures in conductors. A dual judgment mechanism (S9) combining fault probability prediction values ​​with physical thresholds (such as resistance change rate) establishes a multi-level protection system from early warning to fuse protection, significantly reducing the risk of misjudgment caused by single sensor failure.

[0040] 4. Comprehensively optimize test efficiency and cost structure. The dynamic adjustment mechanism for the concentration gradient of the corrosion acceleration factor (S1) and the feedback loop of the digital twin prediction results (S9) form an adaptive optimization system for environmental parameters. This design automatically matches the hydrogen sulfide concentration gradient according to the type of wire harness sheath material (rubber / silicone), accelerating aging while ensuring the authenticity of the material degradation mechanism. The digital twin simulation model corrects the electrical, thermal, and mechanical coupling parameters in real time, and the prediction results are fed back to the test parameter definition link, realizing the iteration of the test load sequence. This closed-loop architecture significantly shortens the equivalent aging test cycle, reduces the energy consumption cost of repeated tests, and provides an efficient verification platform for wire harness design. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The present invention will be further described below with reference to the accompanying drawings and examples.

[0042] Figure 1 It is a structural schematic diagram of a method for testing coupling of dynamic load and electromagnetic interference of a wiring harness according to an embodiment of the present invention. DETAILED DESCRIPTION

[0043] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0044] The method for testing the coupling of dynamic load and electromagnetic interference of a wiring harness of the present invention comprises the following steps:

[0045] S1. Define several environmental parameter groups, including dynamic current pulse gradient, multi-axis vibration frequency gradient, electromagnetic interference frequency gradient, and corrosion acceleration factor concentration gradient; construct a test platform, which includes a dynamic current generator, a multi-axis vibration table, an electromagnetic interference source, a data acquisition system, and a three-axis orthogonal electromagnetic shielding cabin. The cabin shielding effectiveness is ≥80dB, and the cabin is equipped with absorbing materials with a coverage rate of 90% or more.

[0046] S2: Dynamic current pulse loads are applied to the wiring harness based on a dynamic current pulse gradient, and multi-axis vibration excitation is applied to the wiring harness based on a multi-axis vibration frequency gradient. The dynamic current pulse and multi-axis vibration excitation are applied synchronously with a preset phase difference of 0° to 180°, simulating the transient high current and mechanical stress complex environment in actual vehicle operation.

[0047] S3. Apply a broadband electromagnetic interference signal to a wiring harness on a test platform. The wiring harness includes a high-voltage wiring harness and an adjacent low-voltage signal wiring harness. Use a bit error rate monitoring device to monitor the signal crosstalk amplitude and bit error rate changes between the high-voltage wiring harness and the low-voltage signal wiring harness in real time.

[0048] S4, collecting temperature, strain, and high-frequency current waveform data of several designated sensor nodes in the harness in real time through a distributed fiber grating sensor network, where the sensor nodes are dynamically configured according to the harness topology;

[0049] S5. Extract features from the dynamic data collected at several sensor nodes to generate feature vectors, where the feature vectors include the temperature gradient change rate, the dynamic current harmonic distortion rate, and the vibration spectrum energy distribution;

[0050] S6. Input the feature vector into the wiring harness parameter performance analysis model. The wiring harness parameter performance analysis model is deployed on the edge computing device. The temporal-spatial feature extraction is performed through a double-layer bidirectional gated recurrent unit to obtain the target high-dimensional feature vector. The parameter performance regression analysis is performed through the classification regression layer to output the wiring harness performance index.

[0051] S7. Input the feature vector into the wiring harness fault prediction network. The wiring harness fault prediction network is deployed on the edge computing device. The hidden features are extracted through the bidirectional long short-term memory layer. After fusion through the fully connected layer, the wiring harness fault probability prediction value is output.

