Optimizing Dynamical Fuzzy Systems Using Aging Evolution Strategies
نویسندگان
چکیده
This paper introduces an evolutionary optimization algorithm taking advantage of multiple populations and an adaptive aging parameter to achieve faster and more robust convergence. As challenging test cases, the evolutionary algorithm is used to optimize parameters for dynamical fuzzy systems. Our results show that the proposed algorithm is capable of outperforming the traditional reference algorithm. The effect of sampling the membership functions of the dynamical fuzzy system in feedforward and feedback configurations is also studied.
منابع مشابه
Synchronization criteria for T-S fuzzy singular complex dynamical networks with Markovian jumping parameters and mixed time-varying delays using pinning control
In this paper, we are discuss about the issue of synchronization for singular complex dynamical networks with Markovian jumping parameters and additive time-varying delays through pinning control by Takagi-Sugeno (T-S) fuzzy theory.The complex dynamical systems consist of m nodes and the systems switch from one mode to another, a Markovian chain with glorious transition probabili...
متن کاملOn the Notion of Fuzzy Shadowing Property
This paper is concerned with the study of fuzzy dynamical systems. Let (XM ) be a fuzzy metric space in the sense of George and Veeramani. A fuzzy discrete dynamical system is given by any fuzzy continuous self-map dened on X. We introduce the various fuzzy shad- owing and fuzzy topological transitivity on a fuzzy discrete dynamical systems. Some relations between this notions have been proved.
متن کاملDISTURBANCE REJECTION IN NONLINEAR SYSTEMS USING NEURO-FUZZY MODEL
The problem of disturbance rejection in the control of nonlinear systems with additive disturbance generated by some unforced nonlinear systems, was formulated and solved by {itshape Mukhopadhyay} and {itshape Narendra}, they applied the idea of increasing the order of the system, using neural networks the model of multilayer perceptron on several systems of varying complexity, so the objective...
متن کاملDiscrete and fuzzy dynamical genetic programming in the XCSF learning classifier system
A number of representation schemes have been presented for use within Learning Classifier Systems, ranging from binary encodings to neural networks. This paper presents results from an investigation into using discrete and fuzzy dynamical system representations within the XCSF Learning Classifier System. In particular, asynchronous Random Boolean Networks are used to represent the traditional c...
متن کاملParticle swarm approaches using Lozi map chaotic sequences to fuzzy modelling of an experimental thermal-vacuum system
Particle Swarm Optimization (PSO) approach intertwined with Lozi map chaotic sequences to obtain Takagi–Sugeno (TS) fuzzy model for representing dynamical behaviours are proposed in this paper. The proposed method is an alternative for nonlinear identification approaches especially when dealing with complex systems that cannot always be modelled using first principles to determine their dynamic...
متن کامل