BP神经网络洪水预报模型在洪水预报系统中的应用

采用相关分析法,在区域降水、观测断面流量(或水位)因子中识别出影响预报断面径流过程的主要变量,在多个观测断面的数据均为流量情况下,采用基于时延组合的合成流量为影响预报断面径流过程的变量,采用自相关分析法,识别出影响预报断面径流过程的前期流量(或水位),以这些变量为BP神经网络模型的输入,以预报断面的流量(或水位)为模型的输出,在BP神经网络隐层节点数自动优选的基础上,构建了基于BP神经网络的洪水预报模型。将模型载入中国洪水预报系统中,应用结果表明:模型在历史洪水训练样本具有一定代表性的情况下,可获得较高的预报精度。     

BP神经网络模型拟合受回水影响的水位流量关系研究

对受回水影响的水文测站的水位流量关系采用核水文渊站的水位及其与下游形成回水处的水文测站之间的落差作为输入建立BP神经网络模型进行拟合.结果表明,BP神经网络对受回水影响的水位流量关系拟合效果好,可以进行推广应用.     

莱州湾凹陷垦利油田沙河街组储层渗透率评价模型研究

文章以莱州湾凹陷垦利油田沙河街组储层为例,对传统的回归统计模型和基于BP神经网络的人工智能预测模型评价储层渗透率方法和效果进行了对比研究。目标储量报告里定火沙三段中孔、中渗;岩性（粒度）和孔隙度是储层渗透率的主要影响因素。根据岩心及测井数据,建立了孔隙度——粒度二元回归渗透率统计评价模型和BP神经网络渗透率预测模型。通过检验样本集精度对比,分析了隐含层数、隐含层节点数等网络结构参数变化对模型预测结果的影响,重点分析了不同的测井参数输入对BP神经网络模型预测结果的影响。优化后的BP神经网络模型对检验样本集的渗透率预测结果精度最高,其平均相对误差为37%,比传统的二元回归统计模型精度提高了26%。对目标油田三口井连续处理,BP神经网络模型渗透率预测结果更加合理,可以满足开发层段产能分析等生产需求。     

大伙房水库年径流预报方法研究

通过分析大伙房水库所属流域的气候特征,找出合适的预报因子;采用平稳时间序列、逐步线性回归、BP神经网络作为几种典型中长期预报方法的代表,分别对大伙房水库进行年径流预报建模;综合比较三种方法的拟合与检验预报结果,可以得出BP神经网络法是最适合该流域的预报方法.     

典型降水预报ANN多指标优选——以太湖湖西区为例

为提高多种典型人工神经网络应用于降水预报的精度与稳定性并做出优选,对太湖流域湖西区丹徒、丹阳、金坛、溧阳、宜兴5站的年降水量时间序列建立基于组成成分分析的人工神经网络模型,并通过平均相对误差、平均绝对误差、均方根误差及合格率4项评价指标对比分析预报效果。该模型采用Mann-Kendall法、秩和检验法、谱分析法进行组成成分分析;建立BP网络、小波神经网络、RBF网络、GRNN网络及Elman网络模拟并预测随机成分,与确定性成分叠加得年降水量预报结果。在湖西区的研究结果表明,基于组成成分分析的人工神经网络模型的拟合及预测精度高于原始人工神经网络和线性自回归模型,GRNN网络的预测精度与稳定性高于其他4类神经网络。     

黄河源区径流长期演变特征与趋势预测模型研究

利用小波分析方法对黄河源区径流数据系列的多尺度变化特征、突变点及变化趋势进行了分析.结果表明:黄河源区年径流量具有8a、15a、22a和36a左右的变化周期,其中8a、36a左右的周期变化最为显著.这些周期变化表明,2007年后流量将呈增加的趋势;1928、1982年和1985年是径流变化趋势重要的转变点.在小波分解的基础上,基于BP神经网络模型构建了黄河源区年径流量的长期动态预报模型,利用该模型对未来10a的流量变化进行了预测,并对其预报结果进行了分析.     

