Reservoir induced earthquakes analyzed via radial basis function networks

Estimation of the magnitude of reservoir induced seismicity is essential for seismic risk analysis of dam sites. Different geological and empirical methods dealing with the mechanism or magnitude of such earthquakes are available in the literature. In this study, a method based on an artificial neural network utilizing radial basis functions (RBF network) was employed to analyze the problem. The network has only two input neurons, one representing the maximum depth of the reservoir and the other being a comprehensive parameter representing reservoir geometry. Magnitudes of the induced earthquakes predicted using the RBF network were compared with the actual recorded data. Compared with the conventional statistical approach, the proposed method gives a better prediction, both in terms of coefficients of correlation and error rates.     

Optimal seismic design of reinforced concrete structures under timehistory earthquake loads using an intelligent hybrid algorithm

A reliable seismic-resistant design of structures is achieved in accordance with the seismic design codes by designing structures under seven or more pairs of earthquake records. Based on the recommendations of seismic design codes, the average time-history responses(ATHR) of structure is required. This paper focuses on the optimal seismic design of reinforced concrete(RC) structures against ten earthquake records using a hybrid of particle swarm optimization algorithm and an intelligent regression model(IRM). In order to reduce the computational time of optimization procedure due to the computational efforts of time-history analyses, IRM is proposed to accurately predict ATHR of structures. The proposed IRM consists of the combination of the subtractive algorithm(SA), K-means clustering approach and wavelet weighted least squares support vector machine(WWLS-SVM). To predict ATHR of structures, first, the input-output samples of structures are classified by SA and K-means clustering approach. Then, WWLS-SVM is trained with few samples and high accuracy for each cluster. 9- and 18-storey RC frames are designed optimally to illustrate the effectiveness and practicality of the proposed IRM. The numerical results demonstrate the efficiency and computational advantages of IRM for optimal design of structures subjected to time-history earthquake loads.     

Response of base‐isolated nuclear structures for design and beyond‐design basis earthquake shaking

The American Society of Civil Engineers (ASCE) 43‐05 presents two performance objectives for the design of nuclear structures, systems and components in nuclear facilities: (1) 1% probability of unacceptable performance for 100% design basis earthquake (DBE) shaking and (2) 10% probability of unacceptable performance for 150% DBE shaking. To aid in the revision of the ASCE 4‐98 procedures for the analysis and design of base‐isolated nuclear power plants and meet the intent of ASCE 43‐05, a series of nonlinear response‐history analyses was performed to study the impact of the variability in both earthquake ground motion and mechanical properties of isolation systems on the seismic responses of base‐isolated nuclear power plants. Computations were performed for three representative sites (rock and soil sites in the Central and Eastern United States and a rock site in the Western United States) and three types of isolators (lead rubber, Friction Pendulum and low‐damping rubber bearings) using realistic mechanical properties for the isolators. Estimates were made of (1) the ratio of the 99th percentile (90th percentile) response of isolation systems computed using a distribution of spectral demands and distributions of isolator mechanical properties to the median response of isolation systems computed using best‐estimate properties and 100% (150%) spectrum‐compatible DBE ground motions; (2) the number of sets of three‐component ground motions to be used for response‐history analysis to develop a reliable estimate of the median response of isolation systems. The results of this study provide the technical basis for the revision of ASCE Standard 4‐98. Copyright © 2012 John Wiley & Sons, Ltd.     

Groundwater-level forecasting under climate change scenarios using an artificial neural network trained with particle swarm optimization

Abstract

Artificial neural networks (ANNs) have recently been used to predict the hydraulic head in well locations. In the present work, the particle swarm optimization (PSO) algorithm was used to train a feed-forward multi-layer ANN for the simulation of hydraulic head change at an observation well in the region of Agia, Chania, Greece. Three variants of the PSO algorithm were considered, the classic one with inertia weight improvement, PSO with time varying acceleration coefficients (PSO-TVAC) and global best PSO (GLBest-PSO). The best performance was achieved by GLBest-PSO when implemented using field data from the region of interest, providing improved training results compared to the back-propagation training algorithm. The trained ANN was subsequently used for mid-term prediction of the hydraulic head, as well as for the study of three climate change scenarios. Data time series were created using a stochastic weather generator, and the scenarios were examined for the period 2010–2020.

