Refinement and design of rare earth doped photonic crystal fibre amplifier using an ANN approach |
| |
Authors: | Luciano Mescia Girolamo Fornarelli Francesco Prudenzano Francesco Vacca |
| |
Institution: | a Dipartimento di Elettrotecnica ed Elettronica, Politecnico di Bari Via E. Orabona 4—70125 Bari, Italy b Dipartimento di Ingegneria dell'Ambiente e per lo Sviluppo Sostenibile, Politecnico di Bari, V.le del Turismo 8—74100 Taranto, Italy |
| |
Abstract: | A number of numerical and analytical methods with different complexity can be exploited to analyse fibre amplifiers. Conventional approaches make the refinement and design of the devices extremely time consuming, especially when several design parameters have to be simultaneously optimised to obtain the desired performance in terms of gain and noise figure.In order to tackle this issue, a method based on an artificial neural network to perform the refinement and design of erbium doped photonic crystal fibre amplifiers is proposed in this paper. The capability of the neural network to capture the nonlinear functional link among the physical and geometrical characteristics of the fibre amplifier and its gain and noise figure is exploited. In the refinement it is employed to determine the optimal values of the parameters maximising the gain. In the design, it is used to develop an inverse problem solver in order to determine the values of the parameters corresponding to the known values of gain.Numerical results show that the proposed approach finds the refinement/design parameters in good accordance with respect to the conventional one. |
| |
Keywords: | Artificial neural networks Photonic crystal fibre amplifiers Inversion methods |
本文献已被 ScienceDirect 等数据库收录! |