Safety signal control system and method after vehicle collision

Abstract

The invention discloses a safety signal control system and method after vehicle collision, and relates to the technical field of vehicle control. The model training module is used for carrying out threshold value model training according to the road condition information and the vehicle state, a corresponding threshold value is obtained through calculation, the threshold value is issued to the safety air bag controller module, and the collision evaluation module is used for analyzing the collision situation according to the collision energy and the vehicle state and carrying out power-on recovery operation; the safety airbag controller module is used for receiving a collision signal and carrying out collision energy calculation, and high-voltage power-off operation is carried out at the same time in a hard wire control mode, a CAN signal control mode and a PWM signal control mode according to the comparison result of the collision energy and a threshold value issued by the central control module. According to the invention, a high-voltage power-off loop is optimized, rapid response to a collision signal is realized, and the adaptability and safety of the air bag restraint system controller in different collision scenes are improved by dynamically adjusting the collision threshold and implementing comprehensive power-on detection control.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle control, and in particular to a vehicle post-collision safety signal control system and method. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] With the rapid growth of the electric and hybrid vehicle markets, vehicle safety technology is becoming increasingly important. As a core component of a vehicle's passive safety system, the airbag controller bears the crucial responsibility of protecting occupants in collisions. Upon receiving a collision signal, the airbag controller, acting as the control unit for the vehicle's passive safety system, generates a current to disconnect the high-voltage module, preventing secondary injuries.

[0004] However, the existing airbag controller high-voltage power-off system has some problems that need to be solved, which limits its performance in complex collision scenarios.

[0005] First, with the recent growth of the electric vehicle market, high-voltage systems on electric vehicles need to be disconnected promptly in the event of an accident, and the doors unlocked promptly. However, existing high-voltage disconnect switch systems require a long time to transmit signals to the vehicle control module and then disconnect the high voltage according to the strategy when the vehicle is involved in a collision. Furthermore, the high-voltage disconnect circuit is single during a collision, and if the ignition circuit fails, it may not be possible to disconnect the high voltage.

[0006] Secondly, traditional high-voltage power-off systems primarily rely on fixed collision thresholds to determine whether to disconnect the high-voltage circuit. While this fixed threshold approach can meet basic safety requirements to a certain extent, it has significant limitations in practical applications. First, the collision risks and safety requirements faced by vehicles in different driving states (such as high speed, low speed, and parked) are different. For example, at high speeds, a minor collision may not require immediate power disconnection, as this may cause the vehicle to lose power and increase the risk of an accident. However, at low speeds or when parked, even a minor collision may require a timely power disconnection to prevent secondary injuries such as electric shock and fire.

[0007] Furthermore, existing power-off systems often use a one-size-fits-all approach after a collision, shutting off all high-voltage power at once. While this approach ensures safety, in the event of a minor collision, it can cause the vehicle to lose essential auxiliary functions, such as lighting and communications, creating inconvenience for occupants during emergency response.

[0008] To sum up, how to adjust the collision threshold in real time according to actual road conditions, quickly cut off the high-voltage power after a collision, and judge the collision situation and power-on recovery detection of some equipment after the power-off process has become a technical problem that needs to be solved urgently in the existing technology. Summary of the Invention

[0009] In response to the shortcomings of the existing technology, the purpose of the present invention is to provide a vehicle post-collision safety signal control system and method, which optimizes the high-voltage power-off circuit to achieve a rapid response to the collision signal. By dynamically adjusting the collision threshold and implementing comprehensive power-on detection control, the adaptability and safety of the airbag control unit (ACU) in different collision scenarios are improved.

[0010] In order to achieve the above object, the present invention is implemented through the following technical solutions: A first aspect of the present invention provides a vehicle post-collision safety signal control system, comprising: Data acquisition module, used to collect road condition information, vehicle status and collision signals; The central control module includes a model training module and a collision assessment module. The model training module is used to train the threshold model based on road condition information and vehicle status, calculate the corresponding threshold using the trained threshold model, and send the threshold to the airbag controller module. The collision assessment module is used to analyze the collision situation based on the collision energy and vehicle status, and perform power-on recovery operations based on the collision situation; The airbag controller module is used to receive collision signals and calculate collision energy, and perform high-voltage power-off operations based on the comparison results between the collision energy and the threshold value issued by the central control module. The high-voltage power-off operation is performed simultaneously through hard-line control, CAN signal control and PWM signal control.

