CN112947056A - Magnetic-levitation train displacement speed tracking control method based on IGWO-BP-PID - Google Patents

Magnetic-levitation train displacement speed tracking control method based on IGWO-BP-PID Download PDF

Info

Publication number
CN112947056A
CN112947056A CN202110239290.5A CN202110239290A CN112947056A CN 112947056 A CN112947056 A CN 112947056A CN 202110239290 A CN202110239290 A CN 202110239290A CN 112947056 A CN112947056 A CN 112947056A
Authority
CN
China
Prior art keywords
train
neural network
output
system model
train system
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202110239290.5A
Other languages
Chinese (zh)
Other versions
CN112947056B (en
Inventor
刘湘黔
徐洪泽
田毅
袁志鹏
李鹏
栾瑾
王晓红
刘先恺
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.)
Beijing Jiaotong University
CRRC Qingdao Sifang Co Ltd
Original Assignee
Beijing Jiaotong University
CRRC Qingdao Sifang Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Jiaotong University, CRRC Qingdao Sifang Co Ltd filed Critical Beijing Jiaotong University
Priority to CN202110239290.5A priority Critical patent/CN112947056B/en
Publication of CN112947056A publication Critical patent/CN112947056A/en
Application granted granted Critical
Publication of CN112947056B publication Critical patent/CN112947056B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B11/00—Automatic controllers
    • G05B11/01—Automatic controllers electric
    • G05B11/36—Automatic controllers electric with provision for obtaining particular characteristics, e.g. proportional, integral, differential
    • G05B11/42—Automatic controllers electric with provision for obtaining particular characteristics, e.g. proportional, integral, differential for obtaining a characteristic which is both proportional and time-dependent, e.g. P.I., P.I.D.

Abstract

The invention provides a magnetic-levitation train displacement speed tracking control method based on IGWO-BP-PID. The method comprises the following steps: establishing a train system model according to train dynamics stress analysis, and designing a PID controller according to the train system model; determining the structure of a BP neural network according to the input and the output of a train system model, and training the BP neural network off line based on an improved IGWO algorithm; and obtaining proportional, integral and differential parameters of the PID controller according to the optimized BP neural network model and calculating the traction output of the train system. The invention realizes the real-time parameter adjustment of the PID controller based on the optimized network structure, and realizes the accurate tracking of the speed and the displacement of the train, thereby improving the running performance of the train.

