Opt Quant Electron (2008) 40:891–905
DOI 10.1007/s11082-009-9290-5
Accurate radial basis function based neural network
approach for analysis of photonic crystal fibers
M. F. O. Hameed · S. S. A. Obayya · K. Al-Begain ·
A. M. Nasr · M. I. Abo el Maaty
Received: 5 September 2008 / Accepted: 12 March 2009 / Published online: 9 April 2009
© Springer Science+Business Media, LLC. 2009
Abstract In this paper, a new and an accurate artificial neural network approach (ANN)
is presented for the analysis and design of photonic crystal fibers (PCFs). The new ANN
approach is based on the radial basis functions which offer a very quick convergence and
high efficiency during the ANN learning. The accuracy of the suggested approach is demon-
strated via the excellent agreement between the results obtained using the presented approach
and the results of the full vectorial finite difference method (FVFDM). In addition, a new
design of highly birefringence PCF with low losses for the two polarized modes is presented
using the proposed approach.
Keywords Photonic crystal fibers · Optimization · Artificial neural network ·
Radial basis function
1 Introduction
Due to their unusual optical properties, photonic crystal fibers (PCFs) (Benabid 2006;
Broeng et al. 1999) have attracted the interest of many researchers in recent years. PCFs
can be endlessly single mode over a wide wavelength range (Birks et al. 1997), have a large
effective mode area (Knight et al. 1998) and can be tailored to achieve nearly zero and flat
dispersion over a wide range of wavelengths (Gander et al. 1998). PCFs are usually made of
a silica background which contains a regular array of air holes running through the length of
the fibre acting as a cladding. This structure creates bandgaps where propagation at certain
optical frequencies is forbidden. If the central hole is enlarged (low index core) (Benabid
2006) or removed (high index core) (Broeng et al. 1999), a defect will be produced in the
periodic structure. High and low index core PCFs are very promising structures in terms
M. F. O. Hameed · S. Obayya (B ) · K. Al-Begain
Faculty of Advanced Technology, University of Glamorgan, Pontypridd, CF37 1DL, UK
e-mail: sobayya@glam.ac.uk
A. M. Nasr · M. I. Abo el Maaty
Faculty of Engineering, University of Mansoura, Mansoura, Egypt
123