Artificial neural network model for prediction of rock properties from sound level produced during drilling

In many rock engineering applications such as foundations, slopes and tunnels, the intact rock properties are not actually determined by laboratory tests, due to the requirements of high quality core samples and sophisticated test equipments. Thus, predicting the rock properties by using empirical equations has been an attractive research topic relating to rock engineering practice for many years. Soft computing techniques are now being used as alternative statistical tools. In this study, artificial neural network models were developed to predict the rock properties of the intact rock, by using sound level produced during rock drilling. A database of 832 datasets, including drill bit diameter, drill bit speed, penetration rate of the drill bit and equivalent sound level (L_eq) produced during drilling for input parameters, and uniaxial compressive strength (UCS), Schmidt rebound number (SRN), dry density (ρ), P-wave velocity (V_p), tensile strength (TS), modulus of elasticity (E) and percentage porosity (n) of intact rock for output, was established. The constructed models were checked using various prediction performance indices. Goodness of the fit measures revealed that recommended ANN model fitted the data as accurately as experimental results, indicating the usefulness of artificial neural networks in predicting rock properties.     

Sound level produced during rock drilling vis-à-vis rock properties

The process of drilling, in general, always produces sound. Though sound is used as a diagnostic tool in mechanical industry, its application in predicting rock property is not much explored. In this study, an attempt has been made to estimate rock properties such as uniaxial compressive strength, Schmidt rebound number and Young's modulus using sound level produced during rotary drilling. For this purpose, a computer numerical controlled vertical milling centre was used for drilling holes with drill bit diameters ranging from 6 to 20 mm with a shank length of 40 mm. Fourteen different rock types were tested. The study was carried out to develop the empirical relations using multiple regression analysis between sound level produced during drilling and rock properties considering the effects of drill bit diameter, drill bit speed and drill bit penetration rate. The F-test was used to check the validity of the developed models. The measured rock property values and the values calculated from the developed regression model are fairly close, indicating that the developed models could be efficiently used with acceptable accuracy in prediction of rock properties.     

基于人工神经网络模型的岩石特性预测

近年来,软计算技术被用作替代的统计工具。如人工神经网络（ANN）被用于开发预测模型来估计所需的参数。在本研究中,通过利用冲击钻进过程中的一些钻进参数（气压、推力、钻头直径、穿透率）和所产生的声级,建立了预测岩石性质的神经网络模型。在实验室中所产生的数据,用于开发预测岩石特性（如单轴抗压强度、耐磨性、抗拉强度和施密特回弹数）的神经网络模型,并使用各种预测性能指标对所建模型进行检验,结果表明人工神经网络模型适用于岩石性质的预测。     

Performance Evaluation of Button Bits in Coal Measure Rocks by Using Multiple Regression Analyses

Electro-hydraulic and jumbo drills are commonly used for underground coal mines and tunnel drives for the purpose of blasthole drilling and rock bolt installations. Not only machine parameters but also environmental conditions have significant effects on drilling. This study characterizes the performance of button bits during blasthole drilling in coal measure rocks by using multiple regression analyses. The penetration rate of jumbo and electro-hydraulic drills was measured in the field by employing bits in different diameters and the specific energy of the drilling was calculated at various locations, including highway tunnels and underground roadways of coal mines. Large block samples were collected from each location at which in situ drilling measurements were performed. Then, the effects of rock properties and machine parameters on the drilling performance were examined. Multiple regression models were developed for the prediction of the specific energy of the drilling and the penetration rate. The results revealed that hole area, impact (blow) energy, blows per minute of the piston within the drill, and some rock properties, such as the uniaxial compressive strength (UCS) and the drilling rate index (DRI), influence the drill performance.     

