陕西省人工神经元网络降水年,季度预报系统

利用Ｂ－Ｐ人工神经元网络进行了陕西省年度,季度降水预报试验,提出了利用０－１模型解决多等级预报问题的方法,并建立了年度,季度等级预报模型,经过试验,表明该方法预报效果良好,最后对模式在应用中的一些问题及目前其它预报模型的差异等进行了讨论。     

A systematic approach to the input determination for neural network rainfall–runoff models

Input determination has a great influence on the performance of artificial neural network (ANN) rainfall–runoff models. To improve the performance of ANN models, a systematic approach to the input determination for ANN models is proposed. In the proposed approach, the irrelevant inputs are removed. Then an adequate ANN model, which only includes highly relevant inputs, is constructed. Unlike the trial‐and‐error procedure, the proposed approach is more systematic and avoids unnecessary trials. To demonstrate the effectiveness of the proposed approach, an application to actual typhoon events is presented. The results show that the proposed ANN model, which is constructed by the proposed approach, has advantages over those obtained by the trial‐and‐error procedure. The proposed ANN model has a simpler architecture, needs less training time, and performs better. The proposed ANN model is recommended as an alternative to existing rainfall–runoff ANN models. Copyright © 2007 John Wiley & Sons, Ltd.     

Prediction of the sawing quality of Marmarit stones using the capability of artificial neural network

The sawing rate is one of the most significant and effective parameters in extracting building stones via diamond wire sawing. This parameter designates the capability of diamond wire sawing for sawing different stones; in addition, the parameter gives rise to economical considerations for quarry designers. In this study, the existent relations between stone geotechnical parameters and the sawing rate of stones via diamond wire sawing were analyzed using regression and correlation coefficient as well as the collected data from Marmarit stone quarries. Moreover, we estimated the sawing rate of Marmarit using the dimensional stone rock mass rating (DSRMR); upon comparison of the data obtained from DSRMR our pre‐collected data on quarries, we did not gain satisfactory results from DSRMR, hence we used artificial neural network (ANN). The results showed that the percentage of Silica, the coefficient of water absorption, the uniaxial compressive strength (UCS), and abrasive hardness are the proper parameters for creating the ANN. Discontinuities have the least effects possible on diamond wire sawing. Having given the training possibility of the ANN, and its ability to evaluate relations among input parameters, the ANN, which was being trained with Marmarit's traits, was an accurate network for estimating diamond wire sawing in Marmarit quarries, although it could not generalize this network for other stones such as Chini and Crystal. Copyright © 2011 John Wiley & Sons, Ltd.     

Application of integrated back‐propagation network and self organizing map for flood forecasting

Much of the nonlinearity and uncertainty regarding the flood process is because hydrologic data required for estimation are often tremendously difficult to obtain. This study employed a back‐propagation network (BPN) as the main structure in flood forecasting to learn and to demonstrate the sophisticated nonlinear mapping relationship. However, a deterministic BPN model implies high uncertainty and poor consistency for verification work even when the learning performance is satisfactory for flood forecasting. Therefore, a novel procedure was proposed in this investigation which integrates linear transfer function (LTF) and self‐organizing map (SOM) to efficiently determine the intervals of weights and biases of a flood forecasting neural network to avoid the above problems. A SOM network with classification ability was applied to the solutions and parameters of the BPN model in the learning stage, to classify the network parameter rules and to obtain the winning parameters. The outcomes from the previous stage were then used as the ranges of the parameters in the recall stage. Finally, a case study was carried out in Wu‐Shi basin to demonstrate the effectiveness of the proposal. Copyright © 2009 John Wiley & Sons, Ltd.     

