共查询到20条相似文献，搜索用时 31 毫秒
1.
Adaptive neuro-fuzzy inference system (ANFIS) and artificial neural network (ANN) models have been extensively used to predict
different soil properties in geotechnical applications. In this study, it was aimed to develop ANFIS and ANN models to predict
the unconfined compressive strength (UCS) of compacted soils. For this purpose, 84 soil samples with different grain-size
distribution compacted at optimum water content were subjected to the unconfined compressive tests to determine their UCS
values. Many of the test results (for 64 samples) were used to train the ANFIS and the ANN models, and the rest of the experimental
results (for 20 samples) were used to predict the UCS of compacted samples. To train these models, the clay content, fine
silt content, coarse silt content, fine sand content, middle sand content, coarse sand content, and gravel content of the
total soil mass were used as input data for these models. The UCS values of compacted soils were output data in these models.
The ANFIS model results were compared with those of the ANN model and it was seen that the ANFIS model results were very encouraging.
Consequently, the results of this study have important findings indicating reliable and simple prediction tools for the UCS
of compacted soils. 相似文献
2.
3.
为了准确认识和预测伊通盆地鹿乡断陷储层敏感性的分布,从实验分析入手,测量不同样品的敏感性、物性和粘土矿物等参数,结合铸体薄片、压汞、扫描电镜等实验方法,从宏观和微观2个角度分析了储层敏感性与孔隙度、渗透率与各类粘土矿物相对含量之间的关系,分析了储层敏感性与储层的孔喉类型和粘土矿物产状之间的关系,建立了不同微相控制下的孔隙度、渗透率、粘土矿物含量、石英和长石含量的解释模型.最后,选取孔隙度、渗透率、石英含量、长石含量、伊利石含量、高岭石含量、绿泥石含量、伊/蒙混层含量8个参数,采用Elman神经网络方法分别建立了速敏、水敏、酸敏和碱敏的预测模型.结果表明:采用神经网络方法预测的储层敏感性指数与实验结果吻合;五星构造带具有强的速敏、酸敏、碱敏和盐敏,鹿乡断陷中部和西北部具有强的水敏性. 相似文献
4.
A new low-dimensional parameterization based on principal component analysis (PCA) and convolutional neural networks (CNN) is developed to represent complex geological models. The CNN–PCA method is inspired by recent developments in computer vision using deep learning. CNN–PCA can be viewed as a generalization of an existing optimization-based PCA (O-PCA) method. Both CNN–PCA and O-PCA entail post-processing a PCA model to better honor complex geological features. In CNN–PCA, rather than use a histogram-based regularization as in O-PCA, a new regularization involving a set of metrics for multipoint statistics is introduced. The metrics are based on summary statistics of the nonlinear filter responses of geological models to a pre-trained deep CNN. In addition, in the CNN–PCA formulation presented here, a convolutional neural network is trained as an explicit transform function that can post-process PCA models quickly. CNN–PCA is shown to provide both unconditional and conditional realizations that honor the geological features present in reference SGeMS geostatistical realizations for a binary channelized system. Flow statistics obtained through simulation of random CNN–PCA models closely match results for random SGeMS models for a demanding case in which O-PCA models lead to significant discrepancies. Results for history matching are also presented. In this assessment CNN–PCA is applied with derivative-free optimization, and a subspace randomized maximum likelihood method is used to provide multiple posterior models. Data assimilation and significant uncertainty reduction are achieved for existing wells, and physically reasonable predictions are also obtained for new wells. Finally, the CNN–PCA method is extended to a more complex nonstationary bimodal deltaic fan system, and is shown to provide high-quality realizations for this challenging example.
相似文献5.
The sign and the magnitude of the zeta potential must be known for many engineering applications. For clay soils, it is usually
negative, but it is strongly dependent on the pore fluid chemistry. However, measurement of zeta potential time is time-consuming
and requires special and expensive equipment. In this study, the prediction of zeta potential of kaolinite has been investigated
by artificial neural networks (ANNs) and multiple regression analyses (MRAs). To achieve this, ANN and MRA models based on
zeta potential measurements of kaolinite in the presence of salt and heavy metal cations at different pH values have been
developed. The results of the models were compared with the experimental results. The performance indices, including coefficient
of determination, root mean square error, mean absolute error, and variance, were used to assess the performance of the prediction
capacity of the models developed in this study. The obtained indices make it clear that the constructed ANN models were able
to predict zeta potential of kaolinite quite efficiently and outperformed the MRA models. Results showed that ANN models can
be used satisfactorily to predict zeta potential of kaolinite as a rapid inexpensive substitute for laboratory techniques. 相似文献
6.
垃圾填埋场传统封顶和ET封顶的比较研究 总被引：3，自引：0，他引：3
针对传统压实黏土封顶系统存在易干燥开裂的问题,提出了一种新型的ET（蒸发传输）封顶系统。分析了压实黏土封顶系统和新型ET封顶系统的工作机制。在降水和蒸发循环补给的条件下,建立了水分在两种封顶系统中迁移的一维数学模型。以9次降水和蒸发循环补给为边界条件,分别模拟了576 h的水分在两种封顶系统中迁移变化规律。计算结果表明,距补给边界越近,含水率受降水、蒸发的影响越显著,且随着深度的增加出现明显的峰值滞后现象。传统封顶中的压实黏土层由于具有低渗透性,致使整层不能得到有效的水分补给。ET封顶中整个土层可以有效地从边界降水中得到补给,同时在蒸发的条件下,把土层中的储水释放。数值计算结果与试验数据的对比表明,计算值和试验数据基本吻合。这些研究成果有助于垃圾填埋场封顶系统的设计作进一步的改进。 相似文献
7.
In this paper a new approach is presented, based on evolutionary polynomial regression (EPR), for determination of liquefaction potential of sands. EPR models are developed and validated using a database of 170 liquefaction and non-liquefaction field case histories for sandy soils based on CPT results. Three models are presented to relate liquefaction potential to soil geometric and geotechnical parameters as well as earthquake characteristics. It is shown that the EPR model is able to learn, with a very high accuracy, the complex relationship between liquefaction and its contributing factors in the form of a function. The attained function can then be used to generalize the learning to predict liquefaction potential for new cases not used in the construction of the model. The results of the developed EPR models are compared with a conventional model as well as a number of neural network-based models. It is shown that the proposed EPR model provides more accurate results than the conventional model and the accuracy of the EPR results is better than or at least comparable to that of the neural network-based models proposed in the literature. The advantages of the proposed EPR model over the conventional and neural network-based models are highlighted. 相似文献
8.
In the well-log data processing, the principal advantage of the nuclear magnetic resonance (NMR) method is the measurement of fluid volume and pore size distribution without resorting to parameters such as rock resistivity. Preliminary processing of the well-log data allowed first to have the petrophysical parameters and then to evaluate the performances of the transverse relaxation time T 2 NMR. Petrophysical parameters such as the porosity of the formation as well as the effective permeability can be estimated without having recourse the fluid type. The well-log data of five wells were completed during the construction of intelligent models in the Saharan oil field Oued Mya Basin in order to assess the reliability of the developed models. Data processing of NMR combined with conventional well data was performed by artificial intelligence. First, the support vector regression method was applied to a sandy clay reservoir with a model based on the prediction of porosity and permeability. NMR parameters estimated using intelligent systems, i.e., fuzzy logic (FL) model, back propagation neural network (BP-NN), and support vector machine, with conventional well-log data are combined with those of NMR, resulting in a good estimation of porosity and permeability. The results obtained during the processing are then compared to the FL and NN regression models performed by the regression method during the validation stage. They show that the correlation coefficients R 2 estimated vary between 0.959 and 0.964, corresponding to the root mean square error values of 0.20 and 0.15. 相似文献
9.
A key challenge in the oil and gas industry is the ability to predict key petrophysical properties such as porosity and permeability. The predictability of such properties is often complicated by the complex nature of geologic materials. This study is aimed at developing models that can estimate permeability in different reservoir sandstone facies types. This has been achieved by integrating geological characterization, regression models and artificial neural network models with porosity as the input data and permeability as the output. The models have been developed, validated and tested using samples from three wells and their predictive accuracy tested by using them to predict the permeability in a fourth well which was excluded from the model development. The results indicate that developing the models on a facies basis provides a better predictive capability and simpler models compared to developing a single model for all the facies combined. The model for the combined facies predicted permeability with a correlation coefficient of 0.41 which is significantly lower than the correlation coefficient of 0.97, 0.93, 0.99, 0.96, 0.96 and 0.85 for the massive coarse-grained sandstones, massive fine-grained sandstones-moderately sorted, massive fine-grained sandstones-poorly sorted, massive very fine-grained sandstones, parallel-laminated sandstones and bioturbated sandstones, respectively. The models proposed in this paper can predict permeability at up to 99% accuracy. The lower correlation coefficient of the bioturbated sandstone facies compared to other facies is attributed to the complex and variable nature of bioturbation activities which controls the petrophysical properties of highly bioturbated rocks. 相似文献
10.
In reality, footings are most likely to be founded on multi-layered soils. The existing methods for predicting the bearing capacity of 4-layer up to 10-layer cohesive soil are inaccurate. This paper aims to develop a more accurate bearing capacity prediction method based on multiple regression methods and multi-layer perceptrons (MLPs), one type of artificial neural networks (ANNs). Predictions of bearing capacity from the developed multiple regression models and MLP in tractable equations form are obtained and compared with the value predicted using traditional methods. The results indicate ANNs are able to predict accurately the bearing capacity of strip footing and outperform the existing methods. 相似文献
11.
Emad S. AlHomadhi 《Arabian Journal of Geosciences》2014,7(7):2871-2879
In sandstone, there is a trend between porosity (?) and permeability (k). It is a linear relationship having the form log (k)?=?a?+?(b ?). The slope, intercept, and degree of scatter of the log(k)???? trends vary from formation to another. These variations are attributed to differences in initial grain size and sorting, diagenetic history, cementation, clay content, pore geometry, and compaction history. In the literature, permeability and porosity modeling by using lab experiments was carried out by using unconsolidated sandstone, sand packs, or synthetic particles. Such models cannot be applied to predict flow properties of consolidated natural sandstone. Furthermore in these models, sand grain size, shape, and sorting factors were considered as the main factors that affect porosity and permeability. Hardly, any attention was paid to the confining pressure and the fraction of cementing material that bind the grain to form a coherent rock. If these two crucial aspects are not taken into consideration during the model development, the model cannot be applied to natural consolidated sandstone. The main objective of the present paper is to develop a new model for porosity versus permeability taking into account important factors such as sand grain size and sorting, compaction pressure, and concentration of cementing material that bind the sand grains. The effect for clay swelling or migration was however discarded, as the sand grains were washed prior to consolidation. The sand used in producing the sandstone cores was medium- to fine-sized well-sorted sand grains. The grain’s sphericity was measured to be in the range of (0.8–0.9) with little angularity. The fabricated cores have an average compressive strength of 5,700 psi, which is comparable with Bera sandstone strength. Also, the produced cores were stable in the fluid media as they were subjected to 300 °C to allow cementing material to be crystallized. The aspect of the present work was to analyze the dependence of both the permeability as well as the porosity on the variables of the present study that consist of grain size, cementation fraction, and the confining pressure. Using the experimental data, a linear relationship, in terms of each variable, was developed here that can eventually help researchers to fabricate cores with desired properties. The second step was to generate more general models to be used as references for scholars for further work in this research field. Nonlinear regression analysis was carried out on all the three variables of the present study to obtain two nonlinear correlations: one describes the behavior of permeability and the other describes porosity. In the third step, an advanced correlation that describes permeability versus porosity in a quantitative manner was developed by using nonlinear regression analysis. Permeability was studied accordingly as a function of all the three variables of the present study as well as porosity. This step represents the main objective of this paper. 相似文献
12.
A numerical compaction model of overpressuring in shales 总被引：1，自引：0，他引：1
A one-dimensional model of sediment compaction is presented to relate pressure, porosity, permeability, and fluid and solid-particle velocities in an evolving sedimentary basin. The burial history of a sedimentary package is followed and incorporated into rate models for diagenetic reactions to predict clay compositions with depth. The governing set of nonlinear, partial differential equations constitutes a moving boundary problem and is solved by a finite difference scheme. Sedimentation rates and a permeability-porosity function for shales are required to implement the model. Additional factors are incorporated to mimic the effect of increased fluid volume generated by dehydration from clay mineral transformations and by thermal expansion. We demonstrate that the major cause of overpressuring in sediments accumulating along passive margins is nonequilibrium compaction. Sedimentation rates and strata permeability are the most important geologic factors in the formation of overpressured zones. Smectite dehydration and aquathermal pressuring play secondary roles in the development and sustenance of overpressures. 相似文献
13.
致密砂岩气层压裂产能及等级预测方法 总被引：1，自引：0，他引：1
致密砂岩储层孔隙度小、渗透率低、含气饱和度低,基本上没有自然产能,需要进行压裂,因此进行压裂产能的预测很有必要。笔者研究了鄂尔多斯盆地苏里格东部地区盒8段致密砂岩气层的压裂产能及等级预测。利用反映储层流动性质的测井参数(电阻率、自然伽马、声波时差、中子、密度)与反应压裂施工情况的压裂施工参数(单位厚度砂体积、砂比、砂质量浓度、单位厚度排量、单位厚度入井总液量),选择数学统计方法神经网络法进行致密砂岩气层压裂产能等级预测。分析比较Elman神经网络、支持向量回归(SVR)、广义回归神经网络(GRNN)3个神经网络预测致密砂岩气层压裂产能模型的网络结构参数、回判及预测精度以及运行耗费时间。结果表明:3个模型中,GRNN网络参数只有1个,回判和预测精度最高,运行时间小于1 s。因此,选择GRNN模型预测致密砂岩气层压裂产能,并用于苏里格东部地区致密砂岩气层压裂产能的等级预测。等级预测准确率达到90%。 相似文献
14.
P. H. S. W. Kulatilake T. Hudaverdi Qiong Wu 《Geotechnical and Geological Engineering》2012,30(3):665-684
The paper refers the reader to a blast data base developed in a previous study. The data base consists of blast design parameters, explosive parameters, modulus of elasticity and in situ block size. A hierarchical cluster analysis was used to separate the blast data into two different groups of similarity based on the intact rock stiffness. The group memberships were confirmed by the discriminant analysis. A part of this blast data was used to train a single-hidden layer back propagation neural network model to predict mean particle size resulting from blast fragmentation for each of the obtained similarity groups. The mean particle size was considered to be a function of seven independent parameters. An extensive analysis was performed to estimate the optimum value for the number of units for the hidden layer for each of the obtained similarity groups. The blast data that were not used for training were used to validate the trained neural network models. For the same two similarity groups, multivariate regression models were also developed to predict mean particle size. Capability of the developed neural network models as well as multivariate regression models was determined by comparing predictions with measured mean particle size values and predictions based on one of the most applied fragmentation prediction models appearing in the blasting literature. Prediction capability of the trained neural network models as well as multivariate regression models was found to be strong and better than the existing most applied fragmentation prediction model. Diversity of the blasts data used is one of the most important aspects of the developed models. 相似文献
15.
16.
The retention curve of French FoCa compacted clay has been determined at 20, 50 and 80 °C. A saline saturated solution has been used to control the suction. The temperature, up to 80 °C, has no influence on the e(Pc) curve. On the other hand, the water content and the liquid saturation degree are lower at 50 or 80 °C than at 20 °C. A model is proposed to take into account the influence of the temperature, in the framework of Biot's theory.A method to determine the liquid permeability of an unsaturated porous media is proposed. It is based on an analytical solution and on an experimental survey of the transient phase of desorption. This method has been applied to the compacted FoCa clay, at 20 °C. It is easy to implement and efficient. The permeability of FoCa clay has been determined for a large range of suctions. 相似文献
17.
