[go: up one dir, main page]

CN108859648B - A method for determining the switching weighting coefficient of suspension shock absorber damping control - Google Patents

A method for determining the switching weighting coefficient of suspension shock absorber damping control Download PDF

Info

Publication number
CN108859648B
CN108859648B CN201810933191.5A CN201810933191A CN108859648B CN 108859648 B CN108859648 B CN 108859648B CN 201810933191 A CN201810933191 A CN 201810933191A CN 108859648 B CN108859648 B CN 108859648B
Authority
CN
China
Prior art keywords
suspension
shock absorber
damping force
rear wheel
front wheel
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.)
Active
Application number
CN201810933191.5A
Other languages
Chinese (zh)
Other versions
CN108859648A (en
Inventor
陈双
包黎明
赵凯旋
陈剑桥
李政原
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.)
Liaoning University of Technology
Original Assignee
Liaoning University of Technology
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 Liaoning University of Technology filed Critical Liaoning University of Technology
Priority to CN201810933191.5A priority Critical patent/CN108859648B/en
Publication of CN108859648A publication Critical patent/CN108859648A/en
Application granted granted Critical
Publication of CN108859648B publication Critical patent/CN108859648B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60G—VEHICLE SUSPENSION ARRANGEMENTS
    • B60G17/00—Resilient suspensions having means for adjusting the spring or vibration-damper characteristics, for regulating the distance between a supporting surface and a sprung part of vehicle or for locking suspension during use to meet varying vehicular or surface conditions, e.g. due to speed or load
    • B60G17/015—Resilient suspensions having means for adjusting the spring or vibration-damper characteristics, for regulating the distance between a supporting surface and a sprung part of vehicle or for locking suspension during use to meet varying vehicular or surface conditions, e.g. due to speed or load the regulating means comprising electric or electronic elements
    • B60G17/0152—Resilient suspensions having means for adjusting the spring or vibration-damper characteristics, for regulating the distance between a supporting surface and a sprung part of vehicle or for locking suspension during use to meet varying vehicular or surface conditions, e.g. due to speed or load the regulating means comprising electric or electronic elements characterised by the action on a particular type of suspension unit
    • B60G17/0157—Resilient suspensions having means for adjusting the spring or vibration-damper characteristics, for regulating the distance between a supporting surface and a sprung part of vehicle or for locking suspension during use to meet varying vehicular or surface conditions, e.g. due to speed or load the regulating means comprising electric or electronic elements characterised by the action on a particular type of suspension unit non-fluid unit, e.g. electric motor
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/10—Geometric CAD
    • G06F30/15—Vehicle, aircraft or watercraft design

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Geometry (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Mathematical Optimization (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Pure & Applied Mathematics (AREA)
  • Computer Hardware Design (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Mechanical Engineering (AREA)
  • Vehicle Body Suspensions (AREA)

Abstract

本发明公开了基于神经网络的悬架减震器阻尼控制切换加权系数确定方法，包括：采集汽车监测数据，基于包含车身垂向位移、车身俯仰角、侧倾角和前后四个车轮的垂向位移具有线性特征的七自由度运动微分方程，并将其转化为神经网络的样本数据；根据路况类别对所述样本数据进行分类，得到每一路面工况对应的样本数据集合；根据汽车实时监测数据进行路况识别，并将包含所述切换特征加权系数的控制方程作为控制策略输出，本发明针对不同工况对悬架减震器阻尼力进行控制，提高汽车的安全性和舒适性，实现平稳切换。

The invention discloses a method for determining a switching weighting coefficient of a suspension shock absorber damping control based on a neural network. The method includes: collecting vehicle monitoring data; A seven-degree-of-freedom motion differential equation with linear features is converted into the sample data of the neural network; the sample data is classified according to the road condition category, and the sample data set corresponding to each road condition is obtained; according to the real-time vehicle monitoring data The road condition is identified, and the control equation including the switching characteristic weighting coefficient is output as the control strategy. The present invention controls the damping force of the suspension shock absorber according to different working conditions, improves the safety and comfort of the vehicle, and realizes smooth switching. .

Description

一种悬架减震器阻尼控制切换加权系数确定方法A method for determining the switching weighting coefficient of suspension shock absorber damping control

技术领域technical field

本发明涉及汽车主动悬架的多工况切换控制领域，尤其涉及一种基于神经网络的切换控制特征加权系数确定方法。The invention relates to the field of multi-working-condition switching control of an automobile active suspension, in particular to a method for determining the weighting coefficient of switching control characteristics based on a neural network.

背景技术Background technique

悬架系统是车辆的重要组成部分。随着科技的发展及控制技术的不断进步，传统的被动式悬架系统由于其参数不可改变，制约了悬架系统作用的发挥，而主动悬架系统因为参数可调，可实现各工况下的性能最优，并且符合未来汽车低碳化、轻量化、智能化、个性化的发展趋势，从而成为研究热门和趋势。为了提高汽车的舒适性及安全性，现代汽车技术的日益发展使悬架系统越来越智能化。主动、半主动悬架系统通过实时控制，使车辆在各种路面工况下均能达到行驶平顺性和操纵稳定性的最优，具有传统悬架无法比拟的优势。The suspension system is an important part of the vehicle. With the development of science and technology and the continuous progress of control technology, the traditional passive suspension system restricts the performance of the suspension system because its parameters cannot be changed, while the active suspension system can realize the function of the suspension system under various working conditions because its parameters can be adjusted. It has the best performance and is in line with the development trend of low-carbon, lightweight, intelligent and personalized automobiles in the future, thus becoming a research hotspot and trend. In order to improve the comfort and safety of automobiles, the increasing development of modern automobile technology makes the suspension system more and more intelligent. Active and semi-active suspension systems enable the vehicle to achieve optimal driving comfort and handling stability under various road conditions through real-time control, which has incomparable advantages over traditional suspensions.

车辆行驶过程中，行驶工况不断发生变化，针对不同工况采取不同的控制方式对主动悬架的进行控制，提高汽车的舒适性及安全性。当路面工况发生变化时，切换控制力会出现卡顿，突变等现象，所以主动悬架多工况切换控制的平滑切换的研究显得尤为重要。During the driving process of the vehicle, the driving conditions are constantly changing, and different control methods are adopted to control the active suspension according to different working conditions, so as to improve the comfort and safety of the vehicle. When the road conditions change, the switching control force will appear stuck, abrupt change and other phenomena, so the research on the smooth switching of the active suspension multi-condition switching control is particularly important.

发明内容SUMMARY OF THE INVENTION

本发明设计开发了基于神经网络的悬架减震器阻尼控制切换加权系数确定方法，针对不同工况建立神经网络模型，根据实时监测到的汽车状态数据得到不同工况下的汽车悬架的切换控制系数，并据此对悬架减震器阻尼力进行控制，提高汽车的安全性和舒适性，实现平稳切换。The invention designs and develops a method for determining the switching weighting coefficient of the damping control of the suspension shock absorber based on a neural network, establishes a neural network model for different working conditions, and obtains the switching of the vehicle suspension under different working conditions according to the vehicle state data monitored in real time. Control coefficient, and control the damping force of the suspension shock absorber accordingly, improve the safety and comfort of the car, and achieve smooth switching.

本发明提供的技术方案为：The technical scheme provided by the present invention is:

一种基于神经网络的悬架减震器阻尼控制切换加权系数确定方法，包括：A method for determining the switching weighting coefficient of suspension shock absorber damping control based on neural network, comprising:

采集汽车监测数据，建立七自由度运动微分方程，将车身垂向位移、车身俯仰角、侧倾角和前后四个车轮的垂向位移转化为神经网络的样本数据；Collect vehicle monitoring data, establish a seven-degree-of-freedom motion differential equation, and convert the vertical displacement of the vehicle body, the pitch angle of the vehicle body, the roll angle and the vertical displacement of the front and rear four wheels into the sample data of the neural network;

根据路况类别对所述样本数据进行分类，得到每一路面工况对应的样本数据集合；Classify the sample data according to the road condition category to obtain a sample data set corresponding to each road condition;

根据每一路面工况对应的样本数据集合分别建立神经网络模型，包括：A neural network model is established according to the sample data set corresponding to each road condition, including:

将所述车身垂向位移、车身俯仰角、侧倾角和前后四个车轮的垂向位移作为输入层向量构建神经网络，在神经网络中对输入层向量特征进行解析，获得表示该路面工况对应的切换加权系数的向量群；The vertical displacement of the body, the pitch angle of the body, the roll angle and the vertical displacement of the front and rear four wheels are used as input layer vectors to construct a neural network, and the input layer vector features are analyzed in the neural network to obtain the corresponding road conditions. The vector group of switching weighting coefficients;

将所有神经网络模型融合为一个神经网络；以及fuse all neural network models into one neural network; and

根据汽车实时监测数据进行路况识别，并将包含所述切换加权系数的控制方程作为控制策略输出；Identify the road conditions according to the real-time monitoring data of the vehicle, and output the control equation including the switching weighting coefficient as a control strategy;

其中，所述路况类别包括：平直路工况、坡度路面工况和连续减速带。Wherein, the road condition categories include: straight road conditions, slope road conditions and continuous speed bumps.

