Purpose -This paper aims to combine and further develop different mathematical models of the workspace representation of 6 degrees of freedom parallel mechanisms and to bring a new point of view to existing workspace analysis methods through using neural networks (NN). Design/methodology/approach -For the orientation workspace of the 6-3 SPM, discretization method is used which is based on Euler angles and the NN algorithm is applied. Findings -The workspace analysis is carried out in the direction perpendicular to the moving platform which is the most workable direction of 6-3 Stewart platform mechanisms and NN algorithm has decreased processing time. Originality/value -The determination of the point, on that direction, at which the workspace is maximum, is outlined. It is the first time that the NN is used for classification of workspace of a parallel manipulator.

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 6x3 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.

The aim of this study is to present a new model to extend the workspace of a parallel working machine in a chosen direction. Therefore, the existing mathematical models are combined and developed to represent the extension of the workspace of a 6° parallel working machine. For this purpose, the 6-3 Stewart platform mechanism (SPM), which is commonly used in robotic applications, material processing, and flight simulation, and the 6-4 SPM have been chosen. Although there are many studies on parallel mechanisms, the workspace analysis of a parallel working mechanism has not yet been generalized. This study determines the workspace of a parallel working mechanism in the direction perpendicular to the moving platform, which is the most workable direction. For these types of working mechanisms, i.e. mechanical tools used for material processing that is forced to move in a certain chosen direction, the determination of the point in that direction at which the workspace is maximum has to be outlined. After carrying out a kinematic analysis, the discretization method, which is based on Euler angles, is used to represent the orientation workspace of these parallel working mechanisms. Additionally, the orientation workspaces of the 6-3 SPM and the 6-4 SPM are compared. Results are presented in a cylindrical coordinate system.