Numerical Method For Solving Fuzzy Singular Perturbation Problems With Initial Condition

Abstract

In this paper, We present a modified approach that makes use of the neuro-fuzzy system to solve fuzzy singular perturbation problems for ODEs with IC. The name of this modified approach is the modified neuro-fuzzy system method (MNFS). The foundation of this novel approach is to swap off each x in the input vector training. set = , a first-order polynomial which will be as = , . By using MNFS, it is possible to train the neural network outside of the initial and last point range by choosing training points based on the open interval (a, b). By resolving a few numerical cases and comparing the results to those calculated using different numerical techniques, we demonstrate this improved a technique and how neural networks demonstrate yield answers with accurate and strong generalization. The suggested approach is illustrated with a number of instances.