Beam spot position correction method and device, equipment and storage medium

Abstract

The invention discloses a beam spot position correction method and device, equipment and a storage medium, and relates to the technical field of accelerators, a pre-trained prediction network model is used for replacing manual operation to carry out the correction process of the beam spot position, the tiny offset of a beam spot can be accurately read, and the correction accuracy of the beam spot position is improved. The beam spot position can be automatically calibrated without manual participation, and the beam adjusting efficiency is greatly improved. The method comprises the following steps: acquiring magnetic field constraint data for beam spot position correction, wherein the magnetic field constraint data comprises a beam spot center position coordinate, beam energy data and a distance between a correction magnet and a fluorescent target; inputting the magnetic field constraint data into a pre-trained prediction network model so as to predict the magnetic field intensity of the correction magnet in different directions through the prediction network model according to the magnetic field constraint data; and correcting the position of the beam spot according to the magnetic field intensity of the correction magnet in different directions.

Description

Technical Field

[0001] This application relates to the technical field of accelerators, and in particular, to a method, device, equipment, and storage medium for correcting the position of a beam spot. Background Art

[0002] With the continuous development of accelerator technology, accelerators can accelerate charged particles to higher energies and stronger beam intensities, while improving the beam quality and stability. To ensure the beam transmission efficiency, reduce beam loss and scattering, and keep the beam always at the central position of the vacuum orbit is an important task in accelerator beam tuning.

[0003] When the beam travels along the vacuum orbit, the beam spot position can be used to reflect the actual position of the beam in the vacuum orbit. That is to say, by correcting the beam spot position, the beam can be kept near the center point of the orbit. In related technologies, if the beam spot deviates from the center of the vacuum orbit, it means that the beam also deviates from the center, and the beam spot position needs to be corrected. At this time, the beam tuning personnel can correct the position of the beam spot by observing the fluorescent target and changing the magnetic field of the correction iron, so that the beam spot returns to the center position of the vacuum orbit, thereby keeping the beam at the center of the vacuum orbit. However, the correction process of the beam spot position needs to be completed by manual operation, and it is difficult to accurately judge the small deviation of the beam spot and accurately adjust it. It needs to be tried repeatedly to reach the ideal position, resulting in a low accuracy of beam spot position correction. Summary of the Invention

[0004] In view of this, this application provides a method, device, equipment, and storage medium for correcting the position of a beam spot, mainly aiming to solve the problem that in the prior art, it is difficult to accurately judge the small deviation of the beam spot and accurately adjust it by manual operation to correct the beam spot position, and it needs to be tried repeatedly to reach the ideal position, resulting in a low accuracy of beam spot position correction.

[0005] According to the first aspect of this application, a method for correcting the position of a beam spot is provided, including: Obtain the magnetic field constraint data for beam spot position correction, where the magnetic field constraint data includes the beam spot center position coordinates, beam energy data, and the distance between the correction magnet and the fluorescent target; Input the magnetic field constraint data into a pre-trained prediction network model to predict the magnetic field intensities of the correction magnet in different directions by the prediction network model according to the magnetic field constraint data; Correct the beam spot position according to the magnetic field intensities of the correction magnet in different directions.

[0006] Further, before inputting the magnetic field constraint data into a pre-trained prediction network model to predict the magnetic field strengths of the correction magnets in different directions according to the magnetic field constraint data by the prediction network model, the method further includes: Obtaining training data for beam spot position correction, where the training data includes input data for magnetic field strength constraint and output data for magnetic field strength prediction; Training the prediction network model according to the training data, and updating the mapping relationship between the input data and the output data during the training process, where the mapping relationship is used to predict the magnetic field strength of the output data based on the input data as the magnetic field constraint; When the training satisfies the iteration stop condition, generating a prediction network model according to the updated mapping relationship.

[0007] Further, the obtaining of the training data for beam spot position correction includes: Pre-establishing a simulation system for particle acceleration simulation to simulate the variable data for beam spot position correction and the particle distribution at the fluorescent target through the simulation system; Changing the variable data during the simulation process to correspondingly obtain the changed particle distribution at the fluorescent target, and obtaining the beam spot position distribution accompanied by the change of the variable data; Constructing the training data for beam spot position correction according to the beam spot position distribution accompanied by the change of the variable data.

[0008] Further, the variable data includes the magnetic field strengths of the correction magnets in different directions, beam current energy data, and the distance between the correction magnet and the fluorescent target. The changing of the variable data during the simulation process to correspondingly obtain the changed particle distribution at the fluorescent target and obtain the training data for beam spot position correction includes: Changing the magnetic field strengths of the correction magnets in different directions during the simulation process to correspondingly obtain the changed particle distribution at the fluorescent target and obtain the first training data for beam spot position correction; and / or Changing the beam current energy data during the simulation process to correspondingly obtain the changed particle distribution at the fluorescent target and obtain the second training data for beam spot position correction; and / or Changing the distance between the correction magnet and the fluorescent target during the simulation process to correspondingly obtain the changed particle distribution at the fluorescent target and obtain the third training data for beam spot position correction.