Prediction of Drillability of Rocks with Strength Properties Using a Hybrid GA-ANN Technique

The purpose of this paper is to provide a proper, practical and convenient drilling rate index (DRI) prediction model based on rock material properties. In order to obtain this purpose, 47 DRI tests were used. In addition, the relevant strength properties i.e. uniaxial compressive strength and Brazilian tensile strength were also used and selected as input parameters to predict DRI. Examined simple regression analysis showed that the relationships between the DRI and predictors are statistically meaningful but not good enough for DRI estimation in practice. Moreover, multiple regression, artificial neural network (ANN) and hybrid genetic algorithm (GA)-ANN models were constructed to estimate DRI. Several performance indices i.e. coefficient of determination (R²), root mean square error and variance account for were used for evaluation of performance prediction the proposed methods. Based on these results and the use of simple ranking procedure, the best models were chosen. It was found that the hybrid GA-ANN technique can performed better in predicting DRI compared to other developed models. This is because of the fact that the proposed hybrid model can update the biases and weights of the network connection to train by ANN.     

Prediction of uniaxial compressive strength of sandstones using petrography-based models

The uniaxial compressive strength of intact rock is the main parameter used in almost all engineering projects. The uniaxial compressive strength test requires high quality core samples of regular geometry. The standard cores cannot always be extracted from weak, highly fractured, thinly bedded, foliated and/or block-in-matrix rocks. For this reason, the simple prediction models become attractive for engineering geologists. Although, the sandstone is one of the most abundant rock type, a general prediction model for the uniaxial compressive strength of sandstones does not exist in the literature. The main purposes of the study are to investigate the relationships between strength and petrographical properties of sandstones, to construct a database as large as possible, to perform a logical parameter selection routine, to discuss the key petrographical parameters governing the uniaxial compressive strength of sandstones and to develop a general prediction model for the uniaxial compressive strength of sandstones. During the analyses, a total of 138 cases including uniaxial compressive strength and petrographic properties were employed. Independent variables for the multiple prediction model were selected as quartz content, packing density and concavo–convex type grain contact. Using these independent variables, two different prediction models such as multiple regression and ANN were developed. Also, a routine for the selection of the best prediction model was proposed in the study. The constructed models were checked by using various prediction performance indices. Consequently, it is possible to say that the constructed models can be used for practical purposes.     

两种贯通潜孔锤反循环钻头应用效果及理论分析

对于矿区钻孔作业存在的粉尘污染严重、岩矿心采取困难等问题,常规金刚石钻进取心难以满足现场施工要求。采用贯通式潜孔锤反循环连续取心技术替代常规金刚石取心工艺,在保证了较高钻进效率的同时,可有效解决干旱缺水矿区存在的取心及其引起的污染问题,保障施工人员的身体健康。为此,笔者所在课题组研发了两种新型潜孔锤反循环钻头并进行了野外试验,同时,运用LSDYNA数值模拟对设计的两种反循环钻头进行了强度分析。试验结果表明,两种钻头均具有较好的碎岩钻进效果,但花键内喷孔式反循环钻头易发生断裂;数值模拟分析结果显示,钻头的最大应力远高于材料疲劳极限是造成钻头破坏的根本原因,数值模拟结果与试验结果取得了较好的一致性。由此证实了花键内喷孔式反循环钻头结构存在缺陷,设计时应尽量避免在内喷孔周围设置环槽,以保证钻头体强度。     

Application of dimensional & regression analysis in oil drill bit data

Dimensional analysis is applied to derive the design parametric statements. 348 sets of oil drill bit field data are collected and manipulated into non-dimensional forms which are analyzed using the multiple step-wise regression method. The statistical analysis of these oil drill bit field data yields the corresponding regression equation for each design parametric statement. These regression equations compare favorably with those published. They are used to study the effects of various variables and provide the rule-of-thumb design information such as mud flow requirements. The application of these regression equations in oil drill bit design is suggested together with the design procedures to strike a balance between the mechanical energy and hydraulic energy. The study also confirms that the bit diameter is the most influential factor in affecting the mud flow and that the rate of penetration is a function of mechanical energy, hydraulic energy, mud properties, bit hydraulics, borehole depth and bit life.     

