CN111951430A - Vehicle drivability evaluation method and system - Google Patents

Vehicle drivability evaluation method and system Download PDF

Info

Publication number
CN111951430A
CN111951430A CN201910359008.XA CN201910359008A CN111951430A CN 111951430 A CN111951430 A CN 111951430A CN 201910359008 A CN201910359008 A CN 201910359008A CN 111951430 A CN111951430 A CN 111951430A
Authority
CN
China
Prior art keywords
sub
evaluation
condition
drivability
vehicle
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
Application number
CN201910359008.XA
Other languages
Chinese (zh)
Other versions
CN111951430B (en
Inventor
曹昱聪
范良明
吴健瑜
梅兴泰
王师
林长青
曹勇
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangzhou Automobile Group Co Ltd
Original Assignee
Guangzhou Automobile Group Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Guangzhou Automobile Group Co Ltd filed Critical Guangzhou Automobile Group Co Ltd
Priority to CN201910359008.XA priority Critical patent/CN111951430B/en
Publication of CN111951430A publication Critical patent/CN111951430A/en
Application granted granted Critical
Publication of CN111951430B publication Critical patent/CN111951430B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
    • G07C5/00—Registering or indicating the working of vehicles
    • G07C5/08—Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W50/04—Monitoring the functioning of the control system
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques

Landscapes

  • Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Engineering & Computer Science (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Human Computer Interaction (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Combined Controls Of Internal Combustion Engines (AREA)

Abstract

The invention provides a vehicle drivability evaluation method and a vehicle drivability evaluation system, wherein the method includes the steps of: acquiring a working condition parameter set corresponding to a sub-operation working condition of the current driving working condition of the vehicle, wherein the working condition parameter set is formed by all working condition parameters belonging to the same sub-operation working condition; and obtaining a driving performance evaluation result of the current sub-operation working condition according to the working condition parameter set and the vehicle driving performance evaluation model, wherein the evaluation model is established according to a subjective driving performance evaluation result and an objective driving performance evaluation result of the vehicle. The evaluation method can improve the objectivity and the accuracy of the vehicle drivability evaluation result, and solves the problems of low repeatability, strong individual feeling dependence on a test driver and inaccurate and inconsistent vehicle drivability evaluation results in subjective drivability evaluation. In addition, the evaluation method can also accurately and objectively optimize the driving performance of the vehicle in real time and realize real-time adjustment of the dynamic performance.

