Vehicle dynamic adjustment method for side collision accident

Abstract

The invention relates to a vehicle dynamic adjustment method for a side collision accident, and the method comprises the following steps: S1, collecting vehicle body multi-dimensional information data information, vehicle environment information data information and vehicle passenger information data information, and building a real-time updated data model through data fusion; training a neural network according to virtual collision data generated by the vehicle collision simulation software to obtain a collision risk prediction model; s2, inputting data in the model into a collision risk prediction model to obtain the injury degree of a passenger and collision prediction position point information, dividing the state between a vehicle and a potential collision object into different risk levels, and generating a risk map; and S3, the vehicle adjusting system adjusts the height, the speed and the seat posture of a vehicle suspension system and a vehicle safety belt according to the different risk levels, risk prompting is carried out on vehicle passengers so as to reduce the risk levels, and the risk map is updated in real time. According to the invention, the safety of passengers in a side collision accident can be improved.

Description

Technical Field

[0001] The invention relates to the field of vehicle safety collision, and in particular to a vehicle dynamic adjustment method for side collision accidents. Background Art

[0002] A vehicle side collision accident refers to a traffic accident in which the side of one vehicle collides with another vehicle while two or more vehicles are driving. This type of accident is more common in scenes such as urban roads, intersections, and highways, and often results in serious casualties and vehicle damage.

[0003] In a side collision accident, due to the collision angle and collision speed of the two vehicles, the center of gravity of the vehicle being hit will usually be unstable, causing the vehicle body to roll over, endangering the safety of the passengers; and because the impact force acts directly on the side of the vehicle body, the kinetic energy will be quickly transferred to the occupants in the car. The sitting posture and seat position of the occupants in the car will also affect the degree of injury to the occupants, and may even cause serious injuries, especially to the occupants' head area.

[0004] With the continuous advancement of automobile technology, active safety systems are playing an increasingly important role in preventing accidents and reducing the losses caused by collision accidents. Traditional vehicle safety protection measures mainly rely on passive protection, such as strengthening the body structure and installing airbags. Although these measures can provide certain protection when an accident occurs, they have limitations when facing side collision accidents. Summary of the invention

[0005] The purpose of the present invention is to provide a vehicle dynamic adjustment method for side collision accidents, so as to solve the problem of insufficient vehicle protection in vehicle side collision accidents in the prior art.

[0006] In order to achieve the above object, the technical solution adopted by the present invention is as follows: a vehicle dynamic adjustment method for a side collision accident, comprising the following steps:

[0007] S1: Collect multi-dimensional vehicle body information, vehicle environment information and vehicle occupant information data, and build a real-time updated data model through data fusion;

[0008] The neural network is trained based on the virtual collision data generated by the vehicle collision simulation software to obtain a collision risk prediction model;

[0009] S2: inputting the data in the data model into the collision risk prediction model to obtain information on the degree of injury to the occupants and information on the predicted location of the collision, dividing the state between the vehicle and the potential collision object into different risk levels and generating a risk map;

[0010] S3: The vehicle adjustment system adjusts the height of the vehicle suspension system, the vehicle speed, the vehicle seat posture and the vehicle seat belt according to the different risk levels, and issues risk warnings to the vehicle occupants to reduce the risk level, and updates the risk map in real time.

[0011] According to the above technical means, according to different risk levels, the vehicle adjustment system can dynamically adjust the height of the vehicle suspension system, the vehicle speed and the vehicle seat posture, and can adjust the center of gravity of the vehicle by adjusting the height of the vehicle suspension system to prevent the vehicle from rolling over in a side collision accident. It can adjust the position of the vehicle occupants by adjusting the vehicle seat posture to reduce the injuries suffered by the vehicle members in the side collision accident, and thus can reduce the impact force of the vehicle in the side collision and improve the safety of the occupants;

[0012] On the basis of traditional passive safety measures (such as airbags and body structure reinforcement), the vehicle's safety is further improved by actively adjusting the vehicle's state, thereby reducing the severity of vehicle damage caused by side collisions, thereby reducing the probability and severity of accidents, and thus improving the safety of passengers;

[0013] By collecting multi-dimensional information of the vehicle body, vehicle environment information and vehicle occupant information, fusing the information and building a comprehensive vehicle status model in real time, the system can timely and accurately understand the dynamic changes of the vehicle and its surrounding environment, providing a solid data foundation for subsequent risk assessment.

[0014] Furthermore, the height adjustment of the vehicle suspension system includes the vehicle adjustment system lowering the suspension on the impacted side of the vehicle with the ground as a reference and / or the vehicle adjustment system raising the suspension on the non-impacted side of the vehicle with the ground as a reference.

[0015] According to the above technical means, the vehicle adjustment system can accurately lower the suspension height on the impacted side and raise the suspension height on the non-impacted side, which can maintain the balance of the vehicle, help reduce the roll angle of the vehicle during a collision, and thereby stabilize the center of gravity of the vehicle, ensuring that the vehicle can maintain a stable driving state during the adjustment process, preventing the probability and degree of vehicle rollover after a side collision accident, and can adjust the suspension height according to the position of the vehicle collision in a side collision accident.

[0016] Furthermore, the adjusting of the vehicle speed includes the vehicle adjustment system adjusting the magnitude and direction of the vehicle speed.