[0009] Further, the constructing of the training data for beam spot position correction according to the beam spot position distribution accompanied by the change of the variable data includes: Determine multiple groups of associated simulation data according to the beam spot position distribution changed by the accompanying variable data, where the simulation data includes the magnetic field strength of the correction magnet in different directions, beam current energy data, the distance between the correction magnet and the fluorescent target, and the beam spot center position coordinates; Select the beam current energy data, the distance between the correction magnet and the fluorescent target, and the beam spot center position coordinates to construct input data for magnetic field strength constraint; Select the magnetic field strength of the correction magnet in different directions to construct output data for magnetic field strength prediction.

[0010] Further, before training the prediction network model according to the training data and updating the mapping relationship between the input data and the output data during the training process, the method further includes: Set a loss function for measuring the training effect of the prediction network model according to the mean square error function; Correspondingly, calculate the loss value between the predicted output data of the prediction network model and the output data for magnetic field strength prediction according to the loss function during the training process, so as to update the mapping relationship between the input data and the output data through the loss value.

[0011] Further, the correction of the beam spot position according to the magnetic field strength of the correction magnet in different directions includes: According to the magnetic field strength of the correction magnet in different directions, use the opposite value of the magnetic field strength as the position correction parameter; Send the position correction parameter to the correction magnet through a control instruction, so that the correction magnet corrects the beam spot position according to the position correction parameter.

[0012] According to the second aspect of the present application, a beam spot position correction device is provided, including: A first acquisition unit for acquiring magnetic field constraint data for beam spot position correction, where the magnetic field constraint data includes beam spot center position coordinates, beam current energy data, and the distance between the correction magnet and the fluorescent target; A prediction unit for inputting the magnetic field constraint data into a pre-trained prediction network model, so as to predict the magnetic field strength of the correction magnet in different directions by the prediction network model according to the magnetic field constraint data; A correction unit for correcting the beam spot position according to the magnetic field strength of the correction magnet in different directions.

[0013] Further, the device further includes: A second acquisition unit, configured to acquire training data for beam spot position correction before inputting the magnetic field constraint data into a pre-trained prediction network model to predict the magnetic field intensities of correction magnets in different directions through the prediction network model based on the magnetic field constraint data, where the training data includes input data for magnetic field intensity constraint and output data for magnetic field intensity prediction; A training unit, configured to train the prediction network model according to the training data, and update the mapping relationship between the input data and the output data during the training process, where the mapping relationship is used to predict the magnetic field intensity of the output data based on the input data as the magnetic field constraint; A generation unit, configured to generate a prediction network model according to the updated mapping relationship when the training meets the iteration stop condition.

[0014] Further, the second acquisition unit includes: A construction module, configured to pre-construct a simulation system for particle acceleration simulation to simulate the variable data for beam spot position correction and the particle distribution at the fluorescent target through the simulation system; An acquisition module, configured to change the variable data during the simulation process to correspondingly acquire the changed particle distribution at the fluorescent target, and obtain the beam spot position distribution accompanied by the change of the variable data; A construction module, configured to construct training data for beam spot position correction according to the beam spot position distribution accompanied by the change of the variable data.

[0015] Further, the variable data includes the magnetic field intensities of correction magnets in different directions, beam current energy data, and the distance between the correction magnet and the fluorescent target. The acquisition module is specifically configured to: Change the magnetic field intensities of correction magnets in different directions during the simulation process to correspondingly acquire the changed particle distribution at the fluorescent target, and obtain the first training data for beam spot position correction; and / or Change the beam current energy data during the simulation process to correspondingly acquire the changed particle distribution at the fluorescent target, and obtain the second training data for beam spot position correction; and / or Change the distance between the correction magnet and the fluorescent target during the simulation process to correspondingly acquire the changed particle distribution at the fluorescent target, and obtain the third training data for beam spot position correction.

[0016] Further, the construction module is specifically configured to: Determine multiple groups of associated simulation data according to the beam spot position distribution accompanied by the change of the variable data, where the simulation data includes the magnetic field intensities of correction magnets in different directions, beam current energy data, the distance between the correction magnet and the fluorescent target, and the beam spot center position coordinates; Select the beam energy data, correct the distance between the magnet and the fluorescent target, and the coordinates of the beam spot center position, and construct the input data for magnetic field strength constraint; Select the magnetic field strengths of the correction magnet in different directions, and construct the output data for magnetic field strength prediction.

[0017] Further, the training unit is further configured to, before training the prediction network model according to the training data and updating the mapping relationship between the input data and the output data during training, set a loss function for measuring the training effect of the prediction network model according to the mean square error function; Correspondingly, during training, calculate the loss value between the predicted output data of the prediction network model and the output data for magnetic field strength prediction according to the loss function, so as to update the mapping relationship between the input data and the output data through the loss value.

[0018] Further, the correction unit is specifically configured to: According to the magnetic field strengths of the correction magnet in different directions, use the opposite value of the magnetic field strength as the position correction parameter; Send the position correction parameter to the correction magnet through a control instruction, so that the correction magnet corrects the beam spot position according to the position correction parameter.

[0019] According to the third aspect of the present application, there is provided a computer device, including a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, the steps of the method described in the first aspect are implemented.

[0020] According to the fourth aspect of the present application, there is provided a readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method described in the first aspect are implemented.

