| 滑坡预报的BP-GA混合算法 |
| |
| 引用本文： | 吴承祯,洪伟.滑坡预报的BP-GA混合算法[J].山地学报,2000,18(4):360-364. |
| |
| 作者姓名： | 吴承祯 洪伟 |
| |
| 作者单位： | 福建林学院,福建,南平,353001 |
| |
| 基金项目： | 福建省自然科学基金资助项目(F991)。 |
| |
| 摘 要： | 提出了滑坡位移预报的一种改进人工神经网络方法－ＡＮＮ－ＧＡ法，与传统的人工神经网络方法相比，该方法加快一网络的学习速度，提高了滑坡位移的预报精度。同时它是一种面向数据的方法，适合于不同地区不同条件下滑坡的预报。两例滑坡预报平均相对误差分别为３．５５％和１．９３％，明显估于传统的ＢＰ算法（分别为１１．３５％和７．２４％）及ＧＰ改进方法（分别为３．９６％和２．６５％），表明该方法具有科学性、可行性和有
|
| 关 键 词： | 滑坡预报 人工神经网络 遗传算法 |
| 修稿时间： | 1999－06－23 |
BP-GA MIXED ALGORITHMS FOR LANDSLIDE PREDICTION |
| |
| WU Cheng-zen,HONG Wei.BP-GA MIXED ALGORITHMS FOR LANDSLIDE PREDICTION[J].Journal of Mountain Research,2000,18(4):360-364. |
| |
| Authors: | WU Cheng-zen HONG Wei |
| |
| Abstract: | In this paper,a modified method(ANN_GA)for landslide prediction is presented,which can quicken the learning speed of network and improve the predicting precision compared with the traditional artificial neural network.One of the important charcteristics of the ANN_GA method is its ability to generalize the input/output behaviors of functions based on a set of training examples,which is suitable for landslide prediction in different areas and conditions.The studies on landslide cases show that the mean relative precision of BP_GA mixed algorithms is 3 55% and 1 93% respectively, which is significantly better than those of BP traditional algorithms(its mean relative precision is 11 35% and 7 24% respectively)and GP modified algorithms(its mean relative precision is 3 96% and 2 65%, respectively). |
| |
| Keywords: | landslide prediction artificial network genetic algorithms |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
