基于神经网络的车辆主减速器混合遗传算法优化设计

Genetic algorithm optimization on automobile final drive based on neural network

车辆驱动桥的组成包括主减速器、差速器和半轴,其中汽车主减速器的结构和尺寸极大的影响着汽车的动力学性能和经济性,因此采用优化设计方法来设计汽车主减速器是非常重要的。在满足主减速器接触强度、弯曲强度和边界约束的条件下,建立了优化设计数学模型。由于传统的优化方法存在着求解过程复杂和寻优过程容易陷入局部最优解的问题,故通过神经网络方法拟合待求系数,应用遗传算法工具箱调用混合遗传算法寻求最优解,使求解过程得到简化,确保可靠地获得全局最优解。

The structure and size of final drive can affect the dynamic and economic of Automobile greatly,therefore it is very important to adopt optimization methods to design the automobile final drive.Being satisfied with the contact strength of gears,tooth beam strength of gears and boundary constraints conditions,the optimization mathematical model is created which is to minimize the volume sum of pitch circle cylinder of gearsets.Considering the problem of low efficiency and local optimum caused by traditional optimal methods,the hybrid Genetic Algorithm are adopted to solve the optimization model,and neural network method is applied to fit coefficient.So that the optimization process is simplified and global optimum is acquired reliably.