[0021] With the above technical solution, a method, device, equipment and storage medium for correcting the spot position provided by the present application, compared with the prior art that relies on manual operation to achieve the correction process of the spot position, the present application obtains the magnetic field constraint data for correcting the spot position, and the magnetic field constraint data includes the spot center position coordinates, beam energy data, and the distance between the correction magnet and the fluorescent target; inputs the magnetic field constraint data into a pre-trained prediction network model to predict the magnetic field strength of the correction magnet in different directions according to the magnetic field constraint data by the prediction network model; corrects the spot position according to the magnetic field strength of the correction magnet in different directions. The whole process uses a pre-trained prediction network model to replace manual operation for the correction process of the spot position. The prediction network model can accurately read the small offset of the spot according to the beam with different energies and the spot position, and can automatically calibrate the spot position without manual participation, greatly improving the beam adjustment efficiency.

[0022] The above description is only an overview of the technical solution of the present application. In order to be able to understand the technical means of the present application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of the present application more obvious and understandable, the specific embodiments of the present application are hereinafter specifically exemplified. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The schematic embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation of the present application. In the drawings: Figure 1 is a schematic flow chart of the method for correcting the spot position in an embodiment of the present application; Figure 2 is a schematic flow chart of the method for correcting the spot position in another embodiment of the present application; Figure 3 is Figure 2 a schematic flow chart of a specific implementation of step 201 in Figure 4 is a schematic structural diagram of variable data in the simulation system in an embodiment of the present application; Figure 5 is Figure 1 a schematic flow chart of a specific implementation of step 103 in Figure 6 is a schematic structural diagram of the device for correcting the spot position in an embodiment of the present application; Figure 7 is a schematic structural diagram of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0024] The present invention will now be described with reference to several exemplary embodiments. It should be understood that the description of these embodiments is only for enabling those of ordinary skill in the art to better understand and thus implement the present invention, rather than implying any limitation on the scope of the present invention.

[0025] As used herein, the term "comprising" and its variants are to be construed as open-ended terms meaning "including but not limited to". The term "based on" is to be construed as "at least partially based on". The terms "one embodiment" and "an embodiment" are to be construed as "at least one embodiment". The term "another embodiment" is to be construed as "at least one other embodiment".

[0026] In the related art, if the beam spot deviates from the center of the vacuum orbit, it means that the beam current also deviates from the center, and the position of the beam spot needs to be corrected. At this time, the beam tuning personnel can correct the position of the beam spot by observing the fluorescent target and changing the magnetic field of the correction iron, so that the beam spot returns to the center of the vacuum orbit, thereby keeping the beam current at the center of the vacuum orbit. However, the correction process of the beam spot position needs to be completed by manual operation, and it is difficult to accurately judge the small deviation of the beam spot and accurately adjust it. It needs to be tried repeatedly to reach the ideal position, resulting in a low accuracy of the beam spot position correction.

[0027] To solve this problem, the present embodiment provides a method for correcting the position of the beam spot, as Figure 1 shown, this method is applied to the control end of the beam tuning system and includes the following steps: 101. Obtain the magnetic field constraint data for beam spot position correction.

[0028] The beam spot position refers to the position where the beam current forms a light spot on a specific plane or target object in a particle accelerator. Usually, the beam spot position is accurately represented by three-dimensional space coordinates (x, y, z). Among them, the x and y coordinates represent the position of the beam spot on the plane perpendicular to the direction of particle beam movement, and the z coordinate represents the position along the direction of particle beam movement. For example, in a linear accelerator, the z-axis generally coincides with the axis direction of the accelerator, and the particles are accelerated along the z-axis direction, while the position of the beam spot on the xy plane perpendicular to the axis determines the transverse distribution of the particle beam. Here, the beam spot position mainly refers to the position of the particle beam on the xy plane.

[0029] It is understandable that in a particle accelerator, the particle beam needs to be efficiently transmitted among complex pipelines and numerous components. If the beam spot position is inaccurate, it will seriously affect the transmission efficiency. When the beam spot position deviates, the particle beam may deviate from the designed optimal transmission orbit, which will cause the particles to collide with the accelerator pipe wall, resulting in the loss of a large number of particles and a decrease in the beam current intensity. For example, in some large accelerators, even a slight deviation in the beam spot position will cause a large number of particles to hit the pipe wall after long-distance transmission, significantly reducing the number of particles reaching the target position. By correcting the beam spot position, the particle beam can be made to strictly follow the designed central orbit, minimizing the collision of particles with the pipe wall, improving the transmission efficiency of particles, ensuring the beam current intensity and uniformity, and thus providing a stable and high-quality particle beam for subsequent experiments and applications.

[0030] In this embodiment, the magnetic field constraint data includes the beam spot center position coordinates, the beam current energy data, and the distance between the correction magnet and the fluorescent target. Among them, the beam spot center position coordinates refer to the position coordinates at the center of the light spot formed by the particle beam on a specific observation plane of the particle accelerator. Through the beam spot center position coordinates, the actual position of the particles during transmission can be determined to judge whether they deviate from the designed orbit. The beam current energy data describes the energy carried by the particles in the particle beam. In the accelerator, the particles obtain energy through methods such as magnetic field acceleration. The beam current energy data reflects the overall energy state of these particles. Different experiments or applications require particle beams with specific energies. The correction magnet is a device used to generate a magnetic field to change the trajectory of the particle beam, and the fluorescent target is a device used to observe the position and shape of the particle beam. The distance between the correction magnet and the fluorescent target refers to the spatial length from a specific position of the correction magnet to a specific position of the fluorescent target. This distance directly affects the effect of the magnetic field on correcting the beam spot position. By accurately measuring and controlling this distance, the influence of the magnetic field on the particle beam trajectory can be analyzed more accurately, and thus the correction magnet can be precisely adjusted according to the beam spot situation observed on the fluorescent target to achieve effective correction of the beam spot position.

