High Dimensional Multi-objective Grey Optimization of Planetary Gears Type AA with Hybrid Discrete Variables

The optimal design of planetary gears is a problem with high dimensional multi-objective and with complicated calculations & constraints et al. A general method for high dimensional multi-objective optimal design is presented based on degree of grey incidence with hybrid discrete variables. Using grey degree of improved absolute incidence, multi-objective optimization design can be convened to single objective optimization. The method could reasonably deal with value adopting problems of hybrid discrete variables in optimization design. A chaos emigration operator is introduced for carrying out improvement on the fundamental genetic algorithm, and the grey compound genetic algorithmic program GSCHGA for the multi-objective optimization of hybrid discrete variables is developed. The high dimensional multi-objective optimal design example of planetary gears type AA design shows that this algorithm has no special requirements on the characteristics of optimal designing problems, it has a fairly good universal adaptability and a reliable operation of program with a strong ability of overall convergence.