Intelligent cabin non-standard sitting posture passenger-oriented injury severity prediction method and system

Abstract

The invention belongs to the technical field of collision safety, and discloses an intelligent cabin non-standard sitting posture passenger-oriented damage severity prediction method and system, and the method comprises the steps: collecting a real traffic accident case, carrying out the simulation working condition reconstruction, and obtaining a high-risk working condition data set; identifying accident morphological characteristics and passenger injury severity of the high-risk working condition data set to obtain a standard attitude data set under the high-risk working condition; the collision parameters and the passenger posture parameters are considered, a simulation data set with the collision parameters coupled with the non-standard sitting posture parameters is obtained, the standard posture data set and the simulation data set are fused, and a high-risk working condition global sitting posture database is obtained; and training the neural network by using the high-risk working condition global sitting posture database to obtain a trained prediction model, and predicting the severity of the passenger injury by using the trained prediction model. Accurate safety evaluation of the non-standard sitting posture of the intelligent cabin is realized, and passenger injury severity prediction of the non-standard sitting posture of the intelligent cabin is completed through a machine learning algorithm.

Description

Technical Field

[0001] The present invention relates to the field of collision safety technology, and in particular to a method and system for predicting injury severity for occupants in non-standard sitting postures in an intelligent cockpit. 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 development and widespread adoption of autonomous driving technology, traditional driver-centric vehicle design concepts are facing fundamental change. In highly automated driving scenarios (SAE Level 3 and above), occupants will be freed from the constraints of the driving task and will adopt a more flexible and diverse seating position, such as a semi-reclining position, a swiveled seat, or a fully extended leg position. While this transformation improves occupant comfort, it also poses new challenges to the vehicle's passive safety systems. Current collision safety protection systems and evaluation standards based on a standard driving posture are no longer adaptable to future demands. Summary of the Invention

[0004] In order to solve the above problems, the present invention proposes a method and system for predicting the severity of injuries of occupants in non-standard sitting postures in smart cockpits, realizes the accurate safety assessment of non-standard sitting postures in smart cockpits, completes the intelligent identification of high-risk working conditions and the extraction of their biomechanical characteristics, establishes a coupled simulation data set of collision parameters and non-standard sitting posture parameters, and completes the prediction of the severity of injuries of occupants in non-standard sitting postures in smart cockpits through machine learning algorithms.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions: In a first aspect, the present invention provides an injury severity prediction method for occupants in non-standard sitting postures in a smart cockpit, comprising the following steps: Collect real traffic accident case data and use multi-body dynamics to reconstruct simulation conditions, enrich the data, and obtain a high-risk condition data set; Identify the accident morphological characteristics and occupant injury severity of the high-risk working condition data set, and obtain the standard posture data set under high-risk working conditions based on the accident morphological characteristics and occupant injury severity; Based on the standard posture dataset, considering the collision parameters and occupant posture parameters, a simulation dataset coupling the collision parameters and non-standard sitting posture parameters under high-risk working conditions is obtained. The standard posture dataset and the simulation dataset are integrated to obtain a full-domain sitting posture database under high-risk working conditions. The neural network is trained using the global sitting posture database of high-risk working conditions to obtain a trained prediction model, which is then used to predict the severity of occupant injuries.

[0006] As an optional implementation, the final predicted occupant injury severity is further classified into risk levels according to the AIS-ISS scoring standard.

[0007] As an optional implementation manner, the accident morphological characteristics include accident frequency, severity, collision direction, collision position, collision angle, collision speed, occupant injury and collision object.

[0008] As an optional implementation, the occupant injury severity includes casualty conditions and a simplified injury rating.

[0009] As an optional embodiment, the collision parameters include collision speed, collision position, collision angle and vehicle stiffness parameters.

[0010] As an optional implementation manner, the occupant posture parameters include seat orientation, seat angle, occupant sitting posture, seat belt wearing status and airbag triggering timing.