[0031] The execution subject of this embodiment can be a device or equipment for correcting the beam spot position, which can be configured at the control end of the beam tuning system. The beam tuning system can adjust and control the particle beam so that the light spot generated after the particles pass through the accelerator can accurately appear at the center position of the fluorescent target.

[0032] 102. Input the magnetic field constraint data into a pre-trained prediction network model to predict the magnetic field intensities of the correction magnet in different directions by the prediction network model according to the magnetic field constraint data.

[0033] In this embodiment, the pre-trained prediction network model can predict the magnetic field strength acting on the beam according to the magnetic field constraint data. The magnetic field strength includes predicting the magnetic field strength of the correction magnet in different directions, and correspondingly outputs the magnetic field strength of the correction magnet in different directions.

[0034] The above prediction network model can be trained using a neural network. Specifically, during the process of training the neural network, the neural network has multiple layers. The number of neurons in the input layer can be set according to the input magnetic field constraint data, the number of neurons in the output layer can be set according to the output magnetic field strength, and the number of neurons in the middle layer can be customized. For example, the input data includes the x coordinate of the beam spot center position, the y coordinate of the beam spot center position, the beam energy data, and the distance between the correction magnet and the fluorescent target. The output data includes the magnetic field strength of the correction magnet in the x direction and the magnetic field strength of the correction magnet in the y direction. At this time, a four-layer neural network can be set, including 4, 64, 128, 64, and 2 neurons respectively. After model training, the prediction network model can learn the mapping relationship between the input data and the output data to achieve the correction of the beam spot position.

[0035] Correspondingly, in the application stage of the prediction network model, the magnetic field constraint data can be input into the trained prediction network model for magnetic field strength prediction to obtain the magnetic field strength of the correction magnet in different directions.

[0036] 103. Correct the beam spot position according to the magnetic field strength of the correction magnet in different directions.

[0037] It can be understood that there are many reasons for the beam spot to deviate from the center of the fluorescent target. For example, the beam deflects too much or too little in the upstream magnet, etc. Macroscopically, it can be equivalently or abstractly considered that the collimated beam is deflected under the action of the deflection magnet, and the beam spot deviation caused by these reasons can be understood as caused by the equivalent magnetic field strength, that is, the magnetic field strength loaded by the correction magnet in different directions output by the prediction network model.

[0038] Specifically, after the actual position of the beam spot is input into the prediction network model, the magnetic field strength of the correction magnet in different directions output by the prediction network model is the equivalent magnetic field strength Bx, By that causes the beam to deflect. In order to keep the beam at the center position of the vacuum orbit, it is necessary to use the forces -Bx, -By with the same magnitude and opposite directions of the equivalent magnetic field strength for neutralization to adjust the beam spot position so that the beam spot position is located at the center of the fluorescent target.

[0039] The beam spot position correction method provided by the embodiments of the present application, compared with the prior art that relies on manual operation to achieve the beam spot position correction process, obtains the magnetic field constraint data for beam spot position correction through the following steps. The magnetic field constraint data includes the beam spot center position coordinates, beam current energy data, and the distance between the correction magnet and the fluorescent target. The magnetic field constraint data is input into a pre-trained prediction network model to predict the magnetic field strength of the correction magnet in different directions according to the magnetic field constraint data through the prediction network model. The beam spot position is corrected according to the magnetic field strength of the correction magnet in different directions. The entire process replaces manual operation with a pre-trained prediction network model for the beam spot position correction process. The prediction network model can accurately read the minute offset of the beam spot according to the beam current of different energies and the beam spot position, and can automatically calibrate the beam spot position without manual participation, greatly improving the beam tuning efficiency.

[0040] Further, considering the training process of the prediction network model, in the above embodiment, as Figure 2 shown, before step 102, the method further includes the following steps: 201. Obtain the training data for beam spot position correction.

[0041] 202. Train the prediction network model according to the training data, and update the mapping relationship between the input data and the output data during the training process.

[0042] 203. When the training meets the iteration stop condition, generate a prediction network model according to the updated mapping relationship.

[0043] Among them, the training data includes the input data for magnetic field strength constraint and the output data for magnetic field strength prediction. Here, the input data includes the beam current energy data, the distance between the correction magnet and the fluorescent target, and the beam spot center position coordinates, and the output data includes the magnetic field strength of the correction magnet in different directions. The training data can be obtained through a particle acceleration simulation system, can also be obtained through experiments with a magnetic field measurement device, and can also be obtained through electromagnetic theory calculations. There is no limitation on this, and it can be selected according to the actual situation.

