پديدآورندگان :
Agand Pedram p.agand.eng@ieee.org Student Member, IEEE , Advanced Robotics and Automation System (ARAS), Industrial Control Center of Excellence (ICEE), K.N. Toosi University of Technology , Aliyari Shoorehdeli Mahdi aliyari@kntu.ac.ir Senior Member, IEEE , APAC Group, Department of Mechatronics Engineering, K.N. Toosi University of Technology, Tehran, Iran , Teshnehlab Mohammad teshnehlab@eetd.kntu.ac.ir Industrial Control Center of Excellence (ICEE), Faculty of Electrical Engineering, K.N. Toosi University of Technology, Tehran, Iran
كليدواژه :
Neural Networks , Robot Dynamic Identification , Transparent and Flexible Network , Twin Rotor Helicopter
چكيده فارسي :
Inthispaper,anovelarchitectureinmultilayerperceptron (MLP) neural network with flexible activation function and adaptive learning rate is presented for a data-driven identification of robot dynamics. It is assumed that the measurement of robotend-effectorposition,velocityandaccelerationareavailable corrupted by Gaussian noise. Since some general property of robot dynamics are included in the proposed structure as well as optimization indices, this structure is envisaged having good performance in confronting with uncertainty in measurements. The main contribution of this paper is to propose a transparent neural network structure for identification of dynamic terms by introducing a gray-box identifier. Simulation results on 2-DOF serial manipulator reveal the accuracy of the method. Finally, experimental results on a laboratory-scaled twin rotor CE 150 helicopter indicate the applicability of the proposed method.