[0011] In a second aspect, the present invention provides an injury severity prediction system for occupants in non-standard sitting postures in smart cockpits, comprising: The data acquisition module is configured to collect real traffic accident case data, and use multi-body dynamics to reconstruct the simulated working conditions, enrich the data, and obtain a high-risk working condition data set; The standard posture dataset construction module is configured to: identify the accident morphological characteristics and occupant injury severity of the high-risk working condition dataset, and obtain the standard posture dataset under the high-risk working condition based on the accident morphological characteristics and occupant injury severity; The global sitting posture database construction module is configured to: based on the standard posture dataset, consider the collision parameters and occupant posture parameters, obtain a simulation dataset that couples the collision parameters with non-standard sitting posture parameters under high-risk conditions, and fuse the standard posture dataset and the simulation dataset to obtain a high-risk global sitting posture database; The model training and prediction module is configured to: use the global sitting posture database of high-risk working conditions to train the neural network, obtain a trained prediction model, and use the trained prediction model to predict the severity of occupant injuries.

[0012] In a third aspect, the present invention provides an electronic device comprising a memory and a processor, and computer instructions stored in the memory and executed on the processor, wherein the computer instructions, when executed by the processor, perform the method described in the first aspect.

[0013] In a fourth aspect, the present invention provides a computer-readable storage medium for storing computer instructions, wherein when the computer instructions are executed by a processor, the method described in the first aspect is performed.

[0014] In a fifth aspect, the present invention provides a computer program product, comprising a computer program, which implements the method described in the first aspect when executed by a processor.

[0015] Compared with the prior art, the present invention has the following beneficial effects: This paper proposes a method and system for predicting injury severity for occupants in non-standard sitting postures in smart cockpits. This method uses multibody dynamics to reconstruct simulated working conditions, enrich the data set, and construct a high-risk working condition data set. Based on this enriched high-risk working condition data set, the system intelligently identifies high-risk working conditions and extracts their biomechanical features. Furthermore, the system considers collision parameters and occupant posture parameters, establishes a coupled simulation data set combining collision parameters and non-standard sitting posture parameters, and integrates the standard posture data set with the simulation data set to generate a global sitting posture database for high-risk working conditions. Using this database, the system uses a machine learning algorithm to predict injury severity for occupants in non-standard sitting postures in smart cockpits. This system achieves accurate safety assessment of non-standard sitting postures in smart cockpits.

[0016] 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

[0017] The accompanying drawings, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0018] Figure 1 The process of the injury severity prediction method for non-standard sitting posture occupants in the intelligent cockpit provided in embodiment 1 of the present invention Figure 1 ; Figure 2 This is a schematic diagram of the collision working condition of the present invention; Figure 3 The process of the injury severity prediction method for non-standard sitting posture occupants in the intelligent cockpit provided in embodiment 1 of the present invention Figure 2 . DETAILED DESCRIPTION

[0019] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0020] 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.

[0021] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0022] In the absence of conflict, the embodiments of the present invention and the features thereof may be combined with each other.

[0023] Example 1 like Figure 1 As shown, this embodiment provides an injury severity prediction method for occupants in non-standard sitting postures in a smart cockpit, comprising the following steps: S1. Collect real traffic accident case data and use multi-body dynamics to reconstruct simulation conditions, enrich the data, and obtain a high-risk condition data set; S2. Identify the accident morphological characteristics and occupant injury severity of the high-risk working condition dataset, and obtain a standard posture dataset under the high-risk working condition based on the accident morphological characteristics and occupant injury severity; S3. Based on the standard posture dataset, considering the collision parameters and occupant posture parameters, a simulation dataset is obtained that couples the collision parameters with non-standard sitting posture parameters under high-risk conditions. The standard posture dataset and the simulation dataset are then integrated to obtain a global sitting posture database under high-risk conditions. S4. Use the global sitting posture database of high-risk working conditions to train the neural network to obtain a trained prediction model, and use the trained prediction model to predict the severity of occupant injuries.

