Multi-mode Tokamak device rupture early warning method and system

Abstract

The invention discloses a multi-mode Tokamak device fracture early warning method and system, and belongs to the field of Tokamak device safety protection. The method comprises the following steps: step 1, collecting multi-modal data, and marking fracture data in the collected multi-modal data; 2, time axis alignment is carried out on the collected multi-modal data, time slices are divided, and a fracture early warning database is formed; 3, training the fracture early warning model by using the fracture early warning database, and performing real-time deployment on the optimal fracture early warning model obtained by training; and step 4, in the Tokamak experiment process, inputting 0-dimensional diagnosis data and two-dimensional image diagnosis data which are acquired in real time into the optimal fracture early warning model, and performing fracture relief and device protection according to an output fracture early warning result. According to the method, the fracture state of the Tokamak device can be predicted more accurately, the fracture processing actuator is triggered when the Tokamak device is about to be fractured, and the device is better prevented from being fractured and damaged.

Description

Technical Field

[0001] The present invention belongs to the field of safety protection of tokamak devices, and in particular relates to a multi-modal tokamak device rupture early warning method and system. Background Art

[0002] When a tokamak plasma breaks, energy is deposited on the first wall material of the device in a very short time, which will directly cause material damage and affect the safe operation of the device. In devices such as ITER (International Thermonuclear Experimental Reactor) and BEST (Burning plasma Experimental Superconducting Tokamak), due to factors such as high energy storage and large current, the damage caused by the rupture is more serious. During the rupture, eddy currents and corona currents will be generated in the internal components of the device, and the electromagnetic force of tens of thousands of Newtons will be generated by the magnetic field. The current will directly threaten the safety of the internal components. For future fusion reactors, an unmitigated rupture may cause damage to the device and cause inestimable losses. However, the development event chain of plasma rupture is extremely complex, nonlinear and rapid, so it is difficult to warn of plasma rupture based on physical understanding. Therefore, it is urgent to develop a method and system that can provide early warning of ruptures by integrating a variety of diagnostic information such as visible and infrared images of plasma temperature, density and plasma state. Summary of the invention

[0003] In order to solve the problems existing in the prior art, the present invention provides a multi-modal tokamak device rupture warning method and system, which integrates the information in the 0-dimensional time series signal and the two-dimensional image signal, can accurately predict the rupture of the tokamak device, and thus effectively alleviate the rupture hazards.

[0004] In order to achieve the purpose of the present invention, the technical solution adopted by the present invention is as follows: A multi-mode tokamak device rupture early warning method, the method comprising the following steps: Step 1: Data collection and annotation: Collect multimodal data, including 0-dimensional diagnostic data collected and calculated using real-time diagnostics in the tokamak device, and plasma 2D image diagnostic data collected using a camera; annotate the fracture data in the collected multimodal data; Step 2, data preparation: align the collected multimodal data on the time axis and divide them into time slices. Each time slice contains 0-dimensional diagnostic data, 2D image diagnostic data, and annotated rupture data information. The above data and information together form a rupture warning database; Step 3: Model training: Use the fracture warning database to train the fracture warning model, and deploy the optimal fracture warning model obtained through training in real time; Step 4: Rupture warning: During the tokamak experiment, the real-time 0-dimensional diagnostic data and 2D image diagnostic data are input into the optimal rupture warning model, and rupture mitigation and device protection are performed based on the output rupture warning results.

[0005] Furthermore, in step 1, the 0-dimensional diagnostic data includes plasma body current Ip, plasma current error Ip_error, plasma density Ne, ring voltage V_loop, and plasma elongation ratio Kappa; the plasma two-dimensional image diagnostic data collected by the camera includes a tokamak image, and the tokamak image includes any one of an image of the entire plasma area observed along the plasma tangent and an image of a partial plasma area, wherein the band to which the collected plasma two-dimensional image belongs is any one of a visible light band, an infrared band, and an ultraviolet band; the labeling of the rupture data in the collected multimodal data includes labeling by a method combining automatic judgment of the current change rate and expert experience labeling, and marking the time point of the rupture in the collected multimodal data.

[0006] Furthermore, in step 2, aligning the collected multimodal data on the time axis includes downsampling the high sampling rate data to match the low sampling rate data.

[0007] Furthermore, in step 3, the structure of the rupture warning model is: using a convolutional neural network CNN and a long short-term memory network LSTM to process 0-dimensional diagnostic data to obtain a first hidden vector; using a Video Vision Transformer model to process plasma two-dimensional image diagnostic data to obtain a second hidden vector; after splicing the first hidden vector and the second hidden vector, classifying them through a multi-layer perceptron MLP to obtain a rupture warning result.

