Prediction model of surrounding rock deformation in doublecontinuous-arch tunnel based on the ABC-WNN

Purpose–The wavelet neural network(WNN)has the drawbacks of slow convergence speed and easy falling into local optima in data prediction.Although the artificial bee colony(ABC)algorithm has strong global optimization ability and fast convergence speed,it also has the drawbacks of slow speed while finding the optimal solution and weak optimization ability in the later stage.Design/methodology/approach–This article uses an ABC algorithm to optimize the WNN and establishes an ABC-WNN analysis model.Based on the example of the Jinan Yuhan underground tunnel project,the deformation of the surrounding rock of the double-arch tunnel crossing the fault fracture zone is predicted and analyzed,and the analysis results are compared with the actual detection amount.Findings–The comparison results show that the predicted values of the ABC-WNN model have a high degree of fitting with the actual engineering data,with a maximum relative error of only 4.73%.On this basis,the results show that the statistical features of ABC-WNN are the lowest,with the errors at 0.566 and 0.573,compared with the single back propagation(BP)neural network model and WNN model.Therefore,it can be derived that the ABC-WNN model has higher prediction accuracy,better computational stability and faster convergence speed for deformation.Originality/value–This article uses firstly the ABC-WNN for the deformation analysis of double-arch tunnels.This attempt laid the foundation for artificial intelligence prediction in deformation analysis of multiarch tunnels and small clearance tunnels.It can provide a new and effective way for deformation prediction in similar projects.

Chaotic time series prediction for surrounding rock's deformation of deep mine lanes in soft rock

Based on the measured displacements,the change laws of the effect of distance in phase space on the deformation of mine lane were analyzed and the chaotic time series model to predict the surrounding rocks deformation of deep mine lane in soft rock by nonlinear theory and methods was established.The chaotic attractor dimension(D) and the largest Lyapunov index(Emax) were put forward to determine whether the deformation process of mine lane is chaotic and the degree of chaos.The analysis of examples indicates that when D>2 and Emax>0,the surrounding rock's deformation of deep mine lane in soft rock is the chaotic process and the laws of the deformation can still be well demonstrated by the method of the reconstructive state space.Comparing with the prediction of linear time series and grey prediction,the chaotic time series prediction has higher accuracy and the prediction results can provide theoretical basis for reasonable support of mine lane in soft rock.The time of the second support in Maluping Mine of Guizhou,China,is determined to arrange at about 40 d after the initial support according to the prediction results.

Mechanical analysis on deformation of surrounding rock with road-in packing of gob-side entry retaining in fully-mechanized sub-level caving face

Based on the movement regularity of surrounding rock with road-in packing of gob-side entry retaining in fully-mechanized sub-level caving face(RPGERFCF),the me- chanical model of its surrounding rock was established and the calculating formulas of the deformation of the roof,coal wall and filling body were attained.By the mechanical analy- sis to the deformation of the surrounding rock of RPGERFCF,the major factors influencing the deformation of the surrounding rock were found out and the technologic approaches reduced the deformation and enhanced the stability of the surrounding rock were put for- ward.Consequently,the scientific bases were provided for the stability control of the sur- rounding rock of RPGERFCF.

Time effect and prediction of broken rock bulking coefficient on the base of particle discrete element method

Bulking characteristics of gangue are of great significance for the stability of goafs in mining overburden in the caving zones.In this paper,a particle discrete element method with clusters to represent gangue was adopted to explore the bulking coefficient time effect of the broken rock in the caving zone under three-dimensional triaxial compression condition.The phenomena of stress corrosion,deformation,and failure of rock blocks were simulated in the numerical model.Meanwhile,a new criterion of rock fragments damage was put forward.It was found that the broken rock has obvious viscoelastic properties.A new equation based on the Burgers creep model was proposed to predict the bulking coefficient of broken rock.A deformation characteristic parameter of the prediction equation was analyzed,which can be set as a fixed value in the mid-and long-term prediction of the bulking coefficient.There are quadratic function relationships between the deformation characteristic parameter value and Talbot gradation index,axial pressure and confining pressure.

黄土盾构隧道开挖围岩扰动特性模型试验研究

为了探究不同含水率和埋深等工况下的黄土盾构隧道开挖对围岩的扰动作用特征,采用相似模型试验,首先通过三轴试验测定了不同含水率下原状黄土物理参数及强度指标,通过大量试配得到了不同含水率下与原状黄土强度指标参数相似的试验用土。其后,考虑盾构隧道盾尾间隙特征,开展不同含水率及埋深等组合工况下盾构开挖模拟试验,通过微型土压力传感器、百分表等监测元件以及数字图像技术等手段,分析了不同工况下地层变形、地表沉降和围岩应力的变化规律。研究发现:含水率较低时,围岩的自稳能力强;含水率越高,埋深越大,开挖对地层的扰动作用也越大;地表最大沉降值与含水率呈正相关,与埋深呈负相关;围岩剩余应力随含水率和埋深的增大而增大,但当含水率增大至一定值(26.6%)时,围岩剩余应力骤减;基于不同含水率下的围岩应力及变形发展规律,可将黄土含水率分为自稳、形变以及松动含水率,基于含水率和埋深引起的围岩松动情况,可将不同工况下的黄土盾构隧道围岩压力作用模式按照形变压力和松动压力计算,以更加适应黄土地层的特性。

节理巷道围岩卸荷变形试验研究

自然界中的岩体在长期的地质构造运动作用下,内部往往发育不同尺度的节理,而巷道围岩的稳定性与节理的发育密切相关。为研究节理对巷道围岩开挖卸荷变形的影响,采用课题组的开挖卸荷模型试验系统,对不同节理尺寸水泥砂浆围岩试件开展了系列试验。研究结果表明:(1)巷道围岩开挖卸荷变形主要发生在卸荷阶段,维持阶段变形继续存在,但节理对其卸荷变形无明显影响。此阶段,卸荷变形程度显著降低并逐渐趋于稳定,其应变增量大约为100με;(2)与无节理试件相比,含节理试件S-1和S-2的应变平均降低幅度超过70%,远高于S-3,即节理尺寸越大,卸荷变形程度越大,卸荷作用越明显;(3)试件在不同方向的应变差异较大,切向应变均大于径向应变,含节理试件尤为突出。

洛川隧道围岩变形规律模型试验研究

以洛川隧道DK194+835为研究断面,开展不同埋深下隧道模型试验研究。通过各种试验确定原型、相似材料土和衬砌的参数,利用3D打印技术研制出一套新型衬砌材料及连接方式较好的模拟了实际工程中喷射混凝土、钢架、超前小导管。利用自制多点位移计等各种监测原件采集开挖过程中围岩内部变形及地表沉降数据。试验表明:可通过拼装的方式在模型试验中模拟隧道的分布支护,可使用滑动式连接件链接相邻位置的石膏块;不同测点竖向位移均经历缓慢增长(开挖面远离监测断面)、迅速增长(开挖面接近监测断面)、逐步稳定(开挖面经过监测断面)3个阶段。随埋深增加,监测断面前期变形(开挖面远离、接近监测断面)占比减小;地表沉降经历缓慢增长、迅速增长、逐步稳定3个阶段。随埋深增加,监测断面前期地表沉降占比减小。

TBM隧道岩石可掘性评价指标及其应用研究综述

TBM(Tunnel Boring Machine)掘进施工成本中,刀具的磨损占比很高,这通常是由于TBM的刀具设计与岩石强度及硬度不匹配。因此需要对TBM隧道岩石进行可掘性评估,为刀具设计及施工参数确定提供依据。岩石可掘性评价在TBM围岩分级、掘进效率预测等方面十分重要,是评估TBM施工效率与成本的关键,但隧道TBM开挖过程中岩石可掘性的评价通常相当复杂,需要考虑许多参数,且至今国内外对可掘性这一指标尚未有标准化定义。通过文献检索,本文针对可掘性指标的定义,可掘性的研究应用等方面研究进展进行综述。结合已有的研究成果,对TBM可掘性未来的研究方向进行了展望。

应用微芯桩传感器的拉裂型边坡危岩体临崩倾斜变形特征现场实测研究

边坡危岩体崩塌的监测预报一直是地质灾害防灾研究的重点和薄弱环节。基于微电子机械系统(micro-electromechanical system,简称MEMS)技术构建了危岩体微小倾斜角度与强振加速度的“采集-计算-传输”机制,研制了微芯桩传感器,实现了危岩体的低功耗长期监测。通过拉裂型危岩体崩塌现场实测分析,发现了拉裂型危岩体具有倾斜变形加速并伴随强振动频次、幅值增加的崩塌前兆。探明了临崩加速倾斜阶段累计倾斜变形量与倾斜变形速率之间具有显著指数关系,且倾斜速率倒数与距离崩塌时长具有线性相关性,进而建立了“倾斜速率倒数法”崩塌时间预测模型,形成了基于MEMS倾斜角度传感数据特征的预测模型实时应用算法流程。研究成果可对崩塌灾害的监测预警产生积极的促进作用。

基于LSTM-ARIMA模型的隧道围岩变形预测方法研究

为了在隧道施工过程中对隧道围岩变形进行精准预测,以中东某隧道为研究对象,基于隧道围岩监测数据使用LSTM(long short-term memory)和ARIMA(autoregressive integrated moving average)模型进行拟合并预测,进一步通过方差倒数法建立组合模型,采用多个统计学指标对建立的模型预测结果进行对比分析。结果表明,组合模型解决了ARIMA模型对非平稳数据预测精度较差的问题,充分发挥了LSTM和ARIMA模型各自的优势,能够更准确地捕捉数据特征和趋势,提高了对隧道围岩变形预测的准确性和鲁棒性,可为隧道工程的安全施工提供可靠的支持和指导。

Shield Excavation Analysis: Ground Settlement & Mechanical Responses in Complex Strata

This study delves into the effects of shield tunneling in complex coastal strata, focusing on how this constructionmethod impacts surface settlement, the mechanical properties of adjacent rock, and the deformation of tunnelsegments. It investigates the impact of shield construction on surface settlement, mechanical characteristics ofnearby rock, and segment deformation in complex coastal strata susceptible to construction disturbances. Utilizingthe Fuzhou Binhai express line as a case study, we developed a comprehensive numerical model using theABAQUS finite element software. The model incorporates factors such as face force, grouting pressure, jack force,and cutterhead torque. Its accuracy is validated against field monitoring data from engineering projects. Simulationswere conducted to analyze ground settlement and mechanical changes in adjacent rock and segments acrossfive soil layers. The results indicate that disturbances are most significant near the excavation zone of the shieldmachine, with a prominent settlement trough forming and stabilizing around 2.0–3.0 D from the excavation. Theexcavation face compresses the soil, inducing lateral expansion. As grouting pressure decreases, the segmentexperiences upward buoyancy. In mixed strata, softer layers witness increased cutting, intensifying disturbancesbut reducing segment floatation. These findings offer valuable insights for predicting settlements, ensuring segmentand rock safety, and optimizing tunneling parameters.

综采工作面大断面切眼围岩稳定控制研究

综采工作面大断面切眼围岩的稳定性是影响综采工作面正常设备安装与回采的关键因素,以小保当一号煤矿112203综采工作面大断面切眼为研究对象,通过理论分析研究了112203综采工作面大断面切眼顶板变形机理及理论支护参数。采用离散元数值模拟软件建立了UDEC Trigon模型,研究了支护强度对二次成巷顶板裂隙演化规律、破坏模式和损伤程度的影响规律。数值模拟结果表明:合理的支护技术能够控制顶板微裂纹的扩展降低宏观裂隙的发育高度。长短锚索联合支护后顶板岩层中存在的岩石桥能够有效的限制宏观裂缝的形成以及它们之间的相互作用,特别是对交界面区域的重点支护能够降低二次成巷顶板裂隙的发育高度,减弱深部大断面切眼顶板岩层的损伤程度。现场试验表明,采用加长锚索以及单体液压支柱的补强支护后,112203综采工作面大断面切眼两帮移近量稳定在350 mm左右,顶底板移近量稳定在550 mm左右,顶板未出现明显离层,最大顶板离层量为2.4 mm。本文的理论分析及数值模拟有助于理解综采工作面大断面切眼顶板破坏模式,同时为其控制技术参数的设计提供了方法。

基于灰色理论的采动围岩变形混沌时序预测

为实现地下矿山岩体开挖后的变形预测,及时评价围岩稳定性。本文基于监测围岩变形的时间序列,采用G-P算法确定了时间序列重构相空间的最佳嵌入维数和时间延迟,通过对时间序列的相空间重构,分析了其最邻近相点的动态演化规律,并结合灰色预测理论对围岩变形时间序列进行了预测。结果表明,围岩变形时间序列的最佳嵌入维数和时间延迟均为3,最邻近相点平均距离越大,围岩变形的混沌特征越明显,其内在动力系统越复杂,采用灰色理论可以实现对采动围岩变形量的短期精确预测,基于最邻近相点和变形预测结果,可以对围岩稳定状态进行识别,为地下矿山开采过程中围岩稳定性评价提供新的思路。

沿空留墙开采巷道围岩变形分析与预测

针对无煤柱沿空留墙开采中巷道围岩变形量过大的问题,以某煤矿1315无煤柱开采工作面为工程背景,采用数值模拟、理论分析和工程试验的方法,对二次开采扰动下巷道围岩变形规律及机理进行了研究。研究结果表明:较窄及较高的柔模墙会导致更大的岩体变形;构建了工作面前方巷道围岩最大变形量预测模型,并经验算知拟合误差小于3%;使用预测模型预测并对施工方案进行修正后,经过现场检测可以进行安全生产,验证了该模型的准确性。

滑坡-隧道正交体系变形特性试验研究

【目的】对于滑坡-隧道正交体系,滑坡的变形失稳是引发隧道病害的重要原因。为了研究滑坡-隧道正交体系在滑坡失稳过程中的宏观变形特性,【方法】以阳坡里隧道为研究对象,使用自主研发的牵引式滑坡分级滑动模拟试验装置设计开展了12组室内模型试验,研究了在滑坡-隧道正交体系中滑坡失稳情况下隧道埋深、隧道在滑体内的布置位置以及滑动段位置对“洞周位移指数”的影响。【结果】结果显示:滑坡发生失稳时的坡面宏观变形存在一定规律,通常表现为坡面的后缘裂缝以及次级裂缝,且坡面位移沿次级裂缝存在明显分级情况;在其他变量相同的情况下,隧道在滑坡体内部埋深越大、隧道布置位置越靠近滑坡体前缘、滑动段越靠近滑坡中段时,滑坡滑动对隧道周围0.5~1.0倍隧道直径范围内土体的位移影响越大;滑动段位置对洞周位移指数影响最大,当滑动段分别位于滑坡前段、中段和后段时,洞周位移指数分别为小于0.8、大于1.8和介于1.0~1.5之间。【结论】研究成果可为滑坡隧道的变形演化机理、滑坡诱发隧道病害的预测预报以及防治技术等研究提供参考。

基于NAR神经网络和R/S分析法的隧道围岩变形预测分析

为研究隧道围岩变形非线性特点,采用NAR神经网络和R/S分析法,对隧道围岩变形量和变形趋势进行分析。通过NAR神经网络对变形监测样本进行误差分析,认为NAR神经网络对围岩变形短期预测时的误差小精度高。运用R/S分析法对各变形时间序列进行重标极差分析,获得各时序的Hurst指数,分析其与围岩变形趋势的关系,并通过Hurst指数对隧道围岩变形趋势进行判定。结果表明:算例中的断面围岩变形仍然会呈增长趋势,但增长幅度在减小,且水平收敛的趋势性强于拱顶沉降,说明前者受随机扰动影响较小,后期稳定性相对更高。通过运用R/S分析法进行时间序列分析,不仅为围岩变形趋势预判提供了Hurst指数判据,同时也为围岩稳定性分析及治理提供了一种依据。

