CN116118817A - Active wind-proof control method for high-speed train based on active disturbance rejection control - Google Patents
Active wind-proof control method for high-speed train based on active disturbance rejection control Download PDFInfo
- Publication number
- CN116118817A CN116118817A CN202211672396.5A CN202211672396A CN116118817A CN 116118817 A CN116118817 A CN 116118817A CN 202211672396 A CN202211672396 A CN 202211672396A CN 116118817 A CN116118817 A CN 116118817A
- Authority
- CN
- China
- Prior art keywords
- train
- control
- speed
- active
- wind
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61L—GUIDING RAILWAY TRAFFIC; ENSURING THE SAFETY OF RAILWAY TRAFFIC
- B61L23/00—Control, warning, or like safety means along the route or between vehicles or vehicle trains
- B61L23/08—Control, warning, or like safety means along the route or between vehicles or vehicle trains for controlling traffic in one direction only
- B61L23/14—Control, warning, or like safety means along the route or between vehicles or vehicle trains for controlling traffic in one direction only automatically operated
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61L—GUIDING RAILWAY TRAFFIC; ENSURING THE SAFETY OF RAILWAY TRAFFIC
- B61L27/00—Central railway traffic control systems; Trackside control; Communication systems specially adapted therefor
- B61L27/04—Automatic systems, e.g. controlled by train; Change-over to manual control
Abstract
The invention discloses an active wind-proof control method of a high-speed train based on active disturbance rejection control, which comprises the following steps: firstly, a second-order nonlinear dynamics model of a high-speed train is established, an ADRC controller is designed by combining the dynamics model, then an extended state observer ESO is designed, and a system state and an extended state are estimated in real time by using a state error and a control input; and then based on the error signal, designing a nonlinear feedback control law u by using a fal (DEG) function 0 Recombined with the observed state z 3 For u 0 Compensating to make the controlled object be an integrator series type, and further obtaining the actual control quantity; setting the parameters of the ADRC controller by utilizing the improved GA; and loading the designed GA-ADRC controller information into ATO vehicle-mounted equipment, and completing automatic train operation control according to the real train information. The real-time running data of the train is saved and uploaded, and the GA-ADRC control strategy in the simulation environment is further carried outOptimizing, so that the method is more suitable for the real train running environment.
Description
Technical Field
The invention relates to the technical field of automatic operation control of high-speed trains, in particular to an active wind-proof control method of a high-speed train based on active disturbance rejection control.
Background
The areas of China are wide, the geological environment is complex and changeable, and high-speed railway lines in special wind environments such as viaducts, tunnels, hills, mountains and the like are numerous. When the train runs in a strong wind environment, the pneumatic overturning moment of the train can be obviously increased, the impact action between wheel tracks can be enhanced by huge buoyancy and air resistance, the train is forced to slow down to cause large-area delay of a wire net if the train is light, and serious consequences such as derailment overturning, casualties and the like of the train are caused if the train is heavy. Therefore, the wind prevention strategy research needs to be conducted deeply, and powerful support is provided for safe and stable operation of high-speed rails, rapid emergency after disaster and the like.
In view of the importance of the safe running problem of trains in strong wind environments, expert scholars at home and abroad have conducted a great deal of effective research. However, most of the current research results are based on aerodynamic and hydrodynamic analysis, and an external reference scheme is provided for safe operation of the train in a strong wind environment from the aspects of setting a wind shielding device, establishing a wind early warning and monitoring system, optimizing a train suspension system and the like, so that the method cannot be organically combined with a high-speed train automatic driving system (Automatic Train Operation system, ATO). In short, active windbreak control strategies based on ATO systems are currently less common.
The ATO system structure of the high-speed train is shown in figure 1, and the communication between the vehicle-mounted equipment and the ground equipment is completed based on the GSM-R network, so that the platform door control, the data transmission between the stations and the operation planning processing are realized. In addition, through additionally arranging an interface between the train and the vehicle-mounted equipment, signals such as an ATO start button, a handle level, a marshalling running state and the like can be provided for the vehicle-mounted equipment by the vehicle, and effective traction/braking instructions can also be provided for the vehicle by the vehicle-mounted equipment, so that automatic adjustment of the speed of the train is realized. The ATO system is based on bidirectional real-time information interaction of the train and ground, and can automatically send out control instructions by the train without manual operation, thereby realizing the functions of tracking target tracks, accurately stopping, automatically opening and closing doors and the like. Currently, there are many control theories applied to the design of ATO systems for high speed trains, such as: PID control, model predictive control, inversion control, neural network control, or a combination of control modes. The safety of train operation can be greatly reduced due to strong wind disturbance, and higher requirements are also put forward on the immunity of an ATO system control algorithm, and whether the control algorithm can be applied to train operation control in a strong wind environment or not is yet to be further verified.
According to the above-mentioned research situation, it can be known that the following key points are required to be satisfied in designing the ATO control strategy of the high-speed train suitable for the strong wind disturbance environment: (1) The dynamics model adopted should be capable of accurately describing the dynamics of the train in the strong wind environment. (2) The algorithm has strong robustness, and stable control effect can be still realized under the constraint conditions of uncertain parameters, disturbance abnormality, actuator saturation, faults and the like. (3) The algorithm model needs to have strong self-adaptability, and can be applied to different train numbers, different line environments, different initial states and the like. (4) The device has simple structure and low complexity, and enables the controlled object to achieve the effects of rapid convergence and high-precision tracking on the premise of not depending on the accurate model of the controlled object. The dynamic model adopted in the design process of the operation control algorithm of the high-speed train at present does not consider parameter uncertainty caused by strong wind factors.
Disclosure of Invention
Aiming at the problem that the parameter uncertainty caused by strong wind factors is not considered in the design process of a high-speed train operation control algorithm in the prior art, the invention provides an active wind prevention control method for a high-speed train based on active disturbance rejection control.
The invention provides an active anti-interference control-based active windproof control method for a high-speed train, which comprises the following steps:
s1, suppressing running errors caused by incompletely repeated strong wind disturbance on a high-speed train, and an accurate and clear mathematical model is required. The train speed and the ambient wind speed have vector superposition relation, and when the wind direction and the train form a certain angle, a second-order nonlinear dynamics model of the high-speed train is established in consideration of the wind direction angle and the slip angle:
wherein p is the real-time position of the train, V is the running speed of the train, R b Is the basic resistance, d is the disturbance of strong wind, R msc R is the mechanical basic resistance a Is the air basic resistance, c is the basic resistance coefficient, ρ is the air density, S t Is the maximum cross-sectional area of the train, alpha is the wind direction angle, beta is the slip angle, v w Is the wind speed;
s2, designing an ADRC controller by combining the dynamic model of the step S1; in order to enhance the robustness of ADRC and enable the system to achieve overshoot-free tracking, a differential tracker TD form is designed as follows:
in the formula, v 1 Tracking value v for TD output 2 V is 1 K is the sampling times and h is the sampling period; delta is a tracking speed factor, fst (DEG) is a fastest control integral function, h 0 Is a filtering factor.
S3, taking the sum of the basic resistance, the additional resistance and the external disturbance of the dynamic model in the step S1 as an expansion state x 3 ，
x 3 ＝-f b (v,t)-f a (p,v,t)+d(t)
Wherein f b (v, t) and f a (p, v, t) basic resistance and additional resistance of the train at the position and speed of a certain moment respectively, and d (t) represents random disturbance caused by strong wind.
An extended state observer ESO is designed, the state error and the control input are utilized to estimate the system state and the extended state in real time, and the ESO is designed as follows:
wherein ε is the observed error, z 1 、z 2 And z 3 V respectively 1 、v 2 Expanded state x 3 Is a function of the estimated value of (2); v 1 Tracking value, v, output for TD 2 V is 1 K is the sampling times and h is the sampling period; u and y are the input and output of the controlled object, i.e. the traction/braking force and real-time speed of the trainB is a controlled object parameter; beta 1 、β 2 And beta 3 Gain for observer; fal () is a nonlinear saturation function capable of attenuating buffeting, gamma, of the switching interval caused by high gain 1 A is the linear interval width of the nonlinear saturation function 1 And alpha 2 The order of the power of the nonlinear saturation function.
S4, designing a nonlinear feedback control law u by utilizing a fal (level) function according to the generated error signal 0 Recombined with the observed state z 3 For u 0 Compensating to make the controlled object be an integrator series type, and further obtaining the actual control quantity; the nonlinear feedback control law is designed in the form of PD combinations:
wherein ε 1 And epsilon 2 K is the difference between the transition signal and the observed signal p As proportional term coefficient, k d Is a differential term coefficient; gamma ray 2 Linear interval width, α, as a function of fal () 3 And alpha 4 Is the power; u is a nonlinear feedback control law, u 0 The final actual control law after the observer compensation.
S5, setting parameters of an ADRC controller: optimization of ESO observer gain beta using genetic algorithm GA 1 、β 2 、β 3 Nonlinear feedback control law gain k p 、k d There are 5 parameters. The method specifically comprises the following substeps:
s51, initializing a population; determining a parameter range to be optimized, a fitness function, a population scale and a genetic algebra; the fitness function is as follows:
wherein E is a speed tracking error, E is an error allowable range, and P is a penalty value; u is the actual control quantity, u max And u min Traction and braking upper limits, respectively; j is comprehensiveTracking errors and inputting limited evaluation indexes.
S52, simulating an active disturbance rejection algorithm, and calculating the fitness value of each individual according to the fitness function;
s53, adopting a roulette algorithm, selecting a group with small fitness function from the current group, and inheriting the group into the next generation;
s54, designing a self-adaptive crossing mode; according to adaptive cross variation probability P cross 2 genes are selected for chromosome exchange at the same position; wherein the probability P cross The calculation method of (1) is as follows:
wherein f avg And f max Respectively an average fitness value and a maximum fitness value of the population, p 1 And p 2 And f is the current fitness value of the population, and is the maximum and minimum values of the cross/mutation probability prompt.
S55, performing mutation operation according to the self-adaptive multi-bit mutation operator;
s56, ending the algorithm when the genetic algebra reaches a set value or the fitness value is not changed any more; otherwise, the process returns to S52.
S6, loading the designed GA-ADRC controller information into ATO vehicle-mounted equipment, and completing automatic train operation control according to the real train information;
and S7, saving and uploading real-time running data of the train, and further optimizing the GA-ADRC control strategy in the simulation environment to enable the GA-ADRC control strategy to be more suitable for the real train running environment.
Compared with the prior art, the invention has the following advantages:
(1) The accurate dynamics model is the basis and premise of controlling the design of the optimization algorithm. According to the invention, the real-time wind speed, wind direction and other influencing factors are fused to establish a train dynamics model, and the model describes the relation between the air resistance characteristic and the running state of the train in a strong wind environment, so that the dynamics characteristic of the train can be described more accurately.
(2) The automatic disturbance rejection control strategy combined with the improved genetic algorithm is applied to the algorithm design of the automatic driving system of the high-speed train, so that the dependence of the controller on an accurate controlled object model is weakened, the disturbance rejection is strong, the automatic disturbance rejection control system is suitable for severe external environments such as strong wind, and under the condition that parameter uncertainty and external disturbance exist in the system model, the rapid convergence and high-precision tracking of the operation error can be realized, and the aim point performance and the comfort of the operation of the high-speed train are facilitated.
(3) And the ADRC controller parameters are further adjusted and optimized by combining an artificial intelligence algorithm, so that the defects of low efficiency, time and labor waste of the traditional experience adjustment mode are overcome. By combining the improved genetic algorithm with the active disturbance rejection control, the automatic setting and optimization of the parameters of the controller are realized. When the fitness function is designed, the inherent saturation characteristic of the traction motor of the high-speed train is considered, the control input is used as an additional weighting index, the problem of overlarge control signals is avoided, and the safety of the train is effectively improved.
Additional advantages, objects, and features of the invention will be set forth in part in the description which follows and in part will become apparent to those having ordinary skill in the art upon examination of the following or may be learned from practice of the invention.
