基于DRN-BiLSTM模型的矿井涌水量预测
Mine water inflow prediction based on DRN-BiLSTM model
-
摘要: 针对矿井涌水量预测中存在的深度学习模型预测精度不高和适用性不强的问题，提出了一种基于深度残差网络（Deep Residual Network, DRN）和双向长短记忆网络（Bidirectional short and long memory network, BiLSTM）的矿井涌水量预测方法。首先，将矿井涌水量数据进行小波分解和归一化处理，得到趋势项数据和细节项数据；其次，采用DRN网络方法对趋势项数据进行预测，采用BiLSTM网络方法对细节项数据进行预测；最后，将2部分预测结果进行重构得到矿井涌水量预测结果。研究结果表明：DRN-BiLSTM模型相比于单一模型预测精度更高，说明该模型具有更好的泛化性。
-
关键词:
- 矿井涌水量 /
- DRN-BiLSTM模型 /
- 深度残差网络 /
- 双向长短记忆网络 /
- 小波分解
Abstract: For the problem of low accuracy and applicability of the model prediction in the study of mine water inflow, a method of mine water inflow prediction based on bidirectional short and long memory network（BiLSTM） and deep residual network （DRN） is proposed. First, the data of mine water inflow is processed by wavelet decomposition and normalization to obtain trend item data and detail item data. Secondly, the trend item data was predicted by DRN network method, and the detail item data was predicted by BiLSTM network method. Finally, the two parts of the prediction results will be combined to get the mine water inflow prediction results. The results show that the DRN-BiLSTM model has higher prediction accuracy than a single model, indicating that the model has better generalization. -
-
[1] 尹尚先, 王玉国, 李文生.矿井水灾害: 原因·对策·出路[J].煤田地质与勘探, 2023, 51(1): 214-221. YIN Shangxian, WANG Yuguo, LI Wensheng. Cause, countermeasures and solutions of water hazards in coal mines in China[J]. Coal Geology & Exploration, 2023, 51(1): 214-221.
[2] 尹尚先, 连会青, 刘德民, 等.华北型煤田岩溶陷落柱研究70年: 成因·机理·防治[J].煤炭科学技术, 2019, 47(11): 1-29. YIN Shangxian, LIAN Huiqing, LIU Demin, et al. 70 years of investigation on karst collapse columns in North China Colfield: cause of origin, mechanism and prevention[J]. Coal Science and Technology, 2019, 47(11): 1-29.
[3] 尹尚先, 徐维, 尹慧超, 等.深部开采底板厚隔水层突水危险性评价方法研究[J].煤炭科学技术, 2020, 48(1): 83-89. YIN Shangxian, XU Wei, YIN Huichao, et al. Study on risk assessment method of water inrush from thick floor aquifuge in deep mining[J]. Coal Science and Technology, 2020, 48(1): 83-89.
[4] 尹尚先, 王屹, 尹慧超, 等.深部底板奥灰薄灰突水机理及全时空防治技术[J].煤炭学报, 2020, 45(5): 1855-1864. YIN Shangxian, WANG Yi, YIN Huichao, et al. Mechanism and full-time-space prevention and control technology of water inrush from Ordovician and thin limestone in deep mines[J]. Journal of China Coal Society, 2020, 45(5): 1855-1864.
[5] 尹尚先, 连会青, 徐斌, 等.深部带压开采: 传承与创新[J].煤田地质与勘探, 2021, 49(1): 170-181. YIN Shangxian, LIAN Huiqing, XU Bin, et al. Deep mining under safe water pressure of aquifer: Inheritance and innovation[J]. Coal Geology & Exploration, 2021, 49(1): 170-181.
[6] YIN Huichao, WU Qiang, YIN Shangxian, et al. Predicting mine water inrush accidents based on water level anomalies of borehole groups using Long short-term memory and Isolation forest[J]. Journal of Hydrology, 2023, 616: 128813. [7] 李燕, 孙亚军, 徐智敏, 等.影响矿井安全的多含水层矿井涌水构成分析[J].采矿与安全工程学报, 2010, 27(3): 433-437. LI Yan, SUN Yajun, XU Zhimin, et al. Analysis of composition of mine inflow from complicated multiaquifer affecting safety production in coal mines[J]. Journal of Mining & Safety Engineering, 2010, 27(3): 433-437.
[8] 朱赛君, 姜春露, 毕波, 等.基于组合权-改进灰色关联度理论的矿井突水水源识别[J].煤炭科学技术, 2022, 50(4): 165-172. ZHU Saijun, JIANG Chunlu, BI Bo, et al. Identification of mine water inrush source based on combination weight-theory of improved grey relational degree[J]. Coal Science and Technology, 2022, 50(4): 165-172.