[0017] According to the above-mentioned technical means, the vehicle adjustment system can adjust the vehicle speed and direction. The vehicle adjustment system can accurately slow down the vehicle according to the risk level, reduce the kinetic energy during collision, and thus reduce the impact force of the collision on the vehicle and occupants; at the same time, the vehicle adjustment system can adjust the vehicle's driving direction according to the collected data, thereby preventing the vehicle from colliding.

[0018] According to the above-mentioned technical means, the vehicle adjustment system can accurately lower the suspension height on the impacted side and raise the suspension height on the non-impacted side, which can maintain the balance of the vehicle, help reduce the roll angle of the vehicle during a collision, and ensure that the vehicle can maintain a stable driving state during the adjustment process; according to the risk level, the vehicle adjustment system can accurately slow down the speed of the vehicle and reduce the kinetic energy during a collision, thereby reducing the impact force of the collision on the vehicle and occupants; by adjusting the position of the seat along the length of the vehicle, the height of the seat and the angle of the seat back, the lateral displacement of the occupants in a side collision can be reduced, thereby reducing the risk of injury.

[0019] Furthermore, the adjusting of the vehicle seat posture includes the vehicle adjustment system adjusting the distance the vehicle seat moves along the length direction of the vehicle, the height of the vehicle seat and the backrest angle of the vehicle seat.

[0020] According to the above technical means, the vehicle adjustment system can reduce the lateral displacement of the occupants in side collisions and reduce the risk of injury by adjusting the position of the seat along the length of the vehicle, the height of the seat and the angle of the seat back.

[0021] Furthermore, the different risk levels described in S3 are divided into low risk level, medium risk level, high risk level and extremely dangerous risk level from low to high according to the degree of injury suffered by the occupants.

[0022] According to the above technical means, by dividing the risks from low to high into low risk level, medium risk level, high risk level and extremely dangerous risk level, the system can take different response measures according to different risk levels to ensure that the most appropriate protection strategy can be provided in different situations.

[0023] Furthermore, the S3 specifically includes:

[0024] At the low risk level, the vehicle state is not adjusted and the vehicle occupants are not given risk warnings;

[0025] At the medium risk level, the vehicle occupants are given a risk warning, and the height of the vehicle suspension system and / or the vehicle speed and / or the vehicle seat posture are adjusted until the risk level is reduced to a low risk level;

[0026] At the high risk level, the vehicle occupants are given a risk warning, and the height of the vehicle suspension system and / or the vehicle speed and / or the vehicle seat posture are adjusted until the risk level is reduced to a low risk level;

[0027] At the extremely dangerous risk level, the vehicle occupants are given a risk warning and the vehicle seat belts are actively pre-tightened; at the same time, the height of the vehicle suspension system and / or the vehicle speed and / or the vehicle seat posture are adjusted until the risk level is reduced to a low risk level.

[0028] According to the above technical means, at low risk levels, the vehicle status is not adjusted and no risk warning is given to the occupants. This avoids unnecessary interference and waste of resources, while ensuring that the system can respond quickly when necessary; at medium risk levels, the vehicle speed is adjusted and risk warnings are given to the occupants. This measure can effectively reduce the severity of the collision and remind the occupants to prepare in advance; at high risk levels, the vehicle speed, seat position and suspension system height are adjusted. These comprehensive measures can significantly reduce the impact of the collision on the occupants and improve safety; at extremely dangerous risk levels, in addition to the above adjustment measures, the active pre-tightening of the seat belt is triggered in advance, which can provide additional protection before the collision occurs and further reduce the risk of occupant injury.

[0029] Furthermore, the risk warning is that the vehicle adjustment system controls the seat or steering wheel to vibrate to different degrees according to the risk, so as to remind the driver and enable the driver to enter a ready state in advance.

[0030] According to the above-mentioned technical means, at medium risk, high risk and extreme risk levels, the system reminds the occupants through vibration so that they can understand the potential collision risk in advance. This not only improves the occupants' alertness, but also provides the occupants with additional reaction time, enabling them to take appropriate measures, such as adjusting posture or emergency braking, thereby reducing the severity of the collision.

[0031] Furthermore, the method for obtaining the collision risk prediction model in S1 specifically includes the following steps:

[0032] S11: Simulate different collision scenarios through collision simulation software to obtain collision data;

[0033] S12: classifying the unprocessed collision data, selecting a plurality of network models according to the classification type, and combining the network models to obtain an initial collision risk prediction model;

[0034] Preprocessing the collision data, including data cleaning, data normalization and standardization, and feature extraction to obtain preprocessed collision data;

[0035] S13: training the initial collision risk prediction model according to the preprocessed collision data, and optimizing the trained initial collision risk prediction model to obtain an optimal collision risk prediction model.

[0036] According to the above technical means, different collision scenarios are simulated through collision simulation software to obtain rich collision data. These data cover various possible side collision situations, including different speeds, angles, vehicle types and environmental conditions, ensuring that the model can handle a variety of complex situations, providing more comprehensive information, and helping to more accurately predict collision risks; according to the type of collision data, multiple network models are selected for splicing and combination to form an initial collision risk prediction model; key features are extracted from a large amount of raw data to reduce data dimensions and improve the training efficiency of the model. At the same time, the extracted features can better reflect the key factors of collision risk and improve the prediction accuracy of the model; this multi-model fusion method can make full use of the advantages of different models to improve the generalization ability and prediction accuracy of the model.