Drawings
FIG. 1, ATO system architecture diagram of a high speed train.
FIG. 2 is a stress analysis chart.
FIG. 3, ADRC block diagram.
Fig. 4 is a process diagram of parameter optimization of the active disturbance rejection controller.
Fig. 5, comparison of the algorithm before and after improvement.
Fig. 6, velocity tracking effect diagram.
Fig. 7, ESO observation effect diagram.
Fig. 8, parameter tuning graphs.
Fig. 9 is a comparison chart of algorithm control effects.
Detailed Description
The preferred embodiments of the present invention will be described below with reference to the accompanying drawings, it being understood that the preferred embodiments described herein are for illustration and explanation of the present invention only, and are not intended to limit the present invention.
In the active wind prevention control method for the high-speed train based on active disturbance rejection control, in step S1, the operation stress analysis of the high-speed train is shown in figure 2, wherein v w Representing wind speed, v tw Vector combination of representative wind speed and train speed; alpha represents a wind direction angle, which is an included angle between the wind speed direction and the opposite direction of train running, and the value range is more than or equal to 0 degree and less than or equal to 180 degrees; beta represents the slip angle, which is the angle between the combined speed and the train running in the opposite direction. Establishing a second-order nonlinear dynamics model of the high-speed train:
in step S2, in combination with the dynamics model of step S1, a second-order ADRC controller is designed for a high-speed train system with uncertain parameters and external disturbance, and the structure of the second-order ADRC controller is shown in fig. 3. ADRC consists essentially of a tracking differentiator (Tracking Differentiator, TD), a distension state observer (Extended State Observer, ESO), and a nonlinear error feedback law (Nonlinear State Error Feedback, NLSEF). The TD is mainly used for acquiring a transition signal and a differential signal of a target point, avoiding large overshoot caused by overlarge errors generated in an initial stage, the ESO is used for observing an expansion state (namely the sum of system uncertainty and disturbance caused by strong wind) in real time, and the NLSEF is used for compensating the disturbance to form an integral series control law. The design form of TD is as follows:
in step S5: ADRC controller parameter tuning. Optimizing ESO gain beta using improved genetic algorithm (GeneticAlgorithm, GA) 1 、β 2 、β 3 Nonlinear feedback control law gain k p 、k d A total of 5 parameters, the specific optimization procedure is shown in fig. 4.
Fig. 5 is a comparison of the algorithm before and after improvement. As can be seen from fig. 5, the improved algorithm starts to converge at about 15 generations, and compared with the genetic algorithm with fixed cross variation probability, the improved algorithm has the advantages of faster convergence speed, smaller adaptation value, and improved operation efficiency and control precision.
In step S6, the designed GA-ADRC controller information is loaded into ATO vehicle-mounted equipment, and automatic train operation control is completed according to the real train information.
Step S7: and saving and uploading real-time running data of the train, and further optimizing the GA-ADRC control strategy in the simulation environment to enable the GA-ADRC control strategy to be more suitable for the real train running environment.
The train tracking effect of the improved GA-based ADRC controller is shown in fig. 6. The method has the advantages that fine errors appear in the starting, braking and speed adjusting stages, high-precision tracking is kept in other running stages, the speed tracking error of a high-speed train is less than +/-0.3 km/h, the speed and position error convergence speed is high, the requirements of accurate stopping and accurate points are met, and the matching performance of the wind resistance model and the active disturbance rejection control algorithm designed by the method is embodied.
Fig. 7 shows the observed effect of ESO on the operating state and the expanded state. It can be seen that the ESO has a good observation effect on the train running state and the disturbance caused by strong wind, and can meet the design requirement of the follow-up control law. The optimal observer and controller parameters were obtained over 30 iterations as shown in fig. 8.
To embody the advantages of GA-ADRC in terms of control accuracy and accuracy, it is compared with PID controllers and empirically tuning ADRC. The comparison experiment is loaded with the same running environment and train dynamics model, the result is shown in fig. 9, and the comparison of the algorithm control effects is shown in table 1. It can be seen that the tracking error of the PID is more obvious, and more obvious fluctuation exists; although the control effect of ADRC in each stage is better than that of PID control strategy, compared with GA-ADRC, the tracking error of the empirically-set ADRC is larger, and the requirement of safe and accurate vehicle control is difficult to meet. Therefore, the GA-ADRC controller designed by the invention has better robustness and safety.
Table 1, algorithm control effect vs
| Control strategy | Tracking error (m/s) | Accumulated tracking error (m/s) |
| GA-ADRC | ±0.32 | 1.77 |
| ADRC | ±0.48 | 2.52 |
| PID | ±0.66 | 7.43 |
In conclusion, compared with the traditional davis resistance model, the model constructed by the invention is suitable for the dynamic characteristics characterization model of the train in the strong wind running environment, and the model is more in line with the relation between the wind speed, the wind direction, the train speed and the air resistance, and is more refined modeling. Considering that the Active Disturbance Rejection Control (ADRC) is a control method independent of accurate modeling of a system, compared with the defects of the control strategy, the active disturbance rejection controller has simple structure and strong robustness, can take internal disturbance and undetectable external disturbance of a model as the expansion state of the system, realizes accurate observation and real-time compensation of total disturbance through an expansion state observer and a feedback mechanism, is very suitable for the design of a strong nonlinear and uncertain system such as a high-speed train, combines a train dynamics model in a wind environment with an active disturbance rejection control principle, and aims at accurate speed tracking and low handle switching frequency to design an active wind rejection control strategy. In addition, in order to obtain a global optimal solution of the active disturbance rejection parameters, control accuracy is improved, and an active disturbance rejection controller parameter setting optimization strategy is designed in combination with an improved genetic algorithm. When the fitness function is designed, the inherent saturation characteristic of the traction motor of the high-speed train is considered, the control input is used as an additional weighting index, the problem of overlarge control signals is avoided, the safety of the train is effectively improved, and theoretical reference is provided for realizing safe operation of the train in a strong wind environment.
The present invention is not limited to the above-mentioned embodiments, but is intended to be limited to the following embodiments, and any modifications, equivalents and modifications can be made to the above-mentioned embodiments without departing from the scope of the invention.
Claims (4)
1. The active wind-proof control method for the high-speed train based on the active disturbance rejection control is characterized by comprising the following steps of:
s1, establishing a second-order nonlinear dynamics model of the high-speed train:
wherein p is the real-time position of the train, V is the running speed of the train, R b Is the basic resistance, d is the disturbance of strong wind, R msc R is the mechanical basic resistance a Is the air basic resistance, c is the basic resistance coefficient, ρ is the air density, S t Is the maximum cross-sectional area of the train, alpha is the wind direction angle, beta is the slip angle, v w Is the wind speed;
s2, designing an ADRC controller by combining the dynamic model of the step S1;
s3, taking the sum of the basic resistance, the additional resistance and the external disturbance of the dynamic model in the step S1 as an expansion state x 3 ，
x 3 ＝-f b (v,t)-f a (p,v,t)+d(t)
Wherein f b (v, t) and f a (p, v, t) basic resistance and additional resistance of the train at the position and speed of a certain moment respectively, and d (t) represents random disturbance caused by strong wind.
An extended state observer ESO is designed, the state error and the control input are utilized to estimate the system state and the extended state in real time, and the ESO is designed as follows:
wherein ε is the observed error, z 1 、z 2 And z 3 V respectively 1 、v 2 Expanded state x 3 Is a function of the estimated value of (2); v 1 Tracking value, v, output for TD 2 V is 1 K is sampling times, h is a sampling period, u and y are input quantity and output quantity of the controlled object respectively, namely traction/braking force and real-time speed of the train, and b is a parameter of the controlled object; beta 1 、β 2 And beta 3 Gain for observer; fal (-) is a nonlinear saturation function, γ 1 Is the width of a linear interval alpha 1 And alpha 2 Is the power;
s4, designing a nonlinear feedback control law u by utilizing a fal (level) function according to the generated error signal 0 Recombined with the observed state z 3 For u 0 Compensating to make the controlled object be an integrator series type, and further obtaining the actual control quantity; the nonlinear feedback control law is designed in the form of PD combinations:
wherein ε 1 And epsilon 2 K is the difference between the transition signal and the observed signal p As proportional term coefficient, k d Is a differential term coefficient; gamma ray 2 Linear interval width, α, as a function of fal () 3 And alpha 4 An order of powers; u is a nonlinear feedback control law, u 0 The final actual control law after the observer compensation.
S5, setting parameters of an ADRC controller: optimization of ESO observer gain beta using genetic algorithm GA 1 、β 2 、β 3 Nonlinear feedback control law gain k p 、k d A total of 5 parameters;
s6, loading the designed GA-ADRC controller information into ATO vehicle-mounted equipment, and completing automatic train operation control according to the real train information;
and S7, saving and uploading real-time running data of the train, and further optimizing the GA-ADRC control strategy in the simulation environment to enable the GA-ADRC control strategy to be more suitable for the real train running environment.
2. The active wind prevention control method for high-speed trains based on active disturbance rejection control according to claim 1, wherein in the ADRC controller of step S2, a differential tracker TD is designed as follows:
in the formula, v 1 Tracking value v for TD output 2 V is 1 K is the sampling times and h is the sampling period; delta is a tracking speed factor, fst ()'s is the fastest control integral function; h is a 0 Is a filtering factor.
3. The active wind-proof control method for high-speed train based on active disturbance rejection control according to claim 1, wherein the step S5 comprises the following sub-steps:
s51, initializing a population; determining a parameter range to be optimized, a fitness function, a population scale and a genetic algebra;
s52, simulating an active disturbance rejection algorithm, and calculating the fitness value of each individual according to the fitness function;
s53, adopting a roulette algorithm, selecting a group with small fitness function from the current group, and inheriting the group into the next generation;
s54, designing a self-adaptive crossing mode;
s55, performing mutation operation according to the self-adaptive multi-bit mutation operator;
s56, ending the algorithm when the genetic algebra reaches a set value or the fitness value is not changed any more; otherwise, the process returns to S52.
4. The active wind prevention control method for a high-speed train based on active disturbance rejection control according to claim 1, wherein in the step S51, the fitness function is:
wherein E is a speed tracking error, E is an error allowable range, and P is a penalty value; u is the actual control quantity, u max And u min Traction and braking upper limits, respectively; j is the comprehensive tracking error and the input limited evaluation index.
The active wind prevention control method for high-speed train based on active disturbance rejection control according to claim 1, wherein in step S54, the adaptive cross variation probability P is used cross 2 genes are selected for chromosome exchange at the same position; wherein the probability P cross The calculation method of (1) is as follows:
wherein f avg And f max Respectively an average fitness value and a maximum fitness value of the population, p 1 And p 2 And f is the current fitness value of the population, and is the maximum and minimum values of the cross/mutation probability prompt.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211672396.5A CN116118817B (en) | 2022-12-26 | 2022-12-26 | Active wind-proof control method for high-speed train based on active disturbance rejection control |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211672396.5A CN116118817B (en) | 2022-12-26 | 2022-12-26 | Active wind-proof control method for high-speed train based on active disturbance rejection control |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116118817A true CN116118817A (en) | 2023-05-16 |
| CN116118817B CN116118817B (en) | 2023-09-15 |
Family
ID=86303782
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211672396.5A Active CN116118817B (en) | 2022-12-26 | 2022-12-26 | Active wind-proof control method for high-speed train based on active disturbance rejection control |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116118817B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101126817A (en) * | 2007-09-30 | 2008-02-20 | 西南交通大学 | Train windbreak safe monitoring, controlling method and its device |
| JP2014090566A (en) * | 2012-10-30 | 2014-05-15 | Mitsubishi Electric Corp | Automatic train control system |
| CN109725644A (en) * | 2019-01-22 | 2019-05-07 | 湖南云顶智能科技有限公司 | A kind of hypersonic aircraft linear optimization control method |
| CN111391887A (en) * | 2019-12-05 | 2020-07-10 | 中车工业研究院有限公司 | High-speed train control method and design method of robust controller thereof |
| CN112346346A (en) * | 2020-12-04 | 2021-02-09 | 华东交通大学 | Heavy-load train speed tracking control method and system |
| CN114275012A (en) * | 2022-03-04 | 2022-04-05 | 西南交通大学 | Self-adaptive control method for train control level |
-
2022
- 2022-12-26 CN CN202211672396.5A patent/CN116118817B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101126817A (en) * | 2007-09-30 | 2008-02-20 | 西南交通大学 | Train windbreak safe monitoring, controlling method and its device |
| JP2014090566A (en) * | 2012-10-30 | 2014-05-15 | Mitsubishi Electric Corp | Automatic train control system |
| CN109725644A (en) * | 2019-01-22 | 2019-05-07 | 湖南云顶智能科技有限公司 | A kind of hypersonic aircraft linear optimization control method |
| CN111391887A (en) * | 2019-12-05 | 2020-07-10 | 中车工业研究院有限公司 | High-speed train control method and design method of robust controller thereof |
| CN112346346A (en) * | 2020-12-04 | 2021-02-09 | 华东交通大学 | Heavy-load train speed tracking control method and system |
| CN114275012A (en) * | 2022-03-04 | 2022-04-05 | 西南交通大学 | Self-adaptive control method for train control level |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116118817B (en) | 2023-09-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112193280B (en) | Heavy-load train reinforcement learning control method and system | |
| CN111142374B (en) | Speed control method of automatic driving system of suspension type permanent magnet maglev train | |
| CN113283156B (en) | Energy-saving control method for subway station air conditioning system based on deep reinforcement learning | |
| CN107943022A (en) | A kind of PID locomotive automatic Pilot optimal control methods based on intensified learning | |
| US20220180023A1 (en) | Speed Tracking Control Method and System for Heavy-Haul Train | |
| CN113911172A (en) | High-speed train optimal operation control method based on self-adaptive dynamic planning | |
| CN110758413A (en) | Train speed self-adaptive control method based on system parameter identification | |
| Ali et al. | Combined ANFIS method with FA, PSO, and ICA as Steering control optimization on electric car | |
| CN116118817B (en) | Active wind-proof control method for high-speed train based on active disturbance rejection control | |
| CN114275012B (en) | Self-adaptive control method for train control level | |
| CN112947094A (en) | Temperature control PID parameter self-adjusting method for rotary cement kiln | |
| CN113085963B (en) | Dynamic regulation and control method and dynamic regulation and control device for train control level | |
| CN112733448B (en) | Parameter self-learning double Q table combined agent establishing method for automatic train driving system | |
| CN112464453B (en) | Operation speed curve planning simulation method considering dynamic response process of train | |
| CN112109773B (en) | Train speed control method based on H infinity and multi-objective optimization | |
| CN113147768A (en) | Multi-algorithm fusion prediction-based automobile road surface state online estimation system and method | |
| CN114547774B (en) | Heavy-load train arrival curve optimization method and system | |
| CN115871742A (en) | Control method of man-machine hybrid driving intelligent train under multiple scenes | |
| Liu et al. | Research on Model Predictive Control Method of Heavy-Haul Trains Based on Multi-Point Model | |
| CN117369286B (en) | Dynamic positioning control method for ocean platform | |
| Lin et al. | Research on speed tracking control algorithm of the high-speed train based on equivalent sliding mode and RBF neural network | |
| Gao et al. | Study on Multi-Objective Intelligent Speed Controller Model of Automatic Train Operation for High Speed Train Based on Grey System Theory and Genetic Algorithm | |
| CN116909145A (en) | Heavy-duty train speed tracking control method for long and large downhill circulating braking | |
| Yang et al. | Research on Multi-objective Optimal Control of Heavy Haul Train Based on Improved Genetic Algorithm | |
| CN116736689A (en) | Magnetic levitation train suspension feedback control method based on neural network tracking differentiator |
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 |