An electromagnetic compatibility adapter system for an electric vehicle braking system

Abstract

This invention discloses an electromagnetic compatibility (EMC) adaptation system for an electric vehicle braking system, relating to the field of electric vehicle engineering technology. It includes: a full-domain electromagnetic situational awareness engine module, which collects multi-dimensional electromagnetic data of the electric vehicle and external scenarios; a braking electromagnetic disturbance source tracing and monitoring module, which establishes an interference condition correlation model; an intelligent compatibility adaptation decision module, which couples and analyzes the full-scenario electromagnetic environment feature map with the electromagnetic interference parameters of the braking system, matches the EMC threshold range of the braking system, and generates an initial EMC adaptation scheme; and a dynamic closed-loop optimization and control module, which dynamically iteratively optimizes the initial EMC adaptation scheme and outputs the optimal EMC adaptation strategy for the braking system. This invention, through multi-module, multi-dimensional electromagnetic data acquisition, analysis, and adaptation, forms a dynamic feedback closed loop, capable of responding in real time to changes in different electromagnetic environments, ensuring the system's EMC compatibility under complex operating conditions.

Description

Technical Field

[0001] This invention relates to the field of electric vehicle engineering technology, specifically to an electromagnetic compatibility adaptation system for an electric vehicle braking system. Background Technology

[0002] As electric vehicles undergo a profound transformation towards intelligence and electrification, braking systems have evolved from traditional mechanical structures to electric drive control systems centered on electro-hydraulic braking and electronic parking brakes. Their operation relies on the coordinated work of various electronic components, including high-voltage wiring harnesses, motor controllers, and wheel speed sensors. However, the electromagnetic environment of electric vehicles is becoming increasingly complex: on the one hand, electromagnetic radiation and conducted interference generated by high-voltage system switching operations and motor operation can easily intrude into sensitive components of the braking system through spatial coupling or line conduction; on the other hand, external interference such as base station signals and industrial electromagnetic noise in the external road environment further exacerbates the electromagnetic compatibility risks of the braking system. In existing technologies, electric vehicle braking systems... Traditional electromagnetic compatibility (EMC) designs often employ passive protection modes, such as using fixed measures like adding shielding covers and optimizing grounding methods to meet national standard limits. However, these methods have significant limitations: First, they fail to consider the dynamic correlation between braking conditions and electromagnetic interference, making it difficult for fixed protection schemes to adapt to interference variations under different operating conditions. Second, they lack a precise correlation mechanism between electromagnetic interference and component failures. When problems such as response delays or control failures occur in the braking system, it is impossible to quickly pinpoint whether they are caused by EMC issues, increasing the difficulty of troubleshooting. Third, they do not incorporate the dynamic changes and predictions of the external electromagnetic environment, resulting in insufficient targeting of protection schemes. This can easily lead to overprotection, wasting costs, or underprotection, causing safety hazards.

[0003] Furthermore, existing technologies have not formed a closed-loop system of "perception-monitoring-decision-optimization," and the adaptation schemes cannot dynamically iterate according to factors such as electromagnetic environment and component aging, making it difficult to guarantee the electromagnetic compatibility performance and operational safety of the braking system in the long term. Summary of the Invention

[0004] The purpose of this invention is to solve the problems mentioned above by providing an electromagnetic compatibility adaptation system for an electric vehicle braking system.

[0005] The objective of this invention can be achieved through the following technical solutions:

[0006] An electromagnetic compatibility adaptation system for an electric vehicle braking system includes: a global electromagnetic situational awareness engine module, a braking electromagnetic disturbance source tracing and monitoring module, an intelligent compatibility adaptation decision module, and a dynamic closed-loop optimization and control module.

[0007] The full-domain electromagnetic situational awareness engine module is used to collect multi-dimensional electromagnetic data of the electric vehicle and external scene, and generate a full-scene electromagnetic environment feature map through cross-domain data fusion.

[0008] The braking electromagnetic disturbance source tracing and monitoring module is used to capture the electromagnetic radiation and conducted interference parameters of the core components of the braking system in real time, and establish an interference condition correlation model in combination with the braking conditions.

[0009] The intelligent compatibility adaptation decision module is electrically connected to the full-domain electromagnetic situation awareness engine module and the braking electromagnetic disturbance source tracing and monitoring module. It is used to couple and analyze the full-scene electromagnetic environment feature map with the electromagnetic interference parameters of the braking system, match the electromagnetic compatibility threshold range of the braking system, and generate an initial electromagnetic compatibility adaptation scheme.

[0010] The dynamic closed-loop optimization and control module communicates bidirectionally with the intelligent compatibility and adaptation decision module and the global electromagnetic situation awareness engine module. It is used to dynamically iterate and optimize the initial electromagnetic compatibility adaptation scheme based on the real-time updated full-scene electromagnetic environment feature map, and output the optimal electromagnetic compatibility adaptation strategy for the braking system.

[0011] Preferably, the global electromagnetic situational awareness engine module includes:

[0012] The multi-dimensional electromagnetic data acquisition unit is equipped with on-board electromagnetic sensors, environmental electromagnetic monitoring terminals and vehicle bus data interfaces to collect multi-dimensional unstructured electromagnetic data, including electromagnetic fields radiated by the braking system controller, conducted interference from high-voltage wiring harnesses, electromagnetic noise from the external environment and vehicle operating status parameters.

[0013] The electromagnetic feature purification and processing unit performs denoising, normalization and dimensional calibration on multi-dimensional unstructured electromagnetic data, and extracts the time-domain and frequency-domain features of electromagnetic signals through wavelet transform to obtain standardized electromagnetic feature data.

