Intelligent control method for achieving high-confinement mode operation of magnetically confined nuclear fusion plasma

Abstract

This invention discloses an intelligent control method for achieving high-confinement mode operation of magnetically confined nuclear fusion plasma. The method includes: acquiring historical experimental datasets of the magnetically confined nuclear fusion device and constructing a calculation model for the second-stage heating power threshold; acquiring input data in real-time from the diagnostic system of the magnetically confined nuclear fusion device, calculating the second-stage heating power threshold based on the calculation model, and feeding it back to the auxiliary heating system; analyzing the dependency relationship between the second-stage heating power threshold and various plasma state parameters, obtaining a control scheme to reduce the second-stage heating power threshold and providing it to the plasma control system for adjustment, before entering the next control cycle. This invention can dynamically estimate the required second-stage heating power based on the real-time state of the plasma and the device, thus making the estimation of the second-stage heating power threshold more accurate; and adjusting the plasma in real-time to reduce the required second-stage heating power, achieving the transition to high-confinement mode at a lower engineering cost.

Description

Technical Field

[0001] This invention relates to the field of operation control technology for magnetic confinement nuclear fusion devices, specifically to an intelligent control method for realizing high-confinement mode operation of magnetic confinement nuclear fusion plasma. Background Technology

[0002] High confinement mode (H mode) is an advanced operating mode in magnetic confinement nuclear fusion devices represented by tokamak. Its main feature is the formation of a steep pressure gradient at the plasma edge, which significantly improves the core plasma parameters and supports the achievement of higher fusion reaction efficiency.

[0003] The most common method for obtaining high-constraint modes in experiments is to inject sufficiently high secondary heating power to drive the conversion of low-constraint modes to high-constraint modes (Plasma Physics and Controlled Fusion. 65(1): 014001). Several scaling law formulas for the power threshold required to achieve high-constraint modes have been proposed internationally (Journal of Physics: Conference series 123(2008): 012033, Nuclear Fusion 54(2014): 083003). As long as the secondary heating power is injected significantly greater than the scaling law threshold, the expected confinement mode conversion can be achieved. However, this approach has several problems:

[0004] 1. The calibration law only takes the device operating parameters and plasma macroscopic parameters as inputs, and the estimated conversion power threshold has a large uncertainty. Depending on the differences in impurity ion levels in the plasma and heating and feeding methods during device operation, the actual required power may deviate significantly from the calibration law, resulting in a high degree of uncertainty in the control scheme design.

[0005] 2. Simply relying on increasing the secondary heating power to achieve H-mode is subject to significant limitations due to factors such as engineering feasibility and construction capital investment, and may not be feasible in practice.

[0006] 3. The power threshold required to acquire and maintain the H mode will fluctuate with changes in plasma state. If the heating power is designed based solely on the scaling law, the power may be insufficient to maintain the H mode for some time during the experiment, resulting in unexpected mode degradation and affecting the stability of plasma control.

[0007] In view of the above, this application is hereby submitted. Summary of the Invention

[0008] The purpose of this invention is to provide an intelligent control method for achieving high-confinement mode operation in magnetically confined nuclear fusion plasma. Based on calibration using the macroscopic parameters of the magnetically confined nuclear fusion device and the plasma, this invention considers more detailed real-time plasma state information and employs an artificial intelligence algorithm for dynamic estimation of the high-confinement mode transition threshold. Furthermore, the diagnostic system, secondary heating system (i.e., auxiliary heating system), and plasma control system of the magnetically confined nuclear fusion device are connected in series with this algorithm to form an intelligent control method for achieving high-confinement mode operation in the magnetically confined fusion device. This method reduces the secondary heating power required for high-confinement mode by adjusting the plasma state and provides a more accurate power threshold estimate than traditional calibration laws, allowing for the appropriate application of secondary heating power. This results in stable and controllable high-confinement mode operation with lower engineering costs.

