Cooperative fault-tolerant control method for heterogeneous multi-agent systems based on rbf neural network
A multi-agent system and neural network technology, which is applied in the field of cooperative fault-tolerant control of heterogeneous multi-agent systems, can solve problems such as difficulty in realizing cooperative fault-tolerant control, and achieve the effect of strong robustness and anti-disturbance.
Active Publication Date: 2021-11-23
NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
View PDF7 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] In order to solve the technical problems proposed by the above-mentioned background technology, the present invention aims to provide a heterogeneous multi-agent system cooperative fault-tolerant control method based on RBF neural network, to overcome the problem that it is difficult to realize cooperative fault-tolerant control due to different agents
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0074] The present invention takes the following 4 unmanned cars and 2 quadrotor UAVs as implementation objects, wherein x(t)=[x, y, z] T , x, y and z represent the displacement of the unmanned vehicle in the directions of x-axis, y-axis and z-axis respectively; v(t)=[v x , v v , v z ] T , v x , v y and v z Represent the speed of the x-axis, y-axis and z-axis direction of the unmanned vehicle respectively; u(t)=[u x , u y , u z ] T , u x , u y and u z represent the control input of the unmanned aerial vehicle in the directions of x-axis, y-axis and z-axis respectively. In view of the different motion dimensions of drones and unmanned vehicles, in order to facilitate coordinated control, the displacement, speed and control input of the unmanned vehicle in the z-axis direction are all 0 by default.
[0075] Consider the following dynamic equations for an unmanned vehicle:
[0076]
[0077] Among them, take n=3, x i (t)∈R n , v i (t)∈R n and ui (t)∈R n Repre...
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 present invention discloses a collaborative fault-tolerant control method for a heterogeneous multi-agent system based on RBF neural network: firstly, assuming that all the agents can obtain a predetermined trajectory and speed, through the communication link between the heterogeneous multi-agents, Construct the communication topology of the heterogeneous multi-agent system and express it in a directed graph, and calculate the Laplacian matrix; then, analyze the dynamic equation of each agent in detail, considering the multiplicative fault and additive fault of the actuator In the case of , a unified second-order dynamic equation is formed; based on the RBF neural network self-adaption theory and the communication network link, the cooperative fault-tolerant controller of the heterogeneous multi-agent system is designed, and the heterogeneous multi-agent system is obtained based on the consistency theory. The global dynamic equation realizes the cooperative fault-tolerant control of the system. The invention overcomes the problem that the heterogeneous multi-agent system is difficult to coordinate fault-tolerant control due to the difference in the structure of the internal agents, and makes the system have strong robustness and anti-disturbance performance.
Description
technical field [0001] The invention relates to a collaborative fault-tolerant control method for heterogeneous multi-agent systems based on RBF neural network, belonging to the technical field of heterogeneous multi-agent systems. Background technique [0002] In recent years, the unmanned combat system, as a subversive technical equipment that changes the future war mode, has developed rapidly around the world and has become an important force in the military game between countries. Facing the requirements of future combat applications, the heterogeneous unmanned swarm system composed of unmanned aerial vehicle and unmanned vehicle has important research value. [0003] Due to the heterogeneous characteristics of UAVs and unmanned vehicles, the difficulty of formation control increases sharply. There are huge differences between drones and unmanned vehicles. For example, they have different working spaces, different dynamic characteristics, and different speed limits. The...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G05B13/04
CPCG05B13/027G05B13/042
Inventor 张柯任意姜斌丁勇
Owner NANJING UNIV OF AERONAUTICS & ASTRONAUTICS