Cihan Karakuzu

RETRACTED: Retraction notice to: Fuzzy controller training using particle swarm optimization for nonlinear system control

This paper proposes and describes an effective utilization of particle swarm optimization (PSO) to train a Takagi-Sugeno (TS)-type fuzzy controller. Performance evaluation of the proposed fuzzy training method using the obtained simulation results is provided with two samples of highly nonlinear systems: a continuous stirred tank reactor (CSTR) and a Van der Pol (VDP) oscillator. The superiority of the proposed learning technique is that there is no need for a partial derivative with respect to the parameter for learning. This fuzzy learning technique is suitable for real-time implementation, especially if the system model is unknown and a supervised training cannot be run. In this study, all parameters of the controller are optimized with PSO in order to prove that a fuzzy controller trained by PSO exhibits a good control performance.

Neural network training based on FPGA with floating point number format and it’s performance

In this paper, two-layered feed forward artificial neural network’s (ANN) training by back propagation and its implementation on FPGA (field programmable gate array) using floating point number format with different bit lengths are remarked based on EX-OR problem. In the study, being suitable with the parallel data-processing specification on ANN’s nature, it is especially ensured to realize ANN training operations parallel over FPGA. On the training, Virtex2vp30 chip of Xilinx FPGA family is used. The network created on FPGA is coded by using VHDL. By comparing the results to available literature, the technique developed here proved to consume less space for the subjected ANN training which has the same structure and bit length, it is shown to have better performance.

Fuzzy logic based smart traffic light simulator design and hardware implementation

The objective of this study is to develop fuzzy logic based traffic junction light simulator system for design and smart traffic junction light controller purposes and also to observe its performance. Traffic junction simulator hardware is developed to overcome difficulties of working in a real environment and to easily test the performance of the controller. By using the traffic light simulator developed in this study, results of constant duration (conventional) traffic light controller and fuzzy logic based traffic light controller are compared where the vehicle inputs are supplied by the simulator. Statistical experimental results obtained from the implemented simulator show that the fuzzy logic traffic light controller dramatically reduced the waiting time at red lights since the controller adapts itself according to traffic density. It is obvious that the intelligent light controller is going to provide important advantages in terms of economics and environment.

FPGA implementation of neuro-fuzzy system with improved PSO learning

This paper presents the first hardware implementation of neuro-fuzzy system (NFS) with its metaheuristic learning ability on field programmable gate array (FPGA). Metaheuristic learning of NFS for all of its parameters is accomplished by using the improved particle swarm optimization (iPSO). As a second novelty, a new functional approach, which does not require any memory and multiplier usage, is proposed for the Gaussian membership functions of NFS. NFS and its learning using iPSO are implemented on Xilinx Virtex5 xc5vlx110-3ff1153 and efficiency of the proposed implementation tested on two dynamic system identification problems and licence plate detection problem as a practical application. Results indicate that proposed NFS implementation and membership function approximation is as effective as the other approaches available in the literature but requires less hardware resources.

Design and simulation of a fuzzy substrate feeding controller for an industrial scale fed-batch baker yeast fermentor

Conventional control systems can not give satisfactory results in fermentation systems due to process non-linearity and long delay time,. This paper presents design and simulation a fuzzy controller for industrial fed-batch bakers yeast fermentation system in order to maximize the cell-mass production and to minimize ethanol formation. Designed fuzzy controller determines an optimal substrate feeding strategy for an industrial scale fed-batch fermentor relating to status of estimated specific growth rate, elapsed time and ethanol concentration. The proposed controller uses an error in specific growth rate (e), fermentation time (t) and concentration of ethanol (Ce) as controller inputs and produces molasses feeding rate (F) as control output. The controller has been tested on a simulated fed-batch industrial scaled fermenter and resulted in higher productivity than the conventional controller.

Retraction notice to: Fuzzy controller training using particle swarm optimization for nonlinear system control.