Editor Z.W. Kundzewicz; Associate editor L. See

Citation Tapoglou, E., Trichakis, I.C., Dokou, Z., Nikolos, I.K., and Karatzas, G.P., 2014. Groundwater-level forecasting under climate change scenarios using an artificial neural network trained with particle swarm optimization. Hydrological Sciences Journal, 59(6), 1225–1239. http://dx.doi.org/10.1080/02626667.2013.838005     

利用改进的粒子群算法反演视震源时间函数

视震源时间函数的提取是研究震源参数的重要途径. 本文提出了利用改进的粒子群(PSO)算法反演视震源时间函数的方法, 以水平线方法得到的结果作为PSO算法的初值, 并对PSO算法的惯性因子和学习因子进行改进, 提高计算效率. 采用改进的PSO算法对模拟数据进行了反演计算, 并与映射Landweber反褶积(PLD)方法和遗传算法(GA)进行了对比分析. 结果表明, 相对于PLD方法, 改进的PSO算法反演结果与真实结果误差更小; 相对于遗传算法, 改进的PSO算法计算效率提高了5倍以上. 最后, 利用改进的算法对2005年10月8日巴基斯坦克什米尔M_W7.6地震的P波视震源时间函数进行了提取, 结果表明此次地震P波视震源时间函数在25 s之内, 震源沿西北向破裂. 该结果与张勇等的结果一致.     

Time series forecasting by combining the radial basis function network and the self‐organizing map

Based on a combination of a radial basis function network (RBFN) and a self‐organizing map (SOM), a time‐series forecasting model is proposed. Traditionally, the positioning of the radial basis centres is a crucial problem for the RBFN. In the proposed model, an SOM is used to construct the two‐dimensional feature map from which the number of clusters (i.e. the number of hidden units in the RBFN) can be figured out directly by eye, and then the radial basis centres can be determined easily. The proposed model is examined using simulated time series data. The results demonstrate that the proposed RBFN is more competent in modelling and forecasting time series than an autoregressive integrated moving average (ARIMA) model. Finally, the proposed model is applied to actual groundwater head data. It is found that the proposed model can forecast more precisely than the ARIMA model. For time series forecasting, the proposed model is recommended as an alternative to the existing method, because it has a simple structure and can produce reasonable forecasts. Copyright © 2005 John Wiley & Sons, Ltd.     

径向基函数(RBF)神经网络及其应用

介绍了径向基函数(RBF)神经网络的原理、 学习算法及其在地震预报专家系统ESEP 3.0中的应用。 实际应用结果表明, 该神经网络可以很好地克服BP神经网络学习过程的收敛过分依赖于初值和可能出现局部收敛的缺陷, 具有较快的运算速度、 较强的非线性映射能力和较好的预报效能。     

结构随机地震响应分析的复模态法

本文对多自由度基础平动结构随机地震响应问题进行了系统研究。针对用第1振型近似代表上部结构所得方程为非经典阻尼和非对称结构情况。用复模态法解耦。获得了以第1振型表示的结构地震响应的解析解。对单自由度体系。此解即为结构响应的精确解。本文方法也可用于带TMD减震结构等的随机地震响应分析与优化设计。     

Municipal water demand forecasting under peculiar fluctuations in population: a case study of Mashhad,a tourist city

ABSTRACT

Forecasting future water demands has always been of great complexity, especially in the case of tourist cities which are subject to population fluctuations. In addition to the usual uncertainties related to climate and weather variables, daily water consumption in Mashhad, a tourist city is affected by a significant different fluctuation. Mashhad is the second most populous city in Iran. The number of tourists visiting the city is subject to national and religious events, which are respectively based on the Iranian formal calendar (secular calendar) and the Arabic Hijri calendar (Islamic religious calendar). Since religious events move relative to the secular calendar, the coincidence of the two calendars results in peculiar wild fluctuations in population. Artificial neural networks (ANNs) are chosen to predict water demand under such conditions. Three types of ANNs, feedforward back-propagation, cascade-forward and radial basis functions, are developed. In order to track how population fluctuation propagates in the model and affects the outputs, two sets of inputs are considered. For the first set, based on evaluating several repetitions, a typical combination of variables is selected as inputs, whereas for the second set, new calendar-based variables are included to decrease the effect of population fluctuations; the results are then compared using some performance criteria. A large number of runs are also conducted to assess the impact of random initialization of the weights and biases of networks and also the effect of calendar-based inputs on improvement of network performance. It is shown that, from the points of view of performance measures and unchanging outputs through numerous runs, the radial basis network that is trained by patterns including calendar-based inputs can provide the best domestic water demand forecasting under population fluctuations.

