Optimization design and RL-MPC control approach of a motor considering thermal safety in active vibration isolation systems

Read full text
Authors: Lei Zhang, Zisheng Huang
Cited by: 1
References: 39

Abstract

Abstract Active vibration isolation systems are essential for the reliability of high-precision marine and deep-sea equipment, in which electromagnetic actuators are widely adopted for achieving fast response and high efficiency. However, permanent magnet synchronous linear motors (PMSLMs) face a critical trade-off between vibration suppression and thermal safety during long-term operation. To address this challenge, this paper presents an in-house designed PMSLM and proposes an integrated framework that synergizes multi-objective structural optimization with an adaptive reinforcement learning-based model predictive control (RL-MPC) strategy. First, a multi-objective optimization approach is developed by integrating Taguchi orthogonal experiments, the Box–Behnken response surface methodology, and a novel dream optimization algorithm (DOA) to enhance the electromagnetic performance of the motor. Compared with the conventional NSGA-II algorithm, the dream sharing and forgetting mechanism in DOA enables it to effectively escape from local optimal solutions. Simulation results demonstrate a 22.74% increase in average thrust and a 78.81% reduction in thrust ripple, alongside significant improvements in thermal safety. Based on the high-performance motor, this paper proposes an adaptive RL-MPC strategy with proximal policy optimization algorithm. During the offline training phase, the agent iteratively interacts with the data-driven thermal reduced-order model to learn an optimal control strategy. After training, the agent enables the MPC controller to autonomously adapt its weighting matrix for varying thermal conditions during online operation. Simulation results show that the RL-MPC controller effectively maintains the motor temperature within safe limits while achieving superior vibration isolation performance. Ultimately, this study provides a robust technical foundation for the long-term, reliable operation of high-performance active vibration isolation systems in complex marine environments.

Fields of Study & Subjects

Vibration Control and Rheological Fluids Model Reduction and Neural Networks Electric Motor Design and Analysis

Publication details

Journal / source
Engineering Research Express
Publisher
IOP Publishing
Volume
8
Issue
12
Pages
125505–125505
Publication date
1 June 2026