基于差异进化算法的前馈神经网络在大坝变形监测中的应用

针对当前大坝安全监测中广泛采用的回归模型欠拟合的不足,提出了基于差异进化算法的前馈神经网络模型。差异进化算法是基于种群策略的全局优化搜索算法,具有应用简单、收敛快的优点。采用该法训练的神经网络可以有效避免常规BP(back propagation)神经网络收敛于局部极小点的缺陷。将提出的方法应用于某拱坝的变形监测,通过计算表明,应用DE(differential evotntion)神经网络模型预报大坝变形的精度比常规回归模型和BP神经网络模型均有所提高。     

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。     

基于人工神经网络的大坝变形分析与预报——以西津大坝27~#点的变形监测为例

以MATLAB语言为基础,应用BP神经网络、逐步回归分析进行西津大坝27#点的变形分析与预报研究.在此基础上,进一步提出了逐步回归BP神经网络组合的预报方法,并探讨了3种方法的预报结果.研究表明,BP神经网络用于大坝变形分析与预报是可行的,所提出的逐步回归BP神经网络组合法提高了变形影响因子选择的科学性,在预报效果上,优于前两种方法.     

遗传模拟退火的BP算法在冲击地压中的应用

冲击地压的预测、预报的研究,大多数仍停留在简单的统计研究和单因素的预测方面,因而,结果也不十分理想。笔者采用多层前向网络对该问题进行数学建模,网络的训练算法采用基于遗传模拟退火的BP优化算法。该算法是在遗传算法中引入模拟退火机制,将其同BP算法结合,形成一个混合的优化算法。新算法既有神经网络的学习能力和鲁棒性,又有遗传算法的强全局随机搜索能力。同时,利用华丰矿冲击地压的实际监测数据,通过遗传算法的主要性能指标对新算法的参数进行了比较研究,得到优化后的一组参数。利用该参数,对冲击地压的神经网络模型的结构、权值和阈值进行了优化,得到了非全连接的优化神经网络模型。最后,利用该模型对华丰矿冲击地压进行了短期最大震级的预报。预测结果的相对误差率平均为 7.84 %,预测效果比较理想。     

Prediction of pile settlement using artificial neural networks based on standard penetration test data

In recent years artificial neural networks (ANNs) have been applied to many geotechnical engineering problems with some degree of success. With respect to the design of pile foundations, accurate prediction of pile settlement is necessary to ensure appropriate structural and serviceability performance. In this paper, an ANN model is developed for predicting pile settlement based on standard penetration test (SPT) data. Approximately 1000 data sets, obtained from the published literature, are used to develop the ANN model. In addition, the paper discusses the choice of input and internal network parameters which were examined to obtain the optimum model. Finally, the paper compares the predictions obtained by the ANN with those given by a number of traditional methods. It is demonstrated that the ANN model outperforms the traditional methods and provides accurate pile settlement predictions.     

Estimation of effective stress parameter of unsaturated soils by using artificial neural networks

Great efforts are required for determination of the effective stress parameter χ, applying the unsaturated testing procedure, since unsaturated soils that have the three‐phase system exhibit complex mechanical behavior. Therefore, it seems more reasonable to use the empirical methods for estimation of χ. The objective of this study is to investigate the practicability of using artificial neural networks (ANNs) to model the complex relationship between basic soil parameters, matric suction and the parameter χ. Five ANN models with different input parameters were developed. Feed‐forward back propagation was applied in the analyses as a learning algorithm. The data collected from the available literature were used for training and testing the ANN models. Furthermore, unsaturated triaxial tests were carried out under drained condition on compacted specimens. ANN models were validated by a part of data sets collected from the literature and data obtained from the current study, which were not included in the training phase. The analyses showed that the results obtained from ANN models are in satisfactory agreement with the experimental results and ANNs can be used as reliable tool for prediction of χ. Copyright © 2007 John Wiley & Sons, Ltd.     