岩心钻探斜构造地层井斜轨迹预测模型与软件

针对岩心钻探斜构造岩层,把钻进过程分为无旋挤压分量和无压扭转分量,建立了钻头与地层相互作用模型、粗径钻具偏转模型,从而形成了一套综合考虑地层产状、岩性、钻井液润滑系数、钻头偏斜力、钻具组合等影响因素的钻进趋势预测的模型及方法.运用计算机编程技术建立预测软件,结合大陆科学钻探一井(CCSD-1)部分井段相关数据得出预测轨...     

塔东古城地区钻头优选及应用

针对大庆油田塔东区块古城地区地层含砾、岩石硬度大、85%以上井段采用牙轮钻进,导致深部地层钻速慢,钻头磨损严重等问题,在传统钻速预测方法基础上,引入钻头磨损、地层岩性、应用井深等相关参数,建立钻头破岩效率计算方法,并结合所钻遇的地层岩性、测井资料及钻头类型等,建立钻头优选模型,实现钻头选型定量化,提出了适用于古城地区的钻头序列推荐方案。现场成功应用5口井,单只钻头进尺和平均机械钻速均得到了很大的提高,实现了钻头优选提速提效的目的,为古城地区的高效钻井施工提供了重要的技术支撑。     

基于钻进能量理论的隧道凝灰岩地层界面识别及围岩分级方法

钻机钻进过程中钻头旋转产生的扭矩以及作用于钻头的轴推进力是破碎岩石的能量来源,当钻进条件确定时,可用破碎单位体积岩石的实际能耗来反映岩石的物理力学性质。基于此原理在青岛胶州湾海底隧道FK4+375.5的上断面进行了超前地质探孔作业,得到凝灰岩地层中的钻进参数及钻进能量随钻头位移的变化曲线,并利用能量理论对钻进过程中监测的钻机参数进行分析,研究发现：在凝灰岩中,数字钻机参数与围岩岩性响应程度较高,围岩完整、坚硬、无裂隙水时,整体钻进参数值较高;围岩裂隙发育、含水或有断层、夹泥层时,钻进速度、推进力、转速、扭矩、打击能等数据会突变,其值变小。分析所得结果与钻孔取芯、TSP超前预报等物探手段得到的结果基本一致。并采用能量法对围岩进行分析,利用钻进比能划分相应的岩体区段,判断出围岩等级。通过对能量曲线的分析发现,在凝灰岩地层中,当钻进能量小于0.95 kJ时会出现断层或较大的节理裂隙区。     

特高多层胎体孕镶金刚石钻头设计与数值模拟

针对金刚石钻头寿命受限于钻头胎体高度的问题，提出了一种新型多层特高胎体孕镶金刚石钻头的设计方案。钻头设计中，引入了偏心交错切削齿、交替式水口以及挡水片结构，保证了多层特高胎体钻头的冷却及有效钻进。通过强度及水力流场模拟，校核了钻头强度，验证了水路结构的合理性，并进一步实现了钻头成品加工制造。该钻头打破钻头胎体高度的限制，为大幅提高钻头寿命提供了新的思路。移动阅读      

Correlation between Cerchar abrasivity index,rock properties,and drill bit lifetime

The Cerchar abrasivity index (CAI) is one of the most widely known index method for identification of rock abrasivity. It is a simple and fast testing method providing reliable information on rock abrasiveness. In this study, the relationships between the CAI and some rock properties such as uniaxial compressive strength (UCS), point load strength, Brazilian tensile strength and Schmidt rebound hardness, and equivalent quartz content (EQC) are examined. The relationships between the CAI and drill bit lifetime is also investigated and the type of drill bit wear observed is mentioned. Additionally, the CAI is modeled using simple and multiple linear regression analysis based on the rock properties. Drill bit lifetime is also modeled based on the CAI. The results show that the CAI increases with the increase of the UCS, point load strength, Brazilian tensile strength, L-type and N-type Schmidt rebound hardness, and the EQC. It is concluded that the higher and the lower bit lifetime are obtained for marl and andesitic-basaltic formation, respectively. Moreover, flushing holes, inserted button, button removal, and failures of button on the bits are determined as the type of drill bit wear. The modeling results show that the models based on the UCS and the EQC give the better forecasting performances for the CAI.     