基于主成分分析的库存管理神经网络模型研究

从影响合理库存的诸多因素中,利用数理统计的思想,找出若干主要指标,通过建立神经网络模型,进行模拟仿真,寻求一种解决问题的有效方法,把库存调整到理想的状态。     

Prediction of uniaxial compression PFC3D model micro‐properties using artificial neural networks

Artificial neural networks are used to predict the micro‐properties of particle flow code in three dimensions (PFC3D) models needed to reproduce macro‐properties of cylindrical rock samples in uniaxial compression tests. Data for the training and verification of the networks were obtained by running a large number of PFC3D models and observing the resulting macro‐properties. Four artificial networks based on two different architectures were used. The networks used different numbers of input parameters to predict the micro‐properties. Multi‐layer perceptron networks using Young's modulus, Poisson's ratio, uniaxial compressive strength, model particle resolution and the maximum‐to‐minimum particle ratio showed excellent performance in both training and verification. Adding one more variable—namely, minimum particle radius—showed degrading performance. Copyright © 2009 John Wiley & Sons, Ltd.     

High chloride concentrations in the soil and groundwater under an oak hedge in the West of France: an indicator of evapotranspiration and water movement

Chloride is a major anion in soil water and its concentration rises essentially as a function of evapotranspiration. Compared to herbaceous vegetation, high transpiration rates are measured for isolated trees, shelterbelts or hedgerows. This article deals with the influence of a tree hedge on the soil and groundwater Cl^? concentrations and the possibility of using Cl^? as an indicator of transpiration and water movements near the tree rows. Cl^? concentrations were measured over 1 year at different depths in the unsaturated zone and in the groundwater along a transect intersecting a bottomland oak hedge. We observed a strong spatial heterogeneity of Cl^? concentrations, with very high values up to 2 g l^?1 in the unsaturated zone and 1·2 g l^?1 in the upper part of the groundwater. This contrasts with the low and homogeneous concentrations (60–70 mg l^?1) in the deeper part of the groundwater. Cl^? accumulation in the unsaturated zone at the end of the vegetation season allows us to identify the active root zone extension of trees. In winter, upslope of the tree row, downwards leaching partly renews the soil solution in the root zone, while the slow water movement under the trees or farther downslope results in Cl^? accumulation and leads to a salinization of the soil and groundwater. This salinization is of the same order as experimental conditions produce negative effects on oak seedlings. The measurement of Cl^? concentrations in the unsaturated zone under tree rows at the end of the vegetation season would indicate whether certain topographic, pedological or climatic conditions are likely to favour a strong salinization of the soil, as observed in the present study. Copyright © 2009 John Wiley & Sons, Ltd.     

轨道扣件病害自动化检测研究及应用

传统扣件检查基本采用人工检查方式,不仅工作效率低、劳动强度大,而且人为干扰因素多、检查采样率低。针对以上问题,本文提出了一种基于线结构光传感器的轨道扣件损伤和松动检测方法,并开发了轨道扣件智能监测系统以实现扣件病害自动检测。最终将研究成果应用于徐州市某地铁区间轨道扣件检测,验证了该方法的可行性和准确率,为地铁轨道扣件检查提供了新方法。     

基于图分割的可变比例尺地图分幅回溯算法

总结了地图分幅需遵循的原则,并针对地图集中可变比例尺的分幅,将其定义为基于约束条件的图分割问题,用最小生成树(minimum spanning tree,MST)将制图区域关联起来,基于回溯算法对MST裁剪实现地图集的分幅。实验结果表明,所提出的方法能较好顾及地图集分幅的相关原则,满足地图集制作的要求。同时,利用该方法设计的地图集分幅工具已成功应用于《武汉市汉阳地区地名图集》等的制作,有效提高了地图设计人员的工作效率。     

低温雨雪过程的粒子群-神经网络预报模型

利用逐日气温和降水量数据、NCEP/NCAR再分析资料以及预报场资料,通过分析提取我国南方区域持续性低温雨雪过程及其预报因子,使用粒子群-神经网络方法建立非线性的统计集合预报模型 (PSONN-EPM),对我国南方区域持续性低温雨雪过程进行预报试验。结果表明:以过程的冷湿程度及影响范围为标准,将低温雨雪过程分为一般过程和严重过程,并建立不同的预报模型效果较好。通过10 d独立样本预报试验看,基于粒子群-神经网络方法建立的集合预报模型比基于逐步回归方法建立的预报模型的预报平均相对误差小,对严重过程预报能力高于对一般过程预报,且这种非线性统计集合建模方法在建模过程中不需要调整神经网络参数,在实际预报业务中值得尝试。