优选的是，所述运动微分方程为：Preferably, the differential equation of motion is:

左前轮垂向运动方程：The equation of vertical motion of the left front wheel:

Figure GDA0002220758990000021
Figure GDA0002220758990000021

其中，mu1为左前轮非簧载质量，zfl为左前轮垂向位移，

Figure GDA0002220758990000022
为左前轮垂向速度，
Figure GDA0002220758990000023
为左前轮垂向加速度，kt为轮胎刚度，kf为悬架刚度，q1为左前轮路面激励的垂向位移，Fk1为左前悬架减振器阻尼力；Among them, m u1 is the unsprung mass of the left front wheel, z fl is the vertical displacement of the left front wheel,
Figure GDA0002220758990000022
is the vertical speed of the left front wheel,
Figure GDA0002220758990000023
is the vertical acceleration of the left front wheel, k t is the tire stiffness, k f is the suspension stiffness, q 1 is the vertical displacement of the left front wheel road excitation, and F k1 is the damping force of the left front suspension shock absorber;

右前轮垂向运动方程：The equation of vertical motion of the right front wheel:

Figure GDA0002220758990000024
Figure GDA0002220758990000024

其中，mu2为右前轮非簧载质量，zfr为右前轮垂向位移，

Figure GDA0002220758990000025
为右前轮垂向速度，
Figure GDA0002220758990000026
为右前轮垂向加速度，q2为右前轮路面激励的垂向位移，Fk2为右前悬架减振器阻尼力；Among them, m u2 is the unsprung mass of the right front wheel, z fr is the vertical displacement of the right front wheel,
Figure GDA0002220758990000025
is the vertical speed of the right front wheel,
Figure GDA0002220758990000026
is the vertical acceleration of the right front wheel, q 2 is the vertical displacement of the road surface excitation of the right front wheel, and F k2 is the damping force of the shock absorber of the right front suspension;

左后轮垂向运动方程：The equation of vertical motion of the left rear wheel:

Figure GDA0002220758990000027
Figure GDA0002220758990000027

其中，mu3为左后轮非簧载质量，zrl为左后轮垂向位移，为左后轮垂向速度，为左后轮垂向加速度，q3为左后轮路面激励的垂向位移，Fk3左后悬架减振器阻尼力；Among them, m u3 is the unsprung mass of the left rear wheel, z rl is the vertical displacement of the left rear wheel, is the vertical speed of the left rear wheel, is the vertical acceleration of the left rear wheel, q3 is the vertical displacement of the left rear wheel road excitation, F k3 is the damping force of the shock absorber of the left rear suspension;

右后轮垂向运动方程：The equation of vertical motion of the right rear wheel:

Figure GDA0002220758990000031
Figure GDA0002220758990000031

其中，mu4为右后轮非簧载质量，zrr为右后轮垂向位移，

Figure GDA0002220758990000032
为右后轮垂向速度，
Figure GDA0002220758990000033
为右后轮垂向加速度，q4为右后轮路面激励的垂向位移，Fk4右后悬架减振器阻尼力；Among them, m u4 is the unsprung mass of the right rear wheel, z rr is the vertical displacement of the right rear wheel,
Figure GDA0002220758990000032
is the vertical speed of the right rear wheel,
Figure GDA0002220758990000033
is the vertical acceleration of the right rear wheel, q4 is the vertical displacement of the road surface excitation of the right rear wheel, F k4 is the damping force of the shock absorber of the right rear suspension;

zs1为左前轮车身与悬架连接处的垂向位移，zs1＝zs-Lfθ+φB/2；z s1 is the vertical displacement of the connection between the left front wheel body and the suspension, z s1 =z s -L f θ+φB/2;

zs2为右前轮车身与悬架连接处的垂向位移，zs2＝zs-Lfθ-φB/2；z s2 is the vertical displacement of the connection between the right front wheel body and the suspension, z s2 =z s -L f θ-φB/2;

zs3为左后轮车身与悬架连接处的垂向位移，zs3＝zs+Lrθ+φB/2；z s3 is the vertical displacement of the connection between the left rear wheel body and the suspension, z s3 =z s +L r θ+φB/2;

zs4为右后轮车身与悬架连接处的垂向位移，zs4＝zs+Lrθ-φB/2；z s4 is the vertical displacement of the connection between the right rear wheel body and the suspension, z s4 =z s +L r θ-φB/2;

zs为车身垂向位移，Lf为质心距前悬架距离，Lr为质心距悬架右铰接点距离，φ为车身侧倾角，θ为车身俯仰角，B为左右轮距；z s is the vertical displacement of the body, L f is the distance between the center of mass and the front suspension, L r is the distance between the center of mass and the right hinge point of the suspension, φ is the body roll angle, θ is the body pitch angle, and B is the left and right wheelbase;

车身垂向运动方程：Body vertical motion equation:

车身俯仰运动方程:Body pitch equation of motion:

Figure GDA0002220758990000035
Figure GDA0002220758990000035

车身侧倾运动方程：Body roll motion equation:

Figure GDA0002220758990000036
Figure GDA0002220758990000036

其中，

Figure GDA0002220758990000037
为左前轮车身与悬架连接处的垂向速度，
Figure GDA0002220758990000038
为右前轮车身与悬架连接处的垂向速度，
Figure GDA0002220758990000039
为左后轮车身与悬架连接处的垂向速度，
Figure GDA00022207589900000310
为右后轮车身与悬架连接处的垂向速度，
Figure GDA00022207589900000311
为车身俯仰角速度，
Figure GDA00022207589900000312
为车身侧倾角速度， Ix为车身侧倾方向上的转动惯量，Iy为车身俯仰方向上的转动惯量，Cf悬架前减震器阻尼系数，Cr为悬架后减震器阻尼系数，Fk1为左前悬架减振器阻尼力，Fk2为右前悬架减振器阻尼力，Fk3左后悬架减振器阻尼力，Fk4右后悬架减振器阻尼力。in,
Figure GDA0002220758990000037
is the vertical speed at the connection between the left front wheel body and the suspension,
Figure GDA0002220758990000038
is the vertical speed at the connection between the right front wheel body and the suspension,
Figure GDA0002220758990000039
is the vertical speed at the connection between the left rear wheel body and the suspension,
Figure GDA00022207589900000310
is the vertical speed at the connection between the right rear wheel body and the suspension,
Figure GDA00022207589900000311
is the body pitch angular velocity,
Figure GDA00022207589900000312
is the body roll angular velocity, I x is the moment of inertia in the body roll direction, I y is the moment of inertia in the body pitch direction, C f is the damping coefficient of the front shock absorber of the suspension, and C r is the damping of the rear shock absorber of the suspension coefficient, F k1 is the damping force of the left front suspension shock absorber, F k2 is the damping force of the right front suspension shock absorber, F k3 is the damping force of the left rear suspension shock absorber, and F k4 is the damping force of the right rear suspension shock absorber.