[0014] The cross-domain attention fusion computing unit constructs a multimodal fusion network based on an attention mechanism. Taking electromagnetic signal features, environmental parameter features, and vehicle state features as inputs, it calculates the correlation degree of features across different dimensions using a ternary attention weight allocation model. The calculation formula is as follows:

[0015]

[0016] In the formula, For cross-domain fusion loss function, The characteristic vector of the electromagnetic signal. For environmental parameter feature vectors, This is the vehicle state feature vector. The function for calculating the Pearson correlation coefficient. The weights are associated with electromagnetic-environmental characteristics. Assign weights to the environment-vehicle feature association. Weights for the correlation between the whole vehicle and electromagnetic features;

[0017] The electromagnetic situation map generation unit, based on cross-domain fusion of feature data, uses a graph neural network (GNN) to construct a node-edge association model, taking electromagnetic sources, interference paths, and sensitive components as graph nodes and interference intensity as edge weights to generate a dynamically updated full-scene electromagnetic environment feature map.

[0018] Preferably, the braking electromagnetic disturbance tracing and monitoring module includes:

[0019] The core component, the electromagnetic disturbance monitoring matrix unit, deploys high-frequency electromagnetic probes in the brake master cylinder, hydraulic control unit, motor controller, and wheel speed sensor to collect radiated interference field strength and conducted interference voltage in the 10kHz-1GHz frequency band in real time.

[0020] The operating condition-disturbance timing correlation unit synchronously acquires brake pedal travel, brake pressure, vehicle speed, and battery SOC operating condition parameters through the vehicle CAN bus, establishes the correspondence between electromagnetic interference parameters and braking operating condition timing, and generates an operating condition-disturbance correlation dataset.

[0021] The intelligent electromagnetic interference level assessment unit, based on the GB / T18387-2017 standard for electromagnetic compatibility of electric vehicles, classifies electromagnetic interference safety levels (Level 1: no interference risk; Level 2: slight interference; Level 3: moderate interference; Level 4: severe interference). Combining the operating condition-interference correlation dataset, a random forest classification model is trained to achieve real-time assessment of electromagnetic interference levels during braking.

[0022] Preferably, the intelligent compatibility adaptation decision module includes:

[0023] The operating condition-threshold dynamic calibration unit, based on the electromagnetic susceptibility parameters of the core components of the braking system and combined with the electromagnetic compatibility design requirements of the whole vehicle, calibrates the electromagnetic interference safety threshold range under different braking conditions and establishes a threshold-operating condition mapping table.

[0024] The electromagnetic coupling path analysis unit uses electromagnetic topology analysis to construct an electromagnetic interference propagation path model for the braking system, analyzes the coupling path between interference sources and sensitive components of the braking system in the full-scene electromagnetic environment feature map, and identifies key interference nodes.

[0025] The three-dimensional adaptation scheme generation unit generates an initial adaptation scheme based on the electromagnetic interference level assessment results for key interference nodes, from three dimensions: hardware suppression, software optimization, and shielding enhancement. The hardware aspect includes the selection of filter capacitors and adjustment of grounding methods; the software aspect includes timing optimization of braking control algorithms and electromagnetic compatibility redundancy strategies; and the shielding aspect includes grounding optimization of wire harness shielding layers and thickening design of shielding covers for sensitive components.

[0026] Preferably, the intelligent compatibility adaptation decision module further includes:

[0027] The adaptation efficiency simulation prediction unit establishes an electromagnetic compatibility simulation model of the braking system based on electromagnetic simulation software, substitutes the initial adaptation scheme into the model, simulates the braking system response under different electromagnetic environments, and predicts the electromagnetic interference suppression efficiency of the adaptation scheme.

[0028] The multi-target adaptation scheme screening unit sets the evaluation indicators for adaptation schemes (interference suppression efficiency ≥85%, braking performance attenuation ≤3%, cost increase ≤10%), performs multi-target screening on the initial adaptation schemes, and retains the candidate adaptation schemes that meet the evaluation indicators.

[0029] Preferably, the dynamic closed-loop optimization and control module includes:

[0030] The real-time adaptation performance feedback unit obtains electromagnetic interference parameters and braking system operating status after the implementation of the adaptation scheme through real-time data from the global electromagnetic situation awareness engine module and the braking electromagnetic disturbance tracing and monitoring module, and generates a feedback dataset.

[0031] The improved PSO intelligent optimization unit employs an improved particle swarm optimization algorithm. With maximizing electromagnetic interference suppression efficiency as the objective function and braking performance and cost as constraints, it iteratively optimizes the parameters of candidate adaptation schemes. The iterative formula is as follows:

[0032]

[0033] In the formula, For the first per iteration speed, For inertial weights, and As a learning factor, and A random number in the range [0,1]. This is the optimal solution for the individual. This is the globally optimal solution. For the first Next iteration position;

[0034] The operating condition-strategy dynamic matching output unit matches the optimized adaptation parameters with the braking operating conditions to generate a dynamically adjusted optimal electromagnetic compatibility adaptation strategy, which is then sent to the braking system execution components in real time through the vehicle controller.

[0035] Preferably, the dynamic closed-loop optimization and control module further includes:

[0036] The multi-level electromagnetic safety early warning unit triggers a multi-level early warning mechanism when the electromagnetic interference level reaches level three or above, and the interference cannot be suppressed to the safe threshold range even after the adaptation strategy is optimized: Level 1 warning (audio-visual prompt), Level 2 warning (limiting non-emergency braking power), and Level 3 warning (activating mechanical braking redundancy).

