近距离煤层群下位工作面受到上覆遗留斜交煤柱集中应力及采动应力的叠加影响，易造成下伏工作面回采过程中区段煤柱失稳破坏，实现下伏工作面区段煤柱变形的精准监测与超前预测，对于该种条件下工作面安全高效生产具有重要意义。而区段煤柱变形监测近年来通常采用的数值模拟、钻孔窥视、声发射等方法未能实现对区段煤柱内部变形的实时精准监测。引入钻孔植入式光纤光栅监测方式可对区段煤柱内部全区域实现实时变形监测，改善了煤柱变形监测的短板问题。然而，光纤光栅监测技术易受到外界环境的影响，尤其对于井下复杂开采环境的干扰更加敏感。因此引入改进的自适应噪声完备集合经验模态分解（ICEEMDAN）结合散布熵（DE）进行应变数据降噪处理，对比自适应噪声完备集合经验模态分解（CEEMDAN）和集合经验模态分解（EEMD）两种降噪结果，信噪比提升了0.8-2.3dB。将去噪后的区段煤柱应变数据输入长短期记忆神经网络-反向传播神经网络（LSTM-BP）预测模型中结合遗传算法（GA），对工作面进、过、出上覆遗留煤柱时5^-1#区段煤柱应变趋势进行预测，预测结果的准确率在88%-96%。验证了ICEEMDAN-GA-LSTM-BP模型应用在上覆有遗留斜交煤柱时下伏区段煤柱变形应变变化预测中的可靠性、精准性，实现了区段煤柱变形状态的超前预测，为上覆有遗留斜交煤柱下伏区段煤柱变形预测提供了一定思路。本文的主要工作内容如下：

   （1）依托大柳塔活鸡兔井煤矿为工程研究背景，分析影响近距遗留斜交煤柱下伏区段煤柱变形的因素。结合现场实测区段煤柱应变数据，得出上覆遗留斜交煤柱集中应力影响范围、以及工作面进、过、出上覆遗留斜交煤柱时塑性区分布状态。

   （2）建立ICEEMDAN和DE结合降噪算法，对光纤光栅监测区段煤柱变形数据进行降噪，去除冗余数据，对比CEEMDAN和EEMD两种分析降噪方法，根据指标结果验证ICEEMDAN降噪结果的有效性，为后续进行智能化预测提升准确率。

   （3）建立GA-LSTM-BP综合预测模型，将5^-1#区段煤柱变形监测应变数据输入模型，对区段煤柱工作面进、过、出上覆遗留煤柱时，下伏区段煤柱应变光感信号进行预测，准确率在88%-96%，实现了四天内区段煤柱变形应变光感信号的短期预测。证明了ICEEMDAN-GA-LSTM-BP综合预测模型应用在该类工况的有效性。

      本研究成果对于保障井下煤矿，以陕北地区为代表的典型近距遗留斜交煤柱下伏煤层的安全开采具有重要意义，也为该类型工况条件的安全开采以及区段煤柱变形研究提供了科学的理论实践数据支撑。

       The lower working face of the close range coal seam group is easily affected by the concentrated stress of the overlying oblique coal pillars and the superimposed mining stress, which can cause instability and damage to the section coal pillars during the mining process of the lower working face. Realizing accurate monitoring and advanced prediction of the deformation of the section coal pillars in the lower working face is of great significance for the safe and efficient production of the working face under such conditions. However, in recent years, the commonly used methods for monitoring the deformation of section coal pillars, such as numerical simulation, drilling observation, and acoustic emission, have failed to achieve real-time and accurate monitoring of the internal deformation of section coal pillars. The introduction of drilling embedded fiber optic grating monitoring method can achieve real-time deformation monitoring of the entire area inside the section coal pillar, improving the shortcomings of coal pillar deformation monitoring. However, fiber optic grating monitoring technology is susceptible to external environmental influences, especially sensitive to interference from complex underground mining environments. Therefore, an improved adaptive noise complete set empirical mode decomposition (ICEEMDAN) combined with dispersion entropy (DE) was introduced for strain data denoising. Comparing the denoising results of adaptive noise complete set empirical mode decomposition (CEEMDAN) and ensemble empirical mode decomposition (EEMD), the signal-to-noise ratio was improved by 0.8-2.3dB. Input the denoised section coal pillar strain data into the Long Short Term Memory Neural Network Backpropagation Neural Network (LSTM-BP) prediction model, combined with genetic algorithm (GA), to predict the strain trend of the 5-1 # section coal pillar when the working face enters, passes through, and exits the overlying coal pillar, the accuracy of predicting the strain changes of the coal pillars in the underlying section can reach 88% -96%. This further demonstrates the reliability and accuracy of the ICEEMDAN-GA-LSTM-BP model in predicting the deformation and strain changes of coal pillars in the underlying section when there are residual oblique coal pillars overlying. To a certain extent, it has achieved advanced prediction of the deformation status of coal pillars, providing a certain idea for predicting the deformation of coal pillars in the underlying section of overlying oblique coal pillars. The main work of this article is as follows:

