Ultrasonic motors (USM) have great potential to become the actuators of the next generation. However, the current control schemes of USM are still suffering from some shortcomings including limitation of output speed and torque range, and excessive heat generation. Driving schemes based solely on frequency control suffer from reduced efficiencies across most of its operation band due to having a single optimum driving frequency around resonance. In this paper, the effect of preload on USM driving characteristics was demonstrated and it was clarified that preload can affect the driving efficiency, resonance frequency, and output power range. Dynamic preload control has, thus, been proposed as a supplementary controller besides frequency control to enhance the USM performance. The results show that compared to static preload, dynamic preload can expand the output power range of USM (up to 5 W) while keeping a maximum driving efficiency (up to 22%).
Speed control of ultrasonic motors (USM) needs to be precise, fast, and robust; however, this becomes a challenging task due to the nonlinear behavior of these motors including nonlinear response, pull-out phenomenon, and speed hysteresis. However, linear controllers would be suboptimal and unstable, and nonlinear controllers would require expert knowledge, expensive online calculations, or costly model estimation. In this paper, we propose a model-free nonlinear offline controller that can significantly mitigate these challenges. Using deep reinforcement learning (DRL) algorithms, a neural network speed controller was optimized. A soft actor-critic (SAC) DRL algorithm was chosen due to its sample efficiency, fast convergence, and stable learning. To ensure controller stability, a custom control Lyapunov reward function was proposed. The steady-state USM behavior was mathematically modeled for easing controller design under simulation. The SAC agent was designed and trained first in simulation and then further trained experimentally. The experimental results support that the trained controller can successfully expand speed operation range ([0,300] rpm), plan optimal control trajectories, and stabilize performance under varying load torque and temperature drift.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.