Multi-layer NN-based fixed-time distributed optimisation for coordinated dynamic positioning of unmanned surface vehicles.
Saved in:
| Title: | Multi-layer NN-based fixed-time distributed optimisation for coordinated dynamic positioning of unmanned surface vehicles. |
|---|---|
| Authors: | Chang, Ze-Jiang1 (AUTHOR), Yao, Xiang-Yu1,2,3 (AUTHOR) xyyao518@163.com, Zhang, Yun-Hao4 (AUTHOR), Park, Ju H.5 (AUTHOR) |
| Source: | International Journal of Control. Apr2026, Vol. 99 Issue 4, p966-984. 19p. |
| Subjects: | Dynamic positioning systems, Optimization algorithms, Multilayer perceptrons, Feedback control systems, Robust control, Sliding mode control, Autonomous vehicles |
| Abstract: | This article studies the distributed fixed-time coordinated dynamic positioning (CDP) problem for unmanned surface vehicles (USVs) under compound uncertainties constraints including disturbances, model uncertainties, as well as input saturation and quantisation. To tackle the challenging issue, some robust distributed fixed-time optimisation control algorithms are presented. Specifically, the algorithms involve a non-singular fast terminal integral sliding manifold (NFTISM) to ensure the convergence of the sum of local gradients to a zero-residual set within a fixed time, regardless of initial conditions. Subsequently, a sliding-mode-based distributed protocol is introduced to achieve global consensus of states within a fixed time. Additionally, the algorithms utilise multi-layer neural networks (NNs) to approximate the compound unknown disturbances and dynamics of the system. The proposed multi-layer NNs leverage the strengths of both fuzzy NNs (FNNs) and radial basis function NNs (RBFNNs), consequently presenting robust dynamic properties. Note that an event-triggered distributed optimisation protocol is further designed to achieve global optimality within a fixed time, thereby reducing resource consumption and eliminating Zeno behaviours. Finally, simulations show the effectiveness and superiority of the proposed algorithms. [ABSTRACT FROM AUTHOR] |
| Copyright of International Journal of Control is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| Abstract: | This article studies the distributed fixed-time coordinated dynamic positioning (CDP) problem for unmanned surface vehicles (USVs) under compound uncertainties constraints including disturbances, model uncertainties, as well as input saturation and quantisation. To tackle the challenging issue, some robust distributed fixed-time optimisation control algorithms are presented. Specifically, the algorithms involve a non-singular fast terminal integral sliding manifold (NFTISM) to ensure the convergence of the sum of local gradients to a zero-residual set within a fixed time, regardless of initial conditions. Subsequently, a sliding-mode-based distributed protocol is introduced to achieve global consensus of states within a fixed time. Additionally, the algorithms utilise multi-layer neural networks (NNs) to approximate the compound unknown disturbances and dynamics of the system. The proposed multi-layer NNs leverage the strengths of both fuzzy NNs (FNNs) and radial basis function NNs (RBFNNs), consequently presenting robust dynamic properties. Note that an event-triggered distributed optimisation protocol is further designed to achieve global optimality within a fixed time, thereby reducing resource consumption and eliminating Zeno behaviours. Finally, simulations show the effectiveness and superiority of the proposed algorithms. [ABSTRACT FROM AUTHOR] |
|---|---|
| ISSN: | 00207179 |
| DOI: | 10.1080/00207179.2025.2545318 |
