CN113978473A - Vehicle mass and road gradient estimation method - Google Patents
Vehicle mass and road gradient estimation method Download PDFInfo
- Publication number
- CN113978473A CN113978473A CN202111417841.9A CN202111417841A CN113978473A CN 113978473 A CN113978473 A CN 113978473A CN 202111417841 A CN202111417841 A CN 202111417841A CN 113978473 A CN113978473 A CN 113978473A
- Authority
- CN
- China
- Prior art keywords
- gradient
- vehicle
- mass
- road gradient
- road
- 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
Images
Classifications
-
- 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
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/02—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to ambient conditions
- B60W40/06—Road conditions
- B60W40/076—Slope angle of the road
-
- 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
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/12—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to parameters of the vehicle itself, e.g. tyre models
- B60W40/13—Load or weight
-
- 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
- B60W2520/00—Input parameters relating to overall vehicle dynamics
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Mathematical Physics (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
Abstract
The invention relates to a vehicle mass and road gradient estimation method, which comprises the following steps: the method comprises the following steps: acquiring vehicle parameters; step two: establishing a longitudinal dynamics model related to the mass of the whole vehicle and the road gradient and a longitudinal kinematics model related to the road gradient; step three: building a gradient and quality estimator based on a longitudinal dynamics model, and estimating the gradient of the road and the vehicle; building a gradient estimator based on a longitudinal kinematics model to estimate the road gradient; step four: the gradient is fused with the results of the mass estimator and the gradient estimator, and a vehicle mass estimate and a road gradient estimate are output. The method integrates the longitudinal dynamics model of the whole vehicle mass and the road gradient and the longitudinal kinematics model related to the road gradient, can simultaneously integrate the two conditions for estimation when predicting the whole vehicle mass estimation value and the road gradient estimation value, has stronger adaptability, high estimation precision and good stability when facing the variation of the vehicle running condition.
Description
Technical Field
The invention relates to the field of parameter estimation, in particular to a method for estimating vehicle mass and road gradient.
Background
Various active safety systems are gradually increasing during vehicle modernization, but the performance of these systems depends on precise vehicle and environmental parameters. The mass of the heavy commercial vehicle can be changed frequently in the whole running process, and the mass change can reach more than 400% due to the large difference between the unloaded mass and the fully loaded mass. Meanwhile, the quality has great influence on the braking performance, the operation stability and the like of the whole vehicle. If the accurate whole vehicle mass can be acquired in real time, the control effect of the vehicle can be obviously improved. During the running process of the vehicle, the road surface gradient also influences the acceleration performance of the vehicle, and if the gradient of the road can be estimated, the braking and acceleration effects of the vehicle can be improved.
The existing method for estimating the automobile mass and the road gradient by considering the parameter coupling relation comprises the steps of firstly, acquiring vehicle state data and vehicle intrinsic parameters, and calculating to obtain the acceleration a and the transmission ratio i at the kth moment; step two, establishing an automobile mass model and a road gradient model; and step three, constructing a least square quality estimation model and a Kalman filtering slope estimation model based on the automobile quality model and the road slope model respectively, and step four, performing combined estimation on the automobile quality and the road slope by adopting nested loop iteration. The invention can provide real-time road gradient information and automobile load conditions for an automobile intelligent system, and provides important basis for automatic driving aid decision, green driving and automatic transmission gear-shifting control, thereby realizing safe, economic and comfortable driving.
However, in the existing scheme, the road gradient model is constructed only according to a vehicle longitudinal dynamic model, the requirement is high, the used acceleration is obtained by speed differentiation, and a large error is easy to generate. The actual working conditions which are difficult to be suitable for the vehicle are complicated and changeable, and the estimation accuracy is insufficient.
Disclosure of Invention
The invention aims to overcome the problem of insufficient accuracy of vehicle mass and road slope estimation in the prior art, and provides a vehicle mass and road slope estimation method.