[0044] Furthermore, considering the training accuracy of the prediction network model, a loss function for measuring the training effect of the prediction network model can also be set according to the mean square error function; correspondingly, during the training process, the loss value between the predicted output data of the prediction network model and the output data for magnetic field strength prediction is calculated based on the loss function, so as to update the mapping relationship between the input data and the output data through the loss value. Here, the loss function can quantitatively describe the difference degree between the model prediction result and the real result. By calculating the average value of the squares of the differences between the predicted output data and the actual output data as the loss value, this loss value can intuitively understand the accuracy of the prediction network model. Generally, the smaller the value, the closer the prediction result of the prediction network model is to the real result.

[0045] Specifically, as Figure 3 shown, step 201 includes the following steps: 301. Pre-establish a simulation system for particle acceleration simulation to simulate the variable data for beam spot position correction and the particle distribution at the fluorescent target through the simulation system.

[0046] 302. During the simulation process, change the variable data to correspondingly obtain the changed particle distribution at the fluorescent target, and obtain the beam spot position distribution accompanied by the change of the variable data.

[0047] 303. Construct the training data for beam spot position correction according to the beam spot position distribution accompanied by the change of the variable data.

[0048] In this embodiment, the simulation system for particle acceleration simulation is used to simulate the interaction of multiple physical fields such as electromagnetic fields and particle motion. The particle distribution at the correction magnet and the fluorescent target can be simulated according to beam optics and the Monte Carlo method. Specifically, a three-dimensional geometric model including components such as an acceleration cavity, a correction magnet, and a fluorescent target can be created according to the structure of the actual accelerator. This simulation system needs to ensure that the sizes, shapes, and positions of each component are relatively accurate, especially the distance between the correction magnet and the fluorescent target needs to be accurately set. For the correction magnet, the magnetic field strength distribution in different directions can be set according to its physical characteristics and design requirements. By continuously changing the magnetic field value of the correction magnet in the simulation system, the beam direction can be changed, thereby changing the beam spot position on the fluorescent target. At this time, record the magnetic field value of the correction magnet and the beam bunch distribution center at the fluorescent target respectively, so that the change situation of the particle distribution at the fluorescent target with the beam energy and the magnet position can be understood, and multiple groups of training data related to beam spot position correction can be obtained.

[0049] The above variable data includes the magnetic field strength of the correction magnet in different directions, beam energy data, and the distance between the correction magnet and the fluorescent target. In order to better obtain the variation of the particle distribution at the fluorescent target with the beam energy and the magnet position, any parameter in the variable data can be used as a simulation variable for adjustment. In this way, during the simulation process, by changing any parameter in the variable data, the spot position distribution under different variable data combinations can be obtained.

[0050] Specifically, after the variable data is input into the simulation system, during the simulation process, change the magnetic field strength of the correction magnet in different directions to correspondingly obtain the change in the particle distribution at the fluorescent target and obtain the first training data for spot position correction; and / or change the beam energy data during the simulation process to correspondingly obtain the change in the particle distribution at the fluorescent target and obtain the second training data for spot position correction; and / or change the distance between the correction magnet and the fluorescent target during the simulation process to correspondingly obtain the change in the particle distribution at the fluorescent target and obtain the third training data for spot position correction.

[0051] The structure of the variable data in the above simulation system can refer to Figure 4 As shown, by changing any one of the variable data, such as the magnetic field strengths Bx, By of the correction magnet in different directions, the distance length between the correction magnet and the fluorescent target, and the beam energy data energy, the central position coordinates centX, centY of the beam at the center of the fluorescent target can be correspondingly changed.

[0052] It can be understood that in addition to the variable data used as simulation variables, simulation parameters such as the time step and total simulation time of the simulation also need to be set. To ensure the calculation accuracy of the particle motion trajectory, the time step should be small enough, but not too small to cause excessive computational load. The total simulation time needs to be determined according to the expected motion time of the particles from the initial position to the fluorescent target. During the iterative calculation process, for each value of the simulation variable, run the simulation system. When the simulation variable is the magnetic field strength, the force on the particles will change with the change of the magnetic field strength, thus affecting the motion trajectory of the particles. Correspondingly, after each simulation calculation is completed, record the spot position distribution accompanied by the change of the variable data, such as the coordinates and quantities of the particles, as well as the parameters related to the spot position, such as the central position coordinates of the spot and the spot size.

[0053] Correspondingly, after obtaining the beam spot position distribution accompanying the change in adjoint variable data, multiple sets of correlated simulation data can be determined based on the beam spot position distribution accompanying the change in adjoint variable data. The simulation data includes the magnetic field strength of the correction magnet in different directions, beam energy data, the distance between the correction magnet and the fluorescent target, and the beam spot center position coordinates. Select the beam energy data, the distance between the correction magnet and the fluorescent target, and the beam spot center position coordinates to construct the input data for magnetic field strength constraint. Select the magnetic field strength of the correction magnet in different directions to construct the output data for magnetic field strength prediction.

[0054] In an actual application scenario, the training data constructed for the training process of the prediction network model can be expressed as [energy, Bx, By, centX, centY, length], where energy is the beam energy data, Bx and By are the magnetic field strengths of the correction magnet in different directions, centX and centY are the beam spot center position coordinates, and length is the distance between the correction magnet and the fluorescent target. Correspondingly, [energy, centX, centY, length] is the input data for magnetic field strength constraint, and [Bx, By] is the output data for magnetic field strength prediction. Here, the magnetic field strength is equivalent to the label in the supervised training process, and the output data of the prediction network model needs to align with the label so that the prediction network model can obtain the corresponding accurate output data [Bx, By] based on the input data [energy, centX, centY, length].

