Use of Radial Basis Function Type Artificial Neural Networks for Runoff Simulation

In this paper, the applicability of the radial basis function (RBF) type artificial neural networks (ANNs) approach for modeling a hydrologic system is investigated. The method differs from the more widely used multilayer perceptron (MLP) approach in that the nonlinearity of the model is embedded only in the hidden layer of the network. Search for optimal model parameters is carried out in two steps, each of which can be made to be more efficient and much faster than in MLP. This approach is applied to simulate runoff discharges in a small catchment. The results show that the models based on RBF networks can predict runoff with accuracy comparable with that with the MLP approach. An added advantage of RBF network-based models is that they can be developed with relative ease and with much less time compared with their MLP counterparts.     

基于RBF神经网络的边坡稳定性预测

RBF神经网络具有极强的非线性映射能力,精度高。本文基于RBF神经网络原理,采用自组织选取中心法,建立基于RBF神经网络的边坡稳定性预测模型,并选取大量边坡工程数据作为学习训练和预测样本,利用该模型进行学习和预测。研究结果表明,在处理边坡稳定性预测问题中,该方法具有很好的适应性和较高的精度。     

Determination of the optimal parameters in regression models for the prediction of chlorophyll-a: A case study of the Yeongsan Reservoir, Korea

Statistical regression models involve linear equations, which often lead to significant prediction errors due to poor statistical stability and accuracy. This concern arises from multicollinearity in the models, which may drastically affect model performance in terms of a trade-off scenario for effective water resource management logistics. In this paper, we propose a new methodology for improving the statistical stability and accuracy of regression models, and then show how to cope with pitfalls in the models and determine optimal parameters with a decreased number of predictive variables. Here, a comparison of the predictive performance was made using four types of multiple linear regression (MLR) and principal component regression (PCR) models in the prediction of chlorophyll-a (chl-a) concentration in the Yeongsan (YS) Reservoir, Korea, an estuarine reservoir that historically suffers from high levels of nutrient input. During a 3-year water quality monitoring period, results showed that PCRs could be a compact solution for improving the accuracy of the models, as in each case MLR could not accurately produce reliable predictions due to a persistent collinearity problem. Furthermore, based on R² (goodness of fit) and F-overall number (confidence of regression), and the number of explanatory variables (R-F-N) curve, it was revealed that PCR-F(7) was the best model among the four regression models in predicting chl-a, having the fewest explanatory variables (seven) and the lowest uncertainty. Seven PCs were identified as significant variables, related to eight water quality parameters: pH, 5-day biochemical oxygen demand, total coliform, fecal indicator bacteria, chemical oxygen demand, ammonia-nitrogen, total nitrogen, and dissolved oxygen. Overall, the results not only demonstrated that the models employed successfully simulated chl-a in a reservoir in both the test and validation periods, but also suggested that the optimal parameters should cautiously be considered in the design of regression models.     

序贯高斯模拟在围岩质量预测中的应用

围岩质量的准确划分对隧道工程的建设成本控制和施工安全至关重要。根据局部范围内的围岩信息估计整个隧道址区围岩质量分布时,常规的插值算法(反距离加权插值法、平均法等)未能充分考虑变量空间分布的结构性,因此预测精度较低。为了更好地考虑地质信息间的空间结构性,本文结合RMR14法对围岩质量进行定量评价,将序贯高斯模拟方法应用到掌子面前方围岩质量的预测。利用钻孔、物探、地质素描等采集的地质信息,通过变差函数的模拟对其空间自相关性进行定量描述。采用序贯高斯模拟方法,以RMR14法各评分指标为研究对象分别进行变量估计,进而对未开挖掌子面围岩情况进行定量评估。以试刀山隧道工程为例对该方法进行验证,预测结果保持了近70%的预测精度。研究结果表明:基于指标的序贯高斯模拟方法在RMR值预测方面有良好的表现,同时能反映更多的地质信息;此外,序贯高斯模拟方法能够很好地反应空间中RMR值的细微变化,可以克服克里金方法的“平滑效应”;具有一定的工程应用推广价值。     

应用实用动态组合模型预测城市日用水量

将时间序列中的日用水量历史数据引入以温度等作变量的回归分析模型，建立了日用水量非线性回归组合预测模型，同时为进一步提高预测精度，用4阶自回归模型对回归残差序列进行时间序列分析，建立了日用水量预测实用动态组合模型。以华北某市日用水量的实测数据对其进行检验，结果表明该模型具有较高的预测精度。     

