FusionPapers
図版検索トレンドwiki日本の研究
© 2026 FUSIONPAPERS
About法務情報
トップに戻る

Disruption predictor based on neural network and anomaly detection on J-TEXT

W Zheng, Q Q Wu, M Zhang, Z Y Chen, Y X Shang, J N Fan, Y Pan, J-TEXT Team2020年Plasma Physics and Controlled FusionIF 2.2出版社

Disruption prediction is essential for the safe operation of a large scale tokamak. Existing disruption predictors based on machine learning techniques have good prediction performance, but all these methods need large training datasets including many disruptions to develop their successful prediction capability. Future machines are unlikely to provide enough disruption samples since these cause excessive machine damage and the prediction models used are difficult to extrapolate to a machines that the predictor was not trained on. In this paper, a disruption predictor based on a deep learning and anomaly detection technique has been developed. It regards the disruption as an anomaly, and can learn on non-disruptive shots only. The model is trained to extract the hidden features of various non-disruptive shots with a convolutional neural network and a long-shot term memory (LSTM) recurrent neural network. It will predict the future trend of selected diagnostics, then using the predicted future trend and the measured signal to calculate an outlier factor to determine if a disruption is coming. It was tested with J-TEXT discharges in flat top phase and can demonstrate comparable performance to current machine learning disruption prediction techniques, without requiring a disruption data set. This could be applied to future tokamaks and reduce the dependency on disruptive experiments.

日本語訳

突発的崩壊(ディスラプション)予測は、大規模トカマクの安全運転に不可欠である。機械学習技術に基づく既存のディスラプション予測器は良好な予測性能を有するが、これらの手法はすべて、優れた予測能力を開発するために、多くのディスラプションを含む大規模な訓練データセットを必要とする。将来の装置では、ディスラプションが過度の装置損傷を引き起こすため、十分なディスラプションサンプルを得ることは見込めず、また、既存の予測モデルを訓練されていない装置へ外挿することは困難である。本論文では、深層学習と異常検知技術に基づくディスラプション予測器を開発した。本手法はディスラプションを異常とみなし、非ディスラプション放電のみを学習に用いる。モデルは、畳み込みニューラルネットワークと長短期記憶(LSTM)リカレントニューラルネットワークを用いて、様々な非ディスラプション放電の隠れた特徴を抽出するように訓練される。選択した診断量の将来トレンドを予測し、予測された将来トレンドと測定信号を用いて外れ値因子を計算し、ディスラプションが近づいているかどうかを判定する。J-TEXTのフラットトップ位相における放電を用いて検証した結果、ディスラプションデータセットを必要とせずに、既存の機械学習によるディスラプション予測手法と同等の性能を示すことができる。本手法は将来のトカマクに適用可能であり、ディスラプション実験への依存度を低減できる可能性がある。

wiki

Plasma disruptionTEXTJ-TEXTNeural network
この論文にはまだAI要約がありません。

関連論文

Cross-tokamak deployment study of plasma disruption predictors based on convolutional autoencoder

2024Plasma Physics and Controlled Fusion

Adaptive anomaly detection disruption prediction starting from first discharge on tokamak

2025Nuclear Fusion

Hybrid deep-learning architecture for general disruption prediction across multiple tokamaks

2021Nuclear Fusion

Forecasting disruptions in the ADITYA tokamak using neural networks

2000Nuclear Fusion

An interpretable disruption predictor on EAST using improved XGBoost and SHAP

2025Nuclear Fusion

Determining the prediction limits of models and classifiers with applications for disruption prediction in JET

2017Nuclear Fusion

From cold start to sustainable operation: a strategy for disruption prediction across the tokamak lifecycle

2026Nuclear Fusion

Vi-DP: low-latency video-based disruption prediction with multi-FOV fusion in EAST

2026Nuclear Fusion

Adaptive high learning rate probabilistic disruption predictors from scratch for the next generation of tokamaks

2014Nuclear Fusion

Integrated deep learning framework for unstable event identification and disruption prediction of tokamak plasmas

2023Nuclear Fusion