磺胺甲口恶唑氯化消毒副产物生成势及影响因素研究

研究了东太湖水源水中典型抗生素磺胺甲口恶唑(SMX)氯化消毒副产物(DBPs)生成势及影响因素。结果表明:SMX经氯化反应后可生成三卤甲烷、卤乙腈、卤乙酸、卤乙醛、卤代丙酮等多种DBPs,且加氯量、反应时间、反应温度、pH值等因素均会影响其DBPs生成势。当溶液中存在溴离子时,SMX氯化生成的三卤甲烷、卤乙酸的组分及生成量有较大变化,且随着溴离子浓度的增大,一些氯代消毒副产物(Cl-DBPs)会转化为具有更高毒性的溴代消毒副产物(Br-DBPs)。     

基于BP神经网络的江西省铁路货物周转量预测

采用灰色关联分析法筛选出江西省铁路货物周转量的主要影响因素,在此基础上建立了BP神经网络预测模型,并采用多元线性回归模型、二次指数平滑法、灰色GM(1,1)模型分别对江西省铁路货物周转量进行预测,再对结果进行比较和误差分析。研究表明,BP神经网络模型预测精度明显高于其它三个模型,平均误差为0.76%,可用于实际预测。     

供热系统换热站供热参数预测模型对比分析

通过相关性分析确定了集中供热系统换热站供/回水均温的影响因素,进一步依据最小二乘拟合计算得到预测模型中历史供热参数的最佳周期,同时结合室外空气温度和室内温度作为模型输入参数,运用Matlab仿真模拟软件建立广义回归神经网络(GRNN)、Elman递归神经网络(Elman)以及多元线性回归(MLR)预测模型,分别对未来18个时刻的供/回水均温进行仿真验证。分析预测结果发现,MLR预测模型的精度最高,GRNN预测模型精度略低于M LR,而Elman模型预测精度最低。     

几种集中供热负荷预测模型对比

为了精确地预测供热负荷,在预测模型中增加了室内温度影响因子,并采用多元线性回归(MLR)、BP神经网络和基于网格搜索优化支持向量机回归(GS-SVR)的方法,对未来7 d的供热负荷进行了预测。研究结果表明,GS-SVR预测模型的精度最高,其预测精度明显优于MLR和BP神经网络,可用于指导工程实践。     

高强混凝土强度预测的支持向量机模型及应用

高强混凝土的强度受多种因素的影响,其强度的预测是一个动态性的系统工程。采用支持向量机理论,建立了高强混凝土的强度预测的支持向量机预测模型。并将该模型计算结果与实测混凝土28 d抗压强度、BP网络计算的强度、RBF径向基函数神经网络计算的强度、线性回归模型计算的强度、非线性回归模型计算的强度进行比较。研究表明:预测结果与实测结果吻合较好,较线性回归和神经网络预测精度高,为高强混凝土的强度预测提供了一条新途径。     

均值GM（1,1）模型在变形预测中的应用

以变形监测实测20期高程数据为依据,选择前15期建立均值GM(1,1)模型,对后5期数据进行预测,并对建模拟合结果和预测结果进行分析,认为以均值GM(1,1)模型进行拟合预测精度满足要求。并且与以荷载和时间为影响因素建立的多元线性回归预测结果进行比较,相较于多元线性回归预测精度高。该研究对建筑物变形预测有一定的实际应用价值和参考意义。     

基于序列分解法的城市月需水量预测研究

为更好地满足用水需求,提出一种基于BP神经网络、非线性回归、自适应模糊推理系统(ANFIS)的月需水量组合预测模型。首先通过Daubechies小波将月需水量序列分解为趋势项、周期项、随机项,然后利用BP神经网络、非线性回归及ANFIS模型分别对各分解项进行曲线拟合,最后采用拟合的公式进行预测。针对该模型,采用C市2007年1月至2015年12月的数据进行训练,并应用2016年1至3月的数据进行测试。与单BP神经网络模型预测结果的对比表明,该模型对月需水量预测具有较高的精度。     

多重群体遗传规划在高性能混凝土强度预测中的应用

针对影响高性能混凝土强度的主要因素作为输入因子,28 d抗压强度作为输出变量,应用遗传规划理论(GP)建立了高性能混凝土强度预测的非线性显式数学解析式模型。为了更好地保持进化过程中的遗传多样性,提高求解此问题的效率,提出了多重群体遗传规划理论。通过实测数据进行验证,并分别与线性回归模型和神经网络模型相比较,结果表明,多重群体遗传规划(MGGP)模型具有更高的拟合精度和更好的预测效果,在高性能混凝土强度预测方面有很强的实用价值。     