        (1) Based on the engineering research background of the Daliuta Huoji Tujing coal mine, this paper analyzes the factors affecting the deformation of the coal pillars in the underlying section of the close range residual oblique coal pillars. Based on the on-site measured strain data of the section coal pillar, the range of concentrated stress influence on the overlying oblique coal pillar and the distribution of plastic zone when the working face enters, passes through, and exits the overlying oblique coal pillar are obtained.

        (2) Establish a noise reduction algorithm combining ICEEMDAN and DE to denoise the deformation data of coal pillars in the fiber optic grating monitoring section and remove redundant data. Compare the CEEMDAN and EEMD denoising methods, and verify the effectiveness of ICEEMDAN denoising results based on the indicator results. To improve accuracy for subsequent intelligent prediction.

        (3) Establish a GA-LSTM-BP comprehensive prediction model, input the deformation monitoring strain data of coal pillars in the 5^-1# section into the model, and predict the strain photosensitive signal of coal pillars in the underlying section when entering, passing through, and exiting the overlying coal pillars in the working face of the coal pillars. The accuracy is 88% -96%, achieving short-term prediction of deformation strain photosensitive signals of coal pillars in the section within four days. It has been proven that the ICEEMDAN-GA-LSTM-BP comprehensive prediction model is effective in this type of working condition.

         The results of this study are of great significance for ensuring the safe mining of underground coal mines, especially the typical close range legacy oblique coal pillars underlying coal seams represented by the northern Shaanxi region. This provides scientific theoretical and practical data support for the safe mining of this type of working condition and the study of section coal pillar deformation.

[1]王佟, 刘峰, 赵欣等. “双碳”背景下我国煤炭资源保障能力与勘查方向的思考[J/OL]. 煤炭科学技术: 1-8[2024-01-07].

[2]连晓阳. 近距离煤层群开采卸压瓦斯富集规律研究[J]. 煤, 2022, 31(09): 36-38.

[3]白刚, 任杰. 近距离煤层群综放工作面矿压显现规律[J]. 煤, 2022, 31(09): 61-64.

[4]刘润, 袁文华, 洪可等. 近距离煤层上行开采被保护层回采巷道支护技术研究[J]. 建井技术, 2022, 43(04): 1-6.

[5]魏东, 任金武, 张帅等. 采空区下近距离煤层巷道围岩稳定性分析及控制[J]. 能源与环保, 2022, 44(08): 284-289+295.

[6]牛孝田, 孟令海. 极近距离下伏煤层沿空巷道支护技术及应用[J]. 煤炭工程, 2022, 54(08): 26-29.

[7]李林. 陕北浅埋煤层强制放顶工作面矿压显现规律研究[J]. 陕西煤炭, 2015, 34(03): 9-12.

[8]陈建华, 马宝, 董博文. 大柳塔煤矿新构造裂隙控水理论分析[J]. 中国煤炭, 2023, 49(S2): 124-128.

[9]李星达, 周海丰, 冯志忠. 大柳塔煤矿大采高工作面沿空留巷围岩控制研究[J]. 中国煤炭, 2023, 49(S2): 202-214.

