This paper presents a fuzzy neural network approach to virtual product design. Contemporary design process requires the development of a new computational intelligent methodology that involves intelligent integration of design, analysis and evaluation, simulation and optimization in a virtual environment. In the paper, a soft-computing framework is developed for engineering design based on a hy...

In this paper we extend an earlier result within Dempster-Shafer theory [“Fast DempsterShafer Clustering Using a Neural Network Structure,” in Proc. Seventh Int. Conf. Information Processing and Management of Uncertainty in Knowledge-Based Systems (IPMU’98)] where a large number of pieces of evidence are clustered into subsets by a neural network structure. The clustering is done by minimizing ...

The rainfall-runoff relationship is one of the most complex hydrological phenomena. In recent years, hydrologists have successfully applied backpropagation neural network as a tool to model various nonlinear hydrological processes because of its ability to generalize patterns in imprecise or noisy and ambiguous input and output data sets. However, the backpropagation neural network convergence ...

Topology optimization problem, which involves many design variables, is commonly solved by finite element method, a method must recalculate structure-stiffness matrix each time of analysis. OC method is a good way to solve topology optimization problem, nevertheless, it can not solve multiobjective topology optimization problems. This paper introduces an effective solution to Multi-objective to...

This paper suggests an approach to neural network training through the simultaneous optimization of architectures and weights with a Particle Swarm Optimization (PSO)-based multiobjective algorithm. Most evolutionary computation-based training methods formulate the problem in a single objective manner by taking a weighted sum of the objectives from which a single neural network model is generat...

Neural network adaptive filters are mainly used for the interference cancellation techniques. The gradient based design methods are well developed for the design of neural network adaptive filter but they converge to local minima. This paper describes the global optimization interference cancelling techniques for adaptive filtering of interferences in the corrupted signal. The system is designe...

in the present work, the influences of temperature, solvent concentration and ultrasonic irradiation time were numerically analyzed on viscosity reduction of residue fuel oil (rfo). ultrasonic irradiation was applied at power of 280 w and low frequency of 24 khz. the main feature of this research is prediction and optimization of the kinematic viscosity data. the measured results of eighty-four...

In this paper multi-objective genetic algorithms were employed for Pareto approach optimization of turboprop engines. The considered objective functions are used to maximize the specific thrust, propulsive efficiency, thermal efficiency, propeller efficiency and minimize the thrust specific fuel consumption. These objectives are usually conflicting with each other. The design variables consist ...

In this paper we study a problem within Dempster-Shafer theory where 2n − 1 pieces of evidence are clustered by a neural structure into n clusters. The clustering is done by minimizing a metaconflict function. Previously we developed a method based on iterative optimization. However, for large scale problems we need a method with lower computational complexity. The neural structure was found to...

Neural network design aims for high classification accuracy and low network architecture complexity. It is also known that simultaneous optimization of both model accuracy and complexity improves generalization while avoiding overfitting on data. We describe a neural network training procedure that uses multi-objective optimization to evolve networks which are optimal both with respect to class...