优选的是，所述神经网络为三层神经网络模型，依次对输入层向量进行格式化，确定三层神经网络的输入层向量

Figure GDA00022207589900000313
所述输入层向量映射到隐含层，所述隐含层向量为Y＝{y1,y2,y3,y4···ym}，m为节点个数，输出层向量为
Figure GDA00022207589900000314
Preferably, the neural network is a three-layer neural network model, and the input layer vectors are formatted in turn to determine the input layer vector of the three-layer neural network.
Figure GDA00022207589900000313
The input layer vector is mapped to the hidden layer, and the hidden layer vector is Y={y 1 , y 2 , y 3 , y 4 ··· y m }, m is the number of nodes, and the output layer vector is
Figure GDA00022207589900000314

其中，zs为车身垂向位移向量，

Figure GDA0002220758990000041
为车身垂向速度，θ为车身俯仰角，
Figure GDA0002220758990000042
为车身俯仰角速度，φ为车身侧倾角，
Figure GDA0002220758990000043
为车身侧倾角速度，zfl为前轮垂向位移，为前轮垂向速度，zrl为后轮垂向位移，
Figure GDA0002220758990000045
为后轮垂向速度；ladma1为平直路况切换加权系数矩阵，ladma2为坡度路况切换加权系数矩阵，ladma3为连续减速带路况切换加权系数矩阵，
Figure GDA0002220758990000046
为对应工况的左前轮悬架减震器切换特征加权系数，
Figure GDA0002220758990000047
为对应工况的右前轮悬架减震器切换特征加权系数，
Figure GDA0002220758990000048
为对应工况的左后轮悬架减震器切换加权系数，
Figure GDA0002220758990000049
为对应工况的右后轮悬架减震器切换加权系数。Among them, z s is the vertical displacement vector of the vehicle body,
Figure GDA0002220758990000041
is the vertical speed of the body, θ is the pitch angle of the body,
Figure GDA0002220758990000042
is the body pitch angular velocity, φ is the body roll angle,
Figure GDA0002220758990000043
is the body roll angular velocity, z fl is the vertical displacement of the front wheel, is the vertical speed of the front wheel, z rl is the vertical displacement of the rear wheel,
Figure GDA0002220758990000045
is the vertical speed of the rear wheel; ladma 1 is the weighting coefficient matrix for the switching of straight road conditions, ladma 2 is the weighting coefficient matrix for the switching of slope road conditions, and ladma 3 is the weighting coefficient matrix for the switching of continuous deceleration belt road conditions,
Figure GDA0002220758990000046
Switch the characteristic weighting coefficient for the left front wheel suspension shock absorber corresponding to the working condition,
Figure GDA0002220758990000047
Switch the characteristic weighting coefficient for the shock absorber of the right front wheel suspension corresponding to the working condition,
Figure GDA0002220758990000048
Switch the weighting coefficient for the shock absorber of the left rear wheel suspension corresponding to the working condition,
Figure GDA0002220758990000049
Switch the weighting factor for the shock absorber of the right rear wheel suspension corresponding to the working condition.

优选的是，利用如下公式对输入层参数进行格式化：Preferably, the input layer parameters are formatted using the following formula:

Figure GDA00022207589900000410
Figure GDA00022207589900000410

其中，xi为格式化后指标系数，Ti为输入层参量，Timax为输入层参量对应最大值，Timin为输入层参量对应最小值。Among them, x i is the index coefficient after formatting, T i is the input layer parameter, T imax is the corresponding maximum value of the input layer parameter, and T imin is the corresponding minimum value of the input layer parameter.

优选的是，所述隐含层节点数为13个。Preferably, the number of nodes in the hidden layer is 13.

优选的是，所述切换加权系数的控制方程为：Preferably, the control equation of the switching weighting coefficient is:

Figure GDA00022207589900000411
Figure GDA00022207589900000411

其中，Fk1为左前悬架减振器阻尼力，Fk2为右前悬架减振器阻尼力，Fk3左后悬架减振器阻尼力，Fk4右后悬架减振器阻尼力，

Figure GDA00022207589900000412
为平直路工况下左前轮悬架减振器阻尼力，
Figure GDA00022207589900000413
为坡度路面工况下左前轮悬架减振器阻尼力，
Figure GDA00022207589900000414
为连续减速带工况下左前轮悬架减振器阻尼力，
Figure GDA00022207589900000415
为平直路工况下右前轮悬架减振器阻尼力，
Figure GDA00022207589900000416
为坡度路面工况下右前轮悬架减振器阻尼力，
Figure GDA00022207589900000417
为连续减速带工况下左前轮悬架减振器阻尼力；
Figure GDA00022207589900000418
为平直路工况下左后轮悬架减振器阻尼力，
Figure GDA00022207589900000419
为坡度路面工况下左后轮悬架减振器阻尼力，
Figure GDA00022207589900000420
为连续减速带工况下左后轮悬架减振器阻尼力；
Figure GDA00022207589900000421
为平直路工况下右后轮悬架减振器阻尼力，
Figure GDA00022207589900000422
为坡度路面工况下右后轮悬架减振器阻尼力，
Figure GDA00022207589900000423
为连续减速带工况下左后轮悬架减振器阻尼力。Among them, F k1 is the damping force of the left front suspension shock absorber, F k2 is the damping force of the right front suspension shock absorber, F k3 is the damping force of the left rear suspension shock absorber, F k4 is the damping force of the right rear suspension shock absorber,
Figure GDA00022207589900000412
is the damping force of the shock absorber of the left front wheel suspension under straight road conditions,
Figure GDA00022207589900000413
is the damping force of the shock absorber of the left front wheel suspension under slope road conditions,
Figure GDA00022207589900000414
is the damping force of the shock absorber of the left front wheel suspension under the condition of continuous deceleration belt,
Figure GDA00022207589900000415
is the damping force of the shock absorber of the right front wheel suspension under straight road conditions,
Figure GDA00022207589900000416
is the damping force of the shock absorber of the right front wheel suspension under sloping road conditions,
Figure GDA00022207589900000417
is the damping force of the shock absorber of the left front wheel suspension under the condition of continuous speed bumps;
Figure GDA00022207589900000418
is the damping force of the shock absorber of the left rear wheel suspension under flat and straight road conditions,
Figure GDA00022207589900000419
is the damping force of the shock absorber of the left rear wheel suspension under slope road conditions,
Figure GDA00022207589900000420
is the damping force of the shock absorber of the left rear wheel suspension under the condition of continuous speed bumps;
Figure GDA00022207589900000421
is the damping force of the shock absorber of the right rear wheel suspension under straight road conditions,
Figure GDA00022207589900000422
is the damping force of the shock absorber of the right rear wheel suspension under slope road conditions,
Figure GDA00022207589900000423
It is the damping force of the shock absorber of the left rear wheel suspension under the condition of continuous speed bump.

本发明所述的有益效果The beneficial effects of the present invention

本发明设计开发了一种神经网络的切换控制特征加权系数确定方法，本发明设计开发了一种神经网络的切换控制特征加权系数确定方法，针对不同工况建立神经网络模型，根据实时监测到的汽车状态数据得到不同工况下的汽车悬架的控制系数，并据此悬架减震器阻尼力进行控制，提高汽车的安全性和舒适性，实现平稳切换，当路面工况发生变化时，切换控制力会出现卡顿，突变等现象，采用神经网络算法实现主动悬架多工况控制的平滑切换。The present invention designs and develops a method for determining the weighting coefficient of switching control characteristics of a neural network. The present invention designs and develops a method for determining the weighting coefficient of switching control characteristics of a neural network. A neural network model is established for different working conditions. The control coefficient of the vehicle suspension under different working conditions is obtained from the vehicle state data, and the damping force of the suspension shock absorber is controlled according to this, so as to improve the safety and comfort of the vehicle, and achieve smooth switching. When the road conditions change, The switching control force will appear stuck, sudden change and other phenomena. The neural network algorithm is used to realize the smooth switching of the active suspension multi-condition control.

附图说明Description of drawings

图1为本发明所述的七自由度整车动力学模型图。FIG. 1 is a diagram of a vehicle dynamics model with seven degrees of freedom according to the present invention.

图2为本发明所述的神经网络模型的原理图。FIG. 2 is a schematic diagram of the neural network model according to the present invention.

图3为本发明所述的多工况路面仿真结果图。FIG. 3 is a graph showing the simulation results of the multi-condition road surface according to the present invention.

图4为本发明所述的平直路况切换特征加权系数。FIG. 4 is the characteristic weighting coefficients for switching between flat and straight road conditions according to the present invention.