Description

Magnetic-levitation train displacement speed tracking control method based on IGWO-BP-PID
Technical Field
The invention relates to the technical field of magnetic suspension train operation control, in particular to a magnetic suspension train displacement speed tracking control method based on IGWO-BP-PID.
Background
In the high-speed running process of a magnetic suspension train, an automatic driving system needs to accurately and efficiently track a speed curve so as to ensure the safe on-track running of the train. Therefore, the speed tracking control of the magnetic suspension train is the basis of the running of the high-speed magnetic suspension train. However, in the actual running process, the maglev train is subjected to external forces such as air resistance, electromagnetic eddy resistance, ramp resistance and the like, so that the train has large nonlinearity and model parameters are time-varying in the running process.
The traditional PID (proportion-integral-derivative) controller is influenced by the model parameter time change in the train running process, cannot effectively track the ideal speed curve of the train, has larger tracking error and influences the train running performance, therefore, the design of the adaptive speed displacement tracking controller which is suitable for time-varying and non-precise models and has good tracking performance has important engineering application value for automatic and efficient train driving.
Disclosure of Invention
The embodiment of the invention provides a magnetic suspension train displacement speed tracking control method based on IGWO-BP-PID, so as to realize effective tracking control of the displacement speed of the magnetic suspension train.
In order to achieve the purpose, the invention adopts the following technical scheme.
A magnetic suspension train displacement speed tracking control method based on IGWO-BP-PID comprises the following steps:
establishing a train system model according to train dynamics stress analysis, and designing a PID controller according to the train system model;
determining the structure of a BP neural network according to the input and the output of the train system model, and training the BP neural network off line based on an improved Hui wolf optimization algorithm IGWO algorithm to obtain the optimized BP neural network;
acquiring a state vector of the magnetic-levitation train according to the acquired running state information of the magnetic-levitation train, inputting the state vector of the magnetic-levitation train into the optimized BP neural network model, and outputting proportional, integral and differential parameters of a PID controller by the optimized BP neural network model;
and calculating the traction output of the train system in real time according to the proportional, integral and differential parameters of the PID controller and the train system model, and obtaining the real-time displacement speed information of the train according to the traction output of the train system.
Preferably, the establishing of the train system model according to the train dynamics stress analysis includes:
establishing a train system model according to train dynamics stress analysis, wherein the train system model comprises the following steps:
Figure BDA0002961521150000021
Fqfor train tractive effort, FiAs resistance to electromagnetic eddy currents, FaAs air resistance, FsThe slope resistance, m, the car mass, v (t), the train running speed, and x (t), the train displacement state.
Preferably, the designing of the PID controller according to the train system model includes:
designing the following PID controllers according to a train system model:
Figure BDA0002961521150000022
wherein: fq(t) train control tractive effort, kp，ki，kdAdaptive proportional, integral and differential parameters of the controller, respectively, e (t) is the position tracking error,
Figure BDA0002961521150000023
velocity tracking error, of the form:
Figure BDA0002961521150000024
wherein: x is the number of*(t) is a desired position target value of the train, v*(t) is an ideal speed target value of the train;
the discretized PID controller is as follows:
F(t)＝kp[e(t)-e(t-1)]+kie(t)+kd[e(t)-2e(t-2)+e(t-1)]。
preferably, the establishing a structure of the BP neural network according to the input and output of the train system model includes:
setting input information x of BP neural network according to train state informationin(t) including historical error information, current time error information, target value; setting output parameters yo of BP neural networko(t) is proportional, integral, differential parameter of PID controller, that is, yoo(t)＝[kp,ki,kd]T
Determining the structure of the BP neural network according to the input-output state model of the BP neural network as follows:
Figure BDA0002961521150000031
hih(k)＝f(hih(k)) (h＝1,2,...,p)
Figure BDA0002961521150000032
yoo(k)＝f(yio(k)) (o＝1,2,3)
wherein: k denotes the kth sample, f (-) is the activation function, wihConnection weight, w, of input layer and hidden layerhoConnection weight, hi, of hidden layer to output layerh(k) For hidden layer output, p number of hidden layer neurons, bhFor a hidden layer eachThreshold of neuron, boIs the bias of the output layer neurons.
Preferably, the training of the BP neural network offline based on the improved grey wolf optimization algorithm IGWO algorithm to obtain the optimized BP neural network includes:
training a connection weight parameter of the BP neural network based on an improved grey wolf optimization algorithm IGWO algorithm to obtain a weight coefficient of the optimized BP neural network;
initializing parameter w of BP neural networkih,whoAnd the number p of hidden layer neurons;
initializing a population size M and a maximum iteration number I;
generating an initial population x according to the population size Mm；
Calculating the fitness function value of each individual in the population according to the fitness function, and marking the best three individuals as the following individuals according to the fitness values: x is the number ofα,xb,xδ。
And guiding the rest individuals in the rest population to update by utilizing the three optimal individuals, wherein the updating process is as follows:
dα＝|C1·xα-x(t)|,dβ＝|C2·xβ-x(t)|,dδ＝|C3·xδ-x(t)|
x1＝Xα-A1·dα,x2＝Xβ-A2·dβ,x3＝Xδ-A3·dδ
Figure BDA0002961521150000041
wherein: a is 2a r1-a；C＝2·r2，r1,r2Is [0,1 ]]The parameter a is linearly decreased to 0 along with the iteration times;
and (3) mutation operator calculation: randomly selecting s individuals to calculate a mutation operator delta:
Figure BDA0002961521150000042
wherein:
Figure BDA0002961521150000043
Figure BDA0002961521150000045
is a variation constant;
and (3) carrying out variation on the randomly selected s individuals to obtain corresponding variant individuals:
Figure BDA0002961521150000044
and outputting the weight parameters of the BP network according to the optimization result to obtain an optimized BP neural network model.
It can be seen from the technical solutions provided by the embodiments of the present invention that, the embodiments of the present invention provide a PID controller based on a BP network, a weight parameter of a neural network is trained offline based on actual running data of a train through an offline IWGO algorithm, and then real-time parameter adjustment of a speed and displacement tracking controller is realized based on an optimized network structure, so as to realize accurate tracking of train speed and displacement, thereby improving train running performance.
Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a processing flow chart of a magnetic-levitation train displacement velocity tracking control method based on IGWO-BP-PID according to an embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention.
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Further, "connected" or "coupled" as used herein may include wirelessly connected or coupled. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
For the convenience of understanding the embodiments of the present invention, the following description will be further explained by taking several specific embodiments as examples in conjunction with the drawings, and the embodiments are not to be construed as limiting the embodiments of the present invention.
The embodiment of the invention provides a BP neural network-based PID controller of a maglev train, which realizes the high-efficiency tracking of the speed and the position of the train by updating the PID controller parameters in real time under the condition that a maglev train dynamic model is nonlinear time-varying, thereby ensuring the safe and energy-saving running of the train.
The processing flow of the magnetic suspension train displacement speed tracking control method based on IGWO-BP-PID of the embodiment of the invention is shown in figure 1, and comprises the following processing steps:
step S1, establishing a maglev train dynamic model
Establishing a maglev train dynamic model: the maglev train is subjected to external forces such as electromagnetic traction force, electromagnetic eddy resistance, air resistance, ramp resistance and the like in the running process to establish a maglev train dynamic model:
Figure BDA0002961521150000061
wherein: fqFor train tractive effort, FiAs resistance to electromagnetic eddy currents, FaAs air resistance, FsThe slope resistance, m, the car mass, v (t), the train running speed, and x (t), the train displacement state.
Figure BDA0002961521150000062
Figure BDA0002961521150000063
Respectively train running speed and acceleration.
Step S2: designing a PID controller: designing a PID controller of the magnetic-levitation train according to a magnetic-levitation train system model as follows:
Figure BDA0002961521150000071
wherein: fq(t) train control tractive effort, kp，ki，kdThe controller is respectively adaptive to proportional, integral and differential parameters. e (t) is bitThe position of the tracking error is set up,
Figure BDA0002961521150000072
velocity tracking error, of the form:
Figure BDA0002961521150000073
wherein: x is the number of*(t) is an ideal position target value, v*(t) is an ideal speed target value.
Discretization of PID controller: since the train control needs to be periodically controlled, the discretized PID controller is as follows:
F(t)＝kp[e(t)-e(t-1)]+kie(t)+kd[e(t)-2e(t-2)+e(t-1)]
step S3: establishing BP neural network model
Determining the input and output of the BP network: to more effectively utilize train state information, input information x of a neural network is setin(t) including historical error information, current time error information, target value;
the output parameter is proportional, integral and differential parameters of PID controller, that is yoo(t)＝[kp,ki,kd]T。