In order to solve the technical problems, the invention adopts the technical scheme that: a vehicle mass and road grade estimation method comprising the steps of:
the method comprises the following steps: acquiring vehicle parameters;
step two: establishing a longitudinal dynamics model related to the mass of the whole vehicle and the road gradient and a longitudinal kinematics model related to the road gradient according to the parameters in the step one;
step three: building a gradient and quality estimator based on a longitudinal dynamics model, and estimating the gradient of the road and the vehicle; building a gradient estimator based on a longitudinal kinematics model to estimate the road gradient;
step four: the gradient is fused with the results of the mass estimator and the gradient estimator, and a vehicle mass estimate and a road gradient estimate are output.
Preferably, in the second step, the longitudinal dynamics model of mass and road gradient is specifically:
assuming cos α ≈ 1 and sin α ≈ tan α ═ i, simplification yields:
in the formula: t iseIs the drive torque, igIs the transmission ratio of the variator, i0Is the main reducer transmission ratio, etaTIs the mechanical efficiency of the drive chain, r is the rolling radius of the wheel, CDIs the air resistance coefficient, A is the windward area, ρ is the air density, v is the vehicle speed, m is the vehicle mass, g is the gravitational acceleration, i is the slope, α is the toe, f is the rolling resistance coefficient,is the vehicle acceleration;
further modifications yield:
the selected state quantity is as follows:
x1=[v i]T
further can be expressed as:
in the formula: Δ t is the sampling time, W1Is process noise.
Selecting the observed quantity as follows:
y1=[v]
the observation equation was established as follows:
in the formula: Δ t is the sampling time, V1Is the measurement noise.
The resulting state space expression for longitudinal dynamics is shown below:
in the formula: h is1Is an observation matrix; f. of1Is a state transfer function.
Preferably, in the second step, the longitudinal kinematic model of the road gradient is specifically:
in the formula: a isxAcceleration values measured by a longitudinal acceleration sensor;
the selected state quantity is as follows:
x2=[v i]T
further can be expressed as:
in the formula: Δ t is the sampling time, W2Is process noise;
selecting the observed quantity as follows:
y2=[v]
the observation equation was established as follows:
in the formula: Δ t is the sampling time, V2Is process noise;
the resulting state space expression for longitudinal kinematics is as follows:
in the formula: h is2Is an observation matrix.
Preferably, in the third step, a dual extended kalman filter based on longitudinal dynamics is established as the gradient and quality estimator, and the specific process is as follows:
s3.1: predicting parameters;
s3.2: predicting the state;
s3.3: correcting the state;
s3.4: and (6) parameter estimation.
Preferably, a dual extended kalman filter or a dual unscented kalman filter of the gradient and quality estimator based on longitudinal dynamics is set up, and the specific flow is as follows:
s3.1: parameter prediction, specifically:
s3.2: the state prediction specifically includes:
s3.3: and (3) state correction, specifically:
s3.4: parameter estimation, specifically:
in the formula, xp1=[m];xs1=[v i];Ps1、Pp1Respectively a covariance matrix; qp1、Qs1Respectively, process noise covariance matrices; rs1、Rp1Respectively measuring a noise covariance matrix; jacobian matrixObservation matrix Hs1=h1=[1 0](ii) a Observation matrix Is a priori an estimate of the state variable,is a priori estimate of the covariance matrix, Ks1、Kp1Respectively kalman gain.
Preferably, in step three, the slope estimator includes two procedures of prediction and correction based on the extended kalman filter of the longitudinal kinematics.