[0055] In an actual application scenario, the beam spot center position coordinates are used as the current beam spot position, and the center position of the fluorescent target is used as the expected beam spot position. The process of correcting the beam spot position is to adjust the current beam spot position to the expected beam spot position. Specifically, as Figure 5 shown, step 103 includes the following steps: 401. According to the magnetic field strength of the correction magnet in different directions, use the opposite value of the magnetic field strength as the position correction parameter.

[0056] 402. Send the position correction parameter to the correction magnet through a control instruction so that the correction magnet corrects the beam spot position according to the position correction parameter.

[0057] In this embodiment, there is a quantitative relationship between the magnetic field strength of the correction magnet in different directions and the change in the beam spot position. For example, an increase in the magnetic field strength of the correction magnet in the x direction will cause the beam spot position to deviate to the left in the y direction. Correspondingly, it is necessary to control the magnetic field strength of the correction magnet in the x direction to decrease in order to make the beam spot position approach the center in the y direction. That is to say, the correction process of the beam spot position is based on the reaction of the magnetic field strength of the correction magnet in different directions. By taking the inverse of the magnetic field strength, a force opposite to the current beam spot offset direction can be generated, pushing the beam spot towards the center position of the fluorescent target.

[0058] Specifically, the opposite values of the magnetic field strength of the correction magnet in different directions can be used as the position correction parameters for beam spot position correction. This position correction parameter can cause the correction magnet to generate a force on the beam current that is opposite to the current beam spot offset direction. After such an opposite force, the beam current direction will move in the direction opposite to the current beam spot offset, causing the beam spot position to be located at the center of the fluorescent target.

[0059] Furthermore, in order to precisely control the correction magnet, the position correction parameter can be encoded and encapsulated, converted into a control instruction in a specific format. The control instruction contains detailed correction parameter information and requirements for execution operations, and can be sent to the control system of the correction magnet through a set communication link. Correspondingly, after receiving the control instruction, the control system of the correction magnet will parse and verify the control instruction to ensure the accuracy and integrity of the control instruction. Once the verification passes, the control system will adjust the excitation current of the correction magnet according to the position correction parameter in the control instruction. Since the magnetic field strength of the correction magnet has a linear relationship with the excitation current, by changing the magnitude and direction of the excitation current, precise adjustment of the magnetic field strength of the correction magnet in different directions can be achieved, making it generate a force opposite to the original magnetic field strength. After the beam current is affected by this force, its movement trajectory will change, thereby driving the beam spot position to generate a corresponding displacement, realizing the correction of the beam spot position.

[0060] Further, as a specific implementation of the above method, an embodiment of the present application provides a device for correcting the beam spot position, as Figure 6 shown. The device includes: a first acquisition unit 51, a prediction unit 52, and a correction unit 53.

[0061] The first acquisition unit 51 is used to acquire magnetic field constraint data for beam spot position correction. The magnetic field constraint data includes the beam spot center position coordinates, beam current energy data, and the distance between the correction magnet and the fluorescent target. The prediction unit 52 is used to input the magnetic field constraint data into a pre-trained prediction network model, so as to predict the magnetic field strength of the correction magnet in different directions through the prediction network model according to the magnetic field constraint data. A correction unit 53 is configured to correct the beam spot position according to the magnetic field intensities of the correction magnet in different directions.

[0062] Compared with the prior art that relies on manual operation to correct the beam spot position, the beam spot position correction device provided by the embodiments of the present invention obtains magnetic field constraint data for beam spot position correction, where the magnetic field constraint data includes the beam spot center position coordinates, beam current energy data, and the distance between the correction magnet and the fluorescent target. The magnetic field constraint data is input into a pre-trained prediction network model, so that the prediction network model predicts the magnetic field intensities of the correction magnet in different directions according to the magnetic field constraint data. The beam spot position is corrected according to the magnetic field intensities of the correction magnet in different directions. The whole process uses a pre-trained prediction network model to replace manual operation for the beam spot position correction process. The prediction network model can accurately read the tiny offset of the beam spot according to the beam current with different energies and the beam spot position, and can automatically calibrate the beam spot position without manual participation, greatly improving the beam tuning efficiency.

[0063] In a specific application scenario, the device further includes: A second acquisition unit is configured to acquire training data for beam spot position correction before inputting the magnetic field constraint data into the pre-trained prediction network model, so that the prediction network model predicts the magnetic field intensities of the correction magnet in different directions according to the magnetic field constraint data. The training data includes input data for magnetic field intensity constraint and output data for magnetic field intensity prediction. A training unit is configured to train the prediction network model according to the training data, and update the mapping relationship between the input data and the output data during the training process. The mapping relationship is used to predict the magnetic field intensity of the output data based on the input data as the magnetic field constraint. A generation unit is configured to generate a prediction network model according to the updated mapping relationship when the training meets the iteration stop condition.

[0064] In a specific application scenario, the second acquisition unit includes: A construction module is configured to pre-construct a simulation system for particle acceleration simulation, so as to simulate the variable data for beam spot position correction and the particle distribution at the fluorescent target through the simulation system. An acquisition module is configured to change the variable data during the simulation process, so as to correspondingly acquire the changed particle distribution at the fluorescent target, and obtain the beam spot position distribution accompanied by the change of the variable data. A construction module is configured to construct training data for beam spot position correction according to the beam spot position distribution accompanied by the change of the variable data.

