CN109738205A - The occupant restraint method of integrated vehicle automatic emergency brake and air bag system - Google Patents
The occupant restraint method of integrated vehicle automatic emergency brake and air bag system Download PDFInfo
- Publication number
- CN109738205A CN109738205A CN201910020502.3A CN201910020502A CN109738205A CN 109738205 A CN109738205 A CN 109738205A CN 201910020502 A CN201910020502 A CN 201910020502A CN 109738205 A CN109738205 A CN 109738205A
- Authority
- CN
- China
- Prior art keywords
- model
- occupant
- damage
- air bag
- neck
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Landscapes
- Air Bags (AREA)
Abstract
The invention discloses the occupant restraint methods of a kind of integrated vehicle automatic emergency brake and air bag system, include the following steps: step 1, establish occupant restraint system benchmark model；Step 2 tests the damage criterion for the benchmark model that step 1 is established；Step 3 utilizes SVM model prediction occupant's head position；Step 4 judges the accuracy that the occupant's head position come is predicted in step 3；Step 5, using the optimal protection zone chosen in step 4 as constraint condition, concurrently sets automatic emergency brake deceleration constraint condition when crashing.The occupant restraint method of integrated vehicle automatic emergency brake and air bag system of the invention, pass through the setting of step 1 to step 5, it can effectively realize by establishing model, then it carries out exporting in optimal control parameter to the brake system of automobile after damage forecast, enables protection of the brake system of automobile to the occupant that do not fasten the safety belt in collision accident.
Description
Technical field
The present invention relates to a kind of means of defence, more particularly to a kind of integrated vehicle automatic emergency brake and safety
The occupant restraint method of gas-bag system.
Background technique
Along with the raising of vehicle intellectualized degree, more and more driving assistance systems are suggested and push to industrialization, packet
It includes: preceding to hit early warning system, Lane Departure Warning System, self-adaption cruise system and automatic emergency brake system etc..Among these,
Automatic emergency brake system can be in the case where no driver inputs, the vehicle risk sensing results based on current time,
Automatic braking is carried out to vehicle, collision loss can be effectively reduced, is the intelligence of current third party's assessment mechanism stress test
Driving assistance system.
During to automatic emergency brake technical research, although the system can significantly reduce the collision speed of vehicle
Degree, but biggish braking deceleration may make the upper torso portion of human body occur leaning forward and leaving normal in braking process
Position (is offed normal) phenomenon.Since current vehicle occupant restraint system (such as safety belt and air bag) is mainly based upon to just
Normal position occupant's sitting posture design, if there is phenomenon of offing normal, it is most likely that original protection effect is not achieved, or even causes more
Add serious damage.For member with belt, at present can by safety belt is pre-tightened in advance help improve from
Position sitting posture.However for the occupant that do not fasten the safety belt, at present but without effective occupant restraint ameliorative way.
Summary of the invention
In view of the deficiencies of the prior art, the present invention intends to provide a kind of integrated vehicle automatic emergency brake with
The occupant restraint method of air bag system is mainly used for solving under automatic emergency brake system effect, in conjunction with air bag
System fills up the blank at present for this problem-solving approach to the protection question for Retired old person of not fastening the safety belt.
To achieve the above object, the present invention provides the following technical scheme that a kind of integrated vehicle automatic emergency brake and peace
The occupant restraint method of full gas-bag system, includes the following steps:
Step 1 establishes occupant restraint system benchmark model；
Step 2 tests the damage criterion for the benchmark model that step 1 is established, judges that damage criterion is with test result
It is no consistent, continue next step if consistent, if inconsistent return step one re-establishes benchmark model；
Step 3 utilizes SVM model prediction occupant's head position；
Step 4 judges the accuracy that the occupant's head position come is predicted in step 3, judges the accuracy of prediction
Whether more than 90%, optimal protection zone is chosen if more than 90%, is predicted again if being less than 90% return step three；
Step 5, using the optimal protection zone chosen in step 4 as constraint condition, is set simultaneously when crashing
Determine automatic emergency brake deceleration constraint condition, under two constraint condition, solving optimization objective function solves maximum collision
Amount of speed reduction, and optimize to obtain the optimal control parameter A of emergency braking systempre_decelerationWith Tbrake_time, and will
Obtained optimal control parameter is input in brake system, driving brake system acting；
Wherein, Apre_decelerationFor optimal brake deceleration degree, Tbrake_timeFor optimal braking time.
