基于PSONN的大坝监控实时预报模型

将粒子群算法（PSO）引入大坝监测领域,提出一种基于粒子群神经网络（PSONN）的大坝监控预报模型。该模型充分发挥PSO的全局寻优能力和BP神经网络局部细致搜索优势,给BP神经网络提供了良好的初始权值。对逐一粒子群（SPSONN）、整体粒子群（WPSONN）、逐一BP（SBPNN）及整体BP（WBPNN）4种预报模型的对比分析表明：逐一预报模型（SPSONN和SBPNN）的预报精度明显高于对应的整体预报模型（WPSONN和WBPNN）的预报精度;与BP神经网络模型相比,PSONN模型不仅收敛速度明显加快,而且预报精度也有较大提高,尤其是SPSONN模型,其高精度和短历时性完全满足实时预报的需要,可以准确、有效地应用于大坝监测量的实时预报。     

An objective prediction model for typhoon rainstorm using particle swarm optimization: neural network ensemble

A nonlinear ensemble prediction model for typhoon rainstorm has been developed based on particle swarm optimization-neural network (PSO-NN). In this model, PSO algorithm is employed for optimizing the network structure and initial weight of the NN with creating multiple ensemble members. The model input of the ensemble member is the high correlated grid point factors selected from the rainfall forecast field of Japan Meteorological Agency numerical prediction products using the stepwise regression method, and the model output is the future 24 h rainfall forecast of the 89 stations. Results show that the objective prediction model is more accurate than the numerical prediction model which is directly interpolated into the stations, so it can better been implemented for the interpretation and application of numerical prediction products, indicating a potentially better operational weather prediction.     

Particle swarm optimization for numerical bifurcation analysis in computational inelasticity

An efficient and robust algorithm to numerically detect material instability or bifurcation is of great importance to the understanding and simulation of material failure in computational and applied mechanics. In this work, an intelligence optimizer, termed the particle swarm optimization, is introduced to the numerical solution of material bifurcation problem consisting of finding the bifurcation time as well as the corresponding bifurcation directions. The detection of material bifurcation is approached as a constrained minimization problem where the determinant of the acoustic tensor is minimized. The performance of the particle swarm optimization method is tested through numerical bifurcation analysis on both small and finite deformation material models in computational inelasticity with increasing complexity. Compared with conventional numerical approaches to detect material bifurcation, the proposed method demonstrates superior performance in terms of both computational efficiency and robustness. Copyright © 2016 John Wiley & Sons, Ltd.     

Prediction of drought in dry lands through feedforward artificial neural network abilities

Drought is one of the most important natural hazards in Iran. It is especially more prevalent in arid and hyper arid regions where there are serious limitations in regard to providing sufficient water resources. On the other hand, drought modeling and particularly its prediction can play important role in water resources management under conditions of lack of sufficient water resources. Therefore, in this study, drought prediction in a hyper arid location of Iran (Ardakan region) has been surveyed based on the abilities of artificial neural. Standardized Precipitation Index (SPI) in different time scales (3, 6, 9, 12, and 24 monthly time series) computed based on the data gathered from four rain gauge stations. After evaluation and testing of different artificial neural networks (ANN) structures, gradient descent back propagation (traingd) network showed higher abilities than others. Then, the predictions of SPI time series with different monthly lag times (1:12 months) were tested. Generally, drought prediction by ANNs in the Ardakan region has shown considerable results with the correlation coefficient (R) more than 0.79 and in the most cases and it rises more than 0.90, which indicates the ANN’s ability of drought prediction.     

基于粒子迁徙的粒群优化算法及其在岩土工程中的应用

受自然界物种迁徙的启发,提出了一种新的改进的粒群优化算法(MPSO)。算法初始化时,将粒子随机地划分为若干个子粒群,每个子粒群按照给定的策略独立演化,在演化中的指定时段进行粒子的随机迁徙和自适应变异,以保持整个种群的多样性,避免早熟收敛。基准测试函数的计算结果表明,MPSO算法的性能优于其他几种改进算法。堆石体幂函数流变模型,参数较多,具有很强的非线性,将MPSO算法应用到堆石体幂函数流变模型的参数反演中。计算结果表明,利用反演的流变模型参数计算的坝体流变变形与实测变形在发展规律和数值上均比较吻合,证明MPSO算法在多参数、强非线性的复杂模型参数反演中的优越性。     

Application of a feedforward neural network in the search for Kuroko deposits in the Hokuroku district, Japan

