An Active Sound-Based Anti-Drowsiness System and Method for Electric Vehicles Based on Multimodal Information Fusion
By using a multimodal information fusion system to identify motion sickness levels in real time and generate acoustic intervention signals synchronized with vehicle dynamics, the problem of inaccurate motion sickness assessment and lack of auditory information in existing technologies is solved, achieving personalized, multi-sensory motion sickness relief.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- WUHAN UNIV OF TECH
- Filing Date
- 2026-02-28
- Publication Date
- 2026-05-26
AI Technical Summary
Existing active intervention technologies for motion sickness lack real-time and accuracy in assessing motion sickness, and electric vehicles lack the background noise of traditional internal combustion engines, resulting in a lack of auditory information for passengers and an inability to provide accurate sensory cues, especially in electric vehicles where the effect is limited.
A multimodal information fusion system is adopted, which uses vehicle motion sensing and physiological state monitoring, especially EEG signals, combined with a deep learning model to identify motion sickness levels in real time. It also generates acoustic intervention signals that are synchronized with vehicle dynamics through an order synthesis algorithm, and coordinates the control of other devices such as seat vibration and micro-wind system to form a closed-loop optimization.
It achieves accurate and real-time judgment of motion sickness, provides auditory information that is completely synchronized with vehicle dynamics, enhances sensory consistency, personalizes the intensity of intervention, and uses multi-sensory collaboration to alleviate motion sickness and improve travel comfort.
Smart Images
Figure CN122078413A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of intelligent vehicles and active health technology, specifically to an active sound-based motion sickness suppression system and method for electric vehicles based on multimodal information fusion. Background Technology
[0002] Motion sickness (commonly known as kinetosis) is a common symptom of discomfort when traveling, mainly caused by sensory conflict, that is, a discrepancy between the motion perceived by the inner ear's vestibular system and the information received by the visual system. Traditional methods for relieving motion sickness are mostly passive, such as taking medication, opening windows for ventilation, or focusing on a fixed point. However, these methods have limitations, including varying effectiveness from person to person, side effects, or limited applicability.
[0003] With the development of intelligent vehicle technology, some proactive motion sickness intervention technologies have emerged. For example, simple motion sensors can predict vehicle dynamics and provide sound or vibration cues, or biosensors (such as heart rate monitors) can detect discomfort and play pre-stored soothing music.
[0004] However, existing active intervention techniques for motion sickness have the following technical problems: First, the assessment of motion sickness relies heavily on subjective reports or single, delayed physiological indicators, resulting in insufficient real-time, objectivity, and accuracy. Secondly, in terms of intervention methods, the pre-stored sounds or fixed-pattern prompts have a weak correlation with the real-time dynamics of the vehicle, cannot provide accurate sensory indications, and lack adaptive adjustment capabilities, resulting in limited intervention effects. In particular, for electric vehicles, the lack of the sound background (background noise) generated by traditional internal combustion engines makes the vehicle dynamic information obtained by passengers in the auditory dimension even more scarce, which may exacerbate sensory conflict. Summary of the Invention
[0005] To address the shortcomings of existing technologies, this invention proposes an active sound-based motion sickness suppression system and method for electric vehicles based on multimodal information fusion. This system not only achieves accurate and real-time identification of motion sickness, but also compensates for auditory information gaps and enhances the consistency between sensory and visual perception.