Description

Vehicle drivability evaluation method and system
Technical Field
The invention relates to the technical field of vehicle drivability evaluation, in particular to a vehicle drivability evaluation method and a vehicle drivability evaluation system.
Background
Along with the market competition aggravation and the continuous improvement of the requirements of consumers on the vehicle driving feeling, each mainstream vehicle factory pays more attention to the driving performance of the vehicle under different driving conditions, and correspondingly formulated working condition indexes are more and more detailed. Therefore, the research on the vehicle drivability evaluation method is not only beneficial to comprehensively and accurately improving the driving experience of consumers, but also accords with the development direction of the automobile industry.
Vehicle drivability is generally used to evaluate the subjective driving feeling of a driver during longitudinal driving of an automobile. At present, some research and discussion have been carried out on the development modes of vehicle drivability evaluation systems by relevant automobile enterprises and automobile consulting service companies at home and abroad, and subjective drivability evaluation data of professional drivers are mainly used as a unique reference for triggered drivability index evaluation scores. However, subjective drivability evaluation has the characteristics of low repeatability, strong dependence on individual experience of a test driver, and the like. So that the results of subjective drivability assessment by professional drivers are not always consistent and accurate and reliable. If the subjective drivability evaluation data is directly used for establishing a drivability evaluation system, the correlation between the data result of the subjective drivability evaluation and the objective test data quantization relationship is likely to generate inconsistent results due to the subjective difference of the driver.
Disclosure of Invention
The invention aims to provide a drivability evaluation method and a system thereof to solve the problem of inconsistent subjective and objective drivability evaluations in the prior art.
In order to solve the above technical problem, the present invention provides a vehicle drivability evaluation method, including:
acquiring a working condition parameter set corresponding to a sub-operation working condition under the current driving working condition of the vehicle, wherein the working condition parameter set is formed by all working condition parameters belonging to the same sub-operation working condition;
and obtaining a driving performance evaluation result of the current sub-operation working condition according to the working condition parameter set and the vehicle driving performance evaluation model, wherein the evaluation model is established according to a subjective driving performance evaluation result and an objective driving performance evaluation result of the vehicle.
The establishing of the evaluation model according to the subjective drivability evaluation result and the objective drivability evaluation result of the vehicle specifically includes:
acquiring working condition parameter sets corresponding to all sub-operating conditions under which the subjective drivability evaluation and the objective drivability evaluation of the vehicle are consistent under different driving conditions;
establishing an initial model for evaluating the drivability of the sub-operating condition of the vehicle;
and training the initial evaluation model by using the working condition parameter set corresponding to each sub-operation working condition with the consistent subjective drivability evaluation and objective drivability evaluation to obtain an evaluation model.
Before obtaining the working condition parameter set corresponding to each sub-operation working condition with the consistent subjective drivability evaluation and objective drivability evaluation, the method further comprises the following steps:
collecting vehicle signals related to vehicle drivability evaluation, and evaluating the vehicle signals to obtain processed vehicle signals;
calculating working condition parameters corresponding to each sub-operation working condition of the vehicle under different driving working conditions according to the processed vehicle signals to form working condition parameter sets corresponding to the sub-operation working conditions;
obtaining objective drivability evaluation results of the sub-operation conditions according to the condition parameter sets corresponding to the sub-operation conditions;
obtaining subjective drivability evaluation results of each sub-operation condition of the vehicle under different driving conditions;
and screening a working condition parameter set corresponding to the sub-operation working condition with the subjective drivability evaluation result consistent with the objective drivability evaluation result.
Wherein, the obtaining the objective drivability evaluation result of each sub-operation condition according to the condition parameter set corresponding to the sub-operation condition specifically includes:
setting a reference parameter set corresponding to each evaluation level of each sub-operation condition under each driving condition in subjective drivability evaluation, and taking the reference parameter set as a central point of a clustering center;
selecting a plurality of working condition parameter sets of different sub-operating working conditions of the vehicle under the same driving working condition as sample points of sample data, and performing cluster evaluation on the sample data to obtain an objectivity driving evaluation result of each sub-operating working condition.
The clustering evaluation of the sample data to obtain an objectivity driving evaluation result of each sub-operation condition specifically comprises:
calculating Euclidean distances from each sample point in the sample data to each central point of a cluster center, and defining a target function and a constraint condition according to the Euclidean distances;
solving the objective function according to the constraint condition to obtain the confidence level that each sample point belongs to each clustering center;
and selecting the evaluation grade corresponding to the clustering center with the maximum confidence level as an objective drivability evaluation result of the sub-operation working condition corresponding to the sample point.
