It is of great significance to study the accurate prediction of the failure depth of coal seam floor to ensure the safety production of coal mine under the condition of mining under pressure. A new SA-PSO-BP neural network model is proposed to solve the problems of large error, easy to fall into local optimal solution and slow convergence speed in the traditional BP neural network prediction of floor failure depth. The model takes the coal seam dip angle, mining depth, coal seam mining thickness and the inclined length of working face as the evaluation indexes, in order to avoid PSO falling into local optimal solution, a simulated annealing algorithm (SA)was introduced to improve the optimization process of BP neural network by using Particle swarm optimization (PSO), the optimized model is trained and predicted. The results show that the goodness of fit of SA-PSO-BP neural network model is 0.983 5, which is 0.288 2 higher than that of BP neural network, and the root mean square error is 1.319 0, which is 3.864 1 lower than that of BP neural network .The average absolute percentage error is 5.442 3, which is 14.93% less than that of BP neural network. The SA-PSO-BP network model is feasible, and it provides a reasonable method for the prediction of floor failure depth.
[1] 李刚, 张恺, 苏俊辉, 等. 团柏煤矿带压开采条件下11-101工作面合理长度[J]. 煤田地质与勘探, 2019, 47(3):160-165.(Li Gang, Zhang Kai, Su Junhui, et al. Reasonable length of working face 11-101 during mining above confined aquifer in Tuanbai mine[J]. Coal Geology & Exploration, 2019,47(3): 160-165. (in Chinese))
[2] 胡耀青. 我国带压开采研究现状及其展望[J]. 太原理工大学学报, 2002(6):594-600.(Hu Yaoqing. The development and application situation on aquifer mining in China[J]. Journal of Taiyuan University of Technology, 2002(6): 594-600. (in Chinese))
[3] 李兴高, 高延法. 采场底板岩层破坏与损伤分析[J]. 岩石力学与工程学报, 2003(1):35-39.(Li Xinggao, Gao Yanfa. Damage analysis of stope floor strata[J]. Chinese Journal of Rock Mechanics and Engineering, 2003(1): 35-39. (in Chinese))
[4] 许延春, 杨扬. 大埋深煤层底板破坏深度统计公式及适用性分析[J]. 煤炭科学技术, 2013, 41(9):129-132.(Xu Yanchun, Yang Yang. Applicability analysis on statistical formula for failure depth of coal seam floor in deep mine[J]. Coal Science and technology, 2013,41(9): 129-132. (in Chinese))
[5] 张文彬. 综采放顶煤工作面底板应力及其破坏深度分析[J]. 煤炭科学技术, 2010, 38(12):17-21.(Zhang Wenbin. Analysis on floor stress and failure depth of fully mechanized top coal caving mining face[J]. Coal Science and technology, 2010,38(12): 17-21. (in Chinese))
[6] 李海龙, 白海波, 马丹, 等. 采动动载作用下底板岩层裂隙演化规律的相似模拟研究[J]. 采矿与安全工程学报, 2018, 35(2):366-372.(Li Hailong, Bai Haibo, Ma Dan, et al. Physical simulation testing research on mining dynamic loading effect and induced coal seam floor failure[J]. Journal of Mining & safety engineering, 2018,35(2): 366-372. (in Chinese))
[7] 陈继刚, 熊祖强, 李卉, 等. 倾斜特厚煤层综放带压开采底板破坏特征研究[J]. 岩石力学与工程学报, 2016, 35(增1):3018-3023.(Chen Jigang, Xiong Zuqiang, Li Hui, et al. Failure characteristics of floor under predssure inclined and extra thick coal seam in full-mechanized top coal caving faces[J]. Chinese Journal of Rock Mechanics and Engineering, 2016,35(Supp.1): 3018-3023. (in Chinese))
