Nerve self-adaption fault-tolerant control method for train unknown perturbation
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A fault-tolerant control and self-adaptive technology, applied in self-adaptive control, general control system, control/regulation system, etc., can solve problems such as train impact
Active Publication Date: 2016-12-21
BEIJING JIAOTONG UNIV
View PDF3 Cites 27 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
[0005] The purpose of this invention is to propose a neural adaptive fault-tolerant control strategy for this situation to solve the impact of unknown disturbances and actuator failures on the train
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more
Image
Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0078] The compound control method based on the failure of the train actuator provided in this embodiment is used in the position and speed tracking control when the train actuator fails, such as figure 1 As shown, the method includes the following steps:
[0079] S1. Carry out force analysis on the longitudinal motion of the train, and establish the dynamic equation of the longitudinal motion of the train;
[0080] S2. According to the actuator fault and the dynamic equation of the longitudinal motion of the train, the radial basis function of the neural network is used to approximate the unknown additional resistance, and the dynamic equation of the longitudinal motion of the train under the actuator fault is established;
[0081] S3, constructing an approximate proportional-integral-derivative (PID) sliding mode surface;
[0082] S4. According to the train longitudinal motion dynamic equation under the condition of the actuator failure, the closed-loop dynamic equation of ...
Embodiment 2
[0134] In order to verify the effectiveness of the neural adaptive fault-tolerant control method based on the unknown disturbance of the train provided in this embodiment, MATLAB is used for simulation experiment verification, and a detailed description is given.
[0135] The train single-mass model provided in this embodiment comprehensively considers the impact of unknown actuator faults and additional resistance on the train position and speed tracking performance, and adopts a neural adaptive fault-tolerant controller with an approximate PID sliding surface to make the closed-loop system asymptotically stable. Good position and speed tracking performance, good robustness to faults, and good suppression to unknown disturbances.
[0136] In the simulation experiment, the total length of the train running distance is 83.355 kilometers, and the total mass of the train is m=5×105 kg, gravitational acceleration g=9.8 N / kg, slope angle θ=rand(0,5), total tunnel length l s = 1000 ...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more
PUM
Login to view more
Abstract
The invention relates to a nerve self-adaption fault-tolerant control method for train unknown perturbation. Based on the stress analysis of the longitudinal motion of a train, the longitudinal motion dynamic equation of the train is established. According to an actuator fault and the longitudinal motion dynamic equation of the train, a neural network radial basis function is used to approximate unknown additional resistance. The longitudinal motion dynamic equation of the train in the case of the actuator fault is established, and then a proportional-integral-differential sliding-mode surface is constructed. According to the longitudinal motion dynamic equation of the train in the case of the actuator fault, the closed-loop dynamic equation of train is established through an unknown self-adaption law and a controller. The stability of the system is proved, and then an observer and a controller equation are used to control the actual displacement and velocity of the train to approach expected displacement and velocity. According to the invention, the influence of the actuator fault on the train system can be compensated; the influence of additional resistance on the train system is attenuated or removed; and the train system has a good position and velocity tracking performance.
Description
technical field [0001] The invention relates to the technical field of train control. Specifically, it relates to a neural adaptive fault-tolerant control method based on unknown disturbances of trains. Background technique [0002] The safe operation of trains is very important, and its safety is closely related to people's lives, social development and national progress. How to improve the comfort, convenience and effectiveness of trains is a research direction that attracts attention today. [0003] As people's requirements for train reliability and safety are getting higher and higher, actuator failures, sensor failures, component failures, etc. have attracted widespread attention. Fault-tolerant control is a control strategy that effectively reduces the impact of faults and ensures the expected performance of the system. It is mainly divided into passive fault-tolerant control strategies and active fault-tolerant control strategies. [0004] However, there are relati...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more
Application Information
Patent Timeline
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to view more 
Login to view more