[0052] S8. Correct the electrical-thermal-mechanical coupling parameters of the wiring harness based on the digital twin simulation model, and predict the remaining service life and fault threshold of the wiring harness by combining the measured data of S3 and S4 to obtain predicted data;

[0053] S9: When the predicted value of the wiring harness failure probability exceeds the threshold or the failure threshold predicted by S8 is exceeded, the high-speed data recording mode is triggered to store the raw sensor data 60 seconds before the failure; the prediction result of S8 is fed back to S1 to dynamically adjust the gradient step size and loading sequence in the environmental parameter group.

[0054] Specifically, in S1, dynamic current pulse gradients are used to simulate transient load changes during vehicle operation (such as motor start-stop and energy recovery). The gradient settings are graded based on wiring harness type: low-voltage wiring harnesses use a step change from 50A to 200A (10A step), while high-voltage wiring harnesses use a step change from 200A to 500A (50A step). Incremental loading is used to stimulate progressive degradation and capture the nonlinear characteristics of terminal contact resistance.

[0055] The multi-axis vibration frequency gradient is a three-axis independent frequency sequence (10Hz to 500Hz on the X / Y / Z axes) that replicates the road spectrum vibration environment. Its core feature is synchronous loading with the current pulse, with a phase difference of 0° to 180°, accurately simulating the electromechanical coupling effect between the engine vibration peak and the rising edge of the motor current during rapid acceleration. The acceleration amplitude gradient can be set from 0.5g to 20g to match different suspension stiffnesses.

[0056] The electromagnetic interference frequency band gradient is a sequence of frequencies segmented to cover typical interference sources in automotive electronics: the 1MHz to 100MHz band simulates power device switching noise (such as inverter dV / dt), and the 1GHz to 6GHz band simulates high-frequency communication interference (such as radar / 5G). The power ratio of radiated interference (antenna transmission) to conducted interference (coupler injection) is dynamically adjustable.

[0057] The corrosion acceleration factor concentration gradient refers to a series of hydrogen sulfide concentrations differentiated for the sheath material: rubber materials use a low concentration gradient of 10ppm to 500ppm, while silicone materials use a high concentration gradient of 200ppm to 1000ppm. This concentration gradient accelerates the electrochemical corrosion process and shortens the aging test period.

[0058] In S2, phase difference refers to the timing offset between the dynamic current pulse and the multi-axis vibration excitation, expressed in degrees (ranging from 0° to 180°). A 0° phase difference completely coincides with the rising edge of the current pulse and the vibration peak, simulating a sudden acceleration condition (motor peak current is synchronized with engine vibration); a 90° phase difference aligns the half-peak point of the current pulse with the vibration peak, simulating a gear shift jerk condition; and a 180° phase difference aligns the end of the current pulse with the vibration peak, simulating a braking recovery condition (current decay is coupled with suspension vibration). This method can replicate the electromechanical stress coupling effects of actual vehicle operation (e.g., vibration-induced terminal micro-wear is most pronounced at current peaks), resolving the physical distortion problem caused by asynchronous current and vibration loading in traditional testing.

[0059] The loading range of the dynamic current pulse load is 200A~500A, the pulse duration is 1ms~10ms, the frequency is 1Hz~100Hz, and the time deviation between the rising edge of the dynamic current pulse and the vibration peak moment is ≤1ms; multi-axis vibration excitation includes vibration frequency gradients in the X-axis, Y-axis, and Z-axis directions. The vibration frequency range of the X-axis, Y-axis, and Z-axis is 10Hz~500Hz, and the acceleration amplitude is 0.5g~20g.

[0060] Among them, the dynamic current pulse refers to a single transient load event (such as a current waveform with an amplitude of 300A and a duration of 5ms), which is used to simulate specific vehicle operating conditions (such as motor start and stop); the dynamic current pulse gradient is a parameterized pulse sequence.

[0061] In S3, the injection frequency band of the broadband electromagnetic interference signal is 1MHz~6GHz, the interference intensity is 10V / m~100V / m, and the superposition mode includes radiation interference and conduction interference; radiation interference includes the formation of an electromagnetic field around the wire harness through an electromagnetic radiator, and conduction interference includes direct connection of the wire harness through a coupler for conduction. The power ratio of radiation interference to conduction interference is 3:1~1:3.