[0011] Furthermore, in the model training module, the specific steps for threshold model training based on road condition information and vehicle status are as follows: Use random forest model to build threshold model; After annotating known road condition information and vehicle status, the dataset is divided into a training set and a test set. The threshold model is trained using the training set and tested using the test set to obtain a trained threshold model; The trained threshold model is used to calculate the threshold based on real-time road conditions and vehicle status.

[0012] Furthermore, a threshold constant mechanism is set, that is, the threshold calculation results are classified into intervals and the threshold is kept constant within the interval.

[0013] Furthermore, in the collision assessment module, the specific steps for analyzing the collision situation based on the collision energy and vehicle status are as follows: Obtaining the collision energy and post-collision vehicle status calculated by the airbag controller module; Check whether the vehicle status meets the power-on recovery conditions; Determine the collision level based on the collision energy and vehicle status inspection results; Implement corresponding power-on recovery operations according to the collision level.

[0014] Furthermore, the collision levels are divided into minor collisions, moderate collisions and severe collisions. A minor collision means that the collision energy is lower than the set value and the vehicle status inspection result is good. A moderate collision means that the collision energy is lower than the set value but the vehicle equipment is partially damaged, but it does not affect the auxiliary equipment. A severe collision means that the collision energy is higher than the set value or the degree of damage to the vehicle equipment affects the power supply of the high-voltage equipment.

[0015] Furthermore, the high voltage power-off operation is performed simultaneously by hard-wire control, CAN signal control, and PWM signal control, including: Send out current to detonate the high-voltage power-off switch to meet the high-voltage disconnection requirement; Send a collision signal to the BDM through PWM waveform and open the four doors and hazard lights; Send collision signal to BDM via CAN signal and open four doors and hazard lights; Send a collision signal to the BMS through the PWM waveform and disconnect the high voltage; Send a collision signal to the BMS via the CAN signal and disconnect the high voltage.

[0016] A second aspect of the present invention provides a control method for a vehicle post-collision safety signal control system as described in the first aspect, comprising the following steps: The central control module selects the corresponding energy threshold according to the current road conditions and sends the energy threshold to the airbag controller module; After a vehicle collision, a collision signal is sent to the airbag controller module; After receiving the collision signal, the airbag controller module calculates the collision energy and compares the calculated result with the energy threshold. If the calculated result is greater than or equal to the energy threshold, the high-voltage power supply is directly cut off. After detecting that the voltage is stable, power-on recovery operation is performed according to the collision situation.

[0017] A third aspect of the present invention provides a computer-readable storage medium storing a computer program, wherein the computer program is suitable for being loaded by a processor and executing the steps of the control method as described in the second aspect of the present invention.

[0018] A fourth aspect of the present invention provides a computer device, comprising: a processor adapted to execute a computer program; A computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the control method according to the second aspect of the present invention is implemented.

[0019] A fifth aspect of the present invention provides a computer program product or computer program, comprising computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the steps of the control method described in the second aspect of the present invention.

[0020] One or more of the above technical solutions have the following beneficial effects: This invention provides a post-collision safety signal control system and method. By combining dynamic collision threshold adjustment with a phased power-on recovery control method and rapid high-voltage power-off technology, this system achieves a rational post-collision power-off and power-on process, significantly improving the adaptability and safety of the airbag controller in various collision scenarios. Through the collaborative work between the central control module and the airbag controller, the high-voltage power-off process adapts to changing scenarios while ensuring immediate power-off. This invention further enhances the overall safety of the vehicle and provides a more reliable guarantee for the safe operation of electric and hybrid vehicles.

[0021] This invention simultaneously disconnects high-voltage power through hardwired, CAN, and PWM signal control, ensuring rapid interruption of the high-voltage power supply at the moment of a collision. This multi-signal control approach not only improves power-off reliability but also reduces safety risks associated with single-signal failures. This ensures timely interruption of the high-voltage power supply in a variety of complex situations, preventing secondary hazards such as electric shock and fire.

[0022] The present invention uses a model training module in the central control module and a random forest model to dynamically adjust the collision threshold according to road condition information and vehicle status. It can optimize the collision judgment standard in real time according to the actual driving status of the vehicle (such as speed, road conditions, etc.), thereby improving the flexibility and adaptability of the system and the accuracy of collision detection. It also ensures the stability of the threshold within a certain range by setting a dynamic threshold adjustment mechanism, preventing signal delays caused by excessively rapid threshold changes, which may affect the high-voltage power-off response.