Determining the structure of the BP network: determining the structure of the BP network according to an input-output state model of the BP network:
Figure BDA0002961521150000074
hih(k)＝f(hih(k)) (h＝1,2,...,p)
Figure BDA0002961521150000075
yoo(k)＝f(yio(k)) (o＝1,2,3)
wherein: k denotes the kth sample, f (-) is the activation function, wihConnection weight, w, of input layer and hidden layerhoConnection weight, hi, of hidden layer to output layerh(k) For hidden layer output, p number of hidden layer neurons, bhThreshold for neurons of the hidden layer, boIs the bias of the output layer neurons.
Step S4: training and optimizing the BP neural network based on an improved grey wolf optimization algorithm (IGWO) to obtain a weight coefficient of the optimized BP neural network: and training the connection weight parameters of the BP neural network based on an improved grey wolf optimization algorithm (IGWO) according to the historical running data information of the train.
Initializing parameters w of the BP networkih,whoAnd the number p of hidden layer neurons;
initializing a population size M and a maximum iteration number I;
generating an initial population x according to the population size Mm；
Calculating the fitness function value of each individual in the population according to the fitness function, wherein the fitness function value is the error between the output of the neural network and the actual output, and the best three individuals are marked as follows according to the fitness values: x is the number ofα,xb,xδ。
And guiding the rest individuals in the rest population to update by utilizing the three optimal individuals, wherein the updating process is as follows:
dα＝|C1·xα-x(t)|,dβ＝|C2·xβ-x(t)|,dδ＝|C3·xδ-x(t)|
x1＝Xα-A1·dα,x2＝Xβ-A2·dβ,x3＝Xδ-A3·dδ
Figure BDA0002961521150000081
wherein: a is 2a r1-a；C＝2·r2。r1,r2Is [0,1 ]]A random number in between. Parameter a random iterationThe generation number is linearly decreased to 0.
And (3) mutation operator calculation: randomly selecting s individuals to calculate a mutation operator delta:
Figure BDA0002961521150000091
wherein:
Figure BDA0002961521150000092
Figure BDA0002961521150000095
is a variation constant.
And (3) carrying out variation on the randomly selected s individuals to obtain corresponding variant individuals:
Figure BDA0002961521150000093
and (3) outputting an offline network structure: and (4) iteratively training the BP neural network according to the process, and outputting model parameters of the BP neural network, wherein the model parameters comprise weight parameters among neurons.
And step S5, acquiring the running state information of the magnetic-levitation train through vehicle-mounted speed and position sensing equipment.
And obtaining the state vector of the magnetic-levitation train according to the acquired running state information of the magnetic-levitation train. And inputting the state vector of the magnetic-levitation train into the optimized BP neural network model, and outputting the proportional, integral and differential parameters of the PID controller by the optimized BP neural network model.
Step S6: and (3) traction output calculation: and calculating the traction output of the train system in real time according to the proportional, integral and differential parameters of the PID controller and the train system model. I.e. according to
Figure BDA0002961521150000094
Wherein k isp,ki,kdFor training the posterior nerveAnd (6) network output.
And then, obtaining real-time displacement speed information of the train according to the traction output of the train system.
In summary, the embodiments of the present invention provide a PID controller based on a BP network, which trains weight parameters of a neural network offline based on actual operation data of a train through an offline IWGO algorithm, and then realizes real-time parameter adjustment of the PID controller based on an optimized network structure, so as to realize accurate tracking of train speed and displacement, thereby improving train operation performance.
The technical scheme of the embodiment of the invention has the advantages of clear principle and simple design, and the PID tracking controller with online adaptive adjustment and good tracking performance is designed aiming at the problem of the position and speed tracking of the maglev train.
Those of ordinary skill in the art will understand that: the figures are merely schematic representations of one embodiment, and the blocks or flow diagrams in the figures are not necessarily required to practice the present invention.
From the above description of the embodiments, it is clear to those skilled in the art that the present invention can be implemented by software plus necessary general hardware platform. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which may be stored in a storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method according to the embodiments or some parts of the embodiments.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for apparatus or system embodiments, since they are substantially similar to method embodiments, they are described in relative terms, as long as they are described in partial descriptions of method embodiments. The above-described embodiments of the apparatus and system are merely illustrative, and the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims (5)

