生物膜滴滤塔液体分布器实验研究

以有机废气处理生物膜滴滤塔为背景，分别设计了盘式和槽式两种液体分布器，通过实验研究了液体喷淋密度、喷淋区域等对液体分布器分布性能的影响，并对两种分布器的液体分配特性进行了比较，盘式液体分布器的液体分配性能总体上优于槽式液体分布器。随后针对盘式液体研究了安装水平度、进液方式对液体分布性能的影响。     

生物滴滤塔处理恶臭气体工艺优化试验

采用生物滴滤塔进行了恶臭气体恶臭成分脱除试验,探讨了填料层高度、营养液喷淋量和停留时间对恶臭成分的脱除影响。结果表明,优化工艺条件为:填料层高度500mm,喷淋量为20L/h,停留时间40s。并在此条件下进行了连续运行试验,取得了良好效果。     

8．生物膜处理过程中有机过氧化物的同时催化去毒和生物学降解

有氧化作用的酚在合成过程产生的废水,含有大量有机过氧化物,特别是枯烯化过氧氢(CHD)。由于CHD是硝化过程的抑制物,它必须先被降解然后才可排放到有硝化功能的下水道污水厂。     

基于BP神经网络与遗传算法的高压共轨柴油机喷油器结构参数优化研究

利用AVL-FIRE软件对TBD234高压共轨柴油机燃烧过程进行数值模拟,采用L16（54）正交试验作为BP神经网络的训练样本,建立喷油器主要结构参数与柴油机的燃油消耗率、NOx排放、SOOT排放之间的非线性映射关系,以燃油消耗率为优化目标,同时保持较低的NOx和SOOT排放水平,结合遗传算法进行寻优计算,获得了喷孔直径、喷孔个数、喷射夹角和喷油提前角4个参数的最优组合。     

GA Elman多元变量需水预测模型及其应用

针对传统静态前馈神经网络动态性能差、预测精度不高等问题,以上海市需水预测为例,提出一种基于遗传算法(GA)优化Elman神经网络连接权值的GA-Elman模型,并与GA-BP、Elman、BP需水预测模型做了对比。结果表明,GA-Elman需水预测模型行之有效,预测平均相对误差和最大相对误差分别仅为2.764%和6.578%,优于其他预测模型,具有较好的预测精度和泛化能力。     

基于KG-BP神经网络在秦淮河洪水水位预测中的应用

为了提高BP神经网络模型的预测精度,提出了一种基于KNN算法及GA算法优化的BP神经网络的水位预测方法(KG-BP),即通过KNN邻近算法从全样本数据中剔除与待测点相关度较低的样本集,并允许保留K个"优质"训练数据集;将筛选出的"优质"训练数据集代入GA算法中实现初始权阈值的优化;再将"优质"的样本和初始权阈值代入BP模型中进行训练。将该预测方法应用于东山站水位实际预测中,并与BP模型、GA-BP模型的预测结果进行对比分析,验证了KG-BP模型具有较高的预测精度。     

ANN modeling of compact heat exchangers

This paper focuses on the heat transfer analysis of compact heat exchangers through artificial neural network (ANN). The ANN analysis includes heat transfer coefficient, pressure drop and Nusselt number in the compact heat exchangers by using available experimental results in a case study. In this study, data sets are established in 15 different test channel configurations. A feed‐forward back‐propagation algorithm is used in the learning process and testing the network. The learning process is applied to correlate the heat transfer analysis for different ratios of rib spacing and height, various Reynolds numbers, different inlet–outlet temperatures, heat transfer areas and hydraulic diameters. Various hidden numbers of the network are trained for the best prediction of the heat transfer analysis. Heat transfer coefficient, pressure drop and Nusselt number values are predicted by the network algorithm. The results are then compared with the experimental results of the case. The trained ANN results perform well in predicting the heat transfer coefficient, pressure drop and Nusselt number with an average absolute mean relative error of less than 6% compared with the experimental results for staggered cylindrical ribbed and staggered triangular ribbed of test channels in the case study. The ANN approach is found to be a suitable method for heat transfer analysis in compact heat exchangers. Copyright © 2007 John Wiley & Sons, Ltd.     