[0023] The present invention analyzes the collision situation through a collision assessment module, uses collision energy to quantify the severity of the collision, and combines the vehicle status to prevent misjudgment caused by collision energy quantification, thereby achieving a more accurate power-on recovery process and preventing secondary accidents.

[0024] Advantages of additional aspects of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0026] Figure 1 This is a schematic diagram of the high-voltage power-off principle of the airbag controller module in Example 1 of the present invention. DETAILED DESCRIPTION

[0027] It should be noted that the following detailed descriptions are exemplary and intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which the present invention belongs.

[0028] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, they indicate the presence of features, steps, operations, devices, components and / or their combinations; The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0029] Example 1: A first embodiment of the present invention provides a vehicle post-collision safety signal control system, comprising a data acquisition module, a central control module, and an airbag controller module.

[0030] The data acquisition module is used to collect road condition information, vehicle status and collision signals.

[0031] In one specific embodiment, the data acquisition module includes several sensors installed on the vehicle, capable of acquiring vehicle status information such as lateral acceleration, longitudinal acceleration, and speed, as well as collision direction and pressure values during a collision. The vehicle's own detection equipment also monitors the operating status of the vehicle's equipment. Road condition information, such as urban roads or highways, is acquired through cameras and GPS positioning systems.

[0032] The central control module includes a model training module and a collision assessment module. The model training module trains a threshold model based on road conditions and vehicle status, calculates the corresponding threshold using the trained threshold model, and sends the threshold to the airbag controller module. The collision assessment module analyzes the collision situation based on the collision energy and vehicle status and performs power-on recovery operations based on the collision situation.

[0033] In the model training module, the specific steps for threshold model training based on road condition information and vehicle status are as follows: Step 1: Use the random forest model to build a threshold model.

[0034] This embodiment uses a random forest model with good generalization ability and the ability to process multiple features to construct a threshold model. The random forest model can better handle the relationship between multimodal features, such as the impact of the vehicle brand on the anti-bumping ability on different roads, or the impact of differences in the impact resistance of vehicle materials.

[0035] A random forest model consists of multiple decision trees, each of which acts as a weak learner. The number of decision trees determines the model's complexity and computational cost. When splitting each decision tree node, a subset of features is randomly selected, rather than using all features, to increase model diversity. Model hyperparameters such as the number of decision trees, the number of features to be selected, the maximum depth, the minimum number of samples required for each node split, and the minimum number of samples required for each leaf node are important.

[0036] Step 2: Label the known road condition information and vehicle status to form a data set, and divide the data set into a training set and a test set.

[0037] In this embodiment, the known road condition information and vehicle status can be historical vehicle data, existing public datasets, or a combination of the two. The dataset is cleaned to remove noise and outliers. The dataset is then normalized to convert all features to the same scale. Finally, the dataset is partitioned into training and test sets in a 7:3 ratio.

[0038] Step 3: Use the training set to train the threshold model and use the test set to test it to obtain the trained threshold model.

[0039] In this embodiment, a self-attention module is introduced into the random forest model. Specifically, the weights between features are calculated using a learnable weight matrix. The features are weighted and summed according to the calculated weights to generate a new feature representation. The weighted summed features are used as the input of the random forest model. The weight matrix of the self-attention module is trained using a backpropagation algorithm, so that the model can automatically learn the weights between features. During the training process, the output features of the self-attention module are used as the input of the random forest model and trained together.

[0040] More specifically, this embodiment uses collision energy as the primary input feature and other influencing factors, such as road condition information, as auxiliary input features. The self-attention module calculates the query, key, and value matrices for the primary and auxiliary input features. The attention scores and weights for the primary and auxiliary input features are then calculated based on the query, key, and value matrices. The weighted features for the primary and auxiliary input features are further calculated: The weighted features of the main input and auxiliary input are fused to obtain the final feature representation.

[0041] The self-attention module automatically learns the weights between features, enhancing the model's focus on important features and improving its generalization capabilities. The threshold model, based on collision energy calculations, further considers other influencing factors to design more appropriate threshold values, enabling adaptive and dynamic threshold changes. The model's hyperparameters are then optimized through methods such as cross-validation. The trained model is evaluated using a test set, with performance measured using metrics such as accuracy, recall, and F1 score. Based on the evaluation results, the model's structure and parameters are adjusted to further optimize performance.

