Adaptive recurrent neural network with Lyapunov stability learning rules for robot dynamic terms identification. (October 2017)

• Record Type: Journal Article
• Authors: Agand, Pedram; Shoorehdeli, Mahdi Aliyari; Khaki-Sedigh, Ali
• Is Part Of: Engineering applications of artificial intelligence. Volume 65(2017:May)
• Page Start: 1
• Page End: 11
• Publication Date: 2017-10
• Subjects: Neural networks -- Recurrent networks -- Lyapunov function -- Adaptive learning algorithms -- Helicopter; Engineering -- Data processing -- Periodicals; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Ingénierie -- Informatique -- Périodiques; Intelligence artificielle -- Périodiques; Systèmes experts (Informatique) -- Périodiques; Artificial intelligence; Engineering -- Data processing; Expert systems (Computer science); Periodicals; 620.00285
• DOI: 10.1016/j.engappai.2017.07.009
• Languages: English
• ISSNs: 0952-1976

Abstract

Abstract: In this paper, a recurrent neural network coupled with Kalman filter is proposed to identify dynamic terms of robotic manipulator. By cooperating some inherent characteristics of robot, this network has the capability to individually identify nonlinear terms using Weighted Augmentation Error (WAE). To present the infrastructure of architecture, an adaptive scheme based on the conventional Back Propagation (BP) is firstly driven using the Gradient Descent (GD) method. Additionally, a stable adaptive updating rule is extracted from the discrete time Lyapunov candidate as an approach for the general nonlinear system identification. Then, this approach is applied to the predefined network. To experimentally validate the computational efficiency and control applicability of the proposed method, Adaptive Neural Network Based Inverse Dynamic Control (ANN-Based-IDC) is employed on a laboratory-scaled twin-rotor CE-150 helicopter. This experiment illustrates enhancement of steady-state performance from 2-to-3 times more in compared with simple PID. Moreover, disturbance rejection and robustness tests admit capability of the method for online dynamic identification in the presence of output and dynamic perturbation. Highlights: A method for individually identifying nonlinear terms of robot dynamics is proposed. Defining weighted augmentation error confines feasible solution to a convex subset. Recurrent network is utilized to facilitate regression availability conditions. A novel stable adaptive learning rule is extracted from discrete time Lyapunov. Experimental validation on a twin-rotor helicopter illustrates the method efficiency.