Force Tracking Control of Lower Extremity Exoskeleton Based on a New Recurrent Neural Network
The lower extremity exoskeleton can enhance the ability of human limbs, which has been used in many fields. It is difficult to develop a precise force tracking control approach for the exoskeleton because of the dynamics model uncertainty, external disturbances, and unknown human–robot interactive f...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-01-01
|
| Series: | Applied Bionics and Biomechanics |
| Online Access: | http://dx.doi.org/10.1155/2024/5870060 |
| _version_ | 1826820116908605440 |
|---|---|
| author | Yuxuan Cao Jie Chen Li Gao Jiqing Luo Jinyun Pu Shengli Song |
| author_facet | Yuxuan Cao Jie Chen Li Gao Jiqing Luo Jinyun Pu Shengli Song |
| author_sort | Yuxuan Cao |
| collection | DOAJ |
| description | The lower extremity exoskeleton can enhance the ability of human limbs, which has been used in many fields. It is difficult to develop a precise force tracking control approach for the exoskeleton because of the dynamics model uncertainty, external disturbances, and unknown human–robot interactive force lied in the system. In this paper, a control method based on a novel recurrent neural network, namely zeroing neural network (ZNN), is proposed to obtain the accurate force tracking. In the framework of ZNN, an adaptive RBF neural network (ARBFNN) is employed to deal with the system uncertainty, and a fixed-time convergence disturbance observer is designed to estimate the external disturbance of the exoskeleton electrohydraulic system. The Lyapunov stability method is utilized to prove the convergence of all the closed-loop signals and the force tracking is guaranteed. The proposed control scheme’s (ARBFNN-FDO-ZNN) force tracking performances are presented and contrasted with the exponential reaching law-based sliding mode controller (ERL-SMC). The proposed scheme is superior to ERL-SMC with fast convergence speed and lower tracking error peak. Finally, experimental tests are conducted to verify the efficacy of the proposed controller for solving accurate force tracking control issues. |
| first_indexed | 2024-03-08T14:23:14Z |
| format | Article |
| id | doaj.art-6e4a1cb9c37447b8bbb63dfc59adf464 |
| institution | Directory Open Access Journal |
| issn | 1754-2103 |
| language | English |
| last_indexed | 2025-02-16T06:23:33Z |
| publishDate | 2024-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Applied Bionics and Biomechanics |
| spelling | doaj.art-6e4a1cb9c37447b8bbb63dfc59adf4642025-02-03T06:47:40ZengWileyApplied Bionics and Biomechanics1754-21032024-01-01202410.1155/2024/5870060Force Tracking Control of Lower Extremity Exoskeleton Based on a New Recurrent Neural NetworkYuxuan Cao0Jie Chen1Li Gao2Jiqing Luo3Jinyun Pu4Shengli Song5Naval University of EngineeringArmy Engineering UniversityArmy Engineering UniversityArmy Engineering UniversityNaval University of EngineeringArmy Engineering UniversityThe lower extremity exoskeleton can enhance the ability of human limbs, which has been used in many fields. It is difficult to develop a precise force tracking control approach for the exoskeleton because of the dynamics model uncertainty, external disturbances, and unknown human–robot interactive force lied in the system. In this paper, a control method based on a novel recurrent neural network, namely zeroing neural network (ZNN), is proposed to obtain the accurate force tracking. In the framework of ZNN, an adaptive RBF neural network (ARBFNN) is employed to deal with the system uncertainty, and a fixed-time convergence disturbance observer is designed to estimate the external disturbance of the exoskeleton electrohydraulic system. The Lyapunov stability method is utilized to prove the convergence of all the closed-loop signals and the force tracking is guaranteed. The proposed control scheme’s (ARBFNN-FDO-ZNN) force tracking performances are presented and contrasted with the exponential reaching law-based sliding mode controller (ERL-SMC). The proposed scheme is superior to ERL-SMC with fast convergence speed and lower tracking error peak. Finally, experimental tests are conducted to verify the efficacy of the proposed controller for solving accurate force tracking control issues.http://dx.doi.org/10.1155/2024/5870060 |
| spellingShingle | Yuxuan Cao Jie Chen Li Gao Jiqing Luo Jinyun Pu Shengli Song Force Tracking Control of Lower Extremity Exoskeleton Based on a New Recurrent Neural Network Applied Bionics and Biomechanics |
| title | Force Tracking Control of Lower Extremity Exoskeleton Based on a New Recurrent Neural Network |
| title_full | Force Tracking Control of Lower Extremity Exoskeleton Based on a New Recurrent Neural Network |
| title_fullStr | Force Tracking Control of Lower Extremity Exoskeleton Based on a New Recurrent Neural Network |
| title_full_unstemmed | Force Tracking Control of Lower Extremity Exoskeleton Based on a New Recurrent Neural Network |
| title_short | Force Tracking Control of Lower Extremity Exoskeleton Based on a New Recurrent Neural Network |
| title_sort | force tracking control of lower extremity exoskeleton based on a new recurrent neural network |
| url | http://dx.doi.org/10.1155/2024/5870060 |
| work_keys_str_mv | AT yuxuancao forcetrackingcontroloflowerextremityexoskeletonbasedonanewrecurrentneuralnetwork AT jiechen forcetrackingcontroloflowerextremityexoskeletonbasedonanewrecurrentneuralnetwork AT ligao forcetrackingcontroloflowerextremityexoskeletonbasedonanewrecurrentneuralnetwork AT jiqingluo forcetrackingcontroloflowerextremityexoskeletonbasedonanewrecurrentneuralnetwork AT jinyunpu forcetrackingcontroloflowerextremityexoskeletonbasedonanewrecurrentneuralnetwork AT shenglisong forcetrackingcontroloflowerextremityexoskeletonbasedonanewrecurrentneuralnetwork |