Applicability of artificial neural networks for obtaining velocity models from synthetic seismic data

Seismic velocity analysis is a crucial part of seismic data processing and interpretation which has been practiced using different methods. In contrast to time consuming and complicated numerical methods, artificial neural networks (ANNs) are found to be of potential applicability. ANN ability to establish a relationship between an input and output space is considered to be appropriate for mapping seismic velocity corresponding to travel times picked from seismograms. Accordingly a preliminary attempt is made to evaluate the applicability of ANNs to determine velocity and dips of dipping layered earth models corresponding to travel time data. The study is based on synthetic data generated using inverse modeling approach for three earth models. The models include a three-layer structure with same dips and same directions, a three-layer model with different dips and same directions, as well as a two-layer model with different dips and directions. An ANN structure is designed in three layers, namely, input, output, and hidden ones. The training and testing process of the ANN is successfully accomplished using the synthetic data. The evaluation of the applicability of the trained ANN to unknown data sets indicates that the ANN can satisfactorily compute velocity and dips corresponding to travel times. The error intervals between the desired and calculated velocity and dips are shown to be acceptably small in all cases. The applicability of the trained ANN in extrapolating is also evaluated using a number of data outside of the range already known to ANN. The results indicate that the trained ANN acceptably approximates the velocity and dips. Furthermore, the trained ANN is also evaluated in terms of capability of handling deficiency in input data where acceptable results were also achieved in velocity and dip calculations. Generally, this study shows that velocity analysis using ANNs can promisingly tackle the challenge of retrieving an initial velocity model from the travel time hyperbolas of seismic data.     

人工神经网络在水文资料插补延长中的应用

水文资料的插补延长一直是水文计算中的一个难题.本文针对水文资料的插补和水文资料的延长问题进行系统的研究.插补水文资料时,采用人工神经网络双向时间序列插补模型,打破了传统的单向时间序列识别模式,应用缺测时段前后已知时段水文资料,插补出缺测水文资料;展延长系列水文资料则应用人工神经网络参证站模型,并应用流量较大年份的径流资料预测未知年份的径流资料,来进一步提高预测精度,并结合紫坪铺流量资料插补延长实例,检验模型的可行性.结果表明该模型对水文资料的插补或对未知年份的径流量都能够进行较好的预测.     

Neural network prediction of the reliability of heterogeneous cohesive slopes

The reliability of heterogeneous slopes can be evaluated using a wide range of available probabilistic methods. One of these methods is the random finite element method (RFEM), which combines random field theory with the non‐linear elasto‐plastic finite element slope stability analysis method. The RFEM computes the probability of failure of a slope using the Monte Carlo simulation process. The major drawback of this approach is the intensive computational time required, mainly due to the finite element analysis and the Monte Carlo simulation process. Therefore, a simplified model or solution, which can bypass the computationally intensive and time‐consuming numerical analyses, is desirable. The present study investigates the feasibility of using artificial neural networks (ANNs) to develop such a simplified model. ANNs are well known for their strong capability in mapping the input and output relationship of complex non‐linear systems. The RFEM is used to generate possible solutions and to establish a large database that is used to develop and verify the ANN model. In this paper, multi‐layer perceptrons, which are trained with the back‐propagation algorithm, are used. The results of various performance measures indicate that the developed ANN model has a high degree of accuracy in predicting the reliability of heterogeneous slopes. The developed ANN model is then transformed into relatively simple formulae for direct application in practice. Copyright © 2016 John Wiley & Sons, Ltd.     

