An electromagnetic compatibility cooperative system for electric vehicle multi-electric systems

Abstract

This invention relates to the field of electric vehicle power electronics technology, specifically to an electromagnetic compatibility (EMC) collaborative system for multiple electric vehicle systems. The system includes an electromagnetic interference source monitoring module for the vehicle motor, a multi-domain coupled simulation and prediction module, a motor electromagnetic suppression and control module, and an EMC status early warning and feedback module. This invention achieves accurate prediction and evolution trend forecasting of EMC risks in multiple electric systems through the integrated application of digital twin modeling, online learning calibration, and uncertainty quantification. This provides a scientific basis for the formulation of suppression strategies. Furthermore, through the synergistic linkage of a reinforcement learning strategy library and a multi-objective optimization model, it adaptively matches and adapts suppression schemes to different interference scenarios and precisely controls relevant device parameters, improving EMC levels while also considering system energy consumption and response efficiency.

Description

Technical Field

[0001] This invention relates to the field of electric vehicle power electronics technology, specifically to an electromagnetic compatibility cooperative system for multiple electric systems in electric vehicles. Background Technology

[0002] With the rapid development of the new energy vehicle industry, electric vehicles, which are powered by onboard rechargeable batteries (or other energy storage devices) and driven by electric motors while meeting road traffic safety regulations, are experiencing a continuous increase in the integration and complexity of their multi-electric systems (including core electrical components such as motors, batteries, electronic controls, and onboard electrical systems). However, in existing technologies, the multi-electric systems of electric vehicles are prone to problems such as excessive interference, increased energy consumption, and response delays during vehicle operation due to the complexity of electromagnetic interference sources, significant electromagnetic-thermal-mechanical multi-physics coupling characteristics, material aging, assembly deviations, and other non-ideal factors. Furthermore, traditional electromagnetic interference suppression schemes often employ single, fixed strategies, making it difficult to achieve coordinated optimization of electromagnetic compatibility performance, system energy consumption, and control response efficiency. This results in issues such as excessive interference, increased energy consumption, and response delays during vehicle operation, seriously affecting the normal operation of onboard electrical systems and the overall stability of the vehicle.

[0003] Based on this, the present invention provides an electromagnetic compatibility cooperative system for electric vehicle multi-electric systems to solve the aforementioned technical problems. Summary of the Invention

[0004] The purpose of this invention is to provide an electromagnetic compatibility (EMC) collaborative system for multi-electric systems in electric vehicles. This invention achieves accurate prediction and evolution trend forecasting of EMC risks in multi-electric systems through the integrated application of digital twin modeling, online learning calibration, and uncertainty quantification, providing a scientific basis for the formulation of suppression strategies. Furthermore, through the synergistic linkage of reinforcement learning strategy library and multi-objective optimization model, it adaptively matches and adapts suppression schemes to different interference scenarios and precisely controls relevant device parameters, thereby improving the EMC level while taking into account system energy consumption and response efficiency.

[0005] To achieve the above objectives, the present invention provides the following technical solution:

[0006] This invention provides an electromagnetic compatibility (EMC) cooperative system for multiple electric vehicle systems, comprising an electromagnetic interference source monitoring module for the vehicle motor, a multi-domain coupling simulation and prediction module, a motor electromagnetic suppression and control module, and an EMC status early warning and feedback module, wherein:

[0007] The automotive motor electromagnetic interference source monitoring module is used to collect electromagnetic interference signals generated during the operation of the automotive motor in real time and identify the interference frequency band and intensity.

[0008] The multi-domain coupled simulation and prediction module is used to build a dynamic electromagnetic compatibility simulation engine that integrates digital twin technology and online learning algorithms. Based on the collected real-time operating data, it dynamically calibrates the multi-physics coupling model of motor-battery-electronic control-vehicle electrical appliances. By introducing uncertainty quantification methods, it probabilistically models non-ideal factors such as material aging and assembly deviations, and predicts the probability distribution and trend of electromagnetic compatibility risks of multi-electric systems.

[0009] The motor electromagnetic suppression and control module: constructs an interference suppression strategy library based on reinforcement learning algorithm, adaptively matches the motor winding topology reconstruction scheme and inverter drive parameter optimization algorithm according to monitoring results and simulation prediction results, and coordinates the filtering parameters of the dedicated filter device and the shielding level of the shielding device through a multi-objective optimization model.

[0010] The electromagnetic compatibility status early warning and feedback module is used to assess the overall electromagnetic compatibility level of the multi-electric system in real time. When electromagnetic interference exceeds the standard or interference coupling exceeds the limit, it promptly issues an early warning signal and feeds back to the vehicle control system, triggering an emergency control mechanism.

[0011] The automotive motor electromagnetic interference source monitoring module includes a broadband electromagnetic signal acquisition unit, a real-time interference characteristic analysis unit, and a characteristic data standardization and transmission unit, wherein:

[0012] The broadband electromagnetic signal acquisition unit is used to deploy sensor arrays at key locations of the motor and its drive cables to acquire raw electromagnetic interference signals in the conducted and radiated interference frequency bands in real time.

