Introducing a Novel Model-Free Multivariable Adaptive Neural Network Controller for Square MIMO Systems
In this study, a novel Multivariable Adaptive Neural Network Controller (MANNC) is developed for coupled model-free n-input n-output systems. The learning algorithm of the proposed controller does not rely on the model of a system and uses only the history of the system inputs and outputs. The syste...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/6/2089 |
| _version_ | 1797442526054973440 |
|---|---|
| author | Arash Mehrafrooz Fangpo He Ali Lalbakhsh |
| author_facet | Arash Mehrafrooz Fangpo He Ali Lalbakhsh |
| author_sort | Arash Mehrafrooz |
| collection | DOAJ |
| description | In this study, a novel Multivariable Adaptive Neural Network Controller (MANNC) is developed for coupled model-free n-input n-output systems. The learning algorithm of the proposed controller does not rely on the model of a system and uses only the history of the system inputs and outputs. The system is considered as a ‘black box’ with no pre-knowledge of its internal structure. By online monitoring and possessing the system inputs and outputs, the parameters of the controller are adjusted. Using the accumulated gradient of the system error along with the Lyapunov stability analysis, the weights’ adjustment convergence of the controller can be observed, and an optimal training number of the controller can be selected. The Lyapunov stability of the system is checked during the entire weight training process to enable the controller to handle any possible nonlinearities of the system. The effectiveness of the MANNC in controlling nonlinear square multiple-input multiple-output (MIMO) systems is demonstrated via three simulation studies covering the cases of a time-invariant nonlinear MIMO system, a time-variant nonlinear MIMO system, and a hybrid MIMO system, respectively. In each case, the performance of the MANNC is compared with that of a properly selected existing counterpart. Simulation results demonstrate that the proposed MANNC is capable of controlling various types of square MIMO systems with much improved performance over its existing counterpart. The unique properties of the MANNC will make it a suitable candidate for many industrial applications. |
| first_indexed | 2024-03-09T12:43:08Z |
| format | Article |
| id | doaj.art-b66a8b6fab994e53bcc232a7a00f6003 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T12:43:08Z |
| publishDate | 2022-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-b66a8b6fab994e53bcc232a7a00f60032023-11-30T22:16:05ZengMDPI AGSensors1424-82202022-03-01226208910.3390/s22062089Introducing a Novel Model-Free Multivariable Adaptive Neural Network Controller for Square MIMO SystemsArash Mehrafrooz0Fangpo He1Ali Lalbakhsh2Macquarie University College, Macquarie University, Sydney, NSW 2113, AustraliaAdvanced Control Systems Research Group, College of Science and Engineering, Flinders University, Adelaide, SA 5042, AustraliaSchool of Engineering, Macquarie University, Ryde, NSW 2109, AustraliaIn this study, a novel Multivariable Adaptive Neural Network Controller (MANNC) is developed for coupled model-free n-input n-output systems. The learning algorithm of the proposed controller does not rely on the model of a system and uses only the history of the system inputs and outputs. The system is considered as a ‘black box’ with no pre-knowledge of its internal structure. By online monitoring and possessing the system inputs and outputs, the parameters of the controller are adjusted. Using the accumulated gradient of the system error along with the Lyapunov stability analysis, the weights’ adjustment convergence of the controller can be observed, and an optimal training number of the controller can be selected. The Lyapunov stability of the system is checked during the entire weight training process to enable the controller to handle any possible nonlinearities of the system. The effectiveness of the MANNC in controlling nonlinear square multiple-input multiple-output (MIMO) systems is demonstrated via three simulation studies covering the cases of a time-invariant nonlinear MIMO system, a time-variant nonlinear MIMO system, and a hybrid MIMO system, respectively. In each case, the performance of the MANNC is compared with that of a properly selected existing counterpart. Simulation results demonstrate that the proposed MANNC is capable of controlling various types of square MIMO systems with much improved performance over its existing counterpart. The unique properties of the MANNC will make it a suitable candidate for many industrial applications.https://www.mdpi.com/1424-8220/22/6/2089adaptive neural networksmodel-free controlauto-tuningerror back-propagationaccumulated gradientnonlinear systems |
| spellingShingle | Arash Mehrafrooz Fangpo He Ali Lalbakhsh Introducing a Novel Model-Free Multivariable Adaptive Neural Network Controller for Square MIMO Systems Sensors adaptive neural networks model-free control auto-tuning error back-propagation accumulated gradient nonlinear systems |
| title | Introducing a Novel Model-Free Multivariable Adaptive Neural Network Controller for Square MIMO Systems |
| title_full | Introducing a Novel Model-Free Multivariable Adaptive Neural Network Controller for Square MIMO Systems |
| title_fullStr | Introducing a Novel Model-Free Multivariable Adaptive Neural Network Controller for Square MIMO Systems |
| title_full_unstemmed | Introducing a Novel Model-Free Multivariable Adaptive Neural Network Controller for Square MIMO Systems |
| title_short | Introducing a Novel Model-Free Multivariable Adaptive Neural Network Controller for Square MIMO Systems |
| title_sort | introducing a novel model free multivariable adaptive neural network controller for square mimo systems |
| topic | adaptive neural networks model-free control auto-tuning error back-propagation accumulated gradient nonlinear systems |
| url | https://www.mdpi.com/1424-8220/22/6/2089 |
| work_keys_str_mv | AT arashmehrafrooz introducinganovelmodelfreemultivariableadaptiveneuralnetworkcontrollerforsquaremimosystems AT fangpohe introducinganovelmodelfreemultivariableadaptiveneuralnetworkcontrollerforsquaremimosystems AT alilalbakhsh introducinganovelmodelfreemultivariableadaptiveneuralnetworkcontrollerforsquaremimosystems |