Plasma rupture prediction method based on sub-classifier weight voting

Abstract

The invention discloses a plasma rupture prediction method based on sub-classifier weight voting, and the method comprises the steps: 1, training N independent sub-classifiers based on a machine learning technology through N groups of independent plasma rupture feature data; 2, testing the prediction capability of each sub-classifier, and endowing each sub-classifier with a corresponding prediction weight; 3, distributing the feature data of the to-be-predicted time slice to each sub-classifier, and giving prediction result values by the sub-classifiers respectively; 4, carrying out weighted averaging on the prediction result values of the sub-classifiers to obtain a prediction coefficient R, and predicting the to-be-predicted time slice. According to the method, effective information of various fracture related signals can be effectively utilized, interference information is eliminated, the plasma fracture prediction accuracy is improved, and the false alarm phenomenon is reduced.

Description

technical field [0001] The invention belongs to the field of machine learning, in particular to a plasma rupture prediction method based on weight voting of sub-classifiers. Background technique [0002] Plasma rupture is a phenomenon in which the plasma current drops rapidly during the discharge process of EAST and other tokamak devices, and the discharge is suddenly terminated. The escaped electrons released, thermal deposition and electromagnetic stress will cause great damage to the device. The EAST system has a massive gas injection (Massive Gas Injection, MGI) system to alleviate and avoid the rupture phenomenon. When the rupture is about to occur, the MGI system can be used to alleviate and avoid the occurrence of the rupture. Accurate prediction of the impending rupture is required. In recent years, the tokmak device has developed rupture prediction based on machine learning technology, and the EAST device has also carried out plasma rupture prediction based on neura...

AI Technical Summary

Problems solved by technology

[0003] At present, although the research on plasma rupture prediction carried out on the EAST device has achieved a high rate of rupture prediction, there are relatively common false alarms that make rupture predictions and issue rupture warnings when the system is operating normally.

If the actual operation of the plasma rupture prediction gives a false alarm, the tokmak device will take unnecessary measures to alleviate the rupture, which will cause unnecessary equipment and material loss, and will also affect the normal discharge experiment process

Images