Wherein, the objective function and the constraint condition are specifically:
Figure BDA0002046317420000031
Figure BDA0002046317420000032
Figure BDA0002046317420000033
Figure BDA0002046317420000034
wherein J is an objective function, xkiFor the kth sample point X in the sample datakThe ith operating condition parameter of (1); r isjiEvaluation grade R of each sub-operation condition set in subjective driving evaluation processjOf the i-th operating condition parameter, ωkjIs a sample point XkBelonging to a cluster center point RjM is the total number of evaluation levels of the sub-operation condition, l is the number of sample points, n is the number of condition parameters in the condition parameter set corresponding to the sub-operation condition, lambda isjIn order to be a lagrange multiplier,
Figure BDA0002046317420000035
the establishing of the initial model for evaluating the drivability of the vehicle specifically includes: the initial evaluation model established by adopting the feedforward artificial neural network of the single hidden layer is as follows:
Figure BDA0002046317420000036
wherein f (z) is the result of the evaluation of the drivability, z is the working condition parameter set of the corresponding sub-operating working condition, βqAs output weight, hqAnd L is the number of hidden layer nodes.
Wherein the method further comprises:
and evaluating the vehicle drivability performance on line by using the evaluation model, comparing the drivability evaluation result output by the evaluation model with the subjective drivability evaluation result in the sub-operation condition that the vehicle subjective drivability evaluation is consistent with the objective drivability evaluation, and verifying the accuracy of the evaluation model.
Wherein the method further comprises
Acquiring the drivability evaluation result of each sub-operation condition under the same driving condition;
calculating the drivability evaluation result of the driving condition according to the drivability evaluation of each sub-operation condition, and calculating the request torque of the engine according to the drivability evaluation result of the driving condition;
and adjusting the vehicle engine torque according to the requested torque of the engine.
Wherein, the calculating the drivability evaluation result of the driving condition according to the drivability evaluation of each sub-operation condition, and the calculating the requested torque of the engine according to the drivability evaluation result of the driving condition specifically includes:
acquiring the current engine expected torque of the vehicle and the weight coefficient of each sub-operation condition under the same driving condition;
calculating the drivability evaluation of the driving condition according to the weight coefficient and the drivability evaluation of each sub-operation condition;
calibrating an adjustment factor of the requested torque of the engine according to the weight coefficient relation and the drivability evaluation of the driving condition;
and calculating to obtain the requested torque of the engine through the adjusting factor and the engine expected torque.
The calculation of the drivability evaluation of the driving condition according to the weighting system and the drivability evaluation specifically includes:
Figure BDA0002046317420000041
Figure BDA0002046317420000042
P＝diag(p1 p2 … pt)
wherein U is the drivability evaluation of the driving condition, t is the number of sub-operating conditions considered in the driving condition, ptIs a weight coefficient, s, of a certain operating sub-conditiontDriving evaluation results for the sub-operating conditions;
the calculation of the requested torque of the engine through the adjustment factor and the engine expected torque is specifically as follows:
Treq＝μTexp
wherein, TexpTorque expected for the engine, TreqMu is the adjustment factor for the requested torque of the engine.
The present invention also provides a vehicle drivability evaluation system including:
the system comprises a working condition parameter set acquisition unit, a driving condition parameter set acquisition unit and a driving condition parameter set acquisition unit, wherein the working condition parameter set acquisition unit is used for acquiring a working condition parameter set corresponding to a sub-operation working condition of the current driving condition of the vehicle, and the working condition parameter set is formed by a plurality of working condition parameters belonging to the same sub-operation working condition;
and the evaluation result analysis unit is used for obtaining a driving performance evaluation result of the current sub-operation working condition according to the working condition parameter set and the vehicle driving performance evaluation model, wherein the evaluation model is established according to the subjective driving performance evaluation result and the objective driving performance evaluation result of the vehicle.
The embodiment of the invention has the beneficial effects that: according to the vehicle drivability evaluation method, the parameter set corresponding to the sub-operation condition with consistent subjective drivability evaluation and objective drivability evaluation is selected to be used for training the model to obtain the drivability evaluation model. In addition, the evaluation method can also accurately and objectively optimize the driving performance of the vehicle in real time and realize real-time adjustment of the dynamic performance.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flow chart of a vehicle drivability evaluation method according to an embodiment of the present invention.
Fig. 2 is a schematic flow chart of a drivability evaluation model establishing method according to an embodiment of the present invention.
Fig. 3 is an analysis diagram illustrating an objective drivability evaluation result obtained by the vehicle drivability evaluation method according to the embodiment of the present invention.
Detailed Description
The following description of the embodiments refers to the accompanying drawings, which are included to illustrate specific embodiments in which the invention may be practiced.
As described below with reference to fig. 1, an embodiment of the present invention provides a vehicle drivability evaluation method, including:
and S1, acquiring a working condition parameter set corresponding to the sub-operation working condition of the current driving working condition of the vehicle, wherein the working condition parameter set is formed by all working condition parameters belonging to the same sub-operation working condition.
And S2, obtaining a driving performance evaluation result of the current sub-operation working condition according to the working condition parameter set and the vehicle driving performance evaluation model, wherein the evaluation model is established according to the subjective driving performance evaluation result and the objective driving performance evaluation result of the vehicle.
The method of establishing the evaluation model is specifically described below with reference to fig. 2:
and S21, acquiring working condition parameter sets corresponding to the sub-operating working conditions under which the subjective drivability evaluation and the objective drivability evaluation of the vehicle are consistent under different driving working conditions.
Specifically, subjective drivability evaluation results of different sub-operation conditions under different driving conditions are obtained. The subjective drivability evaluation result is derived from subjective drivability evaluation of professional drivers under different driving conditions and different sub-operation conditions, the professional drivers of different ages and different sexes perform multiple driving experiences on automobiles of different grades and different manufacturers, and the drivability of different sub-operation conditions under different driving conditions is evaluated and scored in a report form. Specifically, the drivability evaluation is classified into ten grades in order of "very good", "satisfactory", "not satisfactory", "disturbing", "insufficient", "poor", "very poor", and "unacceptable".
Specifically, vehicle information related to drivability evaluation of a vehicle is collected, and the vehicle information covers various sensor signal feedbacks and other signals related to vehicle drivability, wherein most signals such as engine speed, vehicle speed and pedal position CAN be directly read from a vehicle CAN bus. In order to meet the requirements of different working condition indexes on different signal characteristic emphasis parts, a specific part in a vehicle longitudinal acceleration signal needs to be selectively restrained or enhanced so as to highlight the characteristics of the concerned part. Therefore, in the aspect of the longitudinal acceleration of the vehicle, the original signal data is acquired by externally connecting the vehicle acceleration sensor and the vehicle deceleration sensor separately, and then the original signal data is processed corresponding to different working condition indexes. In addition, after the collected signal data of the vehicle acceleration and deceleration sensor is evaluated, the influence of the usage of related algorithms such as data filtering and smoothing on the measurement precision and linearity should be fully evaluated. After the vehicle information related to the vehicle driving performance is obtained, different driving working conditions are taken as entry points, different operation sub-working conditions under the same driving working condition are considered, a plurality of working condition index parameters corresponding to the different operation sub-working conditions are subdivided, for different working condition indexes, if and only if trigger conditions are met, the working condition indexes are activated to perform related calculation, and corresponding working condition index parameters are output. And the working condition index which is not triggered keeps silent and does not output. Taking the full-throttle operation sub-working condition in the acceleration driving working condition as an example, the full-throttle operation sub-working condition relates to 11 working condition parameters such as expected torque, reference acceleration, rotating speed limit, surge, torque smoothness and the like. Corresponding to each working condition index, there are corresponding detailed rules, and corresponding different calculation modes and trigger conditions. The 11 operating condition parameters form a set of operating condition parameters for the full throttle operating sub-condition. After the working condition parameter sets corresponding to the sub-operating conditions are obtained, in order to quantify the drivability of the sub-operating conditions corresponding to the parameter sets, the working condition parameter sets under the same driving condition are used as sample points of sample data, reference working condition parameter sets corresponding to evaluation grades of the sub-operating conditions under each driving condition in subjective driving evaluation are set, the reference working condition parameter sets are used as initial clustering centers, Euclidean distances from the sample points in the sample data to the clustering centers are calculated, an objective function is established according to the Euclidean distances, the objective function is solved to obtain the confidence level of each sample point in each clustering center, and the objective evaluation result of each sample point is obtained according to the confidence level.
For example, as shown in fig. 3, it is assumed that a driving condition includes sub-operating conditions S1 and S2 …, and each sub-operating condition is evaluated into 10 levels, which are respectively assumed to be R00-R09In total, 10 levels are provided, and the reference working condition parameter set of each level is rjiWherein j is the number of evaluation levels of the sub-operation condition, and i is the number of condition parameters in the condition parameter set of the sub-operation condition. Selecting a plurality of parameter sets of different sub-operation conditions under the same driving condition to form sample data, wherein the sample points are X1, X2 and … Xk …; the operating condition parameter set corresponding to each sample point is xkiCalculating the Euclidean distance from each sample point in each sample data to each cluster center, and defining an objective function according to the Euclidean distance, specifically:
Figure BDA0002046317420000081
Figure BDA0002046317420000082
wherein J is an objective function, l is the number of sample points in the sample data, n is the number of reference parameters in the reference parameter set corresponding to the sub-operation condition, J is the number of evaluation levels of the sub-operation condition, xkiIs the midpoint X of the sample datakThe ith working condition index parameter of (1); r isjiEvaluation of midpoint R for sub-operating conditionsjThe i-th operating condition index parameter of (1), wherein,
