Journal
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
Volume 32, Issue 10, Pages 4490-4498Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TNNLS.2020.3018107
Keywords
Micromechanical devices; Gyroscopes; Convergence; Artificial neural networks; Uncertainty; Learning systems; Sliding mode control; Composite learning; finite-time (FT) convergence; MEMS gyroscopes; periodic reference signal; terminal sliding mode control
Categories
Funding
- Science, Technology and Innovation Commission of Shenzhen Municipality [JCYJ20190806154612782]
- National Natural Science Foundation of China [61933010]
- Shaanxi National Science Foundation [2019JZ-08]
- Innovation Foundation for Doctor Dissertation of Northwestern Polytechnical University [CX202041]
Ask authors/readers for more resources
This article presents a neural terminal sliding mode controller for uncertain MEMS gyroscope dynamics, utilizing a composite learning mechanism for system dynamics learning and achieving FT convergence. By considering the periodic tracking property and selecting a terminal sliding mode surface for TSMC construction, the system tracking and weight convergence are ensured.
This article proposes a neural terminal sliding mode controller (TSMC) with finite-time (FT) convergence for the uncertain MEMS gyroscope dynamics. To address the uncertainty, considering the periodic tracking property of MEMS gyroscopes, a composite learning mechanism driven by the learning performance evaluation signal is applied to learn the system dynamics. By selecting the terminal sliding mode surface, the TSMC is constructed with error feedback and feedforward compensation. Under the TSMC with the composite learning, the system tracking can be guaranteed to be with FT convergence, while the weights of the learning system will converge in FT. The stability of the closed-loop system is analyzed by the Lyapunov approach. The highlight is that the design can obtain the learning knowledge while the information can be directly reused in repeated tasks with no need of online update. The effectiveness of the proposed method is verified via reference signal tracking of MEMS gyroscopes, while the controller using the stored knowledge achieves better tracking performance of faster convergence and higher tracking accuracy with no need of weight update.
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