[8] 白丽扬, 赵金海, 刘占新, 等. 基于数据挖掘算法的底板破坏深度预测[J]. 煤炭工程, 2017, 49(6):92-95.(Bai Liyang, Zhao Jinhai, Liu Zhanxin, et al. Depth prediction of floor damage based on data mining algorithm[J]. Coal Engineering, 2017,49(6): 92-95. (in Chinese))
[9] 于小鸽, 韩进, 施龙青, 等. 基于BP神经网络的底板破坏深度预测[J]. 煤炭学报, 2009, 34(6):731-736.(Yu Xiaoge, Han Jin, Shi Longqing, et al. Forcast of destroyed floor depth based on BP neural networks[J]. Journal of China Coal Society, 2009,34(6): 731-736. (in Chinese))
[10] 许延春, 陈新明, 姚依林. 高水压突水危险工作面防治水关键技术[J]. 煤炭科学技术, 2012, 40(9):99-103.(Xu Yanchun, Chen Xinming, Yao Yilin. Key technology of water prevention and control for coal mining face with high water pressure water inrush dangers [J]. Coal Science and Technology, 2012,40(9): 99-103. (in Chinese))
[11] 高鹰, 谢胜利. 基于模拟退火的粒子群优化算法[J]. 计算机工程与应用, 2004(1):47-50.(Gao Ying, Xie Shengli. Particle swarm optimization algorithms based on simulated annealing[J]. Computer Engineering and Applications, 2004(1): 47-50. (in Chinese))
[12] 施龙青, 徐东晶, 邱梅, 等. 采场底板破坏深度计算公式的改进[J]. 煤炭学报, 2013, 38(增2):299-303.(Shi Longqing, Xu Dongjing, Qiu Mei, et al. Improved on the formula about the depth of damaged floor in working area[J]. Journal of China Coal Society, 2013,38(Supp.2): 299-303. (in Chinese))
[13] 段宏飞. 底板破坏深度六因素线性预测模型[J]. 岩土力学, 2014, 35(11):3323-3330.(Duan Hongfei. Six factors linear prediction model on depth of damage floor[J]. Rock and Soil Mechanics, 2014,35(11): 3323-3330. (in Chinese))
[14] 刘伟韬, 穆殿瑞, 杨利, 等. 倾斜煤层底板破坏深度计算方法及主控因素敏感性分析[J]. 煤炭学报, 2017, 42(4):849-859.(Liu Weitao, Mu Dianrui, Yang Li, et al. Calculation method and main factor sensitivity analysis of inclined coal floor damage depth[J]. Journal of China Coal Society, 2017,42(4): 849-859. (in Chinese))
[15] 陈从磊,姚多喜,赵魁,等.基于灰色神经网络预测青东矿10煤层底板破坏深度[J]. 煤炭技术,2012,31(11):49-51. (Chen Conglei,Yao Duoxi,Zhao Kui,et al. Floor 10 damage depth of green east coal mine based on grey neural network[J]. Coal Technology,2012,31(11):49-51. (in Chinese))
[16] 段宏飞. 煤矿底板采动变形及带压开采突水评判方法研究[D]. 徐州:中国矿业大学, 2012.(Duan Hongfei. Study on mining deformation of floor and evalution method of water inrush mining above confined aquifer[D]. Xuzhou: China University of Mining and Technology, 2012. (in Chinese))
[17] 张培森, 许大强, 张晓乐, 等. 煤层底板破坏深度多因素影响指标分析与深度预测[J]. 采矿与岩层控制工程学报, 2023, 5(3):5-15.(Zhang Peisen, Xu Daqiang, Zhang Xiaole, et al. Multi-factor influence index analysis and depth prediction of coal seam floor failure depth[J]. Journal of Mining and Strata Control Engineering, 2023, 5(3):5-15. (in Chinese))
[18] 王嵘冰, 徐红艳, 李波, 等. BP神经网络隐含层节点数确定方法研究[J]. 计算机技术与发展, 2018, 28(4):31-35.( Wang Rongbing, Xu Hongyan, Li Bo, et al. Research on method of determining hidden layer nodes in BP neural network[J]. Computer Technology and Development, 2018,28(4): 31-35. (in Chinese))
[19] 邵良杉,周玉.基于PSO-ELM-Boosting模型的底板破坏深度预测[J]. 中国安全科学学报,2018,28(4):24-29. (Shao Liangshan, Zhou Yu. Prediction of destroyed floor depth based on PSO-ELM-Boosting model[J]. China Safety Science Journal, 2018,28(4):24-29.(in Chinese))