[10]杨征, 杨小勇, 王宇等. 区域安全评估模型在煤矿安全管理中的应用研究[J]. 工矿自动化, 2023, 49(12): 94-101+129.

[11]周禹良, 杨雪, 许发强. 综放工作面导水裂隙带高度分布式光纤监测技术[J]. 中国矿业, 2022, 31(12): 108-114.

[12]杜传伟, 胡涛, 李业宏等. 煤巷顶板分布式光纤监测的可行性试验研究[J]. 矿业安全与环保, 2022, 49(05): 81-88.

[13]李雪佳, 池明波, 吴宝杨等. 基于分布式光纤监测的煤矿地下水库层间覆岩裂隙发育规律研究[J]. 中国煤炭, 2022, 48(09): 49-56.

[14]杨旭, 杨贵儒, 陈建强. 缓倾斜特厚煤层综放面区段煤柱合理宽度智能分析与确定研究[J]. 煤炭技术, 2020, 39(10): 1-5.

[15]Xia B, Jia J, Yu B, et al. Coupling effects of coal pillars of thick coal seams in large-space stopes and hard stratum on mine pressure[J]. International Journal of Mining Science and Technology, 2017, 27(6): 965-972.

[16]Zhu Z, Zhang H, Nemcik J, et al. Overburden movement characteristics of top-coal caving mining in multi-seam areas[J]. Quarterly Journal of Engineering Geology and Hydrogeology, 2018, 51(2): 276-286.

[17]Wang X, Wu Y, Li X, et al. Numerical investigation into evolution of crack and stress in residual coal pillars under the influence of longwall mining of the adjacent underlying coal seam[J]. Shock and Vibration, 2019: 2094378.

[18]Zhu W, Chen L, Zhou Z, et al. Failure propagation of pillars and roof in a room and pillar mine induced by longwall mining in the lower seam[J]. Rock Mechanics and Rock Engineering, 2019, 52: 1193-1209.

[19]Shang H, Ning J, Hu S, et al. Field and numerical investigations of gateroad system failure under an irregular residual coal pillar in close‐distance coal seams[J]. Energy Science & Engineering, 2019, 7(6): 2720-2740.

[20]Zhu D, Song X, Li H, et al. Cooperative load‐bearing characteristics of a pillar group and a gob pile in partially caved areas at shallow depth[J]. Energy Science & Engineering, 2020, 8(1): 89-103.

[21]Gao R, Yu B, Meng X. Stress distribution and surrounding rock control of mining near to the overlying coal pillar in the working face[J]. International Journal of Mining Science and Technology, 2019, 29(6): 881-887.

[22]Gao X, Zhang S, Zi Y, et al. Study on optimum layout of roadway in close coal seam[J]. Arabian Journal of Geosciences, 2020, 13: 1-17.

[23]高晓龙, 何峰, 王振伟. 近距离下煤层过遗留煤柱应力集中区研究[J]. 山西焦煤科技, 2013, 37(07): 50-53.

[24]张郑伟. 近距离煤层遗留煤柱下确定沿空掘巷的合理位置[J]. 煤, 2016, 25(03): 30-32.

[25]王少卿. 双系煤层开采上覆遗留煤柱下采场强矿压机理研究[J]. 同煤科技, 2020, 2020(05): 8-11.

[26]梁东辉, 张宏凯, 刘超等. 遗留煤柱下四面临空孤岛工作面矿压显现规律研究[J]. 煤炭科技, 2021, 42(02): 122-125.

[27]葛海军, 冯志忠, 李彩云. 浅埋深孤岛工作面下行开采过上覆遗留煤柱强矿压特征及防治技术[J]. 煤炭科学技术, 2022, 50(S1): 36-41.

[28]白正平, 高振俊. 采空区遗留煤柱下开采动载矿压机理及防治技术研究[J]. 煤炭科学技术, 2022, 50(S1): 23-30.

[29]高乐, 赵斌, 周向文等. 遗留煤柱下近距离特厚煤层临空掘巷合理煤柱尺寸[J]. 煤矿安全, 2022, 53(02):219-225+233 .