[0037] Furthermore, the data fusion in S1 includes the following steps:

[0038] S11': extracting key features from the vehicle body multi-dimensional information data, the vehicle environment information data and the vehicle occupant information data;

[0039] S12': Use a multimodal deep learning network to fuse the key features to generate a data model that includes the vehicle body multi-dimensional information data, the vehicle environment information data and the vehicle occupant information data and is updated in real time.

[0040] According to the above technical means, key features are extracted from the multi-dimensional information data of the vehicle body, the vehicle environment information data and the vehicle occupant information data, including the distance between the test vehicle and the collision vehicle, the speed of the test vehicle and the occupant posture of the test vehicle. These key features cover various aspects of the vehicle's driving status, surrounding environment and occupant status, providing comprehensive data support for subsequent data fusion and risk assessment; the key features are fused using a multimodal deep learning network to generate a data model that includes multi-dimensional information data of the vehicle body, vehicle environment information data and vehicle occupant information data and is updated in real time. The multimodal deep learning network can process data of different modes (such as time series data, image data and point cloud data), and extract deep features to improve the prediction accuracy of the model; the application of real-time updated data models and multimodal deep learning networks enables the system to flexibly adjust protection strategies according to different risk levels.

[0041] Furthermore, in S1:

[0042] The vehicle body multi-dimensional information data includes vehicle speed and direction, vehicle suspension height and vehicle acceleration;

[0043] The vehicle environment information data includes the speed and relative position information of surrounding objects with the vehicle as a reference;

[0044] The vehicle occupant information data includes vehicle occupant body type, vehicle occupant posture and seat position information.

[0045] According to the above technical means, the multi-dimensional information data of the vehicle body includes the vehicle's driving speed and direction, the vehicle's suspension height and the vehicle's driving acceleration. These data can fully reflect the vehicle's driving status, provide the system with dynamic information of the vehicle, and help the system accurately assess the vehicle's current status and potential risks. The vehicle's environmental information data includes the speed and relative position information of surrounding objects with the vehicle as a reference. These data can provide detailed information about the vehicle's surrounding environment, help the system identify potential collision objects and risk areas, and make early warnings and adjustments; vehicle occupant information data includes vehicle occupant body shape, occupant posture and seat position information. These data can provide the occupant's current status, help the system adjust the seat posture according to the occupant's specific situation, and ensure that the occupant is in the best protection position in the event of a collision.

[0046] Beneficial effects achieved by the present invention:

[0047] 1. According to different risk levels, the vehicle adjustment system can dynamically adjust the height of the vehicle suspension system, the vehicle speed and the vehicle seat posture. It can adjust the center of gravity of the vehicle by adjusting the height of the vehicle suspension system to prevent the vehicle from rolling over in a side collision accident. It can adjust the position of the vehicle occupants by adjusting the vehicle seat posture to reduce the injuries suffered by the vehicle members in a side collision accident, thereby reducing the impact force of the vehicle in a side collision and improving the safety of the occupants;

[0048] 2. On the basis of traditional passive safety measures (such as airbags and body structure reinforcement), the vehicle status is actively adjusted to further improve the safety of the vehicle, thereby reducing the severity of vehicle damage caused by side collisions, thereby reducing the probability and severity of accidents, and thus improving the safety of passengers;

[0049] 3. By collecting multi-dimensional information of the vehicle body, vehicle environment information and vehicle occupant information, and then fusing the information, and building a comprehensive vehicle status model in real time, the system can timely and accurately understand the dynamic changes of the vehicle and its surrounding environment, providing a solid data foundation for subsequent risk assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 It is a schematic diagram of the overall process of the present invention;

[0051] Figure 2 A schematic diagram of the training process of collision model prediction of the present invention;

[0052] Figure 3 The figure is a schematic diagram of the process of fusing the collected vehicle data according to the present invention.

[0053] The drawings are only used for illustrative purposes and should not be construed as limitations on this patent. In order to better illustrate this embodiment, some parts of the drawings may be omitted, enlarged or reduced, and do not represent the size of the actual product. For those skilled in the art, it is understandable that some well-known structures and their descriptions in the drawings may be omitted. The same or similar numbers correspond to the same or similar parts. The terms describing the positional relationship in the drawings are only used for illustrative purposes and should not be construed as limitations on this patent. DETAILED DESCRIPTION

[0054] It should be noted that, in the absence of conflict, the embodiments and technical features in the embodiments of the present application can be combined with each other, and the detailed description in the specific embodiments should be understood as an explanation of the purpose of the present application and should not be regarded as an improper limitation on the present application.

[0055] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the specific technical solution of the present application will be further described in detail below in conjunction with the drawings in the embodiments of the present application. The following embodiments are used to illustrate the present application, but are not used to limit the scope of the present application.

[0056] In the embodiments of the present application, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of the present application, unless otherwise specified, "multiple" means two or more.

[0057] In the embodiments of the present application, unless otherwise clearly specified and limited, the term "connection" should be understood in a broad sense. For example, "connection" can be a fixed connection, a detachable connection, or an integral connection; it can be a direct connection or an indirect connection through an intermediate medium.