金刚石-硬质合金复合齿钻头在卵砾石地层中的应用

研制的人造金刚石单晶与WC-Co硬质合金复合球齿钻头,具有高耐磨性、高硬度、高冲击韧性,其超硬复合部分在钻进大硬度的卵砾石地层时,能象孕镶金刚石钻头那样切削岩石。野外钻进试验表明,复合齿钻头和普通合金钻头相比,回次进尺提高 1倍以上,小时效率提高 1.5倍以上,平均寿命增加 2.5倍以上,而每m进尺钻头成本降低了35%。      

Application of Generalized Regression Neural Networks in Predicting the Unconfined Compressive Strength of Carbonate Rocks

Measuring unconfined compressive strength (UCS) using standard laboratory tests is a difficult, expensive, and time-consuming task, especially with highly fractured, highly porous, weak rock. This study aims to establish predictive models for the UCS of carbonate rocks formed in various facies and exposed in Tasonu Quarry, northeast Turkey. The objective is to effectively select the explanatory variables from among a subset of the dataset containing total porosity, effective porosity, slake durability index, and P-wave velocity in dry samples and in the solid part of samples. This was based on the adjusted determination coefficient and root-mean-square error values of different linear regression analysis combinations using all possible regression methods. A prediction model for UCS was prepared using generalized regression neural networks (GRNNs). GRNNs were preferred over feed-forward back-propagation algorithm-based neural networks because there is no problem of local minimums in GRNNs. In this study, as a result of all possible regression analyses, alternative combinations involving one, two, and three inputs were used. Through comparison of GRNN performance with that of feed-forward back-propagation algorithm-based neural networks, it is demonstrated that GRNN is a good potential candidate for prediction of the unconfined compressive strength of carbonate rocks. From an examination of other applications of UCS prediction models, it is apparent that the GRNN technique has not been used thus far in this field. This study provides a clear and practical summary of the possible impact of alternative neural network types in UCS prediction.     

Numerical modelling of bit–rock fracture mechanisms in percussive drilling with a continuum approach

This paper presents a numerical method for continuum modelling of the dynamic bit–rock interaction process in percussive drilling. The method includes a constitutive model based on a combination of the recent viscoplastic consistency model, the isotropic damage concept and a parabolic compression cap. The interaction between the drill bit and rock is modelled using contact mechanics by treating the bit as a rigid body. As the bit–rock interaction in percussive drilling is a transient event, the method is implemented in explicit dynamics FEM. The rock strength heterogeneity is characterized at the mesoscopic level statistically using the Weibull distribution. The bit–rock interaction is simulated under axisymmetric conditions using cylindrical and hemispherical buttons. The choice of the quite complex constitutive model accounting, e.g. for plastic compaction, viscoplastic shear and tensile failure along with induced damage and rate dependency is justified by numerical simulations. Moreover, the quasi‐static and dynamic cases are compared in plane strain simulations. Finally, some results clarifying the discrepancy of opinions found in the literature concerning the side (lateral) crack formation are obtained. Copyright © 2010 John Wiley & Sons, Ltd.     

