基于隧道掘进机掘进过程的岩体状态感知方法

针对现有技术无法预先、实时获取隧道掘进机（TBM）掌子面岩体状态参数的问题,提出基于TBM掘进过程监测的岩体状态感知方法. 以吉林引松供水工程TBM施工隧道为依托,分析TBM掘进过程中掘进参数的变化规律,建立TBM掘进参数与岩体参数数据库,研究TBM设备参数和在掘岩体参数之间的相互关系. 分别采用分步回归和聚类分析的方法建立岩机关系模型,利用监测TBM掘进参数实时感知岩石强度、体积节理数和围岩等级等参数. 以石灰岩和花岗岩地层为例,对TBM在掘岩体参数的预测值与实际值进行对比. 结果表明,利用提出的岩体状态感知方法预测的岩石抗压强度UCS和体积节理数与实际值的误差小于18%,预测当前围岩等级与实际岩体状态基本一致,验证了研究结果的准确性.     

基于现场数据的TBM掘进速率研究

为了研究TBM掘进速率在不同地质条件下的变化规律,基于吉林引松供水隧道工程开敞式TBM现场掘进数据,将TBM刀盘破岩过程分为3个阶段：挤压阶段、起裂阶段和破碎阶段,并对破碎阶段应用统计回归方法,分析在不同岩石饱和单轴抗压强度、完整性系数的条件下,TBM刀盘贯入度与刀盘推力、刀盘扭矩的关系.研究表明,在特定施工条件下,刀盘贯入度随刀盘推力增大呈幂函数曲线增长,随刀盘扭矩增大呈线性关系增长,增长率与岩石饱和单轴抗压强度、完整性系数密切相关.进一步建立对于不同强度、完整性岩石的掘进机掘进速率模型,进行实际工程施工预测,预测结果的平均相对误差都低于16%,表明模型预测精度较高,可以为实际工程施工中操作参数的优化和不良地质条件的捕捉提供帮助.     

基于局部线性嵌入和支持向量机回归的TBM施工参数预测

依托吉林引松工程开展隧道掘进机（TBM）施工参数预测研究,提出TBM施工数据分段提取算法,提取上升段前30 s的总推进力、刀盘转速、推进速度、刀盘扭矩、刀盘转速电位器设定值、推进速度电位器设定值、贯入度、贯入度指数(FPI)、扭矩切深指数(TPI)9个参数作为输入;通过局部线性嵌入（LLE）完成对上升段数据特征的降维;基于支持向量机回归（SVR）建立TBM施工控制参数（推进速度、刀盘转速）和负载参数（总推进力、刀盘扭矩）预测模型. 分析是否结合前一掘进循环的FPI、TPI指数进行预测对预测效果的影响. 结果表明,上述方法在推进速度、刀盘转速、总推进力、刀盘扭矩的预测中均取得了较好的预测效果,平均预测绝对百分比误差均小于15%,验证了该预测方法的有效性,该方法可以为TBM现场施工提供指导.     

TBM盘形滚刀破岩过程的数值研究

采用ANSYS/LS-DYNA对TBM(tunnel boring machine)滚刀切削岩石的过程进行动态模拟和动力学分析,研究了破岩过程中滚刀的受力情况和滚刀贯入度及滚动速度对切削力的影响规律.结果表明,当岩石单轴抗压强度为45 MPa时,滚刀承受的侧向力、滚动力及正向力的平均值分别约为0、0.45、4.5 k N,在该工况下滚刀的最佳贯入度及滚动速度分别为10 mm和3.6 r/min.研究结果为工程人员在次硬围岩的工况下设计工作参数提供了合理依据.     