Development of a neural-based forecasting tool to classify recreational water quality using fecal indicator organisms

Users of recreational waters may be exposed to elevated pathogen levels through various point/non-point sources. Typical daily notifications rely on microbial analysis of indicator organisms (e.g., Escherichia coli) that require 18, or more, hours to provide an adequate response. Modeling approaches, such as multivariate linear regression (MLR) and artificial neural networks (ANN), have been utilized to provide quick predictions of microbial concentrations for classification purposes, but generally suffer from high false negative rates. This study introduces the use of learning vector quantization (LVQ) - a direct classification approach - for comparison with MLR and ANN approaches and integrates input selection for model development with respect to primary and secondary water quality standards within the Charles River Basin (Massachusetts, USA) using meteorologic, hydrologic, and microbial explanatory variables. Integrating input selection into model development showed that discharge variables were the most important explanatory variables while antecedent rainfall and time since previous events were also important. With respect to classification, all three models adequately represented the non-violated samples (>90%). The MLR approach had the highest false negative rates associated with classifying violated samples (41-62% vs 13-43% (ANN) and <16% (LVQ)) when using five or more explanatory variables. The ANN performance was more similar to LVQ when a larger number of explanatory variables were utilized, but the ANN performance degraded toward MLR performance as explanatory variables were removed. Overall, the use of LVQ as a direct classifier provided the best overall classification ability with respect to violated/non-violated samples for both standards.     

An artificial neural network-based mathematical model for the prediction of blast-induced ground vibrations

ABSTRACT

This paper presents an artificial neural network (ANN) based mathematical model for the prediction of blast-induced ground vibrations using the data obtained from the literature. A feed-forward back-propagation multi-layer perceptron (MLP) was adopted, and the Levenberg–Marquardt algorithm was used in training the network. The powder factor, the maximum charge per delay, and distance from blasting face to monitoring point are the input variables. The peak particle velocity (PPV) is the targeted output variable. The model was then formulated using the weights and biases output from the ANN simulation. Multilinear regression (MLR) analysis was also performed using the same number of datasets, as in the case of ANN. The quality of the proposed ANN-based model was also tested with another 14 datasets outside the one used in developing the models and compared with more classical models. The coefficient of the determination (R²) of the proposed ANN-based model was the highest.     

Chemometric modeling and prediction of trihalomethane formation in Barcelona's water works plant

Formation and occurrence of trihalomethanes (CHCl3, CHBr3, CHCl2Br, and CHBr2Cl) are investigated in water chlorination disinfection processes in the Barcelona's water works plant (WWP). Twenty-three WWP variables were measured and investigated for correlation with trihalomethane formation. Multivariate statistical methods including principal component analysis (PCA), multilinear regression (MLR), stepwise MLR (SWR), principal component regression (PCR) and partial least squares regression (PLSR) have been used and compared to model and predict the complex behavior observed for the measured trihalomethane concentrations. The results, obtained by PCA as well as the evaluation of the statistical significance of the coefficients in the linear regression vectors, revealed that the most important WWP variables for trihalomethane formation were: water temperature, total organic carbon, added chlorine concentrations, UV absorbance and turbidity at different sites of the WWP, as well as other variables like wells supply flow levels and carbon filters age. Overall, MLR and PLSR methods performed the best and gave similar good predictive properties. Best results were obtained for the total sum of trihalomethane concentrations, TTHM, with average modeling and prediction relative errors of 12% and 16%, respectively. Among the individual trihalomethanes, the concentrations of CHBr3 were the worst predicted ones with average modeling and prediction relative errors between 21-25% and 29-31%, respectively, followed by CHCl2Br with 23-26% and 25-27%. Better predictions were obtained for the concentrations of CHBr2Cl with relative modeling and prediction errors varying between 14-17% and 21%, and for the concentrations of CHCl3 with 21-24% and 23-25% errors, respectively.     