A feedforward neural network with one hidden layer and five neurons was trained to recognize the distance to kuroko mineral deposits. Average amounts per hole of pyrite, sericite, and gypsum plus anhydrite as measured by X-rays in 69 drillholes were used to train the net. Drillholes near and between the Fukazawa, Furutobe, and Shakanai mines were used. The training data were selected carefully to represent well-explored areas where some confidence of the distance to ore was assured. A logarithmic transform was applied to remove the skewness of distance and each variable was scaled and centered by subtracting the median and dividing by the interquartile range. The learning algorithm of annealing plus conjugate gradients was used to minimize the mean squared error of the scaled distance to ore. The trained network then was applied to all of the 152 drillholes that had measured gypsum, sericite, and pyrite. A contour plot of the neural net predicted distance to ore shows fairly wide areas of 1 km or less to ore; each of the known deposit groups is within the 1 km contour. The high and low distances on the margins of the contoured distance plot are in part the result of boundary effects of the contouring algorithm. For example, the short distances to ore predicted west of the Shakanai (Hanaoka) deposits are in basement. However, the short distances to ore predicted northeast of Furotobe, just off the figure, coincide with the location of the Nurukawa kuroko deposit and the Omaki deposit, south of the Shakanai-Hanaoka deposits, seems to be on an extension of short distance to ore contour, but is beyond the 3 km limit from drillholes. Also of interest are some areas only a few kilometers from the Fukazawa and Shakanai groups of deposits that are estimated to be many kilometers from ore, apparently reflecting the network's recognition of the extreme local variability of the geology near some deposits.     

基于粒子群优化的BP神经网络模型参考自适应控制系统

将粒子群优化的BP神经网络作为模型，参考自适应控制系统的控制器，把参考模型输出与系统实际输出的均方误差作为PSO-BP神经网络的适应函数，通过PSO算法强大的搜索性能使自适应控制系统的均方误差最小化。仿真实例结果表明，基于粒子群优化算法的BP神经网络自适应控制系统收敛快、精度高，有较好的网络的泛化和适应能力，能够很好地控制系统的输出跟随参考模型的输出。     

Hybrid particle swarm optimization for first-order reliability method

A reliability analysis method based on the combination of the first-order reliability method (FORM) and hybrid particle swarm optimization (SACPSO) is presented for the reliability optimization calculation. The new reliability method, named as SACPSO-FORM, can be utilized for those complex reliability problems with correlated non-normal variables and implicit performance functions. Three examples are performed to verify its validation, and stability reliability analysis on the complicated rock foundation of a practical gravity dam is demonstrated. The results show that the proposed method is accurate, stable, flexible and efficient for reliability analysis in engineering applications.     

双种群进化粒子群算法求解地下水管理模型

为避免粒子群算法(PSO)早熟的缺点,设计了一种双种群进化粒子群算法(DE-PSO)。DE-PSO是基于PSO,引入选择、交叉及差分变异操作,并结合合理有效的粒子评价方法及越界处理方法之后形成的。将DE-PSO应用于两个地下水管理模型算例,第一个算例DE-PSO解的总抽水量分别比遗传算法(GA)、模拟退火算法(SA)和PSO减少了64、256、207 m3/d,第二个算例DE-PSO解的总治理成本分别比GA、SA和PSO减少了57.74、151.93、76.59万元。两个算例中DE-PSO都表现出稳定的进化趋势,寻优效率好于GA、SA和PSO,可以有效求解地下水管理模型问题。     

喀斯特流域降雨-径流人工神经网络模型结构分析及模拟

喀斯特流域降雨-径流响应是一个非线性过程,分析确定地下河流量过程的主要影响因子对喀斯特流域水文过程模拟具有重要意义.本文利用普定后寨河流域实测降雨、径流系列资料,采用神经网络权重分析法确定该流域的人工神经网络模型结构为两个隐含层、三个输入变量,该人工神经网络模型结构可以保持降雨-径流模拟的稳定性.模型经交叉训练与验证,训练期效率系数(NSC)达0.9以上,验证期NSC达0.88以上.说明神经网络权重分析法能够较好地确立预报因子与预报对象的关系,为喀斯特流域降雨-径流模拟提供一种有效的分析手段.     

基于仿生原理的粒子群算法求解江安校区水动力弥散系数

水动力弥散系数是研究地下水溶质运移的一个重要参数。为了解污染物在地下水中的运移规律,利用基于仿生学原理的粒子群算法,求解四川大学江安校区弥散试验场中的潜水含水层天然流场下的水动力弥散系数,并与最小二乘法和标准曲线对比法的计算结果相比较。研究结果表明,标准曲线法的计算结果受人为主观影响误差较大;最小二乘法计算结果与实测数据拟合较好,但计算过程相对复杂;粒子群算法的求解精度最高,计算更快,具有良好的收敛性,是一种可靠的求解方法。     

Application of convolutional neural network fused with machine learning modeling framework for geospatial comparative analysis of landslide susceptibility

Natural Hazards - Landslides in mountain settlements are among the most widespread and dangerous geohazards. In this study, we aimed to assess landslide susceptibility using Wenchuan, southwest...     

