A real-time machine learning-based disruption predictor in DIII-D

doi:10.1088/1741-4326/ab28bf

This content will become publicly available on July 23, 2020

Title: A real-time machine learning-based disruption predictor in DIII-D

Abstract

A disruption prediction algorithm, named DPRF (Disruption Prediction using Random Forests), has run in real-time in the DIII-D plasma control system (PCS) over more than 900 discharges. DPRF naturally provides a probability mapping associated to its predictions, i.e. the disruptivity signal, now incorporated in the DIII-D PCS. Here, we report on disruption prediction accomplishments in terms of shot-by-shot performances, by simulating alarms on each discharge as in the PCS framework. Due to the optimised performance metric chosen to evaluate DPRF, we find that almost all disruptive discharges are detected in average with few hundred of milliseconds of warning time, but this comes at a high cost of false alarms produced. Performances are not satisfying ITER requirements, where the success rate has to be higher than 95%, but this is not completely unexpected. DPRF is trained on many years of major disruptions occurring during the flattop phase of the plasma current on DIII-D, but without any differentiation by cause. Furthermore, we find that DPRF is affected by a relatively high fraction of false alarms occurring during the first 500 milliseconds from the flattop onset. This subtle effect, more evident on the discharges where DPRF ran in real-time, can be marginalized bymore »« less

Authors:

^[1];

^[2];

^[3];

^[2];

^[2]

General Atomics, San Diego, CA (United States); Massachusetts Inst. of Technology (MIT), Cambridge, MA (United States)
Massachusetts Inst. of Technology (MIT), Cambridge, MA (United States)
Princeton Plasma Physics Lab. (PPPL), Princeton, NJ (United States)

Publication Date:: 2019-07-23

Research Org.:: General Atomics, San Diego, CA (United States); Massachusetts Inst. of Technology (MIT), Cambridge, MA (United States); Princeton Univ., NJ (United States)

Sponsoring Org.:: USDOE Office of Science (SC), Fusion Energy Sciences (FES) (SC-24)

OSTI Identifier:: 1562300

Report Number(s):: DOE-GA-54698
Journal ID: ISSN 0029-5515

Grant/Contract Number:: FC02-04ER54698; SC0014264; AC02-09CH11466

Resource Type:: Accepted Manuscript

Journal Name:: Nuclear Fusion

Additional Journal Information:: Journal Volume: 59; Journal Issue: 9; Journal ID: ISSN 0029-5515

Publisher:: IOP Science

Country of Publication:: United States

Language:: English

Subject:: 70 PLASMA PHYSICS AND FUSION TECHNOLOGY; disruption prediction; machine learning; random forests; DIII-D; real-time

Citation Formats


                    Rea, C., Montes, K. J., Erickson, K. G., Granetz, R. S., and Tinguely, R. A. A real-time machine learning-based disruption predictor in DIII-D.  United States: N. p., 2019. 
        Web.  doi:10.1088/1741-4326/ab28bf.

Copy to clipboard


                    Rea, C., Montes, K. J., Erickson, K. G., Granetz, R. S., & Tinguely, R. A. A real-time machine learning-based disruption predictor in DIII-D.  United States.  doi:10.1088/1741-4326/ab28bf.

Copy to clipboard


                    Rea, C., Montes, K. J., Erickson, K. G., Granetz, R. S., and Tinguely, R. A. Tue .  
        "A real-time machine learning-based disruption predictor in DIII-D".  United States.  doi:10.1088/1741-4326/ab28bf.

Copy to clipboard


                    
@article{osti_1562300,

  title        = {A real-time machine learning-based disruption predictor in DIII-D},

  author       = {Rea, C. and Montes, K. J. and Erickson, K. G. and Granetz, R. S. and Tinguely, R. A.},

  abstractNote = {A disruption prediction algorithm, named DPRF (Disruption Prediction using Random Forests), has run in real-time in the DIII-D plasma control system (PCS) over more than 900 discharges. DPRF naturally provides a probability mapping associated to its predictions, i.e. the disruptivity signal, now incorporated in the DIII-D PCS. Here, we report on disruption prediction accomplishments in terms of shot-by-shot performances, by simulating alarms on each discharge as in the PCS framework. Due to the optimised performance metric chosen to evaluate DPRF, we find that almost all disruptive discharges are detected in average with few hundred of milliseconds of warning time, but this comes at a high cost of false alarms produced. Performances are not satisfying ITER requirements, where the success rate has to be higher than 95%, but this is not completely unexpected. DPRF is trained on many years of major disruptions occurring during the flattop phase of the plasma current on DIII-D, but without any differentiation by cause. Furthermore, we find that DPRF is affected by a relatively high fraction of false alarms occurring during the first 500 milliseconds from the flattop onset. This subtle effect, more evident on the discharges where DPRF ran in real-time, can be marginalized by taking specific precautions on the validity range of the predictions, and performances do improve. Even if presently burdened by some limitations, DPRF provides an incredible and novel advantage. Thanks to the feature contribution analysis (e.g., the identification of which signals contributed to triggering an alarm), it is possible to interpret and explain DPRF predictions. It is the first time that such interpretability features is exploited by a disruption predictor: by uncovering the disruption events' causes, a better understanding of disruption dynamics is achieved, and a clear path toward the design of disruption avoidance strategies can be provided.},

  doi          = {10.1088/1741-4326/ab28bf},

  journal      = {Nuclear Fusion},

  number       = 9,

  volume       = 59,

  place        = {United States},

  year         = {2019},

  month        = {7}

}

Copy to clipboard

Journal Article:

Free Publicly Available Full Text

This content will become publicly available on July 23, 2020

Publisher's Version of Record

DOI: 10.1088/1741-4326/ab28bf

Other availability

Search WorldCat to find libraries that may hold this journal

Citation Metrics:

Cited by: 2 works

Citation information provided by
Web of Science

Save / Share:

Export Metadata

Save to My Library

Works referenced in this record:

Random Forests
journal, January 2001

Breiman, Leo
Machine Learning, Vol. 45, Issue 1, p. 5-32
DOI: 10.1023/A:1010933404324

Similar Records in DOE PAGES and OSTI.GOV collections:

Disruption prediction investigations using Machine Learning tools on DIII-D and Alcator C-Mod

Journal Article Rea, C. ; Granetz, R. S. ; Montes, K. ; ... - Plasma Physics and Controlled Fusion

Using data-driven methodology, we exploit the time series of relevant plasma parameters for a large set of disrupted and non-disrupted discharges to develop a classification algorithm for detecting disruptive phases in shots that eventually disrupt. Comparing the same methodology on different devices is crucial in order to have information on the portability of the developed algorithm and the possible extrapolation to ITER. Therefore, we use data from two very different tokamaks, DIII-D and Alcator C-Mod. We then focus on a subset of disruption predictors, most of which are dimensionless and/or machine-independent parameters, coming from both plasma diagnostics and equilibrium reconstructions,more »« less
Cited by 1
DOI: 10.1088/1361-6587/aac7fe

Full Text Available
Machine learning for disruption warnings on Alcator C-Mod, DIII-D, and EAST

Journal Article Montes, K. J. ; Rea, C. ; Granetz, R. S. ; ... - Nuclear Fusion

In this paper, we report on disruption prediction using a shallow machinelearning method known as Random Forests, trained on large databases containingonly plasma parameters that are available in real-time on Alcator C-Mod, DIII-D, and EAST. The database for each tokamak contains parameters sampled ~10 ⁶ times throughout ~10 ⁴ discharges (disruptive and non-disruptive) over the last 4years of operation. It is found that a number of parameters (e.g.P _rad/P _input,l _i,n/n _G,B _n=1/B ₀) exhibit changes in aggregate as a disruption is approached on one ormore of these tokamaks. However, for each machine, the most useful parameters,as well as themore »« less
Cited by 3
DOI: 10.1088/1741-4326/ab1df4
Exploratory Machine Learning Studies for Disruption Prediction Using Large Databases on DIII-D

Journal Article Rea, Cristina ; Granetz, Robert S. - Fusion Science and Technology

Not provided.
DOI: 10.1080/15361055.2017.1407206
Active real-time control of Alfvén eigenmodes by neutral beam and electron cyclotron heating in the DIII-D tokamak

Journal Article Hu, Wenhui ; Olofsson, K. E. J. ; Welander, A. S. ; ... - Nuclear Fusion

A real-time Alfvén eigenmode (AE) controller is designed and implemented for the first time in DIII-D. The experimental test consists of two parts: (i) open-loop and feedback control using neutral beam power as an actuator and (ii) open-loop control using electron cyclotron heating (ECH) as an actuator. Part (i) demonstrates the feasibility of varying neutral beam power injected into plasma to control overall AE amplitude as well as the successful application of real-time electron cyclotron emission (ECE) as the process controller’s AE amplitude sensor. Here, the temporal evolution of AE amplitude at a specific radial location has also been controlledmore »« less
DOI: 10.1088/1741-4326/aaddaf

Full Text Available
Data-driven reinforcement learning–based real-time energy management system for plug-in hybrid electric vehicles

Journal Article Qi, Xuewei ; Wu, Guoyuan ; Boriboonsomsin, Kanok ; ... - Transportation Research Record

Plug-in hybrid electric vehicles (PHEVs) show great promise in reducing transportation-related fossil fuel consumption and greenhouse gas emissions. Designing an efficient energy management system (EMS) for PHEVs to achieve better fuel economy has been an active research topic for decades. Most of the advanced systems rely either on a priori knowledge of future driving conditions to achieve the optimal but not real-time solution (e.g., using a dynamic programming strategy) or on only current driving situations to achieve a real-time but nonoptimal solution (e.g., rule-based strategy). This paper proposes a reinforcement learning–based real-time EMS for PHEVs to address the trade-off betweenmore »« less
Cited by 4
DOI: 10.3141/2572-01

Full Text Available

Similar Records

This content will become publicly available on July 23, 2020

Title: A real-time machine learning-based disruption predictor in DIII-D

Abstract

Citation Formats

Random Forests journal, January 2001

Random Forests
journal, January 2001