A New Vibration Controller Design Method Using Reinforcement Learning and FIR Filters: A Numerical and Experimental Study

Abstract

High-dimensional high-frequency continuous-vibration control problems often have very complex dynamic behaviors. It is difficult for the conventional control methods to obtain appropriate control laws from such complex systems to suppress the vibration. This paper proposes a new vibration controller by using reinforcement learning (RL) and a finite-impulse-response (FIR) filter. First, a simulator with enough physical fidelity was built for the vibration system. Then, the deep deterministic policy gradient (DDPG) algorithm interacted with the simulator to find a near-optimal control policy to meet the specified goals. Finally, the control policy, represented as a neural network, was run directly on a controller in real-world experiments with high-dimensional and high-frequency dynamics. The simulation results show that the maximum peak values of the power-spectrum-density (PSD) curves at specific frequencies can be reduced by over 63%. The experimental results show that the peak values of the PSD curves at specific frequencies were reduced by more than 47% (maximum over 52%). The numerical and experimental results indicate that the proposed controller can significantly attenuate various vibrations within the range from 50 Hz to 60 Hz.

Vibration Control with Reinforcement Learning Based on Multi-Reward Lightweight Networks

“…Therefore, the introduction of multiple reward signals helps to provide more comprehensive and accurate training signals to improve the learning process and strategies. Compared with the previous method [26], the reward function is as follows:…”

“…Reference [26] proposed the fully connected network and DDPG framework as the primary points of comparison, detailing their parameters and vibration reduction levels. Considering the prevalent use of fully connected network methods in the current domain, we introduced methods such as convolutional neural networks (CNNs), GoogLeNet, and Long Short-Term Memory networks (LSTMs) to expand the experimental scope; relevant parameters and vibration reduction levels are listed in the table above.…”

“…At present, some progress has been made in the combination of reinforcement learning and finite-impulse response filters. Feng et al [26] successfully solved the multiinput/multi-output actual vibration control problem in a frequency range by using RL and FIR filters, which marks the first time that reinforcement learning has been used to solve high-dimensional high-frequency vibration control problems. In order to meet the lightweight requirements of the underlying equipment, they designed the simplest fully connected neural network.…”

Performance and Optimization of a Dual-Stage Vibration Isolation System Using Bio-Inspired Vibration Isolators

“…with complex vibration isolation systems [19][20][21][22][23][24][25], a single-stage vibration isolation system often leads to resonant peaks and standing wave effects at high frequencies [26][27][28][29], which cannot meet the vibration isolation requirements. A dual-stage vibration isolation system draws great interest owing to its better high-frequency effect and higher stability [30][31][32][33][34][35][36].…”

Effects of Carbon Nanotube and Graphene Oxide Incorporation on the Improvements of Magneto-Induced Electrical Sensitivity of Magneto-Rheological Gel

“…Expeditious developments in research to design a tunable vibration absorber (TVA) are the focus of much recent investigation to satisfy the requirements of various applications for suppressing unwanted vibrations [ 1 , 2 , 3 ]. Magneto-rheological (MR) materials, including MR elastomers (MRE) and MR gel (MRG), and polymer matrix incorporating carbonyl iron powder (CIP), are regarded as a possible candidates for application in the TVA systems [ 4 , 5 , 6 ].…”