[0062] The electromagnetic radiator utilizes a broadband log-periodic antenna, driven by a power amplifier and positioned parallel to the axis, one meter above the wiring harness. By adjusting the transmit power (10V / m to 100V / m), a controllable electromagnetic field is generated within the shielded cabin. Field strength calibration is performed at 16 points on a 1.5m x 1.5m vertical plane in accordance with the ISO11452-2 standard, ensuring field intensity fluctuations within the target wiring harness area are ≤±3dB. An X / Y / Z tri-directional antenna array simulates a multi-angle radiation environment. Combined with the bulkhead's absorbing material (coverage >90%), it suppresses reflected standing waves, inducing common-mode currents in the wiring harness conductors, equivalent to the radiated interference effect of a real vehicle inverter.

[0063] In S4, the distributed fiber Bragg grating sensor network is arranged with a sensor node every 10cm to 20cm, with a spatial resolution of ±2mm, a temperature measurement accuracy of ±0.5℃, a strain measurement accuracy of ±1με, and a sampling frequency of 10Hz to 10kHz. The fiber Bragg grating sensors are shielded by a metal braid with a shielding effectiveness of ≥60dB, and data transmission uses wavelength division multiplexing. The sensor nodes and the bit error rate monitoring equipment in S3 are synchronized using the PTP precise time protocol, with a clock deviation of ≤50μs.

[0064] Wiring harness topology refers to the three-dimensional spatial layout and electrical connections of a wiring harness system, including the trunk cable routing, branch node distribution, connector locations, and parallel sections of high and low voltage wiring harnesses. Topological characteristics include: 1. Physical path topology, which refers to the routing and curvature radius of the wiring harness through the sheet metal holes / clip attachment points; 2. Electrical connection topology, which refers to the terminal plug-in relationship and grounding point distribution hierarchy; and 3. Electromagnetic coupling topology, which refers to the length and spacing of adjacent high and low voltage wiring harnesses.

[0065] Distributed fiber optic sensors dynamically configure nodes based on this structure: they are densely deployed (spacing 10 to 20 cm) at key locations such as branch intersections, high curvature areas, and connector near fields, and sparsely deployed in straight sections (spacing > 30 cm), to achieve precise monitoring of stress concentration areas and electromagnetic sensitive areas.

[0066] In S5, the temperature gradient change rate is calculated as follows: dT / dt=(T(t+Δt)-T(t)) / Δt, where T(t) is the temperature at the current moment, T(t+Δt) is the temperature at the next moment, Δt is the sampling interval, and the sampling interval is 0.1 seconds to 10 seconds. The temperature gradient change rate is used to evaluate the thermal stability and failure risk of the wiring harness, and the threshold range is 0.1℃ / s to 5℃ / s. When the temperature gradient change rate dT / dt is greater than 5℃ / s, the dynamic current load is cut off, the multi-axis vibration excitation is stopped, and the electromagnetic interference source is turned off.

[0067] In S5, feature extraction includes fast Fourier transform analysis of the dynamic current waveform, extraction of the total harmonic distortion rate and the energy proportion of the high-frequency component, time series analysis of the temperature data, calculation of the temperature gradient change rate and the standard deviation of the temperature fluctuation, wavelet transform analysis of the vibration data, and extraction of the vibration spectrum energy distribution.

[0068] In S6, the two-layer bidirectional gated recurrent unit includes a first-layer bidirectional recurrent neural network and a second-layer gated recurrent unit. The hidden layer dimension of the first-layer bidirectional recurrent neural network is 64, and the hidden layer dimension of the second-layer gated recurrent unit is 32. The time series features are weightedly fused through the attention mechanism, and the target high-dimensional feature vector with a dimension of 128 is generated after dimensionality reduction.

