Journal
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
Volume 68, Issue 1, Pages 812-820Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIE.2020.2991997
Keywords
Gated recurrent unit (GRU) neural network; learning adaptive robust control (LARC); motion control; tracking accuracy; tracking error prediction
Categories
Funding
- National Nature Science Foundation of China [51922059, 51775305, 91648202]
- Beijing Natural Science Foundation [JQ19010]
- National Youth Talent Support Program
- State Key Laboratory of Mechanical System and Vibration [MSV202007]
Ask authors/readers for more resources
The article proposes a data-based learning adaptive robust control (LARC) strategy based on gated recurrent unit (GRU) neural network, which achieves accurate tracking error prediction, rigorous motion accuracy, and robustness to parameter variations and unknown disturbances simultaneously. By utilizing parameter adaptive control and robust control, a GRU neural network is constructed to precisely predict tracking error, ensuring the effectiveness of the proposed control strategy in real-world scenarios. Experimental investigation confirms the effectiveness of the strategy in providing satisfactory transient/steady-state tracking performance.
To simultaneously achieve accurate tracking error prediction, rigorous motion accuracy, and certain robustness to parameter variations and unknown disturbances, this article proposes a data-based learning adaptive robust control (LARC) strategy based on gated recurrent unit (GRU) neural network. Firstly, parameter adaptive control and robust control are utilized to guarantee the robustness against parametric uncertainties and unknown disturbances. A GRU neural network is then constructed and capable of precisely predicting the tracking error after training with data collected from a linear-motor-driven stage. Essentially, the GRU network can be viewed as a data-based model, which captures the tracking error dynamic characteristics and provides a prediction even before implementing the real trajectory. Consequently, a reference modification and a feedforward compensation part can be formed, which is the significant part of the whole LARC control structure. Comparative experimental investigation not only validates the effectiveness of the tracking error prediction ability, but also demonstrates the practically satisfactory transient/steady-state tracking performance of the proposed control strategy.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available