A robust zeroing neural network and its applications to dynamic complex matrix equation solving and robotic manipulator trajectory tracking
Dynamic complex matrix equation (DCME) is frequently encountered in the fields of mathematics and industry, and numerous recurrent neural network (RNN) models have been reported to effectively find the solution of DCME in no noise environment. However, noises are unavoidable in reality, and dynamic...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-11-01
|
| Series: | Frontiers in Neurorobotics |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fnbot.2022.1065256/full |
| _version_ | 1811220617678028800 |
|---|---|
| author | Jie Jin Jie Jin Lv Zhao Lv Zhao Lei Chen Lei Chen Weijie Chen |
| author_facet | Jie Jin Jie Jin Lv Zhao Lv Zhao Lei Chen Lei Chen Weijie Chen |
| author_sort | Jie Jin |
| collection | DOAJ |
| description | Dynamic complex matrix equation (DCME) is frequently encountered in the fields of mathematics and industry, and numerous recurrent neural network (RNN) models have been reported to effectively find the solution of DCME in no noise environment. However, noises are unavoidable in reality, and dynamic systems must be affected by noises. Thus, the invention of anti-noise neural network models becomes increasingly important to address this issue. By introducing a new activation function (NAF), a robust zeroing neural network (RZNN) model for solving DCME in noisy-polluted environment is proposed and investigated in this paper. The robustness and convergence of the proposed RZNN model are proved by strict mathematical proof and verified by comparative numerical simulation results. Furthermore, the proposed RZNN model is applied to manipulator trajectory tracking control, and it completes the trajectory tracking task successfully, which further validates its practical applied prospects. |
| first_indexed | 2024-04-12T07:45:14Z |
| format | Article |
| id | doaj.art-a894078ed9304a9e96981dfb2959b7f9 |
| institution | Directory Open Access Journal |
| issn | 1662-5218 |
| language | English |
| last_indexed | 2024-04-12T07:45:14Z |
| publishDate | 2022-11-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neurorobotics |
| spelling | doaj.art-a894078ed9304a9e96981dfb2959b7f92022-12-22T03:41:43ZengFrontiers Media S.A.Frontiers in Neurorobotics1662-52182022-11-011610.3389/fnbot.2022.10652561065256A robust zeroing neural network and its applications to dynamic complex matrix equation solving and robotic manipulator trajectory trackingJie Jin0Jie Jin1Lv Zhao2Lv Zhao3Lei Chen4Lei Chen5Weijie Chen6School of Information Engineering, Changsha Medical University, Changsha, ChinaSchool of Information and Electrical Engineering, Hunan University of Science and Technology, Xiangtan, ChinaSchool of Information Engineering, Changsha Medical University, Changsha, ChinaSchool of Information and Electrical Engineering, Hunan University of Science and Technology, Xiangtan, ChinaSchool of Information Engineering, Changsha Medical University, Changsha, ChinaSchool of Information and Electrical Engineering, Hunan University of Science and Technology, Xiangtan, ChinaSchool of Information and Electrical Engineering, Hunan University of Science and Technology, Xiangtan, ChinaDynamic complex matrix equation (DCME) is frequently encountered in the fields of mathematics and industry, and numerous recurrent neural network (RNN) models have been reported to effectively find the solution of DCME in no noise environment. However, noises are unavoidable in reality, and dynamic systems must be affected by noises. Thus, the invention of anti-noise neural network models becomes increasingly important to address this issue. By introducing a new activation function (NAF), a robust zeroing neural network (RZNN) model for solving DCME in noisy-polluted environment is proposed and investigated in this paper. The robustness and convergence of the proposed RZNN model are proved by strict mathematical proof and verified by comparative numerical simulation results. Furthermore, the proposed RZNN model is applied to manipulator trajectory tracking control, and it completes the trajectory tracking task successfully, which further validates its practical applied prospects.https://www.frontiersin.org/articles/10.3389/fnbot.2022.1065256/fullrecurrent neural networkzeroing neural networkdynamic complex matrix equationactivation functionconvergence |
| spellingShingle | Jie Jin Jie Jin Lv Zhao Lv Zhao Lei Chen Lei Chen Weijie Chen A robust zeroing neural network and its applications to dynamic complex matrix equation solving and robotic manipulator trajectory tracking Frontiers in Neurorobotics recurrent neural network zeroing neural network dynamic complex matrix equation activation function convergence |
| title | A robust zeroing neural network and its applications to dynamic complex matrix equation solving and robotic manipulator trajectory tracking |
| title_full | A robust zeroing neural network and its applications to dynamic complex matrix equation solving and robotic manipulator trajectory tracking |
| title_fullStr | A robust zeroing neural network and its applications to dynamic complex matrix equation solving and robotic manipulator trajectory tracking |
| title_full_unstemmed | A robust zeroing neural network and its applications to dynamic complex matrix equation solving and robotic manipulator trajectory tracking |
| title_short | A robust zeroing neural network and its applications to dynamic complex matrix equation solving and robotic manipulator trajectory tracking |
| title_sort | robust zeroing neural network and its applications to dynamic complex matrix equation solving and robotic manipulator trajectory tracking |
| topic | recurrent neural network zeroing neural network dynamic complex matrix equation activation function convergence |
| url | https://www.frontiersin.org/articles/10.3389/fnbot.2022.1065256/full |
| work_keys_str_mv | AT jiejin arobustzeroingneuralnetworkanditsapplicationstodynamiccomplexmatrixequationsolvingandroboticmanipulatortrajectorytracking AT jiejin arobustzeroingneuralnetworkanditsapplicationstodynamiccomplexmatrixequationsolvingandroboticmanipulatortrajectorytracking AT lvzhao arobustzeroingneuralnetworkanditsapplicationstodynamiccomplexmatrixequationsolvingandroboticmanipulatortrajectorytracking AT lvzhao arobustzeroingneuralnetworkanditsapplicationstodynamiccomplexmatrixequationsolvingandroboticmanipulatortrajectorytracking AT leichen arobustzeroingneuralnetworkanditsapplicationstodynamiccomplexmatrixequationsolvingandroboticmanipulatortrajectorytracking AT leichen arobustzeroingneuralnetworkanditsapplicationstodynamiccomplexmatrixequationsolvingandroboticmanipulatortrajectorytracking AT weijiechen arobustzeroingneuralnetworkanditsapplicationstodynamiccomplexmatrixequationsolvingandroboticmanipulatortrajectorytracking AT jiejin robustzeroingneuralnetworkanditsapplicationstodynamiccomplexmatrixequationsolvingandroboticmanipulatortrajectorytracking AT jiejin robustzeroingneuralnetworkanditsapplicationstodynamiccomplexmatrixequationsolvingandroboticmanipulatortrajectorytracking AT lvzhao robustzeroingneuralnetworkanditsapplicationstodynamiccomplexmatrixequationsolvingandroboticmanipulatortrajectorytracking AT lvzhao robustzeroingneuralnetworkanditsapplicationstodynamiccomplexmatrixequationsolvingandroboticmanipulatortrajectorytracking AT leichen robustzeroingneuralnetworkanditsapplicationstodynamiccomplexmatrixequationsolvingandroboticmanipulatortrajectorytracking AT leichen robustzeroingneuralnetworkanditsapplicationstodynamiccomplexmatrixequationsolvingandroboticmanipulatortrajectorytracking AT weijiechen robustzeroingneuralnetworkanditsapplicationstodynamiccomplexmatrixequationsolvingandroboticmanipulatortrajectorytracking |