2003, Volume 5, Issue 7
Strategic Study of CAE >> 2003, Volume 5, Issue 7
Research on the Forecast of the BP Neural Network Based on the Orthogonal Test
Department of Technical Engineering, Southeast University , Nanjing 210096, China
Next Previous
Abstract
The strategy for forecasting the BP neural network was researched on the basis of the training-studying samples that were obtained in the orthogonal test of L9（34). The self-contained orthogonal sample was the basic training and studying cell. When others samples were added into the self-contained orthogonal samples or the self-contained orthogonal samples were cut down, the forecasting results were completely irresponsible. On the same test condition and orthogonal test type, the self-contained orthogonal sample with large information content could forecast that with small information content at high precision. A new test-design approach was put forward. Namely, the self-contained orthogonal sample was obtained through the orthogonal test, and then, the values of all other samples whose factors were the same as that of the self-contained orthogonal sample could be forecast in the BP neural network and its precision was considerable high. Therefore, the time and labors were enormously saved.
Keywords
BP neural network ; orthogonal test ; strategy ; design-test approach ; sample collection
Figures
图1
图2
References
[ 1 ] 从爽.基于METLAB的神经网络原理及应用[M].合肥:中国科技大学出版社,1998.1~10
[ 2 ] 王昌龙,黄惟一.用神经网络法预测集装箱角绘钥件的力学性能[J]铸造,2002,51(4):232~235
[ 3 ] 徐建林,陈超,王智平,等.基于MATLAB的铸件缺陷分析与控制[]]铸造,2002,51(6):362一265
[ 4 ] 路阳,王智平,刘在德,等.混合遗传算法在灰铸铁件缺陷诊断神经网络模型中的应用[J]铸造,2002,51(3):177一179
[ 5 ] 蔡热东,许伟杰,陈念贻.自组织人工神经网络在氰化物非品态形成的判别条件中的应用[J]无机化学学报,1994,10(2):151~154
京公网安备 11010502051620号