Editor D. Koutsoyiannis Associate editor E. Rozos     

Application of PP cluster method in the earthquake swarm analysis

ＡｐｐｌｉｃａｔｉｏｎｏｆＰＰｃｌｕｓｔｅｒｍｅｔｈｏｄｉｎｔｈｅｅａｒｔｈｑｕａｋｅｓｗａｒｍａｎａｌｙｓｉｓＳｈｉ－ＹｏｎｇＺＨＯＵ；（周仕勇）Ｌｉｎｇ－ＲｅｎＺＨＵ；（朱令人）ａｎｄＣｈｕａｎ－ＬｉｎｇＤＥＮＧ（邓传玲）（Ｓｅｉｓｍｏｌｏｇｉｃ...     

The complex temporal sequence structures of non－single exponential attenuation of Batang earthquake swarm with M6．7

Ｔｈｅｃｏｍｐｌｅｘｔｅｍｐｏｒａｌｓｅｑｕｅｎｃｅｓｔｒｕｃｔｕｒｅｓｏｆｎｏｎ－ｓｉｎｇｌｅｅｘｐｏｎｅｎｔｉａｌａｔｔｅｎｕａｔｉｏｎｏｆＢａｔａｎｇｅａｒｔｈｑｕａｋｅｓｗａｒｍｗｉｔｈＭ６．７Ｗａｎ－ＺｈｅｎｇＣＨＥＮＧ（程万正）（Ｓｅｉｓ...     

The application of neural networks to comprehensive prediction by seismology prediction method

IntroductionThe theory of artificial neural netWorks has been used in some fields for recent years such asearthquake damage prediction (Shi, Liu, 1991), earthquake intensity (Wang, 1993), earthquakecomprehensive prediction (Wang, Dai, 1997), and so on. The initial Studies indicate that someresults are prevail over classical statistical pattern recognition and fuZZy recognition methods.Neural network system is a high adaptive nonlinear dynamical system. It can extract causalitythrough a ple…     

Neural network model for liquefaction potential in soil deposits using Turkey and Taiwan earthquake data

Simplified methods have been practiced by researchers to assess nonlinear liquefaction potential of soil. Derived from several field and laboratory tests, various simplified procedures such as stress-based, strain-based, Chinese criteria, etc. have been developed by utilizing case studies and undisturbed soil specimens. In order to address the collective knowledge built up in conventional liquefaction engineering, an alternative general regression neural network model is proposed in this paper.To meet this objective, a total of 620 sets of data including 12 soil and seismic parameters are introduced into the model. The data includes the results of field tests from the two major earthquakes that took place in Turkey and Taiwan in 1999 and some of the desired input parameters are obtained from correlations existing in the literature.The proposed GRNN model was developed in four phases, mainly: identification phase, collection phase, implementation phase, and verification phase. An iterative procedure was followed to maximize the accuracy of the proposed model. The case records were divided randomly into testing, training, and validation datasets.Generating a model that takes into account of 12 soil and seismic parameters is not feasible by using simplified techniques; however, the proposed GRNN model effectively explored the complex relationship between the introduced soil and seismic input parameters and validated the liquefaction decision obtained by simplified methods. The proposed GRNN model predicted well the occurrence/nonoccurrence of soil liquefaction in these sites. The model provides a viable tool to geotechnical engineers in assessing seismic condition in sites susceptible to liquefaction.     

Optimum design of structures against earthquake by wavelet neural network and filter banks

Optimum design of structures for earthquake is achieved by simulated annealing. To reduce the computational work, a fast wavelet transform is used by means of which the number of points in the earthquake record is decreased. The record is decomposed into two parts. One part contains the low frequency of the record, and the other contains the high frequency of the record. The low‐frequency content is the effective part, since most of the energy of the record is contained in this part of the record. Thus, the low‐frequency part of the record is used for dynamic analysis. Then, using a wavelet neural network, the dynamic responses of the structures are approximated. By such approximation, the dynamic analysis of the structure becomes unnecessary in the process of optimization. The wavelet neural networks have been employed as a general approximation tool for the time history dynamic analysis. A number of structures are designed for optimal weight and the results are compared to those corresponding to the exact dynamic analysis. Copyright © 2004 John Wiley & Sons, Ltd.     

