基于神经网络和遗传算法的两跨箱形结构优化设计

Optimal design of two-span box structure based on neural network and genetic algorithm

运用Ansys命令流和均匀试验的设计方法为神经网络训练提供样本数据,通过遗传算法和神经网络的有效结合,成功地解决了约束结构优化问题,验证了应用神经网络和遗传算法的协同优化方法进行结构优化设计的可行性和实用性。

The design method of Ansys command stream and uniform experiment is used to provide sample data for the neural network training,and the problem of optimizing the constrained structure is successfully solve by effectively combining the genetic algorithm and the neural network. The feasibility and practicability of the optimal structural design is verified using the collaborative optimization method of the neural network and the genetic algorithm.