反复扰动下巷道围岩损伤变形预测模型及应用

巷道稳定性对煤矿通风及运输有着重要作用。针对多次扰动下深部巷道围岩的损伤变形范围计算问题,以马蹄沟煤矿3507工作面回风顺槽为工程背景,基于非线性岩体强度参数(内摩擦角、黏聚力)表达式及锚杆最大轴力与围岩塑性区、松动区半径的关系式,根据巷道施工过程中围岩所受不同类型的扰动,分析各个阶段巷道围岩的强度参数及变形破坏范围,包括开挖扰动后的首次弱化,初期支护后的首次补强,预裂爆破后的二次弱化,最后利用锚固岩体塑性区半径作为等效二次开挖半径,建立了反复扰动损伤后巷道围岩塑性区及破裂区范围的预测公式。根据上述反复扰动下的强度参数分析及变形破坏范围预测公式,计算实际工程中顺槽的塑性区及破裂区范围,并给出了合理的二次加固设计方案。结果表明,二次加固方案实施后回风顺槽围岩变形控制效果显著,比二次加固前围岩的变形量减少了68%。

基于灰色-马尔可夫链的隧道围岩变形预测研究

隧道工程施工中,围岩变形是一种常见的工程问题,当变形量达到一定数值时,会影响工程质量,给施工人员带来安全隐患,延误工期。因此,隧道围岩变形预测是保证施工安全,以及工程质量的重要措施。隧道围岩的变形在受到地质构造、地层岩性、应力场、地下水、开挖方式等多种因素的综合影响下,具有时间序列的单调增长性和随机性的特点,针对该特征,将灰色模型预测方法和马尔可夫链概率转移方法结合起来,建立灰色-马尔可夫链模型对围岩的变形进行预测。该预测方法是利用GM(1,1)模型的预测数列增长的特点,来预测围岩变形的宏观发展趋势,在此基础上应用马尔可夫链确定位移时序的状态转移概率矩阵,通过对状态的划分、实测值与灰色拟合值的绝对误差及相对误差等指标的分析,对围岩变形的发展趋势进行更为精确的预测。通过两水隧道算例,隧道围岩变形的计算结果与实测值吻合较好,表明所建立的灰色-马尔可夫链模型是正确的,在隧道围岩变形预测中具有广泛推广应用价值。

西山坪隧道穿煤及采空区围岩变形特性与数值模拟研究

结合渝(重庆)合(合川)高速公路西山坪隧道新奥法施工监测实践,分析了初期支护条件下隧道左线穿煤及采空区(LK35+360～LK35+560)围岩的变形特征,并对穿煤及采空区围岩的位移和应力特性进行了施工动态有限元数值模拟研究,验证了位移监测资料的正确性.为制定采空区处理措施和优化后期支护方案提供了信息.

基于非齐次指数函数灰色模型的隧道围岩变形预测

准确地测量、预测围岩变形是保证隧道施工安全的重要措施之一。围岩变形具有时间序列的单调增长性和随机性等特点,针对其特点,文章采用常规GM(1,1)模型、齐次指数函数灰色模型、非齐次指数函数灰色模型,对隧道的围岩变形进行了预测与对比分析。结果表明,常规GM(1,1)模型、齐次指数函数灰色模型、非齐次指数函数灰色模型三种模型的中误差分别为7.16%、5.01%、2.99%,最终沉降预测值相对误差分别为-8%、-5.52%、-3.05%。非齐次指数函数灰色模型具有较高的精度,在隧道围岩变形预测中具有广泛推广的应用价值。