Fuzzy Basis Function Network Research Articles

Evolving Basis Function Networks for System Identification

This paper is concerned with learning and optimization of different basis function networks in the aspect of structure adaptation and parameter tuning. Basis function networks include the Volterra polynomial, Gaussian radial, B-spline, fuzzy, recurrent fuzzy, and local Gaussian basis function networks. Based on creation and evolution of the type constrained sparse tree, a unified framework is constructed, in which structure adaptation and parameter adjustment of different basis function networks are addressed using a hybrid learning algorithm combining a modified probabilistic incremental program evolution (MPIPE) and random search algorithm. Simulation results for the identification of nonlinear systems show the feasibility and effectiveness of the proposed method.

Evolutionary modelling and optimization of grinding processes

The objective of this study is to develop a framework of modelling the complex grinding processes and finding optimal process conditions to meet the general class of process requirements. In order to achieve the above goal, novel modelling schemes and optimization methods based on evolutionary algorithms (EA) are developed. The optimization problem of grinding processes can be formulated as a constrained non-linear programming problem with mixed-discrete variables. The adaptive least-squares (ALS) algorithm proposed by Lee and Shin's 1998 study is extended for modelling multi-input-multi-output (MIMO) complex grinding processes using fuzzy basis function networks (FBFN), while the modified evolution strategies (ES) is proposed for successful optimization of grinding processes. Two grinding optimization problems demonstrate the superior performance of the proposed scheme.

Adaptive tuning of the fuzzy controller for robots

An adaptive tuning algorithm of the fuzzy controller is developed for a class of serial-link robot arms. The algorithm can on-line tune parameters of premise and consequence parts of fuzzy rules of the fuzzy basis function (FBF) controller. The main part of the fuzzy controller is a fuzzy basis function network to approximate unknown rigid serial-link robot dynamics. Under some mild assumptions, a stability analysis guarantees that both tracking errors and parameter estimate errors are bounded. Moreover, a robust technique is adopted to deal with uncertainties including approximation errors and external disturbances. Simulations of the proposed controller on the PUMA-560 robot arm demonstrate the effectiveness.

99/03189 A fuzzy basis function network based power system stabilizer for generator excitation control

To address the problem of fossil fuel usage and high greenhouse gas emissions at the Missouri University of Science and Technology campus, using of alternative fuels and renewable energy sources can lower energy consumption and greenhouse gas emissions. Biogas, produced by anaerobic digestion of wastewater, organic waste, agricultural waste, industrial waste, and animal by-products is a potential source of renewable energy. In this work, we have discussed the design of CHHP system for the campus using local resources. An energy flow and resource availability study is performed to identify the type and source of feedstock required to continuously run the fuel cell system at peak capacity. Following the resource assessment study, the team selects FuelCell Energy DFC1500TM unit as a MCFC. The CHHP system provides electricity to power the university campus, thermal energy for heating the anaerobic digester, and hydrogen for transportation, back-up power and other needs. In conclusion, the CHHP system will be able to reduce fossil fuel usage, and greenhouse gas emissions at the university campus.

Tuning of Power System Stabilizers Using Fuzzy Basis Function Networks

Tuning of a Power System Stabilizer (PSS) using a Fuzzy Basis Function Network (FBFN) is presented in this paper. The proposed FBFN-based PSS provides a natural framework for combining numerical and linguistic information in a uniform fashion. The proposed FBFN is trained over a wide range of operating conditions in order to re-tune the PSS parameters in real-time based on machine loading conditions. The orthogonal least squares (OLS) learning algorithm is developed for designing an adequate and parsimonious FBFN model. Time domain simulations of a synchronous machine equippedwith the proposed stabilizer subject to major disturbances are investigated. The performance of the proposed FBFN PSS is compared withthose of two widely used conventional power system stabilizers. The results show the robustness and the capability of the proposed FBFN PSS to enhance system damping over a wide range of operating conditions and system parameter variations.

A fuzzy basis function network based power system stabilizer for generator excitation control

A fuzzy basis function network (FBFN) based power system stabilizer (PSS) is presented in this paper. The proposed FBFN-based PSS provides a natural framework for combining numerical and linguistic information in a uniform fashion. The proposed FBFN is trained over a wide range of operating conditions in order to retune the PSS parameters in real-time, based on machine loading conditions. The orthogonal least squares (OLS) learning algorithm is developed for designing an adequate and parsimonious FBFN model. Time domain simulations of a synchronous machine equipped with the proposed stabilizer subject to major disturbances are investigated. The performance of the proposed FBFN PSS is compared with that of a conventional power system stabilizer (CPSS) to demonstrate the superiority of the proposed stabilizer. The effect of parameter changes on the proposed stabilizer performance is also examined. The results show the robustness of the proposed FBFN PSS and its capability to enhance system damping over a wide range of operating conditions.

A hybrid neuro-fuzzy power system stabilizer for multimachine power systems

A fuzzy basis function network (FBFN) based power system stabilizer (PSS) is presented in this paper to improve power system dynamic stability. The proposed FBFN based PSS provides a natural framework for combining numerical and linguistic information in a uniform fashion. The proposed FBFN is trained over a wide range of operating conditions in order to re-tune the PSS parameters in real-time based on machine loading conditions. The orthogonal least squares (OLS) learning algorithm is developed for designing an adequate and parsimonious FBFN model. Time domain simulations of a single machine infinite bus system and a multimachine power system subject to major disturbances are investigated. The performance of the proposed FBFN PSS is compared with that of conventional (CPSS). The results show the capability of the proposed FBFN PSS to enhance the system damping of local modes of oscillations over a wide range of operating conditions. The decentralized nature of the proposed FBFN PSS makes it easy to install and tune.