Rock mass structural recognition from drill monitoring technology in underground mining using discontinuity index and machine learning techniques

A procedure to recognize individual discontinuities in rock mass from measurement while drilling(MWD)technology is developed,using the binary pattern of structural rock characteristics obtained from in-hole images for calibration.Data from two underground operations with different drilling technology and different rock mass characteristics are considered,which generalizes the application of the methodology to different sites and ensures the full operational integration of MWD data analysis.Two approaches are followed for site-specific structural model building:a discontinuity index(DI)built from variations in MWD parameters,and a machine learning(ML)classifier as function of the drilling parameters and their variability.The prediction ability of the models is quantitatively assessed as the rate of recognition of discontinuities observed in borehole logs.Differences between the parameters involved in the models for each site,and differences in their weights,highlight the site-dependence of the resulting models.The ML approach offers better performance than the classical DI,with recognition rates in the range 89%to 96%.However,the simpler DI still yields fairly accurate results,with recognition rates 70%to 90%.These results validate the adaptive MWD-based methodology as an engineering solution to predict rock structural condition in underground mining operations.

Study on temperature field of the drilling machine during the course of drilling in coal mine

The working conditions of the MK-3 type full hydraulic tunnel drilling machine during the course of drilling were analyzed. Based on the energy balance governing equations for the drill rod, the temperature field of drill rod at the normal and non-normal working conditions was numerically obtained. The numerical results show that the maximum temperature at the head of drill rod under the normal working circumstance is insufficient to ignite the gas. But under the non-normal working condition, the local high temperature can ignite the gas easily and cause the fire. In order to prevent the gas fire, the occurrence of the non-normal operating condition must be prevented as far as possible during the drilling.

A BiGRU joint optimized attention network for recognition of drilling conditions

The identification and recording of drilling conditions are crucial for ensuring drilling safety and efficiency. However, the traditional approach of relying on the subjective determination of drilling masters based on experience formulas is slow and not suitable for rapid drilling. In this paper, we propose a drilling condition classification method based on a neural network model. The model uses an improved Bidirectional Gated Recurrent Unit (BiGRU) combined with an attention mechanism to accurately classify seven common drilling conditions simultaneously, achieving an average accuracy of 91.63%. The model also demonstrates excellent generalization ability, real-time performance, and accuracy, making it suitable for actual production. Additionally, the model has excellent expandability, which enhances its potential for further application.

A Novel Half-Bridge Power Supply for High Speed Drilling Electrical Discharge Machining

High Speed Drilling Electrical Discharge Machining (HSDEDM) uses controlled electric sparks to erode the metal in a work-piece. Through the years, HSDEDM process has widely been used in high speed drilling and in manufacturing large aspect ratio holes for hard-to-machine material. The power supplies of HSDEDM providing high power applica-tions can have different topologies. In this paper, a novel Pulsed-Width-Modulated (PWM) half-bridge HSDEDM power supply that achieves Zero-Voltage-Switching (ZVS) for switches and Zero-Current-Switching (ZCS) for the dis-charge gap has been developed. This power supply has excellent features that include minimal component count and inherent protection under short circuit conditions. This topology has an energy conservation feature and removes the need for output bulk capacitors and resistances. Energy used in the erosion process will be controlled by the switched IGBTs in the half-bridge network and be transferred to the gap between the tool and work-piece. The relative tool wear and machining speed of our proposed topology have been compared with that of a normal power supply with current limiting resistances.

Three-dimensional Tool Radius Compensation for Multi-axis Peripheral Milling

Few function about 3D tool radius compensation is applied to generating executable motion control commands in the existing computer numerical control (CNC) systems. Once the tool radius is changed, especially in the case of tool size changing with tool wear in machining, a new NC program has to be recreated. A generic 3D tool radius compensation method for multi-axis peripheral milling in CNC systems is presented. The offset path is calculated by offsetting the tool path along the direction of the offset vector with a given distance. The offset vector is perpendicular to both the tangent vector of the tool path and the orientation vector of the tool axis relative to the workpiece. The orientation vector equations of the tool axis relative to the workpiece are obtained through homogeneous coordinate transformation matrix and forward kinematics of generalized kinematics model of multi-axis machine tools. To avoid cutting into the corner formed by the two adjacent tool paths, the coordinates of offset path at the intersection point have been calculated according to the transition type that is determined by the angle between the two tool path tangent vectors at the corner. Through the verification by the solid cutting simulation software VERICUTwith different tool radiuses on a table-tilting type five-axis machine tool, and by the real machining experiment of machining a soup spoon on a five-axis machine tool with the developed CNC system, the effectiveness of the proposed 3D tool radius compensation method is confirmed. The proposed compensation method can be suitable for all kinds of threeto five-axis machine tools as a general form.

