On the potential of ruled-based machine learning for disruption prediction on JET

被引：9

作者：

Lungaroni, M. ^{[1
,99
]}

Murari, A. ^{[2
,16
,39
]}

Peluso, E. ^{[1
,99
]}

Vega, J. ^{[3
,61
]}

Farias, G. ^{[4
]}

Gelfusa, M. ^{[1
,99
]}

Abduallev, S. ^{[43
]}

Abhangi, M. ^{[50
]}

Abreu, P. ^{[57
]}

Afzal, M. ^{[11
]}

Aggarwal, K. M. ^{[33
]}

Ahlgren, T. ^{[105
]}

Ahn, J. H. ^{[12
]}

Aho-Mantila, L. ^{[115
]}

Aiba, N. ^{[73
]}

Airila, M. ^{[115
]}

Albanese, R. ^{[108
]}

Aldred, V. ^{[11
]}

Alegre, D. ^{[97
]}

Alessi, E. ^{[49
]}

Aleynikov, P. ^{[59
]}

Alfier, A. ^{[16
]}

Alkseev, A. ^{[76
]}

Allinson, M. ^{[11
]}

Alper, B. ^{[11
]}

Alves, E. ^{[57
]}

Ambrosino, G. ^{[108
]}

Ambrosino, R. ^{[109
]}

Amicucci, L. ^{[94
]}

Amosov, V. ^{[92
]}

Sunden, E. Andersson ^{[26
]}

Angelone, M. ^{[94
]}

Anghel, M. ^{[89
]}

Angioni, C. ^{[66
]}

Appel, L. ^{[11
]}

Appelbee, C. ^{[11
]}

Arena, P. ^{[34
]}

Ariola, M. ^{[109
]}

Arnichand, H. ^{[12
]}

Arshad, S. ^{[45
]}

Ash, A. ^{[11
]}

Ashikawa, N. ^{[72
]}

Aslanyan, V. ^{[68
]}

Asunta, O. ^{[5
]}

Auriemma, F. ^{[16
]}

Austin, Y. ^{[11
]}

Avotina, L. ^{[107
]}

Axton, M. D. ^{[11
]}

Ayres, C. ^{[11
]}

Bacharis, M. ^{[28
]}

机构：

[1] Univ Roma Tor Vergata, Dept Ind Engn, Via Politecn 1, Rome, Italy

[2] Univ Padua, INFN, ENEA, Consorzio RFX,CNR,Acciaierie Venete SpA, Corso Stati Uniti 4, I-35127 Padua, Italy

[3] CIEMAT, Lab Nacl Fus, Av Complutense 40, E-28040 Madrid, Spain

[4] Pontificia Univ Catolica Valparaiso, Av Brasil 2147, Valparaiso, Chile

[5] Aalto Univ, POB 14100, FIN-00076 Aalto, Finland

[6] Aix Marseille Univ, CNRS, Ctr Marseille, M2P2 UMR 7340, F-13451 Marseille, France

[7] Aix Marseille Univ, CNRS, IUSTI UMR 7343, F-13013 Marseille, France

[8] Aix Marseille Univ, CNRS, PIIM, UMR 7345, F-13013 Marseille, France

[9] Arizona State Univ, Tempe, AZ USA

[10] Barcelona Supercomp Ctr, Barcelona, Spain

[11] CCFE Culham Sci Ctr, Abingdon OX14 3DB, Oxon, England

[12] CEA, IRFM, F-13108 St Paul Les Durance, France

[13] Univ Calif San Diego, Ctr Energy Res, La Jolla, CA 92093 USA

[14] Ctr Brasileiro Pesquisas Fis, Rua Xavier Sigaud 160, BR-22290180 Rio De Janeiro, Brazil

[15] Consorzio CREATE, Via Claudio 21, I-80125 Naples, Italy

[16] Consorzio RFX, Corso Stati Uniti 4, I-35127 Padua, Italy

[17] Daegu Univ, Gyongsan 712174, Gyeongbuk, South Korea

[18] Univ Carlos III Madrid, Dept Fis, Madrid 28911, Spain

[19] Univ Ghent, Dept Appl Phys UG, St Pietersnieuwstr 41, B-9000 Ghent, Belgium

[20] Chalmers Univ Technol, Dept Earth & Space Sci, SE-41296 Gothenburg, Sweden

[21] Univ Cagliari, Dept Elect & Elect Engn, Piazza Armi 09123, Cagliari, Italy

[22] Comenius Univ, Dept Expt Phys, Fac Math Phys & Informat, Mlynska Dolina F2, Bratislava 84248, Slovakia