[0042] Among them, collision energy is one of the key indicators for evaluating the severity of a collision. The collision energy E can be calculated using the following formula: .

[0043] Where: m is the vehicle mass. v is the velocity at the time of impact. a is the impact acceleration, calculated from the lateral and longitudinal accelerations. g is the acceleration due to gravity.

[0044] Step 4: Use the trained threshold model to calculate the threshold based on real-time traffic information and vehicle status.

[0045] In this embodiment, to prevent the constant threshold fluctuations caused by changing road conditions and vehicle status information from impacting vehicle power-off response and increasing computational burden, conventional methods extend the threshold change time by setting a data collection interval. However, setting an excessively long interval can affect the immediacy of the threshold, rendering it unsuitable for today's real-time environment. To overcome this difficulty, this embodiment implements a threshold constant mechanism, which categorizes the threshold calculation results into intervals and maintains the threshold constant within those intervals. Specifically, threshold intervals are set, and the threshold value first reaching the threshold interval is used as the threshold value sent to the airbag controller module. This means that as long as the threshold fluctuation does not exceed the current threshold interval, the threshold value first reaching the current threshold interval is used as the threshold value sent to the airbag controller module. Until the threshold fluctuation exceeds the current threshold interval, the threshold value sent to the airbag controller module is updated with the threshold value first reaching the new threshold interval. This ensures the real-time dynamics of the threshold value while reducing the frequency of threshold updates to the airbag controller module, further facilitating faster response to collision signals. In addition, since the driver is likely to perform quick operations before a collision, such as sudden braking, in order to prevent the operations in emergency situations from affecting the threshold fluctuations, a data cleaning mechanism for rapid fluctuations in a very short period of time can be set up to eliminate the data fluctuations under emergency operations and not use them as input data for the threshold model to avoid this phenomenon.

[0046] In the collision assessment module, the collision situation is analyzed based on the collision energy and vehicle status.

[0047] First, the collision energy and the vehicle status after the collision calculated by the airbag controller module are obtained.

[0048] In this embodiment, the vehicle status check after the collision includes the damage to various equipment of the vehicle. The collision energy can quantify the real-time situation of the collision, but it is easy to deviate from the actual situation, and the vehicle status cannot directly reflect the collision situation in some cases. Therefore, this embodiment uses the combination of collision energy and vehicle status to evaluate the collision level, which can be more reasonable and accurate. In addition, this embodiment directly uses the calculated collision energy instead of recalculating the vehicle status and collision energy input into machine learning in order to save time. The real-time response after the collision is very important, so this embodiment implements the operation of first cutting off the power and then evaluating, and the recovery after the power outage also needs to be real-time. Therefore, in order to save power-on time, the state and energy are not judged by learning fusion in some methods to ensure that fast power-on can be achieved in the event of a minor collision.

[0049] It should be noted that the power-on recovery process in this embodiment is intended only to enable rapid power-on in situations where the collision energy meets the threshold but no substantial damage has occurred. In situations where the hardware or software cannot detect a serious collision, no power-on recovery attempt is performed and the driver is directed to wait for assistance or quickly exit the vehicle.

[0050] Secondly, check whether the vehicle status meets the power-on recovery conditions.

[0051] The collision level is again determined based on the collision energy and vehicle status inspection results.

[0052] In this embodiment, the collision levels are divided into minor collision, moderate collision and severe collision. Minor collision means that the collision energy is lower than the set value and the vehicle status inspection result is good. Medium collision means that the collision energy is lower than the set value but the vehicle equipment is partially damaged, but it does not affect the auxiliary equipment. Severe collision means that the collision energy is higher than the set value or the degree of damage to the vehicle equipment affects the power supply of the high-voltage equipment.

[0053] A good vehicle condition inspection result means that all vehicle equipment is normal, excluding dents on the exterior. Partial damage to vehicle equipment that does not affect auxiliary equipment means that the wiring is normal, there are no oil leaks or controller damage, and low-voltage auxiliary equipment such as communications and lighting (or partial lighting) can be powered. Some non-critical high-voltage equipment such as entertainment and air conditioning systems is damaged. Vehicle equipment damage that affects the power supply of high-voltage equipment means controller damage, vehicle oil leaks, and damage to the power supply of high-voltage equipment such as the electric power steering system and electric braking system, which cannot be started normally. In this case, try to stay away from the vehicle and seek rescue through other means. The value set in this embodiment is 50,000 J, which can be adjusted based on actual test results and safety standards.

