4TH International Congress on Technology - Engineering & SCIENCE - Kuala Lumpur - Malaysia (2017-08-05)

Optimization Of Epicyclical Gear Train And Shaft Diameter Through Genetic Algorithm

Determination of volume or weight of a gearbox is an important task in preliminary design of power transmission application. Gears are used in most types of machinery and vehicles for the transmission of power, the design of gears is highly complicated involving the various conflicting, dependent parameters and constraints witch need to be analyzed during its design and manufacturing [1, 2, 3, 13]. So, using conventional optimization techniques is not a good solution for optimization. In this study, the dimensional optimization components of gearbox is performed by the non-traditional technique called Genetic Algorithm (GA) [4, 7, 10]. It is referred to as a search method of optimal solution to simulating Darwin's genetic selection and biological evolution process. Genetic algorithm is a series of random iterations and evolutionary computations simulating the process of selection, crossover and mutation occurred in natural selection and population genetic, in according to the survival of the fittest, through crossover and mutation, good quality gradually maintained and combined, while continually producing better individuals and out of bad individuals [5, 6, 14, 16]. The GA is aimed to obtain the optimal dimensions for gears and gearbox shaft with respect of bending strength constraint, contact stress constraint, balance constraints for the planetary gear train and dimension constraints for gears. The non-conventional genetic algorithm was applied to a gearbox with two stage, one was an epicyclical gear train with spur gears and the second one was a simple gear train [9, 15]. The results of the genetic algorithm are obtained by using MATLAB Software [12, 17, 18]. The weight is reduced by an important value compared the initial model, and the parameter like module, shaft diameter, number of teeth and the tooth width are optimized. These obtained results indicate that GA can be used reliably in machine element design problems [8,11,19,20].
Kaoutar Daoudi, El Mostapha Boudi