Machine Learning Methods for Control of Fibre Lasers with Double Gain Nonlinear Loop Mirror

Abstract

Many types of modern lasers feature nonlinear properties, which makes controlling their operation a challenging engineering problem. In particular, fibre lasers present both high-performance devices that are already used for diverse industrial applications, but also interesting and not yet fully understood nonlinear systems. Fibre laser systems operating at high power often have multiple equilibrium states, and this produces complications with the reproducibility and management of such devices. Self-tuning and feedback-enabled machine learning approaches might define a new era in laser science and technology. The present study is the first to demonstrate experimentally the application of machine learning algorithms for control of the pulsed regimes in an all-normal dispersion, figure-eight fibre laser with two independent amplifying fibre loops. The ability to control the laser operation state by electronically varying two drive currents makes this scheme particularly attractive for implementing machine learning approaches. The self-tuning adjustment of two independent gain levels in the laser cavity enables generation-on-demand pulses with different duration, energy, spectral characteristics and time coherence. We introduce and evaluate the application of several objective functions related to selection of the pulse duration, energy and degree of temporal coherence of the radiation. Our results open up the possibility for new designs of pulsed fibre lasers with robust electronics-managed control.

Machine learning and applications in ultrafast photonics

“…This modelling was rapidly followed by an experimental implementation using a singular fitness function to identify self-starting regimes in an NPE laser [31]. A number of subsequent experiments for various laser configurations (NPE, ringcavity, figure-of-eight) have used genetic algorithms to achieve self-tuning and auto-setting in different regimes such as Q-switching, mode-locking, Q-switched mode-locking, or the generation of on-demand pulses with different duration and energies [32][33][34][35][36].…”

Optical Waveform Tailoring in Passive and Laser Cavity Fibre Systems

“…Next, we discuss a new design of a model-locked all-fibre Figure-8 laser employing a nonlinear amplifying loop mirror (NALM) with two active fibre segments and two independently controlled pump-power modules (Fig. 3) [10,11]. This laser layout combines the reliability and robustness of conventional Figure-8 lasers with the flexibility of nonlinear-polarisation-evolution lasers, providing access to a variety of generation regimes with a relatively wide adjustment range of the pulse parameters.…”

Intelligent Breathing Soliton Generation in Ultrafast Fiber Lasers

“…[30,31] The application of advanced algorithmic tools and adaptive feedback and control has recently greatly boosted the progress in the search for a truly selfoptimising laser, and a number of groups have reported on different approaches to automate optimisation of one or more parameters of the laser cavity to reach and maintain a desired operating state. [32][33][34][35][36][37][38][39][40][41] A recent work [42] introduced extra novelty by incorporating fast spectral measurements into the feedback loop of the laser setting which, along with an intelligent polarisation search algorithm, enabled real-time control of the spectral width and shape of ultrashort mode-locked pulses. Despite these significant advances, the intelligent generation of breathing solitons in a fibre laser remains challenging because breathers refer to a highly dynamical state in which the pulse spectral and temporal characteristics change drastically within a period of oscillation, while existing machine-learning strategies are mostly designed to target laser generation regimes of parameter-invariant, stationary pulses.…”