As a further improvement of the present invention, the step of occupant restraint system benchmark model is established in the step 1 is specific
Include the following steps:
Step 1 one, setting instrument board, steering wheel, air bag, dummy model, safe band model and automobile chair model, instrument
Dial plate, steering wheel use multi-body Dynamics Model, and air bag, dummy model, safe band model and automobile chair model use
Finite element model；
Step 1 two carries out set according to model set in step 1 one and constitutes benchmark model.
As a further improvement of the present invention, the test procedure in the step 2 specifically comprises the following steps:
Step 2 one carries out computer simulation to model, extracts the damage of dummy's each section after establishing benchmark model
Hurt index；
Step 2 two gets the damage criterion that practical dummy is subjected to by real vehicle trolley test；
Damage criterion obtained in step 2 one and step 2 two is compared by step 2 three, and judges two damages
Hurt whether index is consistent, completes the test to damage criterion.
As a further improvement of the present invention, the damage criterion in the step 2 includes head injury criterion, chest damage
Hurt index and neck injury index, wherein head injury criterion is calculated by following formula:
In formula, HIC15For head injury criterion, t2-t1For 15ms, PheadFor head injury risk probability, t damage generate when
Between；
Thoracic injury index is calculated by following formula:
In formula, PchestFor thoracic injury risk probability, D indicates dummy model breast compressions amount；
Neck injury index is calculated by following formula:
In formula,Pneck_T, Pneck_CThe respectively damage probability on neck top, damage probability in the middle part of neck and
The damage probability of neck lower part, Nij, T, C respectively indicate the upper, middle and lower of neck.
As a further improvement of the present invention, in the step 3 predict occupant's head position the step of specifically include as
Under:
The distance between occupant's head and steering wheel are divided into 5 sections by step 3 one, are defined as the region region 1- 5 as SVM points
Label in class；
Step 3 two using the different collision deceleration value of computer installation and is emulated, and training and the verifying number of SVM are obtained
According to the training and verify data that then basis is got determine which label occupant's head position is in.
As a further improvement of the present invention, the selecting step of the optimal protection zone in the step 4 is as follows:
The head position of occupant's model is separately adjusted to angularly the middle position in 5 regions by step 4 one, carries out computer simulation；
Step 4 two calculates complex damage function Pcombine=1- (1-Phead)(1-Pneck)(1-Pchest) size；
Step 4 three chooses PcombineMinimum value is as optimal protection zone.
Beneficial effects of the present invention can effectively establish out corresponding benchmark by the setting of step 1 to step 5
Model, then and establish come out benchmark model select optimal protection using the position of SVM model prediction occupant's head
Region all regard optimal protection zone and benchmark model as corresponding constraint condition, mentions later when crashing
Optimal control parameter driving brake system acting is confessed, an effective guarantor so is carried out for un-belted occupant on vehicle
Shield effect, has filled up the blank of the prior art.
Detailed description of the invention
Fig. 1 is the flow chart of means of defence of the invention.
Specific embodiment
The present invention is described in further detail below in conjunction with embodiment given by attached drawing.