[0013] The real-time interference feature analysis unit is used to perform time-frequency analysis on the acquired raw signal and identify the core feature parameters of the interference, including its spectrum, amplitude, and harmonic components.

[0014] The feature data standardization and transmission unit is used to standardize the analyzed feature data.

[0015] The multi-domain coupled simulation and prediction module includes a multi-physics digital twin modeling unit, an online learning and parameter calibration unit, and an uncertainty quantification and risk prediction unit, wherein:

[0016] The multiphysics digital twin modeling unit is used to construct electromagnetic-thermal-mechanical coupling simulation models covering motors, batteries, electronic controls, and vehicle electrical components.

[0017] The online learning and parameter calibration unit dynamically updates model parameters based on real vehicle operation data and synchronizes the state of the simulation engine and the physical system.

[0018] The uncertainty quantification and risk prediction unit is used to introduce probabilistic methods to model non-ideal factors such as material aging and assembly deviations, and output the probability distribution and evolution trend of electromagnetic compatibility risks.

[0019] The multiphysics digital twin modeling unit constructs an electromagnetic-thermal-mechanical coupling simulation model covering the motor, battery, electronic control, and vehicle electrical components. The specific operation is as follows:

[0020] A1: Establish sub-models for each component, including: establishing an electromagnetic field finite element model of the motor based on Maxwell's equations; constructing an electro-thermal coupling lumped parameter model based on the battery thermal conduction law and circuit theory; establishing a switching transient circuit model of the electronic control system by combining the transient characteristics of the switching devices; and establishing an equivalent model of conducted interference of the vehicle's electrical appliances through impedance analysis.

[0021] A2: By sharing boundary conditions and interface variables, the sub-models of each component are bidirectionally coupled in the time and frequency domains. The motor temperature rise is fed back to the winding resistance parameter as a thermal field output, and the electronic control switch is injected into the wire harness radiation model as an electromagnetic interference source.

[0022] A3: Integrating the topology of the high-voltage wiring harness of the whole vehicle, the physical installation position of the components, the distribution of the grounding network and the shielding structure parameters, a unified multi-physics field collaborative simulation framework is formed to support multi-condition simulation of start-stop, acceleration and braking.

[0023] The uncertainty quantification and risk prediction unit introduces a probabilistic method to model non-ideal factors such as material aging and assembly deviations, and outputs the probability distribution and evolution trend of electromagnetic compatibility risks. The specific operation is as follows:

[0024] B1: Identify the degradation rate of the dielectric properties of motor insulation materials, the assembly gap tolerance of high-voltage connectors, and the capacitance drift of filter capacitors as key uncertainty input variables, and assign them probability distribution types and statistical parameters;

[0025] B2: Based on the multiphysics digital twin model, a random sampling method is used to perform multiple forward simulations on uncertain input variables to generate a response sample set of electromagnetic interference intensity in the sensitive frequency band;

[0026] B3: Perform statistical analysis on the response sample set and output the cumulative distribution function of the vehicle's electromagnetic compatibility failure probability and its evolution trend with the vehicle's mileage.

[0027] In B3, the electromagnetic compatibility failure probability is the proportion of samples in the response sample set that exceed a threshold. The specific calculation formula is as follows:

[0028] ;

[0029] in, The probability of electromagnetic compatibility failure is given by N; N is the total number of simulation samples. The peak value of the electromagnetic interference intensity in the i-th simulation is denoted as . This represents the electromagnetic interference limit; I(•) is the indication function, when... hour ,otherwise ;

[0030] An evolutionary correlation equation for key uncertainty variables is established based on vehicle mileage. The specific formula is as follows:

[0031] ;

[0032] in, denoted as the initial dielectric property degradation rate; k is the degradation rate coefficient; and t is the vehicle's mileage.

[0033] The motor electromagnetic suppression and control module includes a suppression strategy library construction unit, a control scheme matching unit, a multi-objective optimization calculation unit, and a suppression device control unit, wherein:

[0034] The suppression strategy library construction unit is used to train and store electromagnetic interference suppression strategies adapted to different interference scenarios using reinforcement learning algorithms, forming a strategy reserve.

[0035] The control scheme matching unit is used to automatically select suitable motor winding topology reconfiguration schemes and inverter drive parameter optimization algorithms based on monitoring results and simulation prediction conclusions.

[0036] The multi-objective optimization calculation unit is used to construct a multi-objective optimization model of synergistic electromagnetic compatibility effect and system energy consumption, and to calculate the optimal combination of control parameters.

[0037] The suppression device control unit is used to coordinately adjust the filtering parameters of the dedicated filter device and the shielding level of the shielding device based on the optimization results.

[0038] The suppression strategy library construction unit uses reinforcement learning algorithms to train and store electromagnetic interference suppression strategies adapted to different interference scenarios, forming a strategy reserve. The specific operation is as follows:

[0039] C1: Electromagnetic interference frequency, amplitude, motor speed, bus current harmonic content, and temperature are used as state inputs for reinforcement learning;

[0040] C2: The motor winding topology switching command, inverter carrier frequency and modulation method, filter order and shielding activation flag are used as the action output space;

[0041] C3: A multi-objective joint reward function is constructed based on the improvement of electromagnetic compatibility margin, system energy efficiency loss, and control response delay. The specific reward function formula is as follows:

[0042] ;

[0043] in, This represents the increase in electromagnetic compatibility margin. To adjust the amplitude of the interference before adjustment; The amplitude of the interference after adjustment; For system energy efficiency benefits, Rated energy consumption; Energy consumption after regulation; To control response delay losses, This is the rated response time; The response time after regulation; , , These are the weighting coefficients;

[0044] C4: Performs offline policy training in a digital twin simulation environment and stores the converged policy mapping relationship as a policy library for interference scenarios and suppression actions, supporting online fine-tuning based on new working condition data.

[0045] The multi-objective optimization calculation unit constructs a multi-objective optimization model for the synergistic electromagnetic compatibility effect and system energy consumption, and calculates the optimal combination of control parameters. The specific operation is as follows:

[0046] D1: With electromagnetic interference suppression level and vehicle system energy consumption as optimization objectives, and motor temperature rise, inverter switching frequency limit, filter physical adjustable range and control response time as constraints, a multi-objective optimization model is constructed.

[0047] D2: The model is solved using a multi-objective optimization algorithm to generate the Pareto optimal solution set;

[0048] D3: Based on the current driving condition priority, select a set of optimal control parameters from the Pareto optimal solution set and output them to the suppression device control unit.

[0049] The electromagnetic compatibility status early warning and feedback module includes a compatibility level assessment unit, a risk early warning triggering unit, and an information feedback execution unit, wherein:

[0050] The compatibility level assessment unit is used to monitor the operating data of the multi-electric system in real time and quantitatively assess whether the overall electromagnetic compatibility level meets the preset standards.

[0051] The risk warning triggering unit is used to issue a corresponding warning signal according to the risk level when electromagnetic interference or interference coupling exceeds the limit is detected.

[0052] The information feedback execution unit is used to synchronously feed back the warning signal and the current compatibility status data to the vehicle control system and trigger the preset emergency control mechanism.

[0053] Compared with the prior art, the beneficial effects of the present invention are:

[0054] This invention achieves accurate prediction and evolution trend forecasting of electromagnetic compatibility risks in multi-electric systems by integrating digital twin modeling, online learning calibration, and uncertainty quantification. This provides a scientific basis for the formulation of suppression strategies. Furthermore, through the synergistic linkage of reinforcement learning strategy library and multi-objective optimization model, it adaptively matches and adapts suppression schemes to different interference scenarios and precisely controls relevant device parameters, thereby improving the level of electromagnetic compatibility while taking into account system energy consumption and response efficiency. Attached Figure Description

[0055] Figure 1 This is a system diagram of an electromagnetic compatibility cooperative system for a multi-electric system of an electric vehicle according to the present invention.

[0056] Figure 2 This is an overall architecture diagram of an electromagnetic compatibility cooperative system for a multi-electric system in an electric vehicle according to the present invention.

[0057] Figure 3 This is a flowchart of a multi-domain coupling simulation and prediction module for an electromagnetic compatibility cooperative system of an electric vehicle multi-electric system according to the present invention.

[0058] Explanation of icon numbers:

[0059] 100. Automotive Motor Electromagnetic Interference Source Monitoring Module; 101. Wideband Electromagnetic Signal Acquisition Unit; 102. Real-time Interference Feature Analysis Unit; 103. Feature Data Standardization and Transmission Unit; 200. Multi-Domain Coupled Simulation and Prediction Module; 201. Multi-Physics Field Digital Twin Modeling Unit; 202. Online Learning and Parameter Calibration Unit; 203. Uncertainty Quantification and Risk Prediction Unit; 300. Motor Electromagnetic Suppression and Control Module; 301. Suppression Strategy Library Construction Unit; 302. Control Scheme Matching Unit; 303. Multi-Objective Optimization Calculation Unit; 304. Suppression Device Control Unit; 400. Electromagnetic Compatibility Status Early Warning and Feedback Module; 401. Compatibility Level Assessment Unit; 402. Risk Early Warning Trigger Unit; 403. Information Feedback Execution Unit. Detailed Implementation

[0060] The technical solutions of the present invention will be clearly and completely described below with reference to 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 of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0061] Example:

[0062] like Figures 1-3 As shown, this embodiment provides an electromagnetic compatibility (EMC) collaborative system for a multi-electric system of an electric vehicle, including an automotive motor EMC source monitoring module 100, a multi-domain coupling simulation and prediction module 200, a motor electromagnetic suppression and control module 300, and an EMC status early warning and feedback module 400. Specifically: the automotive motor EMC source monitoring module 100 is used to collect electromagnetic interference signals generated during the operation of the automotive motor in real time and identify the interference frequency band and intensity; the multi-domain coupling simulation and prediction module 200 is used to construct a dynamic EMC simulation engine that integrates digital twin technology and online learning algorithms, and dynamically calibrates the multi-physics coupling model of motor-battery-electronic control-vehicle electrical appliances based on the collected real-time operating data, by introducing uncertainties... The system employs a quantitative approach to probabilistically model non-ideal factors such as material aging and assembly deviations, and predicts the probability distribution and trends of electromagnetic compatibility risks in multi-electric systems. The motor electromagnetic suppression and control module 300 uses a reinforcement learning algorithm to construct an interference suppression strategy library. Based on monitoring and simulation prediction results, it adaptively matches motor winding topology reconfiguration schemes and inverter drive parameter optimization algorithms. It also uses a multi-objective optimization model to collaboratively control the filtering parameters of dedicated filtering devices and the shielding level of shielding devices. The electromagnetic compatibility status early warning and feedback module 400 is used to assess the overall electromagnetic compatibility level of the multi-electric system in real time. When electromagnetic interference exceeds the standard or interference coupling exceeds the limit, it promptly issues an early warning signal and feeds it back to the vehicle control system, triggering an emergency control mechanism.

[0063] It should be noted that the automotive motor electromagnetic interference source monitoring module 100 senses the interference status in real time, providing input to the multi-domain coupled simulation and prediction module 200 to dynamically calibrate the digital twin model and quantify the risk. This risk prediction and monitoring data jointly drive the motor electromagnetic suppression and control module 300 to adaptively generate and execute a multi-objective optimized suppression strategy. Finally, the electromagnetic compatibility status early warning and feedback module 400 comprehensively evaluates the electromagnetic compatibility level of the system, realizing the linkage between over-limit early warning and vehicle control.

[0064] In this embodiment, it should also be noted that the automotive motor electromagnetic interference source monitoring module 100 includes a wideband electromagnetic signal acquisition unit 101, an interference feature real-time analysis unit 102, and a feature data standardization and transmission unit 103, wherein: the wideband electromagnetic signal acquisition unit 101 is used to deploy sensor arrays at key locations of the motor and its drive cables to acquire raw electromagnetic interference signals in the conducted and radiated interference frequency bands in real time; the interference feature real-time analysis unit 102 is used to perform time-frequency analysis on the acquired raw signals to identify the core feature parameters of the interference spectrum, amplitude, and harmonic components; and the feature data standardization and transmission unit 103 is used to standardize the analyzed feature data.

[0065] It should be noted that the broadband electromagnetic signal acquisition unit 101 acquires the original electromagnetic interference signals at key locations of the motor and drive cable in real time, the interference feature real-time analysis unit 102 performs time-frequency analysis on the original signal to extract core interference features such as spectrum, amplitude and harmonics, and the feature data standardization and transmission unit 103 performs unified formatting and standardization processing on the analysis results.

[0066] Furthermore, it should be noted that the broadband electromagnetic signal acquisition unit 101 deploys broadband current sensors and electromagnetic radiation sensors at key locations such as the motor stator winding end, inverter output end, and drive cable shielding layer to collect raw conducted and radiated interference signals in the 10kHz-1GHz frequency band in real time. The sensor sampling rate is no less than 20MSps, and the dynamic range is ≥80dB. The feature data standardization and transmission unit 103 uses the Z-score standardization method to normalize the analyzed feature data. The formula is: ,in The mean of the feature data. The standard deviation is denoted as .

[0067] In this embodiment, it should also be noted that the multi-domain coupled simulation and prediction module 200 includes a multi-physics digital twin modeling unit 201, an online learning and parameter calibration unit 202, and an uncertainty quantification and risk prediction unit 203. Specifically, the multi-physics digital twin modeling unit 201 is used to construct an electromagnetic-thermal-mechanical coupled simulation model covering the motor, battery, electronic control system, and vehicle electrical components. The specific operation is as follows: A1: Establish sub-models for each component, including: establishing an electromagnetic field finite element model of the motor based on Maxwell's equations, and constructing an electro-thermal coupled lumped model based on the battery thermal conduction law and circuit theory. The system employs a parametric model, combining the transient characteristics of switching devices to establish a transient circuit model for the electronic control system, and using impedance analysis to establish an equivalent model of conducted interference from onboard electrical components. A2: By sharing boundary conditions and interface variables, the sub-models of each component are bidirectionally coupled in the time and frequency domains. Motor temperature rise is fed back to the winding resistance parameters as a thermal field output, and the electronic control switch is injected into the wiring harness radiation model as an electromagnetic interference source. A3: The system integrates the topology of the vehicle's high-voltage wiring harness, the physical installation locations of components, the distribution of the grounding network, and the parameters of the shielding structure, forming a unified multi-physics collaborative simulation framework that supports multi-condition simulations of start-stop, acceleration, and braking. The online learning and parameter calibration unit 202 dynamically updates model parameters based on real vehicle operating data, synchronizing the state of the simulation engine and the physical system. The uncertainty quantification and risk prediction unit 203 introduces probabilistic methods to model non-ideal factors such as material aging and assembly deviations, outputting the probability distribution and evolution trend of electromagnetic compatibility risks. The specific operations are as follows: B1: Identify the degradation rate of the dielectric properties of the motor insulation material, the assembly gap tolerance of the high-voltage connector, and the capacitance drift of the filter capacitor as key uncertainty input variables, and assign them probability distribution types and statistical parameters; B2: Based on the multi-physics digital twin model, use random sampling to perform multiple forward simulations on the uncertainty input variables to generate a response sample set of electromagnetic interference intensity in the sensitive frequency band; B3: Perform statistical analysis on the response sample set, and output the cumulative distribution function of the vehicle's electromagnetic compatibility failure probability and its evolution trend with vehicle mileage. In B3, the electromagnetic compatibility failure probability is the proportion of samples in the response sample set that exceed the threshold, and the specific calculation formula is as follows:

[0068] ;

[0069] in, The probability of electromagnetic compatibility failure is given by N; N is the total number of simulation samples. The peak value of the electromagnetic interference intensity in the i-th simulation is denoted as . This represents the electromagnetic interference limit; I(•) is the indication function, when... hour ,otherwise ;

[0070] An evolutionary correlation equation for key uncertainty variables is established based on vehicle mileage. The specific formula is as follows:

[0071] ;

[0072] in, denoted as the initial dielectric property degradation rate; k is the degradation rate coefficient; and t is the vehicle's mileage.

[0073] It should be noted that the multiphysics digital twin modeling unit 201 constructs a basic framework for electromagnetic-thermal-mechanical coupling simulation covering the motor, battery, electronic control, and vehicle electrical components. The online learning and parameter calibration unit 202 dynamically corrects the model based on real vehicle operation data to achieve state synchronization between the digital twin and the physical system. The uncertainty quantification and risk prediction unit 203, based on the calibrated model, introduces uncertain variables such as material aging and assembly deviation to conduct probabilistic forward simulation. Through statistical analysis, it outputs the probability distribution of electromagnetic compatibility risks and their evolution trend with vehicle mileage.

[0074] Furthermore, it should be noted that the dielectric property degradation rate of the motor insulation material in B1... It follows a Weibull distribution, and its probability density function is: ;in, For shape parameters , For scale parameters ( ∈[0.001, 0.005]), statistical parameters are obtained by fitting accelerated aging test data; the high-voltage connector assembly gap tolerance ∆s follows a normal distribution, and the probability density function is: in, The mean ( ∈[0, 0.1mm]), Standard deviation ( ∈[0.02, 0.05mm]), obtained statistically based on batch production assembly data; the filter capacitor value drift ∆C follows a normal distribution, with the probability density function being: ;in, The mean ( ∈[0, 5%]), Standard deviation ( (∈[0.5%, 1.5%]), obtained based on experimental data on the long-term stability of capacitors.

[0075] The multiphysics digital twin model, constructed based on the multiphysics digital twin modeling unit 201, uses the Latin hypercube sampling method to perform N≥1000 forward simulations on the uncertain input variables, generating a response sample set of electromagnetic interference intensity in the sensitive frequency band of 10kHz-1GHz. .

[0076] In this embodiment, it should also be noted that the motor electromagnetic suppression control module 300 includes a suppression strategy library construction unit 301, a control scheme matching unit 302, a multi-objective optimization calculation unit 303, and a suppression device control unit 304. Specifically, the suppression strategy library construction unit 301 is used to train and store electromagnetic interference suppression strategies adapted to different interference scenarios using reinforcement learning algorithms, forming a strategy reserve. The specific operations are as follows: C1: The electromagnetic interference main frequency, amplitude, motor speed, bus current harmonic content, and temperature are used as the state input for reinforcement learning; C2: The motor winding topology switching command, inverter carrier frequency and modulation method, filter order, and shielding activation flag are used as the action output space; C3: A multi-objective joint reward function is constructed based on the electromagnetic compatibility margin improvement, system energy efficiency loss, and control response delay. The specific reward function formula is:

[0077] ;

[0078] in, This represents the increase in electromagnetic compatibility margin.

[0079] To adjust the amplitude of the interference before adjustment; The amplitude of the interference after adjustment; For system energy efficiency benefits, Rated energy consumption; Energy consumption after regulation; To control response delay losses, This is the rated response time; The response time after regulation; , , C4: Performs offline policy training in a digital twin simulation environment and stores the converged policy mapping relationship as a policy library for interference scenarios and suppression actions, supporting online fine-tuning based on new operating condition data. Control scheme matching unit 302: Used to automatically select suitable motor winding topology reconstruction schemes and inverter drive parameter optimization algorithms based on monitoring results and simulation prediction conclusions; Multi-objective optimization calculation unit 303: Used to construct a multi-objective optimization model for synergistic electromagnetic compatibility effect and system energy consumption, and calculate the optimal combination of control parameters; The specific operation is as follows: D1: With electromagnetic interference suppression level and vehicle system energy consumption as optimization objectives, and with motor temperature rise, inverter switching frequency upper limit, filter physical adjustable range and control response time as constraints, a multi-objective optimization model is constructed; D2: The model is solved using a multi-objective optimization algorithm to generate a Pareto optimal solution set; D3: Based on the priority of the current driving condition, a set of optimal control parameter combinations is selected from the Pareto optimal solution set and output to the suppression device control unit 304. Suppression device control unit 304: used to coordinately adjust the filtering parameters of the dedicated filter device and the shielding level of the shielding device according to the optimization results.