[30]张伟光, 张腾飞, 陈俊智等. 近距离煤层群开采遗留煤柱下沿空掘巷煤柱宽度研究[J]. 新疆地质, 2022, 40(04): 542-547.

[31]王存权. 近距离煤层开采斜交过上覆采空区煤柱矿压规律研究[J]. 中国煤炭, 2006(02): 35-37+44+4.

[32]樊志全. 掘进工作面过上覆采空区斜交煤柱巷道顶板管理技术[J]. 山西煤炭, 2007(04): 31-33.

[33]窦凤金, 屠世浩, 吴其. 斜交煤柱下动压巷道稳定性分析[J]. 矿业安全与环保, 2010, 37(02): 50-53.

[34]黄华. 斜交煤柱叠加影响下工作面应力场分布特征研究[J]. 煤矿安全, 2023, 54(01): 109-116.

[35]Zhang J, Zhang Y, Song Z, et al. Study on the mechanism of coal pillar instability in coal seam sections containing gangue[J]. Physics and Chemistry of the Earth, Parts A/B/C, 2023, 132: 103502.

[36]Bao W X, Ma Z W, Lai H P, et al. Deformation mechanism and treatment technology research of coal pillars in acute inclined goafs under expressway[J]. Applied Geophysics, 2023: 1-15.

[37]刘洋, 陆菜平, 王华等. 不规则煤柱变形破坏机理矩张量反演研究[J]. 采矿与安全工程学报, 2023, 40(06): 1201-1209.

[38]王永健, 卢小波, 杜星宇等. 煤柱变形特征与应力分布规律物理相似模型试验研究[J]. 内蒙古煤炭经济, 2023(23): 67-69.

[39]卢帅峰, 刘泗斐, 万志军等. 沿空掘巷窄煤柱变形及控制措施[J]. 矿业研究与开发, 2020, 40(07): 28-31.

[40]原双丰. 端氏煤矿3110工作面开采对煤柱变形及应力影响[J]. 能源技术与管理, 2020, 45(02): 9-12.

[41]李慎锋, 刘兴邦, 郭运刚等. 急倾斜煤层区段煤柱变形规律及应力变化特征[J]. 煤炭技术, 2019, 38(01): 27-29.

[42]Yugay V, Mekhtiyev A, Madi P, et al. Fiber-Optic System for Monitoring Pressure Changes on Mine Support Elements[J]. Sensors, 2022, 22(5): 1735.

[43]Yurchenko A V, Mekhtiyev A D, Bulatbayev F N, et al. The Model of a Fiber-Optic Sensor for Monitoring Mechanical Stresses in Mine Workings[J]. Russian Journal of Nondestructive Testing, 2018, 54: 528-533.

[44]Moffat R, Sotomayor J, Beltrán J F. Estimating tunnel wall displacements using a simple sensor based on a Brillouin optical time domain reflectometer apparatus[J]. International Journal of Rock Mechanics and Mining Sciences, 2015, 75: 233-243.

[45]许时昂, 张平松, 程刚等. 砂土压缩变形传感光缆耦合试验分析与预测模型研究[J/OL]. 岩土力学, 2024-01-06:

[46]王志坚, 郝军. 断层地质条件下竖井井壁变形监测技术研究[J]. 能源技术与管理, 2023, 48(03): 139-141+183.

[47]井庆贺, 朴春德, 崔义等. 立井井壁变形光纤光栅远程实时监测预警系统[J]. 煤矿安全, 2023, 54(04): 232-238.

[48]赵康, 刘李杰, 杜尚宇等. 光纤光栅传感技术在井筒变形监测中的应用[J]. 陕西煤炭, 2021, 40(S2): 128-132.

[49]柴敬, 刘泓瑞, 张丁丁等. 覆岩载荷扰动下平硐围岩变形分析及支护优化[J]. 工矿自动化, 2023, 49(03): 13-22.

[50]柴敬, 韩志成, 雷武林等. 回采巷道底鼓演化过程的分布式光纤实测研究[J]. 煤炭科学技术, 2023, 51(01): 146-156.

