6055

5664

كارشناسي ارشد

طراحي كاربردي

اصفهان: دانشگاه صنعتي اصفهان، دانشكده مكانيك

1389

هجده،94ص.: مصور،جدول،نمودار

ص.ع.به فارسي و انگليسي

مهدي كشميري

محمد جعفرصديق

7/4/90

سعيد بهبهاني، محمد دانش

مهندسي مكانيك

ID5664

به فارسي و انگليسي: قابل رويت در نسخه ديجيتالي

Design of Robust Neural Network Based on Hybrid Force Position Controller for a Robot Manipulator Mohammad Hossein Ghajar m ghajar@me iut ac ir Date of Submission 2011 04 19 Department of Mechanical Engineering Isfahan University of Technology Isfahan 84156 83111 Iran Degree M Sc Language FarsiSupervisor Mehdi Keshmiri mehdik@cc iut ac ir Abstract A constrained robot manipulator with contact friction between its end effector and environment isconsidered A new intelligent hybrid position force controller is designed The controller includes two majorparts The first part which is called the main controller consists of two closed loops corresponding to motiontracking and force tracking objectives In each loop the decoupled governing equations of the system areinitially linearized using a feedback linearization approach then the linearized loop is controlled by a linearcontroller The second part which is called the tuning controller is an adaptive neural network NN controller to compensate the model based deficiencies of the first part The main contribution of this paper isto improve the model based controller by use of the neural network controller in the presence of some sortof uncertainties in the system modeling The stability condition of the closed loop system is approved byusing the Lyapunov passivity and Linear Matrices Inequalities theorems The performance of the modifiedcontroller is simulated for a two link robot manipulator which interacts with a horizontal surface The resultsshow an excellent enhancement in control strategy by using neural network controller The new controller is implemented on a real two link robot manipulator experimentally In order toaccomplish this implementation first the LuGre parameters are identified by a separate setup which wasbuilt to emulate the end effector and surface friction Then parameters are then utilized in the manipulatorcontroller Experimental showed a very outstanding performance for the added NN controller in the controlof the system especially in the end effector position control Keywords Constrained Robot Manipulator Hybrid Force and Position Control Linear Matrix inequality LMI NeuralNetwork NN

مهدي كشميري

محمد جعفرصديق

سعيد بهبهاني، محمد دانش