A Deep Learning Technique to Control the Non-linear Dynamics of a Gravitational-wave Interferometer

TL;DR

This paper introduces a deep learning-based method combining probabilistic neural networks and Kalman-filter-inspired models to effectively control the non-linear dynamics of a gravitational-wave interferometer, demonstrated through simulation.

Contribution

It presents a novel deep learning approach for non-linear control, integrating state estimation and simple control, tailored for real-time application in LIGO systems.

Findings

Successful simulation of state estimation and control of LIGO mirror.

Real-time capable model running on a single CPU core.

Potential applicability to other non-linear control problems.

Abstract

In this work we developed a deep learning technique that successfully solves a non-linear dynamic control problem. Instead of directly tackling the control problem, we combined methods in probabilistic neural networks and a Kalman-Filter-inspired model to build a non-linear state estimator for the system. We then used the estimated states to implement a trivial controller for the now fully observable system. We applied this technique to a crucial non-linear control problem that arises in the operation of the LIGO system, an interferometric gravitational-wave observatory. We demonstrated in simulation that our approach can learn from data to estimate the state of the system, allowing a successful control of the interferometer's mirror . We also developed a computationally efficient model that can run in real time at high sampling rate on a single modern CPU core, one of the key requirements for the implementation of our solution in the LIGO digital control system. We believe these techniques could be used to help tackle similar non-linear control problems in other applications.