[0024] It also includes classifying the final predicted severity of occupant injury into risk levels according to the AIS-ISS scoring standard.

[0025] We collected real-world traffic accident data and, by setting different boundary conditions, using accident morphological characteristics as decision factors and occupant injury severity as the decision objective, employed a multi-attribute decision-making approach to identify various high-risk operating conditions. Due to limited real-world traffic accident data, we employed multibody dynamics to reconstruct simulated operating conditions, enrich the data, and construct a high-risk operating condition dataset.

[0026] Accident morphological feature identification includes accident frequency, severity, collision direction, collision position, collision angle, collision speed, occupant injury, collision object, etc.

[0027] The severity of occupant injury includes casualties and the Combined Testing Standard (CTS).

[0028] The AIS (Analog Injury Scale) occupant casualty assessment method, through a systematic and standardized medical assessment system, can accurately quantify the extent of injuries to occupants in traffic accidents, providing a scientific basis for medical rescue, accident responsibility determination, and vehicle safety performance improvement. Specifically, this method includes the following steps: 1) In the injury location classification and grading stage, this invention adopts the internationally recognized AIS standard, which divides the human body into nine major anatomical regions: skin, head, maxillofacial region, neck, chest, abdomen and pelvic viscera, spine, upper and lower extremities. The severity of injury in each region is categorized into six grades based on clinical severity, with a score ranging from 1 to 6. 1 represents the mildest injury, while 6 represents the most severe, life-threatening injury. This grading system comprehensively covers all injuries, from minor to fatal.

[0029] 2) During the expert evaluation and scoring phase, this invention requires an evaluation team composed of clinical experts with extensive experience in trauma care. During the evaluation process, experts need to comprehensively consider multiple factors: first, the direct impact of the injury on the patient's vital signs; second, the degree of functional impairment caused by the injury, including long-term effects such as loss of motor function and sensory impairment; and third, the patient's pain level and expected recovery. The evaluation experts must combine imaging examinations, laboratory test results, and clinical observations, and independently score each injury site in strict accordance with the AIS scoring criteria to ensure the objectivity and consistency of the evaluation results.

[0030] 3) During the comprehensive evaluation phase, the present invention adopts differentiated assessment strategies for different injuries. For single-site injuries, the AIS score for that site can accurately reflect the severity of the injury. For patients with multiple injuries, a more scientific Injury Severity Score (ISS) calculation method is used. The specific ISS score calculation formula is as follows: ; AIS1, AIS2, and AIS3 are the highest AIS values of the three most severely injured areas selected from all injured parts.

[0031] To unify the scoring standards of AIS and ISS, the two are normalized to obtain the AIS-ISS joint scoring standard (CTS). The specific formula is as follows: CTS=max(AIS 最高 , ); The highest AIS value was taken (AIS was the highest, ranging from 1 to 6 points), the standardized ISS value was calculated (ranging from 0.07 to 5), and the comprehensive score was the larger of the two values (ranging from 1 to 6 points, consistent with the AIS grading).

[0032] In the CTS evaluation process, the priority principle is adopted: if any part of the AIS = 6 points, it is directly judged as CTS = 6 points (no need to calculate ISS); if ISS ≥ 75 points, even if the highest AIS ≤ 5 points, it is still judged as CTS = 5 points. The specific evaluation criteria are as follows: CTS≤1 point; AIS maximum score ≤1 point; ISS≤8 points; confirmed as mild injury, only simple treatment is required, no hospitalization is required; CTS≤2 points; AIS maximum score ≤2 points; ISS≤15 points; confirmed as moderate injury, no life-threatening; CTS≤3 points; AIS maximum score ≤3 points; ISS≤24 points; confirmed as more serious injury, short-term vital signs are stable; CTS≤4 points; AIS maximum score ≤4 points; ISS≤49 points; confirmed as serious injury, life-threatening; CTS≤5 points; AIS maximum score ≤5 points; ISS≤74 points; confirmed as critical injury, with significantly increased mortality; CTS=6 points; AIS maximum score =6 points or ISS=75 points; confirmed as extremely critical injury, with an extremely low survival rate.