[0009] This invention is achieved through the following technical solution:

[0010] In a first aspect, the present invention provides an intelligent control method for realizing high-confinement mode operation of magnetically confined nuclear fusion plasma, the method comprising:

[0011] Obtain historical test datasets of magnetic confinement nuclear fusion devices, and construct a secondary heating power threshold calculation model based on the historical test datasets;

[0012] Input data is acquired in real time from the diagnostic system of the magnetic confinement nuclear fusion device, and the secondary heating power threshold required to achieve the high confinement mode is calculated based on the secondary heating power threshold calculation model. The secondary heating power threshold is then fed back to the auxiliary heating system.

[0013] The dependence between the secondary heating power threshold and various plasma state parameters is analyzed to obtain a control scheme for reducing the secondary heating power threshold. The control scheme is then provided to the plasma control system for adjustment, and the next control cycle begins.

[0014] This invention first constructs a second-stage heating power threshold calculation model based on historical experimental datasets of magnetic confinement fusion devices. Second, the model obtains real-time input data from the diagnostic system of the magnetic confinement fusion device to calculate the second-stage heating power threshold required to achieve high confinement mode, guiding the second-stage heating system to input power. Then, parameter dependency analysis is performed on the second-stage heating power threshold calculation model to obtain the maximum influencing factors of the power threshold, thereby providing adjustment variables and adjustment directions to reduce the power threshold, which are then controlled by the plasma control system.

[0015] Furthermore, historical test datasets of the magnetic confinement fusion device are obtained, and a secondary heating power threshold calculation model is constructed based on the historical test datasets, including:

[0016] Obtain historical experimental datasets for magnetic confinement fusion devices;

[0017] From the historical experimental dataset, input data X is obtained by acquiring magnetic confinement nuclear fusion device and plasma state data; secondary heating total power data P is collected, and analysis is performed to determine whether the plasma can achieve high confinement mode conversion. Data that has undergone high confinement mode conversion is labeled Y=0, and data that has not undergone high confinement mode conversion is labeled Y=1.

[0018] Based on recurrent neural networks and self-attention neural networks, the relationship between input data X, total secondary heating power data P, and first output label Y in the historical experimental data is fitted to obtain a function F that satisfies the relationship Y = F(X, P), which is denoted as the intermediate model;

[0019] The intermediate model is inversely solved to eliminate the first output label Y and obtain the function G that satisfies the relationship P = G(X), which is the secondary heating power threshold calculation model.

[0020] Furthermore, the intermediate model is inversely solved to eliminate the first output label Y and obtain a function G that satisfies the relationship P = G(X), i.e., the secondary heating power threshold calculation model, including:

[0021] For each input data X, scan P and obtain the turning point where Y changes from 0 to 1, to obtain the secondary heating power threshold corresponding to the magnetic confinement nuclear fusion device and the plasma state;

[0022] Based on recurrent neural networks and self-attention neural networks, the relationship between input data X and second output label P in the historical experimental data is fitted to obtain a function G that satisfies the relationship P = G(X), which is the secondary heating power threshold calculation model.

[0023] Furthermore, the input data is data generated by the magnetic confinement nuclear fusion device and plasma state parameters.

[0024] Furthermore, feeding back the secondary heating power threshold to the auxiliary heating system includes:

[0025] Set a heating margin k, and input heating power to the auxiliary heating system according to the value of P×(1+k), where P is the secondary heating power threshold;

[0026] The setting of the heating margin k includes: when it is necessary to stably achieve a high-constraint mode, k = 1; when it is necessary to save heating power, k = 0.2.

[0027] Furthermore, the control scheme for reducing the secondary heating power threshold includes the adjustment variable and adjustment direction for reducing the secondary heating power threshold.

[0028] Furthermore, the dependence between the secondary heating power threshold and various plasma state parameters is analyzed to obtain a control scheme for reducing the secondary heating power threshold. This control scheme is then provided to the plasma control system for adjustment, including:

[0029] From the list of data contained in the input data X, select the variables that the plasma control system can adjust to form a variable list {x1,x2,…,xn};

[0030] Take the partial derivative for each variable xi in the variable list {x1,x2,…,xn}. To estimate its impact on the required secondary heating power, the variable with the greatest impact on the secondary heating power is obtained; where G is the calculation model for the secondary heating power threshold;

[0031] The variable that has the greatest impact on the secondary heating power is sent to the plasma control system, which then adjusts the direction of the variable xi. If the partial derivative... Then decrease the variable xi; if the partial derivative Then increase the variable xi; thereby achieving the effect of reducing the secondary heating power threshold Y.