Use of interactive multisensor snow and ice mapping system snow cover maps (IMS) and artificial neural networks for simulating river discharges in Eastern Turkey

Basins located in Eastern Turkey are largely fed by snowmelt runoff during spring and early summer seasons. This study investigates the efficiency of artificial neural networks (ANNs) in snowmelt runoff generation. Although ANNs have been used for streamflow simulating/forecasting in the last two decades, using satellite-based snow-covered area (SCA) maps and meteorological observations as inputs to ANN provides a novel basis for estimating streamflow. The proposed methodology is implemented over Upper Euphrates River Basin in Eastern Turkey. SCA data was acquired from Interactive Multisensor Snow and Ice Mapping System (IMS) for an 8-year period from February 2004 to September 2011. Meteorological observations including daily cumulative precipitation and daily average air temperatures were obtained from Turkish State Meteorological Services. The simulation results are promising with coefficient of correlation varying from 0.67 to 0.98 among proposed models. Past days discharge was found to substantially improve the forecast accuracy. The paper presents the expected basin discharge for 2011 water year based on meteorological observations and SCA input.     

Contribution des réseaux de neurones artificiels (RNA) à la caractérisation des pollutions de sol. Exemples des pollutions en hydrocarbures aromatiques polycycliques (HAP)Artificial Neural Networks (ANNs) characterisation of soil pollution: the Polycyclic Aromatic Hydrocarbons (PAHs) case study

We develop the ANNs (Artificial Neural Networks) method to explore contaminant concentration profiles observed in soils of polluted sites. ANNs are particularly efficient in simultaneous analysis of numerous parameters and in identification of complex relations involving field data. Applying the ANN models on a PAH (Polycyclic Aromatic Hydrocarbon) database, we extracted the most characteristic components of known contaminations and applied it to identify the source type of similar polluted sites. The performed tests prove the generalisation capability of the selected ANN model. To cite this article: A. Dan et al., C. R. Geoscience 334 (2002) 957–965.     

三种基于神经网络的洪水实时预报方案的比较研究

在总结神经网络应用的基础上,归纳了3种基于神经网络的洪水实时预报方案。第一种是神经网络水文模型的模拟模式加模拟误差的自回归校正模型,第二种是权重系数固定的神经网络实时预报方案,第三种是权重系数自动更新的神经网络实时预报方案。采用10个不同流域的日流量资料对这3种方案进行率定和校核。比较这3种方案的实时预报精度。结果发现,第三种方案不仅预报精度要高于其他两种方案,而且比第一种方案少了一个自回归校正模型,结构简洁。本文建议采用第三种洪水实时预报方案。     

An application of artificial intelligence for rainfall-runoff modeling

This study proposes an application of two techniques of artificial intelligence (AI) for rainfall-runoff modeling: the artificial neural networks (ANN) and the evolutionary computation (EC). Two different ANN techniques, the feed forward back propagation (FFBP) and generalized regression neural network (GRNN) methods are compared with one EC method, Gene Expression Programming (GEP) which is a new evolutionary algorithm that evolves computer programs. The daily hydrometeorological data of three rainfall stations and one streamflow station for Juniata River Basin in Pennsylvania state of USA are taken into consideration in the model development. Statistical parameters such as average, standard deviation, coefficient of variation, skewness, minimum and maximum values, as well as criteria such as mean square error (MSE) and determination coefficient (R ²) are used to measure the performance of the models. The results indicate that the proposed genetic programming (GP) formulation performs quite well compared to results obtained by ANNs and is quite practical for use. It is concluded from the results that GEP can be proposed as an alternative to ANN models.     

Use of evolutionary computing for modelling some complex problems in geotechnical engineering

In this paper, the feasibility of using evolutionary computing for solving some complex problems in geotechnical engineering is investigated. The paper presents a relatively new technique, i.e. evolutionary polynomial regression (EPR), for modelling three practical applications in geotechnical engineering including the settlement of shallow foundations on cohesionless soils, pullout capacity of small ground anchors and ultimate bearing capacity of pile foundations. The prediction results from the proposed EPR models are compared with those obtained from artificial neural network (ANN) models previously developed by the author, as well as some of the most commonly available methods. The results indicate that the proposed EPR models agree well with (or better than) the ANN models and significantly outperform the other existing methods. The advantage of EPR technique over ANNs is that EPR generates transparent and well-structured models in the form of simple and easy-to-use hand calculation formulae that can be readily used by practising engineers.