Waveguides bending are basic and important structures for high integration optics and circuits allowing to change the wave propagation direction [1]. Due to the abrupt change of the propagation direction of light over the discontinuity region reflection and radiation is expected to occurs and complex numerical techniques, such as the finite element method, should be used for the modeling of such structure while at the same time it requires knowledge of advanced electromagnetic theory and high computational effort and resources. On the other hand, complex neural networks architectures and machine learning algorithms have been used for the modeling of optical fiber couplers [2] and optical fibers and tapers [3]. The main advantages of machine learning based models are their simplicity, the reduced computational effort and time and also their application for synthesis problems. In this work, a machine learning algorithm has been implemented for the modeling of waveguides bending based on Silicon on Silica with a resonator at the bending. The refractive indexes are n1 = 3.476 and n2 =1.444. and the cavity size is defined by the coordinates of five coordinate points. The data set for the training and validation of the proposed model has been obtained by an efficient frequency domain finite element method [4]. Regression higher than 0.98 has been obtained for the efficiency computation. The obtained model is simple, it is less time-consuming and it requires less computational-effort than conventional numerical techniques used for the analysis of this kind of problems. As a conclusion waveguides bending can be analyzed by using machine learning algorithms. Additionally, a machine learning model can be easily adapted for the analysis of several other photonic and plasmonic devices.
|