刀盘掘进过程动态仿真

刀盘是岩石隧道掘进机(TBM)开挖岩石的关键部件,通过试验或者现场施工数据得到其与围岩的相互作用规律极为困难。利用数值模拟方法,在ABAQUS/Explicit环境下建立了模拟刀盘掘进的三维分析模型。采用扩展的DruckerPrager非线性弹塑性模型作为岩体的本构模型;应用包含单元删除功能的损伤失效准则模拟切屑的形成及分离,并基于显式积分算法实现了TBM刀盘掘进全物理过程的直接数值模拟,得到了刀盘的动态掘进载荷以及掌子面岩体的损伤失效状态。仿真结果表明:对于所选定的岩石力学参数,当推进距离达到8.5 mm时,掌子面岩体全面损伤,刀盘进入稳定掘进阶段;在掘进过程中,刀盘载荷波动剧烈,其第1阶主频约为刀盘转动频率的2倍。上述模拟方法可以为TBM掘进过程的分析提供有效的工具。     

TBM滚刀回转破岩性能数值分析

针对隧道掘进机(tunnel boring machine,TBM)刀盘设计过程中盘形滚刀布局的刀间距和贯入度问题,综合岩石力学、弹塑性力学和断裂力学,并运用有限元方法建立了TBM刀盘滚刀的动态破岩三维模型.通过与线切割实验对比验证了模型的正确性和有效性,并在此基础上分析了滚刀的回转破岩,得到刀间距和贯入度对滚刀切削力及比能的影响规律.结果表明:随着刀间距的增加,滚刀所受法向力将会逐渐增大,而其切向力基本保持不变,比能增加先减小后变大,在刀间距为60 mm附近取得最小值;法向力和切向力随着贯入度的增加而增大,比能随着贯入度增加而减小.     

多滚刀顺次作用下岩石破碎模拟及刀间距分析

相邻滚刀刀间距设计是全断面岩石掘进机(TBM)刀盘设计的关键技术之一,刀间距设计的合理与否直接关系到刀盘刀具掘进效率和寿命.刀间距设计不仅与岩石边界条件、刀盘掘进参数及刀具参数有关,而且与刀盘结构相互耦合相互影响,且相邻滚刀之间是一种顺次破碎岩石的过程.基于有限元岩石破碎仿真平台RFPA2D,考虑相邻多滚刀的顺次约束关系,分别以2种典型岩石(泥质粉沙岩和花岗片麻岩)为边界条件,建立多滚刀顺次作用下垂直压入岩石的破碎仿真模型,模拟多滚刀在顺次压入和同时压入岩石的仿真过程,建立了刀间距与岩石破碎能量之间的映射关系,进而建立了多滚刀最优刀间距下顺次角度与岩石破碎能量之间的映射关系,通过此映射关系可以确定滚刀在刀盘上不同位置的最优刀间距和最优的顺次角度,并为下一步滚刀在刀盘盘面上的布置设计提供设计依据.     

基于随钻参数的岩石强度预测与可钻性识别（英文）

快速获取岩石力学参数和准确识别岩石可钻性是指导不同规模钻进工程(钻井、钻孔)和岩石开挖工程安全施工的重要前提。基于4次微钻实验采集的281组钻进参数和岩石力学参数建立数据库。数据库中的随钻参数包括钻进力(F)、扭矩(T)、转速(N)和钻进速度(V),以此计算出比能(SE)和可钻性指数(Id)。以这些参数为输入参数,采用拟合回归分析和机器学习回归方法预测岩石的单轴抗压强度。此外,根据岩石单轴抗压强度(UCS)、抗拉强度(BTS)、磨蚀指数(CAI)和硬度(HL),通过TOPSIS-RSR方法实现岩石可钻性分类,利用机器学习分类方法感知和识别岩石可钻性。在预测和识别过程中,比较不同方法的精度,确定最优模型。研究方法和结论可为岩石强度的实时原位测量和地层可钻性识别提供新途径,为提高岩石钻进和开挖效率、保障施工安全提供依据。     

基于优化BP神经网络的TBM性能预测

由于隧道掘进机(tunnel boring machine,TBM)掘进速度与机器参数、岩体参数之间的非线性关系复杂,难以准确预测,为了构建可靠的TBM性能预测模型,分析TBM掘进速度的主要影响因素,提出应用模拟退火算法(SA)和遗传算法(GA)优化BP神经网络的TBM性能预测模型,并使用吉林引松供水工程的TBM数据库对GA-BP模型和SA-BP模型进行训练测试。结果表明,与传统BP神经网络方法相比,优化后的模型预测泛化性更好,且精度明显提高。优化后的BP神经网络能在一定程度上克服易陷入局部最优的缺陷,应用于TBM性能预测具有良好表现。     

冷补沥青混合料疲劳性能简化试验

目的 提出评价冷补沥青混合料疲劳性能的简化试验方法,从而快捷地评价材料质量.方法 根据美国材料试验协会的标准对冷补沥青混合料的疲劳性能进行研究,应用动态圆锥贯入仪获得贯入指数;通过多元线性回归软件(SPSS)建立预估冷补沥青混合料疲劳次数和疲劳试验中所施加的应力的预测模型;为了检验模型的准确性,将其他两种冷补沥青混合料的试验参数与模型中的进行分析对比.结果 冷补沥青混合料的疲劳寿命与贯入指数呈现正相关关系(R2=0.889);疲劳试验施加的应力的数学倒数与贯入指数呈现负相关关系(R2=0.808).结论 笔者提出的简化试验方法 可通过贯入指数简便地预测冷补沥青混合料的疲劳性能,为优选材料提供技术支持.     

基于XGBoost的隧道掘进机操作参数智能决策系统设计

为了实现隧道施工的同质化,提出基于极端梯度提升算法（XGBoost）预测模型的隧道掘进机（TBM）操作参数的智能决策方法. 定义场操作系数指数（FOI）作为替代传统场切深指数（FPI）的围岩级别特征参数,使用XGBoost算法建立预测模型以实现对FOI的预测,对围岩级别进行预测、判断. 通过对优秀司机在特定FOI下TBM操作参数的选择,建立专家模型实现FOI与特定TBM操作参数的关联,实现TBM操作参数的智能决策. 使用引松工程的现场数据进行对比实验,结果表明,设计的TBM操作参数的智能决策系统能够实现对优秀的TBM司机操作参数决策的复现,相比于以FPI为特征参数的传统智能决策系统,新系统的推进速度和刀盘转速两部分的平均相对误差分别下降8.84 %和7.97 %.     

变转速泵控模拟盾构刀盘驱动系统研究

设计了1.8 m土压平衡(EPB)模拟试验盾构的刀盘驱动液压系统,介绍了该液压驱动系统的工作原理和控制方法,该系统采用了变转速泵控技术.通过统计分类的模式识别方法分析了1.8 m试验盾构的掘进过程,以盾构掘进的场切深指数（FPI）、扭矩切深指数（TPI）构成了掘进土层状况的特征空间,基于土层识别及刀盘驱动功率效能评价建立了盾构刀盘转速专家控制方法.建立该液压驱动系统的AMESim仿真模型,仿真研究了液压系统的效率、开环和闭环调速性能.试验研究表明,该液压系统开环调速性能稳定,但刀盘转速波动较大.     

混合遗传算法求解包含柔性工艺的作业车间调度问题

针对离散制造企业中通常采用柔性工艺设计这一类新的作业车间调度问题,对传统的柔性作业车间调度问题进行了扩展,建立了包含柔性工艺的作业车间调度问题的数学模型.针对问题中在作业调度同时进行柔性工艺选择的特点,设计了改进的遗传算法染色体编码方式和遗传算子,在此基础上,结合变邻域搜索算法,设计了4种不同的邻域结构以产生邻域解,从而提高遗传算法的邻域搜索性能.最后以某轴承公司的实际调度数据为实例,将该算法进行实例测试,并与其他现有的方法相比较,验证了所设计算法的有效性.     

Differentiation and analysis on rock breaking characteristics of TBM disc cutter at different rock temperatures

In order to study rock breaking characteristics of tunnel boring machine(TBM) disc cutter at different rock temperatures,thermodynamic rock breaking mathematical model of TBM disc cutter was established on the basis of rock temperature change by using particle flow code theory and the influence law of interaction mechanism between disc cutter and rock was also numerically simulated.Furthermore,by using the linear cutting experiment platform,rock breaking process of TBM disc cutter at different rock temperatures was well verified by the experiments.Finally,rock breaking characteristics of TBM disc cutter were differentiated and analyzed from microscale perspective.The results indicate the follows.1) When rock temperature increases,the mechanical properties of rock such as hardness,and strength,were greatly reduced,simultaneously the microcracks rapidly grow with the cracks number increasing,which leads to rock breaking load decreasing and improves rock breaking efficiency for TBM disc cutter.2) The higher the rock temperature,the lower the rock internal stress.The stress distribution rules coincide with the Buzin Neske stress circle rules: the maximum stress value is below the cutting edge region and then gradually decreases radiant around; stress distribution is symmetrical and the total stress of rock becomes smaller.3) The higher the rock temperature is,the more the numbers of micro,tensile and shear cracks produced are by rock as well as the easier the rock intrusion,along with shear failure mode mainly showing.4) With rock temperature increasing,the resistance intrusive coefficients of rock and intrusion power decrease obviously,so the specific energy consumption that TBM disc cutter achieves leaping broken also decreases subsequently.5) The acoustic emission frequency remarkably increases along with the temperature increasing,which improves the rock breaking efficiency.     

Influence of some rock strength properties on jaw crusher performance in granite quarry

The influence of rock strength properties on Jaw Crusher performance was carried out to determine the effect of rock strength on crushing time and grain size distribution of the rocks.Investigation was conducted on four different rock samples namely marble,dolomite,limestone and granite which were representatively selected from fragmented lumps in quarries.Unconfined compressive strength and Point load tests were carried out on each rock sample as well as crushing time and size analysis.The results of the strength parameters of each sample were correlated with the crushing time and the grain size distribution of the rock types.The results of the strength tests show that granite has the highest mean value of 101.67 MPa for Unconfined Compressive Strength (UCS) test,6.43 MPa for Point Load test while dolomite has the least mean value of 30.56 MPa for UCS test and 0.95 MPa for Point Load test.According to the International Society for Rock Mechanic (ISRM) standard,the granite rock sample may be classified as having very high strength and dolomite rock sample,low strength.Also,the granite rock has the highest crushing time (21.0 s) and dolomite rock has the least value (5.0 s).Based on the results of the investigation,it was found out that there is a great influence of strength properties on crushing time of rock types.     

Prediction of uniaxial compressive strength and modulus of elasticity for Travertine samples using regression and artificial neural networks

Uniaxial Compressive Strength (UCS) and modulus of elasticity (E) are the most important rock parameters required and determined for rock mechanical studies in most civil and mining projects, in this study, two mathematical methods, regression analysis and Artificial Neural Networks (ANNs), were used to predict the uniaxial compressive strength and modulus of elasticity. The P-wave velocity, the point load index, the Schmidt hammer rebound number and porosity were used as inputs for both methods. The regression equations show that the relationship between P-wave velocity, point load index, Schmidt hammer rebound number and the porosity input sets with uniaxial compressive strength and modulus of elasticity under conditions of linear relations obtained coefficients of determination of (R2) of 0.64 and 0.56, respectively. ANNs were used to improve the regression results. The generalized regression and feed forward neural networks with two outputs (UCS and E) improved the coefficients of determination to more acceptable levels of 0.86 and 0.92 for UCS and to 0.77 and 0.82 for E. The results show that the proposed ANN methods could be applied as a new acceptable method for the prediction of uniaxial compressive strength and modulus of elasticity of intact rocks.     

Selection of regression models for predicting strength and deformability properties of rocks using GA

Recently, many regression models have been presented for prediction of mechanical parameters of rocks regarding to rock index properties. Although statistical analysis is a common method for developing regression models, but still selection of suitable transformation of the independent variables in a regression model is difficult. In this paper, a genetic algorithm (GA) has been employed as a heuristic search method for selection of best transformation of the independent variables (some index properties of rocks) in regression models for prediction of uniaxial compressive strength (UCS) and modulus of elasticity (E). Firstly, multiple linear regression (MLR) analysis was performed on a data set to establish predictive models. Then, two GA models were developed in which root mean squared error (RMSE) was defined as fitness function. Results have shown that GA models are more precise than MLR models and are able to explain the relation between the intrinsic strength/elasticity properties and index properties of rocks by simple formulation and accepted accuracy.