In tokamak plasmas, various Magnetohydrodynamic (MHD) instabilities could be driven by free energy, which enhance the plasma's transportation, leading to a reduction in critical fusion parameters such as temperature and density, and in severe cases, can even cause major plasma disruptions. Accurate identification and active control of MHD is an important technology for maintaining stable operation and improving the parameter performance of fusion reactors in the future, but it is difficult to balance the accuracy, robustness and standard uniformity by traditional methods to recognize MHD instability. This study employs deep learning techniques to learn from 1000 shots manually labeled as three types of MHD instabilities: fishbone mode, long-lived mode, and TM mode, enabling real-time automated recognition of the instabilities. High accuracies of 97.83%, 95.32%, 94.84% are obtained on 200 testing shots, which are measured by area under the receiver-operator characteristic curve (AUC). Data processing methods that conform to the intuition of physics experts, such as short time Fourier transform (STFT), have been retained, and advanced artificial intelligence algorithms such as Resnet have been combined to achieve a high accuracy rate. It also demonstrated the robustness in fully automatic detections over thousands of discharges. Furthermore, this study explores multitask learning techniques. Instead of using three individual neural network to recognize the different instabilities, a joint recognition algorithm is proposed. The joint algorithm shares the encoder of the three networks and use separate decoder branches to output the result of different instabilities. An inspiring outcome is found that the joint algorithm outperforms the individual ones on all of the instability recognition tasks. Implementing multiple MHD recognition tasks jointly can comprehensively improve the model's performance on each task by sharing related information between intrinsically related tasks. This means that in the future, the model can further develop as more tasks are added, revealing a possible technique routine to build an accurate and comprehensive large-scale model for fusion applications. The method realizes high accuracy, robustness and computational efficiency of MHD instability recognition at the same time, providing a powerful means to support the real-time control of MHD instability in future fusion reactors.
This paper presents a deep learning approach to accurately identify different types of magnetohydrodynamic (MHD) instabilities in tokamak plasmas, which can degrade fusion reactor performance. The method achieves high accuracy in real-time detection and can be further expanded to recognize more instability types, providing a powerful tool for fusion reactor control.