Abstract
The time-varying matrix pseudoinverse holds significant importance across multiple domains. Previous research has indicated that the zeroing neural network model exhibits significant advantages in addressing this issue. However, identified shortcomings include a lack of capability to suppress disturbances effectively. This paper proposes two harmonic-resistant recurrent neural network (HRRNN) models designed to address both known and unknown frequencies. Specifically, these models take into account derivatives of harmonic-type disturbances, effectively suppressing harmonic disturbances. Our focus on the simulated implementation of the HRRNN model presents a novel approach for addressing the challenge of time-varying matrix inversion in low-power scenarios. The effectiveness is validated through numerical simulation experiments.
| Original language | English |
|---|---|
| Title of host publication | 2024 IEEE International Conference on Cybernetics and Intelligent Systems (CIS) and IEEE International Conference on Robotics, Automation and Mechatronics (RAM) |
| Publisher | IEEE Institute of Electrical and Electronic Engineers |
| Pages | 496-501 |
| Number of pages | 6 |
| Edition | 2024 |
| ISBN (Electronic) | 979-8-3503-6419-4 |
| ISBN (Print) | 979-8-3503-6420-0 |
| DOIs | |
| Publication status | Published - 2024 |
| MoE publication type | A4 Article in a conference publication |
| Event | 11th IEEE International Conference on Cybernetics and Intelligent Systems and 11th IEEE International Conference on Robotics, Automation and Mechatronics, CIS-RAM 2024 - Hangzhou, China Duration: 8 Aug 2024 → 11 Aug 2024 |
Conference
| Conference | 11th IEEE International Conference on Cybernetics and Intelligent Systems and 11th IEEE International Conference on Robotics, Automation and Mechatronics, CIS-RAM 2024 |
|---|---|
| Country/Territory | China |
| City | Hangzhou |
| Period | 8/08/24 → 11/08/24 |
Keywords
- Harmonic-resistant
- Manipulator
- Recurrent neural network
- Time-varying matrix pseudoinverse