框架结构在汶川5.12大地震中的震害分析及抗震启示

列举了框架结构在汶川5.12大地震中的典型震害现象,重点调查了框架柱、梁柱节点,强梁弱柱及填充墙的震害特点,分析了框架结构未能实现强柱弱梁机制的原因,指出了提高框架柱抗震能力的措施及减轻填充墙地震破坏的对策.     

震后多层砌体结构的抗震鉴定与加固设计

本文以5·12汶川地震后绵竹市某砖混结构住宅为典型调查研究对象,介绍了震后多层砌体结构房屋的常见震害现象和一般震害规律,结合有关规范分析了一般受损建筑不同的抗震鉴定方法和手段,对比分析了各种抗震加固措施的加固效果与适用条件,较为全面地总结了一般多层砌体结构从震害调查到鉴定加固的方法和程序,为灾后砌体结构的抗震加固设计提...     

结构抗震分析用地震动强度指标的研究

随着基于性能结构抗震设计方法的推广应用,结构弹塑性时程分析逐渐成为主要的分析方法,但该方法所面临主要困难是缺乏对地震波选择的统一标准.由于影响地震动的参数很多,且不同参数对结构弹塑性地震响应的影响规律又十分复杂,因此能综合反映各种地震动参数对结构弹塑性地震响应影响的地震动强度指标成为基于性能结构抗震设计方法研究中的一个基本问题.本文参考已有学者的研究成果,总结归纳了现有主要的33个地震动强度指标,基于弹塑性SDOF和MDOF系统的代表性地震响应指标,分析了不同地震动强度指标与不同结构地震响应指标之间的相关性,研究了不同地震动指标的适用范围和优缺点,给出了结构抗震分析用地震强度指标的建议.     

利用广义叠加反演方法估算长岛震群应力降

地震应力降是表征震源特性的一个重要参数,通常由震源谱计算得到.但如何从大量地震的观测谱中校正路径和台站效应,准确地分离出震源谱并计算应力降,仍是一个难题.本文采用广义叠加反演方法通过分阶段叠加从观测谱中迭代分离出震源项、台站项和路径项,并利用分震级的叠加震源项与理论谱的拟合得到经验格林函数,再利用由经验格林函数校正后的真实震源谱估算出应力降.该方法不需要知道仪器响应、场地响应和传播路径上的衰减系数,并且不用事先假设震源具有自相似的恒应力降特征,计算效率很高,适用于反演大量地震的震源参数.我们将广义叠加反演方法应用于长岛震群,利用S波谱估算了1431个M_L≥1.0地震的应力降.结果表明,广义叠加反演方法获得的震源参数和用传统方法得到的结果一致;长岛震群地震的应力降较小（中值是0.3 MPa）,变化范围很大（0.009~3.04 MPa之间）,属于低应力降事件集;同时应力降中值随地震矩增大而增大,偏离了自相似理论.应力降空间变化不均匀,高应力降事件主要集中在震群的端部（NW端）,到最近断层距离的依赖性不强,在9、10 km处的应力降中值略高于其他深度.根据应力降的变化特征和区域构造条件,我们推测地下流体在长岛震群的活动中起到一定的作用.

     

地震诱发的侧向水平位移神经网络预测模型

在对地震液化诱发的侧向水平位移预测模型评述的基础上，分析了地震、地形、土质等实测数据与侧向水平水移之间的相互关系，并提出了侧向位平位移神经网络预测模型。模型较好地反映了参数之间复杂的非线性关系，网络预测结果与实测数据较为吻合，两者之间相关系数为0．9左右。模型数据分析结果表明侧向位移随着距自由临空面距离（L）的增加而呈双曲线关系下降，随液化层厚度的增加而增加。不同L条件一临空面高度与侧向位移之间有一灵敏变化区，即当H约等于4－7m之间时，侧向位移急剧变化。