Evaluation of the energy efficiency of rotary percussive drilling using dimensionless energy index

This paper sets forth a geomechanics framework for assessing the energy efficiency of rotary percussive drilling using the energy criterion, which has been proposed by Victor Oparin for volumetric destruction of high-stress rocks having nonuniform physico-mechanical properties. We review the long-term research and development in the specified area of science and technology, including research and development projects implemented at the Institute of Mining, Siberian Branch of the Russian Academy of Sciences. A new modified expression of Oparin’s dimensionless energy criterion of volumetric rock destruction k is introduced. The range of in situ values is determined for the energy criterion of volumetric rock destruction at the optimized energy efficiency of rotary percussive drilling. The temporospatial intervals of geotechnical monitoring are found to control pneumatic drilling energy efficiency at subsoil use objects in Russia. The integrated experimental, theoretical and geotechnical approach to the comprehensive investigation of real-time processes of rock fracture in rotary percussive drilling using the energy concept possesses the necessary geomechanical performance-and-technology potential to create the next level geotechnical monitoring of drilling systems for various purposes, including determination of physico-mechanical properties and the stress-strain analysis of rock mass in full-scale drilling.

Laser Interferometer Based Measurement for Positioning Error Compensation in Cartesian Multi-Axis Systems

Accuracy is one of the most important key indices to evaluate multi-axis systems’ (MAS’s) characteristics and performances. The accuracy of MAS’s such as machine tools, measuring machines and robots is adversely affected by various error sources, including geometric imperfections, thermal deformations, load effects, and dynamic disturbances. The increasing demand for higher dimensional accuracy in various industrial applications has created the need to develop cost-effective methods for enhancing the overall performance of these mechanisms. Improving the accuracy of a MAS by upgrading the physical structure would lead to an exponential increase in manufacturing costs without totally eliminating geometrical deviations and thermal deformations of MAS components. Hence, the idea of reducing MAS’s error by a software-based alternative approach to provide real-time prediction and correction of geometric and thermally induced errors is considered a strategic step toward achieving the full potential of the MAS. This paper presents a structured approach designed to improve the accuracy of Cartesian MAS’s through software error compensation. Four steps are required to develop and implement this approach: (i) measurement of error components using a multidimensional laser interferometer system, (ii) tridimensional volumetric error mapping using rigid body kinematics, (iii) volumetric error prediction via an artificial neural network model, and finally (iv) implementation of the on-line error compensation. An illustrative example using a bridge type coordinate measuring machine is presented.

Optimization of Parameters CO<SUB>2</SUB>Laser for Drilling Different Types of Glass

The aim of this work is to study in detail the drilling process on glass by CO2 laser. The study parameters considered in the present experiments are based on the laser beam power of range (30% - 80% of 25 W) and an exposure time for drilling (2 - 8 s). The measured diameters of holes by optical methods are between [300 - 800 μm]. The results obtained by optical observations suggest that ordinary and mineral glasses cannot withstand to a contact of the laser beam and crack during the formation of the drilling hole. The minimum power and duration of exposure are the optimal parameters for drilling the organic glass, we observe no micro-cracks, and again we see that the edges of the holes have a good surface quality with a high aspect ratio.

Positioning of Screw Holes Group Based on Digital Camera and Digital Control Drilling

Positioning of screw holes is an important production procedure for steel construction connecting with bolts. In this paper, a new production method is presented, in which the digital camera is used for taking pictures of screw holes and other techniques are advanced. This paper also indicates that the pixels of CCD chip in photogrammetry should be chosen as all geometric units in an image, such as interior elements and all kinds of distortions. The measure can also simplify the camera calibration for determining the size of non-square pixel.

RESEARCH ON THE ADAPTIVE CONTROL OF DRILLING PROCESS

A self-tuning adaptive controller is presented which is used for the adaptive control (AC) of drlling process. The parameters of the controller can be regulated in-processly by on line system identification, so as to fit the variation of the cutting conditions. This control method has been successfully applied to the adaptive control of drilling process. The experimental results indicate that the controller has the ability to adapt to the variation of the cutting process parameters and is good in performance.

