Forward kinematics of the Stewart platform using hybrid immune genetic algorithm

Abstract

The Stewart platform's unique structure presents an interesting problem in its forward kinematics (FK) solution. It involves the solving of a series of simultaneous non-linear equation and, usually, non-unique, multiple sets of solutions are obtained from one set of data. In addition, most effort has been done in solving the forward kinematics solution of the Stewart platform by means of numerical methods. This paper presents a hybrid immune algorithm (IA), genetic algorithm (GA) and fuzzy system (FS) method for solving the FK problem of the Stewart platform. First, we combined the IA and GA, then we added the fuzzy system approach. The penalty function was also considered in the solution. This hybrid system was then used to solve the FK problem. Numerical simulations were carried out using a series discrete points, the results showed good optimization. A comparison with standard genetic algorithm (SGA) and IGA combined with the FS (IGAFS) was carried out. The result show that the IGAFS cost much fewer time than SGA under the same condition. The result demonstrated the accuracy of the proposed IGAFS approach