[0037] The electromagnetic compatibility knowledge base construction unit records electromagnetic environment data, electromagnetic interference parameters, compatibility schemes and optimization effects for the entire scenario, and builds an electromagnetic compatibility compatibility database to provide data support for the subsequent electromagnetic compatibility design of braking systems.

[0038] Preferably, the global electromagnetic situational awareness engine module further includes:

[0039] The external electromagnetic environment time series prediction unit, based on geographical location information and historical electromagnetic environment data, combined with the influence of meteorological conditions (rainfall and humidity) on electromagnetic propagation, trains an LSTM time series prediction model to predict the external electromagnetic noise in the next hour, providing a basis for adjusting the adaptation scheme in advance.

[0040] Preferably, the braking electromagnetic disturbance tracing and monitoring module further includes:

[0041] The electromagnetic disturbance and fault correlation diagnosis unit establishes an electromagnetic disturbance and component fault correlation model based on the abnormal change characteristics of electromagnetic interference parameters and combined with the braking system fault codes, and performs diagnosis and location of braking system faults caused by electromagnetic compatibility issues.

[0042] Preferably, the association model of the electromagnetic disturbance and fault association diagnosis unit adopts an algorithm combining cosine similarity and weight correction, and the calculation formula is as follows:

[0043]

[0044] In the formula, For the first Electromagnetic disturbances and the first The correlation of component failures A correlation of ≥0.8 is considered strong, and 0.5≤ A correlation of <0.8 is considered moderate. A correlation value less than 0.5 is considered a weak association. For feature similarity weights, As the weight for the change in the amplitude of the disturbance, For the duration of the disturbance, weight, For the first The electromagnetic disturbance eigenvector and the first Cosine similarity of fault-like feature vectors For the first When a type of electromagnetic disturbance occurs, the first The amplitude variation of electromagnetic interference of such components For the first The maximum permissible electromagnetic interference amplitude variation threshold for this type of component For the first The duration of electromagnetic disturbances, This is the minimum electromagnetic disturbance duration threshold for a component of this type to fail.

[0045] Compared with the prior art, the beneficial effects of the present invention are:

[0046] Through multi-module, multi-dimensional electromagnetic data acquisition, analysis and adaptation, a dynamic feedback closed loop is formed, which can respond to changes in different electromagnetic environments in real time and ensure the electromagnetic compatibility of the system under complex working conditions. Especially in the application of optimization algorithms, electromagnetic early warning and fault diagnosis, the system has significant advantages in ensuring braking safety and performance. Attached Figure Description

[0047] To facilitate understanding by those skilled in the art, the present invention will be further described below with reference to the accompanying drawings.

[0048] Figure 1 This is a system framework diagram of the present invention;

[0049] Figure 2 This is an internal system framework diagram of the global electromagnetic situational awareness engine module in this invention;

[0050] Figure 3 This is an internal system framework diagram of the braking electromagnetic disturbance tracing and monitoring module in this invention;

[0051] Figure 4 This is a diagram of the internal system framework of the intelligent compatibility and adaptation decision module in this invention.

[0052] Figure 5 This is a diagram of the internal system framework of the dynamic closed-loop optimization and control module in this invention. Detailed Implementation

[0053] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0054] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a mutually exclusive, independent, or alternative embodiment. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0055] Please see Figure 1As shown, an electromagnetic compatibility adaptation system for an electric vehicle braking system includes: a global electromagnetic situational awareness engine module, a braking electromagnetic disturbance source tracing and monitoring module, an intelligent compatibility adaptation decision module, and a dynamic closed-loop optimization and control module.

[0056] The full-domain electromagnetic situational awareness engine module is used to collect multi-dimensional electromagnetic data of the electric vehicle and external scene, and generate a full-scene electromagnetic environment feature map through cross-domain data fusion.

[0057] The braking electromagnetic disturbance source tracing and monitoring module is used to capture the electromagnetic radiation and conducted interference parameters of the core components of the braking system in real time, and establish an interference condition correlation model in combination with the braking conditions.

[0058] The intelligent compatibility adaptation decision module is electrically connected to the full-domain electromagnetic situation awareness engine module and the braking electromagnetic disturbance source tracing and monitoring module. It is used to couple and analyze the full-scene electromagnetic environment feature map with the electromagnetic interference parameters of the braking system, match the electromagnetic compatibility threshold range of the braking system, and generate an initial electromagnetic compatibility adaptation scheme.

[0059] The dynamic closed-loop optimization and control module communicates bidirectionally with the intelligent compatibility and adaptation decision module and the global electromagnetic situation awareness engine module. It is used to dynamically iterate and optimize the initial electromagnetic compatibility adaptation scheme based on the real-time updated full-scene electromagnetic environment feature map, and output the optimal electromagnetic compatibility adaptation strategy for the braking system.

[0060] Please see Figure 2 As shown, the global electromagnetic situational awareness engine module includes:

[0061] The multi-dimensional electromagnetic data acquisition unit is equipped with on-board electromagnetic sensors, environmental electromagnetic monitoring terminals and vehicle bus data interfaces to collect multi-dimensional unstructured electromagnetic data, including electromagnetic fields radiated by the braking system controller, conducted interference from high-voltage wiring harnesses, electromagnetic noise from the external environment and vehicle operating status parameters.

