Redirigiendo al acceso original de articulo en 15 segundos...
Inicio  /  Applied Sciences  /  Vol: 13 Par: 3 (2023)  /  Artículo
ARTÍCULO
TITULO

Performance Comparison of Machine Learning Disruption Predictors at JET

Enrico Aymerich    
Barbara Cannas    
Fabio Pisano    
Giuliana Sias    
Carlo Sozzi    
Chris Stuart    
Pedro Carvalho    
Alessandra Fanni and the JET Contributors    

Resumen

Reliable disruption prediction (DP) and disruption mitigation systems are considered unavoidable during international thermonuclear experimental reactor (ITER) operations and in the view of the next fusion reactors such as the DEMOnstration Power Plant (DEMO) and China Fusion Engineering Test Reactor (CFETR). In the last two decades, a great number of DP systems have been developed using data-driven methods. The performance of the DP models has been improved over the years both for a more appropriate choice of diagnostics and input features and for the availability of increasingly powerful data-driven modelling techniques. However, a direct comparison among the proposals has not yet been conducted. Such a comparison is mandatory, at least for the same device, to learn lessons from all these efforts and finally choose the best set of diagnostic signals and the best modelling approach. A first effort towards this goal is made in this paper, where different DP models will be compared using the same performance indices and the same device. In particular, the performance of a conventional Multilayer Perceptron Neural Network (MLP-NN) model is compared with those of two more sophisticated models, based on Generative Topographic Mapping (GTM) and Convolutional Neural Networks (CNN), on the same real time diagnostic signals from several experiments at the JET tokamak. The most common performance indices have been used to compare the different DP models and the results are deeply discussed. The comparison confirms the soundness of all the investigated machine learning approaches and the chosen diagnostics, enables us to highlight the pros and cons of each model, and helps to consciously choose the approach that best matches with the plasma protection needs.

 Artículos similares

       
 
Zahid Masood, Muhammad Usama, Shahroz Khan, Konstantinos Kostas and Panagiotis D. Kaklis    
Generative models offer design diversity but tend to be computationally expensive, while non-generative models are computationally cost-effective but produce less diverse and often invalid designs. However, the limitations of non-generative models can be... ver más

 
Feifei He, Qinjuan Wan, Yongqiang Wang, Jiang Wu, Xiaoqi Zhang and Yu Feng    
Accurately predicting hydrological runoff is crucial for water resource allocation and power station scheduling. However, there is no perfect model that can accurately predict future runoff. In this paper, a daily runoff prediction method with a seasonal... ver más
Revista: Water

 
Jan Kolínský, Tomá? Prá?il, Ladislav Socha, Jana Svi?elová, Karel Gryc, Josef Häusler and Martin Dvorák    
The present paper describes a comparison of the efficiency of different types of rotors used in the refining of aluminium melt at a foundry degassing unit (FDU). Physical modelling was used to obtain data for six different rotor types under defined exper... ver más
Revista: Applied Sciences

 
Ujwal Sharma, Uma Shankar Medasetti, Taher Deemyad, Mustafa Mashal and Vaibhav Yadav    
This review paper addresses the escalating operation and maintenance costs of nuclear power plants, primarily attributed to rising labor costs and intensified competition from renewable energy sources. The paper proposes a paradigm shift towards a techno... ver más
Revista: Applied Sciences

 
Vladimir Ulansky and Ahmed Raza    
Maintenance strategies play a crucial role in ensuring the reliability and performance of complex systems. Imperfect inspections, characterized by the probabilities of false positives and false negatives, significantly impact the effectiveness of mainten... ver más
Revista: Aerospace