Preferably, the gradient estimator is adapted to, in the gradient estimator,
the prediction is specifically as follows:
the correction is specifically as follows:
in the formula, xs2=[v i]T;Ps2Is a covariance matrix; qs2Is a process noise covariance matrix; rs2Is a measurement noise covariance matrix;Hs2=h2=[1 0]。
preferably, the step four comprises the following specific processes:
s4.1: state interaction;
state estimation value x obtained according to k-1 times1(k-1) and xs2(k-1), covariance estimation value Ps1(k-1) and Ps2(k-1) and model mixture probability μ1(k) And mu2(k) To obtain a mixed state estimation value and a covariance estimation value;
predicted probability c of model jj:
Mixed probability mu of model i to model jij:
μ11(k-1)=p11μ1(k-1)/c1
μ12(k-1)=p12μ1(k-1)/c2
μ21(k-1)=p21μ2(k-1)/c1
μ22(k-1)=p22μ2(k-1)/c2
Hybrid estimation of states xs1i、xs2i:
Mixed estimation of covariance Ps1i、Ps2i:
S4.2: filtering; inputting the mixed state estimation value and covariance estimation value obtained in S4.1 into an estimator to enable the estimator to obtain a state estimation value and a covariance estimation value
After filtering, obtaining:
s4.3: updating the model probability, specifically:
respectively calculating innovation e of k timei:
Innovation covariance matrix calculation Si:
Updating the model probability by adopting a likelihood function, and normalizing:
in the formula, Λ1、Λ2Respectively, the likelihood of the model.
Preferably, the method further comprises a fifth step, wherein the fifth step specifically comprises the following steps:
parameters to be used for calculating the estimated mass of the entire vehicle and the estimated road gradient and other sensor parameters At1As characteristic input neural network, the vehicle mass estimated value and road gradient estimated value A in the fourth stept2Also used as characteristic input neural network, and the quality truth value and road gradient truth value Y of the experimental vehicletInput to the neural network as a tag. Training the neural network to learn the relationship between the features and the labels. For a trained network, At1And At2Inputting the network to obtain the vehicle mass and road gradient Y predicted by the networkt. Using vehicle mass estimate and road slope estimate At2As training data for neural networks, such that the predicted vehicle mass and road grade Y of the networktAnd is more accurate.
Preferably, in the step one, the structural parameters of the whole vehicle are acquired, and the parameters of the vehicle in the running process are acquired by using a sensor.
Compared with the prior art, the invention has the beneficial effects that: the method integrates the longitudinal dynamics model of the whole vehicle mass and the road gradient and the longitudinal kinematics model related to the road gradient, can simultaneously integrate the two conditions for estimation when predicting the whole vehicle mass estimation value and the road gradient estimation value, and has stronger adaptability, high estimation precision and good stability when facing the complexity and the variability of the vehicle running condition.
Drawings
FIG. 1 is a flow chart of a vehicle mass and road grade estimation method of the present invention;
FIG. 2 is a flowchart of the calculation of step four of the present invention;
FIG. 3 is a schematic diagram of the dual extended Kalman filter of the present invention.
Detailed Description
The drawings are for illustrative purposes only and are not to be construed as limiting the patent; for the purpose of better illustrating the embodiments, certain features of the drawings may be omitted, enlarged or reduced, and do not represent the size of an actual product; it will be understood by those skilled in the art that certain well-known structures in the drawings and descriptions thereof may be omitted. The positional relationships depicted in the drawings are for illustrative purposes only and are not to be construed as limiting the present patent.
The same or similar reference numerals in the drawings of the embodiments of the present invention correspond to the same or similar components; in the description of the present invention, it should be understood that if there are terms such as "upper", "lower", "left", "right", "long", "short", etc., indicating orientations or positional relationships based on the orientations or positional relationships shown in the drawings, it is only for convenience of description and simplicity of description, but does not indicate or imply that the device or element referred to must have a specific orientation, be constructed in a specific orientation, and be operated, and therefore, the terms describing the positional relationships in the drawings are only used for illustrative purposes and are not to be construed as limitations of the present patent, and specific meanings of the terms may be understood by those skilled in the art according to specific situations.
In the drawings of the embodiments of the present invention, for convenience of reading and understanding, a front plate, a rear plate and a top plate in a cabinet structure are all shown.
The technical scheme of the invention is further described in detail by the following specific embodiments in combination with the attached drawings:
example 1
FIG. 1 shows an embodiment 1 of a vehicle mass and road grade estimation method, comprising the steps of:
the method comprises the following steps: acquiring vehicle parameters; acquiring structural parameters of the whole vehicle and acquiring parameters of the vehicle in the running process by using a sensor.