矿山救援钻孔中井涌井漏事故预警预测

为解决矿山应急救援钻孔作业过程中井涌井漏事故预警预测困难等问题,建立了基于机器学习的钻进过程井涌井漏事故预警预测模型。首先对井涌井漏事故发生初期时的钻进参数进行事故表征参数分析;其次对事故表征参数进行数据清洗处理,在此基础上,通过XGBoost事故诊断预警模型对井涌井漏事故进行早期诊断识别;随后建立PSO-LSTM事故发展预测模型,对事故发生后的孔底压力参数发展趋势进行预测,提前掌握钻进事故发展状态;最后通过实际钻进数据对预警预测模型的有效性进行验证。结果表明:XGBoost事故诊断预警模型能根据总池体积、立管压力、出入口流量差和动力头负荷这4种钻进参数的异常变化,快速准确诊断钻进过程中的井涌井漏事故;PSO-LSTM事故发展状态预测模型能充分学习孔底压力参数发展规律,综合EMAP、EMA、ERMS、R2这4项误差评价指标,PSO-LSTM模型相较于BP、RNN、SVM模型的预测性能最佳,能准确预测事故发生之后的孔底压力发展趋势,提前掌握井涌井漏事故的严重程度和发展态势。研究结果丰富了钻进过程井涌井漏事故预警预测方法,提高了矿山事故地面救援的可靠性,对矿山应急救援钻孔作业过程中事故控制有着借鉴与指导作用。

智能钻井多目标协同优化系统研究与应用

在深井超深井钻探过程中,井眼中高强度、高研磨性地层导致的钻头早期磨损、井下钻具振动剧烈、井眼清洁不足等,严重制约了深井超深井的安全快速钻进。针对上述问题,文章提出了一种智能钻井多目标协同优化系统,可以实时跟踪、优化钻井参数,提高钻井性能。同时基于机械钻速和机械比能,定义了钻井性能综合评价指标;结合地应力、钻具振动、摩阻扭矩、井眼清洁和破岩能效等地质、物理模型,提出了包含探索、学习和应用三种模式的钻井参数实时优化流程,训练了融合支持向量回归模型和随机森林回归模型的钻井参数实时优化算法。该系统在深地川科1井进行了现场应用,提速比达到了41.5%,为深井超深井钻井优化提速提供了一种新的技术手段。

机器学习在钻柱振动识别与预测中的研究进展

钻柱振动是影响钻井效率、钻柱失效、井眼稳定和钻井安全的主要因素,复杂振动的早期识别对于缓解井下工具受损、提高生产时间至关重要。为此,充分调研国内外机器学习在钻柱振动识别方法方面的研究成果,从数据获取角度对钻柱振动识别与预测方法进行了全面分析,对比研究了各算法模型的框架、特征参数和测试效果,系统评估了各算法模型的优缺点,并对未来振动识别与预测的发展方向提出思考。研究结果表明:①机器学习算法可以从大量振动数据中学习和提取特征来建立模型,对振动进行分类和预测,通过不断优化算法和模型,提高钻柱振动识别与预测的准确性和可靠性;②随着数据采集和处理技术的不断进步,地面与井下多源数据融合方法将多种数据共同分析处理,可以最大程度地发掘地面和井下数据特征,有望成为解决井下问题的重要途径;③随着钻井工程与人工智能技术的不断融合与发展,振动缓解与钻井提速联合优化,将为钻井工程提供更为可靠的指导和决策。结论认为,机器学习在钻柱振动识别与预测方面的应用和发展进一步缓解了超深井井下钻柱振动这一复杂问题,提高了钻井工程的效率和安全性,推进了钻井过程的高效化和智能化发展步伐。

钻装机扒装机构斗齿根与主刀板焊接强度分析

通过SYSWELD对扒装机构斗齿齿根与主刀板焊接部分进行残余应力分析,在保持统一的焊接参数下,采用ZG22CrMnMo代替ZG25CrMnMo制造斗齿,对仿真结果进行分析,得出ZG22CrMnMo焊接变形小。通过改变焊接电流、焊接电压,得到焊接仿真结果。采用ZG22CrMnMo作为钻装机扒装机构斗齿材料满足扒装机构工作强度,在焊接电流200 A、电弧电压24 V时,焊接件的内部残余应力最小,对扒装机构的影响最小,可以增加扒装机构铲斗的使用寿命。

基于损伤力学的矿用定向钻机金属结构寿命评估

针对ZYL-15000D型煤矿用履带式全液压定向钻机底座寿命评估,首先通过Q345B钢的脉动循环加载拉伸疲劳试验数据,拟合得到应力幅值和寿命的关系式,经由应力修正和安全系数的选取,转换得到对称循环下的应力幅值和寿命的关系式。结合基于损伤力学推导出的损伤退化模型,根据Q345B钢试验数据拟合确定损伤退化模型中的待定参数,将Q345B钢对称循环下应力幅值和寿命的关系式代入,得到Q345B钢的疲劳损伤退化模型。然后借助ABAQUS对钻机整机进行结构分析,得到钻机底座的危险点位置(即应力最大处),在该型号样机试验台上通过应变片测得钻机底座危险点处的应力—时间历程。最后采用雨流计数和应力修正,对测得的随机载荷谱进行处理得到雨流计数直方图(应力均值-幅值-循环次数),再转换为对称循环载荷的形式,代入确定的疲劳损伤退化模型中,评估钻机底座的疲劳寿命。