高强混凝土强度预测人工智能方法及应用

高强混凝土的强度预测是一个动态性可变复杂问题,受各种因素的影响。采用多种智能方法,建立了高强混凝土的强度预测的遗传算法与神经网络的集成模型。并将该模型计算结果与实测混凝土28 d抗压强度,RBF径向基函数神经网络计算的强度,非线性回归模型计算的强度进行比较。研究表明:预测结果与实测结果吻合较好,较线性回归和神经网络预测精度高,为高强混凝土的强度预测提供了一条新方法。     

基于线性回归与神经网络的盈余管理研究

在以往对公司治理结构与盈余管理关系的研究中,学者们大多采用多元线性回归的方法,但多元线性回归只是一种描述数量间简单线性关系的方法,使用的前提是满足五条苛刻的假设,可能并不适合于某些实际经济问题的研究。人工神经网络(ANN)是一种非线性的数学计算模型,文章将人工神经网络模型引入上述问题的研究,并将多元线性回归与ANN两种模型的实证研究结果进行分析与对比,用以考察两种模型在盈余管理研究领域的有效性与预测力。     

饮用水氯消毒副产物安全控制的研究现状

叙述了饮用水处理过程中消毒副产物（DBPs）的形成机制和变化情况,总结了DBPs的诱发因子,探讨了DBPs安全控制的基本对策,同时为饮用水高效安全消毒方案的进一步探究提出了建议。     

济南市供水消毒副产物的变化研究

选取济南市主要的三个地表水厂为研究对象,分析了消毒副产物在管网中的变化规律,并提出了控制饮用水中消毒副产物的对策。研究结果表明,济南市饮用水中的消毒副产物主要是三卤甲烷,温度和余氯是管网中控制消毒副产物和TOC浓度的重要因素。     

Multiple linear regression,artificial neural network,and fuzzy logic prediction of 28 days compressive strength of concrete

Evaluating the in situ concrete compressive strength by means of cores cut from hardened concrete is acknowledged as the most ordinary method, however, it is very difficult to predict the compressive strength of concrete since it is affected by many factors such as different mix designs, methods of mixing, curing conditions, compaction, etc. In this paper, considering the experimental results, three different models of multiple linear regression model (MLR), artificial neural network (ANN), and adaptive neuro-fuzzy inference system (ANFIS) are established, trained, and tested within the Matlab programming environment for predicting the 28 days compressive strength of concrete with 173 different mix designs. Finally, these three models are compared with each other and resulted in the fact that ANN and ANFIS models enables us to reliably evaluate the compressive strength of concrete with different mix designs, however, multiple linear regression model is not feasible enough in this area because of nonlinear relationship between the concrete mix parameters. Finally, the sensitivity analysis (SA) for two different sets of parameters on the concrete compressive strength prediction are carried out.     

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.     

基于模拟退火的粒子群算法优化的二次回归在混凝土抗压强度预测中的应用

混凝土抗压强度与其影响因素之间存在着很强的非线性关系,精确预测混凝土抗压强度对提高工程质量和施工进度等具有重要意义。为了提高预测值的精确度,建立了二次回归预测模型,利用基于模拟退火的粒子群算法对模型系数进行了优化和求解。实例仿真表明这种经智能算法优化后的二次回归预测模型优于传统神经网络预测模型,预测精度得到了较大提高。     

大型血小板比率、尿微白蛋白与2型糖尿病并发缺血性脑血管病的关系

目的：研究大型血小板比率（P-LCR）、尿微白蛋白（MA）与2型糖尿病（T2DM）患者并发缺血性脑血管病（ICVD）的关系。方法选择83例 T2DM 并发缺血性脑血管病患者为观察组、94例单纯 T2DM 患者为对照组,对2组患者的年龄、性别、血压、血脂、尿酸、血糖、糖化血红蛋白、血小板参数及 MA 等相关因素进行分析比较,对影响 T2DM 患者并发 ICVD 相关因素采用逐步多因素 Logistic 回归分析,建立 Logistic 回归模型。用 ROC 曲线评价Logistic 回归预测模型 P1、P-LCR 联合 MA 预测模型 P2、P-LCR 的预测能力。结果2组 MPV、PDW 及 P-LCR值与 MA 阳性率比较差异均有统计学意义（P ＝0．00）。多因素 Logistic 回归分析显示年龄、P-LCR、MA、收缩压、糖化血红蛋白是 T2DM 患者并发 ICVD 的独立危险因子。Logistic 回归预测模型 P1、P-LCR 联合 MA 预测模型P2、P-LCR 各自 ROC 曲线下面积分别为0．868、0．779、0．704（P ＝0．00）。结论P-LCR、MA 与 T2DM 并发 ICVD有关,对 P-LCR、MA 联合监测及动态监测有助于 T2DM 并发 ICVD 的早期预测。     