[0062] The electromagnetic feature purification and processing unit performs denoising, normalization and dimensional calibration on multi-dimensional unstructured electromagnetic data, and extracts the time-domain and frequency-domain features of electromagnetic signals through wavelet transform to obtain standardized electromagnetic feature data.

[0063] The cross-domain attention fusion computing unit constructs a multimodal fusion network based on an attention mechanism. Taking electromagnetic signal features, environmental parameter features, and vehicle state features as inputs, it calculates the correlation degree of features across different dimensions using a ternary attention weight allocation model. The calculation formula is as follows:

[0064]

[0065] In the formula, For cross-domain fusion loss function, The characteristic vector of the electromagnetic signal. For environmental parameter feature vectors, This is the vehicle state feature vector. The function for calculating the Pearson correlation coefficient. The weights are associated with electromagnetic-environmental characteristics. Assign weights to the environment-vehicle feature association. Weights for the correlation between the whole vehicle and electromagnetic features;

[0066] The electromagnetic situation map generation unit, based on the cross-domain fused feature data, uses a graph neural network (GNN) to construct a node-edge association model, taking electromagnetic sources, interference paths, and sensitive components as map nodes, and interference intensity as edge weights to generate a dynamically updated full-scene electromagnetic environment feature map.

[0067] By using a multi-dimensional electromagnetic data acquisition unit, combined with on-board electromagnetic sensors and environmental electromagnetic monitoring terminals, comprehensive electromagnetic data acquisition of the entire vehicle and external environment is achieved. This covers unstructured data from multiple dimensions, including braking system controllers, electromagnetic interference, and high-voltage wiring harnesses. By combining cross-domain attention mechanisms and graph neural networks, it not only accurately integrates data from different sources but also generates real-time updated full-scene electromagnetic environment feature maps, providing a foundation for subsequent electromagnetic compatibility adaptation solutions.

[0068] Please see Figure 3 As shown, the braking electromagnetic disturbance tracing and monitoring module includes:

[0069] The core component, the electromagnetic disturbance monitoring matrix unit, deploys high-frequency electromagnetic probes in the brake master cylinder, hydraulic control unit, motor controller, and wheel speed sensor to collect radiated interference field strength and conducted interference voltage in the 10kHz-1GHz frequency band in real time.

[0070] The operating condition-disturbance timing correlation unit synchronously acquires brake pedal travel, brake pressure, vehicle speed, and battery SOC operating condition parameters through the vehicle CAN bus, establishes the correspondence between electromagnetic interference parameters and braking operating condition timing, and generates an operating condition-disturbance correlation dataset.

[0071] The intelligent electromagnetic interference level assessment unit, based on the GB / T18387-2017 standard for electromagnetic compatibility of electric vehicles, classifies electromagnetic interference safety levels (Level 1: no interference risk; Level 2: slight interference; Level 3: moderate interference; Level 4: severe interference). Combining the operating condition-interference correlation dataset, it trains a random forest classification model to achieve real-time assessment of electromagnetic interference levels during braking.

[0072] The random forest is set to have 100 decision trees, with a maximum depth of 10 layers per tree and a minimum number of samples per leaf node of 5. Bootstrap sampling is used to sample the training set with replacement, generating 100 different sub-training sets, each corresponding to the training data of a decision tree. A random feature selection mechanism is also introduced, randomly selecting 5-8 key features to participate in node splitting during the construction of each decision tree, thereby improving the model's generalization ability.

[0073] Model training process:

[0074] Single decision tree training: Each decision tree is constructed based on the CART algorithm. The feature space is recursively divided with the minimum Gini coefficient as the node splitting criterion until the maximum depth or the number of leaf node samples is met.

[0075] Ensemble learning fusion: After all decision trees are trained, the classification results of each decision tree are fused by voting. That is, when predicting the electromagnetic interference level of the input sample, the prediction results of 100 decision trees are counted, and the level that appears most frequently is taken as the final prediction level.

[0076] Model Iteration and Optimization: Verify model performance using the test set, calculate confusion matrix, accuracy, recall, and F1 score. If the model's recall for level 3 and level 4 high-risk interference levels is less than 90%, adjust the number of decision trees (increase to 150) or the maximum depth (adjust to 12 layers), and retrain the model until the performance requirements are met (overall accuracy ≥ 95%, high-risk level recall ≥ 92%).

[0077] This module achieves high-precision electromagnetic interference monitoring by deploying high-frequency electromagnetic probes in core components such as the brake master cylinder and hydraulic control unit. It can capture radiated and conducted interference in the 10kHz to 1GHz frequency band. This refined monitoring method enables more accurate analysis and location of electromagnetic interference sources, providing precise data support for brake electromagnetic compatibility assessment.

[0078] Please see Figure 4 As shown, the intelligent compatibility adaptation decision module includes:

[0079] The operating condition-threshold dynamic calibration unit, based on the electromagnetic susceptibility parameters of the core components of the braking system and combined with the electromagnetic compatibility design requirements of the whole vehicle, calibrates the electromagnetic interference safety threshold range under different braking conditions and establishes a threshold-operating condition mapping table.

[0080] The specific procedure for calibrating the electromagnetic interference safety threshold range under different braking conditions in the operating condition-threshold dynamic calibration unit is as follows:

[0081] Obtaining electromagnetic susceptibility parameters of core components:

[0082] Laboratory testing: The core components of the braking system (brake master cylinder, hydraulic control unit, motor controller, wheel speed sensor) are placed in an electromagnetic anechoic chamber. Electromagnetic interference signals of different frequencies (10kHz-1GHz) and amplitudes are generated using a signal generator and applied to the components through an antenna or coupling fixture. The minimum interference intensity when the component malfunctions (such as wheel speed sensor signal distortion or motor controller response delay) is recorded as the electromagnetic susceptibility threshold (ESD threshold, radiated susceptibility RS threshold, conducted susceptibility CS threshold) for each component.