[51]程刚, 王振雪, 施斌等. 采动覆岩变形多场光纤神经感知与安全保障体系构建究[J]. 煤炭科学技术, 2023, 51(11): 104-118.

[52]朴春德, 何进洋, 卢毅等. 采动覆岩分布式光纤感测模型试验及沉降预测方法研究[J]. 工程地质学报, 2022, 30(05): 1651-1657.

[53]李延河, 杨战标, 朱元广等. 基于弱光纤光栅传感技术的围岩变形监测研究[J]. 煤炭科学技术, 2023, 51(06): 11-19.

[54]Abe T, Matsumoto M, Hashimoto S. Noise reduction combining time-frequency ε-filter and M-transform[J]. The Journal of the Acoustical Society of America, 2008, 124(2): 994-1005.

[55]Liu Y, Li Y, Lin H, et al. An amplitude-preserved time–frequency peak filtering based on empirical mode decomposition for seismic random noise reduction[J]. IEEE Geoscience and Remote Sensing Letters, 2013, 11(5): 896-900.

[56]Qi B, Zhang H, Zhang X. Time-frequency DOA estimation of chirp signals based on multi-subarray[J]. Digital Signal Processing, 2021, 113: 103031.

[57]Yang B, Tang J, Yang C, et al. High-temperature superconducting cable fault location method based on improved time-frequency domain reflection method and EEMD noise reduction[J]. Mathematical Problems in Engineering, 2021, 2021: 1-10.

[58]Zohrevandi M, Setayeshi S, Rabiee A, et al. Blind separation of underdetermined Convolutive speech mixtures by time–frequency masking with the reduction of musical noise of separated signals[J]. Multimedia Tools and Applications, 2021, 80: 12601-12618.

[59]Gálvez M F S, Elliott S J, Cheer J. Time domain optimization of filters used in a loudspeaker array for personal audio[J]. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2015, 23(11): 1869-1878.

[60]Kim H, Ko Y, Moon H, et al. Delay measurement and split-step time-domain analysis of ring resonator all-pass filters[J]. Journal of the Optical Society of Korea, 2014, 18(6): 766-771.

[61]Peng C, Ma X, Lin G, et al. Improving the time domain response of fractional order digital differentiators by windowing[J]. Signal Processing, 2015, 107: 282-289.

[62]Ye Y, Wang M, Spina D, et al. Time-domain characterization of photonic integrated filters subject to fabrication variations[J]. Journal of Lightwave Technology, 2019, 37(21): 5561-5570.

[63]Chen Y, Ma J. Random noise attenuation by fx empirical-mode decomposition predictive filtering[J]. Geophysics, 2014, 79(3): 81-91.

[64]Obidin M V, Serebrovski A P. Signal denoising with the use of the wavelet transform and the Kalman filter[J]. Journal of Communications Technology and Electronics, 2014, 59: 1440-1445.

[65]San Emeterio J L, Rodriguez-Hernandez M A. Wavelet cycle spinning denoising of NDE ultrasonic signals using a random selection of shifts[J]. Journal of Nondestructive Evaluation, 2015, 34: 1-8.

[66]Rucci M, Hardie R C, Barnard K J. Computationally efficient video restoration for Nyquist sampled imaging sensors combining an affine-motion-based temporal Kalman filter and adaptive Wiener filter[J]. Applied optics, 2014, 53(13): 1-13.

[67]So S, George A E W, Ghosh R, et al. Kalman filter with sensitivity tuning for improved noise reduction in speech[J]. Circuits, Systems, and Signal Processing, 2017, 36: 1476-1492.

[68]Li Y, Su Z, Chen K, et al. Application of an EMG interference filtering method to dynamic ECGs based on an adaptive wavelet-Wiener filter and adaptive moving average filter[J]. Biomedical Signal Processing and Control, 2022, 72: 103344.

[69]Bayat E, Afarideh H, Davani F A, et al. Noise reduction of PGNAA spectrum using empirical mode decomposition technique[J]. Radiation Physics and Chemistry, 2018, 149: 49-53.