图5为本发明所述的坡度路况切换特征加权系数。FIG. 5 is the characteristic weighting coefficient of the gradient road condition switching according to the present invention.

图6为本发明所述的连续减速带路况切换特征加权系数。FIG. 6 is the weighting coefficient of the continuous deceleration belt road condition switching feature according to the present invention.

具体实施方式Detailed ways

下面结合附图对本发明做进一步的详细说明，以令本领域技术人员参照说明书文字能够据以实施。The present invention will be further described in detail below with reference to the accompanying drawings, so that those skilled in the art can implement it with reference to the description.

如图1所示，本发明提供的基于神经网络的悬架减震器阻尼控制切换特征加权系数确定方法，包括：建立包含车身垂向位移、车身俯仰角、侧倾角和前后四个车轮的垂向位移具有非线性特征的七自由度运动微分方程：As shown in FIG. 1 , the method for determining the weighting coefficient of suspension damper damping control switching feature based on neural network provided by the present invention includes: establishing a vertical displacement of the vehicle body, the pitch angle of the vehicle body, the roll angle and the vertical displacement of the front and rear four wheels. 7-DOF differential equation of motion with nonlinear characteristics to displacement:

左前轮垂向运动方程：The equation of vertical motion of the left front wheel:

Figure GDA0002220758990000051
Figure GDA0002220758990000051

其中，mu1为左前轮非簧载质量，zfl为左前轮垂向位移，

Figure GDA0002220758990000052
为左前轮垂向速度，
Figure GDA0002220758990000053
为左前轮垂向加速度，kt为轮胎刚度，kf为悬架刚度，q1为左前轮路面激励的垂向位移，Fk1为左前悬架减振器阻尼力；Among them, m u1 is the unsprung mass of the left front wheel, z fl is the vertical displacement of the left front wheel,
Figure GDA0002220758990000052
is the vertical speed of the left front wheel,
Figure GDA0002220758990000053
is the vertical acceleration of the left front wheel, k t is the tire stiffness, k f is the suspension stiffness, q 1 is the vertical displacement of the left front wheel road excitation, and F k1 is the damping force of the left front suspension shock absorber;

右前轮垂向运动方程：The equation of vertical motion of the right front wheel:

Figure GDA0002220758990000054
Figure GDA0002220758990000054

其中，mu2为右前轮非簧载质量，zfr为右前轮垂向位移，

Figure GDA0002220758990000055
为右前轮垂向速度，
Figure GDA0002220758990000061
为右前轮垂向加速度，q2为右前轮路面激励的垂向位移，Fk2为右前悬架减振器阻尼力；Among them, m u2 is the unsprung mass of the right front wheel, z fr is the vertical displacement of the right front wheel,
Figure GDA0002220758990000055
is the vertical speed of the right front wheel,
Figure GDA0002220758990000061
is the vertical acceleration of the right front wheel, q 2 is the vertical displacement of the road surface excitation of the right front wheel, and F k2 is the damping force of the shock absorber of the right front suspension;

左后轮垂向运动方程：The equation of vertical motion of the left rear wheel:

其中，mu3为左后轮非簧载质量，zrl为左后轮垂向位移，

Figure GDA0002220758990000063
为左后轮垂向速度，
Figure GDA0002220758990000064
为左后轮垂向加速度，q3为左后轮路面激励的垂向位移，Fk3左后悬架减振器阻尼力；Among them, m u3 is the unsprung mass of the left rear wheel, z rl is the vertical displacement of the left rear wheel,
Figure GDA0002220758990000063
is the vertical speed of the left rear wheel,
Figure GDA0002220758990000064
is the vertical acceleration of the left rear wheel, q3 is the vertical displacement of the left rear wheel road excitation, F k3 is the damping force of the shock absorber of the left rear suspension;

右后轮垂向运动方程：The equation of vertical motion of the right rear wheel:

Figure GDA0002220758990000065
Figure GDA0002220758990000065

其中，mu4为右后轮非簧载质量，zrr为右后轮垂向位移，

Figure GDA0002220758990000066
为右后轮垂向速度，为右后轮垂向加速度，q4为右后轮路面激励的垂向位移，Fk4右后悬架减振器阻尼力；Among them, m u4 is the unsprung mass of the right rear wheel, z rr is the vertical displacement of the right rear wheel,
Figure GDA0002220758990000066
is the vertical speed of the right rear wheel, is the vertical acceleration of the right rear wheel, q4 is the vertical displacement of the road surface excitation of the right rear wheel, F k4 is the damping force of the shock absorber of the right rear suspension;

zs1为左前轮车身与悬架连接处的垂向位移，zs1＝zs-Lfθ+φB/2；z s1 is the vertical displacement of the connection between the left front wheel body and the suspension, z s1 =z s -L f θ+φB/2;

zs2为右前轮车身与悬架连接处的垂向位移，zs2＝zs-Lfθ-φB/2；z s2 is the vertical displacement of the connection between the right front wheel body and the suspension, z s2 =z s -L f θ-φB/2;

zs3为左后轮车身与悬架连接处的垂向位移，zs3＝zs+Lrθ+φB/2；z s3 is the vertical displacement of the connection between the left rear wheel body and the suspension, z s3 =z s +L r θ+φB/2;

zs4为右后轮车身与悬架连接处的垂向位移，zs4＝zs+Lrθ-φB/2；z s4 is the vertical displacement of the connection between the right rear wheel body and the suspension, z s4 =z s +L r θ-φB/2;

zs为车身垂向位移，Lf为质心距前悬架距离，Lr为质心距悬架右铰接点距离，φ为车身侧倾角，θ为车身俯仰角，B为左右轮距；z s is the vertical displacement of the body, L f is the distance between the center of mass and the front suspension, L r is the distance between the center of mass and the right hinge point of the suspension, φ is the body roll angle, θ is the body pitch angle, and B is the left and right wheelbase;

车身垂向运动方程：Body vertical motion equation:

Figure GDA0002220758990000068
Figure GDA0002220758990000068

车身俯仰运动方程:Body pitch equation of motion:

Figure GDA0002220758990000069
Figure GDA0002220758990000069

车身侧倾运动方程：Body roll motion equation:

Figure GDA00022207589900000610
Figure GDA00022207589900000610

其中，

Figure GDA00022207589900000611
为左前轮车身与悬架连接处的垂向速度，
Figure GDA00022207589900000612
为右前轮车身与悬架连接处的垂向速度，
Figure GDA00022207589900000613
为左后轮车身与悬架连接处的垂向速度，
Figure GDA00022207589900000614
为右后轮车身与悬架连接处的垂向速度，为车身俯仰角速度，
Figure GDA00022207589900000616
为车身侧倾角速度，Ix为车身侧倾方向上的转动惯量，Iy为车身俯仰方向上的转动惯量，Cf悬架前减震器阻尼系数，Cr为悬架后减震器阻尼系数，Fk1为左前悬架减振器阻尼力，Fk2为右前悬架减振器阻尼力，Fk3左后悬架减振器阻尼力，Fk4右后悬架减振器阻尼力。in,
Figure GDA00022207589900000611
is the vertical speed at the connection between the left front wheel body and the suspension,
Figure GDA00022207589900000612
is the vertical speed at the connection between the right front wheel body and the suspension,
Figure GDA00022207589900000613
is the vertical speed at the connection between the left rear wheel body and the suspension,
Figure GDA00022207589900000614
is the vertical speed at the connection between the right rear wheel body and the suspension, is the body pitch angular velocity,
Figure GDA00022207589900000616
is the body roll angular velocity, I x is the moment of inertia in the body roll direction, I y is the moment of inertia in the body pitch direction, C f is the damping coefficient of the front shock absorber of the suspension, and C r is the damping of the rear shock absorber of the suspension coefficient, F k1 is the damping force of the left front suspension shock absorber, F k2 is the damping force of the right front suspension shock absorber, F k3 is the damping force of the left rear suspension shock absorber, and F k4 is the damping force of the right rear suspension shock absorber.