[0069] The wire harness parameter performance analysis model is an evaluation system based on a deep learning architecture, deployed on edge computing devices for real-time processing. Its core utilizes a two-layer bidirectional gated recurrent unit (GRU). The first-layer bidirectional network extracts temporal evolution features of sensor data (such as temperature fluctuation trends), while the second-layer gated unit captures spatial correlation features (such as the correlation of strain distributions across multiple nodes). An attention mechanism fuses spatiotemporal information to generate a 128-dimensional high-dimensional feature vector. Finally, a classification and regression layer maps these features into quantitative performance indicators, including key parameters such as dynamic resistance change rate, insulation impedance decay rate, and thermal imbalance coefficient, comprehensively reflecting the electrical, mechanical, and thermal management status of the wire harness.

[0070] In the S7, the wiring harness fault prediction network is a diagnostic system based on a deep time series model, deployed on edge computing devices to achieve millisecond-level response. Its core utilizes a bidirectional long short-term memory (BiLSTM) layer: the forward and backward LSTMs respectively extract the historical and future dependencies of feature vectors. Using an attention mechanism, they weightedly fuse key time series features (such as sudden temperature changes and sudden increases in current harmonics) to generate a hidden state vector. A fully connected layer further integrates multi-dimensional hidden features, ultimately outputting a predicted fault probability value in the range of 0 to 1. This value covers typical failure modes such as terminal oxidation, insulation cracking, and conductor fatigue, enabling early risk warning.

[0071] The bidirectional long short-term memory layer includes an attention mechanism module. The hidden layer dimensions of the forward LSTM and backward LSTM are both 64. The attention mechanism module calculates the dot product of the query vector and the time series features to generate attention weights, and inputs the weighted features into the fully connected layer. The fully connected layer contains three hidden layers with 128, 64, and 32 neurons, respectively.

[0072] In S8, the digital twin simulation model is built based on finite element analysis, including an electrical-thermal coupling sub-model, a thermal-mechanical coupling sub-model, and an aging prediction sub-model. The model parameters are corrected through the Bayesian optimization algorithm to predict the remaining service life of the wiring harness at time nodes of 1,000 hours, 5,000 hours, and 10,000 hours.

[0073] In S8, the fault threshold is determined based on the following criteria: when the harness resistance change rate exceeds 50% or the signal error rate exceeds 10 -4 When , a fault warning signal is triggered; the resistance change rate calculation formula is: (ΔR) / R0=((Rt-R0)) / R0×100%, where R0 is the initial reference resistance, Rt is the real-time working resistance, and ΔR is the absolute change in resistance;

[0074] The digital twin simulation model uses a Bayesian optimization algorithm to correct parameters, with a convergence condition of less than 5% root mean square error between measured and simulated data. The model accuracy is recalibrated every 24 hours, and the aging prediction sub-model is reconstructed when the error is greater than 5% for three consecutive calibrations.

[0075] The resistance change rate is calculated by comparing the current resistance value with the initial resistance value, and the signal bit error rate is determined by measuring the ratio of the number of bit errors per unit time to the total number of transmitted bits using a bit error meter.

[0076] The aging prediction sub-model introduces hydrogen sulfide concentration as a corrosion acceleration factor with a concentration gradient of 10ppm to 1000ppm. The concentration gradient is dynamically adjusted according to the type of wire harness sheath material: rubber materials use 10ppm to 500ppm, and silicone materials use 200ppm to 1000ppm.