[9] 徐小峰, 余乐安, 林姿汝, 等.基于特征融合的生鲜商品短期销量组合预测[J].管理科学学报, 2022, 25(12): 102-123. XU Xiaofeng, YU Lean, LIN Ziru, et al. Combination forecasting of short-term sales for fresh products based on feature fusion[J]. Journal of Management Sciences in China, 2022, 25(12): 102-123.
[10] 刘晓丹, 潘国营.基于三种时间序列模型的矿井涌水量预测[J].矿业安全与环保, 2022, 49(2): 91-95. LIU Xiaodan, PAN Guoying. Prediction of mine water inflow based on three time series models[J]. Mining Safety & Environmental Protection, 2022, 49(2): 91-95.
[11] 刘浪, 陈建宏, 杨珊, 等.基于灰色关联分析的PSO-BP算法预测矿震危险性[J].中南大学学报(自然科学版), 2011, 42(8): 2400-2405. LIU Lang, CHEN Jianhong, YANG Shan, et al. Application of PSO-BP algorithm in risk prediction of mine earthquake based on grey correlation analysis[J]. Journal of Central South University(Science and Technology), 2011, 42(8): 2400-2405.
[12] 程志友, 汪德胜.基于机器学习与疫情关联特征的短期负荷预测[J].电力系统保护与控制, 2022, 50(23): 1-8. CHENG Zhiyou, WANG Desheng. Short-term load forecasting based on machine learning and epidemic association features[J]. Power System Protection and Control, 2022, 50(23): 1-8.
[13] 欧阳添, 闪锟, 周博天, 等.基于LSTM网络的在线藻类时序数据预测研究: 以三峡水库为例[J].湖泊科学, 2021, 33(4): 1031-1042. OUYANG Tian, SHAN Kun, ZHOU Botian, et al. Research on the online forecasting of algal kinetics based on time-series data and LSTM neural network: Taking Three Gorges Reservoir as an example[J]. Journal of Lake Sciences, 2021, 33(4): 1031-1042.
[14] 徐精诚, 连增增, 董佳琪, 等.基于小波包分解重构算法的北斗抗多路径误差[J].科学技术与工程, 2022, 22(35): 15477-15484. XU Jingcheng, LIAN Zengzeng, DONG Jiaqi, et al. Anti-multipath error of BDS Based on WPT decomposition and reconstruction algorithm[J]. Science Technology and Engineering, 2022, 22(35): 15477-15484.
[15] 刘译文, 赵一帆, 张兰兰, 等.基于小波包分解的长短期记忆网络光伏功率预测[J].计算机与数字工程, 2022, 50(9): 2114-2118. LIU Yiwen, ZHAO Yifan, ZHANG Lanlan, et al. Photovoltaic power forecasting based on wavelet packet decomposition of long short-term memory network[J]. Computer & Digital Engineering, 2022, 50(9): 2114-2118.
[16] 李禄德, 崔东文.基于小波包分解与相空间重构的SSA-ELM水文时间序列预报模型[J].人民珠江, 2022, 43(8): 100-108. LI Lude, CUI Dongwen. SSA-ELM hydrological time series forecast model based on wavelet packet decomposition and phase space reconstruction[J]. Pearl River, 2022, 43(8): 100-108.
[17] 陈倩倩, 林天然.基于DRN-BiGRU模型的滚动轴承剩余寿命预测[J].机电工程, 2022, 39(11): 1575-1581. CHEN Qianqian, LIN Tianran. Remaining useful life prediction of rolling bearings based on DRN-BiGRU algorithm[J]. Journal of Mechanical & Electrical Engineering, 2022, 39(11): 1575-1581.
[18] PAN Shi-Yuan, LIAO Qi, LIANG Yong-Tu. Multivariable sales prediction for filling stations via GA improved BiLSTM[J]. Petroleum Science, 2022, 19(5): 2483-2496. [19] 周星, 张志军, 李英, 等.基于小波包分解重构的超压预测技术及其应用[J].物探化探计算技术, 2021, 43(4): 429-434. ZHOU Xing, ZHANG Zhijun, LI Ying, et al. The application of overpressure prediction based on wavelet packet decomposition and reconstruction[J]. Computing Techniques for Geophysical and Geochemical Exploration, 2021, 43(4): 429-434.
[20] 冯晶晶, 陈文利, 董丹凤.基于小波变换的图像信号分解与重构[J].电子设计工程, 2021, 29(16): 177-180. FENG Jingjing, CHEN Wenli, DONG Danfeng. Image signal decomposition and reconstruction based on wavelets[J]. Electronic Design Engineering, 2021, 29(16): 177-180.
[21] 蒋明峰, 鲁薏, 李杨, 等.基于金字塔卷积结构的深度残差网络心电信号分类方法研究[J].生物医学工程学杂志, 2020, 37(4): 692-698. JIANG Mingfeng, LU Yi, LI Yang, et al. Research on electrocardiogram classification using deep residual network with pyramid convolution structure[J]. Journal of Biomedical Engineering, 2020, 37(4): 692-698.