[0032] Furthermore, the method also includes:

[0033] After entering the next control cycle, the updated secondary heating power threshold is calculated and fed back to the auxiliary heating system to adjust the plasma in real time, reduce the required secondary heating power, and achieve the conversion to the high-confinement mode at a lower engineering cost.

[0034] Secondly, this invention provides an intelligent control system for realizing high-confinement mode operation of magnetically confined nuclear fusion plasma, the system comprising:

[0035] The acquisition unit is used to acquire historical experimental datasets of magnetic confinement fusion devices.

[0036] The model building unit is used to build a secondary heating power threshold calculation model based on the historical test dataset.

[0037] The computing unit is used to acquire input data in real time from the diagnostic system of the magnetic confinement nuclear fusion device, perform calculations based on the secondary heating power threshold calculation model, obtain the secondary heating power threshold required to achieve the high confinement mode, and feed the secondary heating power threshold back to the auxiliary heating system.

[0038] The analysis unit is used to analyze the dependence between the secondary heating power threshold and various plasma state parameters, and to obtain a control scheme to reduce the secondary heating power threshold.

[0039] The control adjustment unit is used to provide the control scheme to the plasma control system for adjustment and to enter the next control cycle.

[0040] Furthermore, the control scheme for reducing the secondary heating power threshold includes the adjustment variable and adjustment direction for reducing the secondary heating power threshold.

[0041] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0042] This invention provides an intelligent control method for high-confinement mode operation in magnetically confined nuclear fusion plasma. Compared with existing methods that analyze the secondary heating power required for confinement mode transition using scaling laws and then apply power significantly higher than the threshold to achieve high-confinement mode operation:

[0043] 1. This invention can dynamically estimate the required secondary heating power based on the real-time status of the plasma and the device, thereby making the estimation of the secondary heating power threshold more accurate;

[0044] 2. This invention can provide a control scheme for reducing the power threshold of the control system, thereby adjusting the plasma in real time, reducing the required secondary heating power, and achieving the conversion to a high-confinement mode at a lower engineering cost;

[0045] 3. The present invention can configure the injection power of the heating system according to the implemented secondary heating power threshold, so as to more stably realize and maintain the high confinement mode and avoid unexpected confinement mode degradation in plasma. Attached Figure Description

[0046] The accompanying drawings, which are included to provide a further understanding of embodiments of the invention and form part of this application, do not constitute a limitation thereof. In the drawings:

[0047] Figure 1 This is a schematic diagram of the overall technical solution of the present invention;

[0048] Figure 2 This is a flowchart illustrating the intelligent control method for realizing high-confinement mode operation of magnetically confined nuclear fusion plasma according to the present invention.

[0049] Figure 3 This is a schematic diagram of the discharge situation in Embodiment 1 of the present invention;

[0050] Figure 4 This is a schematic diagram illustrating how the new P=G(X) function is used to estimate the secondary heating power threshold in real time in Embodiment 1 of the present invention;

[0051] Figure 5 This is a block diagram of the intelligent control system for realizing the high-confinement mode operation of magnetically confined nuclear fusion plasma according to the present invention. Detailed Implementation

[0052] To make the objectives, technical solutions, and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the embodiments and accompanying drawings. The illustrative embodiments and descriptions of the present invention are only used to explain the present invention and are not intended to limit the present invention.

[0053] The existing method of analyzing the secondary heating power required for constraint mode conversion using scaling laws and then applying power significantly higher than the threshold to achieve high constraint modes has the following problems:

[0054] 1. The calibration law only takes the device operating parameters and plasma macroscopic parameters as inputs, and the estimated conversion power threshold has a large uncertainty. Depending on the differences in impurity ion levels in the plasma and heating and feeding methods during device operation, the actual required power may deviate significantly from the calibration law, resulting in a high degree of uncertainty in the control scheme design.

[0055] 2. Simply relying on increasing the secondary heating power to achieve H-mode is subject to significant limitations due to factors such as engineering feasibility and construction capital investment, and may not be feasible in practice.