Improving prediction of soil liquefaction using hybrid optimization algorithms and a fuzzy support vector machine

The phenomenon of soil liquefaction is one of the most complex and interesting fields in geotechnical earthquakes that has drawn the attention of many researchers in recent years. The present study used hybrid particle swarm optimization and genetic algorithms with a fuzzy support vector machine (FSVM) as the classifier for the soil liquefaction prediction problem. Fuzzy logic is used to decrease the outlier sensitivity of the system by inferring the importance of each sample in the training phase to increase the ability of the classifier’s generalization. Using the appropriate combination of optimization algorithms, we can find the best parameters for the classifier during the training phase without the need for trial and error by the user due to the high accuracy of the classifier. The proposed approach was tested on 109 CPT-based field data from five major earthquakes between 1964 and 1983 recorded in Japan, China, the USA and Romania. Good results have been demonstrated for the proposed algorithm. Classification accuracy is 100% for the combination of the optimization algorithms with the FSVM classifier. The results show that the best kernel used in the training of the FSVM classifier is a radial basis function (RBF). According to the experimental results, the proposed algorithm can improve classification accuracy and that it is a feasible method for predicting soil liquefaction using the optimal parameters of the classifier with no user interface.

     

探析电动自行车火灾防治措施

现如今电动自行车成为了我们日常生活中一种必不可少的交通工具,在给我们带来了极大的便利、提供了更高的工作效率和更快的节奏的同时,由于其自身安全性能低、操作不方便等因素导致火灾事故频繁发生.文章借鉴了上海市2020年电动车自行车火灾案例和数据,探索分析电动车自行车火灾的危害和成因,提出了电动车自行车火灾的防治措施.     

Prediction of maximum surface settlement caused by earth pressure balance (EPB) shield tunneling with ANN methods

In order to determine the appropriate model for predicting the maximum surface settlement caused by EPB shield tunneling, three artificial neural network (ANN) methods, back-propagation (BP) neural network, the radial basis function (RBF) neural network, and the general regression neural network (GRNN), were employed and the results were compared. The nonlinear relationship between maximum ground surface settlements and geometry, geological conditions, and shield operation parameters were considered in the ANN models. A total number of 200 data sets obtained from the Changsha metro line 4 project were used to train and validate the ANN models. A modified index that defines the physical significance of the input parameters was proposed to quantify the geological parameters, which improves the prediction accuracy of ANN models. Based on the analysis, the GRNN model was found to outperform the BP and RBF neural networks in terms of accuracy and computational time. Analysis results also indicated that strong correlations were established between the predicted and measured settlements in GRNN model with MAE = 1.10, and RMSE = 1.35, respectively. Error analysis revealed that it is necessary to update datasets during EPB shield tunneling, though the database is huge.     

基于灰色马尔科夫链的建筑事故死亡人数预测研究

建筑安全事故统计数据少、波动大,预测建筑事故死亡人数的精度往往偏低。在传统的预测模型的基础上,取灰色预测模型所需样本少,马尔科夫链可以预测随机波动大的动态过程的优势,建立灰色马尔科夫链,可以增强预测的精度。将该方法以我国2003-2012年建筑事故死亡人数为基础,对2013-2014年我国建筑安全事故死亡人数进行预测,并提出适当的管理措施。     

Going Shopping

<正>Last Sunday,Mother asked me to go shopping for her.I took the list of the things she wanted and went to the shop by bike.I got all the things with no difficulty.After paying for them,I went out of the shop.When I got to the bike,I couldn’t find the key.It must have been left in the shop.I hurried back and asked the seller     

Predicting a water infrastructure leakage index via machine learning

In this study, the infrastructure leakage index (ILI) indicator that is preferred frequently by the water utilities with sufficient data to determine the performances of water distribution systems is modeled for the first time through the three different methodologies using different input data. In addition to the variables in the literature used for the classical ILI calculations, the age parameter is also included in the models. In the first step, the ILI values have been estimated via multiple linear regression (MLR) using water supply quantity, water accrual quantity, network length, service connection length, number of service connections, and pressure variables. Secondly, the Artificial Neural Network (ANN) approach has been applied with raw data to improve the ILI prediction performance. Finally, the data set has been standardized with the Z-Score method for increasing the learning power of the ANN models, and then the ANN predictions have been made by converting the data through the principal component analysis (PCA) method to minimize complexity by reducing the data set size. The model predictions have been evaluated via mean square error, G-value, mean absolute error, mean bias error, and adjusted-R² model performance scale. When the model outputs obtained at the end of the study are evaluated together with the classical ILI calculations, it is seen that the successful ILI predictions with three and four variables, including the age parameter, rather than six variables, have been made through the PC-ANN method. Water utilities with insufficient physical and operational data for ILI indicator calculation can make network performance evaluations by predicting the ILI through the models suggested in this study with high accuracy in a reliable way.     