1. A magnetic suspension train displacement speed tracking control method based on IGWO-BP-PID is characterized by comprising the following steps:
establishing a train system model according to train dynamics stress analysis, and designing a PID controller according to the train system model;
determining the structure of a BP neural network according to the input and the output of the train system model, and training the BP neural network off line based on an improved Hui wolf optimization algorithm IGWO algorithm to obtain the optimized BP neural network;
acquiring a state vector of the magnetic-levitation train according to the acquired running state information of the magnetic-levitation train, inputting the state vector of the magnetic-levitation train into the optimized BP neural network model, and outputting proportional, integral and differential parameters of a PID controller by the optimized BP neural network model;
and calculating the traction output of the train system in real time according to the proportional, integral and differential parameters of the PID controller and the train system model, and obtaining the real-time displacement speed information of the train according to the traction output of the train system.
2. The method of claim 1, wherein said modeling a train system based on a train dynamics stress analysis comprises:
establishing a train system model according to train dynamics stress analysis, wherein the train system model comprises the following steps:
Figure FDA0002961521140000011
Fqfor train tractive effort, FiAs resistance to electromagnetic eddy currents, FaAs air resistance, FsThe slope resistance, m, the car mass, v (t), the train running speed, and x (t), the train displacement state.
3. The method of claim 1, wherein designing a PID controller based on the train system model comprises:
designing the following PID controllers according to a train system model:
Figure FDA0002961521140000025
wherein: fq(t) train control tractive effort, kp，ki，kdAdaptive proportional, integral and differential parameters of the controller, respectively, e (t) is the position tracking error,
Figure FDA0002961521140000021
velocity tracking error, of the form:
Figure FDA0002961521140000022
wherein: x is the number of*(t) is a trainIs desired position target value, v*(t) is an ideal speed target value of the train;
the discretized PID controller is as follows:
F(t)＝kp[e(t)-e(t-1)]+kie(t)+kd[e(t)-2e(t-2)+e(t-1)]。
4. the method of claim 1, wherein establishing the structure of the BP neural network based on the input and output of the train system model comprises:
setting input information x of BP neural network according to train state informationin(t) including historical error information, current time error information, target value; setting output parameters yo of BP neural networko(t) is proportional, integral, differential parameter of PID controller, that is, yoo(t)＝[kp,ki,kd]T
Determining the structure of the BP neural network according to the input-output state model of the BP neural network as follows:
Figure FDA0002961521140000023
hih(k)＝f(hih(k))(h＝1,2,...,p)
Figure FDA0002961521140000024
yoo(k)＝f(yio(k))(o＝1,2,3)
wherein: k denotes the kth sample, f (-) is the activation function, wihConnection weight, w, of input layer and hidden layerhoConnection weight, hi, of hidden layer to output layerh(k) For hidden layer output, p number of hidden layer neurons, bhThreshold for neurons of the hidden layer, boIs the bias of the output layer neurons.
5. The method according to claim 1, wherein the training the BP neural network offline based on the improved grayish wolf optimization algorithm IGWO algorithm to obtain the optimized BP neural network comprises:
training a connection weight parameter of the BP neural network based on an improved grey wolf optimization algorithm IGWO algorithm to obtain a weight coefficient of the optimized BP neural network;
initializing parameter w of BP neural networkih,whoAnd the number p of hidden layer neurons;
initializing a population size M and a maximum iteration number I;
generating an initial population x according to the population size Mm；
Calculating the fitness function value of each individual in the population according to the fitness function, and marking the best three individuals as the following individuals according to the fitness values: x is the number ofα,xb,xδ。
And guiding the rest individuals in the rest population to update by utilizing the three optimal individuals, wherein the updating process is as follows:
dα＝|C1·xα-x(t)|,dβ＝|C2·xβ-x(t)|,dδ＝|C3·xδ-x(t)|
x1＝Xα-A1·dα,x2＝Xβ-A2·dβ,x3＝Xδ-A3·dδ
Figure FDA0002961521140000031
wherein: a is 2a r1-a；C＝2·r2，r1,r2Is [0,1 ]]The parameter a is linearly decreased to 0 along with the iteration times;
and (3) mutation operator calculation: randomly selecting s individuals to calculate a mutation operator delta:
Figure FDA0002961521140000032
wherein:
Figure FDA0002961521140000041
Figure FDA0002961521140000042
is a variation constant;
and (3) carrying out variation on the randomly selected s individuals to obtain corresponding variant individuals:
Figure FDA0002961521140000043
and outputting the weight parameters of the BP network according to the optimization result to obtain an optimized BP neural network model.
CN202110239290.5A 2021-03-04 2021-03-04 Magnetic-levitation train displacement speed tracking control method based on IGWO-BP-PID Active CN112947056B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110239290.5A CN112947056B (en) 2021-03-04 2021-03-04 Magnetic-levitation train displacement speed tracking control method based on IGWO-BP-PID