[0056] 3. The power threshold required to acquire and maintain the H-mode will fluctuate with changes in plasma state. If the heating power is designed based solely on the scaling law, the power may be insufficient to maintain the H-mode for some time during the experiment, resulting in unexpected mode degradation and affecting the stability of plasma control.

[0057] To address the above issues, this invention, building upon the calibration of the magnetic confinement fusion device and its macroscopic plasma parameters, considers more detailed real-time plasma state information to dynamically estimate the high-confinement mode conversion power threshold, which serves as the basis for the activation of the secondary heating system. This invention provides an effective method for achieving this goal.

[0058] The key points of this invention, that is, the new technical means employed, are summarized as follows:

[0059] (1) Real-time plasma state data was used, combined with artificial intelligence models with time series analysis capabilities such as recurrent neural networks and self-attention neural networks, to perform dynamic calculation of the secondary heating power threshold.

[0060] (2) Based on the secondary heating power threshold model P=G(X), the partial derivatives are calculated. We analyzed the variables that have the greatest impact on the secondary heating power threshold and implemented real-time control to reduce the power threshold.

[0061] (3) Configure the auxiliary heating system power input based on the dynamic secondary heating power threshold estimated by Y=F(X).

[0062] Specifically, such as Figure 1 As shown, Figure 1 The diagram illustrates the overall technical solution of this invention. First, this invention constructs a second-stage heating power threshold calculation model based on historical experimental datasets from a magnetically confined nuclear fusion device. Second, this model obtains real-time input data from the diagnostic system of the magnetically confined nuclear fusion device to calculate the second-stage heating power threshold required to achieve a high-confinement mode, guiding the second-stage heating system to input power. Then, parameter dependency analysis is performed on the second-stage heating power threshold calculation model to identify the factors with the greatest influence on the power threshold, thereby providing adjustment variables and directions for reducing the power threshold, which are then controlled by the plasma control system.

[0063] Example 1

[0064] like Figure 2 As shown, this invention provides an intelligent control method for high-confinement mode operation of magnetically confined nuclear fusion plasma. The method includes:

[0065] Step 1: Obtain historical test datasets of the magnetic confinement nuclear fusion device, and construct a secondary heating power threshold calculation model based on the historical test datasets;

[0066] In this embodiment, step 1 specifically includes:

[0067] Step 11: Obtain historical test datasets for the magnetic confinement fusion device;

[0068] Step 12: Obtain input data X from the historical experimental dataset, which consists of magnetic confinement fusion device and plasma state data; input data X is the data formed by magnetic confinement fusion device and plasma state parameters.

[0069] Collect the total power data P of the secondary heating, analyze whether the plasma can achieve high-confinement mode conversion, assign the label Y=0 to the data that has achieved high-confinement mode conversion, and assign the label Y=1 to the data that has not achieved high-confinement mode conversion.

[0070] The sources of input data X include, but are not limited to, those listed in Table 1 below:

[0071] Table 1

[0072] Input physical quantity Measurement methods Circular magnetic field of the device Electromagnetic measurement plasma current Electromagnetic measurement Plasma density Optical polarization measurement Large radius plasma Electromagnetic measurement + data analysis plasma small radius Electromagnetic measurement + data analysis Plasma elongation ratio Electromagnetic measurement + data analysis plasma three angles Electromagnetic measurement + data analysis Plasma boundary safety factor Electromagnetic measurement + data analysis Plasma X-point position Electromagnetic measurement + data analysis plasma temperature Spectroscopic or microwave measurement plasma rotation speed Microwave measurement Effective atomic number of plasma Spectroscopic measurement + data analysis Plasma recirculation level Measuring the intensity of the deuterium α spectral line to indirectly estimate

[0073] Step 13: Based on recurrent neural networks and self-attention neural networks, fit the relationship between the input data X, the total secondary heating power data P, and the first output label Y in the historical experimental data to obtain a function F that satisfies the relationship Y = F(X, P), which is denoted as the intermediate model;

[0074] Step 14 involves inversely solving the intermediate model, eliminating the first output label Y, and obtaining a function G that satisfies the relationship P = G(X), i.e., the secondary heating power threshold calculation model. Step 14 specifically includes:

[0075] A. For each input data X, scan P and obtain the turning point where Y changes from 0 to 1, and obtain the secondary heating power threshold corresponding to the magnetic confinement nuclear fusion device and the plasma state.

