Planetary gear pair design using metaheuristic algorithms

Abstract

This paper considers the problem of formulating the non-linear optimization model for determining the optimal parameters of planetary gearbox, which is solved using a metaheuristic optimization algorithm. To determine the optimal parameters of the planetary gearbox it is necessary to formulate complex objective functions and minimize them, which is often a conflicting problem. To solve this complex optimization problem, in this paper we propose to employ metaheuristic algorithms, which characterize pseudo-randomness and the ability to find the global optimal solution to the multimodal optimization problems. The proposed metaheuristic method is based on the Genetic Algorithm (GA) which is hybridized with the local-search Nelder-Mead method. For the considered optimization problem, the appropriate software is implemented in the MATLAB software package, to verify the results. Inside the considered optimization module, we have defined the appropriate objective functions and constraints which determine the construction of the planetary gearbox. The optimal parameters of the planetary gearbox obtained using the proposed metaheuristic algorithm are compared with the results obtained using several well-known algorithms in the literature. The simulation results of the proposed optimization method indicate a significant improvement in planetary gearbox performance compared to the parameters obtained with well-known algorithms.