Shown in referring to Fig.1, a kind of integrated vehicle automatic emergency brake of the present embodiment and the occupant of air bag system are anti-
Maintaining method includes the following steps:
Step 1 establishes occupant restraint system benchmark model；
Step 2 tests the damage criterion for the benchmark model that step 1 is established, judges that damage criterion is with test result
It is no consistent, continue next step if consistent, if inconsistent return step one re-establishes benchmark model；
Step 3 utilizes SVM model prediction occupant's head position；
Step 4 judges the accuracy that the occupant's head position come is predicted in step 3, judges the accuracy of prediction
Whether more than 90%, optimal protection zone is chosen if more than 90%, is predicted again if being less than 90% return step three；
Step 5, using the optimal protection zone chosen in step 4 as constraint condition, is set simultaneously when crashing
Determine automatic emergency brake deceleration constraint condition, under two constraint condition, solving optimization objective function solves maximum collision
Amount of speed reduction, and optimize to obtain the optimal control parameter A of emergency braking systempre_decelerationWith Tbrake_time, and will
Obtained optimal control parameter is input in brake system, driving brake system acting；
Wherein, Apre_decelerationFor optimal brake deceleration degree, Tbrake_timeFor optimal braking time, this implementation is being used
During occupant restraint method in example, the setting of step 1 to step 4 is first passed through, it can be effectively for interior control
System processed carries out the effect of a preset control parameters, then occur during driver drives vehicle collision accident when
It waits, using preset control parameter before, for when there is collision accident, effectively fastens the safety belt people for Che Shangwei
Member is effectively protected, compared with the prior art in common control system, the personnel that can fasten the safety belt for Che Shangwei exist
Collision accident is effectively protected when generation, has filled up corresponding blank, is avoided when collision accident occurs,
Because of the problem of personnel that do not fasten the safety belt caused by emergency brake fly out from vehicle or injure by hard impacts, wherein the present embodiment
In step one to step 4 can be divided into the earlier preparation stage, and step 5 is then divided into practical stage.
As a kind of improved specific embodiment, the step of occupant restraint system benchmark model is established in the step 1
Specifically comprise the following steps:
Step 1 one, setting instrument board, steering wheel, air bag, dummy model, safe band model and automobile chair model, instrument
Dial plate, steering wheel use multi-body Dynamics Model, and air bag, dummy model, safe band model and automobile chair model use
Finite element model；
Step 1 two carries out set according to model set in step 1 one and constitutes benchmark model, setting through the above steps
It sets, then the impact test model that can be effectively had using computer simulation is repeatedly imitated using computer unit
The mode really simulated can constitute a benchmark model in this way, and as subsequent judgement during collision accident, occupant goes out
The standard now damaged.
As a kind of improved specific embodiment, the test procedure in the step 2 specifically comprises the following steps:
Step 2 one carries out computer simulation to model, extracts the damage of dummy's each section after establishing benchmark model
Hurt index；
Step 2 two gets the damage criterion that practical dummy is subjected to by real vehicle trolley test；
Damage criterion obtained in step 2 one and step 2 two is compared by step 2 three, and judges two damages
Hurt whether index is consistent, complete the test to damage criterion, the benchmark model built can so be carried out effective
Verifying, enables benchmark model more acurrate close to existing actual conditions, avoids the occurrence of because of benchmark model and actual deviation
The inappropriate problem of optimal control parameter finally exported caused by excessive.
As a kind of improved specific embodiment, the damage criterion in the step 2 includes head injury criterion, chest
Portion's damage criterion and neck injury index, wherein head injury criterion is calculated by following formula:
In formula, HIC15For head injury criterion, t2-t1For 15ms, PheadFor head injury risk probability, t damage generate when
Between；
Thoracic injury index is calculated by following formula:
In formula, PchestFor thoracic injury risk probability, D indicates dummy model breast compressions amount；
Neck injury index is calculated by following formula:
In formula,Pneck_T, Pneck_CThe respectively damage probability on neck top, damage probability in the middle part of neck with
And the damage probability of neck lower part, Nij, T, C respectively indicate the upper, middle and lower of neck, so can effectively will collision
The most important site tissue damage situation of occupant carries out the effective side for calculating and analyzing, and passing through comparison significant points index in accident
Formula effectively judges that benchmark model, close to situation, avoids because benchmark model and actual tests are poor with actual tests process
Not the problem of not excessive caused optimized parameter finally obtained does not meet actual conditions.