[0076] B. Based on recurrent neural networks and self-attention neural networks, the relationship between the input data X and the second output label P in the historical test dataset is fitted to obtain a function G that satisfies the relationship P = G(X), which is the secondary heating power threshold calculation model.

[0077] Step 2: Real-time acquisition of input data X from the diagnostic system of the magnetic confinement nuclear fusion device; calculation based on the secondary heating power threshold calculation model P=G(X) to obtain the secondary heating power threshold required to achieve high confinement mode; and feeding back the secondary heating power threshold to the auxiliary heating system.

[0078] In this embodiment, the secondary heating power threshold P is fed back to the auxiliary heating system, and a certain heating margin k is set. The heating power is input to the auxiliary heating system according to the value of P×(1+k). When it is desired to stably achieve a high constraint mode, k should be set to a larger value, for example, 1. When it is desired to save heating power, the value of k can be appropriately reduced, for example, 0.2.

[0079] Step 3: Analyze the dependence between the secondary heating power threshold and each plasma state parameter, obtain a control scheme to reduce the secondary heating power threshold, and provide the control scheme to the plasma control system for adjustment, and then enter the next control cycle.

[0080] In this embodiment, the control scheme for reducing the secondary heating power threshold includes an adjustment variable and an adjustment direction for reducing the secondary heating power threshold.

[0081] In this embodiment, step 3 specifically includes:

[0082] (1) From the data list contained in the input data X, select the variables that the plasma control system can adjust to form a variable list {x1,x2,…,xn};

[0083] (2) Take the partial derivative for each variable xi in the variable list {x1,x2,…,xn}. To estimate its impact on the required secondary heating power, the variable with the greatest impact on the secondary heating power is obtained; where G is the calculation model for the secondary heating power threshold;

[0084] (3) The variable that has the greatest impact on the secondary heating power is sent to the plasma control system, which then adjusts the direction of the variable xi. If the partial derivative... Then decrease the variable xi; if the partial derivative Then increase the variable xi; thereby achieving the effect of reducing the secondary heating power threshold Y.

[0085] Step 4: After entering the next control cycle, the updated secondary heating power threshold is calculated and fed back to the auxiliary heating system to adjust the plasma in real time, reduce the required secondary heating power, and achieve the conversion to high-confinement mode at a lower engineering cost.

[0086] In specific implementation, this invention takes the high-constraint mode control of the China Circulator No. 2A (HL-2A) device as an example, and the specific steps are as follows:

[0087] (1) Collect 275 discharges with H mode and 30 discharges without H mode of HL-2A to form a historical test database, and collect input diagnostic data X and secondary heating power P.

[0088] (2) Manually determine the H-mode conversion time point for each experimental shot, and assign a label Y to the data before and after the conversion point based on the conversion time point, so as to... Figure 3 Taking the discharge scenario shown as an example, the H-mode conversion occurs at approximately 670ms and lasts until approximately 820ms. The typical time delay of the H-mode conversion for the HL-2A device is 10–80ms. Therefore, the data before 590ms and after 820ms will be marked as Y=0, and the data between 590ms and 820ms will be marked as Y=1.

[0089] (3) Use a temporal convolutional neural network (a type of recurrent neural network) to fit the function Y = F(X, P), and then for each X in the dataset, scan the threshold P that changes Y from 0 to 1, and then use the scan results to fit a new function P = G(X). Figure 4 A schematic diagram is given showing the real-time estimation of the secondary heating power threshold using this function. In this step, the accuracy of the Y=F(X,P) function can reach 93%, thus ensuring the reliability of the P=G(X) function obtained by scanning. Figure 4 As shown, if the P=G(X) curve is plotted alongside the actual injected power curve, it can be seen that in the early stage of discharge, the actual injected power is lower than the power required by the H mode. Therefore, after the second-stage heating begins, the plasma does not immediately switch to the H mode. Subsequent changes in the plasma state cause the required power to decrease, falling below the actual injected power, thus causing a mode switch to occur around 670 ms. After maintaining this state for a period of time, changes in the plasma state again cause the power required by the H mode to increase, leading to the plasma exiting the H mode.