[0033] The occupant injury situation under each different standard sitting posture with accident morphological characteristics is quantified into different CTS scores.

[0034] By replacing traditional subjective judgment with a quantitative scoring system, the accuracy and comparability of the evaluation results are greatly improved.

[0035] Identify the accident morphological characteristics and occupant injury severity of the high-risk working condition data set. Based on the accident morphological characteristics and occupant injury severity, obtain the standard posture data set under high-risk working conditions, specifically: The accident morphology characteristics and occupant injury severity of a high-risk operating condition dataset are identified using CTS characterization to generate n samples. The accident morphology characteristic parameters (including occupant posture parameters) of each sample are used as input, along with the occupant injury severity. These data are quantified and then fed into the fitting model for computation, resulting in a visual occupant injury severity model. Predictions are then made using this visual occupant injury severity model.

[0036] Based on the existing accident morphological characteristics and occupant injury severity, a standard posture dataset under high-risk working conditions is obtained. The standard posture refers to the standard sitting posture parameters of each joint of the occupant.

[0037] Based on a standard posture dataset, the occupant posture parameters (i.e., parameters of each occupant's joints) were reconsidered and remodeled for simulation. Each sample's accident morphological characteristic parameters (including occupant sitting posture parameters) were used as input, and the injury severity was output. This data was quantified and input into the fitting model for computation, resulting in a new visual occupant injury severity model. This new visual occupant injury severity model was then used for prediction.

[0038] Based on the accident morphological characteristics and occupant injury severity, a simulation dataset is obtained that couples collision parameters with non-standard sitting posture parameters under high-risk conditions. The standard posture dataset and the simulation dataset are integrated to obtain a global sitting posture database for high-risk conditions. The non-standard posture refers to the occupant's various joint parameters being non-standard sitting posture parameters, such as lying flat.

[0039] Construct a coupled simulation dataset of collision parameters and non-standard sitting posture parameters under high-risk conditions, specifically: 1) Consider the collision parameters, including collision speed (20-120 km / h, in 5 km / h intervals), collision location (front collision, offset collision, side collision, rear collision), collision angle (0°-90°, in 15° intervals), and introduce vehicle stiffness parameters (force-displacement curves of key structures such as front longitudinal beams and rocker beams), such as Figure 2 shown.

[0040] 2) Consider the occupant posture parameters, including: seat orientation (standard / rearward 10° / forward 15°), seat angle (backrest angle 15°-35°), occupant sitting position (standard / side tilt 20° / legs forward / arms crossed); consider the seat belt wearing state (normal / loose / unfastened) and airbag triggering timing (0-50 ms delay) such as Figure 2 shown.

[0041] 3) Based on orthogonal experimental design or Latin hypercube sampling method, generate no less than 1,000 sets of parameter combinations to ensure that all working conditions are covered as much as possible.

[0042] 4) Use existing software to build a dummy model and simulate collision scenarios under various parameter combinations; 5) Output key injury indicators such as occupant head injury criterion (HIC) and chest compression (ThPC).

[0043] 6) After normalizing the different evaluation criteria of the nine parts of AIS, a comprehensive evaluation score is output, which is the same as the CTS evaluation level in the first aspect.

[0044] 7) Output comprehensive evaluation scores for 1,000 different combinations of collision parameters and occupant posture parameters, which is conducive to the establishment of subsequent data sets.

[0045] Expand to a sufficient number of databases. Merge the standard sitting posture dataset (i.e., the standard posture dataset under high-risk working conditions) with the non-standard sitting posture dataset (i.e., the simulation dataset of collision parameters under high-risk working conditions coupled with non-standard sitting posture parameters) to form a multi-dimensional damage database (i.e., the full-domain sitting posture database under high-risk working conditions).

[0046] Through systematic parameter combination and large-scale simulation, the coverage of the non-standard posture damage model is significantly improved; the fusion of simulation and real data solves the problem of insufficient actual samples; and the accuracy of the subsequent neural network prediction model for the severity of occupant injuries in the cabin is significantly improved, realizing the quantitative assessment of collision damage to occupants in non-standard postures.

[0047] By combining deep learning, data-driven and evolutionary computing, an efficient occupant injury prediction algorithm is proposed to construct a mapping model between various collision parameters and occupant injuries, and meet the accuracy requirements.

[0048] Furthermore, to improve the diversity and coverage of the dataset, the present invention adopts data augmentation technology, including applying Gaussian noise perturbation to the original collision parameters to generate multiple neighboring samples, and using a generative adversarial network (GAN) generation model to perform data augmentation on the coupled simulation dataset of collision parameters under high-risk working conditions and standard and non-standard sitting posture parameters, thereby expanding the scale of the training dataset and improving the model's adaptability to different collision scenarios.

[0049] like Figure 3 As shown in the figure, the data augmentation method involves applying Gaussian noise perturbations to the original collision parameters to generate multiple nearest neighbor samples. A generative adversarial network is used as the data derivation matrix. The inputs to both the generator (G) and the discriminator (D) include category labels and data on standard and non-standard sitting posture types. Based on the original dataset, the generative adversarial network performs nonlinear combinations and crossover operations on the data source features in the original dataset to enhance the training dataset.

[0050] Furthermore, the data augmentation dataset was used to construct a deep neural network-based occupant injury prediction model. This model uses a fully connected neural network to effectively learn the complex nonlinear mapping between collision parameters and occupant injury indicators, thereby achieving high-precision prediction of occupant injuries.

[0051] Furthermore, evolutionary computing methods such as genetic algorithms (GA) or particle swarm optimization (PSO) are used to optimize the hyperparameters of deep learning models (such as learning rate, number of hidden layer nodes, regularization coefficient, network structure, etc.). By iteratively searching for the optimal hyperparameter combination, the model's prediction accuracy is improved.

[0052] Furthermore, the training data is divided into a training set and a validation set. The model is trained using the training set, and the model performance is evaluated using the validation set. Methods such as cross-validation are used to ensure the stability and generalization ability of the model.

[0053] Furthermore, a trained deep learning model establishes a mapping relationship between collision parameters and occupant injuries. This model can quickly and accurately predict occupant injuries based on input collision parameters, providing data support for vehicle safety design, collision testing, and intelligent simulation.

[0054] The training model includes a fully connected neural network, in which each neuron is connected to all neurons in the previous and next layers, forming a dense connection structure. The collision parameters (crash speed, collision position and collision angle) and occupant posture parameters (seat orientation, seat angle and occupant sitting posture) are used as Figure 3 The fully connected neural network takes as input the injury severity of the members in non-standard sitting postures in the intelligent cockpit under high-risk working conditions.

[0055] Based on real traffic accident cases and simulation data in my country, this example constructs a high-risk operating condition dataset for non-standard sitting postures in the intelligent cockpit. Taking collision severity, injury risk, and protection effectiveness as the goals, a multidisciplinary fusion algorithm is used to establish an occupant injury severity prediction model. Occupant injury indicators under different sitting postures are tested and evaluated, achieving data modeling, analysis, and prediction of the entire cycle of collision safety performance to complete safety assessment and protection system optimization tasks.

[0056] Specifically include: First, this example can collect data and extract features for non-standard sitting posture conditions to be evaluated. Taking collision parameters, sitting posture parameters, and damage indicators as targets, it establishes a library of typical high-risk conditions and an occupant injury severity model through statistical analysis and intelligent optimization algorithms, and quantitatively assesses the injury risks under different conditions.

[0057] Secondly, this example can construct a coupled simulation data set of collision parameters and non-standard sitting posture parameters. With the biomechanical response, damage mechanism and protection strategy as the goal, through multi-body dynamics simulation and finite element analysis, a sitting posture-collision condition mapping relationship model is established, and the damage threshold under each condition is accurately calibrated.