As a kind of improved specific embodiment, the step of position of prediction occupant's head, is specifically wrapped in the step 3
It includes as follows:
The distance between occupant's head and steering wheel are divided into 5 sections by step 3 one, are defined as the region region 1- 5 as SVM points
Label in class；
Step 3 two using the different collision deceleration value of computer installation and is emulated, and training and the verifying number of SVM are obtained
According to the training and verify data that then basis is got determine which label occupant's head position is in, through the above steps, just
The position and specific head region of occupant, tool can be effectively predicted using supporting vector machine model (abbreviation SVM)
Body is to remove safety belt module before benchmark model use, obtains the occupant restraint system benchmark model without safety belt.So
The braking deceleration in benchmark model is configured afterwards, simulates the braking deceleration of emergency braking system.Deceleration, which is arranged, is
ai=i*0.1g, i=1 ..., 10, wherein g=9.8m/s2, braking the continued deceleration time be 1s, to this 10 groups of setting values into
Row emulation, the region where record braking deceleration value, braking deceleration time and occupant's head, can obtain training and verifying
Data set.The training set of acquisition is trained using formula (4)-(7), is obtained classification function f (x).Then verifying is utilized
Data set verifies the classifying quality of classification function f (x), defines the ratio of the sample correctly classified and verifying lump sample
For accuracy rate PcorrectIf Pcorrect> 90%, then it is assumed that model can be used.If Pcorrect< 90%, it needs to adjust again
σ and C in whole SVM model, and be trained again until the precision of SVM meets the requirements, and are carrying out SVM prediction occupant position
Needing to carry out SVM training operation, training process during setting are as follows: the assorting process in the present invention is more assorting processes, in order to
Convenient for explanation, training method is illustrated using two classification problems, more classification problems can be analogized.For svm classifier
Problem can form optimization problem solving:
And meet:
Wherein α=(α1,...αm) indicate Lagrange factor vector；M indicates the sample of m；C indicates model parameter；xiIt indicates
The feature vector of i-th of sample is expressed as braking deceleration and braking time length, y in the present embodimentiIndicate i-th sample
This label indicates the region where occupant's head in the present embodiment；K(xi,xj)=exp [- (xi-xj)*2σ2] indicate core letter
Number, σ indicate kernel functional parameter.
After solving outgoing vector α using majorized function, ω * and b* can be acquired using formula, and then acquire decision function f
(x)。
In formula, S is the number of supporting vector
F (x)=sign (w*x+b*) (7)
In formula,The model of acquisition is verified using the data sample except m, works as accuracy
When being less than 90%, the parameter σ and C of SVM is readjusted, is moved in circles, until accuracy is more than 90%, at this time
Prediction model is considered more accurate, completes just to will do it prediction later in SVM training, predicts process are as follows: when acquisition one
New data (xnew,ynew) after, the classification of new data can be determined using decision function f (x).
As a kind of improved specific embodiment, the selecting step of the optimal protection zone in the step 4 is as follows:
The head position of occupant's model is separately adjusted to angularly the middle position in 5 regions by step 4 one, carries out computer simulation；
Step 4 two calculates complex damage function Pcombine=1- (1-Phead)(1-Pneck)(1-Pchest) size；
Step 4 three chooses PcombineMinimum value so can effectively select optimal protection zone as optimal protection zone
Domain, such control parameter can be referred to according to optimal protection zone, obtain optimal control parameter.
In conclusion the means of defence of the present embodiment, is based on SVM machine learning algorithm, preferably solves automatic emergency
Braking system and air bag system Collaborative Control problem are perfect not fasten the safety belt occupant's under automatic emergency systemic effect
Means of defence solves the problems, such as this incomplete problem in method at present.