[0058] In the embodiments of the present application, the terms "include", "comprises" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device including the element.

[0059] The technical solution of this embodiment is described in detail below in conjunction with specific drawings.

[0060] like Figure 1 As shown, in this embodiment, a vehicle dynamic adjustment method for a side collision accident includes the following steps:

[0061] S1: Collect multi-dimensional information data of the vehicle body, vehicle environment information data and vehicle occupant information data, and build a real-time updated data model through data fusion; train the neural network according to the virtual collision data generated by the vehicle collision simulation software to obtain the collision risk prediction model; S2: input the data in the data model into the collision risk prediction model to obtain the information on the degree of injury to the occupants and the predicted location point of the collision, divide the state between the vehicle and the potential collision object into different risk levels and generate a risk map; S3: the vehicle adjustment system adjusts the height of the vehicle suspension system, the vehicle speed, the vehicle seat posture and the vehicle seat belts according to the different risk levels, and provides risk warnings to the vehicle occupants to reduce the risk level, and updates the risk map in real time.

[0062] According to different risk levels, the vehicle adjustment system can dynamically adjust the height of the vehicle suspension system, vehicle speed and vehicle seat posture. It can adjust the center of gravity of the vehicle by adjusting the height of the vehicle suspension system to prevent the vehicle from rolling over in a side collision accident. It can adjust the position of the vehicle occupants by adjusting the vehicle seat posture to reduce the injuries suffered by the vehicle occupants in a side collision accident, thereby reducing the impact force of the vehicle in a side collision and improving the safety of the occupants.

[0063] By actively adjusting the vehicle status based on traditional passive safety measures (such as airbags and body structure reinforcement), the vehicle's safety is further improved, thereby reducing the severity of vehicle damage caused by side collisions, thereby reducing the probability and severity of accidents, and improving the safety of passengers.

[0064] By collecting multi-dimensional information of the vehicle body, vehicle environment information and vehicle occupant information, fusing the information and building a comprehensive vehicle status model in real time, the system can timely and accurately understand the dynamic changes of the vehicle and its surrounding environment, providing a solid data foundation for subsequent risk assessment.

[0065] Preferably, the vehicle adjustment system can also adjust the release time of the vehicle airbag, can release the airbag in advance according to the occupant information and collision information, and can reduce the damage to the occupants during the collision.

[0066] Preferably, the vehicle's multi-dimensional information, including speed, acceleration, direction angle, suspension height, and the relative position and speed of surrounding vehicles and obstacles, is collected in real time through the on-board sensor system, and comprehensive analysis is performed in combination with information such as the body shape and seat position of the occupants in the vehicle. The on-board sensor system includes radar, camera, lidar, suspension height sensor, inertial measurement unit and GPS. These sensors work together to collect and analyze vehicle and environmental information in real time; the occupant status monitoring system continuously monitors the occupants' body shape, posture and seat position through the in-vehicle camera and seat pressure sensor, providing accurate data for collision prediction and vehicle dynamic adjustment.

[0067] Preferably, the vehicle collision simulation software includes one or more of multi-rigid body dynamics analysis software (MAthematical DYnamicMODEl MADYMO), dynamic analysis finite element program (LS-DYNA) and computer three-dimensional collision impact simulation system (PAM-CRASH).

[0068] In this embodiment, the height adjustment of the vehicle suspension system includes the vehicle adjustment system lowering the suspension on the impacted side of the vehicle with the ground as a reference and\or the vehicle adjustment system raising the suspension on the non-impacted side of the vehicle with the ground as a reference. The vehicle adjustment system can accurately lower the suspension height on the impacted side and raise the suspension height on the non-impacted side, which can maintain the balance of the vehicle, help reduce the roll angle of the vehicle during a collision, and then stabilize the center of gravity of the vehicle, ensure that the vehicle can still maintain a stable driving state during the adjustment process, prevent the probability and degree of the vehicle rolling over after a side collision accident, and can adjust the suspension height according to the collision position of the vehicle in the side collision accident.

[0069] Preferably, adjusting the height of the vehicle suspension system includes lowering the suspension height on the impacted side of the vehicle, or raising the suspension height on the non-impacted side, or lowering the suspension height on the impacted side of the vehicle and raising the suspension height on the non-impacted side at the same time.

[0070] In this embodiment, adjusting the vehicle speed includes adjusting the magnitude and direction of the vehicle speed by the vehicle adjustment system. The vehicle adjustment system can accurately slow down the vehicle speed according to the risk level by adjusting the magnitude and direction of the vehicle speed, thereby reducing the kinetic energy during the collision and reducing the impact of the collision on the vehicle and the occupants; at the same time, the vehicle adjustment system can adjust the driving direction of the vehicle according to the collected data, thereby preventing the vehicle from colliding.

[0071] The vehicle adjustment system can accurately lower the suspension height on the impacted side and raise the suspension height on the non-impacted side, which can maintain the balance of the vehicle, help reduce the vehicle's roll angle during a collision, and ensure that the vehicle can maintain a stable driving state during the adjustment process; according to the risk level, the vehicle adjustment system can accurately slow down the vehicle and reduce the kinetic energy during a collision, thereby reducing the impact of the collision on the vehicle and occupants; by adjusting the position of the seat along the length of the vehicle, the height of the seat and the angle of the seat back, the lateral displacement of the occupants in a side collision can be reduced, reducing the risk of injury.

