Abstract:Purpose
The purpose of this paper is to accurately obtain the deformation of a hybrid robot and rapidly enable real-time compensation in friction stir welding (FSW). In this paper, a prediction algorithm based on the back-propagation neural network (BPNN) optimized by the adaptive genetic algorithm (GA) is presented.
Design/methodology/approach
Via the algorithm, the deformations of a five-degree-of-freedom (5-DOF) hybrid robot TriMule800 at a limited number of positions are taken as the training set. The cu… Show more
“…The GA and PSO is characterized by rapid convergence and robustness, so they are selected to optimize the BPNN mapper (Sun et al , 2020; Sutyasadi and Parnichkun, 2020). The fitness function of GA and PSO are shown in equation (12).…”
Section: Optimization Of Back-propagation Neural Network Mappermentioning
Purpose
To achieve stable gait planning and enhance the motion performance of quadruped robot, this paper aims to propose a motion control strategy based on central pattern generator (CPG) and back-propagation neural network (BPNN).
Design/methodology/approach
First, the Kuramoto phase oscillator is used to construct the CPG network model, and a piecewise continuous phase difference matrix is designed to optimize the duty cycle of walk gait, so as to realize the gait planning and smooth switching. Second, the mapper between CPG output and joint drive is established based on BP neural network, so that the quadruped robot based on CPG control has better foot trajectory to enhance the motion performance. Finally, to obtain better mapping effect, an evaluation function is resigned to evaluate the proximity between the actual foot trajectory and the ideal foot trajectory. Genetic algorithm and particle swarm optimization are used to optimize the initial weights and thresholds of BPNN to obtain more accurate foot trajectory.
Findings
The method provides a solution for the smooth gait switching and foot trajectory of the robot. The quintic polynomial trajectory is selected to testify the validity and practicability of the method through simulation and prototype experiment.
Originality/value
The paper solved the incorrect duty cycle under the walk gait of CPG network constructed by Kuramoto phase oscillator, and made the robot have a better foot trajectory by mapper to enhance its motion performance.
“…The GA and PSO is characterized by rapid convergence and robustness, so they are selected to optimize the BPNN mapper (Sun et al , 2020; Sutyasadi and Parnichkun, 2020). The fitness function of GA and PSO are shown in equation (12).…”
Section: Optimization Of Back-propagation Neural Network Mappermentioning
Purpose
To achieve stable gait planning and enhance the motion performance of quadruped robot, this paper aims to propose a motion control strategy based on central pattern generator (CPG) and back-propagation neural network (BPNN).
Design/methodology/approach
First, the Kuramoto phase oscillator is used to construct the CPG network model, and a piecewise continuous phase difference matrix is designed to optimize the duty cycle of walk gait, so as to realize the gait planning and smooth switching. Second, the mapper between CPG output and joint drive is established based on BP neural network, so that the quadruped robot based on CPG control has better foot trajectory to enhance the motion performance. Finally, to obtain better mapping effect, an evaluation function is resigned to evaluate the proximity between the actual foot trajectory and the ideal foot trajectory. Genetic algorithm and particle swarm optimization are used to optimize the initial weights and thresholds of BPNN to obtain more accurate foot trajectory.
Findings
The method provides a solution for the smooth gait switching and foot trajectory of the robot. The quintic polynomial trajectory is selected to testify the validity and practicability of the method through simulation and prototype experiment.
Originality/value
The paper solved the incorrect duty cycle under the walk gait of CPG network constructed by Kuramoto phase oscillator, and made the robot have a better foot trajectory by mapper to enhance its motion performance.
“…With the rapid development of the manufacturing industry, hybrid robots have been more and more used in processing and manufacturing (Zieliński et al , 2003; Sun et al , 2020; Petko et al , 2016), such as grinding, owing to their parallel mechanisms with high rigidity and strong load capacity (Wu et al , 2017; Wu et al , 2018). For the generation of robot grinding trajectory, the commonly used method is obtained by commercial computer aided manufacturing (CAM) software (such as Unigraphics, computer aided tri-dimensional application interface, Power Mill) according to the equal chord height error constraints and post-processing (Liu et al , 2019; Käsemodel et al , 2020; Nagata et al , 2013).…”
Purpose
The purpose of this paper is to generate grinding trajectory of unknown model parts simply and efficiently. In this paper, a method of grinding trajectory generation of hybrid robot based on Cartesian space direct teaching technology is proposed.
Design/methodology/approach
This method first realizes the direct teaching of hybrid robot based on 3Dconnexion SpaceMouse (3DMouse) sensor, and the full path points of the robot are recorded in the teaching process. To reduce the jitter and make the speed control more freely when dragging the robot, the sensor data is processed by Kalman filter, and a variable admittance control model is established. And the joint constraint processing is given during teaching. After that, the path points are modified and fitted into double B-splines, and the speed planning is performed to generate the final grinding trajectory.
Findings
Experiment verifies the feasibility of using direct teaching technology in Cartesian space to generate grinding trajectory of unknown model parts. By fitting all the teaching points into cubic B-spline, the smoothness of the grinding trajectory is improved.
Practical implications
The whole method is verified by the self-developed TriMule-600 hybrid robot, and it can also be applied to other industrial robots.
Originality/value
The main contribution of this paper is to realize the direct teaching and trajectory generation of the hybrid robot in Cartesian space, which provides an effective new method for the robot to generate grinding trajectory of unknown model parts.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.