[0065] In a specific application scenario, the variable data includes the magnetic field intensity of the correction magnet in different directions, beam energy data, and the distance between the correction magnet and the fluorescent target. The acquisition module is specifically configured to: During the simulation process, change the magnetic field intensity of the correction magnet in different directions to correspondingly obtain the particle distribution at the fluorescent target, and obtain the first training data for beam spot position correction; and / or During the simulation process, change the beam energy data to correspondingly obtain the particle distribution at the fluorescent target, and obtain the second training data for beam spot position correction; and / or During the simulation process, change the distance between the correction magnet and the fluorescent target to correspondingly obtain the particle distribution at the fluorescent target, and obtain the third training data for beam spot position correction.

[0066] In a specific application scenario, the construction module is specifically configured to: Determine multiple sets of associated simulation data according to the beam spot position distribution changed by the adjoint variable data. The simulation data includes the magnetic field intensity of the correction magnet in different directions, beam energy data, the distance between the correction magnet and the fluorescent target, and the beam spot center position coordinates; Select the beam energy data, the distance between the correction magnet and the fluorescent target, and the beam spot center position coordinates to construct the input data for magnetic field intensity constraint; Select the magnetic field intensity of the correction magnet in different directions to construct the output data for magnetic field intensity prediction.

[0067] In a specific application scenario, the training unit is further configured to, before training the prediction network model according to the training data and updating the mapping relationship between the input data and the output data during the training process, set a loss function for measuring the training effect of the prediction network model according to the mean square error function; Correspondingly, during the training process, calculate the loss value between the predicted output data of the prediction network model and the output data for magnetic field intensity prediction according to the loss function, so as to update the mapping relationship between the input data and the output data through the loss value.

[0068] In a specific application scenario, the correction unit is specifically configured to: According to the magnetic field intensity of the correction magnet in different directions, use the opposite value of the magnetic field intensity as the position correction parameter; Send the position correction parameter to the correction magnet through a control instruction, so that the correction magnet corrects the beam spot position according to the position correction parameter.

[0069] It should be noted that for other corresponding descriptions of the functional units involved in the beam spot position correction device provided in this embodiment, reference can be made to the corresponding descriptions of the above beam spot position correction method, which will not be elaborated here.

[0070] Based on the above beam spot position correction method, correspondingly, an embodiment of the present application further provides a storage medium, on which a computer program is stored, and when the program is executed by a processor, the above beam spot position correction method is implemented.

[0071] Based on such an understanding, the technical solution of the present application can be embodied in the form of a software product, and the software product can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), including several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in various implementation scenarios of the present application.

[0072] Based on the above beam spot position correction method and the embodiment of the beam spot position correction device, in order to achieve the above object, an embodiment of the present application further provides a physical device for beam spot position correction, which can specifically be a computer, a smart phone, a tablet computer, a smart watch, a server, or a network device, etc. The physical device includes a storage medium and a processor; the storage medium is used to store a computer program; the processor is used to execute the computer program to implement the above beam spot position correction method.

[0073] Optionally, the physical device may further include a user interface, a network interface, a camera, a radio frequency (RF) circuit, sensors, an audio circuit, a WI-FI module, etc. The user interface may include a display screen (Display), an input unit such as a keyboard (Keyboard), etc. Optionally, the user interface may further include a USB interface, a card reader interface, etc. The network interface may optionally include a standard wired interface, a wireless interface (such as a WI-FI interface), etc.

[0074] In an exemplary embodiment, refer to Figure 7 , the above physical device includes a communication bus, a processor, a memory, and a communication interface, and may further include an input / output interface and a display device. Among them, each functional unit can complete mutual communication through the bus. The memory stores a computer program, and the processor is used to execute the program stored on the memory to implement the beam spot position correction method in the above embodiment.

[0075] Those skilled in the art can understand that the structure of the physical device for beam spot position correction provided in this embodiment does not constitute a limitation on the physical device, and it may include more or fewer components, or combine some components, or have different component arrangements.

[0076] The storage medium may further include an operating system and a network communication module. The operating system is a program that manages the hardware and software resources of the physical device for correcting the position of the beam spot, and supports the operation of information processing programs and other software and / or programs. The network communication module is used to implement communication between components inside the storage medium, as well as communication with other hardware and software in the information processing physical device.

[0077] Through the description of the above embodiments, those skilled in the art can clearly understand that the present application can be implemented by means of software plus a necessary general hardware platform, or can be implemented by hardware. By applying the technical solution of the present application, compared with the current existing methods, the present application uses a pre-trained prediction network model to replace manual operation to correct the position of the beam spot. This prediction network model can accurately read the small offset of the beam spot according to the beam current of different energies and the position of the beam spot, and can automatically calibrate the position of the beam spot without manual participation, greatly improving the beam tuning efficiency.

[0078] Those skilled in the art can understand that the drawings are only schematic diagrams of a preferred embodiment scenario, and the modules or processes in the drawings are not necessarily essential for implementing the present application. Those skilled in the art can understand that the modules in the device in the embodiment scenario can be distributed in the device in the embodiment scenario according to the description of the embodiment scenario, or can be correspondingly changed and located in one or more devices different from this embodiment scenario. The modules in the above embodiment scenario can be combined into one module, or can be further split into multiple sub-modules.

