A PCA-LSTM neural network-integrated method for phreatic line prediction

doi:10.16265/j.cnki.issn1003-3033.2020.03.015

Abstract

Abstract: In order to prevent dam-breaking accidents of tailings ponds, to excavate effective information of online monitoring system and improve prediction accuracy of phreatic lines, a prediction model was set up based on PCA and LSTM neural network. Then, with Chenkeng tailings pond as an example, Pearson correlation coefficient and variable combination method were introduced to determine 18 features of model inputs, including location of phreatic line of measuring point in the first three days, location of two adjacent surrounding saturation lines, water level of ponds, longitudinal displacement of dam body and rainfall. Finally, PCA was used to eliminate data redundancy between input variables, and LSTM neural network was applied to predict location of phreatic line for the next three days. The results show that PCA-LSTM neural network-based method presents higher predication accuracy with an average absolute error of 0.011 and a decision coefficient of 0.805. And it can achieve stable prediction of phreatic lines for tailings ponds under different rainfall conditions.

Key words: tailings dam, phreatic line, principal component analysis (PCA), long short-term memory (LSTM) neural network, prediction

CLC Number:

X936

DAI Jianfei, YANG Peng, ZHU Liyi, GUO Pan, GUAN Huaiguang. A PCA-LSTM neural network-integrated method for phreatic line prediction[J]. China Safety Science Journal, 2020, 30(3): 94-101.

References

[1] 蔡嗣经, 杨鹏. 金属矿山尾矿问题及其综合利用与治理[J]. 中国工程科学, 2000,2(4): 89-92.
CAI Sijing, YANG Peng. Tailings problems and tailings utilization and treatments in the metal mines[J]. Engineering Sciences, 2000,2(4): 89-92.
[2] 王昆, 杨鹏, KAREN H E, 等. 尾矿库溃坝灾害防控现状及发展[J]. 工程科学学报, 2018,40(5): 526-539.
WANG Kun, YANG Peng, KAREN H E, et al. Current status and developing recommendations of tailings dam failure[J]. Chinese Journal of Engineering, 2018,40(5): 526-539.
[3] HUDSONEDWARDS K. Tackling mine wastes[J]. Science, 2016,352(6283): 288-290.
[4] 戴健非, 杨鹏, 王昕宇. 基于BP神经网络和SVR的Fundão尾矿坝排水数据预测对比研究[J]. 中国安全生产科学技术, 2019,15(3): 92-97.
DAI Jianfei, YANG Peng, WANG Xinyu. Prediction of Fundão dam flow data based on neural network and SVR[J]. Journal of Safety Science and Technology,2019,15(3): 92-97.
[5] 陈虎, 叶义成, 王其虎, 等. 基于ISM和因素频次法的尾矿库溃坝风险分级[J]. 中国安全科学学报, 2018,28(12): 150-157.
CHEN Hu, YE Yicheng, WANG Qihu, et al. Tailings pond dam break risk classification study based on both ISM and factor frequency method[J]. China Safety Science Journal, 2018,28(12): 150-157.
[6] 邱坤南, 沈斐敏. 小波多尺度分析的浸润线预测方法[J]. 福州大学学报:自然科学版, 2016,44(5): 746-752.
QIU Kunnan, SHEN Feimin. Research on infiltration route prediction method based on wavelet multi-resolution-analysis[J]. Journal of Fuzhou University:Natural Science Edition, 2016,44(5): 746-752.
[7] 随晓丹, 罗周全, 秦亚光, 等. 基于小波分解的尾矿坝浸润线预测方法研究[J]. 黄金科学技术, 2019(1): 137-143.
SUI Xiaodan, LUO Zhouquan, QIN Yaguang, et al. Study on prediction method of seepage line of tailings dam based on wavelet decomposition[J]. Gold Science and Technology, 2019(1): 137-143.
[8] 王飞跃. 基于不确定性理论的尾矿坝稳定性分析及综合评价研究[D].长沙:中南大学, 2009.
WANG Feiyue. Based on the uncertainty theory of tailings dam stability analysis and comprehensive evaluation[D]. Changsha: Central South University, 2009.
[9] 郑店坤,许同乐,尹召杰,等.改进PSO-BP神经网络对尾矿坝地下水位的预测方法[J].山东大学学报:工学版,2019,49(3): 108-113.
ZHENG Diankun, XU Tongle, YIN Zhaojie, et al. Prediction method of tailing dam groundwater levels based on improved PSO-BP neural network[J]. Journal of Shandong University:Engineering Science, 2019,49(3): 108-113.
[10] DONG Longjun, SHU Weiwei, SUN Daoyuan, et al. Pre-alarm system based on real-time monitoring and numerical simulation using internet of things and cloud computing for tailings dam in mines[J]. IEEE Access, 2017,5: 21 080-21 089.
[11] XU Tongle, WANG Yingbo, CHEN Kang. Tailings saturation line prediction based on genetic algorithm and BP neural network[J]. Journal of Intelligent & Fuzzy Systems, 2016,30(4): 1 947-1 955.
[12] 李娟, 李翠平, 李春民, 等. 支持向量回归机在尾矿坝浸润线预测中的应用[J]. 中国安全生产科学技术, 2009,5(1): 76-79.
LI Juan, LI Cuiping, LI Chunmin, et al. Forecasting of infiltration route in tailings dam by support vector regression[J]. Journal of Safety Science and Technology, 2009,5(1): 76-79.
[13] 王营博. 尾矿库浸润线监测与预测方法研究[D]. 淄博:山东理工大学, 2017.
WANG Yingbo. Study on monitoring and forecasting methods of saturation line in tailings dam[D]. Zibo: Shandong University of Technology, 2017.
[14] RODGERS J L, ALANNICEWANDER W. Thirteen ways to look at the correlation coefficient[J]. American Statistician, 1988, 42(1): 59-66.
[15] 黄忠山, 田凌, 向东, 等. 基于PCA和SPC-动态神经网络的风电机组齿轮箱油温趋势预测[J]. 清华大学学报:自然科学版, 2018,58(6): 539-546.
HUANG Zhongshan, TIAN Ling, XIANG Dong, et al. Prediction of oil temperature rariations in a wind turbine gearbox based on PCA and an SPC-dynamic neural network hybird[J]. Journal of Tsinghua University:Science and Technology, 2018,58(6): 539-546.
[16] CORTEZ B, CARRERA B, KIM Y J, et al. An architecture for emergency event prediction using LSTM recurrent neural networks[J]. Expert Systems with Applications, 2018,97: 315-324.
[17] GREFF K, SRIVASTAVA R K, KOUTNÍ K, et al. LSTM: a search space odyssey[J]. IEEE Transactions on Neural Networks and Learning Systems, 2016,28(10): 2 222-2 232.
[18] GAURI J, MANISHA S, BASANT A. Optimizing semantic LSTM for spam detection[J]. International Journal of Information Technology, 2019,11(2): 239-250.
[19] FAN Cheng, XIAO Fu, ZHAO Yang. A short-term building cooling load prediction method using deep learning algorithms[J]. Applied Energy, 2017,195: 222-233.
[20] CHEN Shun,GE Lei. Exploring the attention mechanism in LSTM-based Hong Kong stock price movement prediction[J]. Quantitative Finance, 2019,19(9): 1-9.