The above is only a preferred embodiment of the present invention, protection scope of the present invention is not limited merely to above-mentioned implementation
Example, all technical solutions belonged under thinking of the present invention all belong to the scope of protection of the present invention.It should be pointed out that for the art
Those of ordinary skill for, several improvements and modifications without departing from the principles of the present invention, these improvements and modifications
It should be regarded as protection scope of the present invention.
Claims (6)
1. the occupant restraint method of integrated vehicle automatic emergency brake and air bag system, it is characterised in that: including walking as follows
It is rapid:
Step 1 establishes occupant restraint system benchmark model；
Step 2 tests the damage criterion for the benchmark model that step 1 is established, judges that damage criterion is with test result
It is no consistent, continue next step if consistent, if inconsistent return step one re-establishes benchmark model；
Step 3 utilizes SVM model prediction occupant's head position；
Step 4 judges the accuracy that the occupant's head position come is predicted in step 3, judges the accuracy of prediction
Whether more than 90%, optimal protection zone is chosen if more than 90%, is predicted again if being less than 90% return step three；
Step 5, using the optimal protection zone chosen in step 4 as constraint condition, is set simultaneously when crashing
Determine automatic emergency brake deceleration constraint condition, under two constraint condition, solving optimization objective function solves maximum collision
Amount of speed reduction, and optimize to obtain the optimal control parameter A of emergency braking systempre_decelerationWith Tbrake_time, and will
Obtained optimal control parameter is input in brake system, driving brake system acting；
Wherein, Apre_decelerationFor optimal brake deceleration degree, Tbrake_timeFor optimal braking time.
2. the occupant restraint method of integrated vehicle automatic emergency brake and air bag system according to claim 1,
Be characterized in that: the step of occupant restraint system benchmark model is established in the step 1 specifically comprises the following steps:
Step 1 one, setting instrument board, steering wheel, air bag, dummy model, safe band model and automobile chair model, instrument
Dial plate, steering wheel use multi-body Dynamics Model, and air bag, dummy model, safe band model and automobile chair model use
Finite element model；
Step 1 two carries out set according to model set in step 1 one and constitutes benchmark model.
3. the occupant restraint method of integrated vehicle automatic emergency brake and air bag system according to claim 1 or 2,
It is characterized by: the test procedure in the step 2 specifically comprises the following steps:
Step 2 one carries out computer simulation to model, extracts the damage of dummy's each section after establishing benchmark model
Hurt index；
Step 2 two gets the damage criterion that practical dummy is subjected to by real vehicle trolley test；
Damage criterion obtained in step 2 one and step 2 two is compared by step 2 three, and judges two damages
Hurt whether index is consistent, completes the test to damage criterion.
4. the occupant restraint method of integrated vehicle automatic emergency brake and air bag system according to claim 3,
Be characterized in that: the damage criterion in the step 2 includes head injury criterion, thoracic injury index and neck injury index,
Middle head injury criterion is calculated by following formula:
In formula, HIC15For head injury criterion, t2-t1For 15ms, PheadFor head injury risk probability, t damage generate when
Between；
Thoracic injury index is calculated by following formula:
In formula, PchestFor thoracic injury risk probability, D indicates dummy model breast compressions amount；
Neck injury index is calculated by following formula:
In formula, Pneck_Nij, Pneck_T, Pneck_CThe respectively damage probability on neck top, damage probability and neck in the middle part of neck
The damage probability in subordinate portion, Nij, T, C respectively indicate the upper, middle and lower of neck.