[70]He K, Xia Z, Si Y, et al. Noise reduction of welding crack AE signal based on EMD and wavelet packet[J]. Sensors, 2020, 20(3): 761.

[71]Lu W, Zhang L, Liang W, et al. Research on a small-noise reduction method based on EMD and its application in pipeline leakage detection[J]. Journal of Loss Prevention in the Process Industries, 2016, 41: 282-293.

[72]Chen K, Zhang X, Liu Y, et al. An improved denoise method based on EEMD and optimal wavelet threshold for model building of OPAX[J]. Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering, 2021, 235(14): 3530-3544.

[73]Cheng X, Mao J, Li J, et al. An EEMD-SVD-LWT algorithm for denoising a lidar signal[J]. Measurement, 2021, 168: 108405.

[74]Pan L, Liu K, Jiang J, et al. A de-noising algorithm based on EEMD in Raman-based distributed temperature sensor[J]. IEEE Sensors Journal, 2016, 17(1): 134-138.

[75]Haohui W, Xiaowei S, Yang X. Noise source identification method for a carpet tufting machine based on CEEMDAN-AIC[J]. Shock and Vibration, 2021, 2021: 1-13.

[76]Zhang J, Guo Y, Shen Y, et al. Improved CEEMDAN–wavelet transform de-noising method and its application in well logging noise reduction[J]. Journal of Geophysics and Engineering, 2018, 15(3): 775-787.

[77]Zheng Y, Li S, Xing K, et al. A novel noise reduction method of UAV magnetic survey data based on CEEMDAN, permutation entropy, correlation coefficient and wavelet threshold denoising[J]. Entropy, 2021, 23(10): 1309.

[78]Cheikh F, Benhassine N E, Sbaa S. Fetal phonocardiogram signals denoising using improved complete ensemble (EMD) with adaptive noise and optimal thresholding of wavelet coefficients[J]. Biomedical Engineering/Biomedizinische Technik, 2022, 67(4): 237-247.

[79]Li C, Peng T, Zhu Y, et al. Noise reduction method of shearer’s cutting sound signal under strong background noise[J]. Measurement and Control, 2022, 55(7-8): 783-794.

[80]Sibtain M, Li X, Azam M I, et al. Applicability of a three-stage hybrid model by employing a two-stage signal decomposition approach and a deep learning methodology for runoff forecasting at Swat River catchment, Pakistan[J]. Polish Journal of Environmental Studies, 2021, 30(1): 369-384.

[81]Pal S, Mitra M. Empirical mode decomposition based ECG enhancement and QRS detection[J]. Computers in biology and medicine, 2012, 42(1): 83-92.

[82]Feng H L, Fang Y M, Xiang X Q, et al. A data-driven noise reduction method and its application for the enhancement of stress wave signals[J]. The Scientific World Journal, 2012, 2012: 353081.

[83]Chen Y, Ma J. Random noise attenuation by fx empirical mode decomposition predictive filtering: Geophysics, 2014, 79(3): 81-91.

[84]Li Y, Xu F. Signal processing and identification on the surface of Pinus massoniana Lamb. glulam using acoustic emission and improvement complete ensemble empirical mode decomposition with adaptive noise[J]. Measurement, 2019, 148: 106978.

[85]郭代华. 基于改进多尺度散布熵与自适应支持向量机的滚动轴承故障诊断[J]. 轴承, 2022, (11): 76-82.

[86]陈焱, 郑近德, 潘海洋等. 复合多尺度反向散布熵在轴承故障诊断中的应用[J]. 振动与冲击, 2022, 41(19): 55-63.

[87]李瑾, 行鸿彦, 王海峰等. 基于精细复合多尺度散布熵的墙体内管道敲击探测方法[J]. 电子测量技术, 2023, 46(02): 25-30.

[88]宋明瑞, 郭佑民, 刘运航等. 基于小波包散布熵-mRMR特征选取与HHO-KELM的轴承故障诊断方法[J]. 噪声与振动控制, 2023, 43(05): 154-160.

[89]Ghasemi E, Ataei M, Shahriar K. Prediction of global stability in room and pillar coal mines[J]. Natural hazards, 2014, 72: 405-422.