[0054] Finally, the corresponding power-on recovery operation is implemented according to the collision level.

[0055] Specifically, all devices will be automatically restored in a minor collision. Low-voltage auxiliary devices such as communications and lighting equipment that can be restored will be restored in a moderate collision. Power-on recovery is prohibited in a severe collision.

[0056] The airbag controller module is used to receive collision signals and calculate collision energy, and perform high-voltage power-off operations based on the comparison results between the collision energy and the threshold value issued by the central control module.

[0057] The airbag controller module includes a high-voltage power-off switch, which is configured by writing a configuration word. Configuration word 0 means that high-voltage power-off is not supported, and 1 means that high-voltage power-off is supported. Figure 1As shown, when a collision occurs, the collision signal is sent directly to the airbag controller module via hardwired transmission. This bypasses the master controller's comprehensive collision strategy assessment and directly compares it with the current thresholds pre-determined by the central control module. For example, within a 150ms time interval, 8km / h ≤ longitudinal speed, or within a 150ms time interval, 8km / h ≤ lateral speed. When the thresholds are met, a detonation current of 1.75A is output. This significantly reduces signal processing time. This embodiment simultaneously implements high-voltage power-off operations through hardwired control, CAN signal control, and PWM signal control.

[0058] like Figure 1 As shown, specifically: The ACU triggers the high-voltage disconnect switch, activating it to disconnect the high voltage. Using a hardwired circuit, the disconnect switch can be activated within 2ms, achieving a rapid response to high-voltage power outages. When the ACU triggers the disconnect switch, it simultaneously sends a signal to the ICM via CAN, illuminating the fault indicator.

[0059] At the same time, the ACU sends a collision signal to the BDM through a PWM waveform and turns on the four doors and double flashes. It also sends a collision signal to the BDM through a CAN signal and turns on the four doors and double flashes.

[0060] The ACU sends a collision signal to the BMS through a PWM waveform and disconnects the high voltage, and sends a collision signal to the BMS through a CAN signal and disconnects the high voltage.

[0061] This embodiment directly disconnects the pyrotechnic control switch through a hard-wired transmission method using current. When a collision occurs, the current ignites the gunpowder and disconnects the circuit. The advantages are high speed and no signal interference. A collision signal is also sent through a PWM waveform. After sending, the BMS needs to identify the waveform. When a collision occurs, a PWM waveform is sent to the BMS, and then the waveform is identified and the collision is determined by logic. The BMS then issues a command to disconnect the relay again. Since the PWM waveform may be affected and the link is relatively long, it takes a long time to implement the function. This embodiment also sends a collision signal through CAN communication. After sending, the BMS needs to identify the signal type. When a collision occurs, a CAN signal is sent to the BMS, and then the signal is identified and the collision is determined by logic. The BMS then issues a command to disconnect the relay again. The simultaneous implementation of both CAN signals and PWM waveforms further ensures the feasibility of high-voltage power-off, prevents delays and failures caused by the influence of a single signal, and improves the safety of the vehicle.

[0062] Example 2: A second embodiment of the present invention provides a control method for a vehicle post-collision safety signal control system as described in the first embodiment, comprising the following steps: The central control module selects the corresponding energy threshold according to the current road conditions and sends the energy threshold to the airbag controller module; After a vehicle collision, a collision signal is sent to the airbag controller module; After receiving the collision signal, the airbag controller module calculates the collision energy and compares the calculated result with the energy threshold. If the calculated result is greater than or equal to the energy threshold, the high-voltage power supply is directly cut off. After detecting that the voltage is stable, power-on recovery operation is performed according to the collision situation.

[0063] Example 3: A third embodiment of the present invention provides a computer-readable storage medium storing a computer program. The computer program is suitable for being loaded by a processor and executing the steps of the control method described in the second embodiment of the present invention.

[0064] Example 4: A fourth embodiment of the present invention provides a computer device, comprising: a processor adapted to execute a computer program; A computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the steps of the control method described in the second embodiment of the present invention are implemented.

[0065] Embodiment 5: A fifth embodiment of the present invention provides a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the steps of the control method described in the second embodiment of the present invention.

[0066] The steps involved in the above embodiments 2, 3, 4 and 5 correspond to those in the method embodiment 1. For the specific implementation methods, please refer to the relevant description part of the embodiment 1.