5. the occupant restraint method of integrated vehicle automatic emergency brake and air bag system according to claim 1 or 2,
It is characterized by: being specifically included the step of the position of prediction occupant's head in the step 3 as follows:
The distance between occupant's head and steering wheel are divided into 5 sections by step 3 one, are defined as the region region 1- 5 as SVM points
Label in class；
Step 3 two using the different collision deceleration value of computer installation and is emulated, and training and the verifying number of SVM are obtained
According to the training and verify data that then basis is got determine which label occupant's head position is in.
6. the occupant restraint method of integrated vehicle automatic emergency brake and air bag system according to claim 1 or 2,
It is characterized by: the selecting step of the optimal protection zone in the step 4 is as follows:
The head position of occupant's model is separately adjusted to angularly the middle position in 5 regions by step 4 one, carries out computer simulation；
Step 4 two calculates complex damage function Pcombine=1- (1-Phead)(1-Pneck)(1-Pchest) size；
Step 4 three chooses PcombineMinimum value is as optimal protection zone.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910020502.3A CN109738205B (en) | 2019-01-09 | 2019-01-09 | Passenger protection method integrating automatic emergency braking of vehicle and safety air bag system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910020502.3A CN109738205B (en) | 2019-01-09 | 2019-01-09 | Passenger protection method integrating automatic emergency braking of vehicle and safety air bag system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109738205A true CN109738205A (en) | 2019-05-10 |
| CN109738205B CN109738205B (en) | 2020-06-30 |
Family
ID=66364113
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910020502.3A Expired - Fee Related CN109738205B (en) | 2019-01-09 | 2019-01-09 | Passenger protection method integrating automatic emergency braking of vehicle and safety air bag system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109738205B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110766213A (en) * | 2019-10-15 | 2020-02-07 | 清华大学 | Automobile passenger collision damage prediction method and computer equipment |
| WO2021072923A1 (en) * | 2019-10-16 | 2021-04-22 | 清华大学 | Collision severity prediction method for passenger injury risk |
| CN113188807A (en) * | 2021-02-05 | 2021-07-30 | 深圳大雷汽车检测股份有限公司 | Abs result automatic judging algorithm |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN200974518Y (en) * | 2005-11-04 | 2007-11-14 | 福特全球技术公司 | Safety gasbag system for off-position occupant protection and self-adaptive gas discharging |
| CN203063888U (en) * | 2012-12-20 | 2013-07-17 | 浙江吉利汽车研究院有限公司杭州分公司 | Protective device for automobile back row passengers |
| CN104986141A (en) * | 2015-06-16 | 2015-10-21 | 同济大学 | Active collision-prevention method and device for passenger in vehicle |
| US20170028957A1 (en) * | 2015-07-29 | 2017-02-02 | Hyundai Mobis Co., Ltd. | Cushion for driver airbag apparatus |
| CN106904143A (en) * | 2015-12-23 | 2017-06-30 | 上海汽车集团股份有限公司 | The guard method of a kind of pedestrian and passenger, system and controller |
| CN107907344A (en) * | 2017-10-25 | 2018-04-13 | 吉利汽车研究院（宁波）有限公司 | A kind of pedestrian AEB system test platforms |
| CN108394369A (en) * | 2017-02-07 | 2018-08-14 | 丰田自动车株式会社 | Passenger restraint system for vehicle |
-
2019
- 2019-01-09 CN CN201910020502.3A patent/CN109738205B/en not_active Expired - Fee Related
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN200974518Y (en) * | 2005-11-04 | 2007-11-14 | 福特全球技术公司 | Safety gasbag system for off-position occupant protection and self-adaptive gas discharging |
| CN203063888U (en) * | 2012-12-20 | 2013-07-17 | 浙江吉利汽车研究院有限公司杭州分公司 | Protective device for automobile back row passengers |
| CN104986141A (en) * | 2015-06-16 | 2015-10-21 | 同济大学 | Active collision-prevention method and device for passenger in vehicle |
| US20170028957A1 (en) * | 2015-07-29 | 2017-02-02 | Hyundai Mobis Co., Ltd. | Cushion for driver airbag apparatus |