采集汽车监测数据并根据路况类别对样本数据进行分类，得到每一路面工况对应的样本数据集合；根据每一路面工况对应的样本数据集合分别建立神经网络模型，路况类别至少包括：平直路工况、坡度路面工况和连续减速带三个类别，建立至少三个神经网络模型，下面给出其中一个神经网络模型的训练过程，以平直路况神经网络模型为例：Collect vehicle monitoring data and classify the sample data according to the road condition category to obtain a sample data set corresponding to each road condition; establish a neural network model according to the sample data set corresponding to each road condition, and the road condition category at least includes: straight Three categories of road conditions, slope road conditions and continuous speed bumps are established, and at least three neural network models are established. The training process of one of the neural network models is given below, taking the neural network model for straight road conditions as an example:

如图2所示，神经网络模块采用BP神经网络网络，将七自由度整车模型的状态响应向量

Figure GDA0002220758990000071
作为训练样本从输入层输入，输出信号为
Figure GDA0002220758990000072
是实际输出向量；As shown in Figure 2, the neural network module adopts the BP neural network network to convert the state response vector of the seven-degree-of-freedom vehicle model
Figure GDA0002220758990000071
As a training sample input from the input layer, the output signal is
Figure GDA0002220758990000072
is the actual output vector;

zs为车身垂向位移向量，

Figure GDA0002220758990000073
为车身垂向速度，θ为车身俯仰角，
Figure GDA0002220758990000074
为车身俯仰角速度，φ为车身侧倾角，
Figure GDA0002220758990000075
为车身侧倾角速度，zfl为前轮垂向位移，
Figure GDA0002220758990000076
为前轮垂向速度，zrl为后轮垂向位移，
Figure GDA0002220758990000077
为后轮垂向速度。z s is the vertical displacement vector of the vehicle body,
Figure GDA0002220758990000073
is the vertical speed of the body, θ is the pitch angle of the body,
Figure GDA0002220758990000074
is the body pitch angular velocity, φ is the body roll angle,
Figure GDA0002220758990000075
is the body roll angular velocity, z fl is the vertical displacement of the front wheel,
Figure GDA0002220758990000076
is the vertical speed of the front wheel, z rl is the vertical displacement of the rear wheel,
Figure GDA0002220758990000077
is the vertical speed of the rear wheels.

利用如下公式对输入层参数进行格式化：The input layer parameters are formatted using the following formula:

Figure GDA0002220758990000078
Figure GDA0002220758990000078

其中，xi为格式化后指标系数，Ti为输入层参量，输入参量包括：Timax为输入层参量

Figure GDA00022207589900000710
对应最大值，Timin为输入层参量
Figure GDA00022207589900000711
对应最小值。zs为车身垂向位移向量，
Figure GDA00022207589900000712
为车身垂向速度，θ为车身俯仰角，
Figure GDA00022207589900000713
为车身俯仰角速度，φ为车身侧倾角，为车身侧倾角速度，zfl为前轮垂向位移，
Figure GDA00022207589900000715
为前轮垂向速度， zrl为后轮垂向位移，
Figure GDA00022207589900000716
为后轮垂向速度。Among them, x i is the index coefficient after formatting, T i is the input layer parameter, and the input parameters include: T imax is the input layer parameter
Figure GDA00022207589900000710
Corresponding to the maximum value, T imin is the input layer parameter
Figure GDA00022207589900000711
corresponds to the minimum value. z s is the vertical displacement vector of the vehicle body,
Figure GDA00022207589900000712
is the vertical speed of the body, θ is the pitch angle of the body,
Figure GDA00022207589900000713
is the body pitch angular velocity, φ is the body roll angle, is the body roll angular velocity, z fl is the vertical displacement of the front wheel,
Figure GDA00022207589900000715
is the vertical speed of the front wheel, z rl is the vertical displacement of the rear wheel,
Figure GDA00022207589900000716
is the vertical speed of the rear wheels.

进行BP神经网络的训练：建立好BP神经网络节点模型后，即可进行 BP神经网络的训练。根据产品的经验数据获取训练的样本，并给定输入节点 i和隐含层节点j之间的连接权值wij，隐层节点j和输出层节点k之间的连接权值wjk，隐层节点j的阈值θj，输出层节点k的阈值wij、wjk、θj、θk均为-1 到1之间的随机数。BP neural network training: After the BP neural network node model is established, the BP neural network can be trained. The training samples are obtained according to the empirical data of the product, and given the connection weight w ij between the input node i and the hidden layer node j, the connection weight w jk between the hidden layer node j and the output layer node k, the hidden layer The threshold θ j of the layer node j, and the thresholds w ij , w jk , θ j , and θ k of the output layer node k are all random numbers between -1 and 1.

在训练过程中，不断修正wij和wjk的值，直至系统误差小于等于期望误差时，完成神经网络的训练过程。During the training process, the values of w ij and w jk are continuously revised until the system error is less than or equal to the expected error, and the training process of the neural network is completed.

其中，Δδ为训练误差，

Figure GDA0002220758990000081
为输出层向量，n＝1,2,3,4，
Figure GDA0002220758990000082
为样本系数。where Δδ is the training error,
Figure GDA0002220758990000081
is the output layer vector, n=1,2,3,4,
Figure GDA0002220758990000082
is the sample coefficient.

系统的学习规则是让期望输出与实际输出的误差平方和达到某一设定值，以此来调整连接权和阈值向量。当误差减小到设定值后，系统停止学习，此时的权值和阈值被保留在系统内部，成为系统内部知识。The learning rule of the system is to adjust the connection weight and threshold vector so that the squared error between the expected output and the actual output reaches a certain set value. When the error is reduced to the set value, the system stops learning, and the weights and thresholds at this time are retained in the system and become the internal knowledge of the system.

隐含层节点数为13个，激活函数为采用对称饱和线性传递函数，输出层节点数为3，激活函数为log-S型传递函数，训练方法选为自学习适用性算法。The number of hidden layer nodes is 13, the activation function is a symmetric saturated linear transfer function, the number of output layer nodes is 3, the activation function is a log-S type transfer function, and the training method is selected as a self-learning applicability algorithm.

对于隐藏层，激活函数f[·]采用对称饱和线性传递函数(satlins)For the hidden layer, the activation function f[ ] adopts a symmetric saturated linear transfer function (satlins)

Figure GDA0002220758990000083
Figure GDA0002220758990000083

对于输出层，激活函数f[·]采用log-S型传递函数，For the output layer, the activation function f[ ] adopts a log-S type transfer function,

Figure GDA0002220758990000084
Figure GDA0002220758990000084

IW{1,1}和LW{2,1}是层与层之间的连接权，b{1,1}和b{2,1}为权重。IW{1,1} and LW{2,1} are the connection weights between layers, and b{1,1} and b{2,1} are the weights.

如表1所示，给定了一组训练样本以及训练过程中各节点的值。As shown in Table 1, a set of training samples and the values of each node in the training process are given.

表1训练过程各节点值Table 1 The value of each node in the training process

Figure GDA0002220758990000085
Figure GDA0002220758990000085

Figure GDA0002220758990000101
Figure GDA0002220758990000101

Figure GDA0002220758990000111
Figure GDA0002220758990000111

参照上述训练方法，得到平直路工况、坡度路面工况和连续减速带三个类别的神经网络模型，将三个神经网络模型整合为一个神经网络模型Referring to the above training method, three types of neural network models are obtained: straight road conditions, slope road conditions and continuous speed bumps, and the three neural network models are integrated into one neural network model.

输出层向量为

Figure GDA0002220758990000112
The output layer vector is
Figure GDA0002220758990000112

其中，ladma1为平直路况切换加权系数矩阵，ladma2为坡度路况切换加权系数矩阵，ladma3为连续减速带路况切换加权系数矩阵，

Figure GDA0002220758990000113
为对用工况的左前轮切换加权系数，
Figure GDA0002220758990000114
为对应工况的右前轮切换加权系数，
Figure GDA0002220758990000115
为对应工况的左后轮切换加权系数，为对应工况的右后轮切换加权系数。Among them, ladma 1 is the weighting coefficient matrix of the smooth road condition switching, ladma 2 is the weighting coefficient matrix of the gradient road condition switching, and ladma 3 is the weighting coefficient matrix of the continuous deceleration belt road condition switching,
Figure GDA0002220758990000113
is the switching weighting factor of the left front wheel under the working condition,
Figure GDA0002220758990000114
is the switching weighting coefficient of the right front wheel corresponding to the working condition,
Figure GDA0002220758990000115
is the switching weighting coefficient of the left rear wheel corresponding to the working condition, It is the weighting factor for the right rear wheel switching corresponding to the working condition.