[23] Warsaw Univ Technol, Dept Mat Sci, PL-01152 Warsaw, Poland

[24] Korea Adv Inst Sci & Technol, Dept Nucl & Quantum Engn, Daejeon 34141, South Korea

[25] Univ Strathclyde, Dept Phys & Appl Phys, Glasgow G4 ONG, Lanark, Scotland

[26] Uppsala Univ, Dept Phys & Astron, SE-75120 Uppsala, Sweden

[27] Chalmers Univ Technol, Dept Phys, S-41296 Gothenburg, Sweden

[28] Imperial Coll London, Dept Phys, London SW7 2AZ, England

[29] KTH, SCI, Dept Phys, SE-10691 Stockholm, Sweden

[30] Univ Basel, Dept Phys, Basel, Switzerland

[31] Univ Oxford, Dept Phys, Oxford OX1 2JD, England

[32] Univ Warwick, Dept Phys, Coventry CV4 7AL, W Midlands, England

[33] Queens Univ, Dept Pure & Appl Phys, Belfast BT7 1NN, Antrim, North Ireland

[34] Univ Catania, Dipartimento Ingn Elettr Elettron & Informat, I-95125 Catania, Italy

[35] Univ Trento, Dipartimento Ingn Ind, Trento, Italy

[36] Dublin City Univ, Dublin, Ireland

[37] Swiss Plasma Ctr, EPFL, CH-1015 Lausanne, Switzerland

[38] EUROfus Programme Management Unit, Boltzmannstr 2, D-85748 Garching, Germany

[39] Culham Sci Ctr, EUROfus Programme Management Unit, Culham OX14 3DB, England

[40] European Commiss, B-1049 Brussels, Belgium

[41] ULB, Fluid & Plasma Dynam, Campus Plaine CP 231 Blvd Triomphe, B-1050 Brussels, Belgium

[42] FOM Inst DIFFER, Eindhoven, Netherlands

[43] Forschungszentrum Julich GmbH, Inst Energie & Klimaforsch Plasmaphys, D-52425 Julich, Germany

[44] Fourth State Res, 503 Lockhart Dr, Austin, TX USA

[45] Fus Energy Joint Undertaking, Josep Pl 2,Torres Diagonal Litoral B3, Barcelona 08019, Spain

[46] KTH, Fusion Plasma Phys, EES, SE-10044 Stockholm, Sweden

[47] Gen Atom, POB 85608, San Diego, CA 92186 USA

[48] HRS Fusion, W Orange, NJ USA

[49] IFP CNR, Via R Cozzi 53, I-20125 Milan, Italy

[50] Inst Plasma Res, Gandhinagar 382428, Gujarat, India

来源：

FUSION ENGINEERING AND DESIGN | 2018年 / 130卷

关键词：

Disruptions; Machine learning predictors; Classification and regression trees; Boosting; Bagging; Random forests; Noise-based ensembles;

D O I：

10.1016/j.fusengdes.2018.02.087

中图分类号：

TL [原子能技术]; O571 [原子核物理学];

学科分类号：

0827 ; 082701 ;

摘要：

In the last years, it has become apparent that detecting disruptions with sufficient anticipation time is an essential but not exclusive task of predictors. It is also important that the prediction is accompanied by appropriate qualifications of its reliability and it is formulated in mathematical terms appropriate for the task at hand (mitigation, avoidance, classification etc.). In this paper, a wide series of rule-based predictors, of the Classification and Regression Trees (CART) family, have been compared to assess their relative merits. An original refinement of the training, called noise-based ensembles, has allowed not only to obtain significantly better performance but also to increase the interpretability of the results. The final predictors can indeed be represented by a tree or a series of specific and clear rules. Such performance has been proved by analysing large databases of shots on JET with both the carbon wall and the ITER Like Wall. In terms of performance, the developed tools are therefore very competitive with other machine learning techniques, with the specificity of formulating the final models in terms of trees and simple rules.