Hybrid differential evolution and particle swarm optimization for optimal well placement

There is no gainsaying that determining the optimal number, type, and location of hydrocarbon reservoir wells is a very important aspect of field development planning. The reason behind this fact is not farfetched—the objective of any field development exercise is to maximize the total hydrocarbon recovery, which for all intents and purposes, can be measured by an economic criterion such as the net present value of the reservoir during its estimated operational life-cycle. Since the cost of drilling and completion of wells can be significantly high (millions of dollars), there is need for some form of operational and economic justification of potential well configuration, so that the ultimate purpose of maximizing production and asset value is not defeated in the long run. The problem, however, is that well optimization problems are by no means trivial. Inherent drawbacks include the associated computational cost of evaluating the objective function, the high dimensionality of the search space, and the effects of a continuous range of geological uncertainty. In this paper, the differential evolution (DE) and the particle swarm optimization (PSO) algorithms are applied to well placement problems. The results emanating from both algorithms are compared with results obtained by applying a third algorithm called hybrid particle swarm differential evolution (HPSDE)—a product of the hybridization of DE and PSO algorithms. Three cases involving the placement of vertical wells in 2-D and 3-D reservoir models are considered. In two of the three cases, a max-mean objective robust optimization was performed to address geological uncertainty arising from the mismatch between real physical reservoir and the reservoir model. We demonstrate that the performance of DE and PSO algorithms is dependent on the total number of function evaluations performed; importantly, we show that in all cases, HPSDE algorithm outperforms both DE and PSO algorithms. Based on the evidence of these findings, we hold the view that hybridized metaheuristic optimization algorithms (such as HPSDE) are applicable in this problem domain and could be potentially useful in other reservoir engineering problems.     

位移反分析的粒子群优化-高斯过程协同优化方法

针对采用随机全局优化技术进行岩土工程位移反分析存在数值计算量大、效率低的问题,将粒子群优化算法与高斯过程机器学习技术相结合,提出了位移反分析的粒子群优化-高斯过程协同优化方法。该方法利用全局寻优性能优异的粒子群优化算法进行寻优的基础上,采用高斯过程机器学习模型不断地总结历史经验,预测包含全局最优解的最有前景区域,通过提高粒子群搜索效率并降低适应度评价次数,进而有效地降低位移反分析过程中的数值计算工作量。多种测试函数的数学验证和工程算例的研究结果表明该方法是可行的,与传统方法相比较,可显著地降低位移反分析的计算耗时。     

Evaluation of adsorption potential of bamboo biochar for metal-complex dye: equilibrium,kinetics and artificial neural network modeling

Metal-complex dyes are widely used in textile industry, but harmful to the environment and human health due to aromatic structure and heavy metal ions. The objective of this work was to evaluate the adsorption potential of bamboo biochar for the removal of metal-complex dye acid black 172 from solutions. Freundlich model was more suitable for the adsorption process of bamboo biochar than Langmuir isotherm, indicating multilayer adsorption of acid black 172 on a heterogeneous bamboo biochar surface. Adsorption kinetics analysis of pseudo-second-order and Weber–Morris models revealed that intraparticle transport was not the only rate-limiting step. The bamboo biochar exhibited a good adsorption performance even at high ionic strength. Analysis based on the artificial neural network indicated that the temperature with a relative importance of 29 % appeared to be the most influential parameter in the adsorption process for dye removal, followed by time, ionic strength, pH and dye concentration.     

Liquefaction behavior of Indo-Gangetic region using novel metaheuristic optimization algorithms coupled with artificial neural network

Natural Hazards - The present research aims to co-relate the plasticity and liquefaction response of soil as well as its significance in defining liquefaction probability. To accomplish this,...     

基于微粒群算法的大坝材料参数反分析研究

将微粒群算法应用于大坝参数反分析，同时分析了群体规模对算法的搜索效率和搜索质量的影响以及微粒群反分析算法的数值稳定性。对算例的分析结果表明，基于微粒群算法的大坝参数反分析方法简便易行，收敛精度高，且具有很好的抗噪音能力，是一种新的有效、可靠的参数反分析方法。     

基于自适应粒子群优化算法的波阻抗反演方法

针对地震勘探资料依赖线性优化方法进行波阻抗反演不易得到全局极值的问题,提出一种改进的粒子群优化算法-自适应粒子群优化算法进行波阻抗反演。自适应粒子群优化算法是以群智能优化理论为基础,通过3种可能移动方向的带权值组合进行全局寻优。该方法搜索速度较快,且具有较强的全局寻优能力。通过函数测试和波阻抗反演的应用,结果表明,自适应粒子群优化算法是一种适应能力较强的全局优化算法,用该方法进行波阻抗反演是可行有效的。