航天推进技术研究院主办
Li Feng Yuan Junshe.Application of BP neural network in characteristics identification of frame structure[J].Journal of Rocket Propulsion,2009,35(04):30-33.
BP神经网络在结构边界参数识别中的应用
- Title:
- Application of BP neural network in characteristics identification of frame structure
- Keywords:
- frame of rocket motor; stiffness boundary; characteristics identification; BP neu— ral network
- 分类号:
- V434
- 文献标志码:
- A
- 摘要:
- 针对建立发动机动力学模型过程中,试车台机架结构边界环境的不确定状况, 对神经网络在边界刚度识别中的应用进行了研究。以结构模态频率为网络输入,边界X、y、 Z方向的刚度为输出.通过一种增加训练样本的方法大大提高了网络的映射性能,最终的识别 结果达到了预期目标。满足工程需要。
- Abstract:
- Because of the boundary condition uncertainty for the fhme structure of rocket en— gine in establishing the dynamic model of engine,the characteristics of structural stiffness boundary will be identified with neural network in this paper.It would take the modal frequencies of engine inputs,and the X、Y、Z—axis of stiffness boundary as outputs.Then the way of adding training samples improve the learning speed and mapping capability.Finally,the results reach the prospec— tire goal,and the FEM(Finite Element Method)calculations can meet the engineering requirements.
参考文献/References:
[l]Akihiro Suzuki,Keisuke Kamiya.Identification Technique
for Nonlinear Boundary Conditions of a Circular Plate.
Journal ofSound and Vibration,2006(289):130-147.
[2]彭岚,何大鹏,李友荣.基于BP神经网络的工业锅炉
房负荷预测[J].工业加热,2005,35(5):31-33.
[3]Chang C C,Chang T Y P,Xu Y G.Adaptive Neural
Networks for Model Updating of Structures[J].Smart
Mater.Struet,2000(9):59-68.
[4]朱曙光,义永光,谭俊杰,刘心志.气体火焰燃烧状态
在线识别和预报[J].南京理工大学学报:自然科学版,
2008.32(4):468-471.
[5]Xu Y G,“u G R Adaptive Multilayer Perception Networks
for Detection of Cracks in
Anisotropie
Laminated Plates
[J].International Journal of Solids and Structures,2001
(38):5625—5645.
备注/Memo
收稿日期:2009-03—30;修回日期:2009—07—03。 作者简介:李锋(1963一),女,研究员,研究领域为液体火箭发动机强度理论与试验。