[0067] Those skilled in the art will appreciate that the units and algorithmic steps of each example described in conjunction with the embodiments disclosed in this application can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional technical personnel may use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application. In the above embodiments, all or part of the embodiments can be implemented using software, hardware, firmware, or any combination thereof. When implemented using software, all or part of the embodiments can be implemented in the form of a computer program product. A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions according to the embodiments of the present application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted via a computer-readable storage medium. The computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, optical fiber, digital line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer, or a data processing device such as a server or data center that integrates one or more available media. Available media can be magnetic media (e.g., floppy disks, hard disks, tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state drives (SSDs)). The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any technical object of a person skilled in the art that can be easily conceived of within the technical scope disclosed in this application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A vehicle post-collision safety signal control system, characterized in that: include: Data acquisition module, used to collect road condition information, vehicle status and collision signals; The central control module includes a model training module and a collision assessment module. The model training module is used to train the threshold model based on road condition information and vehicle status, calculate the corresponding threshold using the trained threshold model, and send the threshold to the airbag controller module. The collision assessment module is used to analyze the collision situation based on the collision energy and vehicle status, and perform power-on recovery operations based on the collision situation; The airbag controller module is used to receive collision signals and calculate collision energy, and perform high-voltage power-off operations based on the comparison results between the collision energy and the threshold value issued by the central control module. The high-voltage power-off operation is performed simultaneously through hard-line control, CAN signal control and PWM signal control.

2. The vehicle post-collision safety signal control system according to claim 1, characterized in that: In the model training module, the specific steps for threshold model training based on road condition information and vehicle status are as follows: Use random forest model to build threshold model; After annotating known road condition information and vehicle status, the dataset is divided into a training set and a test set. The threshold model is trained using the training set and tested using the test set to obtain a trained threshold model; The trained threshold model is used to calculate the threshold based on real-time road conditions and vehicle status.

3. The vehicle post-collision safety signal control system according to claim 2, characterized in that: A threshold constant mechanism is set, that is, the threshold calculation results are classified into intervals and the threshold is kept constant within the interval.

4. The vehicle post-collision safety signal control system according to claim 1, characterized in that: In the collision assessment module, the specific steps for analyzing the collision situation based on the collision energy and vehicle status are as follows: Obtaining the collision energy and post-collision vehicle status calculated by the airbag controller module; Check whether the vehicle status meets the power-on recovery conditions; Determine the collision level based on the collision energy and vehicle status inspection results; Implement corresponding power-on recovery operations according to the collision level.

5. The vehicle post-collision safety signal control system according to claim 4, characterized in that: Collision levels are divided into minor collisions, moderate collisions and severe collisions. A minor collision means that the collision energy is lower than the set value and the vehicle status inspection result is good. A moderate collision means that the collision energy is lower than the set value but the vehicle equipment is partially damaged, but it does not affect the auxiliary equipment. A severe collision means that the collision energy is higher than the set value or the degree of damage to the vehicle equipment affects the power supply of high-voltage equipment.

6. The vehicle post-collision safety signal control system according to claim 1, characterized in that: High voltage power-off operations can be performed simultaneously through hard-wire control, CAN signal control, and PWM signal control, including: Send out current to detonate the high-voltage power-off switch to meet the high-voltage disconnection requirement; Send a collision signal to the BDM through PWM waveform and open the four doors and hazard lights; Send collision signal to BDM via CAN signal and open four doors and hazard lights; Send a collision signal to the BMS through the PWM waveform and disconnect the high voltage; Send a collision signal to the BMS via the CAN signal and disconnect the high voltage.

7. The control method of the vehicle post-collision safety signal control system according to any one of claims 1 to 6, characterized in that: The following steps are involved: The central control module selects the corresponding energy threshold according to the current road conditions and sends the energy threshold to the airbag controller module; After a vehicle collision, a collision signal is sent to the airbag controller module; After receiving the collision signal, the airbag controller module calculates the collision energy and compares the calculated result with the energy threshold. If the calculated result is greater than or equal to the energy threshold, the high-voltage power supply is directly cut off. After detecting that the voltage is stable, power-on recovery operation is performed according to the collision situation.

8. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the control method according to claim 7 is implemented.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and the computer program is suitable for being loaded by a processor and executing the control method according to claim 7 .

10. A computer device, characterized in that: a processor adapted to execute a computer program; A computer-readable storage medium having a computer program stored therein, wherein the computer program, when executed by the processor, implements the control method according to claim 7.

Images