[0083] Parameter integration: Organize the electromagnetic susceptibility parameters of each core component, establish a component-susceptibility mapping table, and clarify the tolerance limits of different components to different types of electromagnetic interference (radiated interference, conducted interference).

[0084] Breakdown of vehicle electromagnetic compatibility design requirements:

[0085] National standard compliance requirements: Based on the GB / T18387-2017 standard for electromagnetic compatibility of electric vehicles, the electromagnetic interference limit requirements of the braking system in the electromagnetic environment of the vehicle are clearly defined. That is, the electromagnetic interference generated by the braking system shall not affect the normal operation of other electronic systems of the vehicle (such as the automatic driving controller and the in-vehicle entertainment system), and at the same time, it shall be able to withstand the electromagnetic interference generated by other components of the vehicle (such as the drive motor and the high-voltage charging pile).

[0086] Vehicle-level safety redundancy requirements: Based on the functional safety level (ASIL D) of the electric vehicle braking system, a 20% safety margin is reserved on the basis of the electromagnetic susceptibility threshold of the core components to avoid safety risks caused by the decrease in sensitivity due to component aging and changes in ambient temperature and humidity.

[0087] Braking condition classification and threshold calibration:

[0088] Operating Condition Classification: Based on the vehicle's operating scenarios, braking conditions are classified into five typical categories: conventional braking (vehicle speed 30-100km / h, brake pedal travel 20%-50%), emergency braking (vehicle speed ≥60km / h, brake pedal travel ≥80%), low-speed braking (vehicle speed ≤30km / h, brake pedal travel ≤30%), hill braking (slope ≥15°, braking pressure ≥0.6MPa), and energy recovery-assisted braking (battery SOC ≤80%, recovery power ≥30kW).

[0089] Initial Threshold Determination for Single Operating Conditions: For each type of operating condition, considering the working characteristics of the braking system under that condition (such as high peak power output of the motor controller and strong electromagnetic interference radiation during emergency braking), based on 80% (safety margin) of the electromagnetic sensitivity threshold of the core component, and combined with the electromagnetic compatibility design requirements of the whole vehicle, the upper and lower limits of the electromagnetic interference safety threshold under that condition are initially determined; for example, under normal braking conditions, the radiated interference safety threshold range of the wheel speed sensor is initially determined to be [10V / m, 30V / m], and the conducted interference safety threshold range is initially determined to be [0.5V, 2V];

[0090] Multi-condition threshold dynamic correction: Through whole vehicle bench testing, the electromagnetic environment under different operating conditions is simulated, and the operating data of the braking system under different interference intensities are collected to analyze the correlation between electromagnetic interference threshold and braking performance (braking distance, braking deceleration stability). If the threshold range is too wide under a certain operating condition, causing minor functional abnormalities in the braking system, or too narrow, causing excessively high costs for the adaptation solution, the threshold range is adjusted. For example, under emergency braking conditions, in order to ensure timely braking response, the lower limit of the conducted interference safety threshold of the motor controller is increased by 5%, and the upper limit is decreased by 10%, to ensure electromagnetic compatibility safety under high-risk operating conditions.

[0091] Threshold-operating condition mapping table establishment: Five typical braking conditions and their corresponding electromagnetic interference safety threshold ranges (radiated interference field strength threshold range, conducted interference voltage threshold range) are organized into a threshold-operating condition mapping table. The mapping table supports dynamic updates. When a new braking condition (such as braking on icy and snowy roads) is added or the core components are iteratively updated, the above steps are repeated to calibrate the thresholds and add them to the mapping table.

[0092] The electromagnetic coupling path analysis unit uses electromagnetic topology analysis to construct an electromagnetic interference propagation path model for the braking system, analyzes the coupling path between interference sources and sensitive components of the braking system in the full-scene electromagnetic environment feature map, and identifies key interference nodes.

[0093] The three-dimensional adaptation scheme generation unit generates an initial adaptation scheme based on the electromagnetic interference level assessment results for key interference nodes, from three dimensions: hardware suppression, software optimization, and shielding enhancement. The hardware aspect includes the selection of filter capacitors and adjustment of grounding methods; the software aspect includes timing optimization of braking control algorithms and electromagnetic compatibility redundancy strategies; and the shielding aspect includes grounding optimization of wire harness shielding layers and thickening design of shielding covers for sensitive components.

[0094] This module achieves dynamic calibration of electromagnetic interference safety thresholds by establishing a mapping table between dynamic thresholds and operating conditions. In particular, in terms of electromagnetic coupling path analysis and three-dimensional adaptation scheme generation, it combines hardware suppression, software optimization, and shielding enhancement to propose optimal electromagnetic compatibility adaptation schemes for specific characteristics of electromagnetic interference and affected components. In addition, the adaptation effectiveness simulation prediction unit verifies the effectiveness of the schemes through electromagnetic simulation models, providing data support for subsequent optimization.

[0095] The intelligent compatibility and adaptation decision module also includes:

[0096] The adaptation efficiency simulation prediction unit establishes an electromagnetic compatibility simulation model of the braking system based on electromagnetic simulation software, substitutes the initial adaptation scheme into the model, simulates the braking system response under different electromagnetic environments, and predicts the electromagnetic interference suppression efficiency of the adaptation scheme.

