As we all know, rigid structure is the universal form of robots. They can be controlled accurately, but are not suitable enough for applying in rehabilitation, especially for hands. Human's hands have some complic...
详细信息
ISBN:
(纸本)9781479970995
As we all know, rigid structure is the universal form of robots. They can be controlled accurately, but are not suitable enough for applying in rehabilitation, especially for hands. Human's hands have some complicated patterns of movement and narrow joint range of motion, so rigid accessory equipment may cause secondary injury. For the purpose of avoiding this potential risk, the idea of applying soft structure to hand rehabilitation robot is presented in this paper. The soft robot is a new research direction in the field of robot industry, especially in rehabilitation. The soft actuator we presented is made of liquid silicone and thread, and can be tied to the back of human's hands. When it is inflated or deflated, a bending and stretching motion of hands follow with the deformation of soft actuators. It works by deforming repeatedly. The soft actuator has some advantages such as portable, lightweight, low-cost, safe, low-impedance and so on. It works well by the cooperation of vacuum pump which can provide incessant air and solenoid valve which is used for reversing. In the whole system, force sensing resistor and bending sensor are used in the experiments. In order to prove that the soft actuator can work smoothly, we had a test to explore the relationship between air inflow and bending angle. The result that their relationship is close to a straight line means controlling easily and working well. Beacons of these advantages the soft robots have, a wide application prospect in rehabilitation or other fields is available.
According to the limitations and shortcomings of BP neural network in estimating the battery state of charge(State of Charge, SOC), such as slow convergence speed and poor generalization, this paper puts forward an im...
详细信息
ISBN:
(纸本)9781479939800
According to the limitations and shortcomings of BP neural network in estimating the battery state of charge(State of Charge, SOC), such as slow convergence speed and poor generalization, this paper puts forward an improved BP neural network method of battery SOC estimation. Train the improved BP neural network with the experimental data. It compares the trained neural network of SOC with the real values, and uses Matlab to simulate in order to verify the correctness of the algorithm.
In this paper, a novel over-constrained three degree-of-freedom (DOF) spatial parallel manipulator (SPM) is proposed. The architecture of the SPM is comprised of a moving platform attached to a base through two revolu...
详细信息
ISBN:
(纸本)9781479939800
In this paper, a novel over-constrained three degree-of-freedom (DOF) spatial parallel manipulator (SPM) is proposed. The architecture of the SPM is comprised of a moving platform attached to a base through two revolute- prismatic-universal jointed serial linkages and one spherical-prismatic-revolute jointed serial linkage. The prismatic joints are considered to be actively actuated. Kinematics and dynamics of the SPM are studied systematically. Firstly, both of the inverse and forward displacements are derived by analytic formulae. Then, the velocities and the accelerations of the moving platform and each limb are obtained. Finally, dynamics of the mechanism is derived based on the principal of the virtual work. The results are illustrated by numerical examples.
暂无评论