得到包含lamda1、lamda2、lamda3是实际输出向量所述特征加权系数的控制方程包括：The control equation to obtain the feature weighting coefficients containing lamda 1 , lamda 2 , and lamda 3 is the actual output vector includes:

Figure GDA0002220758990000117
Figure GDA0002220758990000117

其中，Fk1为左前悬架减振器阻尼力，Fk2为右前悬架减振器阻尼力，Fk3左后悬架减振器阻尼力，Fk4右后悬架减振器阻尼力，F10为平直路工况下左前悬架减振器阻尼力，F20为坡度路面工况下左前悬架减振器阻尼力，F30为连续减速带工况下左前悬架减振器阻尼力。Among them, F k1 is the damping force of the left front suspension shock absorber, F k2 is the damping force of the right front suspension shock absorber, F k3 is the damping force of the left rear suspension shock absorber, F k4 is the damping force of the right rear suspension shock absorber, F 10 is the damping force of the shock absorber of the left front suspension under the condition of flat and straight road, F 20 is the damping force of the shock absorber of the left front suspension under the condition of slope road, F 30 is the shock absorber of the left front suspension under the condition of continuous deceleration belt damping force.

实验例Experimental example

如图3所示，首先建立依随机平直路、斜坡路、连续减速带的多工况路面仿真模型，时间为0-15s。其中0-5s为随机平直路工况、5-10s为坡度路面工况、10-15s为连续加速带工况。As shown in Figure 3, a multi-condition road simulation model based on random straight road, slope road, and continuous speed bump is established first, and the time is 0-15s. Among them, 0-5s is the random straight road condition, 5-10s is the slope road condition, and 10-15s is the continuous acceleration belt condition.

0-5s的随机平直路工况采用滤波白噪声路面模型描述，运动方程为：The 0-5s random flat road condition is described by the filtered white noise road surface model, and the motion equation is:

其中，G0＝6.4e-6是路面不平度系数,w(t)是t时刻均值为零的高斯白噪声输入，v＝20m/s是车速，f0＝0.2Hz是下截止频率。Among them, G 0 =6.4e-6 is the road surface roughness coefficient, w(t) is the Gaussian white noise input with zero mean value at time t, v=20m/s is the vehicle speed, and f 0 =0.2Hz is the lower cutoff frequency.

5-10s的坡度路面工况在滤波白噪声建立的随机平直路基础上加入坡度为 3％模块。For the 5-10s gradient road condition, a gradient of 3% module is added on the basis of the random straight road established by filtering white noise.

10-15s的连续减速带工况在10s末加入坡度为-3％的消除坡度模块，并且在第11s末加入脉冲模块，此脉冲模块描述的是高0.04m宽0.3m，两条减速带之间间隔2米。In the continuous speed bump working condition of 10-15s, add a slope elimination module with a slope of -3% at the end of 10s, and add a pulse module at the end of the 11s. This pulse module describes a height of 0.04m and a width of 0.3m. 2 meters apart.

采集汽车监测数据，基于七个自由度的汽车运动方程，并仿真路况类别对样本数据进行分类，得到每一路面工况对应的样本数据集合

Figure GDA0002220758990000121
作为训练样本从神经网络的输入层输入，系统的学习规则是让期望输出与实际输出的误差平方和达到某一设定值，以此来调整连接权和阈值向量。当误差减小到设定值后，系统停止学习，此时的权值和阈值被保留在系统内部，成为系统内部知识。作为一种优选，当训练误差
Figure GDA0002220758990000122
时，训练结束；其中，Δδ为训练误差，
Figure GDA0002220758990000123
为输出层向量， n＝1,2,3,4，
Figure GDA0002220758990000124
为对应的样本系数K为阈值，lamda1、lamda2、lamda3是实际输出向量。Collect vehicle monitoring data, classify the sample data based on the vehicle motion equation with seven degrees of freedom, and simulate the road condition category to obtain a sample data set corresponding to each road condition.
Figure GDA0002220758990000121
As training samples are input from the input layer of the neural network, the learning rule of the system is to adjust the connection weight and threshold vector so that the sum of squares of the error between the expected output and the actual output reaches a certain set value. When the error is reduced to the set value, the system stops learning, and the weights and thresholds at this time are retained in the system and become the internal knowledge of the system. As a preference, when the training error
Figure GDA0002220758990000122
When , the training ends; among them, Δδ is the training error,
Figure GDA0002220758990000123
is the output layer vector, n=1,2,3,4,
Figure GDA0002220758990000124
The corresponding sample coefficient K is the threshold, and lamda 1 , lamda 2 , and lamda 3 are the actual output vectors.

输出层向量为

Figure GDA0002220758990000125
The output layer vector is
Figure GDA0002220758990000125

如图4-6所示，采用神经网络算法，得到三种路面工况对应的三个特征加权系数对三个加权系数分别进行均值滤波，保留路面工况改变时刻的变化，其余时间段的值进行滤波处理由于前两秒数据失真，所以从第2秒开始滤波，对lamda1进行滤波，保留7秒前后0.05秒的变化；对lamda2进行滤波，保留7秒和12秒前后0.05秒的变化；对lamda3进行滤波，保留第12秒前后 0.05秒的变化。滤波之后得到三个加权系数。As shown in Figure 4-6, the neural network algorithm is used to obtain three characteristic weighting coefficients corresponding to the three road conditions, and the three weighting coefficients are filtered by the mean value respectively. For filtering processing, due to the distortion of the data in the first two seconds, the filtering starts from the second second, and the lamda1 is filtered, and the change of 0.05 seconds before and after 7 seconds is retained; the lamda2 is filtered, and the change of 0.05 seconds before and after 7 seconds and 12 seconds is retained; lamda3 is filtered to retain the 0.05 second change before and after the 12th second. Three weighting coefficients are obtained after filtering.

得到包含lamda1、lamda2、lamda3是实际输出向量所述加权系数的控制方程包括：The governing equations to obtain the weighting coefficients containing lamda 1 , lamda 2 , and lamda 3 are the actual output vectors include:

Figure GDA0002220758990000126
Figure GDA0002220758990000126

其中，Fk1为左前悬架减振器阻尼力，Fk2为右前悬架减振器阻尼力，Fk3左后悬架减振器阻尼力，Fk4右后悬架减振器阻尼力，为平直路工况下左前轮悬架弹簧垂向载荷力，

Figure GDA0002220758990000128
为坡度路面工况下左前轮悬架减振器阻尼力，
Figure GDA0002220758990000129
为连续减速带工况下左前轮悬架减振器阻尼力，
Figure GDA00022207589900001210
为平直路工况下右前轮悬架减振器阻尼力，
Figure GDA00022207589900001211
为坡度路面工况下右前轮悬架减振器阻尼力，
Figure GDA00022207589900001212
为连续减速带工况下左前轮悬架减振器阻尼力；
Figure GDA00022207589900001213
为平直路工况下左后轮悬架减振器阻尼力，
Figure GDA0002220758990000131
为坡度路面工况下左后轮悬架减振器阻尼力，
Figure GDA0002220758990000132
为连续减速带工况下左后轮悬架减振器阻尼力；
Figure GDA0002220758990000133
为平直路工况下右后轮悬架减振器阻尼力，
Figure GDA0002220758990000134
为坡度路面工况下右后轮悬架减振器阻尼力，为连续减速带工况下左后轮悬架减振器阻尼力。Among them, F k1 is the damping force of the left front suspension shock absorber, F k2 is the damping force of the right front suspension shock absorber, F k3 is the damping force of the left rear suspension shock absorber, F k4 is the damping force of the right rear suspension shock absorber, is the vertical load force of the left front wheel suspension spring under straight road conditions,
Figure GDA0002220758990000128
is the damping force of the shock absorber of the left front wheel suspension under slope road conditions,
Figure GDA0002220758990000129
is the damping force of the shock absorber of the left front wheel suspension under the condition of continuous deceleration belt,
Figure GDA00022207589900001210
is the damping force of the shock absorber of the right front wheel suspension under straight road conditions,
Figure GDA00022207589900001211
is the damping force of the shock absorber of the right front wheel suspension under sloping road conditions,
Figure GDA00022207589900001212
is the damping force of the shock absorber of the left front wheel suspension under the condition of continuous speed bumps;
Figure GDA00022207589900001213
is the damping force of the shock absorber of the left rear wheel suspension under flat and straight road conditions,
Figure GDA0002220758990000131
is the damping force of the shock absorber of the left rear wheel suspension under slope road conditions,
Figure GDA0002220758990000132
is the damping force of the shock absorber of the left rear wheel suspension under the condition of continuous speed bump;
Figure GDA0002220758990000133
is the damping force of the shock absorber of the right rear wheel suspension under straight road conditions,
Figure GDA0002220758990000134
is the damping force of the shock absorber of the right rear wheel suspension under slope road conditions, It is the damping force of the shock absorber of the left rear wheel suspension under the condition of continuous speed bumps.

