Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
496220 | Applied Soft Computing | 2013 | 11 Pages |
Graphical abstractFigure optionsDownload full-size imageDownload as PowerPoint slideHighlights•We consider a system of fuzzy differential equations.•We employ partially fuzzy neural network for solving system of fuzzy differential equations.•We propose a learning algorithm from the cost function for adjusting of weights.
Fuzzy neural network (FNN) can be trained with crisp and fuzzy data. This paper presents a novel approach to solve system of fuzzy differential equations (SFDEs) with fuzzy initial values by applying the universal approximation method (UAM) through an artificial intelligence utility in a simple way. The model finds the approximated solution of SFDEs inside of its domain for the close enough neighborhood of the fuzzy initial points. We propose a learning algorithm from the cost function for adjusting of fuzzy weights. At the same time, some examples in engineering and economics are designed.