引用

页码：62 / 68

页数：7

共 50 条

[1] Investigation of Machine Learning Techniques for Disruption Prediction Using JET Data
Croonen, Joost
Amaya, Jorge
Lapenta, Giovanni
PLASMA, 2023, 6 (01) : 89 - 102
[2] Smart Techniques in Urban Planning: An Insight to Ruled-Based Design
Pisano, Carlo
De Luca, Giuseppe
Dastgerdi, Ahmadreza Shirvani
SUSTAINABILITY, 2020, 12 (01)
[3] Ruled-based feature extraction and recognition from STEP file
Ismail, N
Tan, CF
Wong, SV
Osman, MR
Sulaiman, S
2002 STUDENT CONFERENCE ON RESEARCH AND DEVELOPMENT, PROCEEDINGS: GLOBALIZING RESEARCH AND DEVELOPMENT IN ELECTRICAL AND ELECTRONICS ENGINEERING, 2002, : 90 - 93
[4] A Ruled-Based Part of Speech (RPOS) Tagger for Malay Text Articles
Alfred, Rayner
Mujat, Adam
Obit, Joe Henry
INTELLIGENT INFORMATION AND DATABASE SYSTEMS (ACIIDS 2013), PT II, 2013, 7803 : 50 - 59
[5] Performance Comparison of Machine Learning Disruption Predictors at JET
Aymerich, Enrico
Cannas, Barbara
Pisano, Fabio
Sias, Giuliana
Sozzi, Carlo
Stuart, Chris
Carvalho, Pedro
Fanni, Alessandra
APPLIED SCIENCES-BASEL, 2023, 13 (03):
[6] Ruled-based, Interlingual Motivated Mapping of plWordNet onto SUMO Ontology
Kedzia, Pawel
Piasecki, Maciej
LREC 2014 - NINTH INTERNATIONAL CONFERENCE ON LANGUAGE RESOURCES AND EVALUATION, 2014, : 4351 - 4358
[7] Exploration of Ruled-Based and Probabilistic Localization Algorithms for Wall-Following Robot
SamratulFuady
Pane, YudhaPrawira
Ibrahim, Adrianto Ravi
WidyawardanaAdiprawita
2012 INTERNATIONAL CONFERENCE ON ADVANCED COMPUTER SCIENCE AND INFORMATION SYSTEMS, 2012, : 249 - 254
[8] A machine learning approach based on generative topographic mapping for disruption prevention and avoidance at JET
Pau, A.
Fanni, A.
Carcangiu, S.
Cannas, B.
Sias, G.
Murari, A.
Rimini, F.
Abduallev, S.
Abhangi, M.
Abreu, P.
Afzal, M.
Aggarwal, K. M.
Ahlgren, T.
Ahn, J. H.
Aho-Mantila, L.
Aiba, N.
Airila, M.
Albanese, R.
Aldred, V.
Alegre, D.
Alessi, E.
Aleynikov, P.
Alfier, A.
Alkseev, A.
Allinson, M.
Alper, B.
Alves, E.
Ambrosino, G.
Ambrosino, R.
Amicucci, L.
Amosov, V.
Sunden, E. Andersson
Angelone, M.
Anghel, M.
Angioni, C.
Appel, L.
Appelbee, C.
Arena, P.
Ariola, M.
Arnichand, H.
Arshad, S.
Ash, A.
Ashikawa, N.
Aslanyan, V.
Asunta, O.
Auriemma, F.
Austin, Y.
Avotina, L.
Axton, M. D.
Ayres, C.
NUCLEAR FUSION, 2019, 59 (10)
[9] Comparison of Advanced Machine Learning Tools for Disruption Prediction and Disruption Studies
Odstrcil, Michal
Murari, Andrea
Mlynar, Jan
IEEE TRANSACTIONS ON PLASMA SCIENCE, 2013, 41 (07) : 1751 - 1759
[10] Ruled-based energy management strategy for a Fuel-Cell battery vehicle
Duchossois, F.
Madi, N.
Pascal, J.
2017 IEEE VEHICLE POWER AND PROPULSION CONFERENCE (VPPC), 2017,

← 1 2 3 4 5 →