Workspace analysis of parallel mechanisms through neural networks and genetic algorithms

Abstract

Stewart Platform Mechanism (SPM) is a type of parallel mechanism (PM) which has 6 degrees of freedom. Due to features like precise positioning and high load carrying capacity, PMs have been used in many areas in recent years. But relatively small workspace of the mechanism is the major disadvantage. This paper aims to improve the method for PM workspace analysis. The structure of Artificial Neural Network (ANN) which was used to analyze 6×3 SPM's workspace, is determined by Genetic Algorithms (GA). This structure of ANNs, i.e., weights, biases are very effective on catching highly accurate results of the ANNs. Therefore, calculation of these values and appropriate structure, i.e., number of neurons in hidden layers, by trial and error approach, results in spending too much time. To prevent the loss time and to determine the problem most fitted structure of hidden layers, a GA is developed and tested in simulation environment, i.e., software developed data. It is noted that by using software-calculated-parameters instead of using trial-error-approach parameters gives the user as accurate as trial-error-approach in short time span.