Magnetic Field Compensation Control for Spin-Exchange Relaxation-Free Comagnetometer Using Reinforcement Learning
- Resource Type
- Periodical
- Authors
- Li, F.; Wang, Z.; Wang, R.; Liu, S.; Qin, B.; Liu, Z.; Zhou, X.
- Source
- IEEE Transactions on Instrumentation and Measurement IEEE Trans. Instrum. Meas. Instrumentation and Measurement, IEEE Transactions on. 72:1-10 2023
- Subject
- Power, Energy and Industry Applications
Components, Circuits, Devices and Systems
Magnetometers
Laser excitation
Pump lasers
Magnetic shielding
Magnetic noise
Probes
Heuristic algorithms
Q-learning
real-time control system
reinforcement learning (RL)
spin-exchange relaxation-free comagnetometer (SERFCM)
triaxial drift magnetic field compensation (TDMFC)
- Language
- ISSN
- 0018-9456
1557-9662
The triaxial drift magnetic field compensation (TDMFC) is a prerequisite to maintaining the excellent performance of the spin-exchange relaxation-free comagnetometer (SERFCM). In this article, we develop a previously undescribed controller design architecture running the proposed constrained dynamic action space $Q$ -learning (CDA- $Q$ ) algorithm using reinforcement learning (RL) to solve the TDMFC problem. The architecture contains two parts: offline training and online deployment. Specifically, the CDA- $Q$ algorithm trains the agents with the simulated environment to produce the control strategies adopted in the online deployment. Numerical simulations verify the effectiveness of the obtained control strategies. Experimentally, the control strategies are deployed in the real-time control system achieving efficient and adaptive compensation of the triaxial drift magnetic field. Comparative experiments show that the proposed method is 67.56% more efficient than the existing method.