[22] 孟安波, 许炫淙, 陈嘉铭, 等.基于强化学习和组合式深度学习模型的超短期光伏功率预测[J].电网技术, 2021, 45(12): 4721-4728. MENG Anbo, XU Xuancong, CHEN Jiaming, et al. Ultra short term photovoltaic power prediction based on reinforcement learning and combined deep learning model[J]. Power System Technology, 2021, 45(12): 4721-4728.
[23] 王彦博, 吴俊勇, 季佳伸, 等.基于深度残差收缩网络的电力系统暂态频率安全集成评估[J].电网技术, 2023, 47(2): 482-494. WANG Yanbo, WU Junyong, JI Jiashen, et al. Integrated assessment of power system transient frequency security based on deep residual shrinkage network[J]. Power System Technology, 2023, 47(2): 482-494.
[24] 季佳伸, 吴俊勇, 王彦博, 等.基于深度残差网络的电力系统暂态电压稳定评估[J].电网技术, 2022, 46(7): 2500-2511. JI Jiashen, WU Junyong, WANG Yanbo, et al. Power system transient voltage stability assessment based on deep residual network[J]. Power System Technology, 2022, 46(7): 2500-2511.
[25] 尹佳, 陈翔, 董曼, 等.基于小波分解-长短期记忆网络预测模型的酱卤肉制品安全预测分析[J].食品科学, 2022, 43(3): 121-128. YIN Jia, CHEN Xiang, DONG Man, et al. Prediction and analysis of marinated meat product safety risk using wavelet transform-long short-term memory prediction model[J]. Food Science, 2022, 43(3): 121-128.
[26] 欧阳福莲, 王俊, 周杭霞.基于改进迁移学习和多尺度CNN-BiLSTM-Attention的短期电力负荷预测方法[J].电力系统保护与控制, 2023, 51(2): 132-140. OUYANG Fulian, WANG Jun, ZHOU Hangxia. Short-term power load forecasting method based on improved hierarchical transfer learning and multi-scale CNN-BiLSTM-Attention[J]. Power System Protection and Control, 2023, 51(2): 132-140.
[27] 魏佳恒, 郭惠勇.基于贝叶斯优化BiLSTM模型的输电塔损伤识别[J].振动与冲击, 2023, 42(1): 238-248. WEI Jiaheng, GUO Huiyong. Damage identification of transmission tower based on BO-BiLSTM model[J]. Journal of Vibration and Shock, 2023, 42(1): 238-248.
[28] 李小平, 白超, 石森.基于CNN-BiLSTM模型的机车变压器油中溶解气体浓度预测方法[J].铁道学报, 2022, 44(5): 42-48. LI Xiaoping, BAI Chao, SHI Sen. Prediction method of dissolved gas concentration in transformer oil based on CNN-BiLSTM model[J]. Journal of the China Railway Society, 2022, 44(5): 42-48.
[29] 任建吉, 位慧慧, 邹卓霖, 等.基于CNN-BiLSTM-Attention的超短期电力负荷预测[J].电力系统保护与控制, 2022, 50(8): 108-116. REN Jianji, WEI Huihui, ZOU Zhuolin, et al. Ultra-short-term power load forecasting based on CNN-BiLSTM-Attention[J]. Power System Protection and Control, 2022, 50(8): 108-116.
-
期刊类型引用(6)
1. 陆睿，尹尚先，王玉国，孟浩鹏，王旭. 基于GMS的深部煤层开采工作面涌水量预测. 煤矿安全. 2025(01): 164-170 . 
本站查看
2. 丁莹莹，尹尚先，连会青，卜昌森，刘伟，夏向学，周旺. 基于CEEMDAN和改进的混合时间序列模型工作面涌水量预测研究. 中国安全生产科学技术. 2024(03): 110-117 . 百度学术
3. 丁莹莹，尹尚先，连会青，刘伟，李启兴，祁荣荣，卜昌森，夏向学，李书乾. 基于SSA-CG-Attention模型的多因素采煤工作面涌水量预测. 煤田地质与勘探. 2024(04): 111-119 . 百度学术
4. 姚辉，尹慧超，梁满玉，尹尚先，侯恩科，连会青，夏向学，张金福，吴传实. 机器学习方法在矿井水防治理论体系研究中的应用思考. 煤田地质与勘探. 2024(05): 107-117 . 百度学术
5. 侯恩科，徐林啸，荣统瑞. 彬长大佛寺矿井涌水量时序预测. 西安科技大学学报. 2024(03): 490-500 . 百度学术
6. 范明星，任高峰，吴文博，鲁习奎，李吉民，张聪瑞. 基于降雨量数据的程潮铁矿涌水量时序性预测模型. 金属矿山. 2024(06): 212-219 . 百度学术
其他类型引用(0)
计量
- 文章访问数: 53
- HTML全文浏览量: 1
- PDF下载量: 36
- 被引次数: 6
下载:
