Abstract
Nuclear fusion is a promising alternative to address the problem of sustainable energy production. The tokamak is an approach to fusion based on magnetic plasma confinement, constituting a complex physical system with many control challenges. We study the characteristics and optimization of reservoir computing (RC) for real-time and adaptive prediction of plasma profiles in the DIII-D tokamak. Our experiments demonstrate that RC achieves comparable results to state-of-the-art (deep) convolutional neural networks (CNNs) and long short-term memory (LSTM) models, with a significantly easier and faster training procedure. This efficient approach allows for fast and frequent adaptation of the model to new situations, such as changing plasma conditions or different fusion devices.
Original language | English (US) |
---|---|
Pages (from-to) | 2630-2641 |
Number of pages | 12 |
Journal | IEEE Transactions on Neural Networks and Learning Systems |
Volume | 33 |
Issue number | 6 |
DOIs | |
State | Published - Jun 1 2022 |
All Science Journal Classification (ASJC) codes
- Software
- Computer Science Applications
- Computer Networks and Communications
- Artificial Intelligence
Keywords
- Adaptive learning
- condition monitoring
- nuclear fusion
- reservoir computing (RC)
- tokamak plasma