Results of the JET real-time disruption predictor in the ITER-like wall campaigns

Abstract

The impact of disruptions in JET became even more important with the replacement of the previous Carbon Fiber Composite (CFC) wall with a more fragile full metal ITER-like wall (ILW). The development of robust disruption mitigation systems is crucial for JET (and also for ITER). Moreover, a reliable real-time (RT) disruption predictor is a pre-requisite to any mitigation method. The Advance Predictor Of DISruptions (APODIS) has been installed in the JET Real-Time Data Network (RTDN) for the RT recognition of disruptions. The predictor operates with the new ILW but it has been trained only with discharges belonging to campaigns with the CFC wall. 7 real-time signals are used to characterize the plasma status (disruptive or non-disruptive) at regular intervals of 1ms. After the first 3 JET ILW campaigns (991 discharges), the success rate of the predictor is 98.36% (alarms are triggered in average 426ms before the disruptions). The false alarm and missed alarm rates are 0.92% and 1.64%. IntroductIonDue to the complex and highly non-linear coupling of events that lead to a disruption, predictive physics-driven models of these phenomena have not been established from theoretical considerations so far. As an alternative, data-driven models allow the estimation of useful relationships among several quantities to recognize the signature of an incoming disruption.As mentioned in the abstract, the impact of disruptions in JET is a more serious issue with the ILW [1]. This article shows the results of a disruption predictor at JET, APODIS, that has been in operation in the JET RTDN during the three initial ILW campaigns (C28-C30, between August 2011 and July 2012). The objective has been to assess its prediction capabilities (success rate, missed alarms, false alarms and prediction times) for later use in next campaigns as trigger for mitigation actions. In the above ILW campaigns, the alarm generated by APODIS has been distributed through the RTDN and recorded for off-line analysis, but it has not been used to close any feedback loop.

The influence of an ITER-like wall on disruptions at JET

“…The fact that current quenches are significantly slower or even absent with the ILW makes disruption accounting more ambiguous compared to carbon wall operations and affects the calculation of the disruption rate and disruptivity, as will be shown in the next section. Obviously this will also complicate the assessment of disruption predictors that usually aim to detect the thermal quench [19].…”

Feature selection for disruption prediction from scratch in JET by using genetic algorithms and probabilistic predictors

“…As demonstrated and explained in [1,3,5], the use of frequency domain with that procedure enhances the ability of prediction. According to Table 2, each x corresponds to a signal being turned on.…”

“…The Advance Predictor Of DISruptions (APODIS) was developed as a data-driven model based on a combination of several support vector machine (SVM) classifiers. It has been installed in the JET real-time data network [2] and has been very successful during the last ILW campaigns [3]. An optimized APODIS system to predict from scratch [4] obtained also good prediction rates.…”

Proton Exchange Membrane Fuel Cell Stack Design Optimization Using an Improved Jaya Algorithm

“…A recent example of the use of deep learning (e.g., [8]) in nuclear fusion energy is found in [9] where a method has been developed for predicting disruptive instabilities in controlled fusion plasmas in magnetic-confinement tokamak reactors. Related work on the same type of problem has used machine learning strategies such as neural network [10][11][12], fuzzy logic and regression trees [13], support vector machine classification [14], and genetic algorithms [15]. Deep neural network is shown to outperform linear regression and (shallow) neural network for a short-term natural gas load forecasting application [16].…”