基于BP神经网络的工业锅炉房负荷预测

针对工业锅炉房日负荷变化的特点,采用BP人工神经网络模型对热负荷进行预测。在建立模型时,考虑不同小时的热负荷差异,采用24个单输出的BP网络来分别预测每天24h负荷值;利用MATLAB神经网络工具箱NNT(Neural Network Toolbox)分别实现对24个BP网络预测模型的构建及算法改进;最后,应用一个实例对建立的预测模型和实现方法进行了仿真分析,结果证明,该负荷预测模型网络结构小、收敛速度快、预测精度高、具有较高的实用价值。     

Design optimization of ejectors using ANN and GA

Ejectors are devices that are based on the principle of momentum transfer. A primary fluid passes through a nozzle that is usually of converging–diverging cross-section so that the flow reaches supersonic velocity at the exit. Consequently, a low-pressure region is created just outside the nozzle exit. This pressure gradient draws out the secondary fluid, into the ejector through the annular space—a phenomenon known as entrainment. This paper attempts to design and optimize an ejector with 1,1-dichloro-1-fluoroethane as the working fluid. The governing equations that accurately predict the behavior of the working fluid, are solved using the finite volume method after the discretization of the flow domain, using ANSYS Fluent. A database is created over 1008 similar computational fluid dynamics simulations by recording the input parameter values and the corresponding output parameter values. It is then used to define a function that can precisely predict the output for an unknown set of input parameters. This is achieved through the implementation of artificial neural networks—a surrogate modeling technique. The accuracy of the model is determined from the coefficient of correlation. The objective function thus obtained is optimized with the help of a genetic algorithm (GA)—a nature-inspired optimization technique. The optimal design of the ejector for a set of operating conditions is obtained as the output of the GA.     

Modeling biohydrogen production using different data driven approaches

Three modeling techniques namely multilayer perceptron artificial neural network (MLPANN), microbial kinetic with Levenberg-Marquardt algorithm (MKLMA) developed from microbial growth, and the response surface methodology (RSM) were used to investigate the biohydrogen (BioH₂) process. The MLPANN and MKLMA were used to model the kinetics of major metabolites during the dark fermentation (DF). The MLPANN and RSM were deployed to model the electron-equivalent balance (EEB) from the cumulative data (after 24 h fermentation) during the DF. With the additional experimental results of kinetic data (20 × 10) and cumulative data (18 × 9), the uncertainties of different models were compared. A new effective strategy for modeling the complex BioH₂ process during the DF is proposed: MLPANN and MKLMA are used for the investigation of kinetics of the major metabolites from the limited numbers of experimental data set, and the MLPANN and RSM are used for statistical analysis of the investigated operational parameters upon the major metabolites through EEB perspective. The proposed strategy is a useful and practical paradigm in modeling and optimizing the BioH₂ production during the dark fermentation.     

基于叶片弯掠技术的优化设计

在三维粘性流场的数值计算程序平台上,利用BP神经网络和遗传算法,通过叶片弯掠技术对一轴流风机的转子叶片的周向弯曲角度进行寻优,以使风扇的气动性能进一步提高。通过对比优化前、后的叶轮发现,优化之后的叶片呈现明显的周向前弯曲特征。测试结果显示,其全压和气动效率分别提高了3.56%和1.27%,失速裕度大幅度拓宽36%以上,上、下端部的损失进一步降低。     

BP人工神经网络在钢铁生产过程信息流分析中的应用

钢铁企业生产过程的信息流蕴藏着丰富的生产工艺规律。BP人工神经网络广泛用于信息流分析中,将其概括为四个方面:过程状态参数预测、产品性能参数预测、能耗信息预测和原材料参数优化。分别介绍相关研究和应用工作,指出应用流程中存在的不足,并给出规范流程。最后给出某大型钢铁企业新区焦炉单元的日能耗预测实例,验证了BP人工神经网络在钢铁生产过程信息流分析中的作用和应用流程的有效性。