| CN106904143A (en) * | 2015-12-23 | 2017-06-30 | 上海汽车集团股份有限公司 | The guard method of a kind of pedestrian and passenger, system and controller |
| CN108394369A (en) * | 2017-02-07 | 2018-08-14 | 丰田自动车株式会社 | Passenger restraint system for vehicle |
| CN107907344A (en) * | 2017-10-25 | 2018-04-13 | 吉利汽车研究院（宁波）有限公司 | A kind of pedestrian AEB system test platforms |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110766213A (en) * | 2019-10-15 | 2020-02-07 | 清华大学 | Automobile passenger collision damage prediction method and computer equipment |
| WO2021072923A1 (en) * | 2019-10-16 | 2021-04-22 | 清华大学 | Collision severity prediction method for passenger injury risk |
| CN113188807A (en) * | 2021-02-05 | 2021-07-30 | 深圳大雷汽车检测股份有限公司 | Abs result automatic judging algorithm |
| CN113188807B (en) * | 2021-02-05 | 2024-05-03 | 深圳大雷汽车检测股份有限公司 | Automatic abs result judging algorithm |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109738205B (en) | 2020-06-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105620480B (en) | Intelligent vehicle independence lane-change opportunity decision-making technique | |
| CN109738205A (en) | The occupant restraint method of integrated vehicle automatic emergency brake and air bag system | |
| CN110851958B (en) | Collision severity prediction method for passenger injury risk | |
| CN108960065A (en) | A kind of driving behavior detection method of view-based access control model | |
| Deng et al. | Finite element analysis of occupant head injuries: Parametric effects of the side curtain airbag deployment interaction with a dummy head in a side impact crash | |
| CN105912806B (en) | A kind of small overlapping impact air bag control method based on Adaptive Neural-fuzzy Inference | |
| Katsuhara et al. | Impact kinematics of cyclist and head injury mechanism in car-to-bicycle collision | |
| Gao et al. | A study on the cyclist head kinematic responses in electric-bicycle-to-car accidents using decision-tree model | |
| JP2020061088A (en) | Collision injury prediction model creation method, collision injury prediction method, collision injury prediction system, and advanced automatic accident notification system | |
| CN110766213A (en) | Automobile passenger collision damage prediction method and computer equipment | |
| Isaksson-Hellman et al. | How thirty years of focused safety development has influenced injury outcome in Volvo cars | |
| Jones et al. | A semi-automated approach to real world motor vehicle crash reconstruction using a generic simplified vehicle buck model | |
| Ellway et al. | The development of a Euro NCAP far side occupant test and assessment procedure | |
| Reiterer et al. | Beyond-design-basis evaluation of advanced driver assistance systems | |
| Kuehn et al. | Assessment of vehicle related pedestrian safety | |
| Duma et al. | Analysis of pregnant occupant crash exposure and the potential effectiveness of four-point seatbelts in far side crashes | |
| Hu et al. | A new prototype 4-point seatbelt design to help improve occupant protection in frontal oblique crashes | |
| Kawabe et al. | Different factors influencing post-crash pedestrian kinematics | |
| Namiki et al. | A computer simulation for motorcycle rider injury evaluation in collision | |
| Ressi et al. | Key injury regions for passenger car drivers in frontal crashes: A comparison of results from IGLAD and finite element simulations using a human body model | |
| Perticone et al. | An enhanced method for evaluating the effectiveness of protective devices for road safety application | |
| Dalrymple | Effects of assistive steering devices on air bag deployment | |
| Yang et al. | Restraint System Optimizations Using Diverse Human Body Models in Frontal Crashes | |
| Klinich et al. | Potential safety effects of low-mass vehicles with comprehensive crash avoidance technology | |
| Han et al. | Development of a head-weighted injury criterion for evaluation of multiple types of AIS 4+ injuries for vulnerable road users |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20200630 Termination date: 20220109 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |