Landslide displacement prediction technique using improved neuro-fuzzy system

Landslides are one of the most destructive forms of natural hazards, which cause serious threat to life and properties. Landslide monitoring and perdition of future landslide behavior is an important aspect of disaster mitigation, as it helps to issue early warnings and adopt suitable control measures in time. This paper proposes a technique, landslide displacement prediction using recently proposed extreme learning adaptive neuro-fuzzy inference system (ELANFIS) with empirical mode decomposition (EMD) technique. ELANFIS reduces the computational complexity of conventional ANFIS by incorporating the theoretical idea of extreme learning machines (ELM). The nonlinear original landslide displacement series first converted into a limited number of intrinsic mode functions (IMFs) and one residue. Then, the decomposed data are predicted using ELANFIS algorithm. Final prediction is obtained by summation of outputs of all ELANFIS submodels. The performances of the proposed technique are tested in Baishuihe and Liangshuijing landslides. The results show that ELANFIS with EMD model outperforms state of art methods in terms of prediction accuracy and generalization performance.     

应用一种改进BP神经网络算法预测密度曲线

利用测井数据与地震数据二者相结合进行综合分析,是地震勘探工作者的重要工作。可以通过分析井位处的地震数据与测井数据,提取地震的多个属性,建立一个与测井属性的统计关系。选取已改进的三层网络结构BP神经网络算法,在应用一个实际例子后表明,该算法的主要特点是收敛速度快、计算简单,同时还具有跳出局部最小的能力。应用此神经网络算法对某油田的二维地震数据进行了处理,提取了多种地震属性,并在井位置建立了地震属性与密度曲线的非线性关系,成功预测了剖面密度曲线,为了解储层状况提供了有益的资料。     

Risk assessment and prediction of safety factor for circular failure slope using rock engineering systems

Circular failure is generally observed in the slope of soil, highly jointed rock mass, mine dump and weak rock. Accurate estimation of the safety factor (SF) of slopes and their performance is not an easy task. In this research, based on rock engineering systems (RES), a new approach for the estimation of the SF is presented. The introduced model involves six effective parameters on SF [unit weight (γ), pore pressure ratio (r _u), height (H), angle of internal friction (φ), cohesion (C) and slope angle (\(\beta\))], while retaining simplicity as well. In the case of SF prediction, all the datasets were divided randomly to training and testing datasets for proposing the RES model. For comparison purposes, nonlinear multiple regression models were also employed for estimating SF. The performances of the proposed predictive models were examined according to two performance indices, i.e., coefficient of determination (R ²) and mean square error. The obtained results of this study indicated that the RES is a reliable method to predict SF with a higher degree of accuracy in comparison with nonlinear multiple regression models.     

隧道施工地质超前预报工作方法

论述了隧道施工地质预报的内容、隧道设计与实际造成隧道地质灾害及造成地质勘察资料精度不高原因,提出了通过资料收集、勘察成果整理分析、熟悉设计文件、资料与图纸和隧道施工地质预报阶段补充地质调查,确定隧道施工地质预报重点段,进行洞内地质调查和掌子面地质素描、物探方法的选择和现场实施掌子面探测、探测成果分析、报告提交及施工验证的隧道施工地质超前预报工作方法。     

基于贝叶斯正则化改进BP神经网络的页岩气有机碳含量预测模型

页岩气总有机碳(TOC)含量是评价岩性气藏的关键指标,受复杂地质及岩芯采集等多种因素的影响,常规室内测试分析获得的TOC含量的数据有限且结果有失准确。为合理准确预测页岩气TOC含量,本文首先通过对页岩气储层TOC含量测井资料综合分析选取8条测井曲线,并结合主成分分析法(Principal Component Analysis,PCA)提取四个主成分;其次基于贝叶斯正则化(Bayesian Regularization)改进的BP神经网络方法建立页岩气TOC含量预测的BR-BP模型;最后利用该模型对研究区A区页岩气TOC含量进行预测,并与常规的LM-BP神经网络模型的预测结果进行对比。结果表明：BR-BP模型有较强的非线性拟合能力,能够真实地反映出页岩气TOC含量与各测井参数之间的非线性关系,其模型预测结果与实际值基本吻合,与常规的LM-BP神经网络模型相比,其数据敏感性增强,预测精度有所提高,该研究方法具有一定的理论意义和参考价值,为我国TOC含量预测提供了一种新的技术方法和手段。     

Fragmentation Assessment using the FragScan System: Quality of a Blast

Checking the quality of a blast may be considered as subjective. Checking this quality will require measuring objective parameters. One of them is the resulting fragmentation of the blasted product. Numerous fragmentation 'measuring' systems have been developed and marketed, based on image-processing. This presentation of FragScan will illustrate advantages and difficulties when using such a system. FragScan is essentially defending a policy of large and representative sampling. The purpose is to show how fragmentation is discriminating both productivity and profit of quarry operations on a blast-by blast basis. The next step will then be to 'drive' the blasting process to reach a 'better' fragmentation. Other applications require the fragmentation as an essential result: this is the case for large boulders used in structure-reinforcement. Several case-studies have shown that FragScan can be used for quality-control, checking size-distribution of the product according to the requirements of the end-user. Only clear thinking about the precise use of such a 'measurement' will further the success of this task.     

A hybrid ensemble method for improved prediction of slope stability

Accurate prediction of slope stability is a significant issue in geomechanics with many artificial intelligence (AI) techniques being utilised. However, the application of AI has not reached its full potential because of the lack of more robust algorithms. In this paper, we proposed a hybrid ensemble method for the improved prediction of slope stability using classifier ensembles and genetic algorithm. Gaussian process classification, quadratic discriminant analysis, support vector machine, artificial neural networks, adaptive boosted decision trees, and k‐nearest neighbours were chosen to be individual AI techniques, and the weighted majority voting was used as the combination method. Validation method was chosen to be the 10‐fold cross‐validation, and performance measures were selected to be the accuracy, the receiver operating characteristic curve, and the area under the receiver operating characteristic curve (AUC). Grid search and genetic algorithm were used for the hyperparameter tuning and weight tuning respectively. The results show that the proposed hybrid ensemble method has great potential in improving the prediction of slope stability. Compared with individual classifiers, the optimum ensemble classifier achieved the highest AUC value (0.943) and the highest accuracy (0.902) on the testing set, denoting that the predictive performance has been improved. The optimum ensemble classifier with the Youden's cut‐off was recommended for slope stability prediction with respect to the AUC value, the accuracy, the true positive rate, and the true negative rate. This research indicates that the use of the classifier ensembles, rather than the search for the ideal individual classifiers, might help for the slope stability prediction.     

隧道工程勘察阶段涌水预测的问题探讨

隧道涌水量预测对隧道的设计和施工至关重要,相关勘察规范要求在一定阶段预测隧道涌水量。目前有多种方法用于预测隧道涌水量,但每种方法都有其适用范围。通过对这些方法进行分析,结合对实际隧道工程涌水量的预测,对于裂隙岩体中的隧道,要准确预测隧道涌水量,需要解决两个问题:地下水位和渗透系数。以钻孔水位为基础,利用物探技术,建立等效的虚拟基岩裂隙水连续水位线。渗透系数一般由钻孔水文地质试验测得,在涌水预测时,应根据优势结构面产状进行修正。     

动力打桩一维波动方程的改进及其工程应用

对桩的可打入性进行准确的分析和预测是打桩施工的关键环节,同时也关系到整个工程的进度与成败.近年来,在海洋工程和港口工程中都出现了大直径、超长桩,由于这种桩的重量大对桩的可打入性有显著影响,考虑桩身自重和桩周土阻力,对打桩分析的一维应力波动方程进行改进、推导.采用有限差分法求解波动方程,编制计算程序结合实际工程进行打桩分析,分析结果与实测数据吻合较好,表明经改进的动力打桩一维波动方程能很好的预测桩的可打入性及打桩过程中桩身应力分布情况.     

石灰改性膨胀土工程性质的试验研究

通过对济南、淄博地区膨胀土的室内物理力学性质、石灰改性的系列试验分析,确定了膨胀土的等级、改性后土的胀缩性、强度与剂量的关系及掺入石灰的最佳配比。     

岩爆预测的改进集对分析模型

正确预测岩爆是灾害治理和工程措施的基础。应用集对分析理论探讨了岩爆预测新方法,建立了基于接近度概念的模糊差异度系数的改进计算模型,实例及同其他方法的对比应用表明：基于改进的集对分析方法来预测岩爆是有效可行的,且取得了较好的结果。     

滑坡发生时间预报分析

系统论述了滑坡监测资料的整理方法：滤波和等时化。讨论了滑坡运动响应的主要组成成分。重点阐述了滑坡发生时间预报的理论基础，此基础不同于一般物理方程建立的思路，而是直接来源于观察和经验总结，并抽象为一定的数学模型。单次滑坡发生的整个过程包括孕育、如速、减速、停止等4个阶段，滑坡发生时间则指加速向减速转换的特征时间点，此点是滑坡爆发的峰值点，也是需要预报的特征时间。能够反映滑坡如此运动过程的典型数学函数是Pearl曲线，本质上此S型曲线与系统有阻尼的自由振动微分方程是一致的，也与生物群体演化的虫口方程一致，它们都共同反映了物质运动的一般规律，因此可以用来预测滑坡运动过程。直接运用一般力学报分方程描述滑坡运动过程的困难在于缺乏对滑体系统力学参数的精确把握，直接运用Logistic虫口微分方程则存在模型参数识别的困难，作者还发现某些误用灰色系统理论对Verbulst非线性方程，参数进行辩识。文末，为展示方法而不强调结果，以拥有10a监测资料的某滑坡为例，分析预报了滑坡活动过程，并进行了预测结果的数学检验。     

Wind speed prediction using spatio-temporal covariance

Natural Hazards - High wind poses a number of hazards in different areas such as structural safety, aviation, and wind energy—where low wind speed is also a concern, pollutant transport, to...     

基于Bayes判别分析方法的地下工程岩爆发生及烈度分级预测

在岩爆发生和烈度分级预测的距离判别分析模型的基础上,结合地下工程岩爆的特点和Bayes判别分析理论,提出了地下工程岩爆发生及烈度分级预测的Bayes判别分析方法。综合分析影响岩爆主要因素,选取最大切向应力 、岩石抗压强度 、岩石抗拉强度 和弹性能量指数 作为判别因子建立岩爆预测的Bayes判别分析模型,并利用回代估计法对误判概率进行估计。利用国内外一些重大深部地下工程实例作为学习的样本进行训练建模,经过训练后的模型回判估计的误判率为0。利用该模型对国内3处典型的隧道岩爆情况进行预测,结果与实际情况符合得很好。研究结果表明,Bayes判别模型在岩爆发生可能性及烈度分级预测中具有良好的适用性和有效性。     

Cyclone track prediction using INSAT data

INSAT visible and infrared imageries of three cyclones in the Bay of Bengal during the period 1984–1987 were analysed with a view to improve the cyclone track prediction in this region. It was observed that the rotation in the major structural cloud features (as seen from the cloud-top temperature maps) associated with these cyclones in the Bay of Bengal is followed with a change in direction of their movement. This method is seen to be particularly effective when the cyclone is severe and when the major cloud features persist for a reasonably longer time. In the present study, only the direction of movement is forecast assuming a uniform speed of the cyclone.     

基于空间插值的工程岩体RQD预测方法

作为工程实际中评价岩体性质的重要指标,RQD的应用已相当广泛。但工程岩体中RQD值的分布存在一定的结构性和随机性,因此,通过对特定位置钻探获取的RQD值无法很到位地表达整个空间区域的实际岩石质量。为了弥补这方面的不足,统计学中的空间插值法为此提供了有力的手段。考虑到空间RQD分布存在各向异性,以及在工程坐标系中很难描述RQD分布的结构性,首先计算工程坐标系下已获取RQD值的主要黑塞方向（pHd）;然后构建空间旋转与比例缩放矩阵对其进行坐标标准化处理。在标准化的空间中,引入Kriging插值法,采用变异函数描述RQD在标准空间结构上的变化,建立其空间变异规律的数学模型,并对其进行插值计算;最后将标准空间进行坐标逆变换,实现了对工程坐标系下RQD分布的预测。利用R语言编程将该方法应用于工程实例,结果表明,这种空间插值法能够有效地预测工程岩体中RQD值的分布规律,弥补了局部钻探的局限性。     

GT型土壤固化剂改良土的工程特性研究

GT型土壤固化剂是一种新型的土壤改性加固材料,以高钙灰和脱硫石膏两种工业废料为主要原料,辅以生石灰、水泥、熟石膏、硫酸铝及明矾石等次要成分,采用生石灰消解法除去脱硫石膏中的自由水,按全粉料配料的方法研制而成。按一定掺量向土中掺入石灰和GT型土壤固化剂制成石灰改良土样和固化剂改良土样并进行养护、浸水,对土样进行击实试验、直剪试验、压缩试验和渗透试验。试验结果表明固化剂改良土的击实效果、抗剪强度、压缩性、抗渗透性等工程特性明显优于石灰改良土。分析了GT型土壤固化剂加固土的机理,为进一步的研究和工程应用提供参考。     

深埋长大隧道岩爆预测与工程防治研究

岩爆是深埋长大隧道面临的最主要的地质灾害之一,准确的岩爆预测对保障施工过程中人员、设备的安全具有重要意义。以拉林铁路巴玉隧道为研究对象,依据隧道沿线现场调查工作及试验研究成果,评价了工程区岩体的整体性和岩爆倾向性;以工程地质条件为基础,综合分析隧道工程区地应力场环境及邻近工程实测地应力成果,利用工程类比和三维数值反演方法获得隧道工程区初始应力场;选取隧道横断面作平面应变分析,计算获得开挖后隧道沿线围岩二次应力场;最后利用修改后的谷-陶岩爆判据对隧道全段进行岩爆状态预测,结果表明隧道多段具有发生中等或高等岩爆的可能。     

Carbon monoxide prediction using novel intelligent network

This paper introduces a new structure in neural networks called TD-CMAC, an extension to the conventional Cerebellar Model Arithmetic Computer (CMAC), having reasonable ability in time series prediction. TD-CMAC, the conventional CMAC and a classical neural network model called Multi-Layer Perceptron (MLP) are simulated and evaluated for 1-hour-ahead prediction and 24-hour-ahead prediction of carbon monoxide as one of primary air pollutants. Carbon monoxide data used in this evaluation were recorded and averaged at Villa station in Tehran, Iran from October 3^rd. 2001 to March 14^th. 2002 at one-hour intervals. The results show that the errors made by TD-CMAC is fewer than those made by other models.