木材深孔钻床的开发与机电设计

为了解决传统数控系统和机床结构无法直接用于木材深孔加工的问题,研究深孔加工的原理,分析重难点问题,从特殊的工装夹具系统和机床主体结构设计、机床的柔性辅助装夹系统设计、整个机床的电气控制系统和PLC内部的进给插补逻辑算法等进行研究和阐述。使用木材深孔钻床预加工16 mm的孔,测得精度为15.99 mm,完全符合加工要求。木材深孔钻床的设计与研究解决了木材在自动化深孔加工的问题,为该行业提供了解决方案。

大规模定制家具加工中心多钻头并行作业的优化

大规模定制家具超高的生产效率与高度个性化的产品两大特征决定了其需要依赖高水平的信息化与自动化组织生产,是家具制造业智能制造的前沿领域。运用数控加工中心开展钻孔作业是调和个性化产品制造过程中的矛盾、实现柔性生产的重要手段。当前,数控钻孔工序因其作业时间长且板件之间差异较大而往往成为制造过程中的瓶颈。为切实提高生产效率,本研究立足生产实际,从钻头与孔的位置关系中寻求突破口,提出了数控加工中心多钻头并行作业优化问题。以优化钻头排列为主要途径,减少下钻次数为核心目标,基于制造大数据与工艺规则挖掘信息并简化建模,采用差分进化算法求解钻头排列方案,进一步通过聚类算法探索出面向未来高自动化水平下的差异化钻头排列,形成了一套具有实际意义与普适性的优化方法。通过理论与实践验证了该方法的有效性,达到了缩减作业时间、提升加工效率的目的。对打通大规模定制家具制造瓶颈、推动定制家具智能制造具有一定的指导意义。

基于机器学习的钻井液流变参数智能识别方法

钻井液流变性是钻井液流动和变形的特性,对于携带与悬浮岩屑、提高钻进速度至关重要,准确掌握钻井液流变参数是保证井眼清洁与高效钻进的前提。提出一种基于卷积神经网络(Convolu-tionalNeuralNetwork,CNN)的钻井液流变参数智能识别方法,通过磁力搅拌产生稳定的钻井液流动图像,利用多种数据增强方法增加图像数量并建立数据库,增强模型的鲁棒性和泛化能力。优化AlexNet卷积神经网络算法,构建钻井液流变参数识别模型。将数据库划分为训练集:验证集:测试集=7:2:1,对训练集进行迭代训练并通过验证集调整参数获得最佳拟合模型。此外,运用混淆矩阵、卷积核可视化技术和类激活技术(Gradient-weighted Class Activation Mapping,Grad-CAM)对模型进行多方位评估。结果表明:(1)钻井液流变参数识别模型对钻井液塑性黏度测试的宏精确率为95.2%,宏召回率为94.7%,宏F1值为0.95。(2)对钻井液表观黏度测试的宏精确率为91.6%,宏召回率为91.5%,宏F1值为0.90。(3)利用卷积核可视化技术和Grad-CAM对特征提取进行可视化处理,发现钻井液波纹形状和大小会影响模型流变参数识别准确度。(4)室内测试结果表明,该模型的测试误差为±2 mPa·s,在设计允许范围以内,具有较高的识别精确度和稳定性。所提出的钻井液流变参数实时智能识别方法可为安全、快速和准确地进行钻井液流变性测试提供智能化技术思路。

粘弹性材料钻削温度预测模型的建立与应用

粘弹性材料兼有弹性固体和粘性流体的特性,传统的热分析方法无法准确描述同时发生的粘性和弹性变形。针对该复杂材料特性的材料去除过程中的温度场研究是十分稀少的,提出将机器学习算法应用到药柱钻削加工的温度预测当中。首先利用线性回归进行拟合,侧面证明该模型的非线性。其次利用随机森林和BP神经网络算法进行建模,随机森林模型的随机特性使其具有一定的抗噪能力,BP神经网络模型精度最高,决定系数达到0.989。利用BP神经网络模型的预测功能实现加工过程的提前防控,优化加工参数组合,实现高效安全生产。