[0008] Furthermore, in step 4, 0-dimensional diagnostic data is obtained in real time by reading the acquisition system data through the reflective memory card, and 2D image diagnostic data is obtained in real time through the image acquisition card; the result of the rupture warning is transmitted to the plasma control system in real time through the reflective memory network.

[0009] On the other hand, the present invention also provides a multi-mode tokamak device rupture warning system, the system comprising: Data acquisition and annotation module: used to acquire multimodal data, including 0-dimensional diagnostic data acquired and calculated using real-time diagnostics in the tokamak device, and plasma 2D image diagnostic data acquired using a camera; annotate the fracture data in the acquired multimodal data; Data preparation module: used to align the time axis of the collected multimodal data and divide them into time slices. Each time slice contains 0-dimensional diagnostic data, 2D image diagnostic data, and annotated rupture data information. Rupture warning module: It is used to input the multi-modal data with time axis alignment into the optimal rupture warning model during the tokamak experiment, and perform rupture mitigation and device protection according to the output rupture warning results.

[0010] The beneficial effects of the present invention are: The present invention proposes a multi-modal tokamak device rupture warning method, which combines the tokamak information contained in the 0-dimensional diagnostic signal and the 2-dimensional image data, and can more accurately predict the rupture state of the tokamak device; at the same time, a multi-modal tokamak device rupture warning system is realized, which can predict the plasma rupture state in real time through a multi-modal method, and trigger a rupture processing actuator when it is about to rupture, so as to better avoid the device from suffering rupture damage. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 This is a flow chart of a multi-modal tokamak device rupture warning method of the present invention; Figure 2 This is a structural diagram of a multi-modal tokamak device rupture warning system of the present invention. DETAILED DESCRIPTION

[0012] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the protection scope of the present invention.

[0013] like Figure 1 The figure shows a flow chart of a multi-modal tokamak device rupture warning method. The rupture warning model training process is divided into the following steps: Step 1, data collection and annotation: Collect multimodal data. The 0-dimensional diagnostic signal in this embodiment uses plasma current signal Ip, plasma current error signal Ip_error, density signal Ne, ring voltage V_loop, plasma vertical position z, normalized specific pressure Betan, lithium impurity content Li, plasma elongation ratio Kappa, boundary safety factor Q95, plasma energy storage Wmhd, a total of 10 diagnostic signals. The two-dimensional image diagnostic signal uses a tangential observation camera installed at the plane in the J window. The field of view range is the entire plasma annular cross section, and the image acquisition band is any one of the visible light band, infrared band, and ultraviolet band. Data annotation uses a method of automatically judging the current change rate such as the current drop rate combined with the annotation of experts in the field of rupture to mark the time slice of the rupture in each time data collected.

[0014] Step 2, data preparation: Align the multimodal data collected in step 1 and the labels of the annotated rupture time slices according to the time axis, and downsample the data with a higher sampling rate to keep it consistent with the time axis of the data with a lower sampling rate. Every 10ms is divided into 1 time slice, and each time slice contains 0-dimensional diagnostic data and 2D image diagnostic data, as well as the rupture information of the current time slice, forming a rupture warning database.

[0015] Step 3, model training: use the rupture warning database obtained in step 2 to train the rupture warning model, save the optimal rupture warning model obtained through training, and deploy the optimal rupture warning model in real time, wherein the structure of the rupture warning model is: use the convolutional neural network CNN and the long short-term memory network LSTM to process the 0-dimensional diagnostic data to obtain the first hidden vector; use the Video Vision Transformer model to process the plasma two-dimensional image diagnostic data to obtain the second hidden vector; after splicing the first hidden vector and the second hidden vector, classify them through the multi-layer perceptron MLP to obtain the rupture warning result; Step 4: Rupture warning: During the tokamak experiment, the real-time 0-dimensional diagnostic data and 2D image diagnostic data are input into the optimal rupture warning model, and rupture mitigation and device protection are performed based on the output rupture warning results.

