Matching Optimization for Tractor Powertrain Based on Improved NSGA-Ⅱ Algorithm

FU Shenghui;LI Zhen;DU Yuefeng;MAO Enrong;ZHU Zhongxiang;College of Engineering,China Agricultural University;Beijing Key Laboratory of Optimized Design for Modern Agricultural Equipment;

tractor powertrain;;matching optimization;;drive power loss rate;;specific fuel consumption loss rate;;improved non-dominated sorting genetic algorithm-Ⅱ

In order to optimize matching of the tractor powertrain and improve the power and fuel economy of the tractor,a new matching optimization method for tractor powertrain was put forward based on the improved non-dominated sorting genetic algorithm-Ⅱ. The normal distribution crossover operator(NDX) was introduced to expand the spatial search range on the premise of ensuring the quality of the non-dominated solution set. And meanwhile,the differential evolution mutation operator based differential evolutionary algorithm was used as directional guiding ideology to avoid falling into the local optimum and improve the uniformity of population distribution. Subsequently,by analyzing the design requirements and power-shift transmissions produced by New Holland,Case IH and John Deere,the optimization model of transmission ratios was established with constraints such as vehicle speed,ratio of gear ratios,driving adhesion restriction,and so on. In this model,gear ratios were taken as input variables,and the optimization objective was to get the lowest drive power loss rate and the lowest specific fuel consumption loss rate. The proposed algorithm was used to optimize the tractor powertrain and compared with the original NSGA-Ⅱ and the weighted genetic algorithm. The experimental results showed that the distributed index SP of the proposed algorithm was smaller than that of the original NSGA-Ⅱ,which meant that the improved NSGA-Ⅱ could obtain a more uniformly distributed and precise optimal solutions. And after optimization of the improved NSGA-Ⅱ,the drive power loss rate and the specific fuel consumption loss rate of the tractor could be theoretically reduced by 41. 62% and 62. 8%,respectively,and the climbing angle of the first transport gear could be increased by 2. 35% than before,which was better than NSGA-Ⅱ and the weighted genetic algorithm. The overall performance of the tractor was improved obviously which verified the effectiveness of the improved NSGA-Ⅱ algorithm. To sum up,this method could provide a certain reference for the design and optimization of the tractor transmission.