自适应模糊神经网络在膨胀土胀缩等级分类中的应用

针对膨胀土胀缩等级分类这一多因素评判问题,在分析自适应模糊神经网络原理及结构的基础上,利用减法聚类获得模糊推理规则数目,确定网络结构,建立了适用于膨胀土分类的自适应模糊神经网络,并将其应用于两个实际工程的膨胀土分类中,取得了良好的效果。研究结果表明,自适应模糊神经网络能实现BP网络和模糊综合评判的分类功能,而且比BP网络具有更透明的网络结构、比模糊综合评判更具学习功能,在膨胀土胀缩等级的分类中显示出较强的适用性。     

Fuzzy set approaches to classification of rock masses

Rock mass classification is analogous to multi-feature pattern recognition problem. The objective is to assign a rock mass to one of the pre-defined classes using a given set of criteria. This process involves a number of subjective uncertainties stemming from: (a) qualitative (linguistic) criteria; (b) sharp class boundaries; (c) fixed rating (or weight) scales; and (d) variable input reliability. Fuzzy set theory enables a soft approach to account for these uncertainties by allowing the expert to participate in this process in several ways. Hence, this study was designed to investigate the earlier fuzzy rock mass classification attempts and to devise improved methodologies to utilize the theory more accurately and efficiently. As in the earlier studies, the Rock Mass Rating (RMR) system was adopted as a reference conventional classification system because of its simple linear aggregation.

The proposed classification approach is based on the concept of partial fuzzy sets representing the variable importance or recognition power of each criterion in the universal domain of rock mass quality. The method enables one to evaluate rock mass quality using any set of criteria, and it is easy to implement. To reduce uncertainties due to project- and lithology-dependent variations, partial membership functions were formulated considering shallow (<200 m) tunneling in granitic rock masses. This facilitated a detailed expression of the variations in the classification power of each criterion along the corresponding universal domains. The binary relationship tables generated using these functions were processed not to derive a single class but rather to plot criterion contribution trends (stacked area graphs) and belief surface contours, which proved to be very satisfactory in difficult decision situations. Four input scenarios were selected to demonstrate the efficiency of the proposed approach in different situations and with reference to the earlier approaches.     

地质动力区划中断裂活动性的模糊综合评判

地质构造尤其是活动断裂控制着动力现象的区域性分布,然而活动断裂与矿井动力现象的关系并不是绝对和完全的。对断裂活动性进行评价,确定断裂的动力活动强度,是进行动力现象的预测与预防的重要内容之一。文章通过分析活动断裂的特征及其对矿区原地应力场的影响,提出了既具有代表性又容易获取的适合多尺度断裂活动性评价的5个主要指标,即活动断裂两侧断块的高程差、活动断裂长度、活动断裂走向与最大主应力的夹角、活动断裂走向与最大剪应力的夹角及断裂地震综合指标。利用模糊数学方法,建立了断裂活动性评价的模糊综合评判模型,确定了隶属函数,并通过层次分析法确定了各个指标的权重,最终获得了断裂活动性的模糊综合评判结果。将该方法应用于新汶矿区协庄矿,结果显示冲击地压多发生于具有强活动性的断裂附近。表明文章建立的评判模型能够较好地对断裂活动性进行分级。文章提出的模糊综合评判方法,改进了地质动力区划中断裂活动性评价方法,提高了评价结果的准确性及合理性。     

Joint estimation of PM2.5 and O3 over China using a knowledge-informed neural network

China has currently entered a critical stage of coordinated control of fine particulate matter (PM_2.5) and ozone (O₃), it is thus of tremendous value to accurately acquire high-resolution PM_2.5 and O₃ data. In contrast to traditional studies that usually separately estimate PM_2.5 and O₃, this study proposes a knowledge-informed neural network model for their joint estimation, in which satellite observations, reanalysis data, and ground station measurements are used. The neural network architecture is designed with the shared and specific inputs, the PM_2.5-O₃ interaction module, and the weighted loss function, which introduce the prior knowledge of PM_2.5 and O₃ into neural network modeling. Cross-validation (CV) results indicate that the inclusion of prior knowledge can improve the estimation accuracy, with R² increasing from 0.872 to 0.911 and from 0.906 to 0.937 for PM_2.5 and O₃ estimation under sample-based CV, respectively. In addition, the proposed joint estimation model achieves comparable performance with the separate estimation model, but with higher efficiency. Mapping results of PM_2.5 and O₃ derived by the proposed model have demonstrated interesting findings in the spatial and temporal trends and variations over China.     