[0006] To achieve the above objectives, the present invention provides an active sound-based motion sickness suppression system for electric vehicles based on multimodal information fusion, which is characterized by including a signal acquisition module, a data processing and motion sickness level recognition module, an acoustic signal generation module, and an on-board sound-generating device. The signal acquisition module includes a vehicle motion sensing unit and a physiological state monitoring unit. The vehicle motion sensing unit is used to acquire vehicle motion parameters. The physiological state monitoring unit is used to acquire the physiological state data of the occupants. The physiological state data includes at least the raw electroencephalogram (EEG) signals covering the prefrontal cortex region. The data processing and motion sickness level recognition module is connected to the signal acquisition module, which fuses and analyzes the raw EEG signals and vehicle motion parameters, and outputs the motion sickness level judgment result. The acoustic signal generation module is connected to the signal acquisition module and the data processing and motion sickness level recognition module. First, a virtual fundamental frequency signal is mapped based on the real-time acquired vehicle motion parameters. Then, a synthetic audio signal containing harmonic components of each order is generated through an order synthesis algorithm. When the motion sickness level is the weakest level, the parameter reference values of each order harmonic are set. When the motion sickness level exceeds the weakest level, the corresponding parameters of specific order harmonics are boosted according to the current motion sickness level and the preset mapping relationship to enhance the synthetic audio signal as an acoustic intervention signal. The vehicle-mounted sound device is connected to the acoustic signal generation module, receives acoustic intervention signals, and plays them, providing intervention sounds that are precisely synchronized with the vehicle's dynamic process and whose intensity is adjustable.
[0007] Furthermore, in the data processing and motion sickness level recognition module, the fusion analysis includes preprocessing and calculating the original EEG signal to obtain the EEG comprehensive variation index; simultaneously, calculating the vehicle motion parameters to obtain the vehicle motion characteristics; finally, inputting the EEG comprehensive variation index and the vehicle motion characteristics into the motion sickness level recognition model, outputting the probability distribution of motion sickness levels through the motion sickness level recognition model, and taking the level corresponding to the highest probability as the current motion sickness level judgment result.
[0008] Furthermore, the comprehensive variability index of brain waves is calculated using the following formula. In the formula, CVEI The comprehensive variability index of brain waves, , These are the weighting coefficients. P θ for θ The power spectral density of the wave, P α for α The power spectral density of the wave, P β for β The power spectral density of the wave, P δ for δ The power spectral density of the wave.
[0009] Furthermore, the motion sickness level recognition model is a pre-trained neural network model that integrates CNN and attention mechanisms.
[0010] Furthermore, in the acoustic signal generation module, the order synthesis algorithm is expressed by the following formula: S(t) =∑ A n * sin ( 2π * n * f 0* t ), n=1,2,3...(n (Harmonic order) In the formula, S(t) Indicates a synthesized audio signal. A n These represent the amplitude parameters of each harmonic order. f 0 represents the reference frequency. t Indicates the time it takes for the vehicle to travel.
[0011] Furthermore, it includes a collaborative control module that operates based on the level of motion sickness and the vehicle's motion status, instructing other devices within the vehicle to assist in alleviating motion sickness.
[0012] Furthermore, it also includes a closed-loop control module, which is used to implement different control schemes based on the EEG comprehensive variability index of the next time window; the control schemes include maintaining the current vehicle motion parameters if the next EEG comprehensive variability index decreases; and adjusting the vehicle motion parameters if the next EEG comprehensive variability index increases or remains unchanged, until the motion sickness level is detected to decrease.
[0013] This invention also designs an active sound-based motion sickness suppression method for electric vehicles based on multimodal information fusion, which is characterized by the following steps: S1) Collect vehicle motion parameters and occupant physiological state data, wherein the physiological state data includes at least raw electroencephalogram (EEG) signals covering the prefrontal cortex region; S2) The raw EEG signals and vehicle motion parameters are fused and analyzed to output the motion sickness level judgment result; S3) A virtual fundamental frequency signal is mapped based on the real-time acquired vehicle motion parameters, and then a synthetic audio signal containing harmonic components of each order is generated through an order synthesis algorithm; when the motion sickness level is the weakest level, the parameter reference value of each order harmonic is set; when the motion sickness level exceeds the weakest level, the corresponding parameters of specific order harmonics are boosted according to the current motion sickness level and the preset mapping relationship to enhance the synthetic audio signal as an acoustic intervention signal. S4) Receives and plays acoustic intervention signals, providing intervention sounds that are precisely synchronized with the vehicle's dynamic process and have adjustable intensity; S5) Continue to monitor the physiological status data of passengers to determine whether the motion sickness level has decreased. If the motion sickness level has not decreased, return to step S3) and intervene again after adjusting the synthesized audio signal to form a closed-loop optimization.
[0014] Furthermore, S4 also includes working based on motion sickness level and vehicle motion status, and coordinating with other devices in the vehicle to help alleviate motion sickness.
[0015] The advantages of this invention are: 1. This invention provides accurate and objective judgment: By using EEG signals as the core physiological indicator, extracting power spectrum features of specific frequency bands and calculating the comprehensive variation index, and combining vehicle motion information, a deep learning model is used for fusion analysis, which achieves an objective, quantitative, and real-time accurate judgment of motion sickness level, overcoming the lag and inaccuracy of subjective reports. 2. This invention intervenes in real-time dynamics: It abandons the traditional method of playing pre-stored fixed audio and adopts order synthesis or frequency shifting and pitch shifting algorithms. It can use real-time vehicle motion parameters (such as motor speed, torque, vehicle speed, pedal opening, etc.) as input to synthesize sound that is completely synchronized with the vehicle's "current moment" dynamics. This sound itself carries information about the vehicle's future motion trend and can provide accurate predictions for the occupant's vestibular system, fundamentally alleviating sensory conflict. In particular, it provides effective dynamic compensation for the lack of auditory information caused by the quiet environment of electric vehicles. 3. Personalized Adaptation of the Invention: The system uses motion sickness level as the core control variable and dynamically adjusts the sound synthesis parameters (such as modulation order amplitude and frequency transformation curve) to achieve stepless adjustment of intervention intensity; at the same time, the system forms a closed loop of "monitoring-judgment-intervention-re-monitoring", which can continuously optimize the intervention strategy based on the individual's real-time physiological feedback to achieve a highly personalized motion sickness suppression experience. 4. Multimodal collaboration of the present invention: It not only intervenes through sound, but also links seat vibration, wind system, fragrance and other devices through the collaborative control module to provide consistent environmental cues from multiple sensory channels such as hearing, body sensation and smell, so as to enhance the overall effect of anti-dizziness and improve the comfort of riding. This invention relates to an active acoustic motion sickness suppression system and method for electric vehicles based on multimodal information fusion. It enables accurate judgment of motion sickness and can dynamically generate highly correlated acoustic intervention signals based on the unique vehicle motion parameters of electric vehicles to fill the gap in auditory information and achieve motion sickness suppression. Attached Figure Description
[0016] Figure 1 This is a block diagram of the overall structure of the active sound-based motion sickness suppression system for electric vehicles based on multimodal information fusion in this invention. Figure 2 This is a schematic diagram of the processing flow of the motion sickness level recognition model in this invention; Figure 3 This is a schematic diagram illustrating the principle of generating acoustic intervention signals based on the order synthesis algorithm in this invention; Figure 4 This is a flowchart of the closed-loop control logic in this invention; Figure 5 This is a flowchart of the active sound emission method for motion sickness suppression in electric vehicles based on multimodal information fusion in this invention. Detailed Implementation
[0017] The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.
[0018] In the description of this invention, it should be understood that the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention.
[0019] like Figure 1 As shown, the present invention discloses an active sound-based motion sickness suppression system for electric vehicles based on multimodal information fusion, which is integrated into the vehicle and includes a signal acquisition module 1, a data processing and motion sickness level recognition module 2, an acoustic signal generation module 3, and an on-board sound-generating device 4.
[0020] The signal acquisition module 1 includes a vehicle motion sensing unit and a physiological state monitoring unit. The vehicle motion sensing unit is used to acquire one or more vehicle motion parameters, including vehicle speed, acceleration, angular velocity, accelerator pedal opening, and brake pedal opening. The physiological state monitoring unit is used to acquire physiological state data of the occupants, and the physiological state data includes at least raw electroencephalogram (EEG) signals covering the prefrontal cortex region.
[0021] Specifically, the vehicle motion sensing unit collects vehicle motion parameters via the vehicle's CAN bus. The electroencephalogram (EEG) signals are collected via a wearable device.
[0022] In this example, a portable wireless EEG acquisition device is used to collect the passenger's EEG signals. The electrodes of the wireless EEG acquisition device cover the wearer's forehead Fp1, Fp2 and other points, and collect the raw EEG signals at a sampling rate of no less than 128Hz, and transmit them through Bluetooth or a dedicated wireless network in the vehicle.
[0023] The output of the signal acquisition module 1 is connected to the data processing and motion sickness level recognition module 2 and the acoustic signal generation module 3, respectively.
[0024] The data processing and motion sickness level recognition module 2 receives the raw EEG signals and vehicle motion parameters collected by the signal acquisition module 1, performs fusion analysis on the raw EEG signals and vehicle motion parameters, and outputs the motion sickness level judgment result.
[0025] The fusion analysis includes preprocessing and calculating the raw EEG signals to obtain the EEG comprehensive variation index; simultaneously, calculating the vehicle motion parameters to obtain the vehicle motion characteristics; finally, inputting the EEG comprehensive variation index and the vehicle motion characteristics into the motion sickness level recognition model, outputting the probability distribution of motion sickness levels through the motion sickness level recognition model, and taking the level corresponding to the highest probability as the current motion sickness level judgment result.
[0026] The preprocessing includes power frequency filtering, removal of electrooculogram artifacts, and segmentation; subsequently, a Fast Fourier Transform is performed on each data segment (e.g., 4 seconds in duration) to calculate... Wave (1-4 Hz), Wave (4-8 Hz), Wave (8-13 Hz), The power spectral density of the wave (13-30Hz) is calculated; then, the comprehensive variability index of the EEG is calculated using a preset weighting formula.
[0027] The comprehensive variability index of brain waves is calculated using the following formula. In the formula, CVEI The comprehensive variability index of brain waves, , These are the weighting coefficients. P θ for θ The power spectral density of the wave, P α for α The power spectral density of the wave, P β for β The power spectral density of the wave, P δ for δ The power spectral density of the wave.
[0028] The motion sickness level recognition model is a pre-trained neural network model that integrates CNN and attention mechanisms.
[0029] Specifically, the motion sickness levels include four levels: "no motion sickness", "mild", "moderate", and "severe".
[0030] The output of the data processing and motion sickness level recognition module 2 is connected to the acoustic signal generation module 3.
[0031] The acoustic signal generation module 3 receives vehicle motion parameters (such as motor speed, vehicle speed, and acceleration) from the vehicle motion sensing unit, and receives the motion sickness level results from the data processing and motion sickness level recognition module 2. When the motion sickness level is "mild", "moderate", or "severe", the acoustic signal generation module 3 is activated.
[0032] The acoustic signal generation module 3 first maps a virtual fundamental frequency signal based on the real-time acquired vehicle motion parameters, and then generates a synthesized audio signal containing harmonic components of each order through an order synthesis algorithm. When the motion sickness level is at the weakest level, the parameter reference values of each order harmonic are set. When the motion sickness level exceeds the weakest level, the corresponding parameters of specific order harmonics are boosted according to the current motion sickness level and the preset mapping relationship to enhance the synthesized audio signal as an acoustic intervention signal.
[0033] Specifically, the order synthesis algorithm is expressed by the following formula: S(t) =∑ A n * sin ( 2π * n * f 0* t ), n=1,2,3...(n (Harmonic order) In the formula, S(t) Indicates a synthesized audio signal. A n These represent the amplitude parameters of each harmonic order. f 0 represents the reference frequency. t Indicates the time it takes for the vehicle to travel.