可见，采用神经网络算法针对不同工况采取不同的控制方式对主动悬架的进行控制，针对不同工况建立神经网络模型，根据实时监测到的汽车状态数据得到不同工况下的汽车悬架的控制系数，并据此悬架减震器阻尼力进行控制，提高汽车的安全性和舒适性，实现平稳切换当路面工况发生变化时，切换控制力会出现卡顿，突变等现象，采用神经网络算法实现主动悬架多工况控制的平滑切换。It can be seen that the neural network algorithm is used to control the active suspension in different working conditions, and the neural network model is established for different working conditions. Control coefficient, and control the damping force of the suspension shock absorber according to this, improve the safety and comfort of the car, and achieve smooth switching. When the road conditions change, the switching control force will appear stuck, sudden changes and other phenomena. The network algorithm realizes the smooth switching of active suspension multi-condition control.

尽管本发明的实施方案已公开如上，但其并不仅仅限于说明书和实施方式中所列运用，它完全可以被适用于各种适合本发明的领域，对于熟悉本领域的人员而言，可容易地实现另外的修改，因此在不背离权利要求及等同范围所限定的一般概念下，本发明并不限于特定的细节和这里示出与描述的图例。Although the embodiment of the present invention has been disclosed as above, it is not limited to the application listed in the description and the embodiment, and it can be applied to various fields suitable for the present invention. For those skilled in the art, it can be easily Therefore, the invention is not limited to the specific details and illustrations shown and described herein without departing from the general concept defined by the appended claims and the scope of equivalents.

Claims (6)

1. A suspension shock absorber damping control switching weighting coefficient determination method based on a neural network is characterized by comprising the following steps:
collecting automobile monitoring data, establishing a seven-degree-of-freedom motion differential equation, and converting vertical displacement of an automobile body, a pitch angle of the automobile body, a roll angle and vertical displacement of front and rear wheels into sample data of a neural network;
classifying the sample data according to road condition types to obtain a sample data set corresponding to each road condition;
respectively establishing a neural network model according to a sample data set corresponding to each road surface working condition, wherein the neural network model comprises the following steps:
constructing a neural network by taking the vertical displacement of the vehicle body, the pitch angle of the vehicle body, the roll angle and the vertical displacement of the front and rear wheels as input layer vectors, and analyzing the input layer vector characteristics in the neural network to obtain a vector group representing a switching weighting coefficient corresponding to the road surface working condition;
fusing all the neural network models into a neural network; and
the road condition is identified according to the real-time monitoring data of the automobile, and a control equation containing the switching weighting coefficient is used as a control strategy to be output;
wherein the road condition categories include: the working conditions of a straight road, a slope road surface and a continuous deceleration strip.
2. The neural network-based suspension shock absorber damping control switching weighting coefficient determining method as claimed in claim 1, wherein said differential equation of motion is:
vertical motion equation of the left front wheel:
Figure FDA0002220758980000011
wherein m isu1Left front wheel unsprung mass, zflThe left front wheel is vertically displaced,
Figure FDA0002220758980000012
the vertical speed of the left front wheel is the speed,
Figure FDA0002220758980000013
is the vertical acceleration, k, of the left front wheeltFor tire stiffness, kfFor suspension stiffness, q1Vertical displacement excited for the road surface of the left front wheel, Fk1Damping force of the left front suspension shock absorber;
equation of vertical motion of the right front wheel:
Figure FDA0002220758980000014
wherein m isu2For the unsprung mass of the right front wheel, zfrIs vertically displaced for the right front wheel,
Figure FDA0002220758980000015
the vertical speed of the right front wheel is set,
Figure FDA0002220758980000016
is the vertical acceleration of the right front wheel, q2Vertical displacement excited for the road surface of the front right wheel, Fk2Damping force of the shock absorber of the right front suspension;
left rear wheel vertical equation of motion:
Figure FDA0002220758980000021
wherein m isu3For left rear wheel unsprung mass, zrlThe left rear wheel is vertically displaced,
Figure FDA0002220758980000022
the vertical speed of the left rear wheel is set,
Figure FDA0002220758980000023
vertical acceleration of the left rear wheel, q3Vertical displacement excited for left rear wheel road surface, Fk3Damping force of the left rear suspension shock absorber;
vertical motion equation of the right rear wheel:
Figure FDA0002220758980000024
wherein m isu4Is the unsprung mass of the right rear wheel, zrrIs used for the vertical displacement of the right rear wheel,
Figure FDA0002220758980000025
is the vertical speed of the right rear wheel,
Figure FDA0002220758980000026
is the vertical acceleration of the right rear wheel, q4Vertical displacement excited for the road surface of the right rear wheel, Fk4Damping force of the rear right suspension shock absorber;
zs1is the vertical displacement of the joint of the left front wheel body and the suspension, zs1＝zs-Lfθ+φB/2；
zs2Is the vertical displacement of the joint of the right front wheel body and the suspension, zs2＝zs-Lfθ-φB/2；
zs3Is the vertical displacement of the joint of the left rear wheel body and the suspension, zs3＝zs+Lrθ+φB/2；
zs4Is the vertical displacement of the joint of the right rear wheel body and the suspension, zs4＝zs+Lrθ-φB/2；
zsFor vertical displacement of the car body, LfIs the distance of the center of mass from the front suspension, LrThe distance between the center of mass and the right hinge point of the suspension is shown, phi is the roll angle of the vehicle body, theta is the pitch angle of the vehicle body, and B is the left and right wheel distance;
the vertical motion equation of the vehicle body is as follows:
Figure FDA0002220758980000027
the pitching motion equation of the vehicle body is as follows:
Figure FDA0002220758980000028
vehicle body roll equation of motion:
Figure FDA0002220758980000029
wherein,
Figure FDA00022207589800000210
the vertical speed of the joint of the left front wheel vehicle body and the suspension,
Figure FDA00022207589800000211
is the vertical speed of the joint of the right front wheel body and the suspension,
Figure FDA00022207589800000212
the vertical speed of the joint of the left rear wheel vehicle body and the suspension,
Figure FDA00022207589800000213
is the vertical speed of the joint of the right rear wheel vehicle body and the suspension,
Figure FDA00022207589800000214
for the pitch angle rate of the vehicle body,
Figure FDA00022207589800000215
for vehicle body roll angular velocity, IxMoment of inertia in the roll direction of the vehicle body, IyIs the moment of inertia in the pitch direction of the vehicle body, CfDamping coefficient of front shock absorber of suspension CrDamping coefficient of rear shock absorber of suspension, Fk1Damping force of left front suspension shock absorber, Fk2Damping force for shock absorber of front right suspension, Fk3Damping force of left rear suspension shock absorber, Fk4And damping force of the rear right suspension shock absorber.
3. The method for determining damping control switching weighting coefficient of suspension shock absorber based on neural network as claimed in claim 2, wherein said neural network is a three-layer neural network model, and the input layer vectors are formatted in sequence to determine the input layer vectors of the three-layer neural network
Figure FDA0002220758980000031
The input layer vector is mapped to a hidden layer, and the hidden layer vector is Y ═{y1,y2,y3,y4…ymM is the number of nodes, and the output layer vector is
Figure FDA0002220758980000032
Figure FDA0002220758980000033
Wherein z issIs a vector of the vertical displacement of the vehicle body,is the vertical speed of the vehicle body, theta is the pitch angle of the vehicle body,
Figure FDA0002220758980000035
is the pitch angle speed of the vehicle body, phi is the roll angle of the vehicle body,
Figure FDA0002220758980000036
is the vehicle body roll angle velocity, zflThe front wheel is vertically displaced,
Figure FDA0002220758980000037
is the vertical speed of the front wheel, zrlIn order to make the rear wheel vertically move,
Figure FDA0002220758980000038
is the rear wheel vertical speed; ladma1Switching the weighting coefficient matrix, ladma, for straight road conditions2For switching weighting coefficient matrix, ladma, for gradient road conditions3A weighting coefficient matrix is switched for the road condition of the continuous deceleration strip,
Figure FDA0002220758980000039
the characteristic weighting coefficient is switched for the left front wheel suspension shock absorber corresponding to the working condition,
Figure FDA00022207589800000310
for right front wheel suspension shock absorber switching characteristics corresponding to operating conditions plusThe weight coefficient is a function of the weight coefficient,
Figure FDA00022207589800000311
the weighting coefficients are switched for the left rear wheel suspension shock absorbers corresponding to the working conditions,
Figure FDA00022207589800000312
and switching the weighting coefficients for the right rear wheel suspension shock absorbers in the corresponding working conditions.
4. The neural network-based suspension shock absorber damping control switching weighting coefficient determining method as claimed in claim 3, wherein the input layer parameters are formatted using the following formula:
Figure FDA00022207589800000313
wherein x isiFor the index coefficient after formatting, TiAs an input layer parameter, TimaxFor input layer parameters corresponding to a maximum value, TiminThe input layer parameters correspond to minimum values.
5. The neural network-based suspension shock absorber damping control switching weighting coefficient determining method as claimed in claim 3, wherein the number of hidden layer nodes is 13.
6. The neural network-based suspension shock absorber damping control switching weighting coefficient determining method as claimed in claim 5, wherein the control equation of the switching weighting coefficient is:
Figure FDA0002220758980000041
wherein, Fk1Damping force of left front suspension shock absorber, Fk2Damping force for shock absorber of front right suspension, Fk3Damping force of left rear suspension shock absorber, Fk4The damping force of the shock absorber of the rear right suspension,the damping force of the left front wheel suspension shock absorber under the straight road working condition,the damping force of the left front wheel suspension shock absorber under the working condition of the slope road surface,
Figure FDA0002220758980000044
the damping force of the left front wheel suspension shock absorber under the working condition of the continuous speed bump,for the damping force of the shock absorber of the right front wheel suspension under the straight road working condition,
Figure FDA0002220758980000046
the damping force of the shock absorber of the right front wheel suspension under the working condition of the slope road surface,
Figure FDA0002220758980000047
the damping force of the left front wheel suspension shock absorber under the working condition of the continuous speed bump is adopted;
Figure FDA0002220758980000048
the damping force of the left rear wheel suspension shock absorber under the straight road working condition,the damping force of the left rear wheel suspension shock absorber under the working condition of the slope road surface,
Figure FDA00022207589800000410
the damping force of the left rear wheel suspension shock absorber is under the working condition of the continuous speed bump;the damping force of the shock absorber of the right rear wheel suspension under the condition of straight road work,
Figure FDA00022207589800000412
the damping force of the rear right wheel suspension shock absorber under the working condition of the slope road surface,
Figure FDA00022207589800000413
the damping force of the left rear wheel suspension shock absorber is under the working condition of the continuous speed bump.
CN201810933191.5A 2018-08-16 2018-08-16 A method for determining the switching weighting coefficient of suspension shock absorber damping control Active CN108859648B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810933191.5A CN108859648B (en) 2018-08-16 2018-08-16 A method for determining the switching weighting coefficient of suspension shock absorber damping control