Phytoplankton estimation using plant primary production rates in streams

A new approach is proposed to simulate the daily variation of chlorophyll a in one-dimensional streams. This approach uses the plant primary production rate to quantify the phytoplankton growth rate. The delta method, which is a piecewise analytical solution technique, is applied to determine the diurnal variation in plant primary production rate. The approach is tested by applying it to the Gumsuck stream in the Kyonggi-Do province in Korea. The optimization technique with constraints is used to obtain the best running results. Application of this approach shows that the values calculated using the method presented here are in good agreement with the measured values. Therefore, we conclude that this technique realistically simulates the daily variation of chlorophyll a.     

A hybrid method for grade estimation using genetic algorithm and neural networks

In the present paper, a new hybrid method is proposed for grade estimation. In this method, the multilayer perceptron (MLP) network is trained using the combination of the Levenberg–Marquardt (LM) method and genetic algorithm (GA). Having a few samples for grade estimation, it is difficult to get a proper result using some function approximation methods like neural networks or geostatistical methods. The neural network training methods are very sensitive to initial weight values when there are a few samples as a training dataset. The main objective of the proposed method is to resolve this problem. Here, our method finds the optimal initial weights by combining GA and LM method. Having the optimal initial values for weights, the local minima are avoided in the training phase and subsequently the neural network sustainability is trained optimally. Furthermore, the hybrid method is applied for grade estimation of Gol-e-Gohar iron ore in south Iran. The proposed method shows significant improvements compared to both conventional MLP and Kriging method. The efficiency of the proposed method gets more highlighted when the training data set is small.     

基于RS/GIS的城市财产保险洪灾损失评估研究

如何快速,有效地进行投保户洪涝灾害损失评估是保险行业急需解决的一个重要课题.从洪涝灾害的成灾机理出发,针对保险公司对具体受灾体理赔需求,提出了计算每个投保户洪灾损失率方法,建立基于遥感(RS)和地理信息系统(GIS)的城市财产保险洪涝灾害损失评估模型.建模时较全面地考虑了与投保物性质有关的承灾体易损度和与投保物所处环境有关的地基承载力等因素,并使用RS/GIS将其定量化提取.最后使用广东省深圳市洪灾数据进行模型检验.验证结果表明,模型对于各个投保户均能得到较好的精度.     

Estimation of groundwater recharge using water balance coupled with base-flow-record estimation and stable-base-flow analysis

In this paper, the long-term mean annual groundwater recharge of Taiwan is estimated with the help of a water-balance approach coupled with the base-flow-record estimation and stable-base-flow analysis. Long-term mean annual groundwater recharge was derived by determining the product of estimated long-term mean annual runoff (the difference between precipitation and evapotranspiration) and the base-flow index (BFI). The BFI was calculated from daily streamflow data obtained from streamflow gauging stations in Taiwan. Mapping was achieved by using geographic information systems (GIS) and geostatistics. The presented approach does not require complex hydrogeologic modeling or detailed knowledge of soil characteristics, vegetation cover, or land-use practices. Contours of the resulting long-term mean annual P, BFI, runoff, groundwater recharge, and recharge rates fields are well matched with the topographical distribution of Taiwan, which extends from mountain range toward the alluvial plains of the island. The total groundwater recharge of Taiwan obtained by the employed method is about 18 billion tons per year.An erratum to this article can be found at     

Pumping-rate control for contaminated groundwater with VOCs by using fuzzy inference model

In this paper, a new method is proposed for the remediation of contaminated groundwater. The method is based on fuzzy inference and risk evaluation. The effectiveness of the presented method is assessed in numerical simulations. The main results of the study are as follows: 1) A pump-and-treat control algorithm was proposed by using the fuzzy inference and the human health risk calculation model, 2) It was found that applying the proposed algorithm was likely to reduce the pumped quantity, and 3) It was found that the proposed model can be used to notify residents of the human health risk; the model is based on the ASTM RBCA model for residents. A new fuzzy control system for contaminated groundwater can be used as a useful model for characterising the effects of contaminants on human health and providing helpful information on the human risk assessment of the contaminated groundwater site.     

Reliability analysis for bearing capacity of surface strip footing using fuzzy finite element method

ABSTRACT

This paper presents the reliability analysis on the basis of the foundation failure against bearing capacity using the concept of fuzzy set theory. A surface strip footing is considered for the analysis and the bearing capacity is estimated using the conventional Finite Element Method (FEM). The spatial variability of the variables is taken into consideration to capture the physical randomness of the soil parameters for an isotropic field. A variation of the probability of failure (P_f) against a varying limiting applied pressure (q) is presented for different Coefficient of Variation (COV) of the variables and different scale of fluctuation (θ). The results reveal that the friction angle of soil (?) is the most influencing parameter among the other variables. Further, the influence of the scale of fluctuation (θ) on the probability of failure (P_f) is also examined. It is observed that for a particular COV of ?, higher value of θ predicts higher P_f whereas, P_f increases as COV of ? increases for a particular θ value. Later, a comparison study is accomplished to verify the viability of the present method and it can be noticed that the present method compares well with the other reliability method (First Order Reliability Method) to a reasonably good extent.     