[0058] Thirdly, this example can propose an efficient occupant injury prediction algorithm by combining deep learning, data-driven and evolutionary computing. With the goals of prediction accuracy, computational efficiency and generalization ability, it constructs an intelligent mapping model between collision parameters and occupant injuries, and meets the accuracy requirements of engineering applications.

[0059] Example 2 This embodiment provides an injury severity prediction system for occupants in non-standard sitting postures in a smart cockpit, including: The data acquisition module is configured to collect real traffic accident case data, and use multi-body dynamics to reconstruct the simulated working conditions, enrich the data, and obtain a high-risk working condition data set; The standard posture dataset construction module is configured to: identify the accident morphological characteristics and occupant injury severity of the high-risk working condition dataset, and obtain the standard posture dataset under the high-risk working condition based on the accident morphological characteristics and occupant injury severity; The global sitting posture database construction module is configured to: based on the standard posture dataset, consider the collision parameters and occupant posture parameters, obtain a simulation dataset that couples the collision parameters with non-standard sitting posture parameters under high-risk conditions, and fuse the standard posture dataset and the simulation dataset to obtain a high-risk global sitting posture database; The model training and prediction module is configured to: use the global sitting posture database of high-risk working conditions to train the neural network, obtain a trained prediction model, and use the trained prediction model to predict the severity of occupant injuries.

[0060] It should be noted that the above modules correspond to the steps described in Example 1, and the examples and application scenarios implemented by the above modules and the corresponding steps are the same, but are not limited to the contents disclosed in the above Example 1. It should be noted that the above modules, as part of the system, can be executed in a computer system such as a set of computer-executable instructions.

[0061] In further embodiments, there is also provided: An electronic device includes a memory and a processor, and computer instructions stored in the memory and executed by the processor, wherein when the computer instructions are executed by the processor, the method described in Example 1 is performed. For the sake of brevity, no further details are given here.

[0062] It should be understood that in this embodiment, the processor may be a central processing unit (CPU), or may be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), off-the-shelf field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0063] The memory may include a read-only memory and a random access memory, and provides instructions and data to the processor. A portion of the memory may also include a non-volatile random access memory. For example, the memory may also store information about the device type.

[0064] A computer-readable storage medium is used to store computer instructions, and when the computer instructions are executed by a processor, the method described in Example 1 is performed.

[0065] The method in Example 1 can be directly implemented as a hardware processor, or can be implemented using a combination of hardware and software modules in the processor. The software module can be located in a storage medium mature in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, etc. The storage medium is located in the memory, and the processor reads the information in the memory and, in conjunction with its hardware, completes the steps of the above method. To avoid repetition, it will not be described in detail here.

[0066] A computer program product includes a computer program, which implements the method described in embodiment 1 when executed by a processor.

[0067] The present invention also provides at least one computer program product tangibly stored on a non-transitory computer-readable storage medium. The computer program product includes computer-executable instructions, such as instructions contained in program modules, which are executed in a device on a real or virtual processor of a target to perform the process / method described above. Generally, program modules include routines, programs, libraries, objects, classes, components, data structures, etc. that perform specific tasks or implement specific abstract data types. In various embodiments, the functionality of program modules can be combined or divided between program modules as needed. The machine-executable instructions for the program modules can be executed in local or distributed devices. In distributed devices, program modules can be located in local and remote storage media.

[0068] The computer program code for implementing the method of the present invention can be written in one or more programming languages. These computer program codes can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the computer or other programmable data processing device, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on a computer, partially on a computer, as an independent software package, partially on a computer and partially on a remote computer, or entirely on a remote computer or server.

[0069] In the context of the present invention, computer program code or related data can be carried by any appropriate carrier to enable a device, apparatus, or processor to perform the various processes and operations described above. Examples of carriers include signals, computer-readable media, and the like. Examples of signals include electrical, optical, radio, acoustic, or other forms of propagated signals, such as carrier waves, infrared signals, and the like.