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810933191.5A CN108859648B (en) 2018-08-16 2018-08-16 A method for determining the switching weighting coefficient of suspension shock absorber damping control

Publications (2)

Publication Number Publication Date
CN108859648A CN108859648A (en) 2018-11-23
CN108859648B true CN108859648B (en) 2020-02-18

Family

ID=64319227

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810933191.5A Active CN108859648B (en) 2018-08-16 2018-08-16 A method for determining the switching weighting coefficient of suspension shock absorber damping control

Country Status (1)

Country Link
CN (1) CN108859648B (en)

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110020499A (en) * 2019-04-19 2019-07-16 南京航空航天大学 A kind of road surface fluctuating disturbance identification method based on inverse Wilson method
JP7189514B2 (en) * 2020-06-02 2022-12-14 トヨタ自動車株式会社 Damping control device and damping control method
CN113752770B (en) * 2020-06-03 2023-09-15 观致汽车有限公司 Semi-active suspension control system and method, computer storage medium, and vehicle
CN113183707B (en) * 2021-05-21 2024-04-02 辽宁工业大学 Design method and system of self-adaptive fixed-period sampling controller of full-vehicle active suspension
CN113183709B (en) * 2021-06-04 2022-09-27 合肥工业大学 Preview control method for automobile electric control suspension
CN113570057B (en) * 2021-09-27 2021-12-14 岚图汽车科技有限公司 Vehicle wheel center vertical displacement measuring method and device based on model training

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE19527323A1 (en) * 1995-07-26 1997-01-30 Siemens Ag Circuit arrangement for controlling a device in a motor vehicle
US6212466B1 (en) * 2000-01-18 2001-04-03 Yamaha Hatsudoki Kabushiki Kaisha Optimization control method for shock absorber
CN101269618B (en) * 2008-04-25 2010-06-02 江苏大学 A control method for electronically controlling the damping value of the three-speed adjustable shock absorber of the air suspension
CN101367324B (en) * 2008-10-15 2011-01-12 江苏大学 A Road Surface Grade Prediction Method Based on Air Suspension Vehicle Height Sensor
CN108274969A (en) * 2018-02-27 2018-07-13 江苏大学 A kind of feed energy suspension and its damping method for handover control based on speed subregion

Also Published As

Publication number Publication date
CN108859648A (en) 2018-11-23

Similar Documents

Publication Publication Date Title
CN108859648B (en) A method for determining the switching weighting coefficient of suspension shock absorber damping control
CN110281727B (en) Inertia control active suspension system and control method based on vehicle pose deviation
CN110712490B (en) An active suspension system based on stacked autoencoder and its working method
CN110654195B (en) Vehicle, vehicle suspension system and adjusting method and device thereof
CN106985627B (en) A vehicle road surface recognition system and suspension mode switching method
CN103754081B (en) The optimum fuzzy compound controller method of Vehicle Suspension with Non-linear Spring
Kumarawadu et al. Neuroadaptive combined lateral and longitudinal control of highway vehicles using RBF networks
WO2024125584A1 (en) Method for optimizing pid control parameters of semi-active suspension of vehicle
CN113591360A (en) Magnetorheological damper structure parameter optimization method based on complete vehicle dynamic model
CN109334378B (en) Vehicle ISD suspension active control method based on single neuron PID control
CN109591537A (en) A kind of automotive semi-active suspension control system and method
CN114379583A (en) A system and method for trajectory tracking of autonomous vehicles based on neural network dynamics model
CN112776551B (en) A method and system for semi-active control of magnetorheological suspension based on motion schema
CN1807135A (en) Apery intelligent control method for harmonizing auto magnetorheological half-initiative suspension according to posture
CN105676694A (en) Intelligent sampling data output feedback control method for automobile suspension system
CN117863803A (en) A road surface recognition and intelligent control method and system based on nonlinear vehicle active suspension
CN115963836A (en) Path tracking and vehicle body posture cooperative control method
Hu et al. Preview control of semi-active suspension with adjustable damping based on machine vision
CN113761768B (en) Integrated optimization design method of magnetorheological damper for vehicle vibration suppression
CN113378408B (en) Optimal control method for whole vehicle coupling of electric control suspension
CN115782496A (en) An Intelligent Evolution Method of Semi-Active Suspension System Based on MAP Control
CN113427961B (en) Automobile active suspension H-infinity switching control method based on T-S fuzzy model
CN117841591B (en) ISD suspension control method based on improved fuzzy neural network PID
CN113183707B (en) Design method and system of self-adaptive fixed-period sampling controller of full-vehicle active suspension
jie Yue et al. Research on vehicle suspension systems based on fuzzy logic control

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