Lectotype Optimization of Single-Layer Cylindrical Shell Based on BP Neural Network Method

Sample database was established and the mapping relationship between span,rise-span ratios and type of shell with minimum weight was simulated by using BP neural network method. The selected typical samples were chosen from hundreds of sectional optimized results based on sequential two-level algorithm from five typical types of reticulated domes. This paper provides a simple lectotype optimization method of Single-layer cylindrical shell which was based on BP neural network.

[1]  Paul J. Werbos,et al.  The Roots of Backpropagation: From Ordered Derivatives to Neural Networks and Political Forecasting , 1994 .

[2]  Malik Magdon-Ismail,et al.  No Free Lunch for Early Stopping , 1999, Neural Computation.

[3]  Oleksandr Makeyev,et al.  Neural network with ensembles , 2010, The 2010 International Joint Conference on Neural Networks (IJCNN).