论文部分内容阅读
提出了一种基于误差修正在线贯序超限学习机集成(EOS-ELM)的滑坡位移预测模型.预测过程中对滑坡位移时间序列进行了趋势项和周期项分解,分别考虑了不同的影响因子对滑坡趋势项位移和周期项位移的影响.利用在线贯序超限学习机(OS-ELM)算法分别对趋势项位移和周期项位移建模预测.采用集成预测的思想提高OS-ELM模型的泛化能力,同时为了进一步提高预测精度,提出了一种在线误差修正预测方法.该方法通过对误差序列进行建模预测,修正最终的预测结果.以三峡库区白水河滑坡为例,实验验证了提出方法的有效性.
This paper proposes a landslide displacement prediction model based on error correction online sequence overrun learning machine integration (EOS-ELM). During the forecasting process, the trend term and periodic term term of landslide displacement time series are decomposed respectively considering different influencing factors On the trend of displacement and periodic term displacement of landslide.The OS-ELM algorithm is used to predict the displacement of displacement term and the displacement of periodic term separately.The integrated prediction method is used to improve the OS-ELM model At the same time, in order to further improve the prediction accuracy, an online error correction prediction method is proposed in this paper, which can correct the final prediction result by modeling and forecasting the error sequence.Taking Baishuihe landslide in the Three Gorges reservoir area as an example, The effectiveness of the proposed method.