[0080] It should be noted that the suppression strategy library construction unit 301 uses reinforcement learning to train and update an intelligent suppression strategy library covering multiple interference scenarios offline based on a digital twin environment. The control scheme matching unit 302 combines real-time monitoring and simulation prediction results to initially select suitable winding topology and driving parameter schemes from the strategy library. On this basis, the multi-objective optimization calculation unit 303 further constructs an optimization model with electromagnetic compatibility performance and system energy efficiency as the core objectives, while taking into account temperature rise and response constraints. It solves and selects the Pareto optimal control parameter combination. Finally, the suppression device control unit 304 performs coordinated adjustment of the filter and shielding device.

[0081] Furthermore, it should be noted that the weighting coefficients in C3... , , satisfy In C4, offline policy training is performed in a digital twin simulation environment for typical scenarios such as low-intensity narrowband interference, high-intensity broadband interference, and transient pulse interference. The policy is considered to have converged when the mean fluctuation of the reward function is ≤3% after 500 consecutive training rounds. The converged policy mapping relationship is stored as a policy library of "interference scenario features - suppression action parameters". When the feature similarity between new working condition data and existing scenarios in the policy library is less than 85%, an online fine-tuning mechanism is triggered to update the policy library based on reinforcement learning incremental training.

[0082] The control scheme matching unit 302, based on the K-nearest neighbor algorithm, performs similarity matching between the monitoring results of the automotive motor electromagnetic interference source monitoring module 100, the risk prediction conclusions of the multi-domain coupled simulation and prediction module 200, and the scene features in the suppression strategy library, and selects motor winding topology reconstruction schemes and inverter drive parameter optimization algorithms with similarity ≥ 90%.

[0083] D1: A multi-objective optimization model is constructed with the optimization objectives of maximizing electromagnetic compatibility and minimizing system energy consumption. The objective function is: ,in, , These are the motor winding topology parameters. The inverter carrier frequency, The filter order is given; constraints include: motor temperature rise. Inverter switching frequency filter order Control response time In D2, the NSGA-III algorithm is used to solve the model and generate a Pareto optimal solution set.

[0084] In this embodiment, it should also be noted that the electromagnetic compatibility status warning and feedback module 400 includes a compatibility level assessment unit 401, a risk warning triggering unit 402, and an information feedback execution unit 403. Specifically: the compatibility level assessment unit 401 is used to monitor the operating data of the multi-electric system in real time and quantitatively assess whether the overall electromagnetic compatibility level meets the preset standards; the risk warning triggering unit 402 is used to issue corresponding warning signals according to the risk level when electromagnetic interference exceeds the standard or interference coupling exceeds the limit; and the information feedback execution unit 403 is used to synchronously feed the warning signal and the current compatibility status data back to the vehicle control system and trigger a preset emergency control mechanism.

[0085] It should be noted that the compatibility level assessment unit 401 quantifies the electromagnetic compatibility status of the multi-electric system in real time, the risk warning triggering unit 402 generates graded warning signals according to the risk level based on the assessment results, and the information feedback execution unit 403 synchronously transmits the warning information and compatibility status data back to the vehicle control system to trigger the emergency control mechanism.

[0086] Furthermore, it should be noted that the compatibility level assessment unit 401 monitors in real time the electromagnetic interference intensity, component temperature, energy consumption, and other operating data of the multi-electric system to determine the electromagnetic compatibility margin. , Real-time interference intensity is used as a core evaluation indicator to quantitatively assess whether the overall electromagnetic compatibility level meets the preset standards. (Qualified).

[0087] When electromagnetic interference or interference coupling exceeds the limit, the risk warning triggering unit 402 issues corresponding audible and visual warning signals according to the risk level. There are three risk levels: ① Mild risk: 5%≤M<10%, yellow warning is issued; ② Moderate risk: 0≤M<5%, orange warning is issued; ③ Severe risk: M<0, red warning is issued, and corresponding audible and visual warning signals are issued.

[0088] The emergency mechanism in the information feedback execution unit 403 is as follows: send the highest priority suppression command to the motor electromagnetic suppression control module 300, request the battery management system to limit the peak discharge power, and request the thermal management system to strengthen the cooling of key components.