溪洛渡水电站坝区初始地应力场反演分析研究

初始地应力是岩土工程设计与施工所要考虑的重要因素之一。由实测地应力资料反演初始地应力场的方法很多，且各有优势。根据溪洛渡水电站工程坝区地应力的实测资料，采用有限单元法，结合多元线性回归方法、神经网络方法和遗传算法，分别反演求得整个坝区的初始地应力场。比较发现3种方法反演计算的结果非常接近，且均能模拟实际地应力场的分布规律。进一步的分析结果表明，由于溪洛渡水电站工程坝区在天然情况下岩体的屈服范围很小，坝区初始地应力场的非线性特征不明显，故线性回归分析方法即可满足要求。同时，研究还表明，在结果均能满足要求的前提下，回归分析方法与神经网络方法和遗传算法相比具有更方便快捷、易于掌握、唯一解的优势。     

Electrochemical disinfection of biologically treated wastewater from small treatment systems by using boron-doped diamond (BDD) electrodes – Contribution for direct reuse of domestic wastewater

The aim of the study was to demonstrate the application potential of boron-doped diamond electrodes (BDD) in electrochemical disinfection of biologically treated sewage for direct recycling of domestic wastewater. Discontinuous bulk disinfection experiments with secondary effluents and model solutions were performed to investigate the influence of operating conditions and wastewater parameters on disinfection efficiency and formation of disinfection by-products (adsorbable organically bound halogens, AOX). The inactivation rate accelerates with increasing current density caused by a faster generation of electrochemical oxidants (ECO). It could be shown that the effect of OH radicals in case of the direct electrochemical disinfection of chloride-containing secondary effluents with BDD is negligible because of their fast reaction with typical radical scavengers. The dominating role of electrochemically generated free chlorine in the disinfection process could be explicitly verified. It could be also shown that the disinfection efficiency is strongly affected by the specific wastewater parameters temperature and pH. These effects can be explained by the behaviour of the reactive species. The migration-controlled generation of ECO can be accelerated under turbulent hydrodynamic conditions. The formation of disinfection by-products (AOX) correlates with the introduced electric charge Q applied per volume and is independent of the applied current density.     

基于LSTM多变种模型的岩爆微震参数预测研究

岩爆是深地工程和深部资源开采中必须要解决的核心问题之一。基于改进的LSTM神经网络,提出了用于时间序列预测的LSTM微震多参数预测模型,包括单变量时序预测模型和多元平行序列预测模型。并以峨汉高速大峡谷隧道微震监测数据对模型进行验证,同时与多项式回归方法结果进行对比分析。结果表明:单变量预测模型中堆叠式LSTM(S-LSTM)的预测精度最高;多变量预测模型中卷积LSTM(CNN-LSTM)对累积视体积和能量指数具有最好的预测效果,且余下几种LSTM模型仍可准确实现各参数演化趋势的预测,其精度均优于多项式回归分析方法。研究可为正确识别岩爆当前活动及未来状态的危险性提供理论支撑,为及时掌握岩爆未来活动状态提供重要依据。     

Peak shear strength prediction for discontinuities between two different rock types using a neural network approach

The peak shear strength of discontinuities between two different rock types is essential to evaluate the stability of a rock slope with interlayered rocks. However, current research has paid little attention to shear strength parameters of discontinuities with different joint wall compressive strength (DDJCS). In this paper, a neural network methodology was used to predict the peak shear strength of DDJCS considering the effect of joint wall strength combination, normal stress and joint roughness. The database was developed by laboratory direct shear tests on artificial joint specimens with seven different joint wall strength combinations, four designed joint surface topographies and six types of normal stresses. A part of the experimental data was used to train a back-propagation neural network model with a single-hidden layer. The remaining experimental data was used to validate the trained neural network model. The best geometry of the neural network model was determined by the trial-and-error method. For the same data, multivariate regression analysis was also conducted to predict the peak shear strength of DDJCS. Prediction precision of the neural network model and multivariate regression model was evaluated by comparing the predicted peak shear strength of DDJCS with experimental data. The results showed that the capability of the developed neural network model was strong and better than the multivariate regression model. Finally, the established neural network model was applied in the stability evaluation of a typical rock slope with DDJCS as the critical surface in the Badong formation of China.