[0077] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for testing the coupling of dynamic load and electromagnetic interference of a wiring harness, characterized in that: include: S1. Define several environmental parameter groups, including dynamic current pulse gradient, multi-axis vibration frequency gradient, electromagnetic interference frequency band gradient, and corrosion acceleration factor concentration gradient; construct a test platform, including a dynamic current generator, a multi-axis vibration table, an electromagnetic interference source, a data acquisition system, and a three-axis orthogonal electromagnetic shielding cabin. The cabin shielding effectiveness must be ≥80dB, and the cabin must be equipped with absorbing materials with a coverage rate of 90% or more. S2: Dynamic current pulse loads are applied to the wiring harness based on a dynamic current pulse gradient, and multi-axis vibration excitation is applied to the wiring harness based on a multi-axis vibration frequency gradient. The dynamic current pulse and multi-axis vibration excitation are applied synchronously with a preset phase difference of 0° to 180°, simulating the transient high current and mechanical stress complex environment in actual vehicle operation. S3. Apply a broadband electromagnetic interference signal to a wiring harness on a test platform. The wiring harness includes a high-voltage wiring harness and an adjacent low-voltage signal wiring harness. Use a bit error rate monitoring device to monitor the signal crosstalk amplitude and bit error rate changes between the high-voltage wiring harness and the low-voltage signal wiring harness in real time. S4, collecting temperature, strain, and high-frequency current waveform data of several designated sensor nodes in the harness in real time through a distributed fiber grating sensor network, where the sensor nodes are dynamically configured according to the harness topology; S5. Extract features from the dynamic data collected at several sensor nodes to generate feature vectors, where the feature vectors include the temperature gradient change rate, the dynamic current harmonic distortion rate, and the vibration spectrum energy distribution; S6. Input the feature vector into the wiring harness parameter performance analysis model deployed on the edge computing device, perform temporal-spatial feature extraction through a double-layer bidirectional gated recurrent unit to obtain the target high-dimensional feature vector, and perform parameter performance regression analysis through a classification regression layer to output the wiring harness performance index. S7: Input the feature vector generated in S5 into the wiring harness fault prediction network deployed on the edge computing device, extract hidden features through the bidirectional long short-term memory layer, and output the wiring harness fault probability prediction value after fusion through the fully connected layer; S8. Based on the digital twin simulation model, the electrical-thermal-mechanical coupling parameters of the wiring harness are corrected. Combined with the measured data from S3 and S4, the remaining service life and fault threshold of the wiring harness are predicted to obtain prediction data. S9: When the predicted value of the wiring harness failure probability exceeds the threshold or the failure threshold output by S8 is exceeded, the high-speed data recording mode is triggered to store the raw sensor data 60 seconds before the failure; the predicted data of S8 is fed back to S1 to dynamically adjust the gradient step size and loading sequence in the environmental parameter group.

2. The wiring harness dynamic load and electromagnetic interference coupling test method according to claim 1, characterized in that: In S2, the dynamic current pulse load has a loading range of 200A to 500A, a pulse duration of 1ms to 10ms, a frequency of 1Hz to 100Hz, and a time deviation between the rising edge of the dynamic current pulse and the vibration peak moment of ≤1ms; The multi-axis vibration excitation includes vibration frequency gradients in the X-axis, Y-axis, and Z-axis directions. The vibration frequency ranges of the X-axis, Y-axis, and Z-axis are all 10Hz to 500Hz, and the acceleration amplitude is 0.5g to 20g.

3. The wiring harness dynamic load and electromagnetic interference coupling test method according to claim 1, characterized in that: In S3, the injection frequency band of broadband electromagnetic interference signals is 1MHz to 6GHz, the interference intensity is 10V / m to 100V / m, and the superposition mode includes radiation interference and conduction interference; Radiated interference includes the electromagnetic field formed around the wiring harness through electromagnetic radiators, and conducted interference includes conduction through direct connection of the wiring harness through a coupler. The power ratio of radiated interference to conducted interference is 3:1 to 1:

3.

4. The wiring harness dynamic load and electromagnetic interference coupling test method according to claim 1, characterized in that: In S4, the distributed fiber Bragg grating sensor network has a density of one sensor node every 10 cm to 20 cm, a spatial resolution of ±2 mm, a temperature measurement accuracy of ±0.5 °C, a strain measurement accuracy of ±1 με, a sampling frequency of 10 Hz to 10 kHz, and fiber Bragg grating sensors are shielded by a metal braid with a shielding effectiveness of ≥60 dB. Data transmission uses wavelength division multiplexing. The sensor nodes and the bit error rate monitoring equipment in S3 are synchronized through the PTP precise time protocol, and the clock deviation is ≤50μs.

