Disruption prediction and mitigation is a crucial topic,especially for future large-scale tokamaks,due to disruption’sconcomitant harmful effects on the devices.On this topic,disruption prediction algorithm takes the...Disruption prediction and mitigation is a crucial topic,especially for future large-scale tokamaks,due to disruption’sconcomitant harmful effects on the devices.On this topic,disruption prediction algorithm takes the responsibility to giveaccurate trigger signal in advance of disruptions,therefore the disruption mitigation system can effectively alleviate theharmful effects.In the past 5 years,a deep learning-based algorithm is developed in HL-2A tokamak.It reaches a truepositive rate of 92.2%,a false positive rate of 2.5%and a total accuracy of 96.1%.Further research is implementedon the basis of this algorithm to solve three key problems,i.e.,the algorithm’s interpretability,real-time capability andtransferability.For the interpretability,HL-2A’s algorithm gives saliency maps indicating the correlation between thealgorithm’s input and output by perturbation analysis.The distribution of correlations shows good coherence with thedisruption causes.For the transferability,a preliminary disruption predictor is successfully developed in HL-2M,a newlybuilt tokamak in China.Although only 44 shots are used as the training set of this algorithm,it gives reasonable outputswith the help of data from HL-2A and J-TEXT.For the real-time capacity,the algorithm is accelerated to deal with an inputslice within 0.3 ms with the help of some adjustments on it and TFLite framework.It is also implemented into the plasmacontrol system and gets an accuracy of 89.0%during online test.This paper gives a global perspective on these results anddiscusses the possible pathways to make HL-2A’s algorithm a more comprehensive solution for future tokamaks.展开更多
文摘目的分析持续性姿势-知觉性头晕(persistent postural-perception dizziness,PPPD)患者静息状态下脑自发功能活动的变化,以探讨PPPD的发病机制。材料与方法患者组纳入2021年4月至2022年4月就诊的16名PPPD患者。收集与PPPD患者年龄、男女比例相仿的16例同期健康体检者为对照组。通过病史、体征、眼震电图、甩头实验、前庭诱发肌源性电位和影像学等检查排除其他类型头晕疾病的可能,并进行头晕残障量表、汉密尔顿焦虑量表、汉密尔顿抑郁量表评估和静息态功能MRI扫描,计算分数低频振幅(fractional amplitude of low frequency fluctuation,fALFF)、局部一致性(regional homogeneity,ReHo)。结果患者组左侧楔前叶(t=4.52)的fALFF值较对照组显著升高(P<0.05),而左侧前运动皮质(t=-6.60)和左侧布罗德曼48区(t=-7.61)的ReHo值较对照组显著降低(P<0.05)。结论PPPD患者的楔前叶的功能障碍可能与视觉和前庭信息的异常整合有关;左侧前运动皮质的功能障碍可能与患者主动被动运动时症状加重的现象有关;左侧布罗德曼48区的功能障碍可能与患者的情绪障碍有关。PPPD患者的脑自发功能活动的异常可能是导致PPPD发生的原因,这为PPPD患者的诊断和疗效评价提供了一种新的思路。
基金Project supported by the National MCF R&D Program of China(Grant Nos.2018YFE0302100 and 2019YFE03010003).The authors wish to thank all the members at South Western Institute of Physics for providing data,technique assistance and co-operating during the experiment.
文摘Disruption prediction and mitigation is a crucial topic,especially for future large-scale tokamaks,due to disruption’sconcomitant harmful effects on the devices.On this topic,disruption prediction algorithm takes the responsibility to giveaccurate trigger signal in advance of disruptions,therefore the disruption mitigation system can effectively alleviate theharmful effects.In the past 5 years,a deep learning-based algorithm is developed in HL-2A tokamak.It reaches a truepositive rate of 92.2%,a false positive rate of 2.5%and a total accuracy of 96.1%.Further research is implementedon the basis of this algorithm to solve three key problems,i.e.,the algorithm’s interpretability,real-time capability andtransferability.For the interpretability,HL-2A’s algorithm gives saliency maps indicating the correlation between thealgorithm’s input and output by perturbation analysis.The distribution of correlations shows good coherence with thedisruption causes.For the transferability,a preliminary disruption predictor is successfully developed in HL-2M,a newlybuilt tokamak in China.Although only 44 shots are used as the training set of this algorithm,it gives reasonable outputswith the help of data from HL-2A and J-TEXT.For the real-time capacity,the algorithm is accelerated to deal with an inputslice within 0.3 ms with the help of some adjustments on it and TFLite framework.It is also implemented into the plasmacontrol system and gets an accuracy of 89.0%during online test.This paper gives a global perspective on these results anddiscusses the possible pathways to make HL-2A’s algorithm a more comprehensive solution for future tokamaks.