An unsaturated hydraulic conductivity model for compacted GMZ01 bentonite with consideration of temperature 总被引：1，自引：0，他引：1
W. M. Ye M. Wan B. Chen Y. G. Chen Y. J. Cui J. Wang 《Environmental Earth Sciences》2014,71(4):1937-1944
As one of the most important properties of compacted bentonite used as buffer/backfill materials, hydraulic conductivity is influenced by various factors including temperature, microstructure and suction (or degree of saturation), etc. Based on the readily available results of both temperature-controlled water-retention tests and unsaturated infiltration tests under confined (constant volume) conditions, influences of temperature and microstructure variations on unsaturated hydraulic conductivity of the compacted Gaomiaozi (GMZ01) bentonite were analyzed. Then, a revised unsaturated hydraulic conductivity model considering temperature effects and microstructure changes was developed. With this proposed model, prediction and comparison were made on the unsaturated hydraulic conductivity of the compacted GMZ01 bentonite at 20 °C. Results show that water-retention capacity of compacted GMZ01 bentonite decreases as temperature increases and the degree of the temperature influence depends on suction. Under confined conditions, influence of hydration on microstructure of compacted GMZ01 bentonite depends on pore size. The proposed model can well describe the variations of unsaturated hydraulic conductivity with suction at different temperatures. However, further improvement of the proposed model is needed to account for the phenomenon of inter-aggregate pores clogging that occurred at the initial stage of hydration of compacted GMZ01 bentonite under confined conditions. 相似文献
18.
为研究高填方路堤压实土率相关变形特征,对不同压实度的非饱和压实土分别开展了不同加载速率以及不同围压条件下的CD三轴剪切试验,探讨了不同工况下压实土的剪切强度指标;借助GDS饱和土静态三轴仪的围压控制器来间接测定非饱和压实土体变的途径。试验结果表明：压实土强度及变形特征具有明显的时间相依性,加载速率越大,压实土的抗剪强度越高,超固结变形特性越强,抗剪强度指标黏聚力c值增幅较大、内摩擦角 值增幅较小;低围压下,压实土呈应变软化及剪胀变形,且压实度越高,应变软化及剪胀变形越显著,c值增加明显、 值增加缓慢。采用基于下负荷面的弹黏塑性本构模型对路基压实土的率相关变形特征进行表征,预测结果与试验数据吻合良好,表明该模型适用于高填方路堤长期沉降分析。 相似文献
19.
基于GDS的黏土非线性渗透特性试验研究 总被引：4，自引：0，他引：4
基于黏土渗透性与孔隙比的非线性关系,讨论和总结了4种渗透模型,即 渗透模型、 渗透模型、 渗透模型和 渗透模型。来用GDS高级固结仪,对萧山黏土8个试样进行了一维固结渗透联合试验,使用直接法整理固结压力作用下渗透系数等试验结果,分析了对应于4种非线性渗透模型的土性参数。试验与分析结果表明,萧山黏土渗透性随固结压力增加呈现非线性减少,在50～1 600 kPa压力作用下其的渗透系数从8 ? 10-8 cm•s-1减少为8×10-9 cm•s-1;4种非线性渗透模型对萧山黏土都是适用的。 相似文献
20.
砂砾岩储层孔隙结构复杂、非均质性强,在渗透率计算方面传统的测井解释方法误差较大,目前还没有经典的计算砂砾岩渗透率的测井解释模型。以克拉玛依油田某区八道湾组砂砾岩稠油油藏为例,首先在微观层面上分析了渗透率的主控因素。其次根据本地区的实际情况建立了3套渗透率测井解释方法:一是在前人研究基础上改进了多元回归模型;二是在岩性识别的基础上分不同岩性建立了渗透率模型;三是利用BP神经网络进行了渗透率的预测。最后对传统的经验公式与文中的3种方法进行检验。结果表明,比起传统的经验公式和多元回归模型,基于不同岩性的渗透率模型与BP神经网络在实际应用中效果更好,较大幅度地提高了测井解释精度,在非均质性强的砂砾岩油藏中具有更好的应用前景。 相似文献