Step two: establishing a longitudinal dynamics model related to the mass of the whole vehicle and the road gradient and a longitudinal kinematics model related to the road gradient according to the parameters in the step one;
step three: building a gradient and quality estimator based on a longitudinal dynamics model, and estimating the gradient of the road and the vehicle; building a gradient estimator based on a longitudinal kinematics model to estimate the road gradient;
step four: the gradient is fused with the results of the mass estimator and the gradient estimator, and a vehicle mass estimate and a road gradient estimate are output.
The beneficial effects of this embodiment: the method integrates the longitudinal dynamics model of the whole vehicle mass and the road gradient and the longitudinal kinematics model related to the road gradient, can simultaneously integrate the two conditions for estimation when predicting the whole vehicle mass estimation value and the road gradient estimation value, and has stronger adaptability, high estimation precision and good stability when facing the complexity and the variability of the vehicle running condition.
Example 2
Embodiment 2 of a vehicle mass and road grade estimation method, comprising the steps of:
the method comprises the following steps: acquiring vehicle parameters;
step two: establishing a longitudinal dynamics model related to the mass of the whole vehicle and the road gradient and a longitudinal kinematics model related to the road gradient according to the parameters in the step one;
the longitudinal dynamics model of the mass and the road gradient is specifically as follows:
the longitudinal kinematic model of the road gradient is specifically as follows:
in the formula: t iseIs the drive torque, igIs the transmission ratio of the variator, i0Is the main reducer transmission ratio, etaTIs the mechanical efficiency of the drive chain, r is the rolling radius of the wheel, CDIs the air resistance coefficient, A is the windward area, ρ is the air density, v is the vehicle speed, m is the vehicle mass, g is the gravitational acceleration, i is the slope, α is the toe, f is the rolling resistance coefficient,is the vehicle acceleration;
the longitudinal kinematic model of the road gradient is specifically as follows:
in the formula: a isxAcceleration values measured by a longitudinal acceleration sensor;
step three: a slope and quality estimator is built based on a longitudinal dynamics model, the slope and quality estimator estimates the road slope and the vehicle based on a double-extended Kalman filter of longitudinal dynamics, and the specific flow is as follows:
s3.1: parameter prediction:
s3.2: and (3) state prediction:
s3.3: and (3) state correction:
s3.4: parameter estimation:
in the formula, xp1=[m];xs1=[v i]T;Ps1、Pp1Respectively a covariance matrix; qp1、Qs1Respectively, process noise covariance matrices; rs1、Rp1Respectively measuring a noise covariance matrix; jacobian matrixObservation matrix Hs1=h1=[1 0](ii) a Observation matrix Is a priori an estimate of the state variable,is a priori estimate of the covariance matrix, Ks1、Kp1Respectively kalman gain.
A slope estimator is built based on a longitudinal kinematics model to estimate the road slope, and the slope estimator is based on an extended kalman filter of the longitudinal kinematics, as shown in fig. 3, specifically calculated as follows:
and (3) prediction:
and (3) correction:
in the formula, xs2=[v i]T;Ps2Is a covariance matrix; qs2Is a process noise covariance matrix; rs2Is a measurement noise covariance matrix;Hs2=h2=[1 0]。
step four: as shown in fig. 2, the gradient is fused with the results of the mass estimator and the gradient estimator, and a vehicle mass estimated value and a road gradient estimated value are output. The specific process is as follows:
s4.1: state interaction;
state estimation value x obtained according to k-1 times1(k-1) and xs2(k-1), covariance estimation value Ps1(k-1) and Ps2(k-1) and model mixture probability μ1(k) And mu2(k) To obtain a mixed state estimation value and a covariance estimation value;
predicted probability c of model jj:
Mixed probability mu of model i to model jij:
μ11(k-1)=p11μ1(k-1)/c1
μ12(k-1)=p12μ1(k-1)/c2
μ21(k-1)=p21μ2(k-1)/c1
μ22(k-1)=p22μ2(k-1)/c2
Hybrid estimation of states xs1i、xs2i:
Mixed estimation of covariance Ps1i、Ps2i:
S4.2: filtering; inputting the mixed state estimation value and covariance estimation value obtained in S4.1 into an estimator to enable the estimator to obtain a state estimation value and a covariance estimation value
After filtering, obtaining:
s4.3: updating the model probability, specifically:
respectively calculating innovation e of k timei:
Innovation covariance matrix calculation Si:
Updating the model probability by adopting a likelihood function, and normalizing:
in the formula, Λ1、Λ2Respectively, the likelihood of the model.