5. The wiring harness dynamic load and electromagnetic interference coupling test method according to claim 1, characterized in that: In S5, the temperature gradient change rate is calculated as follows: dT / dt=(T(t+Δt)-T(t)) / Δt, where T(t) is the current temperature, T(t+Δt) is the next temperature, and Δt is the sampling interval, which ranges from 0.1 seconds to 10 seconds. The temperature gradient change rate is used to assess the thermal stability and failure risk of the wiring harness, with a threshold range of 0.1°C / s to 5°C / s. When the temperature gradient change rate dT / dt>5°C / s, the dynamic current load is cut off, the multi-axis vibration excitation is stopped and the electromagnetic interference source is turned off.

6. The wiring harness dynamic load and electromagnetic interference coupling test method according to claim 5, characterized in that: In S5, feature extraction includes fast Fourier transform analysis of the dynamic current waveform, extraction of the total harmonic distortion rate and the energy proportion of the high-frequency component, time series analysis of the temperature data, calculation of the temperature gradient change rate and the standard deviation of the temperature fluctuation, wavelet transform analysis of the vibration data, and extraction of the vibration spectrum energy distribution.

7. The wiring harness dynamic load and electromagnetic interference coupling test method according to claim 1, characterized in that: In S6, the two-layer bidirectional gated recurrent unit includes a first-layer bidirectional recurrent neural network and a second-layer gated recurrent unit. The hidden layer dimension of the first-layer bidirectional recurrent neural network is 64, and the hidden layer dimension of the second-layer gated recurrent unit is 32. The time series features are weightedly fused through the attention mechanism, and the target high-dimensional feature vector with a dimension of 128 is generated after dimensionality reduction.

8. The wiring harness dynamic load and electromagnetic interference coupling test method according to claim 1, characterized in that: In S7, the bidirectional long short-term memory layer includes an attention mechanism module. The hidden layer dimensions of the forward LSTM and backward LSTM are both 64. The attention mechanism module calculates the dot product of the query vector and the time series features to generate attention weights, and inputs the weighted features into the fully connected layer. The fully connected layer contains three hidden layers with 128, 64, and 32 neurons, respectively.

9. The wiring harness dynamic load and electromagnetic interference coupling test method according to claim 1, characterized in that: In S8, the digital twin simulation model is built based on finite element analysis, including an electrical-thermal coupling sub-model, a thermal-mechanical coupling sub-model, and an aging prediction sub-model. The model parameters are corrected through the Bayesian optimization algorithm to predict the remaining service life of the wiring harness at time nodes of 1,000 hours, 5,000 hours, and 10,000 hours.

10. The wiring harness dynamic load and electromagnetic interference coupling test method according to claim 9, characterized in that: In S8, the fault threshold is determined based on the following criteria: when the harness resistance change rate exceeds 50% or the signal error rate exceeds 10 -4 When the fault warning signal is triggered; The resistance change rate calculation formula is: (ΔR) / R0=((Rt-R0)) / R0×100%, where R0 is the initial reference resistance, Rt is the real-time working resistance, and ΔR is the absolute change in resistance. The digital twin simulation model uses a Bayesian optimization algorithm to correct parameters, with a convergence condition of less than 5% root mean square error between measured and simulated data. The model accuracy is recalibrated every 24 hours, and the aging prediction sub-model is reconstructed when the error is greater than 5% for three consecutive calibrations. The resistance change rate is calculated by comparing the current resistance value with the initial resistance value, and the signal bit error rate is determined by measuring the ratio of the number of bit errors per unit time to the total number of transmitted bits using a bit error meter. The aging prediction sub-model introduces hydrogen sulfide concentration as a corrosion acceleration factor with a concentration gradient of 10ppm to 1000ppm. The concentration gradient is dynamically adjusted according to the type of wire harness sheath material: rubber materials use 10ppm to 500ppm, and silicone materials use 200ppm to 1000ppm.

Images