Steady state controller design for aero-engine based on reinforcement learning NNs

2017 ◽  
Author(s):  
Hongmei Zhang ◽  
Shenna Wei ◽  
Guangyan Xu
Keyword(s):  
Reinforcement Learning ◽  
Steady State ◽  
Controller Design ◽  
State Controller ◽  
Aero Engine

Modeling and Control of the Voltage Source Converter

2013 ◽  
Vol 712-715 ◽  
pp. 1760-1766
Author(s):  
Gang Wang ◽  
Zhuo Xin Sun ◽  
Yu Zhu
Keyword(s):  
Steady State ◽  
Pid Control ◽  
Controller Design ◽  
Good Control ◽  
Voltage Source ◽  
Voltage Source Converter ◽  
Modeling And Control ◽  
State Controller ◽  
Control Principle ◽  
And Control

The elementary structure and operation principle of the VSC are introduced. Detailed analysis of the PWM control principle and the steady-state mathematical model. And a steady-state controller design scheme based on the PID control principle is also proposed. The simulation results show that the method have good control ability, quick response to breakdown and good stability.

Robust Stabilizing Controller Design for Inverted Pendulum System

2014 ◽  
Vol 71 (1) ◽  
Author(s):  
Hazem I. Ali
Keyword(s):  
Steady State ◽  
Time Domain ◽  
State Feedback ◽  
Inverted Pendulum ◽  
Controller Design ◽  
H Infinity ◽  
Pendulum System ◽  
Stabilizing Controller ◽  
Inverted Pendulum System ◽  
System Uncertainties

In this paper the design of robust stabilizing state feedback controller for inverted pendulum system is presented. The Ant Colony Optimization (ACO) method is used to tune the state feedback gains subject to different proposed cost functions comprise of H-infinity constraints and time domain specifications. The steady state and dynamic characteristics of the proposed controller are investigated by simulations and experiments. The results show the effectiveness of the proposed controller which offers a satisfactory robustness and a desirable time response specifications. Finally, the robustness of the controller is tested in the presence of system uncertainties and disturbance.

APPLICATION OF NOVEL REINFORCEMENT LEARNING AUTOMATA APPROACH IN POWER SYSTEM REGULATION

2009 ◽  
Vol 18 (08) ◽  
pp. 1609-1625 ◽  
Author(s):  
MOHAMMAD KASHKI ◽  
YOUSSEF L. ABDEL-MAGID ◽  
MOHAMMAD A. ABIDO
Keyword(s):  
Reinforcement Learning ◽  
Pid Controller ◽  
Controller Design ◽  
Learning Automata ◽  
Synchronous Generator ◽  
Optimization Method ◽  
Avr System ◽  
Pid Controller Design ◽  
Analytical System ◽  
Reinforcement Learning Automata

In this paper, a novel efficient optimization method based on reinforcement learning automata (RLA) for optimum parameters setting of conventional proportional-integral-derivative (PID) controller for AVR system of power synchronous generator is proposed. The proposed method is Combinatorial Discrete and Continuous Action Reinforcement Learning Automata (CDCARLA) which is able to explore and learn to improve control performance without the knowledge of the analytical system model. This paper demonstrates the full details of the CDCARLA technique and compares its performance with Particle Swarm Optimization (PSO) as an efficient evolutionary optimization method. The proposed method has been applied to PID controller design. The simulation results show the superior efficiency and robustness of the proposed method.

Sign in / Sign up

Export Citation Format

Share Document