[0097] The multi-target adaptation scheme screening unit sets the evaluation indicators for adaptation schemes (interference suppression efficiency ≥85%, braking performance attenuation ≤3%, cost increase ≤10%), performs multi-target screening on the initial adaptation schemes, and retains the candidate adaptation schemes that meet the evaluation indicators.

[0098] Please see Figure 5 As shown, the dynamic closed-loop optimization and control module includes:

[0099] The real-time adaptation performance feedback unit obtains electromagnetic interference parameters and braking system operating status after the implementation of the adaptation scheme through real-time data from the global electromagnetic situation awareness engine module and the braking electromagnetic disturbance tracing and monitoring module, and generates a feedback dataset.

[0100] The improved PSO intelligent optimization unit employs an improved particle swarm optimization algorithm. With maximizing electromagnetic interference suppression efficiency as the objective function and braking performance and cost as constraints, it iteratively optimizes the parameters of candidate adaptation schemes. The iterative formula is as follows:

[0101]

[0102] In the formula, For the first per iteration speed, For inertial weights, and As a learning factor, and A random number in the range [0,1]. This is the optimal solution for the individual. This is the globally optimal solution. For the first Next iteration position;

[0103] The operating condition-strategy dynamic matching output unit matches the optimized adaptation parameters with the braking operating conditions to generate a dynamically adjusted optimal electromagnetic compatibility adaptation strategy, which is then sent to the braking system execution components in real time through the vehicle controller.

[0104] The dynamic closed-loop optimization and control module also includes:

[0105] The multi-level electromagnetic safety early warning unit triggers a multi-level early warning mechanism when the electromagnetic interference level reaches level three or above, and the interference cannot be suppressed to the safe threshold range even after the adaptation strategy is optimized: Level 1 warning (audio-visual prompt), Level 2 warning (limiting non-emergency braking power), and Level 3 warning (activating mechanical braking redundancy).

[0106] The electromagnetic compatibility knowledge base construction unit records electromagnetic environment data, electromagnetic interference parameters, compatibility schemes and optimization effects for the whole scenario, and builds an electromagnetic compatibility compatibility database to provide data support for the subsequent electromagnetic compatibility design of braking systems.

[0107] The combination of a real-time adaptive performance feedback unit and an improved particle swarm optimization algorithm enables the system to continuously improve the electromagnetic compatibility adaptation scheme through real-time data acquisition and dynamic optimization of the improved PSO algorithm. The system can also adjust its strategy based on real-time feedback to ensure that it can provide optimal electromagnetic compatibility under different operating conditions.

[0108] The global electromagnetic situational awareness engine module also includes:

[0109] The external electromagnetic environment time series prediction unit, based on geographical location information and historical electromagnetic environment data, combined with the influence of meteorological conditions (rainfall and humidity) on electromagnetic propagation, trains an LSTM time series prediction model to predict the external electromagnetic noise in the next hour, providing a basis for adjusting the adaptation scheme in advance.

[0110] The braking electromagnetic disturbance tracing and monitoring module also includes:

[0111] The electromagnetic disturbance and fault correlation diagnosis unit establishes an electromagnetic disturbance and component fault correlation model based on the abnormal change characteristics of electromagnetic interference parameters and combined with the braking system fault codes, and performs diagnosis and location of braking system faults caused by electromagnetic compatibility issues.

[0112] The correlation model of the electromagnetic disturbance and fault correlation diagnosis unit adopts an algorithm combining cosine similarity and weight correction, and the calculation formula is as follows:

[0113]

[0114] In the formula, For the first Electromagnetic disturbances and the first The correlation of component failures A correlation of ≥0.8 is considered strong, and 0.5≤ A correlation of <0.8 is considered moderate. A correlation value less than 0.5 is considered a weak association. For feature similarity weights, As the weight for the change in the amplitude of the disturbance, For the duration of the disturbance, weight, For the first The electromagnetic disturbance eigenvector and the first Cosine similarity of fault-like feature vectors For the first When a type of electromagnetic disturbance occurs, the first The amplitude variation of electromagnetic interference of such components For the first The maximum permissible electromagnetic interference amplitude variation threshold for this type of component For the first The duration of electromagnetic disturbances, This is the minimum electromagnetic disturbance duration threshold for a component of this type to fail.

[0115] In summary, the advantages of this invention are:

[0116] The full-domain electromagnetic situational awareness engine module collects multi-dimensional electromagnetic data of the vehicle and external scenarios. Combined with cross-domain data fusion and graph neural networks, it generates a full-scenario electromagnetic environment feature map, enabling a visual representation of electromagnetic sources, interference paths, and sensitive components. Meanwhile, the braking electromagnetic disturbance tracing and monitoring module collects high-frequency interference parameters for core components of the braking system, establishes an "interference-operating condition" correlation model, and accurately captures interference characteristics under different braking conditions, solving the problem of "incomplete perception and inaccurate positioning" of electromagnetic interference in traditional technologies.

[0117] The intelligent compatibility and adaptation decision module generates multi-dimensional adaptation schemes through electromagnetic coupling path analysis and electromagnetic simulation prediction and multi-target screening to ensure that the initial adaptation scheme achieves the optimal balance between interference suppression, braking performance and cost control. The dynamic closed-loop optimization and control module performs dynamic iterative optimization of the adaptation scheme based on the improved PSO algorithm and real-time feedback data. At the same time, it combines external electromagnetic environment timing prediction to realize the advance adjustment of the adaptation strategy, breaking through the limitations of traditional fixed protection schemes that are "lagging in adaptation and poor in targeting", so that the braking system can always maintain stable operation in complex and ever-changing electromagnetic environments.