地质统计学方法在河南宝丰某矿区铝土矿资源量估算中的应用

利用Surpac 6.3矿业软件,依据矿区铝土矿野外地质资料,建立地质数据库,构建了矿区的矿体三维模型。根据地质统计学的原理,将地质数据库中的样品进行组合,并对变异函数进行拟合和验证,建立变异函数模型,获取相应参数。采用普通克里格法对铝土矿矿体进行品位估值与资源量估算,结果较为准确可靠,为今后的勘查工作和定量、定概率预测提供了科学依据。     

基于杨赤中推估法空间插值的三维地质隐式建模

杨赤中推估法是一种对空间域复合变量通过连续的几何滤波过程来建立核函数的最小二乘推估法,建模过程简便且能基于少量已知数据点取得好的建模效果。针对地质勘查中离散、稀疏而不规则分布的地质特征点数据难以构建地质体三维模型的难点问题,提出了一种基于杨赤中推估法的三维地质空间插值与模型建立的自动化方法。该方法首先以地质特征点数据库为基础,选用负幂指数函数模型建立适合三维地质空间插值的杨赤中推估法估值数学模型;在此基础上,构建一套基于杨赤中推估法的三维地质空间插值计算和地质体隐式建模的自动化实现流程与程序;最后以实例矿化插值数据为基础,采用基于移动立方体算法的三维隐式建模方法,快速构建实例矿体三维模型。与人工交互圈定地质体边界和进行矿体推断的三维地质显式建模相比,这种方法能快速直观地分析地质特征并处理样品分析数据,方法可行且高效。     

利用滨海地下水潮汐效应估计含水层参数:以北海半岛为例

通过分析滨海含水层中观测孔的水位动态资料,确定含水层的水力性质和某些参数,或推测含水层在海底的延伸长度和露头处是否存在覆盖层,是水文地质学家一直很感兴趣的问题之一。文中充分分析了广西北海半岛滨海地区水文地质条件,将研究区第一个承压含水层系统概化为具有上覆弱透水层越流和含水层海底露头覆盖层的垂向三层结构的不稳定流模型。应用该模型的解析解对广西北海半岛滨海含水层系统的观测数据进行了分析,拟合效果很好,并利用最小平方罚函数法估算了研究区含水层的参数。     

A methodology using GIS, aerial photos and remote sensing for loss estimation and flood vulnerability analysis in the Supersano-Ruffano-Nociglia Graben, southern Italy

The impact of calamitous meteoric events and their interaction with the geological and geomorphological environment represent a current problem of the Supersano-Ruffano-Nociglia Graben in southern Italy. Indeed, severe floods take place on a frequent basis not only in autumn and winter, but in summer also. These calamities are not only triggered by exceptional events, but are also amplified by peculiar geological and morpho-structural characteristics of the Graben. Flooding often affects vast agricultural areas and consequently, water-scooping machines cannot remove the rainwater. These events cause warnings and emergency states, involving people as well as socio–economic goods. This study represents an application of a vanguard technique for loss estimation and flood vulnerability analysis, integrating a geographic information system (GIS) with aerial photos and remote sensing methods. The analysis results clearly show that the Graben area is potentially at greatest flood vulnerability, while along the Horsts the flood vulnerability is lower.     

Numerical modeling of hydraulic fracture propagation,closure and reopening using XFEM with application to in‐situ stress estimation

In this paper, a fully coupled model is developed for numerical modeling of hydraulic fracturing in partially saturated weak porous formations using the extended finite element method, which provides an effective means to simulate the coupled hydro‐mechanical processes occurring during hydraulic fracturing. The developed model is for short fractures where plane strain assumptions are valid. The propagation of the hydraulic fracture is governed by the cohesive crack model, which accounts for crack closure and reopening. The developed model allows for fluid flow within the open part of the crack and crack face contact resulting from fracture closure. To prevent the unphysical crack face interpenetration during the closing mode, the crack face contact or self‐contact condition is enforced using the penalty method. Along the open part of the crack, the leakage flux through the crack faces is obtained directly as a part of the solution without introducing any simplifying assumption. If the crack undergoes the closing mode, zero leakage flux condition is imposed along the contact zone. An application of the developed model is shown in numerical modeling of pump‐in/shut‐in test. It is illustrated that the developed model is able to capture the salient features bottomhole pressure/time records exhibit and can extract the confining stress perpendicular to the direction of the hydraulic fracture propagation from the fracture closure pressure. Copyright © 2016 John Wiley & Sons, Ltd.