[0089] In the description of this specification, references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0090] 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 the specific implementations described. 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 cooperative system for multi-electric systems in electric vehicles, characterized in that, It includes an automotive motor electromagnetic interference source monitoring module (100), a multi-domain coupling simulation and prediction module (200), a motor electromagnetic suppression and control module (300), and an electromagnetic compatibility status early warning and feedback module (400), wherein: The automotive motor electromagnetic interference source monitoring module (100) is used to collect electromagnetic interference signals generated during the operation of the automotive motor in real time and identify the interference frequency band and intensity. The multi-domain coupling simulation and prediction module (200) is used to build a dynamic electromagnetic compatibility simulation engine that integrates digital twin technology and online learning algorithms. Based on the collected real-time running data, it dynamically calibrates the multi-physics coupling model of motor-battery-electronic control-vehicle electrical appliances. By introducing uncertainty quantification methods, it probabilistically models the non-ideal factors of material aging and assembly deviation, and predicts the probability distribution and trend of electromagnetic compatibility risks of multi-electric systems. The motor electromagnetic suppression and control module (300) constructs an interference suppression strategy library based on reinforcement learning algorithm. According to the monitoring results and simulation prediction results, it adaptively matches the motor winding topology reconstruction scheme and the inverter drive parameter optimization algorithm. It also coordinates and controls the filter parameters of the dedicated filter device and the shielding level of the shielding device through a multi-objective optimization model. The electromagnetic compatibility status early warning and feedback module (400) is used to evaluate the overall electromagnetic compatibility level of the multi-electric system in real time. When electromagnetic interference exceeds the standard or interference coupling exceeds the limit, it promptly issues an early warning signal and feeds it back to the vehicle control system, triggering an emergency control mechanism.

2. The electromagnetic compatibility cooperative system for a multi-electric system of an electric vehicle according to claim 1, characterized in that, The automotive motor electromagnetic interference source monitoring module (100) includes a broadband electromagnetic signal acquisition unit (101), an interference characteristic real-time analysis unit (102), and a characteristic data standardization and transmission unit (103), wherein: The broadband electromagnetic signal acquisition unit (101) is used to deploy sensor arrays at key locations of the motor and its drive cable to acquire raw electromagnetic interference signals in the conducted and radiated interference frequency bands in real time. The real-time interference feature analysis unit (102) is used to perform time-frequency analysis on the acquired raw signal and identify the core feature parameters of the interference's spectrum, amplitude, and harmonic components. The feature data standardization and transmission unit (103) is used to standardize the analyzed feature data.

3. The electromagnetic compatibility cooperative system for a multi-electric system of an electric vehicle according to claim 1, characterized in that, The multi-domain coupled simulation and prediction module (200) includes a multi-physics digital twin modeling unit (201), an online learning and parameter calibration unit (202), and an uncertainty quantification and risk prediction unit (203), wherein: The multiphysics digital twin modeling unit (201) is used to construct an electromagnetic-thermal-mechanical coupling simulation model covering motors, batteries, electronic controls and vehicle electrical appliances; The online learning and parameter calibration unit (202) dynamically updates model parameters based on real vehicle operation data and synchronizes the state of the simulation engine and the physical system. The uncertainty quantification and risk prediction unit (203) is used to introduce probabilistic methods to model non-ideal factors such as material aging and assembly deviation, and output the probability distribution and evolution trend of electromagnetic compatibility risk.

4. The electromagnetic compatibility cooperative system for a multi-electric system of an electric vehicle according to claim 3, characterized in that, The multiphysics digital twin modeling unit (201) constructs an electromagnetic-thermal-mechanical coupling simulation model covering the motor, battery, electronic control, and vehicle electrical components. The specific operation is as follows: A1: Establish sub-models for each component, including: establishing an electromagnetic field finite element model of the motor based on Maxwell's equations; constructing an electro-thermal coupling lumped parameter model based on the battery thermal conduction law and circuit theory; establishing a switching transient circuit model of the electronic control system by combining the transient characteristics of the switching devices; and establishing an equivalent model of conducted interference of the vehicle's electrical appliances through impedance analysis. A2: By sharing boundary conditions and interface variables, the sub-models of each component are bidirectionally coupled in the time and frequency domains. The motor temperature rise is fed back to the winding resistance parameter as a thermal field output, and the electronic control switch is injected into the wire harness radiation model as an electromagnetic interference source. A3: Integrating the topology of the high-voltage wiring harness of the whole vehicle, the physical installation position of the components, the distribution of the grounding network and the shielding structure parameters, a unified multi-physics field collaborative simulation framework is formed to support multi-condition simulation of start-stop, acceleration and braking.

5. The electromagnetic compatibility cooperative system for a multi-electric system of an electric vehicle according to claim 3, characterized in that, The uncertainty quantification and risk prediction unit (203) introduces a probabilistic method to model the non-ideal factors such as material aging and assembly deviation, and outputs the probability distribution and evolution trend of electromagnetic compatibility risk. The specific operation is as follows: B1: Identify the degradation rate of the dielectric properties of motor insulation materials, the assembly gap tolerance of high-voltage connectors, and the capacitance drift of filter capacitors as key uncertainty input variables, and assign them probability distribution types and statistical parameters; B2: Based on the multiphysics digital twin model, a random sampling method is used to perform multiple forward simulations on uncertain input variables to generate a response sample set of electromagnetic interference intensity in the sensitive frequency band; B3: Perform statistical analysis on the response sample set and output the cumulative distribution function of the vehicle's electromagnetic compatibility failure probability and its evolution trend with the vehicle's mileage.