[0016] When the Tokamak device is in operation, a multi-modal Tokamak device rupture warning system is used to perform real-time rupture prediction. Figure 2As shown, it is a structural diagram of a rupture warning system of a multi-modal tokamak device of the present invention, which includes a data acquisition module, a data preparation module and a rupture warning module. During the experiment, the rupture warning system reads the 0-dimensional diagnostic signal of the tokamak diagnostic system of the front-end signal source into the data acquisition module in real time through the reflective memory network, and collects the high-speed two-dimensional image diagnostic signal in real time through the image acquisition card. Next, the data preparation module denoises and filters the collected 0-dimensional diagnostic signal, resizes the high-speed two-dimensional image signal, and then aligns the 0-dimensional diagnostic signal and the two-dimensional image signal, and then sends them to the rupture warning module. In the rupture warning module, the 0-dimensional diagnostic signal is processed by the CNN+LSTM network, and the video image signal is processed by the Video Vision Transformer (ViViT). After obtaining the rupture warning result, the rupture warning result is transmitted to the plasma control system, i.e., the actuator, in real time through the reflective memory network to perform rupture avoidance or mitigation operations. When it is predicted that the rupture is about to occur, the plasma current is controlled to drop steadily by the control coil, thereby reducing the damage to the device; when the plasma current cannot be controlled, the plasma rupture is quickly alleviated by triggering MGI (large gas injection).

[0017] The specific embodiments described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A multi-mode tokamak device rupture early warning method, characterized in that: The method comprises the following steps: Step 1, data acquisition: collect multimodal data, including 0-dimensional diagnostic data collected and calculated using real-time diagnostics in the tokamak device, and plasma 2D image diagnostic data collected using a camera; annotate the fracture data in the collected multimodal data; Step 2, data preparation: align the collected multimodal data on the time axis and divide them into time slices. Each time slice contains 0-dimensional diagnostic data, 2D image diagnostic data, and annotated rupture data information. The above data and information together form a rupture warning database; Step 3: Model training: Use the fracture warning database to train the fracture warning model, and deploy the optimal fracture warning model obtained through training in real time; Step 4: Rupture warning: During the tokamak experiment, the real-time 0-dimensional diagnostic data and 2D image diagnostic data are input into the optimal rupture warning model, and rupture mitigation and device protection are performed based on the output rupture warning results.

2. A multi-mode tokamak device rupture early warning method according to claim 1, characterized in that: In the step 1, the 0-dimensional diagnostic data includes plasma current Ip, plasma current error Ip_error, plasma density Ne, ring voltage V_loop, and plasma elongation ratio Kappa; the plasma two-dimensional image diagnostic data collected by the camera includes the tokamak position, and the tokamak position includes any one of an image of the entire plasma area observed along the plasma tangent and an image of a partial plasma area, wherein the band to which the collected plasma two-dimensional image belongs is any one of the visible light band, infrared band, and ultraviolet band; the labeling of the rupture data in the collected multimodal data includes labeling by a method combining automatic judgment of the current change rate and expert experience labeling, and marking the time point of the rupture in the collected multimodal data.

3. A multi-mode tokamak device rupture early warning method according to claim 2, characterized in that: In the step 2, aligning the collected multimodal data on the time axis includes downsampling the high sampling rate data to match the low sampling rate data.

4. A multi-mode tokamak device rupture early warning method according to claim 3, characterized in that: In step 3, the structure of the rupture warning model is: using a convolutional neural network CNN and a long short-term memory network LSTM to process 0-dimensional diagnostic data to obtain a first hidden vector; using a Video Vision Transformer model to process plasma two-dimensional image diagnostic data to obtain a second hidden vector; after splicing the first hidden vector and the second hidden vector, classifying them through a multi-layer perceptron MLP to obtain a rupture warning result.

5. A multi-mode tokamak device rupture early warning method according to claim 4, characterized in that: In step 4, 0-dimensional diagnostic data is obtained in real time by reading the acquisition system data through the reflective memory card, and 2D image diagnostic data is obtained in real time through the image acquisition card; the result of the rupture warning is transmitted to the plasma control system in real time through the reflective memory network.

6. A multi-mode tokamak device rupture warning system, characterized in that: The system comprises: Data acquisition module: used to collect multimodal data, including 0-dimensional diagnostic data collected and calculated using real-time diagnostics in the tokamak device, and plasma 2D image diagnostic data collected using a camera; annotate the fracture data in the collected multimodal data; Data preparation module: used to align the time axis of the collected multimodal data and divide them into time slices. Each time slice contains 0-dimensional diagnostic data, 2D image diagnostic data, and annotated rupture data information. Rupture warning module: It is used to input the multi-modal data with time axis alignment into the optimal rupture warning model during the tokamak experiment, and perform rupture mitigation and device protection according to the output rupture warning results.

Images