[0090] (4) Using the automatic differential operator built into the deep learning framework, the controllable parameters on the HL-2A, such as the large radius, small radius, density, and current of the plasma, are calculated. The variable with the greatest impact is identified and then adjusted by the device's control system.

[0091] (5) Based on the real-time calculated secondary heating power threshold P, the secondary heating is applied with a power of 1.5×P to obtain a stable high-confinement mode plasma.

[0092] Example 2

[0093] like Figure 5 As shown, the difference between this embodiment and Embodiment 1 is that this embodiment provides an intelligent control system for realizing the operation of the high confinement mode of magnetically confined nuclear fusion plasma. This system corresponds one-to-one with the intelligent control method for realizing the operation of the high confinement mode of magnetically confined nuclear fusion plasma in Embodiment 1. The system includes:

[0094] The acquisition unit is used to acquire historical experimental datasets of magnetic confinement fusion devices.

[0095] The model building unit is used to build a secondary heating power threshold calculation model based on the historical test dataset.

[0096] The computing unit is used to acquire input data in real time from the diagnostic system of the magnetic confinement nuclear fusion device, perform calculations based on the secondary heating power threshold calculation model, obtain the secondary heating power threshold required to achieve the high confinement mode, and feed the secondary heating power threshold back to the auxiliary heating system.

[0097] An analysis unit is used to analyze the dependence between the secondary heating power threshold and various plasma state parameters, and to obtain a control scheme for reducing the secondary heating power threshold; wherein, the control scheme for reducing the secondary heating power threshold includes the adjustment variable and adjustment direction for reducing the secondary heating power threshold;

[0098] The control adjustment unit is used to provide the control scheme to the plasma control system for adjustment and to enter the next control cycle.

[0099] The execution process of each unit can be carried out according to the intelligent control method flow steps for realizing the high confinement mode operation of magnetic confinement nuclear fusion plasma in Example 1, and will not be described in detail in this example.

[0100] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0101] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0102] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0103] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0104] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. An intelligent control method for realizing high-confinement mode operation of magnetically confined nuclear fusion plasma, characterized in that, The method includes: Historical test datasets of magnetic confinement nuclear fusion devices are obtained, and a secondary heating power threshold calculation model is constructed based on the historical test datasets; the secondary heating power threshold calculation model is based on recurrent neural networks and self-attention neural networks; Input data is acquired in real time from the diagnostic system of the magnetic confinement nuclear fusion device, and the secondary heating power threshold is calculated based on the secondary heating power threshold calculation model to obtain the secondary heating power threshold. The secondary heating power threshold is then fed back to the auxiliary heating system. The dependence between the secondary heating power threshold and various plasma state parameters is analyzed to obtain a control scheme for reducing the secondary heating power threshold. The control scheme is then provided to the plasma control system for adjustment, and the next control cycle begins.

2. The intelligent control method for realizing high-confinement mode operation of magnetically confined nuclear fusion plasma according to claim 1, characterized in that, Obtain historical test datasets for magnetic confinement fusion devices, and construct a secondary heating power threshold calculation model based on these datasets, including: Obtain historical experimental datasets for magnetic confinement fusion devices; From the historical experimental dataset, input data X is obtained by acquiring magnetic confinement nuclear fusion device and plasma state data; secondary heating total power data P is collected, and analysis is performed to determine whether the plasma can achieve high confinement mode conversion. Data that has undergone high confinement mode conversion is labeled Y=0, and data that has not undergone high confinement mode conversion is labeled Y=1. Based on recurrent neural networks and self-attention neural networks, the relationship between input data X, total secondary heating power data P, and first output label Y in the historical experimental data is fitted to obtain a function F that satisfies the relationship Y = F(X, P), which is denoted as the intermediate model; The intermediate model is inversely solved to eliminate the first output label Y and obtain the function G that satisfies the relationship P = G(X), which is the secondary heating power threshold calculation model.