6. The electromagnetic compatibility cooperative system for a multi-electric system of an electric vehicle according to claim 5, characterized in that, In B3, the electromagnetic compatibility failure probability is the proportion of samples in the response sample set that exceed a threshold. The specific calculation formula is as follows: ; in, The probability of electromagnetic compatibility failure is given by N; N is the total number of simulation samples. The peak value of the electromagnetic interference intensity in the i-th simulation is denoted as . This represents the electromagnetic interference limit; I(•) is the indication function, when... hour ,otherwise ; An evolutionary correlation equation for key uncertainty variables is established based on vehicle mileage. The specific formula is as follows: ； in, denoted as the initial dielectric property degradation rate; k is the degradation rate coefficient; and t is the vehicle's mileage.

7. The electromagnetic compatibility cooperative system for a multi-electric system of an electric vehicle according to claim 1, characterized in that, The motor electromagnetic suppression and control module (300) includes a suppression strategy library construction unit (301), a control scheme matching unit (302), a multi-objective optimization calculation unit (303), and a suppression device control unit (304), wherein: The suppression strategy library construction unit (301) is used to train and store electromagnetic interference suppression strategies adapted to different interference scenarios using reinforcement learning algorithms, forming a strategy reserve. The control scheme matching unit (302) is used to automatically select suitable motor winding topology reconfiguration schemes and inverter drive parameter optimization algorithms based on monitoring results and simulation prediction conclusions. The multi-objective optimization calculation unit (303) is used to construct a multi-objective optimization model of synergistic electromagnetic compatibility effect and system energy consumption, and to calculate the optimal combination of control parameters. The suppression device control unit (304) is used to coordinately adjust the filtering parameters of the dedicated filter device and the shielding level of the shielding device according to the optimization results.

8. The electromagnetic compatibility cooperative system for a multi-electric system of an electric vehicle according to claim 7, characterized in that, The suppression strategy library construction unit (301) uses reinforcement learning algorithms to train and store electromagnetic interference suppression strategies adapted to different interference scenarios, forming a strategy reserve. The specific operation is as follows: C1: Electromagnetic interference frequency, amplitude, motor speed, bus current harmonic content, and temperature are used as state inputs for reinforcement learning; C2: The motor winding topology switching command, inverter carrier frequency and modulation method, filter order and shielding activation flag are used as the action output space; C3: A multi-objective joint reward function is constructed based on the improvement of electromagnetic compatibility margin, system energy efficiency loss, and control response delay. The specific reward function formula is as follows: ； in, This represents the increase in electromagnetic compatibility margin. To adjust the amplitude of the interference before adjustment; The amplitude of the interference after adjustment; For system energy efficiency benefits, Rated energy consumption; Energy consumption after regulation; To control response delay losses, This is the rated response time; The response time after regulation; , , These are the weighting coefficients; C4: Performs offline policy training in a digital twin simulation environment and stores the converged policy mapping relationship as a policy library for interference scenarios and suppression actions, supporting online fine-tuning based on new working condition data.

9. The electromagnetic compatibility cooperative system for a multi-electric system of an electric vehicle according to claim 7, characterized in that, The multi-objective optimization calculation unit (303) constructs a multi-objective optimization model for the synergistic electromagnetic compatibility effect and system energy consumption, and calculates the optimal combination of control parameters. The specific operation is as follows: D1: With electromagnetic interference suppression level and vehicle system energy consumption as optimization objectives, and motor temperature rise, inverter switching frequency limit, filter physical adjustable range and control response time as constraints, a multi-objective optimization model is constructed. D2: The model is solved using a multi-objective optimization algorithm to generate the Pareto optimal solution set; D3: Based on the current driving condition priority, select a set of optimal control parameters from the Pareto optimal solution set and output them to the suppression device control unit (304).

10. The electromagnetic compatibility cooperative system for a multi-electric system of an electric vehicle according to claim 1, characterized in that, The electromagnetic compatibility status early warning and feedback module (400) includes a compatibility level assessment unit (401), a risk early warning triggering unit (402), and an information feedback execution unit (403), wherein: The compatibility level assessment unit (401) is used to monitor the operation data of the multi-electric system in real time and quantitatively assess whether the overall electromagnetic compatibility level meets the preset standard. The risk warning triggering unit (402) is used to issue a corresponding warning signal according to the risk level when electromagnetic interference or interference coupling exceeds the limit is detected. The information feedback execution unit (403) is used to synchronously feed back the warning signal and the current compatibility status data to the vehicle control system and trigger the preset emergency control mechanism.

Images