摘要
运用改进的BP-NN,构建了三峡库区滑坡稳定性分析的神经网络方法,并选择30个三峡库区典型滑坡作为样本及算例,BP-NN方法同传递系数法分析结果的对比表明,本方法具有较好的可靠性。此外,本方法输入参数易得,对勘察质量和滑带土等参数依赖小,且简便易行,为三峡库区滑坡稳定性分析提供了新的途径,尤其适宜于三峡库区滑坡详勘前的稳定性预判。
Using the revised BP - NN, this paper presented the neural network method for landslide stability analysis in the Three Gorges area. By choosing 30 typical landslides in this area as examples, the stability state estimated by the revised BP - NN method is highly consistent to that by conventional transfer coefficient method. And the method presented in this paper has following advantages：the input parameters are easily obtained and this method does not deeply rely On investigation quality and shear strength parameters of slips and is a quite simple one. The BP - NN method is a new measure to stability analysis of landslides in the Three Gorges area, which is especially suitable to the stability prediction of landslides before investigation.
出处
《重庆建筑大学学报》
EI
CSCD
北大核心
2006年第6期38-41,83,共5页
Journal of Chongqing Jianzhu University
基金
国家科技攻关重大项目(2004BA901A02)
重庆市重点自然科学基金项目(2005BA7008)
关键词
三峡库区
滑坡
稳定性分析
改进BP-NN
Three Gorges area
landslide
stability analysis
revised BP - NN method