Figure BDA0002046317420000083
is the euclidean distance.
Introducing a Lavarez equation, and converting an objective function into:
Figure BDA0002046317420000084
in order to solve the extreme value of the objective function, the variables ω in the extreme value need to be respectively solvedkjAnd rjiThe derivation is as follows:
Figure BDA0002046317420000085
Figure BDA0002046317420000086
therefore, ωkfAnd rjiThe analytical solutions of (a) are respectively:
Figure BDA0002046317420000087
Figure BDA0002046317420000088
in the formula (I), the compound is shown in the specification,
Figure BDA0002046317420000089
calculated by multiple iterationsTo omegakjAnd rji. Comparison Point (X)k) Belonging to respective central points (R)j) Confidence level of ωkjJ is 1, 2. The evaluation level of the operation condition of the sub-operation of the correlation having the high confidence level is selected as the point (X)k) And evaluating the result of the quantized sub-operation condition of the objective data.
And S22, establishing an initial model for evaluating the drivability evaluation result of the sub-operation condition of the vehicle.
Modeling a drivability evaluation model by adopting a single hidden layer feedforward artificial neural network, wherein the initial model is as follows:
Figure BDA00020463174200000810
wherein f (z) is the output of the neural network, βqAs output weight, hqThe node is output for a hidden layer node, and L is the number of the hidden layer nodes; z is the input to the neural network.
And S23, training the initial model by using the working condition parameter set corresponding to each sub-operation working condition with the consistent subjective drivability evaluation and objective drivability evaluation to obtain an evaluation model.
And inputting the working condition parameter set corresponding to the sub-operation working condition with the objective drivability evaluation result and the subjective drivability evaluation result consistent into the initial model, and training the initial model to obtain an evaluation model.
The method further comprises the steps of evaluating the drivability on line by using the final model, comparing drivability performance obtained by the evaluation model with a result of subjective drivability evaluation in a sub-operation condition where the vehicle subjective drivability evaluation is consistent with the objective drivability evaluation, and verifying the accuracy of the evaluation model.
In a specific embodiment, the evaluation method further comprises: the method comprises the steps of obtaining driving performance evaluation of a vehicle under different sub-operation working conditions, calculating a driving performance evaluation result of the driving working conditions of the vehicle according to the driving performance evaluation under the different sub-operation working conditions, calculating and obtaining a request torque of an engine according to the driving performance evaluation result of the driving working conditions, and adjusting the torque of the engine of the vehicle according to the request torque of the engine.
Specifically, to represent the relative degree of importance between the different sub-operating conditions, a weighting parameter P is introduced:
P＝diag(p1 p2 … pt)
wherein t is the number of sub-operating conditions considered under a certain driving condition; p is a radical oftIs the weight coefficient of a certain sub-operation condition.
The drivability evaluation U for the driving condition is defined as:
Figure BDA0002046317420000091
in the formula (I), the compound is shown in the specification,
Figure BDA0002046317420000093
stand evaluating the result of the drivability evaluation model under a certain operation sub-condition.
Finally, calibrating the adjustment factor in an experimental mode (as shown in the following table 1) according to different weight coefficient relationships and the drivability evaluation result of the driving condition.
TABLE 1 adjustment factor calibration
Figure BDA0002046317420000092
Figure BDA0002046317420000101
Wherein, relation 1: p is a radical of1＞p2＞p3…, relationship 2: p is a radical of2＞p1＞p3…, relationship 3: p is a radical of2＞p1＞p3…。
Applying the calibrated adjustment factor to the online torque request TreqThe calculation of (2):
Treq＝μTexp
in the formula, TexpThe torque is expected for the engine, and is determined by the accelerator opening degree, and μ is an adjustment factor.
According to the vehicle drivability evaluation method, the parameter set corresponding to the sub-operation condition with consistent subjective drivability evaluation and objective drivability evaluation is selected to be used for training the model to obtain the drivability evaluation model. In addition, the evaluation method can also accurately and objectively optimize the driving performance of the vehicle in real time and realize real-time adjustment of the dynamic performance.
Based on the first embodiment of the present invention, a second embodiment of the present invention provides a vehicle drivability evaluation system, including:
the system comprises a working condition parameter set acquisition unit, a driving condition parameter set acquisition unit and a driving condition parameter set acquisition unit, wherein the working condition parameter set acquisition unit is used for acquiring a working condition parameter set corresponding to a sub-operation working condition of the current driving condition of the vehicle, and the working condition parameter set is formed by a plurality of working condition parameters belonging to the same sub-operation working condition;
and the evaluation result analysis unit is used for obtaining a driving performance evaluation result of the current sub-operation working condition according to the working condition parameter set and the vehicle driving performance evaluation model, wherein the evaluation model is established according to the subjective driving performance evaluation result and the objective driving performance evaluation result of the vehicle.
The above disclosure is only for the purpose of illustrating the preferred embodiments of the present invention, and it is therefore to be understood that the invention is not limited by the scope of the appended claims.

