Diagnostic Data Integration Using Deep Neural Networks for Real-Time Plasma Analysis

Recent advances in acquisition equipment are providing experiments with growing amounts of precise, yet affordable sensors. At the same time, an improved computational power, coming from new hardware resources [GPU, field-programmable gate array (FPGA), adaptive compute acceleration platform (ACAP)] has been made available at relatively low costs. This led us to explore the possibility of completely renewing the chain of acquisition for a fusion experiment, where many high-rate sources of data, coming from different diagnostics, can be combined in a wide framework of algorithms. If, on the one hand, adding new data sources with different diagnostics enriches our knowledge about physical aspects, on the other hand, the dimensions of the overall model grow, making relations among variables more and more opaque. A new approach for integrating such heterogeneous diagnostics, based on the composition of deep variational autoencoders, could ease this problem, acting as a structural sparse regularizer. This has been applied to RFX-mod experimental data, integrating the soft X-ray linear images of plasma temperature with the magnetic state. However, to ensure a real-time signal analysis, these algorithmic techniques must be adapted to run in well-suited hardware. In particular, it is shown that, attempting a quantization of neuron transfer functions, such models can be adapted to run in an embedded programmable logic device. The resulting firmware, approximating the deep inference model to a set of simple operations, fits well with the simple logic units that are largely abundant in FPGAs. This is the key factor that permits the use of affordable hardware with complex deep neural topology and operates them in real-time.

[1]  Karl Pearson F.R.S..  LIII. On lines and planes of closest fit to systems of points in space , 1901 .

[2]  D. Biskamp,et al.  Reconnection processes and scaling laws in reversed field pinch magnetohydrodynamics , 1996 .

[3]  S T Roweis,et al.  Nonlinear dimensionality reduction by locally linear embedding. , 2000, Science.

[4]  A. Murari,et al.  Soft X ray tomographic imaging in the RFX reversed field pinch , 2001 .

[5]  D.M. Mount,et al.  An Efficient k-Means Clustering Algorithm: Analysis and Implementation , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Sergio Ortolani,et al.  Machine modification for active MHD control in RFX , 2003 .

[7]  V. Toigo,et al.  High current regimes in RFX-mod , 2007 .

[8]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[9]  Paolo Innocente,et al.  Equilibrium reconstruction for single helical axis reversed field pinch plasmas , 2011, 1101.2153.

[10]  Kevin P. Murphy,et al.  Machine learning - a probabilistic perspective , 2012, Adaptive computation and machine learning series.

[11]  Tommaso Bolzonella,et al.  RFX-mod: A multi-configuration fusion facility for three-dimensional physics studiesa) , 2013 .

[12]  L. Marrelli,et al.  Experimental investigation of electron temperature dynamics of helical states in the RFX-Mod reversed field pinch , 2013 .

[13]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[14]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[15]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[16]  Magnus Jahre,et al.  Streamlined Deployment for Quantized Neural Networks , 2017, ArXiv.

[17]  Christopher Burgess,et al.  beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework , 2016, ICLR 2016.

[18]  A. Luchetta,et al.  A framework for the integration of the development process of Linux FPGA System on Chip devices , 2018 .

[19]  Diviyan Kalainathan,et al.  Generative Neural networks to infer Causal Mechanisms: Algorithms and applications. (Réseaux de Neurones Génératifs pour la Découverte de Mécanismes Causaux: Algorithmes et Applications) , 2019 .

[20]  G. Manduchi,et al.  Upgrades of the RFX-mod reversed field pinch and expected scenario improvements , 2019, Nuclear Fusion.

[21]  Adriano Luchetta,et al.  A Zynq-Based Flexible ADC Architecture Combining Real-Time Data Streaming and Transient Recording , 2018, IEEE Transactions on Nuclear Science.

[22]  Xiang Zhou,et al.  Machine Learning and Control Theory , 2020, Handbook of Numerical Analysis.