The beneficial effects of this embodiment: the method integrates the longitudinal dynamics model of the whole vehicle mass and the road gradient and the longitudinal kinematics model related to the road gradient, can simultaneously integrate the two conditions for estimation when predicting the whole vehicle mass estimation value and the road gradient estimation value, and has stronger adaptability, high estimation precision and good stability when facing the complexity and the variability of the vehicle running condition.
Example 3
An embodiment 3 of a method for estimating a vehicle mass and a road gradient is based on the above embodiment 1 or 2, and is different from the above embodiment in that the method further includes a fifth step, specifically:
parameters to be used for calculating the estimated mass of the entire vehicle and the estimated road gradient and other sensor parameters At1As characteristic input neural network, the vehicle mass estimated value and road gradient estimated value A in the fourth stept2Also used as characteristic input neural network, and the quality truth value and road gradient truth value Y of the experimental vehicletInput to the neural network as a tag. Training the neural network to learn the relationship between the features and the labels. For a trained network, At1And At2Inputting the network to obtain the vehicle mass and road gradient Y predicted by the networkt。
The beneficial effects of this embodiment: the method integrates the longitudinal dynamics model of the whole vehicle mass and the road gradient and the longitudinal kinematics model related to the road gradient, can simultaneously integrate the two conditions for estimation when predicting the whole vehicle mass estimation value and the road gradient estimation value, and has stronger adaptability, high estimation precision and good stability when facing the complexity and the variability of the vehicle running condition.
It should be understood that the above-described embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the embodiments of the present invention. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. And are neither required nor exhaustive of all embodiments. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the claims of the present invention.
Claims (10)
1. A vehicle mass and road grade estimation method, comprising the steps of:
the method comprises the following steps: acquiring vehicle parameters;
step two: establishing a longitudinal dynamics model related to the mass of the whole vehicle and the road gradient and a longitudinal kinematics model related to the road gradient according to the parameters in the step one;
step three: building a gradient and quality estimator based on a longitudinal dynamics model, and estimating the gradient of the road and the vehicle; building a gradient estimator based on a longitudinal kinematics model to estimate the road gradient;
step four: the gradient is fused with the results of the mass estimator and the gradient estimator, and a vehicle mass estimate and a road gradient estimate are output.
2. A vehicle mass and road gradient estimation method as claimed in claim 1, wherein in said step two, the mass and road gradient longitudinal dynamics model is specifically:
in the formula, TeIs the drive torque, igIs the transmission ratio of the variator, i0Is the main reducer transmission ratio, etaTIs the mechanical efficiency of the drive chain, r is the rolling radius of the wheel, CDIs the air resistance coefficient, A is the windward area, ρ is the air density, v is the vehicle speed, m is the vehicle mass, g is the gravitational acceleration, i is the slope, α is the slope angle, f is the rolling resistance coefficient,is the vehicle acceleration;
4. The vehicle mass and road gradient estimation method according to claim 1, characterized in that in the third step, a dual extended kalman filter based on longitudinal dynamics is constructed for the gradient and mass estimator, and the specific process is as follows:
s3.1: predicting parameters;
s3.2: predicting the state;
s3.3: correcting the state;
s3.4: and (6) parameter estimation.
