多属性融合分布式光纤导水裂隙带高度预测方法

doi:10.13229/j.cnki.jdxbgxb.20220051

吉林大学学报(工学版) ›› 2023, Vol. 53 ›› Issue (4): 1200-1210.doi: 10.13229/j.cnki.jdxbgxb.20220051

• 通信与控制工程 • 上一篇

多属性融合分布式光纤导水裂隙带高度预测方法

冀汶莉^1,²(),田忠¹,柴敬^2,³(),张丁丁^2,³,王斌¹

^1.西安科技大学通信与信息工程学院，西安 710054
^2.西安科技大学西部矿井开采及灾害防治教育部重点实验室，西安 710054
^3.西安科技大学能源学院，西安 710054

收稿日期:2022-01-12 出版日期:2023-04-01 发布日期:2023-04-20
通讯作者: 柴敬 E-mail:jiwenli@xust.edu.cn;chaij@xust.edu.cn
作者简介:冀汶莉（1973-），女，副教授.研究方向：人工智能技术在智慧矿山及智能开采中的应用.E-mail： jiwenli@xust.edu.cn
基金资助:
国家重点研发计划项目(2018YFC0808301);国家自然科学基金项目(51804244)

Prediction of water⁃flowing height in fractured zone based on distributed optical fiber and multi⁃attribute fusion

Wen-li JI^1,²(),Zhong TIAN¹,Jing CHAI^2,³(),Ding-ding ZHANG^2,³,Bin WANG¹

^1.College School of Communication and Information Engineering，Xi'an University of Science and Technology，Xi'an 710054，China
^2.Key Laboratory of Western Mine Exploitation and Hazard Prevention，Ministry of Education，Xi'an University of Science and Technology，Xi'an 710054，China
^3.College of Energy Engineering，Xi'an University of Science and Technology，Xi'an 710054，China

Received:2022-01-12 Online:2023-04-01 Published:2023-04-20
Contact: Jing CHAI E-mail:jiwenli@xust.edu.cn;chaij@xust.edu.cn

摘要/Abstract

摘要：

针对上覆岩层导水裂隙带发育高度预测这个研究难点，以光纤监测覆岩变形模拟试验为基础，融合测点频移值、高度、覆岩岩性等因素，提出一种基于深度学习的导水裂隙带发育高度预测方法。先将测点频移值分解为随机、周期和趋势等分量，建立预测模型，叠加后再利用预测频移值变化特征推测导水裂隙带的发育高度。实验结果表明本方法预测的发育高度平均误差为11 mm，其精度控制在允许误差范围内。

关键词: 智能开采, 集成经验模态分解, 组合深度神经网络, 导水裂隙带高度, 光纤测点频移值预测

Abstract:

The prediction height of water-flowing in fractured zone of overburden strata is the difficulty of research. A deep learning model is proposed to estimate the height of the water-conducting fracture zone based on simulation experiments of fiber-optic monitoring overlying rock deformation. The key factors， such as the frequency shift value of the optical fiber sensor， the height of the sensor， the advance length of the working face， the lithology and structure of the overlying rock were select in this model. Firstly， the frequency shift value is decomposed into three components， random frequency shift value， periodic frequency shift value and trend frequency shift value. Then， deep learning model are built to predict each component， and prediction component are superimposed to form the frequency shift value of sensor. Finally， the development height of the water-conducting fracture zone is inferred in accordance with the relationship between curve of frequency shift value change and the development height of fracture zone. The experiments show that the average estimation error of such height is about 11 mm. The predicted heights are accurate and reliable， which can also meet requirements of an engineering test practice.

Key words: smart mining, ensemble empirical mode decomposition, hybrid deep learning network, height of water-flowing fractured zone, prediction of frequency shift value of optical fiber sensor

中图分类号:

TD325

冀汶莉,田忠,柴敬,张丁丁,王斌. 多属性融合分布式光纤导水裂隙带高度预测方法[J]. 吉林大学学报(工学版), 2023, 53(4): 1200-1210.

Wen-li JI,Zhong TIAN,Jing CHAI,Ding-ding ZHANG,Bin WANG. Prediction of water⁃flowing height in fractured zone based on distributed optical fiber and multi⁃attribute fusion[J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(4): 1200-1210.