概率积分法参数辨识的多尺度核偏最小二乘回归方法

 针对传统的偏最小二乘回归(PLS)、人工神经网络(ANN)、支持向量机(SVM)等非线性建模方法在概率积分法参数辨识中存在着预测效果差的不足,提出概率积分法参数辨识的多尺度核偏最小二乘回归(multi-scale KPLS)方法。首先,构建满足容许条件的多尺度高斯核函数;然后,对学习样本进行模糊聚类,以最优分类个数作为多尺度高斯核函数的尺度个数,并采用10次10折交叉验证按照网格搜索方法确定核函数的宽度;最后,详细论述multi-scale KPLS的建模过程。通过实例将multi-scale KPLS的预测结果与3种传统的PLS方法、径向基神经网络(RBF-NN)和SVM模型进行对比分析。结果表明：multi-scale KPLS顾及建模样本的多尺度特性,其预测精度明显高于其他预测模型;multi-scale KPLS有效地克服了各影响因素之间的多重共线性对预测结果的不利影响,具有较强的稳健性;multi-scale KPLS适用于多个因变量对多个自变量的概率积分法参数辨识问题,其建模参数均可自适应确定,在建模效率上优于RBF-NN和SVM。     

火电厂消防设计中冷凝器污垢累积规律的神经网络预测模型

为了防止火电厂锅炉消防设计中冷凝器因结垢而引起锅炉的火灾和爆炸事故,需要对冷凝器污垢系数的发展规律进行预测。设计了一种结合K-均值算法和Chebyshev 神经网络的污垢系数预测模型,针对Chebyshev 神经网络的弊端,应用K-均值算法对其进行改进,将污垢系数随时间发展的曲线分为启动阶段、粘附阶段和老化阶段3 类。结果表明,改进Chebyshev 神经网络模型有效地预测了冷凝器污垢系数发展规律,得到的输出结果比渐进预测和幂率预测模型的预测结果更准确,该模型具有算法简单、收敛速度快的特点。     

CAST工艺的BP和RBF人工神经网络仿真模型

将误差反向传播前馈(BP)神经网络模型和径向基函数(RBF)神经网络模型应用到CAST工艺中,并采用多输入、双输出神经网络模拟处理过程中各变量之间的关系和预测出水水质.误差分析结果表明,训练阶段RBF神经网络模型的拟合精度比BP神经网络模型的高,但两者的预测精度相差不大;测试阶段BP神经网络模型和RBF神经网络模型预测出水COD的平均相对误差分别为6.35%、6.80%,预测出水TN的平均相对误差分别为7.19%、5.49%,均在8%以下,这说明两种神经网络模型均可用于模拟CAST污水处理工艺各变量之间的关系和预测出水水质,为污水厂的运行管理提供了理论依据.     

Road traffic accidents in Singapore expressway tunnels

In rapidly growing economies with limited land space, underground road tunnels are becoming more prevalent. Before the implementation of large-scale underground road systems, it is necessary to garner more knowledge on their implications and impacts. This study examined 608 road traffic accidents (RTAs) that occurred in the three Singapore expressway tunnels, over 2009–2011. Each road tunnel was divided into three zones and RTA characteristics were analysed for each zone. The analyses reveal that RTA rates are higher in the transition zones compared to the interior zones, being mostly attributed to multivehicle crashes. However, mean casualty per RTA was found to be higher in the interior zones. Upon disaggregation by travel direction, it was found that RTAs are more likely to occur when entering the tunnel than exiting. The implications of the findings are discussed.     

勘察质量对基础工程的影响及对策

文中指出当前对勘察工作管理不重视，导致勘察市场混乱，并例举由于勘察质量的粗糙，导致延误工期、浪费及安全事故等，并提出解决问题的办法。     

软土地区简支梁桥的桥台选择与施工

本文对珠江三角洲软土地区简支梁常出现的事故进行了分析 ,提出重视软土地基上的桥台选择与施工顺序的重要性 ,并通过实例分析和列图表进行归纳