[0072] Preferably, in a side collision scenario, by adjusting the suspension height, the contact angle and strength between the side structure of the vehicle and the collision object can be changed, so as to minimize the damage to the passengers in the vehicle caused by the collision. For suspension systems that can adjust the height, common ones are air suspension or electromagnetic suspension. Taking air suspension as an example, when a signal from the electronic control unit (ECU) is received, the air compressor or the exhaust valve will work accordingly. If the suspension height needs to be increased, the air compressor will fill more air into the air spring to extend the spring, thereby increasing the height of the vehicle body; if the height needs to be lowered (in some special collision scenarios, lowering the height may help stabilize the vehicle body posture), the exhaust valve will open and release part of the air in the air spring. Electromagnetic suspension adjusts the height and stiffness of the suspension by changing the electromagnetic force, and its response speed is faster.

[0073] Preferably, automatic emergency steering is an advanced active safety technology for automobiles. It mainly controls the steering of the vehicle automatically to avoid collision or reduce the severity of collision through the coordinated work of the vehicle's own sensors, ECU and steering system when the vehicle faces potential collision risk. It automatically adjusts the direction of the vehicle according to the collision prediction results to keep it as far away from the high risk area of ​​damage as possible. For example, when the risk map predicts that the vehicle is at high risk and extremely dangerous risk, the system will quickly adjust the angle of the steering wheel and change the direction of the vehicle to make the collision point deviate from the high risk area where the occupants are located, such as moving the collision force away from the passenger compartment, or guiding the vehicle to a relatively open and safe direction.

[0074] Preferably, the vehicle's automatically adjustable seat can adjust multiple motors installed inside and outside the vehicle seat, each motor can adjust the vehicle seat's height, backrest angle and position along the vehicle's length, so that the vehicle adjustment system can adjust each motor and further adjust the vehicle seat's height, backrest angle and position along the vehicle's length.

[0075] In this embodiment, adjusting the vehicle seat posture includes the vehicle adjustment system adjusting the distance the vehicle seat moves along the length direction of the vehicle, the height of the vehicle seat, and the backrest angle of the vehicle seat. The vehicle adjustment system can reduce the lateral displacement of the occupant in a side collision and reduce the risk of injury by adjusting the position of the seat along the length direction of the vehicle, the height of the seat, and the backrest angle of the seat.

[0076] In this embodiment, the different risk levels in S3 are divided into low risk level, medium risk level, high risk level and extremely dangerous risk level from low to high according to the degree of injury suffered by the occupants. By dividing the risks from low to high into low risk level, medium risk level, high risk level and extremely dangerous risk level, the system can take different response measures according to different risk levels, ensuring that the most appropriate protection strategy can be provided in different situations.

[0077] In this embodiment, S3 specifically includes:

[0078] At the low risk level, the vehicle state is not adjusted and the vehicle occupants are not given risk warnings;

[0079] At the medium risk level, the vehicle occupants are given a risk warning, and the height of the vehicle suspension system and / or the vehicle speed and / or the vehicle seat posture are adjusted until the risk level is reduced to a low risk level;

[0080] At the high risk level, the vehicle occupants are given a risk warning, and the height of the vehicle suspension system and / or the vehicle speed and / or the vehicle seat posture are adjusted until the risk level is reduced to a low risk level;

[0081] At the extremely dangerous risk level, the vehicle occupants are given a risk warning and the vehicle seat belts are actively pre-tightened; at the same time, the height of the vehicle suspension system and / or the vehicle speed and / or the vehicle seat posture are adjusted until the risk level is reduced to a low risk level.

[0082] At low risk levels, the vehicle status is not adjusted, and no risk warning is given to the occupants. This avoids unnecessary interference and waste of resources, while ensuring that the system can respond quickly when necessary; at medium risk levels, the vehicle speed is adjusted and risk warnings are given to the occupants. This measure can effectively reduce the severity of the collision and remind the occupants to prepare in advance; at high risk levels, the vehicle speed, seat position and suspension system height are adjusted. These comprehensive measures can significantly reduce the impact of the collision on the occupants and improve safety; at extremely dangerous risk levels, in addition to the above-mentioned adjustment measures, the active pre-tightening of the seat belt is triggered in advance, which can provide additional protection before the collision occurs and further reduce the risk of occupant injury.

[0083] Preferably, in a low-risk state, there is a sufficient safe distance between the vehicle and potential collision objects (such as other vehicles, pedestrians, obstacles, etc.), and the vehicle's driving state is stable. For example, under normal traffic flow, the vehicle maintains a following distance from the vehicle in front for several seconds, and the vehicle speed is within a reasonable range. At this time, the sensor (such as radar or ultrasonic sensor) shows that the distance between the vehicle and the surrounding objects is greater than the safe braking distance. For example, for a vehicle traveling at normal speed, if the following distance is greater than 30 meters and the vehicle speed is less than 60km / h, the acceleration sensor shows that the vehicle acceleration is stable, without sudden acceleration or deceleration, and the steering angle sensor shows that the vehicle's driving direction is stable, without sudden steering movements.