3. The intelligent control method for realizing high-confinement mode operation of magnetically confined nuclear fusion plasma according to claim 2, characterized in that, The intermediate model is inversely solved by eliminating the first output label Y and obtaining a function G that satisfies the relationship P = G(X), which is the secondary heating power threshold calculation model, including: For each input data X, scan P and obtain the turning point where Y changes from 0 to 1, to obtain the secondary heating power threshold corresponding to the magnetic confinement nuclear fusion device and the plasma state; Based on recurrent neural networks and self-attention neural networks, the relationship between the input data X and the second output label P in the historical test dataset is fitted to obtain a function G that satisfies the relationship P = G(X), which is the secondary heating power threshold calculation model.

4. The intelligent control method for realizing high-confinement mode operation of magnetically confined nuclear fusion plasma according to claim 1, characterized in that, The input data is data generated from the magnetic confinement nuclear fusion device and plasma state parameters.

5. The intelligent control method for realizing high-confinement mode operation of magnetically confined nuclear fusion plasma according to claim 1, characterized in that, Feeding the secondary heating power threshold back to the auxiliary heating system includes: Set a heating margin k, and input heating power to the auxiliary heating system according to the value of P×(1+k), where P is the secondary heating power threshold; The setting of the heating margin k includes: when it is necessary to stably achieve a high-constraint mode, k = 1; when it is necessary to save heating power, k = 0.

2.

6. The intelligent control method for realizing high-confinement mode operation of magnetically confined nuclear fusion plasma according to claim 1, characterized in that, The control scheme for reducing the secondary heating power threshold includes the adjustment variable and adjustment direction for reducing the secondary heating power threshold.

7. The intelligent control method for realizing high-confinement mode operation of magnetically confined nuclear fusion plasma according to claim 6, characterized in that, Analyzing the dependency relationship between the secondary heating power threshold and various plasma state parameters, a control scheme for reducing the secondary heating power threshold is obtained, and the control scheme is provided to the plasma control system for adjustment, including: From the list of data contained in the input data X, select the variables that the plasma control system can adjust to form a variable list {x1,x2,…,xn}; Take the partial derivative for each variable xi in the variable list {x1,x2,…,xn}. To estimate its impact on the required secondary heating power, the variable with the greatest impact on the secondary heating power is obtained; where G is the calculation model for the secondary heating power threshold; The variable that has the greatest impact on the secondary heating power is sent to the plasma control system, which then adjusts the direction of the variable xi. If the partial derivative... Then decrease the variable xi; if the partial derivative Then increase the variable xi.

8. The intelligent control method for realizing high-confinement mode operation of magnetically confined nuclear fusion plasma according to claim 1, characterized in that, The method also includes: After entering the next control cycle, the updated secondary heating power threshold is calculated and fed back to the auxiliary heating system to adjust the plasma in real time and reduce the required secondary heating power.

9. An intelligent control system for realizing high-confinement mode operation of magnetically confined nuclear fusion plasma, characterized in that, The system includes: The acquisition unit is used to acquire historical experimental datasets of magnetic confinement fusion devices. The model building unit is used to build a secondary heating power threshold calculation model based on the historical test dataset; the secondary heating power threshold calculation model is based on a recurrent neural network and a self-attention neural network. The computing unit is used to acquire input data in real time from the diagnostic system of the magnetic confinement nuclear fusion device, perform calculations based on the secondary heating power threshold calculation model, obtain the secondary heating power threshold, and feed the secondary heating power threshold back to the auxiliary heating system. The analysis unit is used to analyze the dependence between the secondary heating power threshold and various plasma state parameters, and to obtain a control scheme to reduce the secondary heating power threshold. The control adjustment unit is used to provide the control scheme to the plasma control system for adjustment and to enter the next control cycle.

10. The intelligent control system for realizing high-confinement mode operation of magnetically confined nuclear fusion plasma according to claim 9, characterized in that, The control scheme for reducing the secondary heating power threshold includes the adjustment variable and adjustment direction for reducing the secondary heating power threshold.

Images