图/表 11

图1

图2

图3

图4

表1

图5

图6

表2

图7

图8

表3

参考文献 24

1	张军, 王建鹏. 采动覆岩“三带”高度相似模拟及实证研究[J]. 采矿与安全工程学报, 2014, 31(2): 249-254.
	Zhang Jun, Wang Jian-peng. Similar simulation and practical research on the mining overburden roof strata "three-zones" height[J]. Journal of Mining & Safety Engineering, 2014, 31(2): 249-254.
2	李东, 刘生优, 张光德, 等. 鄂尔多斯盆地北部典型顶板水害特征及其防治技术[J]. 煤炭学报, 2017, 42(12): 3249-3254.
	Li Dong, Liu Sheng-you, Zhang Guang-de, et al. Typical roof water disasters and its prevention & control technology in the north of Ordos Basin[J]. Journal of China Coal Society, 2017, 42(12): 3249-3254.
3	Palchik V. Influence of physical characteristics of weak rock mass on height of caved zone over abandoned subsurface coalmine[J]. Environmental Geology, 2002, 42(1): 92-101.
4	钱鸣高, 缪协兴, 许家林. 岩层控制中的关键层的理论研究[J]. 煤炭学报, 1996, 21(3): 225-230.
	Qian Ming-gao, Miao Xie-xing, Xu Jia-lin. Theoretical study of key stratum in ground control[J]. Journal of China Coal Society, 1996, 21(3): 225-230.
5	钱鸣高, 刘听成. 矿山压力及其控制[M].北京: 煤炭工业出版社, 1991.
6	许家林, 朱卫兵, 王晓振. 基于关键层位置的导水裂隙带高度预计方法[J]. 煤炭学报, 2012, 37(5): 762-769.
	Xu Jia-lin, Zhu Wei-bing, Wang Xiao-zhen. New method to predict the height of fractured water-conducting zone by location of key strata[J]. Journal of China Coal Society, 2012, 37(5) : 762-769.
7	张建民, 张凯, 曹志国, 等. 基于采动-爆裂模型的导水裂隙带高度计算方法[J]. 煤炭学报, 2017, 42(6): 1557-1564.
	Zhang Jian-min, Zhang Kai, Cao Zhi-guo, et al. Mining-bursting simulation and height calculation method for conducting-water fractured zone[J]. Journal of China Coal Society, 2017, 42(6): 1557-1564.
8	杨达明, 郭文兵, 赵高博, 等. 厚松散层软弱覆岩下综放开采导水裂隙带发育高度[J]. 煤炭学报, 2019, 44(11) : 3308-3316.
	Yang Da-ming, Guo Wen-bing, Zhao Gao-bo, et al. Overburden failure height of superhigh seam by fully mechanized caving method[J]. Journal of China Coal Society, 2019, 44(11): 3308-3316.
9	杜文刚, 柴敬, 张丁丁, 等. 采动覆岩导水裂隙发育光纤感测与表征模型试验研究[J]. 煤炭学报, 2021, 46(5): 1565-1575.
	Du Wen-gang, Chai Jing, Zhang Ding-ding, et al. Optical fiber sensing and characterization of water flowing fracture development in mining overburden[J]. Journal of China Coal Society, 2021, 46(5): 1565-1575.
10	李振华, 许延春, 李龙飞, 等. 基于BP神经网络的导水裂隙带高度预测[J]. 采矿与安全工程学报, 2015, 32(6): 905-910.
	Li Zhen-hua, Xu Yan-chun, Li Long-fei, et al. Forecast of the height of water flowing fractured zone based on BP neural networks[J]. Journal of Mining & Safety Engineering, 2015, 32(6): 905-910.
11	柴华彬, 张俊鹏, 严超. 基于GA-SVR的采动覆岩导水裂隙带高度预测[J]. 采矿与安全工程学报, 2018,35(2): 359-365.
	Chai Hua-bin, Zhang Jun-peng, Yan Chao. Prediction of water-flowing height in fractured zone of overburden strata based on GA-SVR[J]. Journal of Mining & Safety Engineering, 2018, 35(2): 359-365.
12	柴敬, 雷武林, 杜文刚, 等. 分布式光纤监测的采场巨厚复合关键层变形试验研究[J]. 煤炭学报, 2020, 45(1): 44-53.
	Chai Jing, Lei Wu-lin, Du Wen-gang, et al. Experimental study on the deformation of the thick composite key layer of the stope based on distributed optical fiber monitoring[J]. Journal of China Coal Society, 2020, 45(1): 44-53.
13	侯公羽, 胡涛, 李子祥,等. 基于分布式光纤技术的采动影响下覆岩变形演化规律试验研究[J]. 岩土力学, 2020, 41(3): 970-979.
	Hou Gong-yu, Hu Tao, Li Zi-xiang, et al. Experimental study on overburden deformation evolution under mining effect based on distributed fiber optical sensing technology[J]. Rock and Soil Mechanics, 2020, 41(3): 970-979.
14	Sun B Y, Zhang P S, Wu R X, et al. Dynamic detection and analysis of overburden deformation and failure in a mining face using distributed optical fiber sensing[J]. Journal of Geophysics and Engineering, 2018,15(6): 2545-2555.
15	张丹, 张平松, 施斌, 等. 采场覆岩变形与破坏的分布式光纤监测与分析[J].岩土工程学报, 2015, 37(5): 952-957.
	Zhang Dan, Zhang Ping-song, Shi Bin, et al. Monitoring and analysis of overburden deformation and failure using distributed fiber optic sensing[J]. Chinese Journal of Geotechnical Engineering, 2015, 37(5): 952-957.
16	董丽丽, 杨丹, 张翔. 基于深度学习的大规模语义文本重叠区域检索[J]. 吉林大学学报: 工学版, 2021, 51(5): 1817-1822.
	Dong Li-li, Yang Dan, Zhang Xiang. Large-scale semantic text overlapping region retrieval based on deep learning[J]. Journal of Jilin University(Engineering and Technology Edition), 2021, 51(5): 1817-1822.
17	徐涛, 马克, 刘才华. 基于深度学习的行人多目标跟踪方法[J]. 吉林大学学报: 工学版, 2021, 51(1): 27-38.
	Xu Tao, Ma Ke, Liu Cai-hua. Multi object pedestrian tracking based on deep learning[J]. Journal of Jilin University (Engineering and Technology Edition), 2021, 51(1): 27-38.
18	郭立民, 陈鑫, 陈涛. 基于 AlexNet模型的雷达信号调制类型识别[J]. 吉林大学学报: 工学版, 2019, 49(3): 1000-1008.
	Guo Li⁃min, Chen Xin, Chen Tao. Radar signal modulation type recognition based on AlexNet model[J]. Journal of Jilin University (Engineering and Technology Edition), 2019, 49(3): 1001-1008.
19	袁强. 采动覆岩变形的分布式光纤检测与表征模拟试验研究[D]. 西安: 西安科技大学能源学院,2017.
	Yuan Qiang. Experimental study on detection and representation of mining-induced overburden deformation with distributed optical fiber sensing[D]. Xi'an: School of Energy, Xi'an University of Science and Technology, 2017.
20	毛莺池, 曹海, 何进锋. 面向大坝变形监测的时空一体化预测算法[J]. 计算机科学, 2019, 46(2): 223-239.
	Mao Ying-chi, Cao Hai, He Jin-feng. Spatio-temporal integrated forecasting algorithm for dam deformation[J]. Computer Science, 2019, 46(2): 223-239.
21	王俊, 曹俊兴, 尤加春. 基于GRU神经网络的测井曲线重构[J]. 石油地球物理勘探, 2020, 55(3): 510-520, 468.
	Wang Jun, Cao Jun-xin, You Jia-chun. Reconstruction of logging traces based on GRU neural network[J]. Oil Geophysical Prospecting, 2020, 55(5): 510-520, 468.
22	谢丽蓉, 王斌, 包洪印, 等. 基于EEMD-WOA-LSSVM的超短期风电功率预测[J]. 太阳能学报, 2021, 42(7): 290-296.
	Xie Li-rong, Wang Bin, Bao Hong-yin, et al. Super-short-term wind power forecasting based on EEMD-WOA-LSSVM[J]. Acta Energiae Solaris Sinica, 2021, 42(7): 290-296.
23	郗刘涛. 基于LSTM的采动覆岩变形监测数据预测方法研究[D]. 西安:西安科技大学通信学院,2020.
	Xi Liu⁃tao. Research on monitoring data forecasting method of mining-induced overburden deformation based on LSTM[D]. College of Communication and Information Engineering, Xi'an: Xi'an University of Science and Technology, 2020.
24	胡小娟, 李文平, 曹丁涛, 等. 综采导水裂隙带多因素影响指标研究与高度预计[J]. 煤炭学报, 2012, 37(4): 613-620.
	Hu Xiao-juan, Li Wen-ping, Cao Ding-tao, et al. Index of multiple factors and expected height of fully mechanized water flowing fractured zone[J]. Journal of China Coal Society, 2012, 37(4): 613-620.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

模型参数	IMF1设置	IMF2设置	RE设置
CNN的卷积核数	16	16	16
GRU层数及神经元	2（48，56）	2（87，72）	2（30，71）
BP层数及神经元	2（93，59）	1（39）	2（88，98）
输出神经单元数	1	1	1
时间步长	1	1	1
迭代轮次（Epochs）	500	500	500
损失函数（Loss）	MSE	MSE	MSE
批量大小（Batch_size）	32	32	32
优化算法	Adam	Adam	Adam
初始学习率	0.001	0.001	0.001

评价指标组合模型	Fv1光纤全测点预测			Fv2光纤全测点预测
评价指标组合模型	RMSE/MHz	MAE/MHz	R²	RMSE/MHz	MAE/MHz	R²
GA?CNN?GRU	99.1	63.0	0.529	91.99	63.3	0.565
FDT?GA?CNN?GRU?BP	98.72	59.95	0.639	56.02	38.45	0.714
EEMD?SVM	37.8	31.3	0.931	46.22	39.86	0.88
EEMD?GA?CNN?GRU?BP	4.94	3.0	0.998	8.31	4.69	0.992
改进EEMD?GA?CNN?GRU?BP	2.2	1.5	0.998	4.7	2.7	0.997

工作面开挖/ cm	实测垮落带高度/mm	实测裂隙带高度/mm	推测垮落带高度/mm	推测裂隙带高度/mm	推测导水裂隙带高度/mm	绝对误差/mm
156	420	715	410	710	1120	15
168	460	845	470	830	1300	5
184	490	1020	495	1000	1495	15
196	495	1010	500	1000	1500	5
208	510	1000	500	1000	1500	10

多属性融合分布式光纤导水裂隙带高度预测方法

Prediction of water⁃flowing height in fractured zone based on distributed optical fiber and multi⁃attribute fusion

RICH HTML

PDF (PC)

摘要/Abstract

引用本文

使用本文

图/表 11

参考文献 24

相关文章 0

Metrics

本文评价

推荐阅读 0