[0084] Preferably, in a medium-risk state, the distance between the vehicle and the potential collision object gradually approaches the safe braking distance, or the vehicle has some unstable factors that may cause a collision. For example, the vehicle in front suddenly decelerates, and the distance between the vehicle and the vehicle in front is rapidly shortened, but it has not yet reached the level of emergency braking; or the vehicle is close to the vehicle in the adjacent lane during the lane change process. At this time, the sensor shows that the distance between the vehicle and the object in front is between 50%-90% of the safe braking distance. For example, when the vehicle speed is 80km / h, the following distance is shortened to about 30-50 meters. The acceleration sensor may detect that the vehicle has a certain degree of rapid deceleration or the vehicle is turning, and the steering angle sensor shows that the steering wheel has a certain angle of rotation, and this rotation may cause the vehicle to approach other objects.

[0085] Preferably, in a high-risk state, the distance between the vehicle and the potential collision object is close to or less than the safe braking distance, and a collision is almost inevitable unless emergency measures are taken. For example, an obstacle suddenly appears in front of the vehicle, or the distance to the vehicle in front is sharply shortened to the point of almost rear-ending. The distance sensor shows that the distance between the vehicle and the object in front is less than 50% of the safe braking distance. For example, when the vehicle speed is 100km / h, the following distance is less than 30 meters. The acceleration sensor detects that the vehicle does not have enough deceleration to avoid a collision, and the steering angle sensor shows that it is difficult to avoid the collision object even if the vehicle turns.

[0086] Preferably, in the extreme risk state, the vehicle is already in a collision process or the collision occurs almost instantly. This may be due to various reasons, such as the driver losing consciousness, system failure or other extreme situations that cause the previous safety measures to fail to effectively avoid the collision. The collision sensors (accelerometers installed on the front, side and rear of the vehicle) detect that the vehicle has come into contact with other objects, and the acceleration has changed dramatically, and the degree of change is far beyond the normal driving state.

[0087] In this embodiment, the risk warning is to adjust the system to control the seat or steering wheel to vibrate from high to low according to the risk level from high to low, so as to remind the driver and make the driver ready in advance. At medium risk, high risk and extremely dangerous risk levels, the system reminds the occupants through vibration so that they can understand the potential collision risk in advance, which not only improves the vigilance of the occupants, but also provides the occupants with additional reaction time, so that they can take appropriate measures, such as adjusting their posture or emergency braking, thereby reducing the severity of the collision.

[0088] Preferably, for low risks, when the risk map on the vehicle's display screen or head-up display (HUD) shows blue, the steering wheel vibrates at a low frequency to alert occupants of the risk. At the same time, the dynamic adjustment system adjusts the vehicle's acceleration or deceleration, dynamically adjusts the distance between the vehicle and surrounding barriers and vehicles, to reduce the risk level of the vehicle at that time. When there is sufficient space in front of or behind the vehicle, the vehicle is adjusted to move forward or backward until the risk is reduced to no risk.

[0089] Preferably, for medium risk, when the risk map on the vehicle's display screen or head-up display (HUD) shows yellow, the steering wheel vibrates at a high frequency to prompt the driver to increase vigilance. When there is enough space in front and behind the vehicle, the dynamic adjustment system adjusts the vehicle's acceleration or deceleration, and dynamically adjusts the distance between the vehicle and surrounding barriers and vehicles to reduce the risk level of the vehicle at that time. When there is enough space in front or behind the vehicle, the vehicle is adjusted to move forward or backward until the risk is reduced to no risk.

[0090] Preferably, for high risks, when the risk map on the vehicle's display screen or head-up display (HUD) shows orange, when there are no obstacles in front of and diagonally in front of the vehicle and there is sufficient space, automatic emergency steering is triggered, and the driving vehicle is dynamically adjusted to a safe zone, so that the collision point deviates from the high-risk area where the occupants are located, thereby minimizing the degree of side collision. While steering, the system dynamically adjusts the suspension of the impacted side of the vehicle and the seats for the occupants to lower the driving stability. If the angle of the co-pilot seat back is large, the normal sitting position can be quickly restored until the risk map shows that there is no risk and the suspension and seat are automatically restored.

[0091] Preferably, for extremely dangerous risks, when the risk map on the vehicle's display screen or head-up display (HUD) shows red, when there are no obstacles in front of and diagonally in front of the vehicle and there is sufficient space, automatic emergency steering is triggered to move the collision point away from the high-risk area where the occupants are located, thereby minimizing the degree of side collision. While steering, the system dynamically adjusts the suspension on the impacted side of the vehicle and the seats on which the occupants sit to improve driving stability, and adjusts the seats away from the collision point until the risk is reduced to no risk, and the suspension and seats automatically recover. If necessary, the active pre-tensioning of the seat belts and the side air curtains can be triggered in advance.

[0092] In this embodiment, the risk warning is to adjust the system to control the seat or steering wheel to vibrate to different degrees according to the risk, so as to remind the driver and make the driver ready in advance. At medium risk, high risk and extreme risk levels, the system reminds the occupants through vibration so that they can understand the potential collision risk in advance, which not only improves the vigilance of the occupants, but also provides the occupants with additional reaction time, so that they can take appropriate measures, such as adjusting their posture or emergency braking, thereby reducing the severity of the collision.

[0093] like Figure 2 As shown, in this embodiment, the method for obtaining the collision risk prediction model in S1 specifically includes the following steps:

[0094] S11: Simulate different collision scenarios through collision simulation software to obtain collision data;

[0095] S12: classifying the collision data, selecting a plurality of network models according to the classification type, and combining the network models to obtain an initial collision risk prediction model; preprocessing the collision data, including data cleaning, data normalization and standardization, and feature extraction to obtain preprocessed collision data;

[0096] S13: training an initial collision risk prediction model according to the preprocessed collision data, and optimizing the trained initial collision risk prediction model to obtain an optimal collision risk prediction model.

[0097] Different collision scenarios are simulated by collision simulation software to obtain rich collision data. These data cover various possible side collision situations, including different speeds, angles, vehicle types and environmental conditions, ensuring that the model can handle a variety of complex situations, providing more comprehensive information, and helping to more accurately predict collision risks; according to the type of collision data, multiple network models are selected for splicing and combination to form an initial collision risk prediction model; key features are extracted from a large amount of raw data to reduce data dimensions and improve the training efficiency of the model. At the same time, the extracted features can better reflect the key factors of collision risk and improve the prediction accuracy of the model; this multi-model fusion method can make full use of the advantages of different models to improve the generalization ability and prediction accuracy of the model.

[0098] Preferably, the types of collision data include time series data, image data and point cloud data.

[0099] Preferably, for time series data (such as vehicle speed, acceleration), a recurrent neural network (RNN), a long short-term memory network (LSTM) or a gated recurrent unit (GRU) is selected; for image data (such as camera images), a convolutional neural network (CNN) is selected; for point cloud data (such as LiDAR), a point cloud processing network (PointNet), a voxel network (VoxelNet) or a graph neural network (GNN) is selected; for multimodal data fusion, a multimodal deep learning network, such as a joint CNN, RNN or a pure thinking model (Transformer) is selected; for damage prediction, a regression neural network or a multi-task learning network is selected.

[0100] In this embodiment, the types of collision data in S22 include time series data, image data and point cloud data. The acquired collision data includes time series data, image data and point cloud data. These multi-modal data provide more comprehensive information and help to more accurately predict collision risks.

[0101] like Figure 3 As shown, in this embodiment, the data fusion in S1 includes the following steps:

[0102] S11': extracting key features from vehicle body multi-dimensional information data, vehicle environment information data and vehicle occupant information data;

[0103] S12': Use a multimodal deep learning network to fuse key features and generate a data model that includes multi-dimensional information data of the vehicle body, vehicle environment information data, and vehicle occupant information data and is updated in real time.

[0104] Extract key features from vehicle body multi-dimensional information data, vehicle environment information data and vehicle occupant information data, including the distance between the test vehicle and the collision vehicle, the speed of the test vehicle and the occupant posture of the test vehicle. These key features cover various aspects of vehicle driving status, surrounding environment and occupant status, providing comprehensive data support for subsequent data fusion and risk assessment; use a multimodal deep learning network to fuse the key features and generate a real-time updated data model including vehicle body multi-dimensional information data, vehicle environment information data and vehicle occupant information data. The multimodal deep learning network can process data of different modes (such as time series data, image data and point cloud data), and extract deep features to improve the prediction accuracy of the model; the real-time updated data model and the application of the multimodal deep learning network enable the system to flexibly adjust the protection strategy according to different risk levels.

[0105] In this embodiment, in S1: the vehicle body multi-dimensional information data includes the vehicle's driving speed and direction, the vehicle's suspension height and the vehicle's driving acceleration; the vehicle's environmental information data includes the speed and relative position information of surrounding objects with the vehicle as a reference; the vehicle's occupant information data includes the vehicle's occupant's body shape, vehicle's occupant's posture and seat position information.

[0106] The multi-dimensional information data of the vehicle body includes the vehicle's speed and direction, the height of the vehicle's suspension, and the acceleration of the vehicle. These data can fully reflect the vehicle's driving status, provide the system with dynamic information about the vehicle, and help the system accurately assess the vehicle's current status and potential risks. The vehicle's environmental information data includes the speed and relative position information of surrounding objects with the vehicle as a reference. These data can provide detailed information about the vehicle's surrounding environment, help the system identify potential collision objects and risk areas, and make early warnings and adjustments; the vehicle's occupant information data includes the vehicle's occupant's body shape, occupant posture, and seat position information. These data can provide the occupant's current status, help the system adjust the seat posture according to the occupant's specific situation, and ensure that the occupant is in the best protection position in the event of a collision.

[0107] In summary, if Figure 1 to Figure 3 As shown, in this embodiment, a vehicle dynamic adjustment method for a side collision accident includes the following steps:

[0108] S1: Collect multi-dimensional vehicle body information, vehicle environment information and vehicle occupant information data, and build a real-time updated data model through data fusion;

[0109] Using collision simulation software to simulate different collision scenarios to obtain collision data; preprocessing the collision data, including data cleaning, data normalization and standardization, and feature extraction to obtain preprocessed collision data; classifying the collision data, and selecting multiple network models according to the type of collision data, and combining the network models to obtain an initial collision risk prediction model; training the initial collision risk prediction model based on the preprocessed collision data, and optimizing the trained initial collision risk prediction model to obtain the optimal collision risk prediction model;

[0110] S2: Input the data in the data model into the collision risk prediction model to obtain the occupant injury degree information and the collision prediction location information, divide the status between the vehicle and the potential collision object into different risk levels and generate a risk map;

[0111] S3: The vehicle adjustment system adjusts the height of the vehicle suspension system, vehicle speed and vehicle seat posture according to different risk levels, and provides risk warnings to vehicle occupants to reduce the risk level, and updates the risk map in real time.

