Title :
Sensitivity analysis of a planar mechanism using neural network
Author :
Xu, W.L. ; Yang, T.W. ; Wang, X.S.
Author_Institution :
Centre for Intelligent Design, Autom. & Manuf., City Univ. of Hong Kong, Kowloon, Hong Kong
Abstract :
A planar four-bar mechanism is one of the most useful and simplest mechanisms used in mechanical systems, whose accuracy makes significant contributions to the machinery precision. The manufacturing error and assembly error involved in a linkage mechanism must be controlled in order to satisfy the accuracy specification. Since the linkage parameters deviate from their nominal value due to the above mechanical errors, sensitivity has to be studied for evaluating the effect of these deviations on the kinematics performance of the mechanism. In this study a neural-network-based approach is proposed to analyze the static transmission accuracy of a four-bar mechanism and investigate the sensitivity of each link error to the total precision of the mechanism
Keywords :
kinematics; mechanical engineering computing; neural nets; sensitivity analysis; assembly error; kinematics performance; linkage mechanism; manufacturing error; neural-network-based approach; planar four-bar mechanism; sensitivity analysis; static transmission accuracy; Assembly; Couplings; Error correction; Kinematics; Machine intelligence; Manufacturing; Mechanical systems; Neural networks; Neurons; Sensitivity analysis;
Conference_Titel :
Systems, Man, and Cybernetics, 1997. Computational Cybernetics and Simulation., 1997 IEEE International Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-4053-1
DOI :
10.1109/ICSMC.1997.635311