[0034] Specifically, the system first calculates or maps a virtual base frequency based on vehicle motion parameters (such as vehicle speed and motor speed). Next, using an order synthesis algorithm, a generator containing... , , Synthesized audio signal with equal harmonic components. Amplitude of each harmonic order. It is not fixed, but dynamically determined by the current level of motion sickness. For example, in the case of "mild" motion sickness, the amplitude values of each harmonic are set as the baseline values. When the detected motion sickness level is "moderate," the module, based on a preset mapping relationship, increases the amplitude of a specific order (such as order 2 or order 4) to 1.5. This makes the sound sound "brighter" or more suggestive.
[0035] The acoustic signal generation module 3 can also select vehicle motion parameters as modulation sources, select different frequency-time transformation curves of vehicle motion parameters according to the level of motion sickness, and then use a frequency shifting and modulation algorithm to select frequency shift curves from gentle to steep according to the order of motion sickness level from low to high, and finally generate a significantly changed sound frequency signal as an acoustic intervention signal.
[0036] Specifically, when the motion sickness level is low, such as "mild" motion sickness, a gentle frequency shift curve is used to make the sound frequency changes soft; when the motion sickness level is high, such as "severe" motion sickness, a steeper frequency shift curve is used to make the sound frequency changes more significant and dynamic, so as to produce a stronger predictive effect of motion and guide attention.
[0037] In this embodiment, the acoustic signal generation module 3 selects the longitudinal acceleration signal as the modulation source and selects different frequency-time transformation curves according to the degree of motion sickness.
[0038] The vehicle-mounted sound device 4 receives and plays acoustic intervention signals from the acoustic signal generation module 3, providing intervention sounds that are precisely synchronized with the vehicle's dynamic process and have adjustable intensity, thus compensating for the gap in auditory information for passengers and enhancing the consistency between sensory and visual perception.
[0039] The synthesized digital audio signal is amplified and then played by speakers (vehicle-mounted sound device 4) placed near the headrest or seat of the target occupant, providing them with sound feedback that is precisely synchronized with the vehicle's dynamic process and has adjustable intensity.
[0040] Preferably, the electric vehicle active sound-based motion sickness suppression system based on multimodal information fusion further includes a collaborative control module 5.
[0041] The collaborative control module 5 operates based on the level of motion sickness and the vehicle's motion status, instructing other devices within the vehicle to assist in alleviating motion sickness. Specifically, this includes instructing the smart seat to generate slight vibrations synchronized with the sound rhythm, and instructing a miniature fan within the seat to activate, blowing a gentle breeze to enhance the "feeling of ventilation" and "dynamic environmental cues" through multi-sensory collaboration, thus helping to alleviate discomfort. Alternatively, it may instruct the vehicle's fragrance system to assist in alleviating motion sickness.
[0042] For example, when the system determines that the motion sickness is "moderate" and the vehicle is in a frequent start-stop condition, the collaborative control module 5 is activated.
[0043] Preferably, the electric vehicle active sound-based motion sickness suppression system based on multimodal information fusion further includes a closed-loop control module 6.
[0044] The electric vehicle active sound-based motion sickness suppression system based on multimodal information fusion forms a closed loop. After the intervention sound is played, the physiological state monitoring unit continues to operate. The data processing and motion sickness level recognition module 2 calculates the comprehensive variability index of electroencephalograms for the next time window. The closed-loop control module 6 is used to implement different control schemes based on the comprehensive variability index of the EEG in the next time window. The control schemes include: if the comprehensive variability index of the EEG decreases in the next time window, it indicates that the acoustic intervention is effective and the current vehicle motion parameters are maintained; if the comprehensive variability index of the EEG increases or remains unchanged in the next time window, the vehicle motion parameters are adjusted until the motion sickness level is detected to decrease.
[0045] Specifically, methods for adjusting vehicle motion parameters include: further increasing the amplitude of key orders in the order synthesis algorithm, or using more exaggerated curves in frequency shifting and pitch shifting, and then re-evaluating the effect until a decrease in motion sickness level is detected.
[0046] This invention also designs an active sound-based motion sickness suppression method for electric vehicles based on multimodal information fusion, comprising the following steps: S1) Collect vehicle motion parameters and occupant physiological state data, wherein the physiological state data includes at least raw electroencephalogram (EEG) signals covering the prefrontal cortex region.
