oalogo2  

AUTHOR(S): 

Sahin Yildirim

 

TITLE

Force Analysis of a Modified Mechanism System Using Artificial Neural Networks

pdf PDF

KEYWORDS

Four-bar mechanism, artificial neural network, force, spring

ABSTRACT

In this investigation, kinematic parameters variations of a proposed four-bar mechanism are analysed using a proposed recurrent artificial neural network predictor. The proposed neural predictor has three layers, which are input layer, output layer and hidden layer. The hidden layer consisted of recurrent structure to keep dynamic memory for later use. The mechanism is an extended version of a four-bar mechanism. Two elements, spring and viscous, are employed to overcome big force problem on the mechanism. Based on the results presented, the force analysis problem for four-bar mechanism is completely solvable by using artificial neural networks. The effectiveness of the proposed scheme is demonstrated by simulation results in high speed repetitive motion tracking and load change conditions. No prior knowledge of system dynamics is required for this scheme.

Cite this paper

Sahin Yildirim. (2016) Force Analysis of a Modified Mechanism System Using Artificial Neural Networks. International Journal of Control Systems and Robotics, 1, 162-168