Abstract
In this work, an advantage actor critic (A2C) based intelligent automatic frequency control (AFC) system was developed for X-band linear accelerator (LINAC). A2C is one type of reinforcement learning, which indicates how software agents should perform actions in an environment. In this paper, the A2C based AFC algorithm and its environment design, simulation result, and controller hardware and software processes are described. The objective of our design is to match LINAC and magnetron frequency, and it is implemented via reward shaping using comparison with the reflected power in the adjacent time. The simulation with the A2C algorithm was implemented in two modes, namely, periodic and White Gaussian Noise (WGN) waves, for analysis with temperature and random disturbance, respectively. In order to create artificial disturbance in the experiment, the magnetron shaft was shifted randomly every 0.5 s by using WGN with 18° angle of the step motor. The standard deviation of the reflected power was 5.63 kW, and the average power was 130.9 kW. To obtain maximum reward at the beginning of the A2C training, the adjacent frequency is needed. The measured average reflected power and standard deviation were 122.8 kW and 1.75 kW, respectively, after 2000 iterations. The results show that the reflected power and standard deviation of the AFC with A2C were lower compared to open-loop with artificial disturbance. The RF station of a medical X-band LINAC was used as the test bench, and the performance was confirmed by the results of an experiment conducted at Sungkyunkwan University in Korea.
Highlights
In scientific research, particle accelerators such as cyclotrons, synchrotrons, and linear accelerators (LINAC) are essential instrumentation, and large-scale accelerators are used for basic research in particle physics
AFFILIATIONS 1 Department of Energy Science, Sungkyunkwan University, Suwon 16419, South Korea 2College of Information and Communication Engineering, Sungkyunkwan University, Suwon 16419, South Korea a)Electronic mail: jschai@skku.edu. Particle accelerators such as cyclotrons, synchrotrons, and linear accelerators (LINAC) are essential instrumentation, and large-scale accelerators are used for basic research in particle physics
In commercial applications such as accelerator mass spectrometry (AMS), cargo screening, and positron emission tomography (PET) isotopes, there is a demand for compact accelerators due to space limitations and their advantages with regard to portability
Summary
Particle accelerators such as cyclotrons, synchrotrons, and linear accelerators (LINAC) are essential instrumentation, and large-scale accelerators are used for basic research in particle physics. The X-band electron linear accelerator (LINAC) is widely used in industrial and medical applications such as nondestructive test (NDT) and radiation therapy (RT) For such applications, the X-band LINAC has advantages such as compactness, higher shunt impedance, and higher breakdown voltage, and pulsed magnetrons of up to 2 MW are mostly used for feeding RF power to the cavity.. AFC using a proportional-integral-derivative (PID) controller is not appropriate for reflected power, which is created by a different frequency; in order to overcome this problem, we applied a reinforcement learning process based on AFC to forward view. Our work describes an A2C based AFC algorithm, including the environment design, simulation result, controller hardware, and software process. The RF station of a medical X-band LINAC was used as the test bench, and the performance was evaluated from the results of the experiments conducted at Sungkyunkwan University in Korea
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call