The intelligent knee prosthesis is capable of human-like bionic lower limb control through advanced control systems and artificial intelligence algorithms that will potentially minimize gait limitations for above-knee...The intelligent knee prosthesis is capable of human-like bionic lower limb control through advanced control systems and artificial intelligence algorithms that will potentially minimize gait limitations for above-knee amputees and facilitate their reintegration into society.In this paper,we sum up the control strategies corresponding to the prevailing control objectives(position and impedance)of the current intelligent knee prosthesis.Although these control strategies have been successfully implemented and validated in relevant experiments,the existing deficiencies still fail to achieve optimal performance of the controllers,which complicates the definition of a standard control method.Before a mature control system can be developed,it is more important to realize the full potential for the control strategy,which requires upgrading and refining the relevant key technologies based on the existing control methods.For this reason,we discuss potential areas for improvement of the prosthetic control system based on the summarized control strategies,including intent recognition,sensor system,prosthetic evaluation,and parameter optimization algorithms,providing future directions toward optimizing control strategies for the next generation of intelligent knee prostheses.展开更多
The research purpose was to improve the accuracy in identifying the prosthetic leg locomotion mode.Surface electromyography(sEMG)combined with high-order zero-crossing was used to identify the prosthetic leg locomotio...The research purpose was to improve the accuracy in identifying the prosthetic leg locomotion mode.Surface electromyography(sEMG)combined with high-order zero-crossing was used to identify the prosthetic leg locomotion modes.sEMG signals recorded from residual thigh muscles were chosen as inputs to pattern classifier for locomotion-mode identification.High-order zero-crossing were computed as the sEMG features regarding locomotion modes.Relevance vector machine(RVM)classifier was investigated.Bat algorithm(BA)was used to compute the RVM classifier kernel function parameters.The classification performance of the particle swarm optimization-relevance vector machine(PSO-RVM)and RVM classifiers was compared.The BA-RVM produced lower classification error in sEMG pattern recognition for the transtibial amputees over a variety of locomotion modes:upslope,downgrade,level-ground walking and stair ascent/descent.展开更多
基金The authors would liketo thank the support of the National Natural Science Foundation of China(grant no.62073224)National Key Research and Development Program of China(grant no.2018YFB1307303).
文摘The intelligent knee prosthesis is capable of human-like bionic lower limb control through advanced control systems and artificial intelligence algorithms that will potentially minimize gait limitations for above-knee amputees and facilitate their reintegration into society.In this paper,we sum up the control strategies corresponding to the prevailing control objectives(position and impedance)of the current intelligent knee prosthesis.Although these control strategies have been successfully implemented and validated in relevant experiments,the existing deficiencies still fail to achieve optimal performance of the controllers,which complicates the definition of a standard control method.Before a mature control system can be developed,it is more important to realize the full potential for the control strategy,which requires upgrading and refining the relevant key technologies based on the existing control methods.For this reason,we discuss potential areas for improvement of the prosthetic control system based on the summarized control strategies,including intent recognition,sensor system,prosthetic evaluation,and parameter optimization algorithms,providing future directions toward optimizing control strategies for the next generation of intelligent knee prostheses.
基金the Center Plain Science and Technology Innovation Talents(No.194200510016)the Science and Technology Innovation Team Project of Henan Province University(No.19IRTSTHN013)the Key Scien-tific Research Support Project for Institutions of Higher Learning in Henan Province(No.18A413014)。
文摘The research purpose was to improve the accuracy in identifying the prosthetic leg locomotion mode.Surface electromyography(sEMG)combined with high-order zero-crossing was used to identify the prosthetic leg locomotion modes.sEMG signals recorded from residual thigh muscles were chosen as inputs to pattern classifier for locomotion-mode identification.High-order zero-crossing were computed as the sEMG features regarding locomotion modes.Relevance vector machine(RVM)classifier was investigated.Bat algorithm(BA)was used to compute the RVM classifier kernel function parameters.The classification performance of the particle swarm optimization-relevance vector machine(PSO-RVM)and RVM classifiers was compared.The BA-RVM produced lower classification error in sEMG pattern recognition for the transtibial amputees over a variety of locomotion modes:upslope,downgrade,level-ground walking and stair ascent/descent.