[0070] Those skilled in the art will appreciate that the units and algorithm steps of the various examples described in conjunction with this embodiment 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. Professionals and technicians can 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.

[0071] Although the above describes the specific embodiments of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art on the basis of the technical solution of the present invention without any creative work are still within the scope of protection of the present invention.

Claims

1. An injury severity prediction method for occupants in non-standard sitting positions in smart cockpits is characterized by: The following steps are involved: Collect real traffic accident case data and use multi-body dynamics to reconstruct simulation conditions, enrich the data, and obtain a high-risk condition data set; Identify the accident morphological characteristics and occupant injury severity of the high-risk working condition data set, and obtain the standard posture data set under high-risk working conditions based on the accident morphological characteristics and occupant injury severity; Based on the standard posture dataset, considering the collision parameters and occupant posture parameters, a simulation dataset coupling the collision parameters and non-standard sitting posture parameters under high-risk working conditions is obtained. The standard posture dataset and the simulation dataset are integrated to obtain a full-domain sitting posture database under high-risk working conditions. The neural network is trained using the global sitting posture database of high-risk working conditions to obtain a trained prediction model, which is then used to predict the severity of occupant injuries.

2. The method for predicting injury severity for occupants in non-standard sitting postures in a smart cockpit according to claim 1, characterized in that: It also includes classifying the final predicted severity of occupant injury into risk levels according to the AIS-ISS scoring standard.

3. The method for predicting injury severity for occupants in non-standard sitting postures in a smart cockpit according to claim 1, characterized in that: Accident morphological characteristics include accident frequency, severity, collision direction, collision location, collision angle, collision speed, occupant injuries and collision object.

4. The method for predicting injury severity for occupants in non-standard sitting postures in a smart cockpit according to claim 1, characterized in that: The severity of occupant injuries includes casualties and concise injury rating.

5. The method for predicting injury severity for occupants in non-standard sitting postures in a smart cockpit according to claim 1, characterized in that: Collision parameters include collision speed, collision position, collision angle and vehicle stiffness parameters.

6. The method for predicting injury severity for occupants in non-standard sitting postures in a smart cockpit according to claim 1, characterized in that: Occupant posture parameters include seat orientation, seat angle, occupant sitting posture, seat belt wearing status and airbag triggering timing.

7. The injury severity prediction system for occupants in non-standard sitting positions in smart cockpits is characterized by: include: The data acquisition module is configured to collect real traffic accident case data, and use multi-body dynamics to reconstruct the simulated working conditions, enrich the data, and obtain a high-risk working condition data set; The standard posture dataset construction module is configured to: identify the accident morphological characteristics and occupant injury severity of the high-risk working condition dataset, and obtain the standard posture dataset under the high-risk working condition based on the accident morphological characteristics and occupant injury severity; The global sitting posture database construction module is configured to: based on the standard posture dataset, consider the collision parameters and occupant posture parameters, obtain a simulation dataset that couples the collision parameters with non-standard sitting posture parameters under high-risk conditions, and fuse the standard posture dataset and the simulation dataset to obtain a high-risk global sitting posture database; The model training and prediction module is configured to: use the global sitting posture database of high-risk working conditions to train the neural network, obtain a trained prediction model, and use the trained prediction model to predict the severity of occupant injuries.

8. An electronic device, characterized in that: The method comprises a memory and a processor, and computer instructions stored in the memory and executed on the processor, wherein when the computer instructions are executed by the processor, the method according to any one of claims 1 to 6 is completed.

9. A computer-readable storage medium, characterized in that Used to store computer instructions, which, when executed by a processor, complete the method according to any one of claims 1 to 6.

10. A computer program product, characterized in that The invention comprises a computer program, which is used to implement the method according to any one of claims 1 to 6 when the computer program is executed by a processor.

Images