NXT* SCARA Model Based Design Controlled by Neural Network

摘要: This paper describes experimental results applying Artificial Neu ral Networks (ANNs) to perform the position control of a real SCARA man ipulator robot. approach has performed very successfully, with better obtained Radial Basis Function (RBF) networks when co mpared P controller and sliding mode positional controller. For mu lti -input lti-output (MIMO) continuous-time nonlinear systems, there are few available due difficulty in handling coupling mat rix between different inputs. A stable neural network was developed for class mult i-variable systems. The nonlinearit ies unknowns systems or controllers approximated by linearly nonlinearly parameterized networks, such as Neural (RBF NNs) Multilayer Net works (M NNs). introduction is talking about ANN wh ich can be learned many methods non linear system determine effective mputational technique structure simple possible give high efficiency classical P-controller. NXT SCA RA modeling two link planar robot arm, its kinemat ics inverse kinematics motion equations, exp lanation trajectory making edge arm.Then design, inputs, outputs how tracking NN using RBFNN that attractive problems, rapid settling t ime, no overshoot reduce error. simu lation lained which present proposed imp roves response realizes good dynamic roboustness nonlinearity self tuning without change parameters. calculated MATLAB/ SIMULINK.