per
Iranian Society of Instrumentation and Control Engineers
Journal of Control
2008-8345
2538-3752
2011-06
5
1
1
13
article
Centralized Constrained Predictive Control on Information Coupled Supply Chain Management System
mohammad Miranbeigi
m.miran@ut.ac.ir
1
Ali Akbar Jalali
drjalali@iust.ac.ir
2
Supply chain management system (SCM) is a network of suppliers and manufacturers and warehouses and distributors and retailers, with large delay times. The control system aims at operating the supply chain at the optimal point despite the influence of demand changes. In this paper, an information coupled supply chain management system model based on “Beer Game Theory” was used and was developed to an supply chain management consist of supply, manufacture, warehouse, distribution, retailer units .Then a centralized constrained model predictive controller applied on that. Also a move suppression term added to cost function, which increased system robustness toward changes on demands
http://joc.kntu.ac.ir/article-1-92-en.pdf
Supply Chain Management System
Demand
Information Coupled Supply Chain Management System
Model Predictive Controller
Move Suppression Term.
per
Iranian Society of Instrumentation and Control Engineers
Journal of Control
2008-8345
2538-3752
2011-06
5
1
14
26
article
A Hybrid Learning Algorithm for Fuzzy Wavelet Networks Design for Functions Approximation, Online Identification and Control of Nonlinear Systems
Maryam Shahriari Kahkeshi
m.shahriyarikahkeshi@ec.iut.ac.ir
1
Maryam Zekri
mzekri@cc.iut.ac.ir
2
In this paper, a hybrid learning algorithm is presented for fuzzy wavelet networks (FWNs) design for functions approximation, online identification and control of nonlinear systems. The proposed algorithm is based on orthogonal least square (OLS) algorithm, Shufled Frog Leaping (SFL) algorithm and recursive least square method (RLS). The OLS algorithm is used for determine network dimensions, number of fuzzy rules and wavelets in each fuzzy rule and for purifying wavelets in each sub-WNN. So, after selection of important wavelets based on training data set, FWN structure is constructed and initial values of the network parameters are determined. Then linear and nonlinear parameters of the network are tuned based on recursive least square method and SFL algorithm, respectively. In order to show the capabilities and effectiveness of the proposed method, simulation results are presented for some example: function approximation, online identification and control of nonlinear systems. Also, the results obtained by the proposed approach are compared with the previous approaches reported in the literature. Simulation results show that the proposed method improves model approximation accuracy and performance index by using less number of fuzzy rules compare to other methods for study systems.
http://joc.kntu.ac.ir/article-1-93-en.pdf
Fuzzy Wavelet Networks
Shuffled Frog Leaping Algorithm
Functions Approximation
Identification and Control of Nonlinear System.
per
Iranian Society of Instrumentation and Control Engineers
Journal of Control
2008-8345
2538-3752
2011-06
5
1
27
37
article
Application of Energy Absorption Capacity Concept for Stability Analysis of Multi-Agent Systems
Karim Rahmani
rahmani2003@yahoo.com
1
Ahmad Afshar
aafshar@aut.ac.ir
2
Ali Akbar Jamshidifar
gamshidifar@irost.org
3
The issue of stability analysis of multi-agent systems (MASs) is focal point in this paper. In this paper, new concept of “Energy Absorption Capacity (EAC)” is extended to analyze the stability of MAS. EAC is defined for every equilibrium point of a system and is the maximum absorbed energy by the system preserving the stability of that point. An agent is considered a hybrid entity compromising a number of modes with continuous evolution within the modes and transition between them. A MAS is a group of agents that start from an initial state and cooperate with each other to achieve a pre-determined goal. In this work, it is shown that the EAC concept has good potential for stability analysis of both agent and multi-agent (MAS) systems. Finally, two examples are presented to support the proposed approach.
http://joc.kntu.ac.ir/article-1-99-en.pdf
Stability
Energy Absorption Capacity (EAC)
Absolute EAC
Instantaneous EAC
Hybrid Agent
Multi-Agent Systems.
per
Iranian Society of Instrumentation and Control Engineers
Journal of Control
2008-8345
2538-3752
2011-06
5
1
38
49
article
Optimal Active and Reactive Power Sharing between several Distributed Generation Units in a Stand-Alone MicroGrid Using Artificial Neural Network
Ali asghar Ghadimi
a-ghadimi@araku.ac.ir
1
hasan Rastegar
rastegar@aut.ac.ir
2
Farzad Razavi
razavi.farzad@taut.ac.ir
3
This paper is concerned with the generation control in small stand-alone MicroGrids consisting of inverter interfaced Distributed Generation (DG) units. An intelligent and on-line Microgrid Management System (MGMS) using Artificial Neural Network (ANN) controller is used in this study and it determines the amount of power produced from generation units in a stand-alone MicroGrid. The ANN trained with a data generated from a Genetic Algorithm (GA) solved optimal power flow problem, which defines generation unit’s power in order to have a minimum power loss in the system, considering normal buses voltage and rating of generation units. Simulation results in a typical distribution system consisting two DG units show that the proposed method can meet the requirements of the system and DG units rating in stand-alone operations. In this way the system is managed in an on-line, optimal, and reliable situation that guarantee the continuity of power to loads in stand-alone mode of a MicroGrid.