5. The vehicle mass and road gradient estimation method according to claim 4, characterized in that a dual extended Kalman filter or a dual unscented Kalman filter of a gradient and mass estimator based on longitudinal dynamics is constructed, and the specific flow is as follows:
s3.1: parameter prediction, specifically:
s3.2: the state prediction specifically includes:
s3.3: and (3) state correction, specifically:
s3.4: parameter estimation, specifically:
in the formula, xp1=[m];xs1=[v i]T;Ps1、Pp1Respectively a covariance matrix; qp1、Qs1Respectively, process noise covariance matrices; rs1、Rp1Respectively measuring a noise covariance matrix; jacobian matrixObservation matrix Hs1=h1=[1 0](ii) a Observation matrix Is a priori an estimate of the state variable,is a priori estimate of the covariance matrix, Ks1、Kp1Respectively kalman gain.
6. The vehicle mass and road gradient estimation method according to claim 5, wherein in the third step, the gradient estimator is based on an extended Kalman filter of longitudinal kinematics, and the method comprises two procedures of prediction and correction.
7. A vehicle mass and road grade estimation method according to claim 6, wherein, in the grade estimator,
the prediction is specifically as follows:
the correction is specifically as follows:
8. the vehicle mass and road grade estimation method according to claim 7, wherein the step four is specifically performed by:
s4.1: state interaction;
state estimation value x obtained according to k-1 times1(k-1) and xs2(k-1), covariance estimation value Ps1(k-1) and Ps2(k-1) and model mixture probability μ1(k) And η2(k) To obtain a mixed state estimation value and a covariance estimation value;
predicted probability c of model jj:
Mixed probability mu of model i to model jij:
μ11(k-1)=p11μ1(k-1)/c1
μ12(k-1)=p12μ1(k-1)/c2
μ21(k-1)=p21μ2(k-1)/c1
μ22(k-1)=p22μ2(k-1)/c2
Hybrid estimation of states xs1i、xs2i:
Mixed estimation of covariance Ps1i、Ps2i:
S4.2: filtering; inputting the mixed state estimation value and covariance estimation value obtained in S4.1 into an estimator to enable the estimator to obtain a state estimation value and a covariance estimation value
After filtering, obtaining:
s4.3: updating the model probability, specifically:
respectively calculating the innovation of k timeei:
Innovation covariance matrix calculation Si:
Updating the model probability by adopting a likelihood function, and normalizing:
in the formula, Λ1、Λ2Respectively, the likelihood of the model.
9. A vehicle mass and road grade estimation method according to any one of claims 1-8, further comprising step five, specifically:
parameters to be used for calculating the estimated mass of the entire vehicle and the estimated road gradient and other sensor parameters At1As characteristic input neural network, the vehicle mass estimated value and road gradient estimated value A in the fourth stept2Also used as characteristic input neural network, and the quality truth value and road gradient truth value Y of the experimental vehicletInput to the neural network as a tag. Training the neural network to learn the relationship between the features and the labels. For a trained network, At1And At2Inputting the network to obtain the vehicle mass and road gradient Y predicted by the networkt。
10. A vehicle mass and road gradient estimation method according to any one of claims 1-8, characterized in that in step one, structural parameters of the whole vehicle are obtained and parameters of the vehicle during driving are obtained by using sensors.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111417841.9A CN113978473B (en) | 2021-11-25 | 2021-11-25 | Vehicle mass and road gradient estimation method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111417841.9A CN113978473B (en) | 2021-11-25 | 2021-11-25 | Vehicle mass and road gradient estimation method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113978473A true CN113978473A (en) | 2022-01-28 |
CN113978473B CN113978473B (en) | 2023-05-23 |
Family
ID=79732011
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111417841.9A Active CN113978473B (en) | 2021-11-25 | 2021-11-25 | Vehicle mass and road gradient estimation method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113978473B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114655224A (en) * | 2022-03-21 | 2022-06-24 | 潍柴动力股份有限公司 | Road gradient estimation method, electronic device and storage medium |
