.png){kind=icon}
.png){kind=icon}
Return
A deep reinforcement learning-based control method for electric linear loading systems
.png){kind=icon}
PRE
AI
DOI：10.1007/s12206-025-1139-8.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
To address the complex parameter tuning in electric linear loading systems under varying loads, a composite control method of deep reinforcement learning and PI algorithm is proposed. An improved feedforward strategy tackles force and nonlinearity while cutting complexity. An adaptive PI algorithm (FC-TD3) combines TD3 and the strategy for online tuning. Using the system as subject, optimal parameters from offline learning are applied. Experiments prove it optimizes parameters and boosts system performance.
Keywords:
Electric linear loading system
Deep reinforcement learning
Feedforward compensation strategy
TD3 algorithm
Parameter tuning
Journal
IF:
1.7
Papers:
601
Citations:
1.2W