三峡库区库岸堆积层滑坡变形趋势分析  

Analysis of the deformation trend of landslides in the accumulation layer on the bank of Three Gorges Reservoir area

作　　者：苗元亮 张书坤 孟超 MIAO Yuaniang;ZHANG Shukun;MENG Chao(Shandong Water Conservancy Group Co.,Ltd.,Shandong Jinan 250014,China)

机构地区：[1]山东水总有限公司,山东济南250014

出　　处：《中国地质调查》2024年第6期86-92,共7页Geological Survey of China

摘　　要：为了准确掌握三峡库区库岸堆积层滑坡的变形发展规律,基于滑坡变形监测数据,利用重标极差法、灰色模型及优化广义回归神经网络等开展滑坡变形趋势的综合研究。研究成果表明:在滑坡变形趋势判别结果中,各监测点的Hurst指数均大于0.5,得到滑坡变形具持续增加趋势;在变形预测结果中,随GM(1,1)-SFLA-GRNN模型的不断优化组合处理,预测精度明显提高,说明模型构建过程是合理的,且其预测显示滑坡变形仍会进一步增加,所得预测结果的平均相对误差介于1.76%~1.82%,训练时间介于52.21~57.23 ms,具有较优的预测效果;之后,引入BP神经网络和支持向量机,开展类比预测,发现GM(1,1)-SFLA-GRNN模型相较BP神经网络和支持向量机具有更高的预测精度及更快的训练速度,优越性显著。对比滑坡变形趋势判别结果和变形预测结果,滑坡变形仍会进一步增加且无收敛趋势,滑坡防治的必要性显著,且相互佐证了两类分析方法的合理性,为滑坡防治提供了一定的理论支持。In order to accurately grasp the deformation and development laws of landslides in the accumulation la-ger on the bank of the Three Gorges Reservoir area,the authors conducted a comprehensive study on landslide de-formation trends using the rescaled range method,grey model and optimized generalized regression neural net-work,based on the landslide deformation monitoring data.The research results show that the Hurst exponent of each monitoring point is greater than 0.5 in the landslide deformation trend discrimination results,indicating a continuous increasing trend of landslide deformation.In the deformation prediction results,with the continuous optimization and combination processing of the GM(1,1)-SFLA GRNN model,the prediction accuracy has been significantly improved,indicating that the model construction process is reasonable.Besides,its prediction shows that landslide deformation will continue to increase.The average relative error of the obtained prediction re-sults is between 1.76%and 1.82%,and the training time is between 52.21 ms and 57.23 ms,which has a bet-ter prediction effect.Then,BP neural network and support vector machine were introduced for analogical predic-tion.The results show that the GM(1,1)-SFRA-GRNN model has relatively higher prediction accuracy and faster training speed compared to BP neural network and support vector machine.Comparing the results of land-slide deformation trend discrimination and the results of deformation prediction,the authors found that landslide deformation will continue to increase without convergence trend.The necessity of landslide prevention and control is significant,and the rationality of the two analysis methods is mutually supported,providing certain theoretical support for landslide prevention and control.

关 键 词：库岸滑坡 重标极差法 变形预测 趋势分析 

分 类 号：P642[天文地球—工程地质学]