论文标题
尾矿池塘风险预测的小波-CNN-LSTM模型
A Wavelet-CNN-LSTM Model for Tailings Pond Risk Prediction
论文作者
论文摘要
尾矿池塘是存储工业废物的地方。一旦尾矿池塘倒塌，附近的村庄将被摧毁，有害化学物质将造成严重的环境污染。迫切需要一个可靠的预测模型，该模型可以研究尾巴大坝稳定系数的变化趋势并发出早期警告。为了填补空白，这项工作提出了一个混合网络 - 基于小波的长短记忆（LSTM）和卷积神经网络（CNN），即小波局-CNN-LSTM NetWrok，用于预测尾矿池塘的风险。首先，我们构建了特别的非线性数据处理方法，以将缺失的值与数值反转（NI）方法相结合，该方法结合了相关分析，灵敏度分析和随机森林（RF）算法。其次，提出了一种新的预测模型来监视饱和线，这是尾矿池的寿命，可以直接反映尾矿池的稳定性。在使用离散小波变换（DWT）将原始饱和线数据分解为4层小波并删除数据后，使用CNN来识别和学习时间序列中的空间结构，然后是LSTM细胞，用于检测长期依赖性。最后，通过将模型与其他最先进的算法进行比较，进行了不同的实验来评估我们的模型的有效性。结果表明，小波-CNN-LSTM在平均绝对百分比误差（MAPE），根平方误差（RMSE）和r 2中达到最佳分数。
Tailings ponds are places for storing industrial waste. Once the tailings pond collapses, the villages nearby will be destroyed and the harmful chemicals will cause serious environmental pollution. There is an urgent need for a reliable forecast model, which could investigate the variation trend of stability coefficient of tailing dam and issue early warnings. In order to fill the gap, this work presents an hybrid network - Wavelet-based Long-Short-Term Memory (LSTM) and Convolutional Neural Network (CNN), namely Wavelet-CNN-LSTM netwrok for predicting the tailings pond risk. Firstly, we construct the especial nonlinear data processing method to impute the missing value with the numerical inversion (NI) method, which combines correlation analysis, sensitivity analysis, and Random Forest (RF) algorithms. Secondly, a new forecasting model was proposed to monitor the saturation line, which is the lifeline of the tailings pond and can directly reflect the stability of the tailings pond. After using the discrete wavelet transform (DWT) to decompose the original saturation line data into 4-layer wavelets and de-noise the data, the CNN was used to identify and learn the spatial structures in the time series, followed by LSTM cells for detecting the long-short-term dependence. Finally, different experiments were conducted to evaluate the effectiveness of our model by comparing it with other state-of-the-art algorithms. The results show that Wavelet-CNN-LSTM achieves the best score both in mean absolute percentage error (MAPE), root-mean-square error (RMSE) and R 2 .