Claims (12)

1. A vehicle drivability evaluation method characterized by comprising the steps of:
acquiring a working condition parameter set corresponding to a sub-operation working condition of the current driving working condition of the vehicle, wherein the working condition parameter set is formed by all working condition parameters belonging to the same sub-operation working condition;
and obtaining a driving performance evaluation result of the current sub-operation working condition according to the working condition parameter set and the vehicle driving performance evaluation model, wherein the evaluation model is a model established according to a subjective driving performance evaluation result and an objective driving performance evaluation result of the vehicle.
2. The method of claim 1, wherein: the establishing of the evaluation model according to the subjective drivability evaluation result and the objective drivability evaluation result of the vehicle specifically includes:
acquiring working condition parameter sets corresponding to all sub-operating conditions under which the subjective drivability evaluation and the objective drivability evaluation of the vehicle are consistent under different driving conditions;
establishing an initial model for evaluating the drivability evaluation result of the sub-operation condition of the vehicle;
and training the initial model by using the working condition parameter set corresponding to each sub-operation working condition with consistent subjective drivability evaluation and objective drivability evaluation to obtain the evaluation model.
3. The method according to claim 2, further comprising, before obtaining the set of operating condition parameters corresponding to the sub-operating conditions for which the subjective drivability assessment is consistent with the objective drivability assessment:
collecting vehicle signals related to vehicle drivability evaluation, and evaluating the vehicle signals to obtain processed vehicle signals;
calculating working condition parameters corresponding to each sub-operation working condition of the vehicle under different driving working conditions according to the processed vehicle signals to form working condition parameter sets corresponding to the sub-operation working conditions;
obtaining objective drivability evaluation results of the sub-operation conditions according to the condition parameter sets corresponding to the sub-operation conditions;
obtaining subjective drivability evaluation results of each sub-operation condition of the vehicle under different driving conditions;
and screening a working condition parameter set corresponding to the sub-operation working condition with the subjective drivability evaluation result consistent with the objective drivability evaluation result.
4. The method according to claim 3, wherein the obtaining the objective drivability evaluation result of each sub-operation condition according to the condition parameter set corresponding to the sub-operation condition specifically includes:
setting a reference parameter set corresponding to each evaluation level of each sub-operation condition under each driving condition in subjective drivability evaluation, and taking the reference parameter set as a central point of a clustering center;
selecting a plurality of working condition parameter sets of different sub-operating working conditions of the vehicle under the same driving working condition as sample points of sample data, and performing cluster evaluation on the sample data to obtain an objectivity driving evaluation result of each sub-operating working condition.
5. The method according to claim 4, wherein the performing cluster evaluation on the sample data to obtain an objectivity driving evaluation result for each sub-operation condition specifically comprises:
calculating Euclidean distances from each sample point in the sample data to each central point of a cluster center, and defining a target function and a constraint condition according to the Euclidean distances;
solving the objective function according to the constraint condition to obtain the confidence level that each sample point belongs to each clustering center;
and selecting the evaluation grade corresponding to the clustering center with the maximum confidence level as an objective drivability evaluation result of the sub-operation working condition corresponding to the sample point.
6. The method of claim 5, wherein the objective function and constraint conditions are specifically:
Figure FDA0002046317410000021
Figure FDA0002046317410000022
Figure FDA0002046317410000023
wherein J is an objective function, xkiFor the kth sample point X in the sample datakThe ith operating condition parameter of (1); r isjiA j-th evaluation level R of each sub-operation condition set in the subjective driving evaluation processjOf the i-th operating condition parameter, ωkfIs a sample point XkBelonging to a cluster center point RjM is the total number of evaluation levels of the sub-operation condition, l is the number of sample points, n is the number of condition parameters in the condition parameter set corresponding to the sub-operation condition, lambda isjIn order to be a lagrange multiplier,
Figure FDA0002046317410000024
7. the method according to claim 2, wherein the initial model for evaluating the drivability evaluation result of the sub-operating condition of the vehicle is an initial evaluation model established by using a single hidden layer feedforward artificial neural network:
Figure FDA0002046317410000031
wherein f (z) is the result of drivability evaluation of the sub-operating condition, z is the set of operating condition parameters for the corresponding sub-operating condition, βqAs output weight, hqAnd L is the number of hidden layer nodes.
8. The method of claim 7, further comprising:
and evaluating the vehicle drivability performance on line by using the evaluation model, comparing the drivability evaluation result output by the evaluation model with the subjective drivability evaluation result in the sub-operation condition that the vehicle subjective drivability evaluation is consistent with the objective drivability evaluation, and verifying the accuracy of the evaluation model.
9. The method of any one of claims 1-8, further comprising
Acquiring the drivability evaluation result of each sub-operation condition under the same driving condition;
calculating the drivability evaluation result of the driving condition according to the drivability evaluation result of each sub-operation condition, and calculating the request torque of the engine according to the drivability evaluation result of the driving condition;
and adjusting the vehicle engine torque according to the requested torque of the engine.
10. The optimization method according to claim 9, wherein the calculating of the drivability evaluation result of the driving condition according to the drivability evaluation result of each sub-operation condition includes:
acquiring the current engine expected torque of the vehicle and the weight coefficient of each sub-operation condition under the same driving condition;
calculating the drivability evaluation of the driving condition according to the weight coefficient and the drivability evaluation of each sub-operation condition;
calibrating an adjustment factor of the requested torque of the engine according to the weight coefficient relation and the drivability evaluation of the driving condition;
and calculating to obtain the requested torque of the engine through the adjusting factor and the engine expected torque.
11. The optimization method according to claim 10, wherein calculating the drivability assessment of the driving profile from the weighting system and the drivability assessment specifically comprises:
Figure FDA0002046317410000041
S＝[s1 s2 … s3]T
P＝diag(p1 p2 …pt)
wherein U is the drivability evaluation of the driving condition, t is the number of sub-operating conditions considered in the driving condition, ptIs the weight coefficient of the t sub-operating condition, stDriving evaluation results for the tth sub-operation condition;
the calculation of the requested torque of the engine through the adjustment factor and the engine expected torque is specifically as follows:
Treq＝μTexp
wherein, TexpTorque expected for the engine, TreqMu is the adjustment factor for the requested torque of the engine.
12. A vehicle drivability evaluation system characterized by comprising:
the system comprises a working condition parameter set acquisition unit, a driving condition parameter set acquisition unit and a driving condition parameter set acquisition unit, wherein the working condition parameter set acquisition unit is used for acquiring a working condition parameter set corresponding to a sub-operation working condition of the current driving condition of the vehicle, and the working condition parameter set is formed by a plurality of working condition parameters belonging to the same sub-operation working condition;
and the evaluation result analysis unit is used for obtaining a driving performance evaluation result of the current sub-operation working condition according to the working condition parameter set and the vehicle driving performance evaluation model, wherein the evaluation model is established according to the subjective driving performance evaluation result and the objective driving performance evaluation result of the vehicle.
CN201910359008.XA 2019-04-30 2019-04-30 Vehicle drivability evaluation method and system Active CN111951430B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910359008.XA CN111951430B (en) 2019-04-30 2019-04-30 Vehicle drivability evaluation method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910359008.XA CN111951430B (en) 2019-04-30 2019-04-30 Vehicle drivability evaluation method and system