http://joc.kntu.ac.ir/article-1-94-en.pdf
MicroGrid
State Estimation
Genetic Algorithm
Artificial Neural Network
Load Sharing
Distributed Generation
per
Iranian Society of Instrumentation and Control Engineers
Journal of Control
2008-8345
2538-3752
2011-06
5
1
50
63
article
Action Value Function Approximation Based on Radial Basis Function Network for Reinforcement Learning
Vali Derhami
vderhami@yazduni.ac.ir
1
Omid Mehrabi
omidmehrabi62@yahoo.com
2
One of the challenges encountered in the application of classical reinforcement learning methods to real-control problems is the curse of dimensiality. In order to overcome this difficulty, hybrid algorithms that combine reinforcement learning with various function approximators have attracted many research interests. In this paper, a novel Neural Reinforcement Learning (NRL) scheme which is based on Sarsa learning and Radial Basis Function (RBF) network is proposed. The RBF network is used to approximate the Action Value Function (AVF) on-line. The inputs of RBF network are state-action pairs of system and its outputs are corresponding approximated AVF. As the necessary condition for the convergence of NSL to the optimal task performance, the existence of stationary points for NSL which coincide with the fixed points of Approximate Action Value Iteration (AAVI) are proved. The validity of the proposed algorithm is tested through simulation examples: mountain car control task, and acrobot problem. Overall results demonstrate that our algorithm can effectively improve convergence speed and the efficiency of experience exploitation.
http://joc.kntu.ac.ir/article-1-95-en.pdf
Neural reinforcement learning
Critic-only architecture
RBF neural network
Sarsa
stationary points.
per
Iranian Society of Instrumentation and Control Engineers
Journal of Control
2008-8345
2538-3752
2011-06
5
1
64
76
article
Solving the Local Minimum Problem in Path Planning Algorithm based on the Virtual Potential Field and the Principles of Liquid Movement
Bijan Moaveni
b_moaveni@iust.ac.ir
1
Davood Ghanbari Gol
Davoodgol_34@yahoo.com
2
Path planning and obstacle avoidance are important problems in intelligent mobile agent systems. In this paper, a novel path planning algorithm and a new obstacle avoidance approach to solve the local minimum problem of mobile agents are presented. This path planning algorithms is introduced based on the principles of liquid movement. In addition to, by modifying the potential function methodology for this algorithm, a new obstacle avoidance approach is presented. This new algorithm, by finding the collision free path, guarantees the global convergence to the target when the target is reachable. Also, in this paper, an online version of the algorithm is presented. Simulation results are given to show the effectiveness of the methodology
http://joc.kntu.ac.ir/article-1-96-en.pdf
Mobile Agent
Path Planning
Obstacle Avoidance
Potential Functions
per
Iranian Society of Instrumentation and Control Engineers
Journal of Control
2008-8345
2538-3752
2011-06
5
1
77
86
article
Player Localization and Tracking in Field Model Space using Graph Representation in Football Broadcast Videos
Mehrtash Manafifard
mehrtash64@yahoo.com
1
Hamid Ebadi
ebadi@kntu.ac.ir
2
Hamid Abrishami Moghaddam
moghadam@eetd.kntu.ac.ir
3
Precise player localization is the key step for improved analysis such as player tracking in soccer broadcast videos. Extracting player trajectories provides some essencial information for coaches and sport experts to determine weaknesses and strengths of the players and the team and to evaluate overall strategy of the game. As far as previous scenes are missed by camera motion, continuous player trajectory could be depicted by trajectory extraction on constructed mosaic. The goal of this paper is to transform player position to the field model and extract all trajectories in both image and model spaces. Therefore, players are detected using Gaussian Mixture Model and Gentle Adaboost. After removing extra regions such as goal post and lines, isolating occluded players, player labeling and transforming player positions to the same coordinate system, player tracking is carried out. Finally, the proposed player detection and tracking methods are applied for 78 frames taken from six soccer sequences.
http://joc.kntu.ac.ir/article-1-98-en.pdf
Video images
Track
GMM
Adaboost
Football players.