Modeling of a sequencing batch reactor treating municipal wastewater using multi-layer perceptron and radial basis function artificial neural networks

A sequencing batch reactor was modeled using multi-layer perceptron and radial basis function artificial neural networks (MLPANN and RBFANN). Then, the effects of influent concentration (IC), filling time (FT), reaction time (RT), aeration intensity (AI), SRT and MLVSS concentration were examined on the effluent concentrations of TSS, TP, COD and NH₄⁺-N. The results showed that the optimal removal efficiencies would be obtained at FT of 1 h, RT of 6 h, aeration intensity of 0.88 m³/min and SRT of 30 days. In addition, COD and TSS removal efficiencies decreased and TP and NH₄⁺-N removal efficiencies did not change significantly with increases of influent concentration. The TSS, TP, COD and NH₄⁺-N removal efficiencies were 86%, 79%, 94% and 93%, respectively. The training procedures of all contaminants were highly collaborated for both RBFANN and MLPANN models. The results of training and testing data sets showed an almost perfect match between the experimental and the simulated effluent of TSS, TP, COD and NH₄⁺-N. The results indicated that with low experimental values of input data to train ANNs the MLPANN models compared to RBFANN models are more precise due to their higher coefficient of determination (R²) and lower root mean squared errors (RMSE) values.     

人工神经网络在预测深基坑周边地表沉降变形中的应用研究

深基坑开挖引起的周边地表变形预测是一个复杂非线性问题,引起地表沉降的影响因素很多,各因素之间呈高度的非线性关系。传统的基坑用边地表沉降变形预测方法存在着一定的局限性,其预测精度有待提高,而人工神经网络是一种多元非线性动力学系统,可以灵活方便地对多成因的复杂未知系统进行高度建模,实现全面考虑各种主要影响因素的深基坑周边地表沉降变形预测。本文介绍了误差反向传播(BP)网络模型的结构、学习过程及其算法的改进,径向基函数(RBF)网络模型的结构及其学习过程;分析了影响深基坑开挖周边土体沉降变形的主要影响因素;以25个基坑工程的地表沉降实测资料为训练样本,建立了11个输入影响因素的BP神经网络模型和RBF神经网络模型,通过对样本的学习训练过程及对5个检验样本的预测精度,说明了人工神经网络用于预测基坑周边地表沉降的可行性和准确性。     

Prenatal ultrasonographic diagnosis of radial-ray reduction malformations

Radial-ray reduction malformations (RRRMs) may occur isolated or in association with other anomalies. The data of seven fetuses born with RRRMs were collected. Six fetuses had associated lethal abnormalities of the central nervous system, urogenital system, and/or heart, detected by ultrasound. In five cases, it was possible to establish the precise diagnosis, enabling an informed prognosis and subsequent genetic counselling. The diagnoses were: Edwards syndrome (n=3), VACTERL association (n=1), and Poland-Moebius-like complex (n= 1). In two cases, a complete diagnosis was not possible because of inadequate evaluation of these fetuses before and/or after birth. A proposal is given for the diagnostic approach for infants with RRRMs detected in the antenatal period by means of ultrasonography.     

基于RBF和PSO的双喉道气动矢量喷管优化设计

本文探索了一种能多变量综合优化的方法,即对喷管进行参数化设计后,用均匀试验设计(UED)将试验样本均匀散布在设计区间内,求出各性能参数后,利用径向基神经网络(RBF)对试验样本进行拟合,再用粒子群算法(PSO)对训练好的神经网络进行寻优,找出了更好的双喉道气动矢量喷管设计参数组合。数值模拟结果显示,优化后的双喉道气动矢量喷管的矢量角有了明显提高。试验表明这种优化方法具有很好的优化能力,可以用来对喷管几何外形进行参数优化。      

基于多元统计分析和RBFNNs的水质评价方法

提出了一种基于多元统计分析和RBFNNs的水质评价方法,其可适用于大尺度、多断面、长时间的水质评价工作,旨在补充以往相关研究工作.其主要程序为:利用方差分析对各断面多年水质监测样本进行时间与空间尺度上的显著差异性分析,识别出具有显著差异的样本,然后通过层次聚类分析把上述样本进行聚类分组,最后应用径向基神经网络对各组样本进行水质评价,并把此评价结果再分解到各断面各时段,此方法的特点为在不损失信息的前提下能大大减轻水质评价工作量,且客观可信、分辨率高,并能综合反映总体与个别特征.以辽宁省太子河为例,通过方差分析将2001～2003年6个断面的144个样本归纳为存在显著差异的74个样本,再通过聚类分析得到9个相似组,相应的水质评价结果为2.7394、4.4306、4.0994、2.777、4.2192、4.1214、4.4129、4.4259、4.4359,与传统单项指数法的结果基本一致.具体落实到各断面,结果表明,2001～2003 年间太子河大部分断面的水质处于Ⅳ类以上.     

水环境有机污染物预测的径向基函数网络模型

水环境中有机污染物的扩散迁移是一个由多种因素影响的复杂的非线性过程，根据河流有机污染物的浓度与其影响因素之间存在的映射关系，以实际监测数据为基础，建立了一个水环境有机污染物浓度预测的径向基函数网络模型，实例验证表明，该方法预测精度较高，具有一定的应用与推广价值。     

Effects of wastewater discharge on formation of Fe plaque on root surface and radial oxygen loss of mangrove roots

Effects of wastewater discharge on radial oxygen loss (ROL), formation of iron (Fe) plaque on root surface, and their correlations in Bruguiera gymnorrhiza (L.) Poir and Excoecaria agallocha L. were investigated. ROL along a lateral root increased more rapidly in control than that in strong wastewater (with pollutant concentrations ten times of that in municipal sewage, 10NW) treatment, but less Fe plaque was formed in control for both plants. For B. gymnorrhiza receiving 10NW, Fe plaque formation was more at basal and mature zones than at root tip, while opposite trend was shown in E. agallocha. At day 0, the correlation between ROL and Fe plaque was insignificant, but negative and positive correlations were found in 10NW and control, respectively, at day 105, suggesting that more ROL was induced leading to more Fe plaque. However, excess Fe plaque also served as a ‘barrier’ to prevent excessive ROL in 10NW plants.     

A high pressure liquid chromatographic method for the analysis of zearalenone in chicken blood

Abstract

A high pressure liquid chromatographic (HPLC) method is described to determine zearalenone in chicken blood. Samples are extracted with acetonitrile, followed by a hexane cleanup procedure and extracted further with ethyl acetate. The analysis of zearalenone is by HPLC using a reverse phase radial compression separation system, an ultraviolet absorbance detector and a mobile phase of acetonitrile‐water 60:40 (v/v). Recoveries of zearalenone in blood at levels of 50–200 ng/ml are in the range of 66.8–72.6%.