A Time Series Prediction Model of High Slope Displacement Based on Support Vector Machine and Elman Neural Network

LIU Chong; SHEN Zhen-zhong; GAN Lei; DANZENG Chi-lie; YAN Zhong-qi

doi:10.11988/ckyyb.20171018

PDF(1807 KB)

Journal of Changjiang River Scientific Research Institute ›› 2019, Vol. 36 ›› Issue (5) : 62-68. DOI: 10.11988/ckyyb.20171018

ENGINEERING SAFETY AND DISASTER PREVENTION

A Time Series Prediction Model of High Slope Displacement Based on Support Vector Machine and Elman Neural Network

LIU Chong¹, SHEN Zhen-zhong^1,2, GAN Lei^1,2, DANZENG Chi-lie¹, YAN Zhong-qi³

Author information +

History +

Abstract

A new displacement time series predicting model was proposed by integrating support vector machine (SVM) and Elman neural network, named as SVM-Elman model. In the process of measured displacement data learning, by searching the best historical step and the best prediction step, SVM model was optimized by particle swarm algorithm to dynamically forecast the trend of development. In the meantime, Elman neural network has the ability of dynamically reflecting the development trend of the absolute error of SVM model prediction. By comparing the influence of different hidden layers of Elman neural network on the prediction results, the optimal number of hidden layer was determined for SVM-Elman model and hence modifying the predicted data of SVM in real time. The proposed SVM-Elman model was applied to the strong unloading high slope on the left bank of a concrete face rockfill dam, and the prediction result was compared with that of conventional SVM. Results demonstrate that the proposed model has superior accuracy and real application value in predicting the deformations of high slope.

Key words

prediction of high slope displacement / support vector machine / Elman neural network / SVM-Elman model / particle swarm optimization algorithm / number of hidden layer

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

LIU Chong, SHEN Zhen-zhong, GAN Lei, DANZENG Chi-lie, YAN Zhong-qi. A Time Series Prediction Model of High Slope Displacement Based on Support Vector Machine and Elman Neural Network[J]. Journal of Changjiang River Scientific Research Institute. 2019, 36(5): 62-68 https://doi.org/10.11988/ckyyb.20171018

References

[1] 郝小员,郝小红,熊红梅,等. 滑坡时间预报的非平稳时间序列方法研究. 工程地质学报,1999, 7(3): 279-283.
[2] 刘冲,沈振中,甘磊,等. 基于模糊灰色聚类-组合赋权的病险水库康复度综合评价方法. 水利水电科技进展,2018, 38(3): 36-41.
[3] 沈晶鑫,房彬,郑东健,等. 基于AdaBoost集成的WPSO-RBF大坝变形监控模型. 长江科学院院报,2018, 35(5): 57-62.
[4] 秦鹏,张喆瑜,秦植海,等. 滑坡体监测数据的改进变维分形-人工神经网络耦合预测模型. 长江科学院院报,2012,29(3): 29-34.
[5] 陈昌彦,王思敬,沈小克.边坡岩体稳定性的人工神经网络预测模型.岩土工程学报,2001,23(2):157-161.
[6] 刘开云,乔春生,滕文彦. 边坡位移非线性时间序列采用支持向量机算法的智能建模与预测研究. 岩土工程学报,2004, 26(1): 57-61.
[7] 谈小龙. 基于边坡位移监测数据的进化支持向量机预测模型研究. 岩土工程学报,2009, 31(5): 750-755.
[8] VAPNIK V N. An Overview of Statistical Learning Theory. IEEE Transactions on Neural Networks, 1999, 10(5): 988-999.
[9] 江婷,沈振中,徐力群,等. 基于支持向量机-小波神经网络的边坡位移时序预测模型. 武汉大学学报(工学版),2017, 50(2): 174-181.
[10] 钱秋培,崔伟杰,包腾飞,等. 基于SVM的混凝土坝变形监控模型预测能力实例分析. 长江科学院院报,2018, 35(8): 46-50.
[11] KENNEDY J, EBERHART R. Particle Swarm Optimization∥Proceedings of IEEE International Conference on Neural Networks, Perth, November 27- December 1, 1995: 1942-1948.
[12] BRATTON D, KENNEDY J. Defining a Standard for Particle Swarm Optimization∥Proceedings of the 2007 IEEE Swarm Intelligence Symposium, Washington, April 1-5, 2007: 120-127.
[13] 徐飞,徐卫亚,刘康,等. 岩石力学性态预测的PSO-SVM模型. 岩石力学与工程学报,2009, 28(增2): 3699-3704.
[14] 郑志成,徐卫亚,徐飞,等. 基于混合核函数PSO-LSSVM的边坡变形预测. 岩土力学,2012, 33(5): 1421-1426.
[15] 张俊,殷坤龙,王佳佳,等. 基于时间序列与PSO-SVR耦合模型的白水河滑坡位移预测研究. 岩石力学与工程学报,2015, 34(2): 382-391.
[16] 姜谙男. 基于PSO-SVM非线性时序模型的隧洞围岩变形预报. 岩土力学,2007,28(6): 1176-1180.
[17] 要震,许继平,孔建磊,等. 基于GA-Elman的河流水位预测方法研究. 长江科学院院报,2018,35(9): 34-37.
[18] 吕飞,沈振中. 基于Elman神经网络的面板堆石坝沉降预测模型. 水电能源科学,2011, 29(12): 56-59.
[19] 李鹏鹏,苏怀智,郭芝韵,等. 基于人工蜂群算法与Elman神经网络的大坝变形监控模型. 水利水电技术,2017, 48(3): 104-108.