[0118] By constructing a correlation model combining cosine similarity and weight correction through an electromagnetic disturbance and fault correlation diagnostic unit, abnormal electromagnetic interference parameters are quantitatively correlated with braking system fault codes, enabling accurate diagnosis and location of electromagnetic compatibility faults. This solves the pain points of "fuzzy causality and difficulty in troubleshooting" between electromagnetic interference and faults in traditional technologies, significantly shortens fault troubleshooting time, and reduces after-sales maintenance costs.

[0119] The multi-level electromagnetic safety early warning unit in the dynamic closed-loop optimization and control module triggers a layered early warning mechanism for different levels of electromagnetic interference. In extreme cases, it activates mechanical braking redundancy, forming a dual safety guarantee of "active adaptation + passive protection". At the same time, the historical data accumulated by the electromagnetic adaptation knowledge base construction unit provides data support for the subsequent design of the braking system, continuously improving the reliability and maturity of the product's electromagnetic compatibility design.

[0120] The system achieves full lifecycle optimization of the adaptation strategy through dynamic iterative optimization and timeliness evaluation of the adaptation scheme, and the effectiveness of the adaptation scheme is always maintained at a high level. At the same time, the construction of the association model and the adaptation database can support cross-vehicle migration and adaptation, reduce the repetitive development work of electromagnetic compatibility design for new models, reduce R&D costs, and shorten the product launch cycle.

[0121] The preferred embodiments of the present invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to any specific implementation. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention. The invention is limited only by the claims and their full scope and equivalents.

Claims

1. An electromagnetic compatibility adaptation system for an electric vehicle braking system, characterized in that, include: The module includes a global electromagnetic situational awareness engine, a braking electromagnetic disturbance tracing and monitoring module, an intelligent compatibility and adaptation decision-making module, and a dynamic closed-loop optimization and control module. The full-domain electromagnetic situational awareness engine module is used to collect multi-dimensional electromagnetic data of the electric vehicle and external scene, and generate a full-scene electromagnetic environment feature map through cross-domain data fusion. The braking electromagnetic disturbance source tracing and monitoring module is used to capture the electromagnetic radiation and conducted interference parameters of the core components of the braking system in real time, and establish an interference condition correlation model in combination with the braking conditions. The intelligent compatibility adaptation decision module is electrically connected to the full-domain electromagnetic situation awareness engine module and the braking electromagnetic disturbance source tracing and monitoring module. It is used to couple and analyze the full-scene electromagnetic environment feature map with the electromagnetic interference parameters of the braking system, match the electromagnetic compatibility threshold range of the braking system, and generate an initial electromagnetic compatibility adaptation scheme. The dynamic closed-loop optimization and control module communicates bidirectionally with the intelligent compatibility and adaptation decision module and the full-domain electromagnetic situation awareness engine module. It is used to dynamically iterate and optimize the initial electromagnetic compatibility adaptation scheme based on the real-time updated full-scene electromagnetic environment feature map, and output the optimal electromagnetic compatibility adaptation strategy for the braking system. The global electromagnetic situational awareness engine module includes: The multi-dimensional electromagnetic data acquisition unit is equipped with on-board electromagnetic sensors, environmental electromagnetic monitoring terminals and vehicle bus data interfaces to collect multi-dimensional unstructured electromagnetic data, including electromagnetic fields radiated by the braking system controller, conducted interference from high-voltage wiring harnesses, electromagnetic noise from the external environment and vehicle operating status parameters. The electromagnetic feature purification and processing unit performs denoising, normalization and dimensional calibration on multi-dimensional unstructured electromagnetic data, and extracts the time-domain and frequency-domain features of electromagnetic signals through wavelet transform to obtain standardized electromagnetic feature data. The cross-domain attention fusion computing unit constructs a multimodal fusion network based on an attention mechanism. Taking electromagnetic signal features, environmental parameter features, and vehicle state features as inputs, it calculates the correlation degree of features across different dimensions using a ternary attention weight allocation model. The calculation formula is as follows: ， In the formula, For cross-domain fusion loss function, The characteristic vector of the electromagnetic signal. For environmental parameter feature vectors, This is the vehicle state feature vector. The function for calculating the Pearson correlation coefficient. The weights are associated with electromagnetic-environmental characteristics. Assign weights to the environment-vehicle feature association. The weights for the correlation between the whole vehicle and electromagnetic features; The electromagnetic situation map generation unit, based on cross-domain fused feature data, uses a graph neural network to construct a node-edge association model, taking electromagnetic sources, interference paths, and sensitive components as graph nodes and interference intensity as edge weights to generate a dynamically updated full-scene electromagnetic environment feature map. The dynamic closed-loop optimization and control module includes: The real-time adaptation performance feedback unit obtains electromagnetic interference parameters and braking system operating status after the implementation of the adaptation scheme through real-time data from the global electromagnetic situation awareness engine module and the braking electromagnetic disturbance tracing and monitoring module, and generates a feedback dataset. The improved PSO intelligent optimization unit employs an improved particle swarm optimization algorithm. With maximizing electromagnetic interference suppression efficiency as the objective function and braking performance and cost as constraints, it iteratively optimizes the parameters of candidate adaptation schemes. The iterative formula is as follows: ， In the formula, For the first per iteration speed, For inertial weights, and As a learning factor, and A random number in the range [0,1]. This is the optimal solution for the individual. This is the globally optimal solution. For the first Next iteration position; The operating condition-strategy dynamic matching output unit matches the optimized adaptation parameters with the braking operating conditions to generate a dynamically adjusted optimal electromagnetic compatibility adaptation strategy, which is then sent to the braking system execution components in real time through the vehicle controller.