Publications (2)

Publication Number Publication Date
CN111951430A true CN111951430A (en) 2020-11-17
CN111951430B CN111951430B (en) 2022-04-29

Family

ID=73335456

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910359008.XA Active CN111951430B (en) 2019-04-30 2019-04-30 Vehicle drivability evaluation method and system

Country Status (1)

Country Link
CN (1) CN111951430B (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113029593A (en) * 2021-03-26 2021-06-25 奇瑞新能源汽车股份有限公司 Method and device for evaluating drivability of automobile
CN113291315A (en) * 2021-05-28 2021-08-24 中汽研（天津）汽车工程研究院有限公司 Method for automatically identifying whole vehicle drivability working conditions for multisource power assembly vehicle type
CN114103927A (en) * 2021-12-09 2022-03-01 安徽江淮汽车集团股份有限公司 Control method of double-motor series-parallel hybrid electric vehicle
CN115406670A (en) * 2022-08-16 2022-11-29 中国第一汽车股份有限公司 Vehicle performance testing method and device, electronic equipment and vehicle
WO2023051065A1 (en) * 2021-09-29 2023-04-06 华为技术有限公司 Parameter calibration method and apparatus
CN117387967A (en) * 2023-10-26 2024-01-12 麦格纳动力总成(江西)有限公司 Automobile drivability testing method and system

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1498717A2 (en) * 2003-07-15 2005-01-19 Universität Stuttgart Procedure and device for determining the crosswind behaviour of a vehicle
KR20050014605A (en) * 2003-07-31 2005-02-07 김승한 Dynamic Ride-Comfort Analysis System
CN101579232A (en) * 2008-05-14 2009-11-18 横滨橡胶株式会社 Method and system for evaluating driving conditions of a vehicle
US20130079989A1 (en) * 2011-09-23 2013-03-28 Toyota Motor Engineering & Manufacturing North America, Inc. Drivability evaluation target levels
WO2017099689A1 (en) * 2015-12-10 2017-06-15 Tofas Turk Otomobil Fabrikasi Anonim Sirketi A vehicle drivability evaluation system and method
CN107192560A (en) * 2017-05-17 2017-09-22 重庆长安汽车股份有限公司 A kind of vehicle accelerates power method for objectively evaluating
CN108072530A (en) * 2016-11-17 2018-05-25 南京依维柯汽车有限公司 A kind of automobile drives the evaluation method of performance
CN108388730A (en) * 2018-02-24 2018-08-10 北京车和家信息技术有限公司 The method of vehicle development
CN109100157A (en) * 2018-08-20 2018-12-28 中国汽车技术研究中心有限公司 One kind driving system safety testing device and method for P2 configuration hybrid vehicle

