A dimensionality reduction algorithm for mapping tokamak operational regimes using a variational autoencoder (VAE) neural network. (18th November 2021)

• Record Type: Journal Article
• Authors: Wei, Y.; Levesque, J.P.; Hansen, C.J.; Mauel, M.E.; Navratil, G.A.
• Is Part Of: Nuclear fusion. Volume 61:Number 12(2021)
• Publication Date: 2021-11-18
• Subjects: disruption avoidance -- machine learning -- neural network -- variational autoencoder -- HBT-EP -- feedback control; Nuclear fusion -- Periodicals; 621.48405
• DOI: 10.1088/1741-4326/ac3296
• Languages: English
• ISSNs: 0029-5515

Abstract

Abstract: A variational autoencoder (VAE) is a type of unsupervised neural network which is able to learn meaningful data representations in a reduced dimensional space. We present an application of VAE in identifying the operational stability boundary of tokamak plasma discharges. This model was implemented using a dataset of over 3000 discharges from the high beta tokamak-extended pulse (HBT-EP) device. We found the VAE model to be capable of forming a continuous low-dimensional operational space map and identifying the operational boundaries using a specified warning time window. By projecting the operational parameters onto the same reduced space, this provides an intuitive way for the machine operator or an automated control system to perform disruption avoidance using a relevant control actuator as a discharge approaches a boundary. Pre-programmed GPU control experiments were conducted to demonstrate this control technique using HBT-EP's saddle control coils as a horizontal position actuator, showing the ability to avoid the oncoming disruptive event and extend the duration of the discharge.