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110239290.5A CN112947056B (en) 2021-03-04 2021-03-04 Magnetic-levitation train displacement speed tracking control method based on IGWO-BP-PID

Publications (2)

Publication Number Publication Date
CN112947056A true CN112947056A (en) 2021-06-11
CN112947056B CN112947056B (en) 2022-10-14

Family

ID=76247579

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110239290.5A Active CN112947056B (en) 2021-03-04 2021-03-04 Magnetic-levitation train displacement speed tracking control method based on IGWO-BP-PID

Country Status (1)

Country Link
CN (1) CN112947056B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116880217A (en) * 2023-09-06 2023-10-13 江西理工大学 Unmanned tracking operation feature modeling method for maglev train

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5268834A (en) * 1991-06-24 1993-12-07 Massachusetts Institute Of Technology Stable adaptive neural network controller
CN104834215A (en) * 2015-03-24 2015-08-12 浙江师范大学 Variation particle swarm optimized BP neural network proportion integration differentiation (PID) control algorithm
KR101770594B1 (en) * 2016-08-19 2017-08-24 한국철도기술연구원 Real time speed of train optimization system and real time speed of train optimization method using the same
CN109376493A (en) * 2018-12-17 2019-02-22 武汉理工大学 A kind of radial base neural net car speed tracking of particle group optimizing
CN110758413A (en) * 2019-10-24 2020-02-07 北京航盛新能科技有限公司 Train speed self-adaptive control method based on system parameter identification
CN111709524A (en) * 2020-07-03 2020-09-25 江苏科技大学 RBF neural network optimization method based on improved GWO algorithm

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5268834A (en) * 1991-06-24 1993-12-07 Massachusetts Institute Of Technology Stable adaptive neural network controller
CN104834215A (en) * 2015-03-24 2015-08-12 浙江师范大学 Variation particle swarm optimized BP neural network proportion integration differentiation (PID) control algorithm
KR101770594B1 (en) * 2016-08-19 2017-08-24 한국철도기술연구원 Real time speed of train optimization system and real time speed of train optimization method using the same
CN109376493A (en) * 2018-12-17 2019-02-22 武汉理工大学 A kind of radial base neural net car speed tracking of particle group optimizing
CN110758413A (en) * 2019-10-24 2020-02-07 北京航盛新能科技有限公司 Train speed self-adaptive control method based on system parameter identification
CN111709524A (en) * 2020-07-03 2020-09-25 江苏科技大学 RBF neural network optimization method based on improved GWO algorithm

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
徐木子等: "基于改进PSO-GWO算法的无人艇路径跟踪控制系统研究", 《武汉理工大学学报》 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116880217A (en) * 2023-09-06 2023-10-13 江西理工大学 Unmanned tracking operation feature modeling method for maglev train
CN116880217B (en) * 2023-09-06 2023-11-10 江西理工大学 Unmanned tracking operation feature modeling method for maglev train

Also Published As

Publication number Publication date
CN112947056B (en) 2022-10-14

Similar Documents

Publication Publication Date Title
Novi et al. Real-time control for at-limit handling driving on a predefined path
CN108520155B (en) Vehicle behavior simulation method based on neural network
CN110758413B (en) Train speed self-adaptive control method based on system parameter identification
CN110456634B (en) Unmanned vehicle control parameter selection method based on artificial neural network
CN113911172A (en) High-speed train optimal operation control method based on self-adaptive dynamic planning
CN112947056B (en) Magnetic-levitation train displacement speed tracking control method based on IGWO-BP-PID
Chen et al. Rhonn modelling-enabled nonlinear predictive control for lateral dynamics stabilization of an in-wheel motor driven vehicle
WO2020098226A1 (en) System and methods of efficient, continuous, and safe learning using first principles and constraints
CN113703319A (en) Joint module inequality constraint optimal robust control method based on reinforcement learning
CN106687871A (en) System and method for controller adaptation
Evans et al. High-speed autonomous racing using trajectory-aided deep reinforcement learning
CN112947055B (en) Method for tracking and controlling displacement speed of magnetic suspension train based on echo state network
CN116050190B (en) Product performance and degradation state analysis method based on digital twinning
CN114987511A (en) Method for simulating human driving behavior to train neural network-based motion controller
CN116620327A (en) Lane changing decision method for realizing automatic driving high-speed scene based on PPO and Lattice
CN108319146B (en) Discrete particle swarm training-based method for radial basis function neural network
CN113759701A (en) High-speed train speed control method and system
CN113419433A (en) Design method of tracking controller of under-actuated system of self-balancing electric wheelchair
Olwan et al. Behavior Evaluation of Vehicle Platoon via Different Fuzzy-X Tuned Controllers
CN112937587A (en) Road feel simulation method based on K-Medoids and classification regression tree
Mao et al. Adaptive position tracking control of high-speed trains with piecewise dynamics
Pasterkamp et al. Optimal design of neural networks for estimation of tyre/road friction
CN116101349A (en) Train speed tracking control method based on equivalent sliding mode and RBF neural network
CN114954567B (en) Parking control method and system for urban rail on-line train
Ding et al. Sliding Mode-Based Distributed Trajectory Tracking Control of Four-body Train Systems

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