[0112] The serial numbers of the embodiments of the present application are only for description and do not represent the advantages and disadvantages of the embodiments. The above are only preferred embodiments of the present application, and do not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made by using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A vehicle dynamic adjustment method for a side collision accident, characterized in that: The following steps are involved: S1: Collect multi-dimensional vehicle body information, vehicle environment information and vehicle occupant information data, and build a real-time updated data model through data fusion; The neural network is trained based on the virtual collision data generated by the vehicle collision simulation software to obtain a collision risk prediction model; S2: inputting the data in the data model into the collision risk prediction model to obtain information on the degree of injury to the occupants and information on the predicted location of the collision, dividing the state between the vehicle and the potential collision object into different risk levels and generating a risk map; S3: The vehicle adjustment system adjusts the height of the vehicle suspension system, the vehicle speed, the vehicle seat posture and the vehicle seat belt according to the different risk levels, and provides risk warnings to the vehicle occupants to reduce the risk level, and updates the risk map in real time.

2. The vehicle dynamic adjustment method for a side collision accident according to claim 1, characterized in that: The height adjustment of the vehicle suspension system includes the vehicle adjustment system lowering the suspension on the impacted side of the vehicle with the ground as a reference and / or the vehicle adjustment system raising the suspension on the non-impacted side of the vehicle with the ground as a reference.

3. The vehicle dynamic adjustment method for a side collision accident according to claim 1, characterized in that: The adjusting of the vehicle speed includes the vehicle adjusting system adjusting the magnitude and direction of the vehicle speed.

4. The vehicle dynamic adjustment method for a side collision accident according to claim 1, characterized in that: The adjusting the posture of the vehicle seat includes the vehicle adjustment system adjusting the distance the vehicle seat moves along the length direction of the vehicle, the height of the vehicle seat, and the backrest angle of the vehicle seat.

5. The vehicle dynamic adjustment method for side collision accidents according to claim 1, characterized in that: The different risk levels described in S3 are divided into low risk level, medium risk level, high risk level and extremely dangerous risk level from low to high according to the degree of injury suffered by the occupants.

6. The vehicle dynamic adjustment method for side collision accidents according to claim 5, characterized in that: The S3 specifically includes: At the low risk level, the vehicle state is not adjusted and the vehicle occupants are not given risk warnings; At the medium risk level, the vehicle occupants are given a risk warning, and the height of the vehicle suspension system and / or the vehicle speed and / or the vehicle seat posture are adjusted until the risk level is reduced to a low risk level; At the high risk level, the vehicle occupants are given a risk warning, and the height of the vehicle suspension system and / or the vehicle speed and / or the vehicle seat posture are adjusted until the risk level is reduced to a low risk level; At the extremely dangerous risk level, the vehicle occupants are given a risk warning and the vehicle seat belts are actively pre-tightened; at the same time, the height of the vehicle suspension system and / or the vehicle speed and / or the vehicle seat posture are adjusted until the risk level is reduced to a low risk level.

7. The vehicle dynamic adjustment method for side collision accidents according to claim 6, characterized in that: The risk warning is that the vehicle adjustment system controls the seat or steering wheel to vibrate to different degrees according to the risk, so as to remind the driver and enable the driver to enter a preparation state in advance.

8. The vehicle dynamic adjustment method for side collision accidents according to claim 1, characterized in that: The method for obtaining the collision risk prediction model in S1 specifically comprises the following steps: S11: Simulate different collision scenarios through collision simulation software to obtain collision data; S12: classifying the collision data, selecting a plurality of network models according to the classification type, and combining the network models to obtain an initial collision risk prediction model; Preprocessing the collision data, including data cleaning, data normalization and standardization, and feature extraction to obtain preprocessed collision data; S13: training the initial collision risk prediction model according to the preprocessed collision data, and optimizing the trained initial collision risk prediction model to obtain an optimal collision risk prediction model.

9. The vehicle dynamic adjustment method for a side collision accident according to claim 1, characterized in that: The data fusion in S1 includes the following steps: S11': extracting key features from the vehicle body multi-dimensional information data, the vehicle environment information data and the vehicle occupant information data; S12': Use a multimodal deep learning network to fuse the key features to generate a data model that includes the vehicle body multi-dimensional information data, the vehicle environment information data and the vehicle occupant information data and is updated in real time.

10. The vehicle dynamic adjustment method for side collision accidents according to claim 1, characterized in that: In S1: The vehicle body multi-dimensional information data includes vehicle speed and direction, vehicle suspension height and vehicle acceleration; The vehicle environment information data includes the speed and relative position information of surrounding objects with the vehicle as a reference; The vehicle occupant information data includes vehicle occupant body type, vehicle occupant posture and seat position information.

Images