[90]Ahmad M, Al-Shayea N A, Tang X W, et al. Predicting the pillar stability of underground mines with random trees and C4. 5 decision trees[J]. Applied Sciences, 2020, 10(18): 6486.

[91]Dai J, Shan P, Zhou Q. Study on intelligent identification method of coal pillar stability in fully mechanized caving face of thick coal seam[J]. Energies, 2020, 13(2): 305.

[92]Li N, Zare M, Yi C, et al. Stability risk assessment of underground rock pillars using logistic model trees[J]. International journal of environmental research and public health, 2022, 19(4): 2136.

[93]Yadav A, Singh G S P, Behera B. A Machine Learning Model for Evaluation of Chain Pillar Stability in Deep Longwall Workings in India[J]. Mining, Metallurgy & Exploration, 2023, 40(6): 1-19.

[94]周健, 李夕兵, 史秀志等. 用Fisher判别法和支持向量机预测地下矿山矿柱稳定性(英文)[J]. Transactions of Nonferrous Metals Society of China, 2011, 21(12): 2734-2743.

[95]陈顺满, 吴爱祥, 王贻明. 基于贡献率和未确知测度理论的矿柱稳定性预测[J]. 武汉大学学报(工学版), 2017, 50(05): 697-703.

[96]柴敬, 张锐新, 欧阳一博等. 基于贝叶斯算法优化的CatBoost矿压显现预测[J].工矿自动化, 2023, 49(07): 83-91.

[97]柴敬, 王润沛, 杜文刚等. 基于XGBoost的光纤监测矿压时序预测研究[J].采矿与岩层控制工程学报, 2020, 2(04): 64-71.

[98]Cheng P, Chen D, Wang J. Research on underwear pressure prediction based on improved GA-BP algorithm[J]. International Journal of Clothing Science and Technology, 2021, 33(4): 619-642.

[99]Cheng P, Chen D, Wang J. Research on prediction model of thermal and moisture comfort of underwear based on principal component analysis and Genetic Algorithm–Back Propagation neural network[J]. International Journal of Nonlinear Sciences and Numerical Simulation, 2021, 22(6): 607-619.

[100]Wang J. Analysis of sports performance prediction model based on GA-BP neural network algorithm[J]. Computational Intelligence and Neuroscience, 2021, 2021: 4091821.

[101]Zheng L. Research on application of improved genetic algorithm and bp neural network in air quality evaluation[J]. FRESENIUS ENVIRONMENTAL BULLETIN, 2022, 31(6): 6043-6052.

[102]Chandra R, Goyal S, Gupta R. Evaluation of deep learning models for multi-step ahead time series prediction[J]. Ieee Access, 2021, 9: 83105-83123.

[103]Chen D, Zhang J, Jiang S. Forecasting the short-term metro ridership with seasonal and trend decomposition using loess and LSTM neural networks[J]. IEEE Access, 2020, 8: 91181-91187.

[104]Chen Y. Voltages prediction algorithm based on LSTM recurrent neural network[J]. Optik, 2020, 220: 164869.

[105]Lu W, Rui H, Liang C, et al. A method based on GA-CNN-LSTM for daily tourist flow prediction at scenic spots[J]. Entropy, 2020, 22(3): 261.

[106]Jiang Y, Zhan Z H, Tan K C, et al. Optimizing niche center for multimodal optimization problems[J]. IEEE Transactions on Cybernetics, 2021, 53(4): 2544-2557.

[107]Liu Y, Shen W, Zhang C, et al. Agent-based simulation and optimization of hybrid flow shop considering multi-skilled workers and fatigue factors[J]. Robotics and Computer-Integrated Manufacturing, 2023, 80: 102478.

[108]Subbaiyan R, Ganesan A. Modeling and optimization of antibacterial effect of lichen‐associated bacteria, Bacillus subtilis KSRLAB3 strain against marine fouling bacteria, Vibrio alginolyticus[J]. Biotechnology and Applied Biochemistry, 2023, 70(5): 1616-1628.