双钻头自平衡钻进系统用多通道连续缆管设计

为解决矿山灾害钻孔救援过程中地面钻机对地下钻头“长臂管辖”式驱动导致的钻进效率低、对孔壁扰动大和起下钻辅助时间长等问题,提出了无钻机双钻头仿生自平衡连续缆管钻进技术,而多功能连续缆管设计是该技术的重点和难点之一。为此,根据自平衡钻进系统的需求,从功能、结构、参数三大方面对多通道连续缆管进行设计。为实现连续钻进,多通道缆管需要同时具备泥浆循环、电能与信号传输和电磁屏蔽等功能,此外,还要具有足够强度和良好的弹性。对缆管的铠装缆线外径、内管与外管内外径参数进行设计并计算钻井液环空上返流速,计算结果表明缆管内外管直径参数设计满足最低上返流速要求。采用理论计算与数值模拟相结合的方法对缆管的关键部件进行受力分析,对外管抗拉压弯强度及外管壁抗挤压强度等进行强度校核。结果表明：多通道连续缆管结构设计合理,性能可靠,能够满足无钻机双钻头仿生自平衡钻进系统的技术要求,为矿山灾害无钻机双钻头仿生自平衡钻孔救援工作提供一种安全可靠、快速机动的多通道连续缆管技术和方法。     

承德M24矿区深孔钻探钻进参数的选择分析

结合承德M24矿区深孔钻探工程,对钻进参数的选择情况进行了分析。分析认为,深孔钻进中,钻进压力的选择要综合考虑钻进的口径大小,岩石的硬度、强度、研磨性、完整性;在一定范围内,金刚石钻头的钻速和转速成正比例关系;冲冼液的选择应根据钻头类型与规格,胎体性能,钻孔深度,岩石研磨性、完整程度等来选择;适当扩大金刚石钻头的外径尺寸,能有效地避免高泵压的危害;可通过观察钻机主电机的电流指示表数值变化,判断孔内钻杆工况,电流的变化反映出钻机回转扭矩的变化。     

基于多钻进参数和概率分类方法的地层识别研究

传统的超前钻探地质预报常以某个钻进参数的变化率作为地层识别的主要依据。钻头破岩是一个复杂的力学过程,应考虑多个参数的协同作用,仅采用单钻进参数识别地层的不确定性较大。首先,对超前钻探数据进行预处理,包括标准化、频数分布分析和敏感性分析,筛选出对地层变化敏感的关键钻进参数;其次,基于能量守恒、二元无序逻辑回归分析和多参数变异性分析原理分别建立了破岩能量、逻辑回归概率和地层硬度3种地层识别综合指标;最后,采用基于贝叶斯原理的概率分类方法建立地层识别模型,利用ROC分析方法得到模型参数,实现基于多钻进参数和概率分类方法的地层识别。以地质条件复杂的隧道工程为例,介绍了该地层识别方法的应用,结果表明：3种地层识别综合指标均具有较好的跨孔地层识别能力,识别准确率超过80%;破岩能量和逻辑回归概率指标适用于较近距离的跨孔地层识别,平均识别准确率分别为86.3%和84.1%;逻辑回归概率指标对软弱夹层识别能力较强,准确率达到94.2%;地层硬度指标适用于较远距离的跨孔地层识别;灰岩识别准确率最大达到93.2%。     

煤层顶板大直径定向钻孔用双级双速PDC钻头设计及应用

大直径定向钻进成孔技术的发展, 为“以孔代巷”技术抽采采空区上隅角瓦斯提供了技术支持。受限于井下设备条件, 常规大直径钻孔主要采用逐级扩孔工艺。然而, 逐级扩孔钻进需要多次提钻、下钻, 辅助时间长、工人劳动强度大。为提高煤层顶板大直径钻孔成孔效率, 开发了双级双速钻进工艺, 该工艺采用螺杆马达与钻机分别驱动一级、二级钻头进行单次双级扩孔钻进, 可大大提高成孔效率。通过分析双级双速钻进工艺特点、拟钻地层岩性等, 从剖面形状、切削齿排布、水路设计以及导向器设计等方面设计了双级双速钻头, 该钻头采用球头螺旋形导向器, 更容易沿既有钻孔轨迹钻进; 采用等切削布齿, 提高破岩效率、降低切削齿不均匀磨损, 进而提高钻头寿命与钻进效率。设计的双级双速钻头进行了现场试验, 试验表明双级双速钻头能够沿先导孔钻进, 较常规逐级扩孔钻头综合效率提高25%以上, 使用后钻头磨损均匀, 满足了双级双速工艺要求, 大大提高了煤层顶板大直径钻孔施工效率。