2. The electromagnetic compatibility adaptation system for an electric vehicle braking system according to claim 1, characterized in that, The braking electromagnetic disturbance tracing and monitoring module includes: The core component, the electromagnetic disturbance monitoring matrix unit, deploys high-frequency electromagnetic probes in the brake master cylinder, hydraulic control unit, motor controller, and wheel speed sensor to collect radiated interference field strength and conducted interference voltage in real time. The operating condition-disturbance timing correlation unit synchronously acquires brake pedal travel, brake pressure, vehicle speed, and battery SOC operating condition parameters through the vehicle CAN bus, establishes the correspondence between electromagnetic interference parameters and braking operating condition timing, and generates an operating condition-disturbance correlation dataset. The intelligent evaluation unit for electromagnetic disturbance levels, based on the electromagnetic compatibility standard for electric vehicles, classifies electromagnetic interference safety levels, and trains a random forest classification model by combining the operating condition-interference correlation dataset to conduct real-time evaluation of electromagnetic interference levels during braking.

3. The electromagnetic compatibility adaptation system for an electric vehicle braking system according to claim 2, characterized in that, The intelligent compatibility and adaptation decision module includes: The operating condition-threshold dynamic calibration unit, based on the electromagnetic susceptibility parameters of the core components of the braking system and combined with the electromagnetic compatibility design requirements of the whole vehicle, calibrates the electromagnetic interference safety threshold range under different braking conditions and establishes a threshold-operating condition mapping table. The electromagnetic coupling path analysis unit uses electromagnetic topology analysis to construct an electromagnetic interference propagation path model for the braking system, analyzes the coupling path between interference sources and sensitive components of the braking system in the full-scene electromagnetic environment feature map, and identifies key interference nodes. The three-dimensional adaptation scheme generation unit generates an initial adaptation scheme from three dimensions: hardware suppression, software optimization, and shielding enhancement, based on the electromagnetic interference level assessment results for key interference nodes.

4. The electromagnetic compatibility adaptation system for an electric vehicle braking system according to claim 3, characterized in that, The intelligent compatibility and adaptation decision module also includes: The adaptation efficiency simulation prediction unit establishes an electromagnetic compatibility simulation model of the braking system based on electromagnetic simulation software, substitutes the initial adaptation scheme into the model, simulates the braking system response under different electromagnetic environments, and predicts the electromagnetic interference suppression efficiency of the adaptation scheme. The multi-target adaptation scheme screening unit sets the evaluation index for adaptation schemes, performs multi-target screening on the initial adaptation schemes, and retains the candidate adaptation schemes that meet the evaluation indexes.

5. The electromagnetic compatibility adaptation system for an electric vehicle braking system according to claim 4, characterized in that, The dynamic closed-loop optimization and control module also includes: The multi-level electromagnetic safety early warning unit triggers a multi-level early warning mechanism when the electromagnetic interference level reaches level three or above, and the interference cannot be suppressed to the safe threshold range even after the adaptation strategy is optimized. The electromagnetic compatibility knowledge base construction unit records electromagnetic environment data, electromagnetic interference parameters, adaptation schemes and optimization effects for all scenarios, and builds an electromagnetic compatibility adaptation database.

6. The electromagnetic compatibility adaptation system for an electric vehicle braking system according to claim 5, characterized in that, The global electromagnetic situational awareness engine module also includes: The external electromagnetic environment time series prediction unit, based on geographical location information and historical electromagnetic environment data, combined with the influence of meteorological conditions on electromagnetic propagation, trains an LSTM time series prediction model to predict electromagnetic noise in the internal and external environments.

7. The electromagnetic compatibility adaptation system for an electric vehicle braking system according to claim 6, characterized in that, The braking electromagnetic disturbance tracing and monitoring module also includes: The electromagnetic disturbance and fault correlation diagnosis unit establishes an electromagnetic disturbance and component fault correlation model based on the abnormal change characteristics of electromagnetic interference parameters and combined with the braking system fault codes, and performs diagnosis and location of braking system faults caused by electromagnetic compatibility issues.

8. The electromagnetic compatibility adaptation system for an electric vehicle braking system according to claim 7, characterized in that, The correlation model of the electromagnetic disturbance and fault correlation diagnosis unit adopts an algorithm combining cosine similarity and weight correction, and the calculation formula is as follows: ， In the formula, For the first Electromagnetic disturbances and the first The correlation of component failures A correlation of ≥0.8 is considered strong, and 0.5≤ A correlation of <0.8 is considered moderate. A correlation value less than 0.5 is considered a weak association. For feature similarity weights, As the weight for the change in the amplitude of the interference, Weighted by the duration of the disturbance. For the first The eigenvector of electromagnetic disturbance and the first Cosine similarity of fault-like feature vectors For the first When a type of electromagnetic disturbance occurs, the first The amplitude variation of electromagnetic interference of such components For the first The maximum permissible electromagnetic interference amplitude variation threshold for this type of component For the first The duration of electromagnetic disturbances, This is the minimum electromagnetic disturbance duration threshold for a component of this type to fail.

Images