CN114919585A (en) * | 2022-07-22 | 2022-08-19 | 杭州宏景智驾科技有限公司 | Vehicle weight and road gradient estimation method based on vehicle dynamics model |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112613253A (en) * | 2021-01-06 | 2021-04-06 | 东南大学 | Vehicle mass and road gradient combined self-adaptive estimation method considering environmental factors |
-
2021
- 2021-11-25 CN CN202111417841.9A patent/CN113978473B/en active Active
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112613253A (en) * | 2021-01-06 | 2021-04-06 | 东南大学 | Vehicle mass and road gradient combined self-adaptive estimation method considering environmental factors |
Non-Patent Citations (5)
Title |
---|
付翔;刘会康;黄斌;: "基于CRLS的路面坡度及轮毂电机车辆质量估计", 数字制造科学 * |
任志英;沈亮量;黄伟;刘星星;: "基于AEKF的车辆质量与道路坡度实时估计", 振动.测试与诊断 * |
李尊;孔盼;史艳龙;: "重型商用车质量和道路坡度估算方法", 重型汽车 * |
赵健;李至轩;朱冰;李雅欣;孙玉泽;: "基于交互多模型的车辆质量与道路坡度估计", 中国公路学报 * |
郝胜强;罗培培;席军强;: "基于稳态卡尔曼滤波的车辆质量与道路坡度估计", 汽车工程 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114655224A (en) * | 2022-03-21 | 2022-06-24 | 潍柴动力股份有限公司 | Road gradient estimation method, electronic device and storage medium |
CN114919585A (en) * | 2022-07-22 | 2022-08-19 | 杭州宏景智驾科技有限公司 | Vehicle weight and road gradient estimation method based on vehicle dynamics model |
CN114919585B (en) * | 2022-07-22 | 2022-11-04 | 杭州宏景智驾科技有限公司 | Vehicle weight and road gradient estimation method based on vehicle dynamics model |
Also Published As
Publication number | Publication date |
---|---|
CN113978473B (en) | 2023-05-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112613253B (en) | Vehicle mass and road gradient combined self-adaptive estimation method considering environmental factors | |
CN113978473A (en) | Vehicle mass and road gradient estimation method | |
CN103661393B (en) | Kinematic road gradient is estimated | |
CN110588657B (en) | Joint estimation method for vehicle motion state and road gradient | |
CN109583571B (en) | Mobile robot soft ground trafficability prediction method based on LSTM network | |
CN113806861B (en) | Method for estimating vehicle mass and road gradient of two-step structure | |
CN103661352A (en) | Static road gradient estimation | |
CN107458380A (en) | A kind of road grade real-time estimation method being applied under comprehensive driving cycles | |
CN113830088B (en) | Intelligent semi-trailer tractor trajectory tracking prediction control method and vehicle | |
CN111198032A (en) | Real-time estimation method for automobile mass | |
CN112180361A (en) | Vehicle-mounted radar target tracking method based on dynamic federal filtering | |
JP5337090B2 (en) | Vehicle characteristic information estimation device and warning device using the same | |
CN115271040A (en) | Vehicle quality estimation method based on adaptive extended Kalman filtering | |
CN114802223A (en) | Intelligent vehicle controllable capacity grade prediction method | |
CN117719519A (en) | Vehicle running state estimation method | |
CN116674571A (en) | Real-time estimation method for automobile quality and gradient based on data confidence factor | |
CN116538286A (en) | Commercial vehicle gear shifting system and method considering NVH characteristics | |
CN113158569B (en) | Tank car side-tipping state high-reliability estimation method based on long-short term memory network | |
CN112417365A (en) | Automatic driving truck quality estimation method based on extended Kalman filtering | |
CN111703429A (en) | Method for estimating longitudinal speed of wheel hub motor driven vehicle | |
CN111695196A (en) | Tank car side-tipping state pre-judging method based on vehicle body kinematics information | |
CN117077281A (en) | UKF-CNN-LSTM-based heavy-load transport vehicle centroid slip angle estimation method | |
CN113721509B (en) | Parameter estimation method based on container truck signal acquisition device | |
CN114357624B (en) | Vehicle weight estimation algorithm based on second-order linear differential tracker and parameter bilinear model | |
CN116588119B (en) | Vehicle state estimation method based on tire model parameter self-adaption |
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 |