Control Technology for Power Resources Based on Improved Q Learning Algorithm for Automated Intelligent Control

2018 ◽  
Vol 22 (7) ◽  
pp. 1065-1070
Author(s):  
Run Ma ◽  
Keyword(s):  
Control Method ◽  
Learning Algorithm ◽  
Network Services ◽  
Power Resource ◽  
Q Learning ◽  
Control Power ◽  
Power Resources ◽  
Femtocell Network ◽  
Indoor Wireless ◽  
And Control

With the advancement in internet technologies, requirements for quality of indoor wireless communication have increased. Femtocell, which is an effective approach to improve indoor communication quality, can provide highly-efficient indoor network services for users. This study puts forward a power resource control method based on Q learning algorithm for improved solutions to the problems of frequency spectrum and power resource allocation of a two-tier femtocell network. The algorithm was further improved, and was compared with the traditional algorithm via a simulation experiment. It was found that the improved Q learning algorithm could enhance the message capacity and control power resource; this provides a reference for the application of Q learning algorithm in femtocell communication.

scholarly journals Design and Simulation of Adaptive PID Controller Based on Fuzzy Q-Learning Algorithm for a BLDC Motor

2020 ◽  
Author(s):  
Reza Rouhi Ardeshiri ◽  
Nabi Nabiyev ◽  
Shahab S. Band ◽  
Amir Mosavi
Keyword(s):  
Reinforcement Learning ◽  
Pid Controller ◽  
Control Method ◽  
Learning Algorithm ◽  
Bldc Motor ◽  
Motor Speed ◽  
Q Learning ◽  
Brushless Dc ◽  
Intelligent Control Systems ◽  
And Control

Reinforcement learning (RL) is an extensively applied control method for the purpose of designing intelligent control systems to achieve high accuracy as well as better performance. In the present article, the PID controller is considered as the main control strategy for brushless DC (BLDC) motor speed control. For better performance, the fuzzy Q-learning (FQL) method as a reinforcement learning approach is proposed to adjust the PID coefficients. A comparison with the adaptive PID (APID) controller is also performed for the superiority of the proposed method, and the findings demonstrate the reduction of the error of the proposed method and elimination of the overshoot for controlling the motor speed. MATLAB/SIMULINK has been used for modeling, simulation, and control design of the BLDC motor.

scholarly journals On the Convergence of Stochastic Iterative Dynamic Programming Algorithms

1994 ◽  
Vol 6 (6) ◽  
pp. 1185-1201 ◽  
Author(s):  
Tommi Jaakkola ◽  
Michael I. Jordan ◽  
Satinder P. Singh
Keyword(s):  
Dynamic Programming ◽  
Learning Algorithm ◽  
Q Learning ◽  
Recent Developments ◽  
Prediction And Control ◽  
Iterative Dynamic Programming ◽  
And Control ◽  
Programming Algorithms ◽  
Proof Of Convergence ◽  
New Algorithms

Recent developments in the area of reinforcement learning have yielded a number of new algorithms for the prediction and control of Markovian environments. These algorithms, including the TD(λ) algorithm of Sutton (1988) and the Q-learning algorithm of Watkins (1989), can be motivated heuristically as approximations to dynamic programming (DP). In this paper we provide a rigorous proof of convergence of these DP-based learning algorithms by relating them to the powerful techniques of stochastic approximation theory via a new convergence theorem. The theorem establishes a general class of convergent algorithms to which both TD(λ) and Q-learning belong.

Research on Control Method of Expressway Off-Ramp Based on Q-Learning Algorithm and Extension Control

2012 ◽  
Vol 433-440 ◽  
pp. 6033-6037
Author(s):  
Xiao Ming Liu ◽  
Xiu Ying Wang
Keyword(s):  
Queue Length ◽  
Control Method ◽  
Learning Algorithm ◽  
Control Strategies ◽  
Traffic Light ◽  
Q Learning ◽  
Reward Function ◽  
Movement Characteristics ◽  
Queue Lengths ◽  
Simulation Results

The movement characteristics of traffic flow nearby have the important influence on the main line. The control method of expressway off-ramp based on Q-learning and extension control is established by analyzing parameters of off-ramp and auxiliary road. First, the basic description of Q-learning algorithm and extension control is given and analyzed necessarily. Then reward function is gained through the extension control theory to judge the state of traffic light. Simulation results show that compared to the queue lengths of off-ramp and auxiliary road, control method based on Q-learning algorithm and extension control greatly reduced queue length of off-ramp, which demonstrates the feasibility of control strategies.

A Research on Aero-engine Control Based on Deep Q Learning

2020 ◽  
Vol 0 (0) ◽  
Author(s):  
Qiangang Zheng ◽  
Zhihua Xi ◽  
Chunping Hu ◽  
Haibo ZHANG ◽  
Zhongzhi Hu
Keyword(s):  
Value Function ◽  
Control Method ◽  
Learning Algorithm ◽  
Training Data ◽  
Engine Control ◽  
Q Learning ◽  
Model Free ◽  
Deep Learning Algorithm ◽  
Aero Engine ◽  
Action Value

AbstractFor improving the response performance of engine, a novel aero-engine control method based on Deep Q Learning (DQL) is proposed. The engine controller based on DQL has been designed. The model free algorithm – Q learning, which can be performed online, is adopted to calculate the action value function. To improve the learning capacity of DQL, the deep learning algorithm – On Line Sliding Window Deep Neural Network (OL-SW-DNN), is adopted to estimate the action value function. For reducing the sensitivity to the noise of training data, OL-SW-DNN selects nearest point data of certain length as training data. Finally, the engine acceleration simulations of DQR and the Proportion Integration Differentiation (PID) which is the most commonly used as engine controller algorithm in industry are both conducted to verify the validity of the proposed method. The results show that the acceleration time of the proposed method decreased by 1.475 second while satisfied all of engine limits compared with the tradition controller.

Perencanaan Pengendalian Kualitas Produk Pakaian Bayi dengan Metode Six Sigma Pada CV. AGP

JEMAP ◽  
2020 ◽  
Vol 3 (1) ◽  
Author(s):  
Albertus Reynaldo Kurniawan ◽  
Bayu Prestianto
Keyword(s):  
Quality Control ◽  
Continuous Improvement ◽  
Six Sigma ◽  
Screen Printing ◽  
Control Method ◽  
Operational Performance ◽  
Machine Maintenance ◽  
Quality Product ◽  
Break Time ◽  
And Control

Quality control becomes an important key for companies in suppressing the number of defective produced products. Six Sigma is a quality control method that aims to minimize defective products to the lowest point or achieve operational performance with a sigma value of 6 with only yielding 3.4 defective products of 1 million product. Stages of Six Sigma method starts from the DMAIC (Define, Measure, Analyze, Improve and Control) stages that help the company in improving quality and continuous improvement. Based on the results of research on baby clothes products, data in March 2018 the percentage of defective products produced reached 1.4% exceeding 1% tolerance limit, with a Sigma value of 4.14 meaning a possible defect product of 4033.39 opportunities per million products. In the pareto diagram there were 5 types of CTQ (Critical to Quality) such as oblique obras, blobor screen printing, there is a fabric / head cloth code on the final product, hollow fabric / thin fabric fiber, and dirty cloth. The factors caused quality problems such as Manpower, Materials, Environtment, and Machine. Suggestion for consideration of company improvement was continuous improvement on every existing quality problem like in Manpower factor namely improving comprehension, awareness of employees in producing quality product and improve employee's accuracy, Strength Quality Control and give break time. Materials by making the method of cutting the fabric head, the Machine by scheduling machine maintenance and the provision of needle containers at each employees desk sewing and better environtment by installing exhaust fan and renovating the production room.

An Efficient Approach for Modeling and Control of a Quadrotor

2016 ◽  
Vol 4 (2) ◽  
pp. 1-16
Author(s):  
Ahmed S. Khusheef
Keyword(s):  
Pid Control ◽  
Control Method ◽  
Mechanical Design ◽  
Loop Control ◽  
Modeling And Control ◽  
Loop Control System ◽  
And Control ◽  
Close Loop Control ◽  
Close Loop Control System ◽  
Made In

 A quadrotor is a four-rotor aircraft capable of vertical take-off and landing, hovering, forward flight, and having great maneuverability. Its platform can be made in a small size make it convenient for indoor applications as well as for outdoor uses. In model there are four input forces that are essentially the thrust provided by each propeller attached to each motor with a fixed angle. The quadrotor is basically considered an unstable system because of the aerodynamic effects; consequently, a close-loop control system is required to achieve stability and autonomy. Such system must enable the quadrotor to reach the desired attitude as fast as possible without any steady state error. In this paper, an optimal controller is designed based on a Proportional Integral Derivative (PID) control method to obtain stability in flying the quadrotor. The dynamic model of this vehicle will be also explained by using Euler-Newton method. The mechanical design was performed along with the design of the controlling algorithm. Matlab Simulink was used to test and analyze the performance of the proposed control strategy. The experimental results on the quadrotor demonstrated the effectiveness of the methodology used.

Application of improved Q learning algorithm to job shop problem

2009 ◽  
Vol 28 (12) ◽  
pp. 3268-3270
Author(s):  
Chao WANG ◽  
Jing GUO ◽  
Zhen-qiang BAO
Keyword(s):  
Job Shop ◽  
Learning Algorithm ◽  
Q Learning

Application Study on Finger Joint Motion in Rehabilitation Training

2014 ◽  
Vol 644-650 ◽  
pp. 879-883
Author(s):  
Jing Jing Yu
Keyword(s):  
Control Method ◽  
Finger Joint ◽  
Continuous Passive Motion ◽  
Joint Motion ◽  
Joint Movement ◽  
Rehabilitation Training ◽  
Angle Data ◽  
Finger Flexion ◽  
And Control ◽  
Flexion And Extension

In various forms of movement of finger rehabilitation training, Continuous Passive Motion (CPM) of single degree of freedom (1 DOF) has outstanding application value. Taking classic flexion and extension movement for instance, this study collected the joint angle data of finger flexion and extension motion by experiments and confirmed that the joint motion of finger are not independent of each other but there is certain rule. This paper studies the finger joint movement rule from qualitative and quantitative aspects, and the conclusion can guide the design of the mechanism and control method of finger rehabilitation training robot.

Sign in / Sign up

Export Citation Format

Share Document