A machine learning model for regression of interrupted Surface Electromyography(sEMG)signals to future control-oriented signals(e.g.,robot’s joint angle and assistive torque)of an active biomechatronic device for hig...A machine learning model for regression of interrupted Surface Electromyography(sEMG)signals to future control-oriented signals(e.g.,robot’s joint angle and assistive torque)of an active biomechatronic device for high-level myoelectric-based hierarchical control is proposed.A Recurrent Neural Network(RNN)was trained using output data,initially obtained from offline optimization of the biomechatronic(human–robot)device and shifted by the prediction horizon.The input of the RNN consisted of interrupted sEMG signals(to mimic signal disconnections)and previous kinematic signals of the assistive system.The RNN with a 0.1-s prediction horizon could predict the control-oriented joint angle and assistive torque with 92%and 86.5%regression accuracy,respectively,for the test dataset.This proposed approach permits a fast,predictive,and direct estimation of control-oriented signals instead of an iterative process that optimizes assistive torque in the inverse dynamic simulation of a multibody human–robot system.Training with these interrupted input signals significantly improves the regression accuracy in the case of sEMG signal disconnection.This Robust Predictive Control-oriented Machine Learning(Robust-MuscleNET)model can support volitional high-level myoelectric-based control of biomechatronic devices,such as exoskeletons,prostheses,and assistive/resistive robots.Future work should study the application to prosthesis control as well as the repeatability of the high-level controller with electrode shift.The low-level hierarchical controller that manages the human–robot interaction,the assistance/resistance strategy,and the actuator coordination should also be studied.展开更多
Reaction flywheel is a significant actuator for satellites＇ attitude control. To improve output torque and rotational speed accuracy for reaction flywheel, this paper reviews the modeling and control approaches of DC...Reaction flywheel is a significant actuator for satellites＇ attitude control. To improve output torque and rotational speed accuracy for reaction flywheel, this paper reviews the modeling and control approaches of DC-DC converters and presents an application of the variable structure system theory with associated sliding regimes. Firstly, the topology of reaction flywheel is constructed. The small signal linearization process for a buck converter is illustrated. Then, based on the state averaging models and reaching qualification expressed by the Lee derivative, the general results of the sliding mode control （SMC） are analyzed. The analytical equivalent control laws for reaction flywheel are deduced detailedly by selecting various sliding surfaces at electromotion, energy consumption braking, reverse connection braking stages. Finally, numerical and experimental examples are presented for illustrative purposes. The results demonstrate that favorable agreement is established between the simulations and experiments. The proposed control strategy achieves preferable rotational speed regulation, strong rejection of modest disturbances, and high-precision output torque and rotational speed tracking abilities.展开更多
基金supported by funding from the Canada Research Chairs Program and the Natural Sciences and Engineering Research Council of Canada.The authors wish to thank Ekso Bionics Holdings Inc.for providing the Ekso EVO passive shoulder exoskeleton.
文摘A machine learning model for regression of interrupted Surface Electromyography(sEMG)signals to future control-oriented signals(e.g.,robot’s joint angle and assistive torque)of an active biomechatronic device for high-level myoelectric-based hierarchical control is proposed.A Recurrent Neural Network(RNN)was trained using output data,initially obtained from offline optimization of the biomechatronic(human–robot)device and shifted by the prediction horizon.The input of the RNN consisted of interrupted sEMG signals(to mimic signal disconnections)and previous kinematic signals of the assistive system.The RNN with a 0.1-s prediction horizon could predict the control-oriented joint angle and assistive torque with 92%and 86.5%regression accuracy,respectively,for the test dataset.This proposed approach permits a fast,predictive,and direct estimation of control-oriented signals instead of an iterative process that optimizes assistive torque in the inverse dynamic simulation of a multibody human–robot system.Training with these interrupted input signals significantly improves the regression accuracy in the case of sEMG signal disconnection.This Robust Predictive Control-oriented Machine Learning(Robust-MuscleNET)model can support volitional high-level myoelectric-based control of biomechatronic devices,such as exoskeletons,prostheses,and assistive/resistive robots.Future work should study the application to prosthesis control as well as the repeatability of the high-level controller with electrode shift.The low-level hierarchical controller that manages the human–robot interaction,the assistance/resistance strategy,and the actuator coordination should also be studied.
基金supported by the National Natural Science Foundation of China(No.61121003)
文摘Reaction flywheel is a significant actuator for satellites＇ attitude control. To improve output torque and rotational speed accuracy for reaction flywheel, this paper reviews the modeling and control approaches of DC-DC converters and presents an application of the variable structure system theory with associated sliding regimes. Firstly, the topology of reaction flywheel is constructed. The small signal linearization process for a buck converter is illustrated. Then, based on the state averaging models and reaching qualification expressed by the Lee derivative, the general results of the sliding mode control （SMC） are analyzed. The analytical equivalent control laws for reaction flywheel are deduced detailedly by selecting various sliding surfaces at electromotion, energy consumption braking, reverse connection braking stages. Finally, numerical and experimental examples are presented for illustrative purposes. The results demonstrate that favorable agreement is established between the simulations and experiments. The proposed control strategy achieves preferable rotational speed regulation, strong rejection of modest disturbances, and high-precision output torque and rotational speed tracking abilities.
