摘要
用人工神经网络算法,对某型导弹固体火箭发动机喷管防水板结构的5个参数进行了研究。模拟得到了防水板在中心受到150 mm、大小为10 t压头的最差工况下的变形与应变,并与试验对比验证数值模拟的正确性。以防水板最大主应力和最小质量为目标函数,获得了目标函数随设计变量的曲线关系,并对参数进行了灵敏度分析。优化能有效减轻防水板质量,较传统设计方法使其质量下降了45.95%,优化结果可指导发动机防水板结构的优化设计。
Five parameters of waterproof board( WB) for the SRM of some type of missile were investigated using artificial neural network algorithm( ANN). The objective function employed in the present work was the max stress and the min mass of the SRM waterproof board which bears a hydraulic pressure. The deformation and the strain of the waterproof board under the force of 10 t at center position were obtained,and the correctness of the numerical simulation was verified by comparing to the experimental results.The objective function vs. design variables curves were plotted,and the parameters sensitivity analysis were carried out. Optimization can decrease the mass of the waterproof board effectively by 45. 59% compared to traditional methods. The results obtained can be used as a guidline for the optimal structure design of the SRM waterproof board.
出处
《固体火箭技术》
EI
CAS
CSCD
北大核心
2015年第5期707-711,共5页
Journal of Solid Rocket Technology
关键词
人工神经网络算法
有限元静力分析
喷管防水板
结构优化
artificial neural network algorithm
finite element static analysis
the waterproof board of the nozzle
structure optimization