[0047] The vehicle motion parameters include motor speed, motor torque, vehicle speed, acceleration, pedal opening, and other parameters.
[0048] S2) The raw EEG signals and vehicle motion parameters are fused and analyzed to output the motion sickness level judgment result.
[0049] Specifically, this involves preprocessing EEG signals, extracting features, calculating CVEI, and combining vehicle motion characteristics with a trained AI model to determine the current level of motion sickness.
[0050] S3) A virtual fundamental frequency signal is mapped based on the real-time acquired vehicle motion parameters. Then, a synthetic audio signal containing harmonic components of each order is generated through an order synthesis algorithm. When the motion sickness level is at the weakest level, the parameter reference values of each order harmonic are set. When the motion sickness level exceeds the weakest level, the corresponding parameters of specific order harmonics are boosted according to the current motion sickness level and the preset mapping relationship to enhance the synthetic audio signal as an acoustic intervention signal.
[0051] S4) Receives and plays the acoustic intervention signal, providing intervention sound that is precisely synchronized with the vehicle's dynamic process and has adjustable intensity. Specifically, the acoustic intervention signal synthesized in S3) is played to the target occupants through an onboard generator (such as an in-vehicle speaker).
[0052] Preferably, it also includes working based on the degree of motion sickness and the vehicle's motion status, and coordinating with other devices in the vehicle to help alleviate motion sickness.
[0053] S5) Continue to monitor the physiological status data of passengers to determine whether the motion sickness level has decreased. If the motion sickness level has not decreased, return to step S3) and intervene again after adjusting the synthesized audio signal to form a closed-loop optimization.
[0054] This invention relates to an active acoustic motion sickness suppression system and method for electric vehicles based on multimodal information fusion. It enables accurate judgment of motion sickness and can dynamically generate highly correlated acoustic intervention signals based on the unique vehicle motion parameters of electric vehicles to fill the gap in auditory information and achieve motion sickness suppression.
[0055] The above embodiments are preferred embodiments of the present invention, but the embodiments of the present invention are not limited to the above embodiments. Any changes, modifications, substitutions, combinations, or simplifications made without departing from the spirit and principle of the present invention shall be considered equivalent substitutions and shall be included within the protection scope of the present invention.
Claims
1. An active sound-based motion sickness suppression system for electric vehicles based on multimodal information fusion, characterized in that: It includes a signal acquisition module (1), a data processing and motion sickness level recognition module (2), an acoustic signal generation module (3), and an on-board sound generation device (4). The signal acquisition module (1) includes a vehicle motion sensing unit and a physiological state monitoring unit. The vehicle motion sensing unit is used to collect vehicle motion parameters. The physiological state monitoring unit is used to collect physiological state data of the occupants, and the physiological state data includes at least raw electroencephalogram (EEG) signals covering the prefrontal cortex region. The data processing and motion sickness level recognition module (2) is connected to the signal acquisition module (1) to perform fusion analysis on the original EEG signal and vehicle motion parameters, and output the motion sickness level judgment result; The acoustic signal generation module (3) is connected to the signal acquisition module (1) and the data processing and motion sickness level recognition module (2) respectively. First, a virtual fundamental frequency signal is mapped according to the real-time acquired vehicle motion parameters. Then, a synthetic audio signal containing harmonic components of each order is generated through the order synthesis algorithm. When the motion sickness level is the weakest level, the parameter reference value of each order harmonic is set. When the motion sickness level exceeds the weakest level, the corresponding parameters of specific order harmonics are boosted according to the current motion sickness level and the preset mapping relationship to enhance the synthetic audio signal as an acoustic intervention signal. The vehicle-mounted sound device (4) is connected to the acoustic signal generation module (3), receives acoustic intervention signals, and plays them to provide intervention sounds that are precisely synchronized with the vehicle's dynamic process and whose intensity is adjustable.