This article has been retracted at the request of the author and/or the Editor-in-Chief. Please see Elsevier Policy on Article Withdrawal (http://www.elsevier.com/locate/withdrawalpolicy). Reason: This article has been retracted at the request of the Editor in Chief as the author has plagiarized parts of previously published papers in introductory and discussion sections: Jang J-SR, ANFIS: adaptive-network-based fuzzy inference system, IEEE Trans Syst Man Cybern 1993;23(3):665-85 Parrott Daniel, Li Xiaodong, Locating and tracking multiple dynamic optima by a particle swarm model using speciation, IEEE Trans Evol Comput 2006;10(4):440-58. Juang, C.-F., Liou, Y.-C. On the hybrid of genetic algorithm and particle swarm optimization for evolving recurrent neural network 2004 IEEE International Conference on Neural Networks - Conference Proceedings 3, pp. 2285-2289 Cai, X., Zhang, N., Venayagamoorthy, G.K., Wunsch II, D.C., Time series prediction with recurrent neural networks using a hybrid PSO-EA algorithm, 2004 IEEE International Conference on Neural Networks - Conference Proceedings 2, pp. 1647-1652 Lu, C.-F., Juang, C.-F., Control of flexible AC transmission system by evolutionary fuzzy controller, 2004 Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics 3, pp. 2292-2296 Jang, Jyh-Shing R., Self-learning fuzzy controllers based on temporal back propagation, 1992, IEEE Transactions on Neural Networks 3 (5), pp. 714-723 Ray, W.H., New approaches to the dynamics of nonlinear systems with implications for process and control design, 1981, Chemical Process Control 2 119 One of the conditions of submission of a paper for publication is that authors declare explicitly that all portions of their work are original and have not appeared in a publication elsewhere. Re-use of any text, figures, or data should be appropriately cited. Since this article quoted sections of prior work without appropriate acknowledgment, it violates scientific publishing system protocol. The scientific community takes a very strong view on this matter and we apologize to readers of the journal that this was not detected during the submission process.

An experimental comparison of fuzzy, neuro and classical control techniques

Neural, fuzzy logic and classical (PI) control techniques were compared based on an experimental application in this study. Experimental studies were implemented on a water temperature control system. The control techniques were compared through experimental studies under identical conditions with respect to set-point regulation and load disturbance regulation in real time. It was found that the fuzzy logic control technique demonstrated better performance than the others and offered some advantages. This paper gives an idea that superiority of control techniques of neural and fuzzy logic is related to structure of system and design experience.

FUZZY NEURAL NETWORK CONTROLLER AS A REAL TIME CONTROLLER USING PSO

Direct current (DC) motors are commonly used to control position or speed in many applications. The speed of the DC motors is adjustable in a wide range with advantages such as easy control theorems and high performances. DC motors are used in industrial branches like transportation, electrical train, vehicle, crane, printer, drivers, paper industry in which adjustable speed and sensitive position handling are necessarily. In recent years, these applications are commonly used for household appliance in which low power and low cost are required with adjustable speed and sensitive position handling as well. In this study, permanent magnet direct current motor actuator is implemented by using fuzzy neural network structure . Particle Swarm Optimization (PSO) algorithm is used as training algorithm of fuzzy neural network controller. Learning and control in real time is executed in Matlab. Dynamic performance of the system is observed for constant and variable reference trajectory of speed.

Moving target tracking via adaptive one step ahead neuro-fuzzy estimator

This paper intends to cope with single target tracking nonlinear filtering problem with an Adaptive Neuro-Fuzzy Inference System (ANFIS). ANFIS provides faster adaptation, adequate convergence and easy using over other standard filters. The ANFIS used in this study is trained on-line while the target is moving to estimate the next position of target at the end of the training. The proposed system calculates the speed and the acceleration rate of the object and estimates the next absolute position of the target between two position measurements interval. Estimation performance of the presented system has been tested using few predetermined position data. The test results show that the proposed ANFIS position estimator system has been successively estimated the next position of the moving target and can be used in real target tracking systems.