Simple neural network compact form model-free adaptive controller for thin McKibben muscle system
This paper proposes a simple neural network compact form model-free adaptive controller (NNCFMFAC) for a single thin McKibben muscle (TMM) system. The main contribution of this work is the simplification of the current neural network (NN) based compact form model-free adaptive controller (CFMFAC), w...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Published: |
Institute of Electrical and Electronics Engineers
2022
|
| Online Access: | http://psasir.upm.edu.my/id/eprint/103196/ |
| _version_ | 1848863958673391616 |
|---|---|
| author | Abdul Hafidz, Muhamad Hazwan Mohd Faudzi, Ahmad Athif Norsahperi, Nor Mohd Haziq Jamaludin, Mohd Najeb Awang Hamid, Dayang Tiawa Mohamaddan, Shahrol |
| author_facet | Abdul Hafidz, Muhamad Hazwan Mohd Faudzi, Ahmad Athif Norsahperi, Nor Mohd Haziq Jamaludin, Mohd Najeb Awang Hamid, Dayang Tiawa Mohamaddan, Shahrol |
| author_sort | Abdul Hafidz, Muhamad Hazwan |
| building | UPM Institutional Repository |
| collection | Online Access |
| description | This paper proposes a simple neural network compact form model-free adaptive controller (NNCFMFAC) for a single thin McKibben muscle (TMM) system. The main contribution of this work is the simplification of the current neural network (NN) based compact form model-free adaptive controller (CFMFAC), which requires only two adaptive weights. This is achieved by designing a NN topology to specifically enhance the CFMFAC response. The prominent control parameters of the CFMFAC are combined and an adaptive weight is used for self-tuning, while the second adaptive weight is used to minimize the offset at each operating point. Hence the issues of redundant adaptive weights in complex neuro-based CFMFACs and slow response of the CFMFAC are significantly addressed. The idea is proven in three ways: analytically, simulation on a nonlinear system and experiments on a TMM platform. Experimental results demonstrating the superiority of the proposed method over the conventional CFMFAC is confirmed by a 76% improvement in convergence speed and a 60% reduction in root mean square error (RMSE). It is envisaged that the proposed controller can be very useful for TMM driven applications as it is model-independent, has fast response, high tracking accuracy, and minimal complexity. |
| first_indexed | 2025-11-15T13:41:11Z |
| format | Article |
| id | upm-103196 |
| institution | Universiti Putra Malaysia |
| institution_category | Local University |
| last_indexed | 2025-11-15T13:41:11Z |
| publishDate | 2022 |
| publisher | Institute of Electrical and Electronics Engineers |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | upm-1031962024-06-28T10:02:30Z http://psasir.upm.edu.my/id/eprint/103196/ Simple neural network compact form model-free adaptive controller for thin McKibben muscle system Abdul Hafidz, Muhamad Hazwan Mohd Faudzi, Ahmad Athif Norsahperi, Nor Mohd Haziq Jamaludin, Mohd Najeb Awang Hamid, Dayang Tiawa Mohamaddan, Shahrol This paper proposes a simple neural network compact form model-free adaptive controller (NNCFMFAC) for a single thin McKibben muscle (TMM) system. The main contribution of this work is the simplification of the current neural network (NN) based compact form model-free adaptive controller (CFMFAC), which requires only two adaptive weights. This is achieved by designing a NN topology to specifically enhance the CFMFAC response. The prominent control parameters of the CFMFAC are combined and an adaptive weight is used for self-tuning, while the second adaptive weight is used to minimize the offset at each operating point. Hence the issues of redundant adaptive weights in complex neuro-based CFMFACs and slow response of the CFMFAC are significantly addressed. The idea is proven in three ways: analytically, simulation on a nonlinear system and experiments on a TMM platform. Experimental results demonstrating the superiority of the proposed method over the conventional CFMFAC is confirmed by a 76% improvement in convergence speed and a 60% reduction in root mean square error (RMSE). It is envisaged that the proposed controller can be very useful for TMM driven applications as it is model-independent, has fast response, high tracking accuracy, and minimal complexity. Institute of Electrical and Electronics Engineers 2022 Article PeerReviewed Abdul Hafidz, Muhamad Hazwan and Mohd Faudzi, Ahmad Athif and Norsahperi, Nor Mohd Haziq and Jamaludin, Mohd Najeb and Awang Hamid, Dayang Tiawa and Mohamaddan, Shahrol (2022) Simple neural network compact form model-free adaptive controller for thin McKibben muscle system. IEEE Access, 10. pp. 123410-123422. ISSN 2169-3536 https://ieeexplore.ieee.org/document/9934849/ 10.1109/access.2022.3215980 |
| spellingShingle | Abdul Hafidz, Muhamad Hazwan Mohd Faudzi, Ahmad Athif Norsahperi, Nor Mohd Haziq Jamaludin, Mohd Najeb Awang Hamid, Dayang Tiawa Mohamaddan, Shahrol Simple neural network compact form model-free adaptive controller for thin McKibben muscle system |
| title | Simple neural network compact form model-free adaptive controller for thin McKibben muscle system |
| title_full | Simple neural network compact form model-free adaptive controller for thin McKibben muscle system |
| title_fullStr | Simple neural network compact form model-free adaptive controller for thin McKibben muscle system |
| title_full_unstemmed | Simple neural network compact form model-free adaptive controller for thin McKibben muscle system |
| title_short | Simple neural network compact form model-free adaptive controller for thin McKibben muscle system |
| title_sort | simple neural network compact form model-free adaptive controller for thin mckibben muscle system |
| url | http://psasir.upm.edu.my/id/eprint/103196/ http://psasir.upm.edu.my/id/eprint/103196/ http://psasir.upm.edu.my/id/eprint/103196/ |