2. The active sound-based motion sickness suppression system for electric vehicles based on multimodal information fusion according to claim 1, characterized in that: In the data processing and motion sickness level recognition module (2), the fusion analysis includes preprocessing and calculating the original EEG signal to obtain the comprehensive EEG variation index; at the same time, calculating the vehicle motion parameters to obtain the vehicle motion characteristics; Finally, the EEG comprehensive variability index and vehicle motion characteristics are input into the motion sickness level recognition model. The model outputs the probability distribution of motion sickness levels, and the level corresponding to the highest probability is taken as the current motion sickness level judgment result.
3. The active sound-based motion sickness suppression system for electric vehicles based on multimodal information fusion according to claim 2, characterized in that: The comprehensive variability index of brain waves is calculated using the following formula. In the formula, CVEI The comprehensive variability index of brain waves, , These are the weighting coefficients. P θ for θ The power spectral density of the wave, P α for α The power spectral density of the wave, P β for β The power spectral density of the wave, P δ for δ The power spectral density of the wave.
4. The active sound-based motion sickness suppression system for electric vehicles based on multimodal information fusion according to claim 3, characterized in that: The motion sickness level recognition model is a pre-trained neural network model that integrates CNN and attention mechanisms.
5. The active sound-based motion sickness suppression system for electric vehicles based on multimodal information fusion according to claim 1, characterized in that: In the acoustic signal generation module (3), the order synthesis algorithm is expressed by the following formula. S(t) =∑ A n * sin ( 2π * n * f 0* t ), n=1,2,3...(n (Harmonic order) In the formula, S(t) Indicates a synthesized audio signal. A n These represent the amplitude parameters of each harmonic order. f 0 represents the reference frequency. t Indicates the time it takes for the vehicle to travel.
6. The active sound-based motion sickness suppression system for electric vehicles based on multimodal information fusion according to claim 1, characterized in that: It includes a collaborative control module (5), which operates based on the motion sickness level and the vehicle's motion status, and instructs other devices in the vehicle to assist in alleviating motion sickness.
7. The active sound-based motion sickness suppression system for electric vehicles based on multimodal information fusion according to claim 6, characterized in that: It also includes a closed-loop control module (6), which is used to implement different control schemes based on the EEG comprehensive variation index of the next time window; the control schemes include maintaining the current vehicle motion parameters if the next EEG comprehensive variation index decreases; and adjusting the vehicle motion parameters if the next EEG comprehensive variation index increases or remains unchanged, until the motion sickness level is detected to decrease.
8. A method for active sound-based motion sickness suppression in electric vehicles based on multimodal information fusion, characterized in that, Includes the following steps: S1) Collect vehicle motion parameters and occupant physiological state data, wherein the physiological state data includes at least raw electroencephalogram (EEG) signals covering the prefrontal cortex region; S2) The raw EEG signals and vehicle motion parameters are fused and analyzed to output the motion sickness level judgment result; S3) A virtual fundamental frequency signal is mapped based on the real-time acquired vehicle motion parameters, and then a synthetic audio signal containing harmonic components of each order is generated through an order synthesis algorithm; when the motion sickness level is the weakest level, the parameter reference value of each order harmonic is set; when the motion sickness level exceeds the weakest level, the corresponding parameters of specific order harmonics are boosted according to the current motion sickness level and the preset mapping relationship to enhance the synthetic audio signal as an acoustic intervention signal. S4) Receives and plays acoustic intervention signals, providing intervention sounds that are precisely synchronized with the vehicle's dynamic process and have adjustable intensity; S5) Continue to monitor the physiological status data of passengers to determine whether the motion sickness level has decreased. If the motion sickness level has not decreased, return to step S3) and intervene again after adjusting the synthesized audio signal to form a closed-loop optimization.
9. The active sound-based motion sickness suppression method for electric vehicles based on multimodal information fusion according to claim 8, characterized in that: S4 also includes working based on motion sickness level and vehicle motion status, and coordinating with other devices in the vehicle to help alleviate motion sickness.