Abstract:This paper presents a new algorithm for fuzzy c-regression model clustering. The proposed methodology is based on adding a second regularization term in the objective function of a Fuzzy C-Regression Model (FCRM) clustering algorithm in order to take into account noisy data. In addition, a new error measure is used in the objective function of the FCRM algorithm, replacing the one used in this type of algorithm. Then, particle swarm optimization is employed to finally tune parameters of the obtained fuzzy mode… Show more
“…Until err ≤ ε, then stop. Otherwise set l = l + 1 and return to Step 1. Like those in [7], {y(k − 1), y(k − 2), u(k), u(k − 1)} are chosen as input variables. The number of fuzzy rules is four.…”
Section: End For End Formentioning
confidence: 99%
“…The EPSO-FCRM algorithm uses two phases of learning algorithms to construct fuzzy models. In the first phase, the EPSO algorithm is used to search the optimal parameters of the fuzzy model by minimizing a defined objective function and is given as [7]:…”
Section: Fcrm Algorithm Based On Epsomentioning
confidence: 99%
“…Later, Li et al [5] as well as Li et al [6] utilized new FCRM clustering algorithm (NFCRMA) to nonlinear complex system identification. Recently, Soltani et al [7] proposed a new method of FCRM algorithm (PSO-NFCRM) using a modified objective function, a new error measure, and a parameter estimation based particle swarm optimization, in order to take into consideration the noisy data and the sensitive to initialization. However, the PSO can be easily trapped in local optima and premature convergence [8].…”
This paper addresses the effectiveness of fuzzy c-regression models algorithm and Euclidean particle swarm optimization to nonlinear system identification in a noisy environment. The fuzzy c-regression models (FCRM) clustering algorithm is sensitive to initialization that leads to converge to a local minimum of the objective function. In addition, The particle swarm optimization can be easily trapped in local optima and premature convergence. In order to overcome these problems, the Euclidean particle swarm optimization is proposed to optimize the initial states of FCRM algorithm. Thereafter, weighted recursive least squares is employed to fine tune parameters of the obtained fuzzy model. Finally, the proposed approach is tested by studying a nonlinear modeling problems to verify the identification performance.
“…Until err ≤ ε, then stop. Otherwise set l = l + 1 and return to Step 1. Like those in [7], {y(k − 1), y(k − 2), u(k), u(k − 1)} are chosen as input variables. The number of fuzzy rules is four.…”
Section: End For End Formentioning
confidence: 99%
“…The EPSO-FCRM algorithm uses two phases of learning algorithms to construct fuzzy models. In the first phase, the EPSO algorithm is used to search the optimal parameters of the fuzzy model by minimizing a defined objective function and is given as [7]:…”
Section: Fcrm Algorithm Based On Epsomentioning
confidence: 99%
“…Later, Li et al [5] as well as Li et al [6] utilized new FCRM clustering algorithm (NFCRMA) to nonlinear complex system identification. Recently, Soltani et al [7] proposed a new method of FCRM algorithm (PSO-NFCRM) using a modified objective function, a new error measure, and a parameter estimation based particle swarm optimization, in order to take into consideration the noisy data and the sensitive to initialization. However, the PSO can be easily trapped in local optima and premature convergence [8].…”
This paper addresses the effectiveness of fuzzy c-regression models algorithm and Euclidean particle swarm optimization to nonlinear system identification in a noisy environment. The fuzzy c-regression models (FCRM) clustering algorithm is sensitive to initialization that leads to converge to a local minimum of the objective function. In addition, The particle swarm optimization can be easily trapped in local optima and premature convergence. In order to overcome these problems, the Euclidean particle swarm optimization is proposed to optimize the initial states of FCRM algorithm. Thereafter, weighted recursive least squares is employed to fine tune parameters of the obtained fuzzy model. Finally, the proposed approach is tested by studying a nonlinear modeling problems to verify the identification performance.
“…For example, the proposed hybrid particle swarm gravitational search algorithm which adopting co-evolutionary techniques to update the IGSA acceleration and particle positions with IPSO velocite simultaneously [5]. In the queue robot make decisions independently, through the coordination and cooperation between each other from the current position to determine their next position [12].…”
Abstract-Cluster control system to realize mutual coordination between individual objects must determine the control and the information relationship in terms of logical and physical aspects. Study these problems of the system structure, system structure and control can be combined and ensure smooth information flow and control flow in the system and the framework for the interaction between the individual. Cluster control algorithm ensure cooperation among multiple control individual effectively, to deal with an emergency to be able to react quickly, improve the real-time performance and effectiveness of control system. This paper proposed a new methodology to Group Intelligence Control by using a distributed control algorithm and a Swarm Intelligence algorithm to optimize the path of the individual of the cluster and the real-time control of each object. In the first part of this paper, we introduced the appearance and the development of Group Intelligence Control system. Then, the paper proposed our methodology of the proposed Group Intelligence Control system.
“…Moreover, it contains many variables which are too vague to model. In order to build an accurate model for the pumping station system, several algorithms based on Takagi-Sugeno (T-S) fuzzy model [1][2][3][4][5][6][7] have been carried out recently to identify the parameters for "black-box" systems using input-output data sets, among them the Fuzzy-C Means (FCM) algorithm [8][9][10][11][12][13][14][15][16]. The latter is particularly the most effective technique that can be used in nonlinear systems identification.…”
This paper proposes a discrete-time switching controller strategy for a hydraulic process pumping station. The proposed solution leads to improving control system performances with two tests: combination of Fuzzy-PD and PI controllers and Fuzzy-PID and PI controllers. The proposed design methodology is based on accurate model for pumping station (PS), which is developed in previous works using Fuzzy-C Means (FCM) algorithm. The control law design is based on switching control; a fuzzy supervisor manages the switching from one to another and regulates the rate of participation of each order, in order to satisfy various objectives of a stable pumping station like the asymptotic stability of the tracking error. To validate the proposed solution, experimental tests are made and analyzed. Compared to the conventional PI and fuzzy logic (FL) approaches, the results show that the switching controller allows exhibiting excellent transient response over a wide range of operating conditions and especially is easier to be implemented in practice.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.