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1498717A2 (en) * 2003-07-15 2005-01-19 Universität Stuttgart Procedure and device for determining the crosswind behaviour of a vehicle
KR20050014605A (en) * 2003-07-31 2005-02-07 김승한 Dynamic Ride-Comfort Analysis System
CN101579232A (en) * 2008-05-14 2009-11-18 横滨橡胶株式会社 Method and system for evaluating driving conditions of a vehicle
US20130079989A1 (en) * 2011-09-23 2013-03-28 Toyota Motor Engineering & Manufacturing North America, Inc. Drivability evaluation target levels
WO2017099689A1 (en) * 2015-12-10 2017-06-15 Tofas Turk Otomobil Fabrikasi Anonim Sirketi A vehicle drivability evaluation system and method
CN108072530A (en) * 2016-11-17 2018-05-25 南京依维柯汽车有限公司 A kind of automobile drives the evaluation method of performance
CN107192560A (en) * 2017-05-17 2017-09-22 重庆长安汽车股份有限公司 A kind of vehicle accelerates power method for objectively evaluating
CN108388730A (en) * 2018-02-24 2018-08-10 北京车和家信息技术有限公司 The method of vehicle development
CN109100157A (en) * 2018-08-20 2018-12-28 中国汽车技术研究中心有限公司 One kind driving system safety testing device and method for P2 configuration hybrid vehicle

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
刘普辉，章桐: "汽车驾驶品质主客观测试评价及相关性分析", 《中国工程机械学报》 *

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113029593A (en) * 2021-03-26 2021-06-25 奇瑞新能源汽车股份有限公司 Method and device for evaluating drivability of automobile
CN113291315A (en) * 2021-05-28 2021-08-24 中汽研（天津）汽车工程研究院有限公司 Method for automatically identifying whole vehicle drivability working conditions for multisource power assembly vehicle type
WO2023051065A1 (en) * 2021-09-29 2023-04-06 华为技术有限公司 Parameter calibration method and apparatus
CN114103927A (en) * 2021-12-09 2022-03-01 安徽江淮汽车集团股份有限公司 Control method of double-motor series-parallel hybrid electric vehicle
CN115406670A (en) * 2022-08-16 2022-11-29 中国第一汽车股份有限公司 Vehicle performance testing method and device, electronic equipment and vehicle
CN117387967A (en) * 2023-10-26 2024-01-12 麦格纳动力总成(江西)有限公司 Automobile drivability testing method and system

Also Published As

Publication number Publication date
CN111951430B (en) 2022-04-29

Similar Documents

Publication Publication Date Title
CN111951430B (en) Vehicle drivability evaluation method and system
CN113159435B (en) Method and system for predicting remaining driving mileage of new energy vehicle
CN112115555B (en) Method for monitoring instantaneous oil consumption of automobile in intelligent networking environment
CN108920854A (en) It is a kind of based on wireless interconnected and noise inline diagnosis harmony method for evaluating quality and system of athe portable client
CN102567782A (en) Neural-network-based automobile engine torque estimation method
CN112862164B (en) Dry clutch temperature prediction method based on dynamic neural network time sequence prediction
JP7318076B1 (en) Evaluating the impact of switching working conditions on vehicle fuel consumption
CN111537888A (en) Data-driven echelon battery SOC prediction method
CN114781245B (en) Transient automobile fuel consumption estimation method and system based on fuel consumption strong correlation parameter correction
CN114329347B (en) Method and device for predicting metering error of electric energy meter and storage medium
CN116402390A (en) Road construction area traffic influence evaluation method and system based on primitive model
CN110851784A (en) Early warning method for field operation of electric energy meter
CN111027618A (en) Automobile dynamic property and economic property expectation quantification method
CN107679630A (en) Maintenance operation time estimation method based on proportional maintenance model
CN116662925A (en) Industrial process soft measurement method based on weighted sparse neural network
CN116538286A (en) Commercial vehicle gear shifting system and method considering NVH characteristics
CN114970698B (en) Metering equipment operation performance prediction method based on improved LWPS
Zhou et al. Objective Evaluation of Drivability in Passenger Cars with Dual‐Clutch Transmission: A Case Study of Static Gearshift Condition
AU2021102567A4 (en) Rapid diagnosis method of soil fertility grade based on hyperspectral data
CN116205530A (en) Urban intelligent parking planning method and system
CN115587327A (en) Automobile oil consumption prediction method considering Jerk
CN114254498A (en) Engine dynamic oil consumption prediction method and system based on BP neural network
CN110210711B (en) Electric vehicle electric energy metering accuracy assessment method
CN111507003A (en) Method for predicting key variables of debutanizer based on quality-related dynamic characteristic extraction
CN114626234B (en) Credibility evaluation method and system for digital twin combined model of equipment

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