Masters Theses

Keywords and Phrases

Convolutional Neural Network; Machine Learning; Multimode Fiber; Specklegram; Wavelength Meter

Abstract

“Wavelength meters are very important for precision measurements of both pulses and continuous-wave optical sources. Conventional wavelength meters employ gratings, prisms, interferometers, and other wavelength-sensitive materials in their design. Here, we report a simple and compact wavelength meter based on a section of multimode fiber and a camera. The concept is to correlate the multimodal interference pattern (i.e., speckle pattern) at the end-face of a multimode fiber with the wavelength of the input lightsource. Through a series of experiments, specklegrams from the end face of a multimode fiber as captured by a charge-coupled device (CCD) camera were recorded; the images were analyzed using a convolutional neural network (CNN) model for the design of a specklegram wavelength meter. The developed specklegram wavelength meter can accurately map speckle patterns of signature wavelength up to a resolution of 1 pm, which is the operating range of the Hewlett Packard 8168F tunable laser used for the experiment. Furthermore, the incorporated machine learning algorithm of the CNN model can optimally generalize for un-trained categories of a dataset from the same equipment. Up to 150,000 images were captured and utilized to train the CNN over the duration of the experiment. The CNN was trained with several categories of image data sets: from 10 nm, to 1 nm, and progressively down to 1 pm (for selected wavelengths). After training and finetuning, the final output shows 100% classification accuracy for the speckle patterns produced from the design set-up. This shows that a machine learning model can be used for the analysis of specklegrams in the design of a wavelength meter. Also, the developed model can be deployed on modern equipment for wavelength metering at negligible cost”--Abstract, page iii.

Advisor(s)

Huang, Jie

Committee Member(s)

Watkins, Steve Eugene, 1960-
Esmaeelpour, Mina

Department(s)

Electrical and Computer Engineering

Degree Name

M.S. in Electrical Engineering

Publisher

Missouri University of Science and Technology

Publication Date

Fall 2021

Pagination

x, 30 pages

Note about bibliography

Includes bibliographic references (pages 25-29).

Rights

© 2021 Ogbole Collins Inalegwu, All rights reserved.

Document Type

Thesis - Open Access

File Type

text

Language

English

Thesis Number

T 11950

Share

 
COinS