[0079] The above serial numbers of the present application are only for description and do not represent the advantages or disadvantages of the embodiment scenario. The above disclosure is only several specific embodiment scenarios of the present application. However, the present application is not limited thereto, and any change that can be thought of by those skilled in the art should fall within the protection scope of the present application.

Claims

1. A method for correcting a beam spot position, characterized in that: include: Acquiring magnetic field constraint data for beam spot position correction, wherein the magnetic field constraint data includes beam spot center position coordinates, beam energy data, and the distance between the correction magnet and the fluorescent target; Inputting the magnetic field constraint data into a pre-trained prediction network model, so as to predict the magnetic field strength of the correction magnet in different directions according to the magnetic field constraint data through the prediction network model; The beam spot position is corrected according to the magnetic field strength of the correction magnet in different directions.

2. The method for correcting the beam spot position according to claim 1, characterized in that: Before inputting the magnetic field constraint data into a pre-trained prediction network model so as to predict the magnetic field strength of the correction magnet in different directions according to the magnetic field constraint data through the prediction network model, the method further includes: Acquiring training data for beam spot position correction, the training data comprising input data for magnetic field intensity constraint and output data for magnetic field intensity prediction; Training the prediction network model according to the training data, and updating the mapping relationship between the input data and the output data during the training process, wherein the mapping relationship is used to predict the magnetic field intensity of the output data based on the input data as a magnetic field constraint; When the training meets the iteration stopping condition, a prediction network model is generated according to the updated mapping relationship.

3. The method for correcting the beam spot position according to claim 2, characterized in that: The step of acquiring the training data for beam spot position correction includes: Pre-establishing a simulation system for particle acceleration simulation, so as to simulate variable data for beam spot position correction and particle distribution at a fluorescent target through the simulation system; Changing the variable data during the simulation process to obtain a corresponding change in the particle distribution at the fluorescent target, and obtaining a beam spot position distribution accompanying the change in the variable data; According to the beam spot position distribution accompanying the change of the variable data, training data for beam spot position correction is constructed.

4. The method for correcting the beam spot position according to claim 3, characterized in that: The variable data includes the magnetic field strength of the correction magnet in different directions, beam energy data, and the distance between the correction magnet and the fluorescent target. The variable data is changed during the simulation process to obtain the particle distribution at the fluorescent target accordingly to obtain the training data for beam spot position correction, including: During the simulation process, the magnetic field strength of the correction magnet in different directions is changed to obtain the particle distribution at the fluorescent target accordingly, and obtain the first training data for beam spot position correction; and / or Changing the beam energy data during the simulation process to correspondingly change the particle distribution at the fluorescent target and obtain second training data for beam spot position correction; and / or During the simulation process, the distance between the correction magnet and the fluorescent target is changed to obtain the particle distribution at the fluorescent target accordingly, thereby obtaining the third training data for beam spot position correction.

5. The method for correcting the beam spot position according to claim 3, characterized in that: The step of constructing training data for beam spot position correction according to the beam spot position distribution changed by the accompanying variable data comprises: Determine a plurality of sets of associated simulation data according to the beam spot position distribution of the accompanying variable data change, wherein the simulation data include the magnetic field strength of the correction magnet in different directions, beam energy data, the distance between the correction magnet and the fluorescent target, and the coordinates of the center position of the beam spot; Select beam energy data, the distance between the correction magnet and the fluorescent target, and the coordinates of the center position of the beam spot to construct input data for magnetic field intensity constraint; The magnetic field strength of the correction magnet in different directions is selected to construct output data for magnetic field strength prediction.

6. The method for correcting the beam spot position according to claim 2, characterized in that: Before training the prediction network model according to the training data and updating the mapping relationship between the input data and the output data during the training, the method further includes: The loss function that measures the training effect of the loss prediction network model is set according to the mean square error function; Correspondingly, during the training process, the loss value between the predicted output data of the prediction network model and the output data for magnetic field strength prediction is calculated according to the loss function, so as to update the mapping relationship between the input data and the output data through the loss value.

7. The method for correcting the beam spot position according to any one of claims 1 to 6, characterized in that: The step of correcting the beam spot position according to the magnetic field strength of the correction magnet in different directions includes: According to the magnetic field strength of the correction magnet in different directions, using the opposite value of the magnetic field strength as a position correction parameter; The position correction parameter is sent to the correction magnet through a control instruction, so that the correction magnet corrects the beam spot position according to the position correction parameter.

8. A beam spot position correction device, characterized in that: include: A first acquisition unit is used to acquire magnetic field constraint data for beam spot position correction, wherein the magnetic field constraint data includes beam spot center position coordinates, beam energy data, and a distance between a correction magnet and a fluorescent target; A prediction unit, used for inputting the magnetic field constraint data into a pre-trained prediction network model, so as to predict the magnetic field strength of the correction magnet in different directions according to the magnetic field constraint data through the prediction network model; The correction unit is used to correct the beam spot position according to the magnetic field strength of the correction magnet in different directions.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the beam spot position correction method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the beam spot position correction method according to any one of claims 1 to 7 are implemented.

Images